…me prefix (#30116)

* fix(team): reserve team budget raises for proxy admins on /team/update (#30030)

The caller's PERSONAL max_budget was the wrong yardstick for /team/update: a
team's spend ceiling has nothing to do with the admin's own key budget. That
comparison was an unintended side effect of reusing _check_user_team_limits()
(which exists for the /team/new path) and broke the UI, which re-sends the
unchanged budget on every save.

New behavior on /team/update for standalone teams:
- A team admin (already authorized via _verify_team_access) may freely KEEP or
  LOWER the team budget, and change models/tpm/rpm, without being gated by their
  personal limits.
- GROWING a team's spend ceiling is a budget-authority action reserved for proxy
  admins -> 403 for team admins. "Growing" covers both raising max_budget above
  the team's current finite value and removing the cap entirely (max_budget=null,
  detected via model_fields_set so an explicit null is distinguished from an
  omitted field). For a team that currently has no cap, setting a finite value is
  a restriction and is allowed.
- Org-scoped teams remain governed by _check_org_team_limits() (capped by the
  org budget).

Also reverts the #29525 existing_team_max_budget workaround in
_check_user_team_limits() back to the create-only form; /team/new still enforces
the creator's personal caps.

docs(access_control): resolve the contradiction in the team-admin section —
team admins can keep/lower the budget and manage rate limits/models, but cannot
raise the team budget (proxy-admin only).

tests: unit + behavior coverage for raise-blocked, cap-removal-blocked (team
admin), raise/removal allowed (proxy admin), uncapped-team restriction allowed,
keep/lower/resend allowed, and unchanged create-path guards.

Co-authored-by: Cursor <[email protected]>

* test(ui): data-driven App Router migration E2E smoke (default + server-root-path) (#29974)

* test(ui): add a data-driven App Router migration E2E smoke

Add a growing Playwright smoke for migrated pages: for each segment it deep-links
to the path route, asserts the URL and that the dashboard shell rendered, then
clicks off to a legacy page and asserts navigation still works. Driven by
e2e_tests/fixtures/migratedPages.ts, so adding a page is one line.

Runs in two situations against the same proxy: the default mount (npm run
e2e:migration) and a non-root SERVER_ROOT_PATH mount (npm run e2e:migration:root).
globalSetup now logs in at `${SERVER_ROOT_PATH}/ui/login` so the admin storage
state is valid under a prefix. Seeded with api-reference; append the rest as their
migrations merge.

* test(ui): support headed slow-motion + watch pauses in the migration smoke

Honor SLOWMO in the server-root-path config (the default config already did),
and add an env-gated E2E_WATCH_MS pause so a headed run lingers on each state.
Both are no-ops by default, so CI behavior is unchanged.

* test(ui): make the migration smoke a sidebar-click user journey

Rework the smoke from deep-linking to a real navigation journey: start at the
landing page, click the migrated page in the sidebar (expanding submenus for
nested items), assert the path route rendered, reload it (the check a wrong
server_root_path breaks), bounce to a legacy page and back, and — once two pages
are migrated — navigate directly between two migrated pages. Verifies via URL +
shell render, driven by the same fixture list.

* test(ui): address review on the migration smoke

Escape ROOT and segment before interpolating them into RegExp URL matchers so a
future segment containing regex metacharacters can't silently widen the match.
Make the server-root-path config fail fast when SERVER_ROOT_PATH is unset instead
of silently re-running the default mount and passing without exercising the prefix.

* test(ui): drop unused watch helper and fix stale smoke README

* test(ui): run the migration smoke under a server root path in CI

* test(ui): harden + instrument the server-root-path proxy reboot in CI

* test(ui): run the server-root-path migration smoke as its own CI job

Replace the in-place proxy reboot in e2e_ui_testing with a dedicated
e2e_ui_testing_server_root_path job that boots the proxy once with
SERVER_ROOT_PATH=/litellm, matching how every other proxy variant in the
config gets its own job rather than killing and relaunching the live proxy.

The reboot was failing deterministically: after pkill -9 and relaunch the
prefixed proxy never came back up on :4000 (connection refused), so the smoke
never ran. The readiness step that was supposed to surface the cause could
never reach its boot-log tail because CircleCI runs steps under bash -eo
pipefail and the preceding `curl -sv ... | tail` aborted the step with curl's
exit 7. Booting the proxy as the job's own background step lets any boot crash
land in that step's log instead of being swallowed.

The default e2e_ui_testing job is unchanged aside from dropping the reboot,
prefixed-readiness, and prefixed-smoke steps; the migration smoke still runs at
the root mount there via the default Playwright config.

* fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through (#24232)

* fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through

* test: mock post_call_response_headers_hook in audio speech route tests

* chore(ui): remove dead App Router route stubs under (dashboard) (#30045)

models-and-endpoints, organizations, and virtual-keys each had a page.tsx
route under (dashboard)/ that is not in MIGRATED_PAGES, so the sidebar and
deep links never resolve to it and the route is unreachable. Each was a thin
wrapper that handed the shared view empty or no-op props (empty modelData with
a no-op setModelData, hardcoded empty organizations, no-op
setUserRole/setUserEmail), so reaching one would render a degraded page in any
case. The real wrapper belongs in the PR that flips each page into
MIGRATED_PAGES, written with eyes on it and a test

This continues the dead-scaffolding cleanup from #28891. The shared components
these wrappers rendered (ModelsAndEndpointsView, OrganizationFilters) stay,
since the legacy ?page= switch in app/page.tsx and src/components still import
them

* fix(ui/mcp): reset OAuth state on create-server modal close so a prior server's token no longer leaks into the next add-server session (#30000)

* fix(ui/mcp): reset OAuth hook state on modal close so a prior server's token no longer leaks into the next add-server session

* fix(ui/mcp): clear in-flight OAuth guard on reset and reset form/tools on modal close so nothing leaks on a parent-driven dismiss

* fix(mcp): allow team access-group grants in OAuth authorize/token access check (#30041)

* fix(mcp): honor team access-group grants in OAuth authorize/token access check

* test(mcp): mock build_effective_auth_contexts in non-admin authorize tests for isolation

* docs(security): require a reproduction video for vulnerability reports (#30048) (#30063)

With AI models capable of automated vulnerability discovery now publicly
available, we expect a large increase in report volume, much of it
unverified. Requiring a video of the exploit running against a live
instance raises the bar for submissions and keeps triage focused on
reproducible issues. Reports without a video will be closed and reopened
if one is added later.

Co-authored-by: stuxf <[email protected]>

* feat(ui): add admin flag to disable in-product UI nudges for everyone (#29796)

* feat(ui): add admin flag to disable in-product UI nudges for everyone

Admins can now suppress the survey and Claude Code feedback popups for
all users via a single disable_ui_nudges UI setting, instead of relying
on each user dismissing them individually.

* fix(ui): suppress nudges while ui settings are loading

Gate nudgesDisabled on the ui-settings loading state so an admin with
disable_ui_nudges on doesn't see the survey prompt flash, and the
getInProductNudgesCall fetch doesn't fire, on a cold page load before
the flag resolves. Falls back to showing nudges if the fetch errors.

* test(ui): wrap CreateKeyPage test in QueryClientProvider

page.tsx now calls useUISettings (react-query), which needs a
QueryClient that layout.tsx supplies in production but the test did
not. Add the provider and mock getUiSettings so the query resolves.

* chore(ui): remove dead dashboard files and unused dependencies (#30047)

* chore(ui): remove dead dashboard files and unused dependencies

knip flagged seven orphaned source/config files with no importers and
five declared dependencies that nothing in the tree uses. Removing them
shrinks the dashboard bundle's source surface and keeps the manifest
honest; vite stays installed transitively via vitest, so test tooling is
unaffected.

* fix(ci): restore serverRootPath.config.ts referenced by SERVER_ROOT_PATH workflow

The dead-code sweep removed e2e_tests/serverRootPath.config.ts, but its spec
(tests/login/serverRootPathRedirect.spec.ts) and the test_server_root_path.yml
workflow step still depend on it, so the redirect e2e job failed to load a
config that no longer existed.

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593) (#30009)

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593)

After replace_model_in_jsonl, body.model is a stripped provider id. Reverse-mapping it via resolve_model_name_from_model_id is first-match on model_list and caused false 403s when multiple deployments share the same stripped name. Use target_model_names from the unified file id instead.

Co-authored-by: Cursor <[email protected]>

* fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)

Restores the reverse-lookup for the JSONL body.model fallback path so that
legacy/pre-target_model_names managed files still map stripped provider IDs
back to proxy aliases before auth. Also cleans up redundant `or None`.

Co-Authored-By: Claude Sonnet 4.6 <[email protected]>

* Revert "fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)"

This reverts commit 30d2e96.

---------

Co-authored-by: Cursor <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>

* Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI (#30064)

* Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI

Adds cost map entries for claude-fable-5 ($10/$50 per MTok, 1M context,
128K output, adaptive thinking only) on the Anthropic API, Bedrock
converse (base, global, and us/eu geo inference profiles at the 10%
regional premium), Vertex AI, and Azure AI (Microsoft Foundry, which
serves Fable 5 with the full 1M context window unlike Opus 4.8).

Registers anthropic.claude-fable-5 in BEDROCK_CONVERSE_MODELS, lists the
model in the setup wizard, and extends the reasoning effort e2e grid.
The Bedrock, Vertex, and Azure grid cells carry fail_reason markers
until the CI accounts are provisioned: Bedrock needs the provider data
sharing opt-in Fable 5 requires, and the Foundry resource needs a
claude-fable-5 deployment.

The first-party entry carries provider_specific_entry {us: 1.1} for the
inference_geo premium and deliberately no fast multiplier since Fable 5
has no fast mode.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Drop removed sampling params for Claude 4.7+ when drop_params is set

Fable 5, Opus 4.7, and Opus 4.8 removed sampling params: the API rejects
top_p, top_k, and any temperature other than 1 with a 400. LiteLLM was
forwarding them even with drop_params enabled because the Anthropic and
Bedrock converse transformations passed temperature/top_p through
unconditionally.

Mirror the GPT-5/o-series handling: temperature=1 still passes through,
other values and any top_p are dropped when drop_params is set, and
without drop_params a clean client-side UnsupportedParamsError tells the
caller how to opt in, instead of surfacing the raw provider error.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Drive sampling param gating from the cost map and cover top_k

Greptile review follow-ups on the sampling param fix: the restriction for
Fable 5 / Opus 4.7 / 4.8 is now declared as supports_sampling_params: false
on every affected cost map entry (perplexity excluded; that route is
OpenAI-compatible and maps sampling params upstream) and read back through
a tri-state map lookup, keeping the name check only as a fallback for
provider-routed ids whose hosted map entries predate the flag, the same
layering supports_adaptive_thinking uses. top_k bypasses map_openai_params
as a provider-specific kwarg, so it is gated at the shared
AnthropicConfig.transform_request boundary (direct, Bedrock invoke, Vertex,
Azure) and in the Bedrock converse _handle_top_k_value path, with
drop_params threaded through the converse transform helpers.

Also updates the reasoning effort grid cell count assertion for the four
Fable 5 rows added on this branch (29 x 11 cells).

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Declare supports_sampling_params in the cost map schema

The model map validation schema uses additionalProperties: false, so the
new flag must be declared for the 28 entries that carry it; this was the
one failing job (misc / Run tests) on the previous commit.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* fix(bedrock): gate top_k=0 on converse to match Anthropic boundary

Truthiness check let top_k=0 silently disappear on models that removed
sampling params, while AnthropicConfig.transform_request treats 0 as
present and raises UnsupportedParamsError (or drops when drop_params is
set). Switch to 'is not None' so converse, direct Anthropic, invoke,
Vertex, and Azure all behave the same for top_k=0.

---------

Co-authored-by: Cursor Agent <[email protected]>

* Fix LiteLLM DB skills never executing due to tool name prefix mismatch

Skill IDs are generated as litellm_skill_<uuid> and the model-facing
tool name is the sanitized skill ID, but the post-call execution gates
in SkillsInjectionHook only ran tools whose name starts with "skill_",
so DB skills were silently returned to the client as raw tool calls.

Add LITELLM_SKILL_ID_PREFIX to the skills constants module, use it for
ID generation, DB skill detection, and both execution gates, and fix
the README and docstring examples that documented the unrecognized
litellm:skill_... form.

Fixes #28122.

---------

Co-authored-by: milan-berri <[email protected]>
Co-authored-by: Cursor <[email protected]>
Co-authored-by: ryan-crabbe-berri <[email protected]>
Co-authored-by: michelligabriele <[email protected]>
Co-authored-by: tin-berri <[email protected]>
Co-authored-by: yuneng-jiang <[email protected]>
Co-authored-by: stuxf <[email protected]>
Co-authored-by: Sameer Kankute <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>
Co-authored-by: Mateo Wang <[email protected]>

…omits output_item.added (#30115)

* fix(team): reserve team budget raises for proxy admins on /team/update (#30030)

The caller's PERSONAL max_budget was the wrong yardstick for /team/update: a
team's spend ceiling has nothing to do with the admin's own key budget. That
comparison was an unintended side effect of reusing _check_user_team_limits()
(which exists for the /team/new path) and broke the UI, which re-sends the
unchanged budget on every save.

New behavior on /team/update for standalone teams:
- A team admin (already authorized via _verify_team_access) may freely KEEP or
  LOWER the team budget, and change models/tpm/rpm, without being gated by their
  personal limits.
- GROWING a team's spend ceiling is a budget-authority action reserved for proxy
  admins -> 403 for team admins. "Growing" covers both raising max_budget above
  the team's current finite value and removing the cap entirely (max_budget=null,
  detected via model_fields_set so an explicit null is distinguished from an
  omitted field). For a team that currently has no cap, setting a finite value is
  a restriction and is allowed.
- Org-scoped teams remain governed by _check_org_team_limits() (capped by the
  org budget).

Also reverts the #29525 existing_team_max_budget workaround in
_check_user_team_limits() back to the create-only form; /team/new still enforces
the creator's personal caps.

docs(access_control): resolve the contradiction in the team-admin section —
team admins can keep/lower the budget and manage rate limits/models, but cannot
raise the team budget (proxy-admin only).

tests: unit + behavior coverage for raise-blocked, cap-removal-blocked (team
admin), raise/removal allowed (proxy admin), uncapped-team restriction allowed,
keep/lower/resend allowed, and unchanged create-path guards.

Co-authored-by: Cursor <[email protected]>

* test(ui): data-driven App Router migration E2E smoke (default + server-root-path) (#29974)

* test(ui): add a data-driven App Router migration E2E smoke

Add a growing Playwright smoke for migrated pages: for each segment it deep-links
to the path route, asserts the URL and that the dashboard shell rendered, then
clicks off to a legacy page and asserts navigation still works. Driven by
e2e_tests/fixtures/migratedPages.ts, so adding a page is one line.

Runs in two situations against the same proxy: the default mount (npm run
e2e:migration) and a non-root SERVER_ROOT_PATH mount (npm run e2e:migration:root).
globalSetup now logs in at `${SERVER_ROOT_PATH}/ui/login` so the admin storage
state is valid under a prefix. Seeded with api-reference; append the rest as their
migrations merge.

* test(ui): support headed slow-motion + watch pauses in the migration smoke

Honor SLOWMO in the server-root-path config (the default config already did),
and add an env-gated E2E_WATCH_MS pause so a headed run lingers on each state.
Both are no-ops by default, so CI behavior is unchanged.

* test(ui): make the migration smoke a sidebar-click user journey

Rework the smoke from deep-linking to a real navigation journey: start at the
landing page, click the migrated page in the sidebar (expanding submenus for
nested items), assert the path route rendered, reload it (the check a wrong
server_root_path breaks), bounce to a legacy page and back, and — once two pages
are migrated — navigate directly between two migrated pages. Verifies via URL +
shell render, driven by the same fixture list.

* test(ui): address review on the migration smoke

Escape ROOT and segment before interpolating them into RegExp URL matchers so a
future segment containing regex metacharacters can't silently widen the match.
Make the server-root-path config fail fast when SERVER_ROOT_PATH is unset instead
of silently re-running the default mount and passing without exercising the prefix.

* test(ui): drop unused watch helper and fix stale smoke README

* test(ui): run the migration smoke under a server root path in CI

* test(ui): harden + instrument the server-root-path proxy reboot in CI

* test(ui): run the server-root-path migration smoke as its own CI job

Replace the in-place proxy reboot in e2e_ui_testing with a dedicated
e2e_ui_testing_server_root_path job that boots the proxy once with
SERVER_ROOT_PATH=/litellm, matching how every other proxy variant in the
config gets its own job rather than killing and relaunching the live proxy.

The reboot was failing deterministically: after pkill -9 and relaunch the
prefixed proxy never came back up on :4000 (connection refused), so the smoke
never ran. The readiness step that was supposed to surface the cause could
never reach its boot-log tail because CircleCI runs steps under bash -eo
pipefail and the preceding `curl -sv ... | tail` aborted the step with curl's
exit 7. Booting the proxy as the job's own background step lets any boot crash
land in that step's log instead of being swallowed.

The default e2e_ui_testing job is unchanged aside from dropping the reboot,
prefixed-readiness, and prefixed-smoke steps; the migration smoke still runs at
the root mount there via the default Playwright config.

* fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through (#24232)

* fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through

* test: mock post_call_response_headers_hook in audio speech route tests

* chore(ui): remove dead App Router route stubs under (dashboard) (#30045)

models-and-endpoints, organizations, and virtual-keys each had a page.tsx
route under (dashboard)/ that is not in MIGRATED_PAGES, so the sidebar and
deep links never resolve to it and the route is unreachable. Each was a thin
wrapper that handed the shared view empty or no-op props (empty modelData with
a no-op setModelData, hardcoded empty organizations, no-op
setUserRole/setUserEmail), so reaching one would render a degraded page in any
case. The real wrapper belongs in the PR that flips each page into
MIGRATED_PAGES, written with eyes on it and a test

This continues the dead-scaffolding cleanup from #28891. The shared components
these wrappers rendered (ModelsAndEndpointsView, OrganizationFilters) stay,
since the legacy ?page= switch in app/page.tsx and src/components still import
them

* fix(ui/mcp): reset OAuth state on create-server modal close so a prior server's token no longer leaks into the next add-server session (#30000)

* fix(ui/mcp): reset OAuth hook state on modal close so a prior server's token no longer leaks into the next add-server session

* fix(ui/mcp): clear in-flight OAuth guard on reset and reset form/tools on modal close so nothing leaks on a parent-driven dismiss

* fix(mcp): allow team access-group grants in OAuth authorize/token access check (#30041)

* fix(mcp): honor team access-group grants in OAuth authorize/token access check

* test(mcp): mock build_effective_auth_contexts in non-admin authorize tests for isolation

* docs(security): require a reproduction video for vulnerability reports (#30048) (#30063)

With AI models capable of automated vulnerability discovery now publicly
available, we expect a large increase in report volume, much of it
unverified. Requiring a video of the exploit running against a live
instance raises the bar for submissions and keeps triage focused on
reproducible issues. Reports without a video will be closed and reopened
if one is added later.

Co-authored-by: stuxf <[email protected]>

* feat(ui): add admin flag to disable in-product UI nudges for everyone (#29796)

* feat(ui): add admin flag to disable in-product UI nudges for everyone

Admins can now suppress the survey and Claude Code feedback popups for
all users via a single disable_ui_nudges UI setting, instead of relying
on each user dismissing them individually.

* fix(ui): suppress nudges while ui settings are loading

Gate nudgesDisabled on the ui-settings loading state so an admin with
disable_ui_nudges on doesn't see the survey prompt flash, and the
getInProductNudgesCall fetch doesn't fire, on a cold page load before
the flag resolves. Falls back to showing nudges if the fetch errors.

* test(ui): wrap CreateKeyPage test in QueryClientProvider

page.tsx now calls useUISettings (react-query), which needs a
QueryClient that layout.tsx supplies in production but the test did
not. Add the provider and mock getUiSettings so the query resolves.

* chore(ui): remove dead dashboard files and unused dependencies (#30047)

* chore(ui): remove dead dashboard files and unused dependencies

knip flagged seven orphaned source/config files with no importers and
five declared dependencies that nothing in the tree uses. Removing them
shrinks the dashboard bundle's source surface and keeps the manifest
honest; vite stays installed transitively via vitest, so test tooling is
unaffected.

* fix(ci): restore serverRootPath.config.ts referenced by SERVER_ROOT_PATH workflow

The dead-code sweep removed e2e_tests/serverRootPath.config.ts, but its spec
(tests/login/serverRootPathRedirect.spec.ts) and the test_server_root_path.yml
workflow step still depend on it, so the redirect e2e job failed to load a
config that no longer existed.

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593) (#30009)

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593)

After replace_model_in_jsonl, body.model is a stripped provider id. Reverse-mapping it via resolve_model_name_from_model_id is first-match on model_list and caused false 403s when multiple deployments share the same stripped name. Use target_model_names from the unified file id instead.

Co-authored-by: Cursor <[email protected]>

* fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)

Restores the reverse-lookup for the JSONL body.model fallback path so that
legacy/pre-target_model_names managed files still map stripped provider IDs
back to proxy aliases before auth. Also cleans up redundant `or None`.

Co-Authored-By: Claude Sonnet 4.6 <[email protected]>

* Revert "fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)"

This reverts commit 30d2e96.

---------

Co-authored-by: Cursor <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>

* Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI (#30064)

* Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI

Adds cost map entries for claude-fable-5 ($10/$50 per MTok, 1M context,
128K output, adaptive thinking only) on the Anthropic API, Bedrock
converse (base, global, and us/eu geo inference profiles at the 10%
regional premium), Vertex AI, and Azure AI (Microsoft Foundry, which
serves Fable 5 with the full 1M context window unlike Opus 4.8).

Registers anthropic.claude-fable-5 in BEDROCK_CONVERSE_MODELS, lists the
model in the setup wizard, and extends the reasoning effort e2e grid.
The Bedrock, Vertex, and Azure grid cells carry fail_reason markers
until the CI accounts are provisioned: Bedrock needs the provider data
sharing opt-in Fable 5 requires, and the Foundry resource needs a
claude-fable-5 deployment.

The first-party entry carries provider_specific_entry {us: 1.1} for the
inference_geo premium and deliberately no fast multiplier since Fable 5
has no fast mode.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Drop removed sampling params for Claude 4.7+ when drop_params is set

Fable 5, Opus 4.7, and Opus 4.8 removed sampling params: the API rejects
top_p, top_k, and any temperature other than 1 with a 400. LiteLLM was
forwarding them even with drop_params enabled because the Anthropic and
Bedrock converse transformations passed temperature/top_p through
unconditionally.

Mirror the GPT-5/o-series handling: temperature=1 still passes through,
other values and any top_p are dropped when drop_params is set, and
without drop_params a clean client-side UnsupportedParamsError tells the
caller how to opt in, instead of surfacing the raw provider error.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Drive sampling param gating from the cost map and cover top_k

Greptile review follow-ups on the sampling param fix: the restriction for
Fable 5 / Opus 4.7 / 4.8 is now declared as supports_sampling_params: false
on every affected cost map entry (perplexity excluded; that route is
OpenAI-compatible and maps sampling params upstream) and read back through
a tri-state map lookup, keeping the name check only as a fallback for
provider-routed ids whose hosted map entries predate the flag, the same
layering supports_adaptive_thinking uses. top_k bypasses map_openai_params
as a provider-specific kwarg, so it is gated at the shared
AnthropicConfig.transform_request boundary (direct, Bedrock invoke, Vertex,
Azure) and in the Bedrock converse _handle_top_k_value path, with
drop_params threaded through the converse transform helpers.

Also updates the reasoning effort grid cell count assertion for the four
Fable 5 rows added on this branch (29 x 11 cells).

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Declare supports_sampling_params in the cost map schema

The model map validation schema uses additionalProperties: false, so the
new flag must be declared for the 28 entries that carry it; this was the
one failing job (misc / Run tests) on the previous commit.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* fix(bedrock): gate top_k=0 on converse to match Anthropic boundary

Truthiness check let top_k=0 silently disappear on models that removed
sampling params, while AnthropicConfig.transform_request treats 0 as
present and raises UnsupportedParamsError (or drops when drop_params is
set). Switch to 'is not None' so converse, direct Anthropic, invoke,
Vertex, and Azure all behave the same for top_k=0.

---------

Co-authored-by: Cursor Agent <[email protected]>

* fix(anthropic): avoid index -1 content_block_delta in messages stream

When a /v1/messages request is routed through the Responses API
adapter, AnthropicResponsesStreamWrapper only emits content_block_start
on response.output_item.added. Some upstreams (LMStudio for example)
never send that event, so the text delta handler fell back to
_current_block_index, which starts at -1, and clients received
content_block_delta events with index -1 and no preceding
content_block_start. Anthropic SDKs then fail with "text part -1 not
found"

The text delta handler now synthesizes a content_block_start with a
fresh block index whenever the delta references an unregistered item_id
or no block is open yet, and registers the item_id so follow-up deltas
reuse the same index

Addresses the /v1/messages defect in #27442

* Make test sys.path shim resolve relative to the file, not the CWD

os.path.abspath("../../../../../../..") depends on where pytest is
invoked from; anchoring on os.path.dirname(__file__) makes the import
work from any working directory. Also corrects the depth: the repo root
is six levels above this file, not seven.

---------

Co-authored-by: milan-berri <[email protected]>
Co-authored-by: Cursor <[email protected]>
Co-authored-by: ryan-crabbe-berri <[email protected]>
Co-authored-by: michelligabriele <[email protected]>
Co-authored-by: tin-berri <[email protected]>
Co-authored-by: yuneng-jiang <[email protected]>
Co-authored-by: stuxf <[email protected]>
Co-authored-by: Sameer Kankute <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>
Co-authored-by: Mateo Wang <[email protected]>

…0114)

* fix(team): reserve team budget raises for proxy admins on /team/update (#30030)

The caller's PERSONAL max_budget was the wrong yardstick for /team/update: a
team's spend ceiling has nothing to do with the admin's own key budget. That
comparison was an unintended side effect of reusing _check_user_team_limits()
(which exists for the /team/new path) and broke the UI, which re-sends the
unchanged budget on every save.

New behavior on /team/update for standalone teams:
- A team admin (already authorized via _verify_team_access) may freely KEEP or
  LOWER the team budget, and change models/tpm/rpm, without being gated by their
  personal limits.
- GROWING a team's spend ceiling is a budget-authority action reserved for proxy
  admins -> 403 for team admins. "Growing" covers both raising max_budget above
  the team's current finite value and removing the cap entirely (max_budget=null,
  detected via model_fields_set so an explicit null is distinguished from an
  omitted field). For a team that currently has no cap, setting a finite value is
  a restriction and is allowed.
- Org-scoped teams remain governed by _check_org_team_limits() (capped by the
  org budget).

Also reverts the #29525 existing_team_max_budget workaround in
_check_user_team_limits() back to the create-only form; /team/new still enforces
the creator's personal caps.

docs(access_control): resolve the contradiction in the team-admin section —
team admins can keep/lower the budget and manage rate limits/models, but cannot
raise the team budget (proxy-admin only).

tests: unit + behavior coverage for raise-blocked, cap-removal-blocked (team
admin), raise/removal allowed (proxy admin), uncapped-team restriction allowed,
keep/lower/resend allowed, and unchanged create-path guards.

Co-authored-by: Cursor <[email protected]>

* test(ui): data-driven App Router migration E2E smoke (default + server-root-path) (#29974)

* test(ui): add a data-driven App Router migration E2E smoke

Add a growing Playwright smoke for migrated pages: for each segment it deep-links
to the path route, asserts the URL and that the dashboard shell rendered, then
clicks off to a legacy page and asserts navigation still works. Driven by
e2e_tests/fixtures/migratedPages.ts, so adding a page is one line.

Runs in two situations against the same proxy: the default mount (npm run
e2e:migration) and a non-root SERVER_ROOT_PATH mount (npm run e2e:migration:root).
globalSetup now logs in at `${SERVER_ROOT_PATH}/ui/login` so the admin storage
state is valid under a prefix. Seeded with api-reference; append the rest as their
migrations merge.

* test(ui): support headed slow-motion + watch pauses in the migration smoke

Honor SLOWMO in the server-root-path config (the default config already did),
and add an env-gated E2E_WATCH_MS pause so a headed run lingers on each state.
Both are no-ops by default, so CI behavior is unchanged.

* test(ui): make the migration smoke a sidebar-click user journey

Rework the smoke from deep-linking to a real navigation journey: start at the
landing page, click the migrated page in the sidebar (expanding submenus for
nested items), assert the path route rendered, reload it (the check a wrong
server_root_path breaks), bounce to a legacy page and back, and — once two pages
are migrated — navigate directly between two migrated pages. Verifies via URL +
shell render, driven by the same fixture list.

* test(ui): address review on the migration smoke

Escape ROOT and segment before interpolating them into RegExp URL matchers so a
future segment containing regex metacharacters can't silently widen the match.
Make the server-root-path config fail fast when SERVER_ROOT_PATH is unset instead
of silently re-running the default mount and passing without exercising the prefix.

* test(ui): drop unused watch helper and fix stale smoke README

* test(ui): run the migration smoke under a server root path in CI

* test(ui): harden + instrument the server-root-path proxy reboot in CI

* test(ui): run the server-root-path migration smoke as its own CI job

Replace the in-place proxy reboot in e2e_ui_testing with a dedicated
e2e_ui_testing_server_root_path job that boots the proxy once with
SERVER_ROOT_PATH=/litellm, matching how every other proxy variant in the
config gets its own job rather than killing and relaunching the live proxy.

The reboot was failing deterministically: after pkill -9 and relaunch the
prefixed proxy never came back up on :4000 (connection refused), so the smoke
never ran. The readiness step that was supposed to surface the cause could
never reach its boot-log tail because CircleCI runs steps under bash -eo
pipefail and the preceding `curl -sv ... | tail` aborted the step with curl's
exit 7. Booting the proxy as the job's own background step lets any boot crash
land in that step's log instead of being swallowed.

The default e2e_ui_testing job is unchanged aside from dropping the reboot,
prefixed-readiness, and prefixed-smoke steps; the migration smoke still runs at
the root mount there via the default Playwright config.

* fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through (#24232)

* fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through

* test: mock post_call_response_headers_hook in audio speech route tests

* chore(ui): remove dead App Router route stubs under (dashboard) (#30045)

models-and-endpoints, organizations, and virtual-keys each had a page.tsx
route under (dashboard)/ that is not in MIGRATED_PAGES, so the sidebar and
deep links never resolve to it and the route is unreachable. Each was a thin
wrapper that handed the shared view empty or no-op props (empty modelData with
a no-op setModelData, hardcoded empty organizations, no-op
setUserRole/setUserEmail), so reaching one would render a degraded page in any
case. The real wrapper belongs in the PR that flips each page into
MIGRATED_PAGES, written with eyes on it and a test

This continues the dead-scaffolding cleanup from #28891. The shared components
these wrappers rendered (ModelsAndEndpointsView, OrganizationFilters) stay,
since the legacy ?page= switch in app/page.tsx and src/components still import
them

* fix(ui/mcp): reset OAuth state on create-server modal close so a prior server's token no longer leaks into the next add-server session (#30000)

* fix(ui/mcp): reset OAuth hook state on modal close so a prior server's token no longer leaks into the next add-server session

* fix(ui/mcp): clear in-flight OAuth guard on reset and reset form/tools on modal close so nothing leaks on a parent-driven dismiss

* fix(mcp): allow team access-group grants in OAuth authorize/token access check (#30041)

* fix(mcp): honor team access-group grants in OAuth authorize/token access check

* test(mcp): mock build_effective_auth_contexts in non-admin authorize tests for isolation

* docs(security): require a reproduction video for vulnerability reports (#30048) (#30063)

With AI models capable of automated vulnerability discovery now publicly
available, we expect a large increase in report volume, much of it
unverified. Requiring a video of the exploit running against a live
instance raises the bar for submissions and keeps triage focused on
reproducible issues. Reports without a video will be closed and reopened
if one is added later.

Co-authored-by: stuxf <[email protected]>

* feat(ui): add admin flag to disable in-product UI nudges for everyone (#29796)

* feat(ui): add admin flag to disable in-product UI nudges for everyone

Admins can now suppress the survey and Claude Code feedback popups for
all users via a single disable_ui_nudges UI setting, instead of relying
on each user dismissing them individually.

* fix(ui): suppress nudges while ui settings are loading

Gate nudgesDisabled on the ui-settings loading state so an admin with
disable_ui_nudges on doesn't see the survey prompt flash, and the
getInProductNudgesCall fetch doesn't fire, on a cold page load before
the flag resolves. Falls back to showing nudges if the fetch errors.

* test(ui): wrap CreateKeyPage test in QueryClientProvider

page.tsx now calls useUISettings (react-query), which needs a
QueryClient that layout.tsx supplies in production but the test did
not. Add the provider and mock getUiSettings so the query resolves.

* chore(ui): remove dead dashboard files and unused dependencies (#30047)

* chore(ui): remove dead dashboard files and unused dependencies

knip flagged seven orphaned source/config files with no importers and
five declared dependencies that nothing in the tree uses. Removing them
shrinks the dashboard bundle's source surface and keeps the manifest
honest; vite stays installed transitively via vitest, so test tooling is
unaffected.

* fix(ci): restore serverRootPath.config.ts referenced by SERVER_ROOT_PATH workflow

The dead-code sweep removed e2e_tests/serverRootPath.config.ts, but its spec
(tests/login/serverRootPathRedirect.spec.ts) and the test_server_root_path.yml
workflow step still depend on it, so the redirect e2e job failed to load a
config that no longer existed.

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593) (#30009)

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593)

After replace_model_in_jsonl, body.model is a stripped provider id. Reverse-mapping it via resolve_model_name_from_model_id is first-match on model_list and caused false 403s when multiple deployments share the same stripped name. Use target_model_names from the unified file id instead.

Co-authored-by: Cursor <[email protected]>

* fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)

Restores the reverse-lookup for the JSONL body.model fallback path so that
legacy/pre-target_model_names managed files still map stripped provider IDs
back to proxy aliases before auth. Also cleans up redundant `or None`.

Co-Authored-By: Claude Sonnet 4.6 <[email protected]>

* Revert "fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)"

This reverts commit 30d2e96.

---------

Co-authored-by: Cursor <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>

* Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI (#30064)

* Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI

Adds cost map entries for claude-fable-5 ($10/$50 per MTok, 1M context,
128K output, adaptive thinking only) on the Anthropic API, Bedrock
converse (base, global, and us/eu geo inference profiles at the 10%
regional premium), Vertex AI, and Azure AI (Microsoft Foundry, which
serves Fable 5 with the full 1M context window unlike Opus 4.8).

Registers anthropic.claude-fable-5 in BEDROCK_CONVERSE_MODELS, lists the
model in the setup wizard, and extends the reasoning effort e2e grid.
The Bedrock, Vertex, and Azure grid cells carry fail_reason markers
until the CI accounts are provisioned: Bedrock needs the provider data
sharing opt-in Fable 5 requires, and the Foundry resource needs a
claude-fable-5 deployment.

The first-party entry carries provider_specific_entry {us: 1.1} for the
inference_geo premium and deliberately no fast multiplier since Fable 5
has no fast mode.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Drop removed sampling params for Claude 4.7+ when drop_params is set

Fable 5, Opus 4.7, and Opus 4.8 removed sampling params: the API rejects
top_p, top_k, and any temperature other than 1 with a 400. LiteLLM was
forwarding them even with drop_params enabled because the Anthropic and
Bedrock converse transformations passed temperature/top_p through
unconditionally.

Mirror the GPT-5/o-series handling: temperature=1 still passes through,
other values and any top_p are dropped when drop_params is set, and
without drop_params a clean client-side UnsupportedParamsError tells the
caller how to opt in, instead of surfacing the raw provider error.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Drive sampling param gating from the cost map and cover top_k

Greptile review follow-ups on the sampling param fix: the restriction for
Fable 5 / Opus 4.7 / 4.8 is now declared as supports_sampling_params: false
on every affected cost map entry (perplexity excluded; that route is
OpenAI-compatible and maps sampling params upstream) and read back through
a tri-state map lookup, keeping the name check only as a fallback for
provider-routed ids whose hosted map entries predate the flag, the same
layering supports_adaptive_thinking uses. top_k bypasses map_openai_params
as a provider-specific kwarg, so it is gated at the shared
AnthropicConfig.transform_request boundary (direct, Bedrock invoke, Vertex,
Azure) and in the Bedrock converse _handle_top_k_value path, with
drop_params threaded through the converse transform helpers.

Also updates the reasoning effort grid cell count assertion for the four
Fable 5 rows added on this branch (29 x 11 cells).

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Declare supports_sampling_params in the cost map schema

The model map validation schema uses additionalProperties: false, so the
new flag must be declared for the 28 entries that carry it; this was the
one failing job (misc / Run tests) on the previous commit.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* fix(bedrock): gate top_k=0 on converse to match Anthropic boundary

Truthiness check let top_k=0 silently disappear on models that removed
sampling params, while AnthropicConfig.transform_request treats 0 as
present and raises UnsupportedParamsError (or drops when drop_params is
set). Switch to 'is not None' so converse, direct Anthropic, invoke,
Vertex, and Azure all behave the same for top_k=0.

---------

Co-authored-by: Cursor Agent <[email protected]>

* fix: enable compact-2026-01-12 beta header for vertex_ai provider

The vertex_ai block in anthropic_beta_headers_config.json mapped
compact-2026-01-12 to null, so update_headers_with_filtered_beta
stripped the header before the request reached Vertex while the
compact_20260112 context edit stayed in the body, and Vertex rejected
the request with HTTP 400. Vertex rawPredict accepts the header, and
the bedrock and databricks blocks already forward it. Mirrors #21867,
which enabled context-1m-2025-08-07 for vertex_ai the same way.

Fixes #27290.

---------

Co-authored-by: milan-berri <[email protected]>
Co-authored-by: Cursor <[email protected]>
Co-authored-by: ryan-crabbe-berri <[email protected]>
Co-authored-by: michelligabriele <[email protected]>
Co-authored-by: tin-berri <[email protected]>
Co-authored-by: yuneng-jiang <[email protected]>
Co-authored-by: stuxf <[email protected]>
Co-authored-by: Sameer Kankute <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>
Co-authored-by: Mateo Wang <[email protected]>

* fix(team): reserve team budget raises for proxy admins on /team/update (#30030)

The caller's PERSONAL max_budget was the wrong yardstick for /team/update: a
team's spend ceiling has nothing to do with the admin's own key budget. That
comparison was an unintended side effect of reusing _check_user_team_limits()
(which exists for the /team/new path) and broke the UI, which re-sends the
unchanged budget on every save.

New behavior on /team/update for standalone teams:
- A team admin (already authorized via _verify_team_access) may freely KEEP or
  LOWER the team budget, and change models/tpm/rpm, without being gated by their
  personal limits.
- GROWING a team's spend ceiling is a budget-authority action reserved for proxy
  admins -> 403 for team admins. "Growing" covers both raising max_budget above
  the team's current finite value and removing the cap entirely (max_budget=null,
  detected via model_fields_set so an explicit null is distinguished from an
  omitted field). For a team that currently has no cap, setting a finite value is
  a restriction and is allowed.
- Org-scoped teams remain governed by _check_org_team_limits() (capped by the
  org budget).

Also reverts the #29525 existing_team_max_budget workaround in
_check_user_team_limits() back to the create-only form; /team/new still enforces
the creator's personal caps.

docs(access_control): resolve the contradiction in the team-admin section —
team admins can keep/lower the budget and manage rate limits/models, but cannot
raise the team budget (proxy-admin only).

tests: unit + behavior coverage for raise-blocked, cap-removal-blocked (team
admin), raise/removal allowed (proxy admin), uncapped-team restriction allowed,
keep/lower/resend allowed, and unchanged create-path guards.

Co-authored-by: Cursor <[email protected]>

* test(ui): data-driven App Router migration E2E smoke (default + server-root-path) (#29974)

* test(ui): add a data-driven App Router migration E2E smoke

Add a growing Playwright smoke for migrated pages: for each segment it deep-links
to the path route, asserts the URL and that the dashboard shell rendered, then
clicks off to a legacy page and asserts navigation still works. Driven by
e2e_tests/fixtures/migratedPages.ts, so adding a page is one line.

Runs in two situations against the same proxy: the default mount (npm run
e2e:migration) and a non-root SERVER_ROOT_PATH mount (npm run e2e:migration:root).
globalSetup now logs in at `${SERVER_ROOT_PATH}/ui/login` so the admin storage
state is valid under a prefix. Seeded with api-reference; append the rest as their
migrations merge.

* test(ui): support headed slow-motion + watch pauses in the migration smoke

Honor SLOWMO in the server-root-path config (the default config already did),
and add an env-gated E2E_WATCH_MS pause so a headed run lingers on each state.
Both are no-ops by default, so CI behavior is unchanged.

* test(ui): make the migration smoke a sidebar-click user journey

Rework the smoke from deep-linking to a real navigation journey: start at the
landing page, click the migrated page in the sidebar (expanding submenus for
nested items), assert the path route rendered, reload it (the check a wrong
server_root_path breaks), bounce to a legacy page and back, and — once two pages
are migrated — navigate directly between two migrated pages. Verifies via URL +
shell render, driven by the same fixture list.

* test(ui): address review on the migration smoke

Escape ROOT and segment before interpolating them into RegExp URL matchers so a
future segment containing regex metacharacters can't silently widen the match.
Make the server-root-path config fail fast when SERVER_ROOT_PATH is unset instead
of silently re-running the default mount and passing without exercising the prefix.

* test(ui): drop unused watch helper and fix stale smoke README

* test(ui): run the migration smoke under a server root path in CI

* test(ui): harden + instrument the server-root-path proxy reboot in CI

* test(ui): run the server-root-path migration smoke as its own CI job

Replace the in-place proxy reboot in e2e_ui_testing with a dedicated
e2e_ui_testing_server_root_path job that boots the proxy once with
SERVER_ROOT_PATH=/litellm, matching how every other proxy variant in the
config gets its own job rather than killing and relaunching the live proxy.

The reboot was failing deterministically: after pkill -9 and relaunch the
prefixed proxy never came back up on :4000 (connection refused), so the smoke
never ran. The readiness step that was supposed to surface the cause could
never reach its boot-log tail because CircleCI runs steps under bash -eo
pipefail and the preceding `curl -sv ... | tail` aborted the step with curl's
exit 7. Booting the proxy as the job's own background step lets any boot crash
land in that step's log instead of being swallowed.

The default e2e_ui_testing job is unchanged aside from dropping the reboot,
prefixed-readiness, and prefixed-smoke steps; the migration smoke still runs at
the root mount there via the default Playwright config.

* fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through (#24232)

* fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through

* test: mock post_call_response_headers_hook in audio speech route tests

* chore(ui): remove dead App Router route stubs under (dashboard) (#30045)

models-and-endpoints, organizations, and virtual-keys each had a page.tsx
route under (dashboard)/ that is not in MIGRATED_PAGES, so the sidebar and
deep links never resolve to it and the route is unreachable. Each was a thin
wrapper that handed the shared view empty or no-op props (empty modelData with
a no-op setModelData, hardcoded empty organizations, no-op
setUserRole/setUserEmail), so reaching one would render a degraded page in any
case. The real wrapper belongs in the PR that flips each page into
MIGRATED_PAGES, written with eyes on it and a test

This continues the dead-scaffolding cleanup from #28891. The shared components
these wrappers rendered (ModelsAndEndpointsView, OrganizationFilters) stay,
since the legacy ?page= switch in app/page.tsx and src/components still import
them

* fix(ui/mcp): reset OAuth state on create-server modal close so a prior server's token no longer leaks into the next add-server session (#30000)

* fix(ui/mcp): reset OAuth hook state on modal close so a prior server's token no longer leaks into the next add-server session

* fix(ui/mcp): clear in-flight OAuth guard on reset and reset form/tools on modal close so nothing leaks on a parent-driven dismiss

* fix(mcp): allow team access-group grants in OAuth authorize/token access check (#30041)

* fix(mcp): honor team access-group grants in OAuth authorize/token access check

* test(mcp): mock build_effective_auth_contexts in non-admin authorize tests for isolation

* docs(security): require a reproduction video for vulnerability reports (#30048) (#30063)

With AI models capable of automated vulnerability discovery now publicly
available, we expect a large increase in report volume, much of it
unverified. Requiring a video of the exploit running against a live
instance raises the bar for submissions and keeps triage focused on
reproducible issues. Reports without a video will be closed and reopened
if one is added later.

Co-authored-by: stuxf <[email protected]>

* feat(ui): add admin flag to disable in-product UI nudges for everyone (#29796)

* feat(ui): add admin flag to disable in-product UI nudges for everyone

Admins can now suppress the survey and Claude Code feedback popups for
all users via a single disable_ui_nudges UI setting, instead of relying
on each user dismissing them individually.

* fix(ui): suppress nudges while ui settings are loading

Gate nudgesDisabled on the ui-settings loading state so an admin with
disable_ui_nudges on doesn't see the survey prompt flash, and the
getInProductNudgesCall fetch doesn't fire, on a cold page load before
the flag resolves. Falls back to showing nudges if the fetch errors.

* test(ui): wrap CreateKeyPage test in QueryClientProvider

page.tsx now calls useUISettings (react-query), which needs a
QueryClient that layout.tsx supplies in production but the test did
not. Add the provider and mock getUiSettings so the query resolves.

* chore(ui): remove dead dashboard files and unused dependencies (#30047)

* chore(ui): remove dead dashboard files and unused dependencies

knip flagged seven orphaned source/config files with no importers and
five declared dependencies that nothing in the tree uses. Removing them
shrinks the dashboard bundle's source surface and keeps the manifest
honest; vite stays installed transitively via vitest, so test tooling is
unaffected.

* fix(ci): restore serverRootPath.config.ts referenced by SERVER_ROOT_PATH workflow

The dead-code sweep removed e2e_tests/serverRootPath.config.ts, but its spec
(tests/login/serverRootPathRedirect.spec.ts) and the test_server_root_path.yml
workflow step still depend on it, so the redirect e2e job failed to load a
config that no longer existed.

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593) (#30009)

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593)

After replace_model_in_jsonl, body.model is a stripped provider id. Reverse-mapping it via resolve_model_name_from_model_id is first-match on model_list and caused false 403s when multiple deployments share the same stripped name. Use target_model_names from the unified file id instead.

Co-authored-by: Cursor <[email protected]>

* fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)

Restores the reverse-lookup for the JSONL body.model fallback path so that
legacy/pre-target_model_names managed files still map stripped provider IDs
back to proxy aliases before auth. Also cleans up redundant `or None`.

Co-Authored-By: Claude Sonnet 4.6 <[email protected]>

* Revert "fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)"

This reverts commit 30d2e96.

---------

Co-authored-by: Cursor <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>

* Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI (#30064)

* Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI

Adds cost map entries for claude-fable-5 ($10/$50 per MTok, 1M context,
128K output, adaptive thinking only) on the Anthropic API, Bedrock
converse (base, global, and us/eu geo inference profiles at the 10%
regional premium), Vertex AI, and Azure AI (Microsoft Foundry, which
serves Fable 5 with the full 1M context window unlike Opus 4.8).

Registers anthropic.claude-fable-5 in BEDROCK_CONVERSE_MODELS, lists the
model in the setup wizard, and extends the reasoning effort e2e grid.
The Bedrock, Vertex, and Azure grid cells carry fail_reason markers
until the CI accounts are provisioned: Bedrock needs the provider data
sharing opt-in Fable 5 requires, and the Foundry resource needs a
claude-fable-5 deployment.

The first-party entry carries provider_specific_entry {us: 1.1} for the
inference_geo premium and deliberately no fast multiplier since Fable 5
has no fast mode.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Drop removed sampling params for Claude 4.7+ when drop_params is set

Fable 5, Opus 4.7, and Opus 4.8 removed sampling params: the API rejects
top_p, top_k, and any temperature other than 1 with a 400. LiteLLM was
forwarding them even with drop_params enabled because the Anthropic and
Bedrock converse transformations passed temperature/top_p through
unconditionally.

Mirror the GPT-5/o-series handling: temperature=1 still passes through,
other values and any top_p are dropped when drop_params is set, and
without drop_params a clean client-side UnsupportedParamsError tells the
caller how to opt in, instead of surfacing the raw provider error.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Drive sampling param gating from the cost map and cover top_k

Greptile review follow-ups on the sampling param fix: the restriction for
Fable 5 / Opus 4.7 / 4.8 is now declared as supports_sampling_params: false
on every affected cost map entry (perplexity excluded; that route is
OpenAI-compatible and maps sampling params upstream) and read back through
a tri-state map lookup, keeping the name check only as a fallback for
provider-routed ids whose hosted map entries predate the flag, the same
layering supports_adaptive_thinking uses. top_k bypasses map_openai_params
as a provider-specific kwarg, so it is gated at the shared
AnthropicConfig.transform_request boundary (direct, Bedrock invoke, Vertex,
Azure) and in the Bedrock converse _handle_top_k_value path, with
drop_params threaded through the converse transform helpers.

Also updates the reasoning effort grid cell count assertion for the four
Fable 5 rows added on this branch (29 x 11 cells).

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Declare supports_sampling_params in the cost map schema

The model map validation schema uses additionalProperties: false, so the
new flag must be declared for the 28 entries that carry it; this was the
one failing job (misc / Run tests) on the previous commit.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* fix(bedrock): gate top_k=0 on converse to match Anthropic boundary

Truthiness check let top_k=0 silently disappear on models that removed
sampling params, while AnthropicConfig.transform_request treats 0 as
present and raises UnsupportedParamsError (or drops when drop_params is
set). Switch to 'is not None' so converse, direct Anthropic, invoke,
Vertex, and Azure all behave the same for top_k=0.

---------

Co-authored-by: Cursor Agent <[email protected]>

* fix(proxy): coerce litellm_settings.max_budget env var to float

When max_budget is set in litellm_settings via os.environ/MAX_BUDGET,
the env var resolves to a string and the generic setattr branch in
ProxyConfig.load_config stored it as-is, so the startup check
litellm.max_budget > 0 raised TypeError. The earlier fix (#23855) only
covered the CLI initialize() path. Coerce the value to float in the
settings loop, matching the existing max_internal_user_budget handling.

Fixes #26696.

---------

Co-authored-by: milan-berri <[email protected]>
Co-authored-by: Cursor <[email protected]>
Co-authored-by: ryan-crabbe-berri <[email protected]>
Co-authored-by: michelligabriele <[email protected]>
Co-authored-by: tin-berri <[email protected]>
Co-authored-by: yuneng-jiang <[email protected]>
Co-authored-by: stuxf <[email protected]>
Co-authored-by: Sameer Kankute <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>
Co-authored-by: Mateo Wang <[email protected]>

…omits output_item.added (#30115)

* fix(team): reserve team budget raises for proxy admins on /team/update (#30030)

The caller's PERSONAL max_budget was the wrong yardstick for /team/update: a
team's spend ceiling has nothing to do with the admin's own key budget. That
comparison was an unintended side effect of reusing _check_user_team_limits()
(which exists for the /team/new path) and broke the UI, which re-sends the
unchanged budget on every save.

New behavior on /team/update for standalone teams:
- A team admin (already authorized via _verify_team_access) may freely KEEP or
  LOWER the team budget, and change models/tpm/rpm, without being gated by their
  personal limits.
- GROWING a team's spend ceiling is a budget-authority action reserved for proxy
  admins -> 403 for team admins. "Growing" covers both raising max_budget above
  the team's current finite value and removing the cap entirely (max_budget=null,
  detected via model_fields_set so an explicit null is distinguished from an
  omitted field). For a team that currently has no cap, setting a finite value is
  a restriction and is allowed.
- Org-scoped teams remain governed by _check_org_team_limits() (capped by the
  org budget).

Also reverts the #29525 existing_team_max_budget workaround in
_check_user_team_limits() back to the create-only form; /team/new still enforces
the creator's personal caps.

docs(access_control): resolve the contradiction in the team-admin section —
team admins can keep/lower the budget and manage rate limits/models, but cannot
raise the team budget (proxy-admin only).

tests: unit + behavior coverage for raise-blocked, cap-removal-blocked (team
admin), raise/removal allowed (proxy admin), uncapped-team restriction allowed,
keep/lower/resend allowed, and unchanged create-path guards.

Co-authored-by: Cursor <[email protected]>

* test(ui): data-driven App Router migration E2E smoke (default + server-root-path) (#29974)

* test(ui): add a data-driven App Router migration E2E smoke

Add a growing Playwright smoke for migrated pages: for each segment it deep-links
to the path route, asserts the URL and that the dashboard shell rendered, then
clicks off to a legacy page and asserts navigation still works. Driven by
e2e_tests/fixtures/migratedPages.ts, so adding a page is one line.

Runs in two situations against the same proxy: the default mount (npm run
e2e:migration) and a non-root SERVER_ROOT_PATH mount (npm run e2e:migration:root).
globalSetup now logs in at `${SERVER_ROOT_PATH}/ui/login` so the admin storage
state is valid under a prefix. Seeded with api-reference; append the rest as their
migrations merge.

* test(ui): support headed slow-motion + watch pauses in the migration smoke

Honor SLOWMO in the server-root-path config (the default config already did),
and add an env-gated E2E_WATCH_MS pause so a headed run lingers on each state.
Both are no-ops by default, so CI behavior is unchanged.

* test(ui): make the migration smoke a sidebar-click user journey

Rework the smoke from deep-linking to a real navigation journey: start at the
landing page, click the migrated page in the sidebar (expanding submenus for
nested items), assert the path route rendered, reload it (the check a wrong
server_root_path breaks), bounce to a legacy page and back, and — once two pages
are migrated — navigate directly between two migrated pages. Verifies via URL +
shell render, driven by the same fixture list.

* test(ui): address review on the migration smoke

Escape ROOT and segment before interpolating them into RegExp URL matchers so a
future segment containing regex metacharacters can't silently widen the match.
Make the server-root-path config fail fast when SERVER_ROOT_PATH is unset instead
of silently re-running the default mount and passing without exercising the prefix.

* test(ui): drop unused watch helper and fix stale smoke README

* test(ui): run the migration smoke under a server root path in CI

* test(ui): harden + instrument the server-root-path proxy reboot in CI

* test(ui): run the server-root-path migration smoke as its own CI job

Replace the in-place proxy reboot in e2e_ui_testing with a dedicated
e2e_ui_testing_server_root_path job that boots the proxy once with
SERVER_ROOT_PATH=/litellm, matching how every other proxy variant in the
config gets its own job rather than killing and relaunching the live proxy.

The reboot was failing deterministically: after pkill -9 and relaunch the
prefixed proxy never came back up on :4000 (connection refused), so the smoke
never ran. The readiness step that was supposed to surface the cause could
never reach its boot-log tail because CircleCI runs steps under bash -eo
pipefail and the preceding `curl -sv ... | tail` aborted the step with curl's
exit 7. Booting the proxy as the job's own background step lets any boot crash
land in that step's log instead of being swallowed.

The default e2e_ui_testing job is unchanged aside from dropping the reboot,
prefixed-readiness, and prefixed-smoke steps; the migration smoke still runs at
the root mount there via the default Playwright config.

* fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through (#24232)

* fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through

* test: mock post_call_response_headers_hook in audio speech route tests

* chore(ui): remove dead App Router route stubs under (dashboard) (#30045)

models-and-endpoints, organizations, and virtual-keys each had a page.tsx
route under (dashboard)/ that is not in MIGRATED_PAGES, so the sidebar and
deep links never resolve to it and the route is unreachable. Each was a thin
wrapper that handed the shared view empty or no-op props (empty modelData with
a no-op setModelData, hardcoded empty organizations, no-op
setUserRole/setUserEmail), so reaching one would render a degraded page in any
case. The real wrapper belongs in the PR that flips each page into
MIGRATED_PAGES, written with eyes on it and a test

This continues the dead-scaffolding cleanup from #28891. The shared components
these wrappers rendered (ModelsAndEndpointsView, OrganizationFilters) stay,
since the legacy ?page= switch in app/page.tsx and src/components still import
them

* fix(ui/mcp): reset OAuth state on create-server modal close so a prior server's token no longer leaks into the next add-server session (#30000)

* fix(ui/mcp): reset OAuth hook state on modal close so a prior server's token no longer leaks into the next add-server session

* fix(ui/mcp): clear in-flight OAuth guard on reset and reset form/tools on modal close so nothing leaks on a parent-driven dismiss

* fix(mcp): allow team access-group grants in OAuth authorize/token access check (#30041)

* fix(mcp): honor team access-group grants in OAuth authorize/token access check

* test(mcp): mock build_effective_auth_contexts in non-admin authorize tests for isolation

* docs(security): require a reproduction video for vulnerability reports (#30048) (#30063)

With AI models capable of automated vulnerability discovery now publicly
available, we expect a large increase in report volume, much of it
unverified. Requiring a video of the exploit running against a live
instance raises the bar for submissions and keeps triage focused on
reproducible issues. Reports without a video will be closed and reopened
if one is added later.

Co-authored-by: stuxf <[email protected]>

* feat(ui): add admin flag to disable in-product UI nudges for everyone (#29796)

* feat(ui): add admin flag to disable in-product UI nudges for everyone

Admins can now suppress the survey and Claude Code feedback popups for
all users via a single disable_ui_nudges UI setting, instead of relying
on each user dismissing them individually.

* fix(ui): suppress nudges while ui settings are loading

Gate nudgesDisabled on the ui-settings loading state so an admin with
disable_ui_nudges on doesn't see the survey prompt flash, and the
getInProductNudgesCall fetch doesn't fire, on a cold page load before
the flag resolves. Falls back to showing nudges if the fetch errors.

* test(ui): wrap CreateKeyPage test in QueryClientProvider

page.tsx now calls useUISettings (react-query), which needs a
QueryClient that layout.tsx supplies in production but the test did
not. Add the provider and mock getUiSettings so the query resolves.

* chore(ui): remove dead dashboard files and unused dependencies (#30047)

* chore(ui): remove dead dashboard files and unused dependencies

knip flagged seven orphaned source/config files with no importers and
five declared dependencies that nothing in the tree uses. Removing them
shrinks the dashboard bundle's source surface and keeps the manifest
honest; vite stays installed transitively via vitest, so test tooling is
unaffected.

* fix(ci): restore serverRootPath.config.ts referenced by SERVER_ROOT_PATH workflow

The dead-code sweep removed e2e_tests/serverRootPath.config.ts, but its spec
(tests/login/serverRootPathRedirect.spec.ts) and the test_server_root_path.yml
workflow step still depend on it, so the redirect e2e job failed to load a
config that no longer existed.

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593) (#30009)

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593)

After replace_model_in_jsonl, body.model is a stripped provider id. Reverse-mapping it via resolve_model_name_from_model_id is first-match on model_list and caused false 403s when multiple deployments share the same stripped name. Use target_model_names from the unified file id instead.

Co-authored-by: Cursor <[email protected]>

* fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)

Restores the reverse-lookup for the JSONL body.model fallback path so that
legacy/pre-target_model_names managed files still map stripped provider IDs
back to proxy aliases before auth. Also cleans up redundant `or None`.

Co-Authored-By: Claude Sonnet 4.6 <[email protected]>

* Revert "fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)"

This reverts commit 30d2e96.

---------

Co-authored-by: Cursor <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>

* Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI (#30064)

* Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI

Adds cost map entries for claude-fable-5 ($10/$50 per MTok, 1M context,
128K output, adaptive thinking only) on the Anthropic API, Bedrock
converse (base, global, and us/eu geo inference profiles at the 10%
regional premium), Vertex AI, and Azure AI (Microsoft Foundry, which
serves Fable 5 with the full 1M context window unlike Opus 4.8).

Registers anthropic.claude-fable-5 in BEDROCK_CONVERSE_MODELS, lists the
model in the setup wizard, and extends the reasoning effort e2e grid.
The Bedrock, Vertex, and Azure grid cells carry fail_reason markers
until the CI accounts are provisioned: Bedrock needs the provider data
sharing opt-in Fable 5 requires, and the Foundry resource needs a
claude-fable-5 deployment.

The first-party entry carries provider_specific_entry {us: 1.1} for the
inference_geo premium and deliberately no fast multiplier since Fable 5
has no fast mode.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Drop removed sampling params for Claude 4.7+ when drop_params is set

Fable 5, Opus 4.7, and Opus 4.8 removed sampling params: the API rejects
top_p, top_k, and any temperature other than 1 with a 400. LiteLLM was
forwarding them even with drop_params enabled because the Anthropic and
Bedrock converse transformations passed temperature/top_p through
unconditionally.

Mirror the GPT-5/o-series handling: temperature=1 still passes through,
other values and any top_p are dropped when drop_params is set, and
without drop_params a clean client-side UnsupportedParamsError tells the
caller how to opt in, instead of surfacing the raw provider error.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Drive sampling param gating from the cost map and cover top_k

Greptile review follow-ups on the sampling param fix: the restriction for
Fable 5 / Opus 4.7 / 4.8 is now declared as supports_sampling_params: false
on every affected cost map entry (perplexity excluded; that route is
OpenAI-compatible and maps sampling params upstream) and read back through
a tri-state map lookup, keeping the name check only as a fallback for
provider-routed ids whose hosted map entries predate the flag, the same
layering supports_adaptive_thinking uses. top_k bypasses map_openai_params
as a provider-specific kwarg, so it is gated at the shared
AnthropicConfig.transform_request boundary (direct, Bedrock invoke, Vertex,
Azure) and in the Bedrock converse _handle_top_k_value path, with
drop_params threaded through the converse transform helpers.

Also updates the reasoning effort grid cell count assertion for the four
Fable 5 rows added on this branch (29 x 11 cells).

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Declare supports_sampling_params in the cost map schema

The model map validation schema uses additionalProperties: false, so the
new flag must be declared for the 28 entries that carry it; this was the
one failing job (misc / Run tests) on the previous commit.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* fix(bedrock): gate top_k=0 on converse to match Anthropic boundary

Truthiness check let top_k=0 silently disappear on models that removed
sampling params, while AnthropicConfig.transform_request treats 0 as
present and raises UnsupportedParamsError (or drops when drop_params is
set). Switch to 'is not None' so converse, direct Anthropic, invoke,
Vertex, and Azure all behave the same for top_k=0.

---------

Co-authored-by: Cursor Agent <[email protected]>

* fix(anthropic): avoid index -1 content_block_delta in messages stream

When a /v1/messages request is routed through the Responses API
adapter, AnthropicResponsesStreamWrapper only emits content_block_start
on response.output_item.added. Some upstreams (LMStudio for example)
never send that event, so the text delta handler fell back to
_current_block_index, which starts at -1, and clients received
content_block_delta events with index -1 and no preceding
content_block_start. Anthropic SDKs then fail with "text part -1 not
found"

The text delta handler now synthesizes a content_block_start with a
fresh block index whenever the delta references an unregistered item_id
or no block is open yet, and registers the item_id so follow-up deltas
reuse the same index

Addresses the /v1/messages defect in #27442

* Make test sys.path shim resolve relative to the file, not the CWD

os.path.abspath("../../../../../../..") depends on where pytest is
invoked from; anchoring on os.path.dirname(__file__) makes the import
work from any working directory. Also corrects the depth: the repo root
is six levels above this file, not seven.

---------

Co-authored-by: milan-berri <[email protected]>
Co-authored-by: Cursor <[email protected]>
Co-authored-by: ryan-crabbe-berri <[email protected]>
Co-authored-by: michelligabriele <[email protected]>
Co-authored-by: tin-berri <[email protected]>
Co-authored-by: yuneng-jiang <[email protected]>
Co-authored-by: stuxf <[email protected]>
Co-authored-by: Sameer Kankute <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>
Co-authored-by: Mateo Wang <[email protected]>

…0114)

* fix(team): reserve team budget raises for proxy admins on /team/update (#30030)

The caller's PERSONAL max_budget was the wrong yardstick for /team/update: a
team's spend ceiling has nothing to do with the admin's own key budget. That
comparison was an unintended side effect of reusing _check_user_team_limits()
(which exists for the /team/new path) and broke the UI, which re-sends the
unchanged budget on every save.

New behavior on /team/update for standalone teams:
- A team admin (already authorized via _verify_team_access) may freely KEEP or
  LOWER the team budget, and change models/tpm/rpm, without being gated by their
  personal limits.
- GROWING a team's spend ceiling is a budget-authority action reserved for proxy
  admins -> 403 for team admins. "Growing" covers both raising max_budget above
  the team's current finite value and removing the cap entirely (max_budget=null,
  detected via model_fields_set so an explicit null is distinguished from an
  omitted field). For a team that currently has no cap, setting a finite value is
  a restriction and is allowed.
- Org-scoped teams remain governed by _check_org_team_limits() (capped by the
  org budget).

Also reverts the #29525 existing_team_max_budget workaround in
_check_user_team_limits() back to the create-only form; /team/new still enforces
the creator's personal caps.

docs(access_control): resolve the contradiction in the team-admin section —
team admins can keep/lower the budget and manage rate limits/models, but cannot
raise the team budget (proxy-admin only).

tests: unit + behavior coverage for raise-blocked, cap-removal-blocked (team
admin), raise/removal allowed (proxy admin), uncapped-team restriction allowed,
keep/lower/resend allowed, and unchanged create-path guards.

Co-authored-by: Cursor <[email protected]>

* test(ui): data-driven App Router migration E2E smoke (default + server-root-path) (#29974)

* test(ui): add a data-driven App Router migration E2E smoke

Add a growing Playwright smoke for migrated pages: for each segment it deep-links
to the path route, asserts the URL and that the dashboard shell rendered, then
clicks off to a legacy page and asserts navigation still works. Driven by
e2e_tests/fixtures/migratedPages.ts, so adding a page is one line.

Runs in two situations against the same proxy: the default mount (npm run
e2e:migration) and a non-root SERVER_ROOT_PATH mount (npm run e2e:migration:root).
globalSetup now logs in at `${SERVER_ROOT_PATH}/ui/login` so the admin storage
state is valid under a prefix. Seeded with api-reference; append the rest as their
migrations merge.

* test(ui): support headed slow-motion + watch pauses in the migration smoke

Honor SLOWMO in the server-root-path config (the default config already did),
and add an env-gated E2E_WATCH_MS pause so a headed run lingers on each state.
Both are no-ops by default, so CI behavior is unchanged.

* test(ui): make the migration smoke a sidebar-click user journey

Rework the smoke from deep-linking to a real navigation journey: start at the
landing page, click the migrated page in the sidebar (expanding submenus for
nested items), assert the path route rendered, reload it (the check a wrong
server_root_path breaks), bounce to a legacy page and back, and — once two pages
are migrated — navigate directly between two migrated pages. Verifies via URL +
shell render, driven by the same fixture list.

* test(ui): address review on the migration smoke

Escape ROOT and segment before interpolating them into RegExp URL matchers so a
future segment containing regex metacharacters can't silently widen the match.
Make the server-root-path config fail fast when SERVER_ROOT_PATH is unset instead
of silently re-running the default mount and passing without exercising the prefix.

* test(ui): drop unused watch helper and fix stale smoke README

* test(ui): run the migration smoke under a server root path in CI

* test(ui): harden + instrument the server-root-path proxy reboot in CI

* test(ui): run the server-root-path migration smoke as its own CI job

Replace the in-place proxy reboot in e2e_ui_testing with a dedicated
e2e_ui_testing_server_root_path job that boots the proxy once with
SERVER_ROOT_PATH=/litellm, matching how every other proxy variant in the
config gets its own job rather than killing and relaunching the live proxy.

The reboot was failing deterministically: after pkill -9 and relaunch the
prefixed proxy never came back up on :4000 (connection refused), so the smoke
never ran. The readiness step that was supposed to surface the cause could
never reach its boot-log tail because CircleCI runs steps under bash -eo
pipefail and the preceding `curl -sv ... | tail` aborted the step with curl's
exit 7. Booting the proxy as the job's own background step lets any boot crash
land in that step's log instead of being swallowed.

The default e2e_ui_testing job is unchanged aside from dropping the reboot,
prefixed-readiness, and prefixed-smoke steps; the migration smoke still runs at
the root mount there via the default Playwright config.

* fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through (#24232)

* fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through

* test: mock post_call_response_headers_hook in audio speech route tests

* chore(ui): remove dead App Router route stubs under (dashboard) (#30045)

models-and-endpoints, organizations, and virtual-keys each had a page.tsx
route under (dashboard)/ that is not in MIGRATED_PAGES, so the sidebar and
deep links never resolve to it and the route is unreachable. Each was a thin
wrapper that handed the shared view empty or no-op props (empty modelData with
a no-op setModelData, hardcoded empty organizations, no-op
setUserRole/setUserEmail), so reaching one would render a degraded page in any
case. The real wrapper belongs in the PR that flips each page into
MIGRATED_PAGES, written with eyes on it and a test

This continues the dead-scaffolding cleanup from #28891. The shared components
these wrappers rendered (ModelsAndEndpointsView, OrganizationFilters) stay,
since the legacy ?page= switch in app/page.tsx and src/components still import
them

* fix(ui/mcp): reset OAuth state on create-server modal close so a prior server's token no longer leaks into the next add-server session (#30000)

* fix(ui/mcp): reset OAuth hook state on modal close so a prior server's token no longer leaks into the next add-server session

* fix(ui/mcp): clear in-flight OAuth guard on reset and reset form/tools on modal close so nothing leaks on a parent-driven dismiss

* fix(mcp): allow team access-group grants in OAuth authorize/token access check (#30041)

* fix(mcp): honor team access-group grants in OAuth authorize/token access check

* test(mcp): mock build_effective_auth_contexts in non-admin authorize tests for isolation

* docs(security): require a reproduction video for vulnerability reports (#30048) (#30063)

With AI models capable of automated vulnerability discovery now publicly
available, we expect a large increase in report volume, much of it
unverified. Requiring a video of the exploit running against a live
instance raises the bar for submissions and keeps triage focused on
reproducible issues. Reports without a video will be closed and reopened
if one is added later.

Co-authored-by: stuxf <[email protected]>

* feat(ui): add admin flag to disable in-product UI nudges for everyone (#29796)

* feat(ui): add admin flag to disable in-product UI nudges for everyone

Admins can now suppress the survey and Claude Code feedback popups for
all users via a single disable_ui_nudges UI setting, instead of relying
on each user dismissing them individually.

* fix(ui): suppress nudges while ui settings are loading

Gate nudgesDisabled on the ui-settings loading state so an admin with
disable_ui_nudges on doesn't see the survey prompt flash, and the
getInProductNudgesCall fetch doesn't fire, on a cold page load before
the flag resolves. Falls back to showing nudges if the fetch errors.

* test(ui): wrap CreateKeyPage test in QueryClientProvider

page.tsx now calls useUISettings (react-query), which needs a
QueryClient that layout.tsx supplies in production but the test did
not. Add the provider and mock getUiSettings so the query resolves.

* chore(ui): remove dead dashboard files and unused dependencies (#30047)

* chore(ui): remove dead dashboard files and unused dependencies

knip flagged seven orphaned source/config files with no importers and
five declared dependencies that nothing in the tree uses. Removing them
shrinks the dashboard bundle's source surface and keeps the manifest
honest; vite stays installed transitively via vitest, so test tooling is
unaffected.

* fix(ci): restore serverRootPath.config.ts referenced by SERVER_ROOT_PATH workflow

The dead-code sweep removed e2e_tests/serverRootPath.config.ts, but its spec
(tests/login/serverRootPathRedirect.spec.ts) and the test_server_root_path.yml
workflow step still depend on it, so the redirect e2e job failed to load a
config that no longer existed.

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593) (#30009)

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593)

After replace_model_in_jsonl, body.model is a stripped provider id. Reverse-mapping it via resolve_model_name_from_model_id is first-match on model_list and caused false 403s when multiple deployments share the same stripped name. Use target_model_names from the unified file id instead.

Co-authored-by: Cursor <[email protected]>

* fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)

Restores the reverse-lookup for the JSONL body.model fallback path so that
legacy/pre-target_model_names managed files still map stripped provider IDs
back to proxy aliases before auth. Also cleans up redundant `or None`.

Co-Authored-By: Claude Sonnet 4.6 <[email protected]>

* Revert "fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)"

This reverts commit 30d2e96.

---------

Co-authored-by: Cursor <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>

* Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI (#30064)

* Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI

Adds cost map entries for claude-fable-5 ($10/$50 per MTok, 1M context,
128K output, adaptive thinking only) on the Anthropic API, Bedrock
converse (base, global, and us/eu geo inference profiles at the 10%
regional premium), Vertex AI, and Azure AI (Microsoft Foundry, which
serves Fable 5 with the full 1M context window unlike Opus 4.8).

Registers anthropic.claude-fable-5 in BEDROCK_CONVERSE_MODELS, lists the
model in the setup wizard, and extends the reasoning effort e2e grid.
The Bedrock, Vertex, and Azure grid cells carry fail_reason markers
until the CI accounts are provisioned: Bedrock needs the provider data
sharing opt-in Fable 5 requires, and the Foundry resource needs a
claude-fable-5 deployment.

The first-party entry carries provider_specific_entry {us: 1.1} for the
inference_geo premium and deliberately no fast multiplier since Fable 5
has no fast mode.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Drop removed sampling params for Claude 4.7+ when drop_params is set

Fable 5, Opus 4.7, and Opus 4.8 removed sampling params: the API rejects
top_p, top_k, and any temperature other than 1 with a 400. LiteLLM was
forwarding them even with drop_params enabled because the Anthropic and
Bedrock converse transformations passed temperature/top_p through
unconditionally.

Mirror the GPT-5/o-series handling: temperature=1 still passes through,
other values and any top_p are dropped when drop_params is set, and
without drop_params a clean client-side UnsupportedParamsError tells the
caller how to opt in, instead of surfacing the raw provider error.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Drive sampling param gating from the cost map and cover top_k

Greptile review follow-ups on the sampling param fix: the restriction for
Fable 5 / Opus 4.7 / 4.8 is now declared as supports_sampling_params: false
on every affected cost map entry (perplexity excluded; that route is
OpenAI-compatible and maps sampling params upstream) and read back through
a tri-state map lookup, keeping the name check only as a fallback for
provider-routed ids whose hosted map entries predate the flag, the same
layering supports_adaptive_thinking uses. top_k bypasses map_openai_params
as a provider-specific kwarg, so it is gated at the shared
AnthropicConfig.transform_request boundary (direct, Bedrock invoke, Vertex,
Azure) and in the Bedrock converse _handle_top_k_value path, with
drop_params threaded through the converse transform helpers.

Also updates the reasoning effort grid cell count assertion for the four
Fable 5 rows added on this branch (29 x 11 cells).

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Declare supports_sampling_params in the cost map schema

The model map validation schema uses additionalProperties: false, so the
new flag must be declared for the 28 entries that carry it; this was the
one failing job (misc / Run tests) on the previous commit.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* fix(bedrock): gate top_k=0 on converse to match Anthropic boundary

Truthiness check let top_k=0 silently disappear on models that removed
sampling params, while AnthropicConfig.transform_request treats 0 as
present and raises UnsupportedParamsError (or drops when drop_params is
set). Switch to 'is not None' so converse, direct Anthropic, invoke,
Vertex, and Azure all behave the same for top_k=0.

---------

Co-authored-by: Cursor Agent <[email protected]>

* fix: enable compact-2026-01-12 beta header for vertex_ai provider

The vertex_ai block in anthropic_beta_headers_config.json mapped
compact-2026-01-12 to null, so update_headers_with_filtered_beta
stripped the header before the request reached Vertex while the
compact_20260112 context edit stayed in the body, and Vertex rejected
the request with HTTP 400. Vertex rawPredict accepts the header, and
the bedrock and databricks blocks already forward it. Mirrors #21867,
which enabled context-1m-2025-08-07 for vertex_ai the same way.

Fixes #27290.

---------

Co-authored-by: milan-berri <[email protected]>
Co-authored-by: Cursor <[email protected]>
Co-authored-by: ryan-crabbe-berri <[email protected]>
Co-authored-by: michelligabriele <[email protected]>
Co-authored-by: tin-berri <[email protected]>
Co-authored-by: yuneng-jiang <[email protected]>
Co-authored-by: stuxf <[email protected]>
Co-authored-by: Sameer Kankute <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>
Co-authored-by: Mateo Wang <[email protected]>

* fix(team): reserve team budget raises for proxy admins on /team/update (#30030)

The caller's PERSONAL max_budget was the wrong yardstick for /team/update: a
team's spend ceiling has nothing to do with the admin's own key budget. That
comparison was an unintended side effect of reusing _check_user_team_limits()
(which exists for the /team/new path) and broke the UI, which re-sends the
unchanged budget on every save.

New behavior on /team/update for standalone teams:
- A team admin (already authorized via _verify_team_access) may freely KEEP or
  LOWER the team budget, and change models/tpm/rpm, without being gated by their
  personal limits.
- GROWING a team's spend ceiling is a budget-authority action reserved for proxy
  admins -> 403 for team admins. "Growing" covers both raising max_budget above
  the team's current finite value and removing the cap entirely (max_budget=null,
  detected via model_fields_set so an explicit null is distinguished from an
  omitted field). For a team that currently has no cap, setting a finite value is
  a restriction and is allowed.
- Org-scoped teams remain governed by _check_org_team_limits() (capped by the
  org budget).

Also reverts the #29525 existing_team_max_budget workaround in
_check_user_team_limits() back to the create-only form; /team/new still enforces
the creator's personal caps.

docs(access_control): resolve the contradiction in the team-admin section —
team admins can keep/lower the budget and manage rate limits/models, but cannot
raise the team budget (proxy-admin only).

tests: unit + behavior coverage for raise-blocked, cap-removal-blocked (team
admin), raise/removal allowed (proxy admin), uncapped-team restriction allowed,
keep/lower/resend allowed, and unchanged create-path guards.

Co-authored-by: Cursor <[email protected]>

* test(ui): data-driven App Router migration E2E smoke (default + server-root-path) (#29974)

* test(ui): add a data-driven App Router migration E2E smoke

Add a growing Playwright smoke for migrated pages: for each segment it deep-links
to the path route, asserts the URL and that the dashboard shell rendered, then
clicks off to a legacy page and asserts navigation still works. Driven by
e2e_tests/fixtures/migratedPages.ts, so adding a page is one line.

Runs in two situations against the same proxy: the default mount (npm run
e2e:migration) and a non-root SERVER_ROOT_PATH mount (npm run e2e:migration:root).
globalSetup now logs in at `${SERVER_ROOT_PATH}/ui/login` so the admin storage
state is valid under a prefix. Seeded with api-reference; append the rest as their
migrations merge.

* test(ui): support headed slow-motion + watch pauses in the migration smoke

Honor SLOWMO in the server-root-path config (the default config already did),
and add an env-gated E2E_WATCH_MS pause so a headed run lingers on each state.
Both are no-ops by default, so CI behavior is unchanged.

* test(ui): make the migration smoke a sidebar-click user journey

Rework the smoke from deep-linking to a real navigation journey: start at the
landing page, click the migrated page in the sidebar (expanding submenus for
nested items), assert the path route rendered, reload it (the check a wrong
server_root_path breaks), bounce to a legacy page and back, and — once two pages
are migrated — navigate directly between two migrated pages. Verifies via URL +
shell render, driven by the same fixture list.

* test(ui): address review on the migration smoke

Escape ROOT and segment before interpolating them into RegExp URL matchers so a
future segment containing regex metacharacters can't silently widen the match.
Make the server-root-path config fail fast when SERVER_ROOT_PATH is unset instead
of silently re-running the default mount and passing without exercising the prefix.

* test(ui): drop unused watch helper and fix stale smoke README

* test(ui): run the migration smoke under a server root path in CI

* test(ui): harden + instrument the server-root-path proxy reboot in CI

* test(ui): run the server-root-path migration smoke as its own CI job

Replace the in-place proxy reboot in e2e_ui_testing with a dedicated
e2e_ui_testing_server_root_path job that boots the proxy once with
SERVER_ROOT_PATH=/litellm, matching how every other proxy variant in the
config gets its own job rather than killing and relaunching the live proxy.

The reboot was failing deterministically: after pkill -9 and relaunch the
prefixed proxy never came back up on :4000 (connection refused), so the smoke
never ran. The readiness step that was supposed to surface the cause could
never reach its boot-log tail because CircleCI runs steps under bash -eo
pipefail and the preceding `curl -sv ... | tail` aborted the step with curl's
exit 7. Booting the proxy as the job's own background step lets any boot crash
land in that step's log instead of being swallowed.

The default e2e_ui_testing job is unchanged aside from dropping the reboot,
prefixed-readiness, and prefixed-smoke steps; the migration smoke still runs at
the root mount there via the default Playwright config.

* fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through (#24232)

* fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through

* test: mock post_call_response_headers_hook in audio speech route tests

* chore(ui): remove dead App Router route stubs under (dashboard) (#30045)

models-and-endpoints, organizations, and virtual-keys each had a page.tsx
route under (dashboard)/ that is not in MIGRATED_PAGES, so the sidebar and
deep links never resolve to it and the route is unreachable. Each was a thin
wrapper that handed the shared view empty or no-op props (empty modelData with
a no-op setModelData, hardcoded empty organizations, no-op
setUserRole/setUserEmail), so reaching one would render a degraded page in any
case. The real wrapper belongs in the PR that flips each page into
MIGRATED_PAGES, written with eyes on it and a test

This continues the dead-scaffolding cleanup from #28891. The shared components
these wrappers rendered (ModelsAndEndpointsView, OrganizationFilters) stay,
since the legacy ?page= switch in app/page.tsx and src/components still import
them

* fix(ui/mcp): reset OAuth state on create-server modal close so a prior server's token no longer leaks into the next add-server session (#30000)

* fix(ui/mcp): reset OAuth hook state on modal close so a prior server's token no longer leaks into the next add-server session

* fix(ui/mcp): clear in-flight OAuth guard on reset and reset form/tools on modal close so nothing leaks on a parent-driven dismiss

* fix(mcp): allow team access-group grants in OAuth authorize/token access check (#30041)

* fix(mcp): honor team access-group grants in OAuth authorize/token access check

* test(mcp): mock build_effective_auth_contexts in non-admin authorize tests for isolation

* docs(security): require a reproduction video for vulnerability reports (#30048) (#30063)

With AI models capable of automated vulnerability discovery now publicly
available, we expect a large increase in report volume, much of it
unverified. Requiring a video of the exploit running against a live
instance raises the bar for submissions and keeps triage focused on
reproducible issues. Reports without a video will be closed and reopened
if one is added later.

Co-authored-by: stuxf <[email protected]>

* feat(ui): add admin flag to disable in-product UI nudges for everyone (#29796)

* feat(ui): add admin flag to disable in-product UI nudges for everyone

Admins can now suppress the survey and Claude Code feedback popups for
all users via a single disable_ui_nudges UI setting, instead of relying
on each user dismissing them individually.

* fix(ui): suppress nudges while ui settings are loading

Gate nudgesDisabled on the ui-settings loading state so an admin with
disable_ui_nudges on doesn't see the survey prompt flash, and the
getInProductNudgesCall fetch doesn't fire, on a cold page load before
the flag resolves. Falls back to showing nudges if the fetch errors.

* test(ui): wrap CreateKeyPage test in QueryClientProvider

page.tsx now calls useUISettings (react-query), which needs a
QueryClient that layout.tsx supplies in production but the test did
not. Add the provider and mock getUiSettings so the query resolves.

* chore(ui): remove dead dashboard files and unused dependencies (#30047)

* chore(ui): remove dead dashboard files and unused dependencies

knip flagged seven orphaned source/config files with no importers and
five declared dependencies that nothing in the tree uses. Removing them
shrinks the dashboard bundle's source surface and keeps the manifest
honest; vite stays installed transitively via vitest, so test tooling is
unaffected.

* fix(ci): restore serverRootPath.config.ts referenced by SERVER_ROOT_PATH workflow

The dead-code sweep removed e2e_tests/serverRootPath.config.ts, but its spec
(tests/login/serverRootPathRedirect.spec.ts) and the test_server_root_path.yml
workflow step still depend on it, so the redirect e2e job failed to load a
config that no longer existed.

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593) (#30009)

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593)

After replace_model_in_jsonl, body.model is a stripped provider id. Reverse-mapping it via resolve_model_name_from_model_id is first-match on model_list and caused false 403s when multiple deployments share the same stripped name. Use target_model_names from the unified file id instead.

Co-authored-by: Cursor <[email protected]>

* fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)

Restores the reverse-lookup for the JSONL body.model fallback path so that
legacy/pre-target_model_names managed files still map stripped provider IDs
back to proxy aliases before auth. Also cleans up redundant `or None`.

Co-Authored-By: Claude Sonnet 4.6 <[email protected]>

* Revert "fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)"

This reverts commit 30d2e96.

---------

Co-authored-by: Cursor <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>

* Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI (#30064)

* Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI

Adds cost map entries for claude-fable-5 ($10/$50 per MTok, 1M context,
128K output, adaptive thinking only) on the Anthropic API, Bedrock
converse (base, global, and us/eu geo inference profiles at the 10%
regional premium), Vertex AI, and Azure AI (Microsoft Foundry, which
serves Fable 5 with the full 1M context window unlike Opus 4.8).

Registers anthropic.claude-fable-5 in BEDROCK_CONVERSE_MODELS, lists the
model in the setup wizard, and extends the reasoning effort e2e grid.
The Bedrock, Vertex, and Azure grid cells carry fail_reason markers
until the CI accounts are provisioned: Bedrock needs the provider data
sharing opt-in Fable 5 requires, and the Foundry resource needs a
claude-fable-5 deployment.

The first-party entry carries provider_specific_entry {us: 1.1} for the
inference_geo premium and deliberately no fast multiplier since Fable 5
has no fast mode.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Drop removed sampling params for Claude 4.7+ when drop_params is set

Fable 5, Opus 4.7, and Opus 4.8 removed sampling params: the API rejects
top_p, top_k, and any temperature other than 1 with a 400. LiteLLM was
forwarding them even with drop_params enabled because the Anthropic and
Bedrock converse transformations passed temperature/top_p through
unconditionally.

Mirror the GPT-5/o-series handling: temperature=1 still passes through,
other values and any top_p are dropped when drop_params is set, and
without drop_params a clean client-side UnsupportedParamsError tells the
caller how to opt in, instead of surfacing the raw provider error.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Drive sampling param gating from the cost map and cover top_k

Greptile review follow-ups on the sampling param fix: the restriction for
Fable 5 / Opus 4.7 / 4.8 is now declared as supports_sampling_params: false
on every affected cost map entry (perplexity excluded; that route is
OpenAI-compatible and maps sampling params upstream) and read back through
a tri-state map lookup, keeping the name check only as a fallback for
provider-routed ids whose hosted map entries predate the flag, the same
layering supports_adaptive_thinking uses. top_k bypasses map_openai_params
as a provider-specific kwarg, so it is gated at the shared
AnthropicConfig.transform_request boundary (direct, Bedrock invoke, Vertex,
Azure) and in the Bedrock converse _handle_top_k_value path, with
drop_params threaded through the converse transform helpers.

Also updates the reasoning effort grid cell count assertion for the four
Fable 5 rows added on this branch (29 x 11 cells).

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Declare supports_sampling_params in the cost map schema

The model map validation schema uses additionalProperties: false, so the
new flag must be declared for the 28 entries that carry it; this was the
one failing job (misc / Run tests) on the previous commit.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* fix(bedrock): gate top_k=0 on converse to match Anthropic boundary

Truthiness check let top_k=0 silently disappear on models that removed
sampling params, while AnthropicConfig.transform_request treats 0 as
present and raises UnsupportedParamsError (or drops when drop_params is
set). Switch to 'is not None' so converse, direct Anthropic, invoke,
Vertex, and Azure all behave the same for top_k=0.

---------

Co-authored-by: Cursor Agent <[email protected]>

* fix(proxy): coerce litellm_settings.max_budget env var to float

When max_budget is set in litellm_settings via os.environ/MAX_BUDGET,
the env var resolves to a string and the generic setattr branch in
ProxyConfig.load_config stored it as-is, so the startup check
litellm.max_budget > 0 raised TypeError. The earlier fix (#23855) only
covered the CLI initialize() path. Coerce the value to float in the
settings loop, matching the existing max_internal_user_budget handling.

Fixes #26696.

---------

Co-authored-by: milan-berri <[email protected]>
Co-authored-by: Cursor <[email protected]>
Co-authored-by: ryan-crabbe-berri <[email protected]>
Co-authored-by: michelligabriele <[email protected]>
Co-authored-by: tin-berri <[email protected]>
Co-authored-by: yuneng-jiang <[email protected]>
Co-authored-by: stuxf <[email protected]>
Co-authored-by: Sameer Kankute <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>
Co-authored-by: Mateo Wang <[email protected]>

* fix(mcp): report scoped server name during initialize (#29865)

* fix mcp scoped server name

* Update litellm/proxy/_experimental/mcp_server/mcp_context.py

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* test(mcp): cover scoped server name in the SSE initialize handler

---------

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* fix(ui): show all session logs in the drawer, not just the first 50 (#29795)

* fix(ui): show newest session logs first

* test(ui): keep session log pagination coverage

* fix(ui): show all session logs in the drawer, not just the first page

The session detail drawer fetched session logs via sessionSpendLogsCall
without page/page_size, so it only ever received the backend default of one
page (50 rows). Sessions with more than 50 calls had the rest unreachable in
the UI (#29153).

sessionSpendLogsCall now takes page/page_size, and the drawer fetches the
first page, reads total_pages, then fetches the remaining pages and
accumulates them before the existing client-side sort. This keeps the single
continuous list (and the selected-log lookup and keyboard navigation, which
all assume the full session) correct. Fetching is bounded by a page cap, and
the sidebar shows a "showing most recent N" note if a session exceeds it.

The rows are lightweight metadata (the endpoint excludes messages/response),
so the full set is small; request/response bodies are still loaded per log on
demand.

* fix(ui): default session drawer to most recent log, newest first

Open a session with its most recent log selected, and order the sidebar
newest-first to match the all-sessions logs overview. MCP calls stay
grouped last. The latest log by time is computed explicitly, since the
MCP grouping means it is not always the first row.

* Apply fetching pages in batches suggestion from @greptile-apps[bot]

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* fix(ui): derive session total from accumulated rows when backend omits it

Compute the session total after all pages are fetched, falling back to the
accumulated row count rather than the first page's. Guards the truncation
note against a backend response that omits total but spans multiple pages.

---------

Co-authored-by: Yufeng He <[email protected]>
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* fix(proxy): handle Mistral multipart passthrough (#29927)

* fix(proxy): handle Mistral multipart passthrough

* chore: satisfy passthrough ci formatting

* test(proxy): cover Mistral passthrough in CI shard

* fix(vertex_ai): use REP host for context caching on eu/us multi-region endpoints (#29573)

Context caching built the cachedContents URL as
https://{location}-aiplatform.googleapis.com, which is an invalid host for the
eu/us multi-region endpoints and returns 404. The inference path already
resolves these to the REP host (https://aiplatform.{geo}.rep.googleapis.com)
via get_vertex_base_url(); reuse that helper in
_get_token_and_url_context_caching so caching uses the same host as inference.

Adds tests covering the eu/us multi-region cachedContents URLs (v1 and
v1beta1).

Fixes #29571

* Support per-model encrypted content affinity config (#29760)

Co-authored-by: shin-berri <[email protected]>
Co-authored-by: yuneng-jiang <[email protected]>

* fix: propagate upstream status code in proxy API exception handler (#29402)

* fix: propagate upstream status code in proxy API exception handler

When Google GenAI / Vertex returns a 404 for deprecated or missing
models via streamGenerateContent, the exception was falling through to
a generic handler that defaulted to 500. Now provider exceptions
carrying a valid HTTP status_code correctly propagate it through to
the ProxyException.

* fix: apply black formatting to common_request_processing.py

* fix: tighten status code range to 400-599 and deduplicate ProxyException raise

* fix(tests): use valid vertex_location in context caching tests

Replace "test_location" (contains underscore) with "us-central1" so tests
pass the regex validation added in get_vertex_base_url().

Co-Authored-By: Claude Sonnet 4.6 <[email protected]>

* feat(sdk): add xAI OAuth provider (#29866)

* Add xAI OAuth provider

* Update oauth.py

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* Fix xAI OAuth CI failures

* Add xAI OAuth coverage tests

* Move xAI OAuth coverage tests to core utils

* Address xAI OAuth review comments

* Prevent xAI OAuth api_base token exfiltration

* Treat blank xAI OAuth api keys as absent

* Wrap invalid xAI OAuth JSON responses

* Use xAI OAuth behind explicit flag

---------

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* fix(proxy) #27734 allow clearing budget_duration and team_member fields by sending null on /key/update and /team/update (#27751)

* fix(proxy): allow clearing budget_duration and team_member fields by sending null on /key/update and /team/update

Fixes #27734

Sending null for budget_duration, team_member_budget,
team_member_budget_duration, team_member_rpm_limit, or
team_member_tpm_limit via /key/update or /team/update returned 200 OK
but silently ignored the null value. The fields remained unchanged in
the database.

Root causes:
- /key/update: prepare_key_update_data() popped budget_duration from the
  update dict but never re-added it (or budget_reset_at) when the value
  was None.
- /team/update: _set_budget_reset_at() only acted when budget_duration
  was non-None, leaving a stale budget_reset_at in the DB.
- /team/update: team_member_* null values bypassed the budget table
  update entirely because should_create_budget() requires at least one
  non-None field.

* test(proxy): cover no-budget-row path in clear_team_member_budget_fields

* fix(presidio): unmask PII tokens in Anthropic native SSE streaming bytes (#30028)

* fix(presidio): unmask PII tokens in Anthropic native SSE streaming bytes

When output_parse_pii=true on the Anthropic native path (anthropic/claude-*),
response chunks arrive as raw bytes in SSE format. _stream_pii_unmasking was
yielding those bytes unchanged, so <PERSON_1> tokens were never replaced with
the original values before reaching the caller.

Add _unmask_sse_bytes_chunk to parse each data: line, find content_block_delta
/ text_delta events, and apply _unmask_pii_text before re-encoding. Wire it
into _stream_pii_unmasking so bytes chunks are unmasked when pii_tokens exist.

* fix(presidio): handle CRLF line endings and non-ASCII PII in SSE unmask

Strip trailing \r before the [DONE] guard so CRLF-terminated SSE chunks
don't bypass it and silently swallow a JSONDecodeError. Add
ensure_ascii=False to json.dumps so non-ASCII replacement values like
accented names are preserved as UTF-8 on the wire rather than being
\uXXXX-escaped. Add regression tests for both cases.

* feat(bedrock_mantle): path-aware Responses routing (/v1/responses vs /openai/v1/responses) (#29925)

* feat(bedrock_mantle): path-aware Responses routing (/v1/responses vs /openai/v1/responses)

Bedrock Mantle serves the Responses API on two upstream paths:
  - gpt frontier models (gpt-5.5 / gpt-5.4) on /openai/v1/responses
  - every other Responses-capable model (e.g. gpt-oss) on the standard /v1/responses

BedrockMantleResponsesAPIConfig gains a `use_openai_path` flag; the provider gate in
utils.py picks the path per model: openai.gpt-* (non gpt-oss) -> /openai/v1/responses;
any model declared mode=responses (price-map entry or user model_info) -> /v1/responses;
everything else returns None and keeps the existing chat-completions emulation.

Adds gpt-5.5 / gpt-5.4 price-map entries, registry wiring, and the routing-matrix tests.

* feat(bedrock_mantle): data-driven frontier routing via use_openai_responses_path

Addresses the Greptile review point that frontier detection should be a
price-map field rather than a hardcoded name match. The gate now routes a
model to /openai/v1/responses when its price-map entry declares
use_openai_responses_path, so a frontier model whose name does not follow the
openai.gpt- convention can be onboarded by JSON alone. The name-convention
check is kept as a fallback that needs no price-map entry, which preserves
zero-change routing for a future gpt-6 before its entry loads. gpt-5.5 / gpt-5.4
get the flag in both price maps. Adds tests for the data-driven flag path and
for the flag presence on the gpt-5.x entries; both branches are mutation-tested.

* test(model_prices): allow use_openai_responses_path in price-map schema

The model_prices_and_context_window.json schema validator
(test_aaamodel_prices_and_context_window_json_is_valid) enforces
additionalProperties: false, so the new use_openai_responses_path flag on the
gpt-5.5 / gpt-5.4 entries failed validation. Add it to the schema as a boolean,
alongside the other supports_* / capability flags.

* Add Tensormesh serverless models to the model cost map (#30037)

* Add Tensormesh serverless models to the model cost map

* Flag reasoning support on the Tensormesh models that expose thinking mode

* fix(proxy): invalidate stale key spend counter after budget reset or manual spend update (#30001)

* fix(proxy): reconcile stale key spend counter after budget reset

* fix(proxy): invalidate stale key spend counter after budget reset or manual spend update

* fix(proxy): remove read-time stale counter reconciliation to prevent budget bypass

* revert: undo unrelated formatting changes in enterprise directory

* test(proxy): add unit test for key spend update invalidating counter

* test(proxy): fix mocked update_data and hash token expectations in unit test

* fix(proxy): use Responses-API transformer in pass-through cost tracking (#29728)

The `elif is_responses:` branch of `openai_passthrough_handler` was
calling the chat-completions `transform_response` on a Responses API
payload. The chat-completions transformer expects `choices: [...]`
in the raw response; the Responses API uses `output: [...]` and
`usage.input_tokens` / `usage.output_tokens` (not
`prompt_tokens` / `completion_tokens`). The result was a
KeyError 'choices' deep inside `convert_to_model_response_object`,
swallowed by the surrounding `except Exception` in the handler, and
the SpendLogs row was written by the fallback path with zeroed-out
tokens, spend, and model.

This bug silently undercounts cost for every successful pass-through
call to either OpenAI's `/v1/responses` or Azure's
`/openai/v1/responses` (deployments configured for the Responses
API). Reproduced 2026-06-04 against a real Azure OpenAI Responses
API deployment proxied through LiteLLM v1.88.0.

Fix: use the dedicated
`OpenAIResponsesAPIConfig.transform_response_api_response` for the
Responses branch. This transformer already exists in LiteLLM
(`litellm/llms/openai/responses/transformation.py`) and knows the
Responses-API on-the-wire shape. `litellm.completion_cost` already
handles `ResponsesAPIResponse` natively with `call_type="responses"`,
so no downstream changes are needed.

Tests:

  test_responses_api_uses_responses_transformer_not_chat_completions
    NEW. Real regression test — exercises the openai_passthrough_handler
    with a real-shaped Responses payload (no `choices`, has `output`
    and Responses-API `usage` keys) and NO mocked `get_provider_config`.
    Pre-fix: raises KeyError 'choices' inside the chat-completions
    transformer (the bug). Post-fix: returns a ResponsesAPIResponse,
    completion_cost is called with call_type="responses" and a
    ResponsesAPIResponse instance (asserted).
    Verified to fail on un-fixed handler + pass on fixed handler
    before commit.

  test_responses_api_cost_tracking
    UPDATED. Old test mocked `get_provider_config` (no longer called
    in the responses branch post-fix). Now mocks the Responses
    transformer directly (`OpenAIResponsesAPIConfig.transform_response_api_response`)
    to test the downstream cost-calc contract.

Out of scope for this PR (separate followup):
  - Recognizing *.cognitiveservices.azure.com (the newer Azure
    OpenAI hostname) in the is_openai_*_route checks. Separate PR.

Co-authored-by: shin-berri <[email protected]>
Co-authored-by: yuneng-jiang <[email protected]>

* fix(skills): execute DB skills by matching the litellm_skill_ tool name prefix (#30116)

Skill IDs are generated as litellm_skill_<uuid> and the model-facing
tool name is the sanitized skill ID, but the post-call execution gates
in SkillsInjectionHook only ran tools whose name starts with "skill_",
so DB skills were silently returned to the client as raw tool calls.

Fixes #28122.

Co-authored-by: Cursor <[email protected]>

* fix(anthropic): synthesize content_block_start when Responses stream omits output_item.added (#30115)

* fix(team): reserve team budget raises for proxy admins on /team/update (#30030)

The caller's PERSONAL max_budget was the wrong yardstick for /team/update: a
team's spend ceiling has nothing to do with the admin's own key budget. That
comparison was an unintended side effect of reusing _check_user_team_limits()
(which exists for the /team/new path) and broke the UI, which re-sends the
unchanged budget on every save.

New behavior on /team/update for standalone teams:
- A team admin (already authorized via _verify_team_access) may freely KEEP or
  LOWER the team budget, and change models/tpm/rpm, without being gated by their
  personal limits.
- GROWING a team's spend ceiling is a budget-authority action reserved for proxy
  admins -> 403 for team admins. "Growing" covers both raising max_budget above
  the team's current finite value and removing the cap entirely (max_budget=null,
  detected via model_fields_set so an explicit null is distinguished from an
  omitted field). For a team that currently has no cap, setting a finite value is
  a restriction and is allowed.
- Org-scoped teams remain governed by _check_org_team_limits() (capped by the
  org budget).

Also reverts the #29525 existing_team_max_budget workaround in
_check_user_team_limits() back to the create-only form; /team/new still enforces
the creator's personal caps.

docs(access_control): resolve the contradiction in the team-admin section —
team admins can keep/lower the budget and manage rate limits/models, but cannot
raise the team budget (proxy-admin only).

tests: unit + behavior coverage for raise-blocked, cap-removal-blocked (team
admin), raise/removal allowed (proxy admin), uncapped-team restriction allowed,
keep/lower/resend allowed, and unchanged create-path guards.

Co-authored-by: Cursor <[email protected]>

* test(ui): data-driven App Router migration E2E smoke (default + server-root-path) (#29974)

* test(ui): add a data-driven App Router migration E2E smoke

Add a growing Playwright smoke for migrated pages: for each segment it deep-links
to the path route, asserts the URL and that the dashboard shell rendered, then
clicks off to a legacy page and asserts navigation still works. Driven by
e2e_tests/fixtures/migratedPages.ts, so adding a page is one line.

Runs in two situations against the same proxy: the default mount (npm run
e2e:migration) and a non-root SERVER_ROOT_PATH mount (npm run e2e:migration:root).
globalSetup now logs in at `${SERVER_ROOT_PATH}/ui/login` so the admin storage
state is valid under a prefix. Seeded with api-reference; append the rest as their
migrations merge.

* test(ui): support headed slow-motion + watch pauses in the migration smoke

Honor SLOWMO in the server-root-path config (the default config already did),
and add an env-gated E2E_WATCH_MS pause so a headed run lingers on each state.
Both are no-ops by default, so CI behavior is unchanged.

* test(ui): make the migration smoke a sidebar-click user journey

Rework the smoke from deep-linking to a real navigation journey: start at the
landing page, click the migrated page in the sidebar (expanding submenus for
nested items), assert the path route rendered, reload it (the check a wrong
server_root_path breaks), bounce to a legacy page and back, and — once two pages
are migrated — navigate directly between two migrated pages. Verifies via URL +
shell render, driven by the same fixture list.

* test(ui): address review on the migration smoke

Escape ROOT and segment before interpolating them into RegExp URL matchers so a
future segment containing regex metacharacters can't silently widen the match.
Make the server-root-path config fail fast when SERVER_ROOT_PATH is unset instead
of silently re-running the default mount and passing without exercising the prefix.

* test(ui): drop unused watch helper and fix stale smoke README

* test(ui): run the migration smoke under a server root path in CI

* test(ui): harden + instrument the server-root-path proxy reboot in CI

* test(ui): run the server-root-path migration smoke as its own CI job

Replace the in-place proxy reboot in e2e_ui_testing with a dedicated
e2e_ui_testing_server_root_path job that boots the proxy once with
SERVER_ROOT_PATH=/litellm, matching how every other proxy variant in the
config gets its own job rather than killing and relaunching the live proxy.

The reboot was failing deterministically: after pkill -9 and relaunch the
prefixed proxy never came back up on :4000 (connection refused), so the smoke
never ran. The readiness step that was supposed to surface the cause could
never reach its boot-log tail because CircleCI runs steps under bash -eo
pipefail and the preceding `curl -sv ... | tail` aborted the step with curl's
exit 7. Booting the proxy as the job's own background step lets any boot crash
land in that step's log instead of being swallowed.

The default e2e_ui_testing job is unchanged aside from dropping the reboot,
prefixed-readiness, and prefixed-smoke steps; the migration smoke still runs at
the root mount there via the default Playwright config.

* fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through (#24232)

* fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through

* test: mock post_call_response_headers_hook in audio speech route tests

* chore(ui): remove dead App Router route stubs under (dashboard) (#30045)

models-and-endpoints, organizations, and virtual-keys each had a page.tsx
route under (dashboard)/ that is not in MIGRATED_PAGES, so the sidebar and
deep links never resolve to it and the route is unreachable. Each was a thin
wrapper that handed the shared view empty or no-op props (empty modelData with
a no-op setModelData, hardcoded empty organizations, no-op
setUserRole/setUserEmail), so reaching one would render a degraded page in any
case. The real wrapper belongs in the PR that flips each page into
MIGRATED_PAGES, written with eyes on it and a test

This continues the dead-scaffolding cleanup from #28891. The shared components
these wrappers rendered (ModelsAndEndpointsView, OrganizationFilters) stay,
since the legacy ?page= switch in app/page.tsx and src/components still import
them

* fix(ui/mcp): reset OAuth state on create-server modal close so a prior server's token no longer leaks into the next add-server session (#30000)

* fix(ui/mcp): reset OAuth hook state on modal close so a prior server's token no longer leaks into the next add-server session

* fix(ui/mcp): clear in-flight OAuth guard on reset and reset form/tools on modal close so nothing leaks on a parent-driven dismiss

* fix(mcp): allow team access-group grants in OAuth authorize/token access check (#30041)

* fix(mcp): honor team access-group grants in OAuth authorize/token access check

* test(mcp): mock build_effective_auth_contexts in non-admin authorize tests for isolation

* docs(security): require a reproduction video for vulnerability reports (#30048) (#30063)

With AI models capable of automated vulnerability discovery now publicly
available, we expect a large increase in report volume, much of it
unverified. Requiring a video of the exploit running against a live
instance raises the bar for submissions and keeps triage focused on
reproducible issues. Reports without a video will be closed and reopened
if one is added later.

Co-authored-by: stuxf <[email protected]>

* feat(ui): add admin flag to disable in-product UI nudges for everyone (#29796)

* feat(ui): add admin flag to disable in-product UI nudges for everyone

Admins can now suppress the survey and Claude Code feedback popups for
all users via a single disable_ui_nudges UI setting, instead of relying
on each user dismissing them individually.

* fix(ui): suppress nudges while ui settings are loading

Gate nudgesDisabled on the ui-settings loading state so an admin with
disable_ui_nudges on doesn't see the survey prompt flash, and the
getInProductNudgesCall fetch doesn't fire, on a cold page load before
the flag resolves. Falls back to showing nudges if the fetch errors.

* test(ui): wrap CreateKeyPage test in QueryClientProvider

page.tsx now calls useUISettings (react-query), which needs a
QueryClient that layout.tsx supplies in production but the test did
not. Add the provider and mock getUiSettings so the query resolves.

* chore(ui): remove dead dashboard files and unused dependencies (#30047)

* chore(ui): remove dead dashboard files and unused dependencies

knip flagged seven orphaned source/config files with no importers and
five declared dependencies that nothing in the tree uses. Removing them
shrinks the dashboard bundle's source surface and keeps the manifest
honest; vite stays installed transitively via vitest, so test tooling is
unaffected.

* fix(ci): restore serverRootPath.config.ts referenced by SERVER_ROOT_PATH workflow

The dead-code sweep removed e2e_tests/serverRootPath.config.ts, but its spec
(tests/login/serverRootPathRedirect.spec.ts) and the test_server_root_path.yml
workflow step still depend on it, so the redirect e2e job failed to load a
config that no longer existed.

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593) (#30009)

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593)

After replace_model_in_jsonl, body.model is a stripped provider id. Reverse-mapping it via resolve_model_name_from_model_id is first-match on model_list and caused false 403s when multiple deployments share the same stripped name. Use target_model_names from the unified file id instead.

Co-authored-by: Cursor <[email protected]>

* fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)

Restores the reverse-lookup for the JSONL body.model fallback path so that
legacy/pre-target_model_names managed files still map stripped provider IDs
back to proxy aliases before auth. Also cleans up redundant `or None`.

Co-Authored-By: Claude Sonnet 4.6 <[email protected]>

* Revert "fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)"

This reverts commit 30d2e96f77ef521ccaaf2193fe554980380eb669.

---------

Co-authored-by: Cursor <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>

* Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI (#30064)

* Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI

Adds cost map entries for claude-fable-5 ($10/$50 per MTok, 1M context,
128K output, adaptive thinking only) on the Anthropic API, Bedrock
converse (base, global, and us/eu geo inference profiles at the 10%
regional premium), Vertex AI, and Azure AI (Microsoft Foundry, which
serves Fable 5 with the full 1M context window unlike Opus 4.8).

Registers anthropic.claude-fable-5 in BEDROCK_CONVERSE_MODELS, lists the
model in the setup wizard, and extends the reasoning effort e2e grid.
The Bedrock, Vertex, and Azure grid cells carry fail_reason markers
until the CI accounts are provisioned: Bedrock needs the provider data
sharing opt-in Fable 5 requires, and the Foundry resource needs a
claude-fable-5 deployment.

The first-party entry carries provider_specific_entry {us: 1.1} for the
inference_geo premium and deliberately no fast multiplier since Fable 5
has no fast mode.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Drop removed sampling params for Claude 4.7+ when drop_params is set

Fable 5, Opus 4.7, and Opus 4.8 removed sampling params: the API rejects
top_p, top_k, and any temperature other than 1 with a 400. LiteLLM was
forwarding them even with drop_params enabled because the Anthropic and
Bedrock converse transformations passed temperature/top_p through
unconditionally.

Mirror the GPT-5/o-series handling: temperature=1 still passes through,
other values and any top_p are dropped when drop_params is set, and
without drop_params a clean client-side UnsupportedParamsError tells the
caller how to opt in, instead of surfacing the raw provider error.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Drive sampling param gating from the cost map and cover top_k

Greptile review follow-ups on the sampling param fix: the restriction for
Fable 5 / Opus 4.7 / 4.8 is now declared as supports_sampling_params: false
on every affected cost map entry (perplexity excluded; that route is
OpenAI-compatible and maps sampling params upstream) and read back through
a tri-state map lookup, keeping the name check only as a fallback for
provider-routed ids whose hosted map entries predate the flag, the same
layering supports_adaptive_thinking uses. top_k bypasses map_openai_params
as a provider-specific kwarg, so it is gated at the shared
AnthropicConfig.transform_request boundary (direct, Bedrock invoke, Vertex,
Azure) and in the Bedrock converse _handle_top_k_value path, with
drop_params threaded through the converse transform helpers.

Also updates the reasoning effort grid cell count assertion for the four
Fable 5 rows added on this branch (29 x 11 cells).

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Declare supports_sampling_params in the cost map schema

The model map validation schema uses additionalProperties: false, so the
new flag must be declared for the 28 entries that carry it; this was the
one failing job (misc / Run tests) on the previous commit.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* fix(bedrock): gate top_k=0 on converse to match Anthropic boundary

Truthiness check let top_k=0 silently disappear on models that removed
sampling params, while AnthropicConfig.transform_request treats 0 as
present and raises UnsupportedParamsError (or drops when drop_params is
set). Switch to 'is not None' so converse, direct Anthropic, invoke,
Vertex, and Azure all behave the same for top_k=0.

---------

Co-authored-by: Cursor Agent <[email protected]>

* fix(anthropic): avoid index -1 content_block_delta in messages stream

When a /v1/messages request is routed through the Responses API
adapter, AnthropicResponsesStreamWrapper only emits content_block_start
on response.output_item.added. Some upstreams (LMStudio for example)
never send that event, so the text delta handler fell back to
_current_block_index, which starts at -1, and clients received
content_block_delta events with index -1 and no preceding
content_block_start. Anthropic SDKs then fail with "text part -1 not
found"

The text delta handler now synthesizes a content_block_start with a
fresh block index whenever the delta references an unregistered item_id
or no block is open yet, and registers the item_id so follow-up deltas
reuse the same index

Addresses the /v1/messages defect in #27442

* Make test sys.path shim resolve relative to the file, not the CWD

os.path.abspath("../../../../../../..") depends on where pytest is
invoked from; anchoring on os.path.dirname(__file__) makes the import
work from any working directory. Also corrects the depth: the repo root
is six levels above this file, not seven.

---------

Co-authored-by: milan-berri <[email protected]>
Co-authored-by: Cursor <[email protected]>
Co-authored-by: ryan-crabbe-berri <[email protected]>
Co-authored-by: michelligabriele <[email protected]>
Co-authored-by: tin-berri <[email protected]>
Co-authored-by: yuneng-jiang <[email protected]>
Co-authored-by: stuxf <[email protected]>
Co-authored-by: Sameer Kankute <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>
Co-authored-by: Mateo Wang <[email protected]>

* fix: enable compact-2026-01-12 beta header for vertex_ai provider (#30114)

* fix(team): reserve team budget raises for proxy admins on /team/update (#30030)

The caller's PERSONAL max_budget was the wrong yardstick for /team/update: a
team's spend ceiling has nothing to do with the admin's own key budget. That
comparison was an unintended side effect of reusing _check_user_team_limits()
(which exists for the /team/new path) and broke the UI, which re-sends the
unchanged budget on every save.

New behavior on /team/update for standalone teams:
- A team admin (already authorized via _verify_team_access) may freely KEEP or
  LOWER the team budget, and change models/tpm/rpm, without being gated by their
  personal limits.
- GROWING a team's spend ceiling is a budget-authority action reserved for proxy
  admins -> 403 for team admins. "Growing" covers both raising max_budget above
  the team's current finite value and removing the cap entirely (max_budget=null,
  detected via model_fields_set so an explicit null is distinguished from an
  omitted field). For a team that currently has no cap, setting a finite value is
  a restriction and is allowed.
- Org-scoped teams remain governed by _check_org_team_limits() (capped by the
  org budget).

Also reverts the #29525 existing_team_max_budget workaround in
_check_user_team_limits() back to the create-only form; /team/new still enforces
the creator's personal caps.

docs(access_control): resolve the contradiction in the team-admin section —
team admins can keep/lower the budget and manage rate limits/models, but cannot
raise the team budget (proxy-admin only).

tests: unit + behavior coverage for raise-blocked, cap-removal-blocked (team
admin), raise/removal allowed (proxy admin), uncapped-team restriction allowed,
keep/lower/resend allowed, and unchanged create-path guards.

Co-authored-by: Cursor <[email protected]>

* test(ui): data-driven App Router migration E2E smoke (default + server-root-path) (#29974)

* test(ui): add a data-driven App Router migration E2E smoke

Add a growing Playwright smoke for migrated pages: for each segment it deep-links
to the path route, asserts the URL and that the dashboard shell rendered, then
clicks off to a legacy page and asserts navigation still works. Driven by
e2e_tests/fixtures/migratedPages.ts, so adding a page is one line.

Runs in two situations against the same proxy: the default mount (npm run
e2e:migration) and a non-root SERVER_ROOT_PATH mount (npm run e2e:migration:root).
globalSetup now logs in at `${SERVER_ROOT_PATH}/ui/login` so the admin storage
state is valid under a prefix. Seeded with api-reference; append the rest as their
migrations merge.

* test(ui): support headed slow-motion + watch pauses in the migration smoke

Honor SLOWMO in the server-root-path config (the default config already did),
and add an env-gated E2E_WATCH_MS pause so a headed run lingers on each state.
Both are no-ops by default, so CI behavior is unchanged.

* test(ui): make the migration smoke a sidebar-click user journey

Rework the smoke from deep-linking to a real navigation journey: start at the
landing page, click the migrated page in the sidebar (expanding submenus for
nested items), assert the path route rendered, reload it (the check a wrong
server_root_path breaks), bounce to a legacy page and back, and — once two pages
are migrated — navigate directly between two migrated pages. Verifies via URL +
shell render, driven by the same fixture list.

* test(ui): address review on the migration smoke

Escape ROOT and segment before interpolating them into RegExp URL matchers so a
future segment containing regex metacharacters can't silently widen the match.
Make the server-root-path config fail fast when SERVER_ROOT_PATH is unset instead
of silently re-running the default mount and passing without exercising the prefix.

* test(ui): drop unused watch helper and fix stale smoke README

* test(ui): run the migration smoke under a server root path in CI

* test(ui): harden + instrument the server-root-path proxy reboot in CI

* test(ui): run the server-root-path migration smoke as its own CI job

Replace the in-place proxy reboot in e2e_ui_testing with a dedicated
e2e_ui_testing_server_root_path job that boots the proxy once with
SERVER_ROOT_PATH=/litellm, matching how every other proxy variant in the
config gets its own job rather than killing and relaunching the live proxy.

The reboot was failing deterministically: after pkill -9 and relaunch the
prefixed proxy never came back up on :4000 (connection refused), so the smoke
never ran. The readiness step that was supposed to surface the cause could
never reach its boot-log tail because CircleCI runs steps under bash -eo
pipefail and the preceding `curl -sv ... | tail` aborted the step with curl's
exit 7. Booting the proxy as the job's own background step lets any boot crash
land in that step's log instead of being swallowed.

The default e2e_ui_testing job is unchanged aside from dropping the reboot,
prefixed-readiness, and prefixed-smoke steps; the migration smoke still runs at
the root mount there via the default Playwright config.

* fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through (#24232)

* fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through

* test: mock post_call_response_headers_hook in audio speech route tests

* chore(ui): remove dead App Router route stubs under (dashboard) (#30045)

models-and-endpoints, organizations, and virtual-keys each had a page.tsx
route under (dashboard)/ that is not in MIGRATED_PAGES, so the sidebar and
deep links never resolve to it and the route is unreachable. Each was a thin
wrapper that handed the shared view empty or no-op props (empty modelData with
a no-op setModelData, hardcoded empty organizations, no-op
setUserRole/setUserEmail), so reaching one would render a degraded page in any
case. The real wrapper belongs in the PR that flips each page into
MIGRATED_PAGES, written with eyes on it and a test

This continues the dead-scaffolding cleanup from #28891. The shared components
these wrappers rendered (ModelsAndEndpointsView, OrganizationFilters) stay,
since the legacy ?page= switch in app/page.tsx and src/components still import
them

* fix(ui/mcp): reset OAuth state on create-server modal close so a prior server's token no longer leaks into the next add-server session (#30000)

* fix(ui/mcp): reset OAuth hook state on modal close so a prior server's token no longer leaks into the next add-server session

* fix(ui/mcp): clear in-flight OAuth guard on reset and reset form/tools on modal close so nothing leaks on a parent-driven dismiss

* fix(mcp): allow team access-group grants in OAuth authorize/token access check (#30041)

* fix(mcp): honor team access-group grants in OAuth authorize/token access check

* test(mcp): mock build_effective_auth_contexts in non-admin authorize tests for isolation

* docs(security): require a reproduction video for vulnerability reports (#30048) (#30063)

With AI models capable of automated vulnerability discovery now publicly
available, we expect a large increase in report volume, much of it
unverified. Requiring a video of the exploit running against a live
instance raises the bar for submissions and keeps triage focused on
reproducible issues. Reports without a video will be closed and reopened
if one is added later.

Co-authored-by: stuxf <[email protected]>

* feat(ui): add admin flag to disable in-product UI nudges for everyone (#29796)

* feat(ui): add admin flag to disable in-product UI nudges for everyone

Admins can now suppress the survey and Claude Code feedback popups for
all users via a single disable_ui_nudges UI setting, instead of relying
on each user dismissing them individually.

* fix(ui): suppress nudges while ui settings are loading

Gate nudgesDisabled on the ui-settings loading state so an admin with
disable_ui_nudges on doesn't see the survey prompt flash, and the
getInProductNudgesCall fetch doesn't fire, on a cold page load before
the flag resolves. Falls back to showing nudges if the fetch errors.

* test(ui): wrap CreateKeyPage test in QueryClientProvider

page.tsx now calls useUISettings (react-query), which needs a
QueryClient that layout.tsx supplies in production but the test did
not. Add the provider and mock getUiSettings so the query resolves.

* chore(ui): remove dead dashboard files and unused dependencies (#30047)

* chore(ui): remove dead dashboard files and unused dependencies

knip flagged seven orphaned source/config files with no importers and
five declared dependencies that nothing in the tree uses. Removing them
shrinks the dashboard bundle's source surface and keeps the manifest
honest; vite stays installed transitively via vitest, so test tooling is
unaffected.

* fix(ci): restore serverRootPath.config.ts referenced by SERVER_ROOT_PATH workflow

The dead-code sweep removed e2e_tests/serverRootPath.config.ts, but its spec
(tests/login/serverRootPathRedirect.spec.ts) and the test_server_root_path.yml
workflow step still depend on it, so the redirect e2e job failed to load a
config that no longer existed.

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593) (#30009)

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593)

After replace_model_in_jsonl, body.model is a stripped provider id. Reverse-mapping it via resolve_model_name_from_model_id is first-match on model_list and caused false 403s when multiple deployments share the same stripped name. Use target_model_names from the unified file id instead.

Co-authored-by: Cursor <[email protected]>

* fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)

Restores the reverse-lookup for the JSONL body.model fallback path so that
legacy/pre-target_model_names managed files still map stripped provider IDs
back to proxy aliases before auth. Also cleans up redundant `or None`.

Co-Authored-By: Claude Sonnet 4.6 <[email protected]>

* Revert "fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)"

This reverts commit 30d2e96f77ef521ccaaf2193fe554980380eb669.

---------

Co-authored-by: Cursor <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>

* Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI (#30064)

* Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI

Adds cost map entries for claude-fable-5 ($10/$50 per MTok, 1M context,
128K output, adaptive thinking only) on the Anthropic API, Bedrock
converse (base, global, and us/eu geo inference profiles at the 10%
regional premium), Vertex AI, and Azure AI (Microsoft Foundry, which
serves Fable 5 with the full 1M context window unlike Opus 4.8).

Registers anthropic.claude-fable-5 in BEDROCK_CONVERSE_MODELS, lists the
model in the setup wizard, and extends the reasoning effort e2e grid.
The Bedrock, Vertex, and Azure grid cells carry fail_reason markers
until the CI accounts are provisioned: Bedrock needs the provider data
sharing opt-in Fable 5 requires, and the Foundry resource needs a
claude-fable-5 deployment.

The first-party entry carries provider_specific_entry {us: 1.1} for the
inference_geo premium and deliberately no fast multiplier since Fable 5
has no fast mode.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Drop removed sampling params for Claude 4.7+ when drop_params is set

Fable 5, Opus 4.7, and Opus 4.8 removed sampling params: the API rejects
top_p, top_k, and any temperature other than 1 with a 400. LiteLLM was
forwarding them even with drop_params enabled because the Anthropic and
Bedrock converse transformations passed temperature/top_p through
unconditionally.

Mirror the GPT-5/o-series handling: temperature=1 still passes through,
other values and any top_p are dropped when drop_params is set, and
without drop_params a clean client-side UnsupportedParamsError tells the
caller how to opt in, instead of surfacing the raw provider error.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Drive sampling param gating from the cost map and cover top_k

Greptile review follow-ups on the sampling param fix: the restriction for
Fable 5 / Opus 4.7 / 4.8 is now declared as supports_sampling_params: false
on every affected cost map entry (perplexity excluded; that route is
OpenAI-compatible and maps sampling params upstream) and read back through
a tri-state map lookup, keeping the name check only as a fallback for
provider-routed ids whose hosted map entries predate the flag, the same
layering supports_adaptive_thinking uses. top_k bypasses map_openai_params
as a provider-specific kwarg, so it is gated at the shared
AnthropicConfig.transform_request boundary (direct, Bedrock invoke, Vertex,
Azure) and in the Bedrock converse _handle_top_k_value path, with
drop_params threaded through the converse transform helpers.

Also updates the reasoning effort grid cell count assertion for the four
Fable 5 rows added on this branch (29 x 11 cells).

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Declare supports_sampling_params in the cost map schema

The model map validation schema uses additionalProperties: false, so the
new flag must be declared for the 28 entries that carry it; this was the
one failing job (misc / Run tests) on the previous commit.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* fix(bedrock): gate top_k=0 on converse to match Anthropic boundary

Truthiness check let top_k=0 silently disappear on models that removed
sampling params, while AnthropicConfig.transform_request treats 0 as
present and raises UnsupportedParamsError (or drops when drop_params is
set). Switch to 'is not None' so converse, direct Anthropic, invoke,
Vertex, and Azure all behave the same for top_k=0.

---------

Co-authored-by: Cursor Agent <[email protected]>

* fix: enable compact-2026-01-12 beta header for vertex_ai provider

The vertex_ai block in anthropic_beta_headers_config.json mapped
compact-2026-01-12 to null, so update_headers_with_filtered_beta
stripped the header before the request reached Vertex while the
compact_20260112 context edit stayed in the body, and Vertex rejected
the request with HTTP 400. Vertex rawPredict accepts the header, and
the bedrock and databricks blocks already forward it. Mirrors #21867,
which enabled context-1m-2025-08-07 for vertex_ai the same way.

Fixes #27290.

---------

Co-authored-by: milan-berri <[email protected]>
Co-authored-by: Cursor <[email protected]>
Co-authored-by: ryan-crabbe-berri <[email protected]>
Co-authored-by: michelligabriele <[email protected]>
Co-authored-by: tin-berri <[email protected]>
Co-authored-by: yuneng-jiang <[email protected]>
Co-authored-by: stuxf <[email protected]>
Co-authored-by: Sameer Kankute <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>
Co-authored-by: Mateo Wang <[email protected]>

* fix(proxy): coerce litellm_settings.max_budget env var to float (#30113)

* fix(team): reserve team budget raises for proxy admins on /team/update (#30030)

The caller's PERSONAL max_budget was the wrong yardstick for /team/update: a
team's spend ceiling has nothing to do with the admin's own key budget. That
comparison was an unintended side effect of reusing _check_user_team_limits()
(which exists for the /team/new path) and broke the UI, which re-sends the
unchanged budget on every save.

New behavior on /team/update for standalone teams:
- A team admin (already authorized via _verify_team_access) may freely KEEP or
  LOWER the team budget, and change models/tpm/rpm, without being gated by their
  personal limits.
- GROWING a team's spend ceiling is a budget-authority action reserved for proxy
  admins -> 403 for team admins. "Growing" covers both raising max_budget above
  the team's current finite value and removing the cap entirely (max_budget=null,
  detected via model_fields_set so an explicit null is distinguished from an
  omitted field). For a team that currently has no cap, setting a finite value is
  a restriction and is allowed.
- Org-scoped teams remain governed by _check_org_team_limits() (capped by the
  org budget).

Also reverts the #29525 existing_team_max_budget workaround in
_check_user_team_limits() back to the create-only form; /team/new still enforces
the creator's personal caps.

docs(access_control): resolve the contradiction in the team-admin section —
team admins can keep/lower the budget and manage rate limits/models, but cannot
raise the team budget (proxy-admin only).

tests: unit + behavior coverage for raise-blocked, cap-removal-blocked (team
admin), raise/removal allowed (proxy admin), uncapped-team restriction allowed,
keep/lower/resend allowed, and unchanged create-path guards.

Co-authored-by: Cursor <[email protected]>

* test(ui): data-driven App Router migration E2E smoke (default + server-root-path) (#29974)

* test(ui): add a data-driven App Router migration E2E smoke

Add a growing Playwright smoke for migrated pages: for each segment it deep-links
to the path route, asserts the URL and that the dashboard shell rendered, then
clicks off to a legacy page and asserts navigation still works. Driven by
e2e_tests/fixtures/migratedPages.ts, so adding a page is one line.

Runs in two situations against the same proxy: the default mount (npm run
e2e:migration) and a non-root SERVER_ROOT_PATH mount (npm run e2e:migration:root).
globalSetup now logs in at `${SERVER_ROOT_PATH}/ui/login` so the admin storage
state is valid under a prefix. Seeded with api-reference; append the rest as their
migrations merge.

* test(ui): support headed slow-motion + watch pauses in the migration smoke

Honor SLOWMO in the server-root-path config (the default config already did),
and add an env-gated E2E_WATCH_MS pause so a headed run lingers on each state.
Both are no-ops by default, so CI behavior is unchanged.

* test(ui): make the migration smoke a sidebar-click user journey

Rework the smoke from deep-linking to a real navigation journey: start at the
landing page, click the migrated page in the sidebar (expanding submenus for
nested items), assert the path route rendered, reload it (the check a wrong
server_root_path breaks), bounce to a legacy page and back, and — once two pages
are migrated — navigate directly between two migrated pages. Verifies via URL +
shell render, driven by the same fixture list.

* test(ui): address review on the migration smoke

Escape ROOT and segment before interpolating them into RegExp URL matchers so a
future segment containing regex metacharacters can't silently widen the match.
Make the server-root-path config fail fast when SERVER_ROOT_PATH is unset instead
of silently re-running the default mount and passing without exercising the prefix.

* test(ui): drop unused watch helper and fix stale smoke README

* test(ui): run the migration smoke under a server root path in CI

* test(ui): harden + instrument the server-root-path proxy reboot in CI

* test(ui): run the server-root-path migration smoke as its own CI job

Replace the in-place proxy reboot in e2e_ui_testing with a dedicated
e2e_ui_testing_server_root_path job that boots the proxy once with
SERVER_ROOT_PATH=/litellm, matching how every other proxy variant in the
config gets its own job rather than killing and relaunching the live proxy.

The reboot was failing deterministically: after pkill -9 and relaunch the
prefixed proxy never came back up on :4000 (connection refused), so the smoke
never ran. The readiness step that was supposed to surface the cause could
never reach its boot-log tail because CircleCI runs steps under bash -eo
pipefail and the preceding `curl -sv ... | tail` aborted the step with curl's
exit 7. Booting the proxy as the job's own background step lets any boot crash
land in that step's log instead of being swallowed.

The default e2e_ui_testing job is unchanged aside from dropping the reboot,
prefixed-readiness, and prefixed-smoke steps; the migration smoke still runs at
the root mount there via the default Playwright config.

* fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through (#24232)

* fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through

* test: mock post_call_response_headers_hook in audio speech route tests

* chore(ui): remove dead App Router route stubs under (dashboard) (#30045)

models-and-endpoints, organizations, and virtual-keys each had a page.tsx
route under (dashboard)/ that is not in MIGRATED_PAGES, so the sidebar and
deep links never resolve to it and the route is unreachable. Each was a thin
wrapper that handed the shared view empty or no-op props (empty modelData with
a no-op setModelData, hardcoded empty organizations, no-op
setUserRole/setUserEmail), so reaching one would render a degraded page in any
case. The real wrapper belongs in the PR that flips each page into
MIGRATED_PAGES, written with eyes on it and a test

This continues the dead-scaffolding cleanup from #28891. The shared components
these wrappers rendered (ModelsAndEndpointsView, OrganizationFilters) stay,
since the legacy ?page= switch in app/page.tsx and src/components still import
them

* fix(ui/mcp): reset OAuth state on create-server modal close so a prior server's token no longer leaks into the next add-server session (#30000)

* fix(ui/mcp): reset OAuth hook state on modal close so a prior server's token no longer leaks into the next add-server session

* fix(ui/mcp): clear in-flight OAuth guard on reset and reset form/tools on modal close so nothing leaks on a parent-driven dismiss

* fix(mcp): allow team access-group grants in OAuth authorize/token access check (#30041)

* fix(mcp): honor team access-group grants in OAuth authorize/token access check

* test(mcp): mock build_effective_auth_contexts in non-admin authorize tests for isolation

* docs(security): require a reproduction video for vulnerability reports (#30048) (#30063)

With AI models capable of automated vulnerability discovery now publicly
available, we expect a large increase in report volume, much of it
unverified. Requiring a video of the exploit running against a live
instance raises the bar for submissions and keeps triage focused on
reproducible issues. Reports without a video will be closed and reopened
if one is added later.

Co-authored-by: stuxf <[email protected]>

* feat(ui): add admin flag to disable in-product UI nudges for everyone (#29796)

* feat(ui): add admin flag to disable in-product UI nudges for everyone

Admins can now suppress the survey and Claude Code feedback popups for
all users via a single disable_ui_nudges UI setting, instead of relying
on each user dismissing them individually.

* fix(ui): suppress nudges while ui settings are loading

Gate nudgesDisabled on the ui-settings loading state so an admin with
disable_ui_nudges on doesn't see the survey prompt flash, and the
getInProductNudgesCall fetch doesn't fire, on a cold page load before
the flag resolves. Falls back to showing nudges if the fetch errors.

* test(ui): wrap CreateKeyPage test in QueryClientProvider

page.tsx now calls useUISettings (react-query), which needs a
QueryClient that layout.tsx supplies in production but the test did
not. Add the provider and mock getUiSettings so the query resolves.

* chore(ui): remove dead dashboard files and unused dependencies (#30047)

* chore(ui): remove dead dashboard files and unused dependencies

knip flagged seven orphaned source/config files with no importers and
five declared dependencies that nothing in the tree uses. Removing them
shrinks the dashboard bundle's source surface and keeps the manifest
honest; vite stays installed transitively via vitest, so test tooling is
unaffected.

* fix(ci): restore serverRootPath.config.ts referenced by SERVER_ROOT_PATH workflow

The dead-code sweep removed e2e_tests/serverRootPath.config.ts, but its spec
(tests/login/serverRootPathRedirect.spec.ts) and the test_server_root_path.yml
workflow step still depend on it, so the redirect e2e job failed to load a
config that no longer existed.

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593) (#30009)

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593)

After replace_model_in_jsonl, body.model is a stripped provider id. Reverse-mapping it via resolve_model_name_from_model_id is first-match on model_list and caused false 403s when multiple deployments share the same stripped name. Use target_model_names from the unified file id instead.

Co-authored-by: Cursor <[email protected]>

* fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)

Restores the reverse-lookup for the JSONL body.model fallback path so that
legacy/pre-target_model_names managed files still map stripped provider IDs
back to proxy aliases before auth. Also cleans up redundant `or None`.

Co-Authored-By: Claude Sonnet 4.6 <[email protected]>

* Revert "fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)"

This reverts commit 30d2e96f77ef521ccaaf2193fe554980380eb669.

---------

Co-authored-by: Cursor <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>

* Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI (#30064)

* Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI

Adds cost map entries for claude-fable-5 ($10/$50 per MTok, 1M context,
128K output, adaptive thinking only) on the Anthropic API, Bedrock
converse (base, global, and us/eu geo inference profiles at the 10%
regional premium), Vertex AI, and Azure AI (Microsoft Foundry, which
serves Fable 5 with the full 1M context window unlike Opus 4.8).

Registers anthropic.claude-fable-5 in BEDROCK_CONVERSE_MODELS, lists the
model in the setup wizard, and extends the reasoning effort e2e grid.
The Bedrock, Vertex, and Azure grid cells carry fail_reason markers
until the CI accounts are provisioned: Bedrock needs the provider data
sharing opt-in Fable 5 requires, and the Foundry resource needs a
claude-fable-5 deployment.

The first-party entry carries provider_specific_entry {us: 1.1} for the
inference_geo premium and deliberately no fast multiplier since Fable 5
has no fast mode.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Drop removed sampling params for Claude 4.7+ when drop_params is set

Fable 5, Opus 4.7, and Opus 4.8 removed sampling params: the API rejects
top_p, top_k, and any temperature other than 1 with a 400. LiteLLM was
forwarding them even with drop_params enabled because the Anthropic and
Bedrock converse transformations passed temperature/top_p through
unconditionally.

Mirror the GPT-5/o-series handling: temperature=1 still passes through,
other values and any top_p are dropped when drop_params is set, and
without drop_params a clean client-side UnsupportedParamsError tells the
caller how to opt in, instead of surfacing the raw provider error.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Drive sampling param gating from the cost map and cover top_k

Greptile review follow-ups on the sampling param fix: the restriction for
Fable 5 / Opus 4.7 / 4.8 is now declared as supports_sampling_params: false
on every affected cost map entry (perplexity excluded; that route is
OpenAI-compatible and maps sampling params upstream) and read back through
a tri-state map lookup, keeping the name check only as a fallback for
provider-routed ids whose hosted map entries predate the flag, the same
layering supports_adaptive_thinking uses. top_k bypasses map_openai_params
as a provider-specific kwarg, so it is gated at the shared
AnthropicConfig.transform_request boundary (direct, Bedrock invoke, Vertex,
Azure) and in the Bedrock converse _handle_top_k_value path, with
drop_params threaded through the converse transform helpers.

Also updates the reasoning effort grid cell count assertion for the four
Fable 5 rows added on this branch (29 x 11 cells).

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Declare supports_sampling_params in the cost map schema

The model map validation schema uses additionalProperties: false, so the
new flag must be declared for the 28 entries that carry it; this was the
one failing job (misc / Run tests) on the previous commit.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* fix(bedrock): gate top_k=0 on converse to match Anthropic boundary

Truthiness check let top_k=0 silently disappear on models that removed
sampling params, while AnthropicConfig.transform_request treats 0 as
present and raises UnsupportedParamsError (or drops when drop_params is
set). Switch to 'is not None' so converse, direct Anthropic, invoke,
Vertex, and Azure all behave the same for top_k=0.

---------

Co-authored-by: Cursor Agent <[email protected]>

* fix(proxy): coerce litellm_settings.max_budget env var to float

When max_budget is set in litellm_settings via os.environ/MAX_BUDGET,
the env var resolves to a string and the generic setattr branch in
ProxyConfig.load_config stored it as-is, so the startup check
litellm.max_budget > 0 raised TypeError. The earlier fix (#23855) only
covered the CLI initialize() path. Coerce the value to float in the
settings loop, matching the existing max_internal_user_budget handling.

Fixes #26696.

---------

Co-authored-by: milan-berri <[email protected]>
Co-authored-by: Cursor <[email protected]>
Co-authored-by: ryan-crabbe-berri <[email protected]>
Co-authored-by: michelligabriele <[email protected]>
Co-authored-by: tin-berri <[email protected]>
Co-authored-by: yuneng-jiang <[email protected]>
Co-authored-by: stuxf <[email protected]>
Co-authored-by: Sameer Kankute <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>
Co-authored-by: Mateo Wang <[email protected]>

* fix(router): don't drop bedrock pass-through deployments using IAM credentials (#30111)

* Fix Bedrock passthrough deployment dropped when using IAM credentials

Bedrock deployments with use_in_pass_through enabled and IAM/OIDC auth
(aws_role_name, no api_key) hit the generic pass-through branch in
Router._initialize_deployment_for_pass_through, which calls
set_pass_through_credentials and raises "api_key is required". The
exception drops the deployment from the router entirely, breaking both
passthrough and normal routing for that model.

Skip the credential store write when no api_key is set; the bedrock
passthrough route resolves AWS credentials at request time via
BedrockConverseLLM.get_credentials(), not the passthrough credential
store, so there is nothing to register here.

Fixes #27728.

* Reset passthrough credentials singleton before api_key credential test

The test reads the module-level passthrough_endpoint_router singleton,
so a stale "openai" entry written by an earlier test in the same
process could make the assertion pass without exercising the code path.
Clearing the credentials dict up front makes the test order-independent.

* fix(sdk): stop mirroring reasoning_content in provider_specific_fields (#30110)

The dict-to-response conversion path mirrored reasoning_content into
provider_specific_fields, while live provider transforms (Anthropic's
_build_provider_specific_fields) only set it top-level on the Message.
Cache-replayed messages therefore serialized differently from live
ones, breaking disk cache key stability for multi-turn conversations
with extended thinking.

The mirror was added for DeepSeek before Message.reasoning_content
existed as a top-level attribute. The top-level field is still set by
the converter, so DeepSeek's request-side promotion is unaffected.

Fixes #27337.

* fix(mcp): coerce mcp_server_cost_info values to float at ingest (#30109)

* fix(mcp): coerce mcp_server_cost_info values to float at ingest

YAML 1.1 parses scientific notation without a decimal point
(e.g. 7e-05) as a string, and MCPServerCostInfo is a TypedDict with no
runtime validation, so a string-typed default_cost_per_query from
config.yaml flowed through the proxy untouched and crashed the MCP
server settings page with '.toFixed is not a function'. Normalize
mcp_server_cost_info on both the config and DB load paths, dropping
non-numeric values with a warning instead of failing the server load.

Fixes #27097.

* fix(mcp): drop non-numeric default_cost_per_query instead of nulling it

Keeping the key with a None value still exposes a null to the UI,
which can crash .toFixed formatting when the consumer checks key
existence rather than truthiness. Delete the key on coercion failure,
matching how non-numeric per-tool cost entries are already omitted.

* fix(proxy): count embedding and text completion tokens toward TPM limits (#30105)

* fix(proxy): count embedding and text completion tokens toward TPM limits

The parallel request limiters only read token usage off ModelResponse,
so EmbeddingResponse and TextCompletionResponse objects left
total_tokens at 0 and the per key, user, team, and end user TPM
counters never incremented. Requests to /v1/embeddings and
/v1/completions were effectively free against any tpm_limit. In the v3
limiter this was worse: the post-call reconciliation computed actual
usage as 0 and refunded the pre-call reservation made at request time.

Broaden the isinstance checks to accept EmbeddingResponse and
TextCompletionResponse, which both expose a Usage object, at the four
per-scope sites in parallel_request_limiter.py and at the usage
extraction in parallel_request_limiter_v3.py. ResponsesAPIResponse was
already covered in v3 via BaseLiteLLMOpenAIResponseObject.

Fixes #27738.

* test(proxy): cover v1 limiter TPM counting for embedding and text completion responses

Exercise the broadened isinstance sites in parallel_request_limiter.py
by asserting that async_log_success_event adds total_tokens to the per
key, user, team, and end user TPM counters for EmbeddingResponse and
TextCompletionResponse objects. The counters are pre-seeded at zero so
the assertion is exactly the increment; on the pre-fix code these
responses left total_tokens at 0 and the test fails.

* fix(openai): forward client headers on the text completion path (#30103)

* fix(openai): forward client headers on the text completion path

litellm.completion() merges caller headers with extra_headers, but the
text-completion-openai branch never passed the merged dict to
openai_text_completions.completion(), and the handler only used its
headers argument for logging. Pass the merged headers through the call
site and set them as extra_headers on the outgoing request, mirroring
the chat completion handler, so x-* client headers forwarded by the
proxy reach the provider on /v1/completions.

Fixes #27410.

* Drop redundant extra_headers assignment and fix test module collision

completion() merges extra_headers into headers before the
text-completion-openai branch, and the handler now sets the merged
headers as extra_headers on the request, so the branch-local
optional_params["extra_headers"] assignment was a dead duplicate.
Removing it keeps the assignment in one place while both entry paths
(litellm.text_completion and direct handler callers) still forward
headers; a new regression test pins the extra_headers kwarg path.

Also rename the test module to test_completion_handler.py since its
basename collided with tests/test_litellm/llms/bedrock/batches/
test_handler.py and broke pytest collection.

* fix(bedrock): route Anthropic-shape count_tokens to InvokeModel and base64-encode the body (#30102)

* fix(bedrock): route Anthropic-shape count_tokens to InvokeModel

POST /v1/messages/count_tokens with Anthropic content blocks
({"type": "text"|"tool_use"|...}) was routed to the Converse input of
the Bedrock CountTokens API. The Converse transform copies list content
through verbatim, so Bedrock rejected the request with a 400 and the
caller silently fell back to the local tokenizer, returning counts that
can be off by ~50% on tool-heavy payloads.

_detect_input_type now routes messages whose content blocks carry a
"type" key (Anthropic shape) to the invokeModel input, which forwards
the body verbatim. The invokeModel body is now base64-encoded as the
CountTokens API requires (InvokeModelTokensRequest.body is a
base64-encoded blob), and Anthropic Messages bodies get the
anthropic_version and max_tokens fields Bedrock validates against.

Fixes #27632.

* refactor(bedrock): name the CountTokens max_tokens placeholder

Replace the magic 1024 with a module-level
DEFAULT_ANTHROPIC_INVOKE_MODEL_MAX_TOKENS constant so the intent is
explicit and t…

…T-3593) (#30009)

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593)

After replace_model_in_jsonl, body.model is a stripped provider id. Reverse-mapping it via resolve_model_name_from_model_id is first-match on model_list and caused false 403s when multiple deployments share the same stripped name. Use target_model_names from the unified file id instead.

Co-authored-by: Cursor <[email protected]>

* fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)

Restores the reverse-lookup for the JSONL body.model fallback path so that
legacy/pre-target_model_names managed files still map stripped provider IDs
back to proxy aliases before auth. Also cleans up redundant `or None`.

Co-Authored-By: Claude Sonnet 4.6 <[email protected]>

* Revert "fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)"

This reverts commit 30d2e96.

---------

Co-authored-by: Cursor <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>
(cherry picked from commit 2cd7e87)

…T-3593) (#30009)

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593)

After replace_model_in_jsonl, body.model is a stripped provider id. Reverse-mapping it via resolve_model_name_from_model_id is first-match on model_list and caused false 403s when multiple deployments share the same stripped name. Use target_model_names from the unified file id instead.

Co-authored-by: Cursor <[email protected]>

* fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)

Restores the reverse-lookup for the JSONL body.model fallback path so that
legacy/pre-target_model_names managed files still map stripped provider IDs
back to proxy aliases before auth. Also cleans up redundant `or None`.

Co-Authored-By: Claude Sonnet 4.6 <[email protected]>

* Revert "fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)"

This reverts commit 30d2e96.

---------

Co-authored-by: Cursor <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>
(cherry picked from commit 2cd7e87)

chore(release): backport #30064 (Claude Fable 5) and #30009 to stable/1.84.x and cut 1.84.7

chore(release): backport #30064, #29991, #30009 to stable/1.85.x

…T-3593) (#30009)

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593)

After replace_model_in_jsonl, body.model is a stripped provider id. Reverse-mapping it via resolve_model_name_from_model_id is first-match on model_list and caused false 403s when multiple deployments share the same stripped name. Use target_model_names from the unified file id instead.

Co-authored-by: Cursor <[email protected]>

* fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)

Restores the reverse-lookup for the JSONL body.model fallback path so that
legacy/pre-target_model_names managed files still map stripped provider IDs
back to proxy aliases before auth. Also cleans up redundant `or None`.

Co-Authored-By: Claude Sonnet 4.6 <[email protected]>

* Revert "fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)"

This reverts commit 30d2e96.

---------

Co-authored-by: Cursor <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>
(cherry picked from commit 2cd7e87)

chore(release): backport #30064, #29991, #30009 to stable/1.86.x and cut 1.86.5

…T-3593) (#30009)

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593)

After replace_model_in_jsonl, body.model is a stripped provider id. Reverse-mapping it via resolve_model_name_from_model_id is first-match on model_list and caused false 403s when multiple deployments share the same stripped name. Use target_model_names from the unified file id instead.

Co-authored-by: Cursor <[email protected]>

* fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)

Restores the reverse-lookup for the JSONL body.model fallback path so that
legacy/pre-target_model_names managed files still map stripped provider IDs
back to proxy aliases before auth. Also cleans up redundant `or None`.

Co-Authored-By: Claude Sonnet 4.6 <[email protected]>

* Revert "fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)"

This reverts commit 30d2e96.

---------

Co-authored-by: Cursor <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>
(cherry picked from commit 2cd7e87)

…T-3593) (#30009)

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593)

After replace_model_in_jsonl, body.model is a stripped provider id. Reverse-mapping it via resolve_model_name_from_model_id is first-match on model_list and caused false 403s when multiple deployments share the same stripped name. Use target_model_names from the unified file id instead.

Co-authored-by: Cursor <[email protected]>

* fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)

Restores the reverse-lookup for the JSONL body.model fallback path so that
legacy/pre-target_model_names managed files still map stripped provider IDs
back to proxy aliases before auth. Also cleans up redundant `or None`.

Co-Authored-By: Claude Sonnet 4.6 <[email protected]>

* Revert "fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)"

This reverts commit 30d2e96.

---------

Co-authored-by: Cursor <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>
(cherry picked from commit 2cd7e87)

…AIDR, Mantle SigV4, NetApp streaming-cost fix, and team-scoped Datadog toward v1.89.0-rc.3 (#30179)

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593) (#30009)

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593)

After replace_model_in_jsonl, body.model is a stripped provider id. Reverse-mapping it via resolve_model_name_from_model_id is first-match on model_list and caused false 403s when multiple deployments share the same stripped name. Use target_model_names from the unified file id instead.

Co-authored-by: Cursor <[email protected]>

* fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)

Restores the reverse-lookup for the JSONL body.model fallback path so that
legacy/pre-target_model_names managed files still map stripped provider IDs
back to proxy aliases before auth. Also cleans up redundant `or None`.

Co-Authored-By: Claude Sonnet 4.6 <[email protected]>

* Revert "fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)"

This reverts commit 30d2e96.

---------

Co-authored-by: Cursor <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>
(cherry picked from commit 2cd7e87)

* feat(guardrails): capture user and model metadata in CrowdStrike AIDR

(cherry picked from commit 6fc715c)

* fix(guardrails): read CrowdStrike AIDR identity from both metadata bags (#29991)

Capture user_id and extra_info from metadata or litellm_metadata. The single-bag read dropped identity whenever a request carried a present litellm_metadata field (null or a user-supplied dict), since /chat/completions routes the authenticated identity into metadata while the guardrail read litellm_metadata first

(cherry picked from commit 1bbaf1c)

* feat(bedrock_mantle): add SigV4/IAM auth to Responses API route (#29788)

Applied as the squash diff of PR #29788 (head 9800b2f), which landed
upstream inside the litellm_oss_staging_080626 sync (32c88ca, #29932)
and has no standalone commit to cherry-pick. The rc line already carries
the prerequisite #29490 Responses route via the 040626 sync.

* fix: completion_cost AttributeError on streaming Anthropic web_search responses (#26153) (#27346)

Cherry-picked from staging squash 4a3860d.

The rc line predates the Usage.__init__ server_tool_use dict->ServerToolUse
coercion that staging carries (it landed via the squashed OSS sync #29932 /
32c88ca, not as a standalone commit). The calculate_usage
Usage(**returned_usage.model_dump()) round-trip re-serializes server_tool_use
to a plain dict, so without that coercion the rebuilt usage holds a dict and the
regression test asserting a ServerToolUse type fails. Restored the coercion in
litellm/types/utils.py to satisfy the prerequisite -- it matches #27346's own
first commit (coerce server_tool_use dict to ServerToolUse in Usage.__init__),
which was dropped from the squash only because staging already carried it.

* feat(datadog): add team-scoped Datadog callback support (#29947)

Cherry-picked from the PR head 9c049da (single-commit PR, merged to
litellm_oss_branch). Applied cleanly; no conflicts.

Note: black --check in this worktree flags pre-existing multi-line string
formatting in litellm_core_utils/litellm_logging.py (lines ~1006-1050) that is
already present on the patch/v1.89.0-rc.1 base and is untouched by this pick --
left as-is to avoid reformatting unrelated lines.

---------

Co-authored-by: Sameer Kankute <[email protected]>
Co-authored-by: Cursor <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>
Co-authored-by: Kenan Yildirim <[email protected]>
Co-authored-by: yuneng-jiang <[email protected]>
Co-authored-by: Kent <[email protected]>
Co-authored-by: ishaan-berri <[email protected]>
Co-authored-by: aanchal22 <[email protected]>

…T-3593) (BerriAI#30009)

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593)

After replace_model_in_jsonl, body.model is a stripped provider id. Reverse-mapping it via resolve_model_name_from_model_id is first-match on model_list and caused false 403s when multiple deployments share the same stripped name. Use target_model_names from the unified file id instead.

Co-authored-by: Cursor <[email protected]>

* fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)

Restores the reverse-lookup for the JSONL body.model fallback path so that
legacy/pre-target_model_names managed files still map stripped provider IDs
back to proxy aliases before auth. Also cleans up redundant `or None`.

Co-Authored-By: Claude Sonnet 4.6 <[email protected]>

* Revert "fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)"

This reverts commit 30d2e96.

---------

Co-authored-by: Cursor <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>
(cherry picked from commit 2cd7e87)

…T-3593) (BerriAI#30009)

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593)

After replace_model_in_jsonl, body.model is a stripped provider id. Reverse-mapping it via resolve_model_name_from_model_id is first-match on model_list and caused false 403s when multiple deployments share the same stripped name. Use target_model_names from the unified file id instead.

Co-authored-by: Cursor <[email protected]>

* fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)

Restores the reverse-lookup for the JSONL body.model fallback path so that
legacy/pre-target_model_names managed files still map stripped provider IDs
back to proxy aliases before auth. Also cleans up redundant `or None`.

Co-Authored-By: Claude Sonnet 4.6 <[email protected]>

* Revert "fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)"

This reverts commit 30d2e96.

---------

Co-authored-by: Cursor <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>

* fix(mcp): report scoped server name during initialize (#29865)

* fix mcp scoped server name

* Update litellm/proxy/_experimental/mcp_server/mcp_context.py

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* test(mcp): cover scoped server name in the SSE initialize handler

---------

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* fix(ui): show all session logs in the drawer, not just the first 50 (#29795)

* fix(ui): show newest session logs first

* test(ui): keep session log pagination coverage

* fix(ui): show all session logs in the drawer, not just the first page

The session detail drawer fetched session logs via sessionSpendLogsCall
without page/page_size, so it only ever received the backend default of one
page (50 rows). Sessions with more than 50 calls had the rest unreachable in
the UI (#29153).

sessionSpendLogsCall now takes page/page_size, and the drawer fetches the
first page, reads total_pages, then fetches the remaining pages and
accumulates them before the existing client-side sort. This keeps the single
continuous list (and the selected-log lookup and keyboard navigation, which
all assume the full session) correct. Fetching is bounded by a page cap, and
the sidebar shows a "showing most recent N" note if a session exceeds it.

The rows are lightweight metadata (the endpoint excludes messages/response),
so the full set is small; request/response bodies are still loaded per log on
demand.

* fix(ui): default session drawer to most recent log, newest first

Open a session with its most recent log selected, and order the sidebar
newest-first to match the all-sessions logs overview. MCP calls stay
grouped last. The latest log by time is computed explicitly, since the
MCP grouping means it is not always the first row.

* Apply fetching pages in batches suggestion from @greptile-apps[bot]

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* fix(ui): derive session total from accumulated rows when backend omits it

Compute the session total after all pages are fetched, falling back to the
accumulated row count rather than the first page's. Guards the truncation
note against a backend response that omits total but spans multiple pages.

---------

Co-authored-by: Yufeng He <[email protected]>
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* fix(proxy): handle Mistral multipart passthrough (#29927)

* fix(proxy): handle Mistral multipart passthrough

* chore: satisfy passthrough ci formatting

* test(proxy): cover Mistral passthrough in CI shard

* fix(vertex_ai): use REP host for context caching on eu/us multi-region endpoints (#29573)

Context caching built the cachedContents URL as
https://{location}-aiplatform.googleapis.com, which is an invalid host for the
eu/us multi-region endpoints and returns 404. The inference path already
resolves these to the REP host (https://aiplatform.{geo}.rep.googleapis.com)
via get_vertex_base_url(); reuse that helper in
_get_token_and_url_context_caching so caching uses the same host as inference.

Adds tests covering the eu/us multi-region cachedContents URLs (v1 and
v1beta1).

Fixes #29571

* Support per-model encrypted content affinity config (#29760)

Co-authored-by: shin-berri <[email protected]>
Co-authored-by: yuneng-jiang <[email protected]>

* fix: propagate upstream status code in proxy API exception handler (#29402)

* fix: propagate upstream status code in proxy API exception handler

When Google GenAI / Vertex returns a 404 for deprecated or missing
models via streamGenerateContent, the exception was falling through to
a generic handler that defaulted to 500. Now provider exceptions
carrying a valid HTTP status_code correctly propagate it through to
the ProxyException.

* fix: apply black formatting to common_request_processing.py

* fix: tighten status code range to 400-599 and deduplicate ProxyException raise

* fix(tests): use valid vertex_location in context caching tests

Replace "test_location" (contains underscore) with "us-central1" so tests
pass the regex validation added in get_vertex_base_url().

Co-Authored-By: Claude Sonnet 4.6 <[email protected]>

* feat(sdk): add xAI OAuth provider (#29866)

* Add xAI OAuth provider

* Update oauth.py

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* Fix xAI OAuth CI failures

* Add xAI OAuth coverage tests

* Move xAI OAuth coverage tests to core utils

* Address xAI OAuth review comments

* Prevent xAI OAuth api_base token exfiltration

* Treat blank xAI OAuth api keys as absent

* Wrap invalid xAI OAuth JSON responses

* Use xAI OAuth behind explicit flag

---------

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* fix(proxy) #27734 allow clearing budget_duration and team_member fields by sending null on /key/update and /team/update (#27751)

* fix(proxy): allow clearing budget_duration and team_member fields by sending null on /key/update and /team/update

Fixes #27734

Sending null for budget_duration, team_member_budget,
team_member_budget_duration, team_member_rpm_limit, or
team_member_tpm_limit via /key/update or /team/update returned 200 OK
but silently ignored the null value. The fields remained unchanged in
the database.

Root causes:
- /key/update: prepare_key_update_data() popped budget_duration from the
  update dict but never re-added it (or budget_reset_at) when the value
  was None.
- /team/update: _set_budget_reset_at() only acted when budget_duration
  was non-None, leaving a stale budget_reset_at in the DB.
- /team/update: team_member_* null values bypassed the budget table
  update entirely because should_create_budget() requires at least one
  non-None field.

* test(proxy): cover no-budget-row path in clear_team_member_budget_fields

* fix(presidio): unmask PII tokens in Anthropic native SSE streaming bytes (#30028)

* fix(presidio): unmask PII tokens in Anthropic native SSE streaming bytes

When output_parse_pii=true on the Anthropic native path (anthropic/claude-*),
response chunks arrive as raw bytes in SSE format. _stream_pii_unmasking was
yielding those bytes unchanged, so <PERSON_1> tokens were never replaced with
the original values before reaching the caller.

Add _unmask_sse_bytes_chunk to parse each data: line, find content_block_delta
/ text_delta events, and apply _unmask_pii_text before re-encoding. Wire it
into _stream_pii_unmasking so bytes chunks are unmasked when pii_tokens exist.

* fix(presidio): handle CRLF line endings and non-ASCII PII in SSE unmask

Strip trailing \r before the [DONE] guard so CRLF-terminated SSE chunks
don't bypass it and silently swallow a JSONDecodeError. Add
ensure_ascii=False to json.dumps so non-ASCII replacement values like
accented names are preserved as UTF-8 on the wire rather than being
\uXXXX-escaped. Add regression tests for both cases.

* feat(bedrock_mantle): path-aware Responses routing (/v1/responses vs /openai/v1/responses) (#29925)

* feat(bedrock_mantle): path-aware Responses routing (/v1/responses vs /openai/v1/responses)

Bedrock Mantle serves the Responses API on two upstream paths:
  - gpt frontier models (gpt-5.5 / gpt-5.4) on /openai/v1/responses
  - every other Responses-capable model (e.g. gpt-oss) on the standard /v1/responses

BedrockMantleResponsesAPIConfig gains a `use_openai_path` flag; the provider gate in
utils.py picks the path per model: openai.gpt-* (non gpt-oss) -> /openai/v1/responses;
any model declared mode=responses (price-map entry or user model_info) -> /v1/responses;
everything else returns None and keeps the existing chat-completions emulation.

Adds gpt-5.5 / gpt-5.4 price-map entries, registry wiring, and the routing-matrix tests.

* feat(bedrock_mantle): data-driven frontier routing via use_openai_responses_path

Addresses the Greptile review point that frontier detection should be a
price-map field rather than a hardcoded name match. The gate now routes a
model to /openai/v1/responses when its price-map entry declares
use_openai_responses_path, so a frontier model whose name does not follow the
openai.gpt- convention can be onboarded by JSON alone. The name-convention
check is kept as a fallback that needs no price-map entry, which preserves
zero-change routing for a future gpt-6 before its entry loads. gpt-5.5 / gpt-5.4
get the flag in both price maps. Adds tests for the data-driven flag path and
for the flag presence on the gpt-5.x entries; both branches are mutation-tested.

* test(model_prices): allow use_openai_responses_path in price-map schema

The model_prices_and_context_window.json schema validator
(test_aaamodel_prices_and_context_window_json_is_valid) enforces
additionalProperties: false, so the new use_openai_responses_path flag on the
gpt-5.5 / gpt-5.4 entries failed validation. Add it to the schema as a boolean,
alongside the other supports_* / capability flags.

* Add Tensormesh serverless models to the model cost map (#30037)

* Add Tensormesh serverless models to the model cost map

* Flag reasoning support on the Tensormesh models that expose thinking mode

* fix(proxy): invalidate stale key spend counter after budget reset or manual spend update (#30001)

* fix(proxy): reconcile stale key spend counter after budget reset

* fix(proxy): invalidate stale key spend counter after budget reset or manual spend update

* fix(proxy): remove read-time stale counter reconciliation to prevent budget bypass

* revert: undo unrelated formatting changes in enterprise directory

* test(proxy): add unit test for key spend update invalidating counter

* test(proxy): fix mocked update_data and hash token expectations in unit test

* fix(proxy): use Responses-API transformer in pass-through cost tracking (#29728)

The `elif is_responses:` branch of `openai_passthrough_handler` was
calling the chat-completions `transform_response` on a Responses API
payload. The chat-completions transformer expects `choices: [...]`
in the raw response; the Responses API uses `output: [...]` and
`usage.input_tokens` / `usage.output_tokens` (not
`prompt_tokens` / `completion_tokens`). The result was a
KeyError 'choices' deep inside `convert_to_model_response_object`,
swallowed by the surrounding `except Exception` in the handler, and
the SpendLogs row was written by the fallback path with zeroed-out
tokens, spend, and model.

This bug silently undercounts cost for every successful pass-through
call to either OpenAI's `/v1/responses` or Azure's
`/openai/v1/responses` (deployments configured for the Responses
API). Reproduced 2026-06-04 against a real Azure OpenAI Responses
API deployment proxied through LiteLLM v1.88.0.

Fix: use the dedicated
`OpenAIResponsesAPIConfig.transform_response_api_response` for the
Responses branch. This transformer already exists in LiteLLM
(`litellm/llms/openai/responses/transformation.py`) and knows the
Responses-API on-the-wire shape. `litellm.completion_cost` already
handles `ResponsesAPIResponse` natively with `call_type="responses"`,
so no downstream changes are needed.

Tests:

  test_responses_api_uses_responses_transformer_not_chat_completions
    NEW. Real regression test — exercises the openai_passthrough_handler
    with a real-shaped Responses payload (no `choices`, has `output`
    and Responses-API `usage` keys) and NO mocked `get_provider_config`.
    Pre-fix: raises KeyError 'choices' inside the chat-completions
    transformer (the bug). Post-fix: returns a ResponsesAPIResponse,
    completion_cost is called with call_type="responses" and a
    ResponsesAPIResponse instance (asserted).
    Verified to fail on un-fixed handler + pass on fixed handler
    before commit.

  test_responses_api_cost_tracking
    UPDATED. Old test mocked `get_provider_config` (no longer called
    in the responses branch post-fix). Now mocks the Responses
    transformer directly (`OpenAIResponsesAPIConfig.transform_response_api_response`)
    to test the downstream cost-calc contract.

Out of scope for this PR (separate followup):
  - Recognizing *.cognitiveservices.azure.com (the newer Azure
    OpenAI hostname) in the is_openai_*_route checks. Separate PR.

Co-authored-by: shin-berri <[email protected]>
Co-authored-by: yuneng-jiang <[email protected]>

* fix(skills): execute DB skills by matching the litellm_skill_ tool name prefix (#30116)

Skill IDs are generated as litellm_skill_<uuid> and the model-facing
tool name is the sanitized skill ID, but the post-call execution gates
in SkillsInjectionHook only ran tools whose name starts with "skill_",
so DB skills were silently returned to the client as raw tool calls.

Fixes #28122.

Co-authored-by: Cursor <[email protected]>

* fix(anthropic): synthesize content_block_start when Responses stream omits output_item.added (#30115)

* fix(team): reserve team budget raises for proxy admins on /team/update (#30030)

The caller's PERSONAL max_budget was the wrong yardstick for /team/update: a
team's spend ceiling has nothing to do with the admin's own key budget. That
comparison was an unintended side effect of reusing _check_user_team_limits()
(which exists for the /team/new path) and broke the UI, which re-sends the
unchanged budget on every save.

New behavior on /team/update for standalone teams:
- A team admin (already authorized via _verify_team_access) may freely KEEP or
  LOWER the team budget, and change models/tpm/rpm, without being gated by their
  personal limits.
- GROWING a team's spend ceiling is a budget-authority action reserved for proxy
  admins -> 403 for team admins. "Growing" covers both raising max_budget above
  the team's current finite value and removing the cap entirely (max_budget=null,
  detected via model_fields_set so an explicit null is distinguished from an
  omitted field). For a team that currently has no cap, setting a finite value is
  a restriction and is allowed.
- Org-scoped teams remain governed by _check_org_team_limits() (capped by the
  org budget).

Also reverts the #29525 existing_team_max_budget workaround in
_check_user_team_limits() back to the create-only form; /team/new still enforces
the creator's personal caps.

docs(access_control): resolve the contradiction in the team-admin section —
team admins can keep/lower the budget and manage rate limits/models, but cannot
raise the team budget (proxy-admin only).

tests: unit + behavior coverage for raise-blocked, cap-removal-blocked (team
admin), raise/removal allowed (proxy admin), uncapped-team restriction allowed,
keep/lower/resend allowed, and unchanged create-path guards.

Co-authored-by: Cursor <[email protected]>

* test(ui): data-driven App Router migration E2E smoke (default + server-root-path) (#29974)

* test(ui): add a data-driven App Router migration E2E smoke

Add a growing Playwright smoke for migrated pages: for each segment it deep-links
to the path route, asserts the URL and that the dashboard shell rendered, then
clicks off to a legacy page and asserts navigation still works. Driven by
e2e_tests/fixtures/migratedPages.ts, so adding a page is one line.

Runs in two situations against the same proxy: the default mount (npm run
e2e:migration) and a non-root SERVER_ROOT_PATH mount (npm run e2e:migration:root).
globalSetup now logs in at `${SERVER_ROOT_PATH}/ui/login` so the admin storage
state is valid under a prefix. Seeded with api-reference; append the rest as their
migrations merge.

* test(ui): support headed slow-motion + watch pauses in the migration smoke

Honor SLOWMO in the server-root-path config (the default config already did),
and add an env-gated E2E_WATCH_MS pause so a headed run lingers on each state.
Both are no-ops by default, so CI behavior is unchanged.

* test(ui): make the migration smoke a sidebar-click user journey

Rework the smoke from deep-linking to a real navigation journey: start at the
landing page, click the migrated page in the sidebar (expanding submenus for
nested items), assert the path route rendered, reload it (the check a wrong
server_root_path breaks), bounce to a legacy page and back, and — once two pages
are migrated — navigate directly between two migrated pages. Verifies via URL +
shell render, driven by the same fixture list.

* test(ui): address review on the migration smoke

Escape ROOT and segment before interpolating them into RegExp URL matchers so a
future segment containing regex metacharacters can't silently widen the match.
Make the server-root-path config fail fast when SERVER_ROOT_PATH is unset instead
of silently re-running the default mount and passing without exercising the prefix.

* test(ui): drop unused watch helper and fix stale smoke README

* test(ui): run the migration smoke under a server root path in CI

* test(ui): harden + instrument the server-root-path proxy reboot in CI

* test(ui): run the server-root-path migration smoke as its own CI job

Replace the in-place proxy reboot in e2e_ui_testing with a dedicated
e2e_ui_testing_server_root_path job that boots the proxy once with
SERVER_ROOT_PATH=/litellm, matching how every other proxy variant in the
config gets its own job rather than killing and relaunching the live proxy.

The reboot was failing deterministically: after pkill -9 and relaunch the
prefixed proxy never came back up on :4000 (connection refused), so the smoke
never ran. The readiness step that was supposed to surface the cause could
never reach its boot-log tail because CircleCI runs steps under bash -eo
pipefail and the preceding `curl -sv ... | tail` aborted the step with curl's
exit 7. Booting the proxy as the job's own background step lets any boot crash
land in that step's log instead of being swallowed.

The default e2e_ui_testing job is unchanged aside from dropping the reboot,
prefixed-readiness, and prefixed-smoke steps; the migration smoke still runs at
the root mount there via the default Playwright config.

* fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through (#24232)

* fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through

* test: mock post_call_response_headers_hook in audio speech route tests

* chore(ui): remove dead App Router route stubs under (dashboard) (#30045)

models-and-endpoints, organizations, and virtual-keys each had a page.tsx
route under (dashboard)/ that is not in MIGRATED_PAGES, so the sidebar and
deep links never resolve to it and the route is unreachable. Each was a thin
wrapper that handed the shared view empty or no-op props (empty modelData with
a no-op setModelData, hardcoded empty organizations, no-op
setUserRole/setUserEmail), so reaching one would render a degraded page in any
case. The real wrapper belongs in the PR that flips each page into
MIGRATED_PAGES, written with eyes on it and a test

This continues the dead-scaffolding cleanup from #28891. The shared components
these wrappers rendered (ModelsAndEndpointsView, OrganizationFilters) stay,
since the legacy ?page= switch in app/page.tsx and src/components still import
them

* fix(ui/mcp): reset OAuth state on create-server modal close so a prior server's token no longer leaks into the next add-server session (#30000)

* fix(ui/mcp): reset OAuth hook state on modal close so a prior server's token no longer leaks into the next add-server session

* fix(ui/mcp): clear in-flight OAuth guard on reset and reset form/tools on modal close so nothing leaks on a parent-driven dismiss

* fix(mcp): allow team access-group grants in OAuth authorize/token access check (#30041)

* fix(mcp): honor team access-group grants in OAuth authorize/token access check

* test(mcp): mock build_effective_auth_contexts in non-admin authorize tests for isolation

* docs(security): require a reproduction video for vulnerability reports (#30048) (#30063)

With AI models capable of automated vulnerability discovery now publicly
available, we expect a large increase in report volume, much of it
unverified. Requiring a video of the exploit running against a live
instance raises the bar for submissions and keeps triage focused on
reproducible issues. Reports without a video will be closed and reopened
if one is added later.

Co-authored-by: stuxf <[email protected]>

* feat(ui): add admin flag to disable in-product UI nudges for everyone (#29796)

* feat(ui): add admin flag to disable in-product UI nudges for everyone

Admins can now suppress the survey and Claude Code feedback popups for
all users via a single disable_ui_nudges UI setting, instead of relying
on each user dismissing them individually.

* fix(ui): suppress nudges while ui settings are loading

Gate nudgesDisabled on the ui-settings loading state so an admin with
disable_ui_nudges on doesn't see the survey prompt flash, and the
getInProductNudgesCall fetch doesn't fire, on a cold page load before
the flag resolves. Falls back to showing nudges if the fetch errors.

* test(ui): wrap CreateKeyPage test in QueryClientProvider

page.tsx now calls useUISettings (react-query), which needs a
QueryClient that layout.tsx supplies in production but the test did
not. Add the provider and mock getUiSettings so the query resolves.

* chore(ui): remove dead dashboard files and unused dependencies (#30047)

* chore(ui): remove dead dashboard files and unused dependencies

knip flagged seven orphaned source/config files with no importers and
five declared dependencies that nothing in the tree uses. Removing them
shrinks the dashboard bundle's source surface and keeps the manifest
honest; vite stays installed transitively via vitest, so test tooling is
unaffected.

* fix(ci): restore serverRootPath.config.ts referenced by SERVER_ROOT_PATH workflow

The dead-code sweep removed e2e_tests/serverRootPath.config.ts, but its spec
(tests/login/serverRootPathRedirect.spec.ts) and the test_server_root_path.yml
workflow step still depend on it, so the redirect e2e job failed to load a
config that no longer existed.

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593) (#30009)

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593)

After replace_model_in_jsonl, body.model is a stripped provider id. Reverse-mapping it via resolve_model_name_from_model_id is first-match on model_list and caused false 403s when multiple deployments share the same stripped name. Use target_model_names from the unified file id instead.

Co-authored-by: Cursor <[email protected]>

* fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)

Restores the reverse-lookup for the JSONL body.model fallback path so that
legacy/pre-target_model_names managed files still map stripped provider IDs
back to proxy aliases before auth. Also cleans up redundant `or None`.

Co-Authored-By: Claude Sonnet 4.6 <[email protected]>

* Revert "fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)"

This reverts commit 30d2e96f77ef521ccaaf2193fe554980380eb669.

---------

Co-authored-by: Cursor <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>

* Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI (#30064)

* Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI

Adds cost map entries for claude-fable-5 ($10/$50 per MTok, 1M context,
128K output, adaptive thinking only) on the Anthropic API, Bedrock
converse (base, global, and us/eu geo inference profiles at the 10%
regional premium), Vertex AI, and Azure AI (Microsoft Foundry, which
serves Fable 5 with the full 1M context window unlike Opus 4.8).

Registers anthropic.claude-fable-5 in BEDROCK_CONVERSE_MODELS, lists the
model in the setup wizard, and extends the reasoning effort e2e grid.
The Bedrock, Vertex, and Azure grid cells carry fail_reason markers
until the CI accounts are provisioned: Bedrock needs the provider data
sharing opt-in Fable 5 requires, and the Foundry resource needs a
claude-fable-5 deployment.

The first-party entry carries provider_specific_entry {us: 1.1} for the
inference_geo premium and deliberately no fast multiplier since Fable 5
has no fast mode.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Drop removed sampling params for Claude 4.7+ when drop_params is set

Fable 5, Opus 4.7, and Opus 4.8 removed sampling params: the API rejects
top_p, top_k, and any temperature other than 1 with a 400. LiteLLM was
forwarding them even with drop_params enabled because the Anthropic and
Bedrock converse transformations passed temperature/top_p through
unconditionally.

Mirror the GPT-5/o-series handling: temperature=1 still passes through,
other values and any top_p are dropped when drop_params is set, and
without drop_params a clean client-side UnsupportedParamsError tells the
caller how to opt in, instead of surfacing the raw provider error.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Drive sampling param gating from the cost map and cover top_k

Greptile review follow-ups on the sampling param fix: the restriction for
Fable 5 / Opus 4.7 / 4.8 is now declared as supports_sampling_params: false
on every affected cost map entry (perplexity excluded; that route is
OpenAI-compatible and maps sampling params upstream) and read back through
a tri-state map lookup, keeping the name check only as a fallback for
provider-routed ids whose hosted map entries predate the flag, the same
layering supports_adaptive_thinking uses. top_k bypasses map_openai_params
as a provider-specific kwarg, so it is gated at the shared
AnthropicConfig.transform_request boundary (direct, Bedrock invoke, Vertex,
Azure) and in the Bedrock converse _handle_top_k_value path, with
drop_params threaded through the converse transform helpers.

Also updates the reasoning effort grid cell count assertion for the four
Fable 5 rows added on this branch (29 x 11 cells).

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Declare supports_sampling_params in the cost map schema

The model map validation schema uses additionalProperties: false, so the
new flag must be declared for the 28 entries that carry it; this was the
one failing job (misc / Run tests) on the previous commit.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* fix(bedrock): gate top_k=0 on converse to match Anthropic boundary

Truthiness check let top_k=0 silently disappear on models that removed
sampling params, while AnthropicConfig.transform_request treats 0 as
present and raises UnsupportedParamsError (or drops when drop_params is
set). Switch to 'is not None' so converse, direct Anthropic, invoke,
Vertex, and Azure all behave the same for top_k=0.

---------

Co-authored-by: Cursor Agent <[email protected]>

* fix(anthropic): avoid index -1 content_block_delta in messages stream

When a /v1/messages request is routed through the Responses API
adapter, AnthropicResponsesStreamWrapper only emits content_block_start
on response.output_item.added. Some upstreams (LMStudio for example)
never send that event, so the text delta handler fell back to
_current_block_index, which starts at -1, and clients received
content_block_delta events with index -1 and no preceding
content_block_start. Anthropic SDKs then fail with "text part -1 not
found"

The text delta handler now synthesizes a content_block_start with a
fresh block index whenever the delta references an unregistered item_id
or no block is open yet, and registers the item_id so follow-up deltas
reuse the same index

Addresses the /v1/messages defect in #27442

* Make test sys.path shim resolve relative to the file, not the CWD

os.path.abspath("../../../../../../..") depends on where pytest is
invoked from; anchoring on os.path.dirname(__file__) makes the import
work from any working directory. Also corrects the depth: the repo root
is six levels above this file, not seven.

---------

Co-authored-by: milan-berri <[email protected]>
Co-authored-by: Cursor <[email protected]>
Co-authored-by: ryan-crabbe-berri <[email protected]>
Co-authored-by: michelligabriele <[email protected]>
Co-authored-by: tin-berri <[email protected]>
Co-authored-by: yuneng-jiang <[email protected]>
Co-authored-by: stuxf <[email protected]>
Co-authored-by: Sameer Kankute <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>
Co-authored-by: Mateo Wang <[email protected]>

* fix: enable compact-2026-01-12 beta header for vertex_ai provider (#30114)

* fix(team): reserve team budget raises for proxy admins on /team/update (#30030)

The caller's PERSONAL max_budget was the wrong yardstick for /team/update: a
team's spend ceiling has nothing to do with the admin's own key budget. That
comparison was an unintended side effect of reusing _check_user_team_limits()
(which exists for the /team/new path) and broke the UI, which re-sends the
unchanged budget on every save.

New behavior on /team/update for standalone teams:
- A team admin (already authorized via _verify_team_access) may freely KEEP or
  LOWER the team budget, and change models/tpm/rpm, without being gated by their
  personal limits.
- GROWING a team's spend ceiling is a budget-authority action reserved for proxy
  admins -> 403 for team admins. "Growing" covers both raising max_budget above
  the team's current finite value and removing the cap entirely (max_budget=null,
  detected via model_fields_set so an explicit null is distinguished from an
  omitted field). For a team that currently has no cap, setting a finite value is
  a restriction and is allowed.
- Org-scoped teams remain governed by _check_org_team_limits() (capped by the
  org budget).

Also reverts the #29525 existing_team_max_budget workaround in
_check_user_team_limits() back to the create-only form; /team/new still enforces
the creator's personal caps.

docs(access_control): resolve the contradiction in the team-admin section —
team admins can keep/lower the budget and manage rate limits/models, but cannot
raise the team budget (proxy-admin only).

tests: unit + behavior coverage for raise-blocked, cap-removal-blocked (team
admin), raise/removal allowed (proxy admin), uncapped-team restriction allowed,
keep/lower/resend allowed, and unchanged create-path guards.

Co-authored-by: Cursor <[email protected]>

* test(ui): data-driven App Router migration E2E smoke (default + server-root-path) (#29974)

* test(ui): add a data-driven App Router migration E2E smoke

Add a growing Playwright smoke for migrated pages: for each segment it deep-links
to the path route, asserts the URL and that the dashboard shell rendered, then
clicks off to a legacy page and asserts navigation still works. Driven by
e2e_tests/fixtures/migratedPages.ts, so adding a page is one line.

Runs in two situations against the same proxy: the default mount (npm run
e2e:migration) and a non-root SERVER_ROOT_PATH mount (npm run e2e:migration:root).
globalSetup now logs in at `${SERVER_ROOT_PATH}/ui/login` so the admin storage
state is valid under a prefix. Seeded with api-reference; append the rest as their
migrations merge.

* test(ui): support headed slow-motion + watch pauses in the migration smoke

Honor SLOWMO in the server-root-path config (the default config already did),
and add an env-gated E2E_WATCH_MS pause so a headed run lingers on each state.
Both are no-ops by default, so CI behavior is unchanged.

* test(ui): make the migration smoke a sidebar-click user journey

Rework the smoke from deep-linking to a real navigation journey: start at the
landing page, click the migrated page in the sidebar (expanding submenus for
nested items), assert the path route rendered, reload it (the check a wrong
server_root_path breaks), bounce to a legacy page and back, and — once two pages
are migrated — navigate directly between two migrated pages. Verifies via URL +
shell render, driven by the same fixture list.

* test(ui): address review on the migration smoke

Escape ROOT and segment before interpolating them into RegExp URL matchers so a
future segment containing regex metacharacters can't silently widen the match.
Make the server-root-path config fail fast when SERVER_ROOT_PATH is unset instead
of silently re-running the default mount and passing without exercising the prefix.

* test(ui): drop unused watch helper and fix stale smoke README

* test(ui): run the migration smoke under a server root path in CI

* test(ui): harden + instrument the server-root-path proxy reboot in CI

* test(ui): run the server-root-path migration smoke as its own CI job

Replace the in-place proxy reboot in e2e_ui_testing with a dedicated
e2e_ui_testing_server_root_path job that boots the proxy once with
SERVER_ROOT_PATH=/litellm, matching how every other proxy variant in the
config gets its own job rather than killing and relaunching the live proxy.

The reboot was failing deterministically: after pkill -9 and relaunch the
prefixed proxy never came back up on :4000 (connection refused), so the smoke
never ran. The readiness step that was supposed to surface the cause could
never reach its boot-log tail because CircleCI runs steps under bash -eo
pipefail and the preceding `curl -sv ... | tail` aborted the step with curl's
exit 7. Booting the proxy as the job's own background step lets any boot crash
land in that step's log instead of being swallowed.

The default e2e_ui_testing job is unchanged aside from dropping the reboot,
prefixed-readiness, and prefixed-smoke steps; the migration smoke still runs at
the root mount there via the default Playwright config.

* fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through (#24232)

* fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through

* test: mock post_call_response_headers_hook in audio speech route tests

* chore(ui): remove dead App Router route stubs under (dashboard) (#30045)

models-and-endpoints, organizations, and virtual-keys each had a page.tsx
route under (dashboard)/ that is not in MIGRATED_PAGES, so the sidebar and
deep links never resolve to it and the route is unreachable. Each was a thin
wrapper that handed the shared view empty or no-op props (empty modelData with
a no-op setModelData, hardcoded empty organizations, no-op
setUserRole/setUserEmail), so reaching one would render a degraded page in any
case. The real wrapper belongs in the PR that flips each page into
MIGRATED_PAGES, written with eyes on it and a test

This continues the dead-scaffolding cleanup from #28891. The shared components
these wrappers rendered (ModelsAndEndpointsView, OrganizationFilters) stay,
since the legacy ?page= switch in app/page.tsx and src/components still import
them

* fix(ui/mcp): reset OAuth state on create-server modal close so a prior server's token no longer leaks into the next add-server session (#30000)

* fix(ui/mcp): reset OAuth hook state on modal close so a prior server's token no longer leaks into the next add-server session

* fix(ui/mcp): clear in-flight OAuth guard on reset and reset form/tools on modal close so nothing leaks on a parent-driven dismiss

* fix(mcp): allow team access-group grants in OAuth authorize/token access check (#30041)

* fix(mcp): honor team access-group grants in OAuth authorize/token access check

* test(mcp): mock build_effective_auth_contexts in non-admin authorize tests for isolation

* docs(security): require a reproduction video for vulnerability reports (#30048) (#30063)

With AI models capable of automated vulnerability discovery now publicly
available, we expect a large increase in report volume, much of it
unverified. Requiring a video of the exploit running against a live
instance raises the bar for submissions and keeps triage focused on
reproducible issues. Reports without a video will be closed and reopened
if one is added later.

Co-authored-by: stuxf <[email protected]>

* feat(ui): add admin flag to disable in-product UI nudges for everyone (#29796)

* feat(ui): add admin flag to disable in-product UI nudges for everyone

Admins can now suppress the survey and Claude Code feedback popups for
all users via a single disable_ui_nudges UI setting, instead of relying
on each user dismissing them individually.

* fix(ui): suppress nudges while ui settings are loading

Gate nudgesDisabled on the ui-settings loading state so an admin with
disable_ui_nudges on doesn't see the survey prompt flash, and the
getInProductNudgesCall fetch doesn't fire, on a cold page load before
the flag resolves. Falls back to showing nudges if the fetch errors.

* test(ui): wrap CreateKeyPage test in QueryClientProvider

page.tsx now calls useUISettings (react-query), which needs a
QueryClient that layout.tsx supplies in production but the test did
not. Add the provider and mock getUiSettings so the query resolves.

* chore(ui): remove dead dashboard files and unused dependencies (#30047)

* chore(ui): remove dead dashboard files and unused dependencies

knip flagged seven orphaned source/config files with no importers and
five declared dependencies that nothing in the tree uses. Removing them
shrinks the dashboard bundle's source surface and keeps the manifest
honest; vite stays installed transitively via vitest, so test tooling is
unaffected.

* fix(ci): restore serverRootPath.config.ts referenced by SERVER_ROOT_PATH workflow

The dead-code sweep removed e2e_tests/serverRootPath.config.ts, but its spec
(tests/login/serverRootPathRedirect.spec.ts) and the test_server_root_path.yml
workflow step still depend on it, so the redirect e2e job failed to load a
config that no longer existed.

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593) (#30009)

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593)

After replace_model_in_jsonl, body.model is a stripped provider id. Reverse-mapping it via resolve_model_name_from_model_id is first-match on model_list and caused false 403s when multiple deployments share the same stripped name. Use target_model_names from the unified file id instead.

Co-authored-by: Cursor <[email protected]>

* fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)

Restores the reverse-lookup for the JSONL body.model fallback path so that
legacy/pre-target_model_names managed files still map stripped provider IDs
back to proxy aliases before auth. Also cleans up redundant `or None`.

Co-Authored-By: Claude Sonnet 4.6 <[email protected]>

* Revert "fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)"

This reverts commit 30d2e96f77ef521ccaaf2193fe554980380eb669.

---------

Co-authored-by: Cursor <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>

* Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI (#30064)

* Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI

Adds cost map entries for claude-fable-5 ($10/$50 per MTok, 1M context,
128K output, adaptive thinking only) on the Anthropic API, Bedrock
converse (base, global, and us/eu geo inference profiles at the 10%
regional premium), Vertex AI, and Azure AI (Microsoft Foundry, which
serves Fable 5 with the full 1M context window unlike Opus 4.8).

Registers anthropic.claude-fable-5 in BEDROCK_CONVERSE_MODELS, lists the
model in the setup wizard, and extends the reasoning effort e2e grid.
The Bedrock, Vertex, and Azure grid cells carry fail_reason markers
until the CI accounts are provisioned: Bedrock needs the provider data
sharing opt-in Fable 5 requires, and the Foundry resource needs a
claude-fable-5 deployment.

The first-party entry carries provider_specific_entry {us: 1.1} for the
inference_geo premium and deliberately no fast multiplier since Fable 5
has no fast mode.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Drop removed sampling params for Claude 4.7+ when drop_params is set

Fable 5, Opus 4.7, and Opus 4.8 removed sampling params: the API rejects
top_p, top_k, and any temperature other than 1 with a 400. LiteLLM was
forwarding them even with drop_params enabled because the Anthropic and
Bedrock converse transformations passed temperature/top_p through
unconditionally.

Mirror the GPT-5/o-series handling: temperature=1 still passes through,
other values and any top_p are dropped when drop_params is set, and
without drop_params a clean client-side UnsupportedParamsError tells the
caller how to opt in, instead of surfacing the raw provider error.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Drive sampling param gating from the cost map and cover top_k

Greptile review follow-ups on the sampling param fix: the restriction for
Fable 5 / Opus 4.7 / 4.8 is now declared as supports_sampling_params: false
on every affected cost map entry (perplexity excluded; that route is
OpenAI-compatible and maps sampling params upstream) and read back through
a tri-state map lookup, keeping the name check only as a fallback for
provider-routed ids whose hosted map entries predate the flag, the same
layering supports_adaptive_thinking uses. top_k bypasses map_openai_params
as a provider-specific kwarg, so it is gated at the shared
AnthropicConfig.transform_request boundary (direct, Bedrock invoke, Vertex,
Azure) and in the Bedrock converse _handle_top_k_value path, with
drop_params threaded through the converse transform helpers.

Also updates the reasoning effort grid cell count assertion for the four
Fable 5 rows added on this branch (29 x 11 cells).

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Declare supports_sampling_params in the cost map schema

The model map validation schema uses additionalProperties: false, so the
new flag must be declared for the 28 entries that carry it; this was the
one failing job (misc / Run tests) on the previous commit.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* fix(bedrock): gate top_k=0 on converse to match Anthropic boundary

Truthiness check let top_k=0 silently disappear on models that removed
sampling params, while AnthropicConfig.transform_request treats 0 as
present and raises UnsupportedParamsError (or drops when drop_params is
set). Switch to 'is not None' so converse, direct Anthropic, invoke,
Vertex, and Azure all behave the same for top_k=0.

---------

Co-authored-by: Cursor Agent <[email protected]>

* fix: enable compact-2026-01-12 beta header for vertex_ai provider

The vertex_ai block in anthropic_beta_headers_config.json mapped
compact-2026-01-12 to null, so update_headers_with_filtered_beta
stripped the header before the request reached Vertex while the
compact_20260112 context edit stayed in the body, and Vertex rejected
the request with HTTP 400. Vertex rawPredict accepts the header, and
the bedrock and databricks blocks already forward it. Mirrors #21867,
which enabled context-1m-2025-08-07 for vertex_ai the same way.

Fixes #27290.

---------

Co-authored-by: milan-berri <[email protected]>
Co-authored-by: Cursor <[email protected]>
Co-authored-by: ryan-crabbe-berri <[email protected]>
Co-authored-by: michelligabriele <[email protected]>
Co-authored-by: tin-berri <[email protected]>
Co-authored-by: yuneng-jiang <[email protected]>
Co-authored-by: stuxf <[email protected]>
Co-authored-by: Sameer Kankute <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>
Co-authored-by: Mateo Wang <[email protected]>

* fix(proxy): coerce litellm_settings.max_budget env var to float (#30113)

* fix(team): reserve team budget raises for proxy admins on /team/update (#30030)

The caller's PERSONAL max_budget was the wrong yardstick for /team/update: a
team's spend ceiling has nothing to do with the admin's own key budget. That
comparison was an unintended side effect of reusing _check_user_team_limits()
(which exists for the /team/new path) and broke the UI, which re-sends the
unchanged budget on every save.

New behavior on /team/update for standalone teams:
- A team admin (already authorized via _verify_team_access) may freely KEEP or
  LOWER the team budget, and change models/tpm/rpm, without being gated by their
  personal limits.
- GROWING a team's spend ceiling is a budget-authority action reserved for proxy
  admins -> 403 for team admins. "Growing" covers both raising max_budget above
  the team's current finite value and removing the cap entirely (max_budget=null,
  detected via model_fields_set so an explicit null is distinguished from an
  omitted field). For a team that currently has no cap, setting a finite value is
  a restriction and is allowed.
- Org-scoped teams remain governed by _check_org_team_limits() (capped by the
  org budget).

Also reverts the #29525 existing_team_max_budget workaround in
_check_user_team_limits() back to the create-only form; /team/new still enforces
the creator's personal caps.

docs(access_control): resolve the contradiction in the team-admin section —
team admins can keep/lower the budget and manage rate limits/models, but cannot
raise the team budget (proxy-admin only).

tests: unit + behavior coverage for raise-blocked, cap-removal-blocked (team
admin), raise/removal allowed (proxy admin), uncapped-team restriction allowed,
keep/lower/resend allowed, and unchanged create-path guards.

Co-authored-by: Cursor <[email protected]>

* test(ui): data-driven App Router migration E2E smoke (default + server-root-path) (#29974)

* test(ui): add a data-driven App Router migration E2E smoke

Add a growing Playwright smoke for migrated pages: for each segment it deep-links
to the path route, asserts the URL and that the dashboard shell rendered, then
clicks off to a legacy page and asserts navigation still works. Driven by
e2e_tests/fixtures/migratedPages.ts, so adding a page is one line.

Runs in two situations against the same proxy: the default mount (npm run
e2e:migration) and a non-root SERVER_ROOT_PATH mount (npm run e2e:migration:root).
globalSetup now logs in at `${SERVER_ROOT_PATH}/ui/login` so the admin storage
state is valid under a prefix. Seeded with api-reference; append the rest as their
migrations merge.

* test(ui): support headed slow-motion + watch pauses in the migration smoke

Honor SLOWMO in the server-root-path config (the default config already did),
and add an env-gated E2E_WATCH_MS pause so a headed run lingers on each state.
Both are no-ops by default, so CI behavior is unchanged.

* test(ui): make the migration smoke a sidebar-click user journey

Rework the smoke from deep-linking to a real navigation journey: start at the
landing page, click the migrated page in the sidebar (expanding submenus for
nested items), assert the path route rendered, reload it (the check a wrong
server_root_path breaks), bounce to a legacy page and back, and — once two pages
are migrated — navigate directly between two migrated pages. Verifies via URL +
shell render, driven by the same fixture list.

* test(ui): address review on the migration smoke

Escape ROOT and segment before interpolating them into RegExp URL matchers so a
future segment containing regex metacharacters can't silently widen the match.
Make the server-root-path config fail fast when SERVER_ROOT_PATH is unset instead
of silently re-running the default mount and passing without exercising the prefix.

* test(ui): drop unused watch helper and fix stale smoke README

* test(ui): run the migration smoke under a server root path in CI

* test(ui): harden + instrument the server-root-path proxy reboot in CI

* test(ui): run the server-root-path migration smoke as its own CI job

Replace the in-place proxy reboot in e2e_ui_testing with a dedicated
e2e_ui_testing_server_root_path job that boots the proxy once with
SERVER_ROOT_PATH=/litellm, matching how every other proxy variant in the
config gets its own job rather than killing and relaunching the live proxy.

The reboot was failing deterministically: after pkill -9 and relaunch the
prefixed proxy never came back up on :4000 (connection refused), so the smoke
never ran. The readiness step that was supposed to surface the cause could
never reach its boot-log tail because CircleCI runs steps under bash -eo
pipefail and the preceding `curl -sv ... | tail` aborted the step with curl's
exit 7. Booting the proxy as the job's own background step lets any boot crash
land in that step's log instead of being swallowed.

The default e2e_ui_testing job is unchanged aside from dropping the reboot,
prefixed-readiness, and prefixed-smoke steps; the migration smoke still runs at
the root mount there via the default Playwright config.

* fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through (#24232)

* fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through

* test: mock post_call_response_headers_hook in audio speech route tests

* chore(ui): remove dead App Router route stubs under (dashboard) (#30045)

models-and-endpoints, organizations, and virtual-keys each had a page.tsx
route under (dashboard)/ that is not in MIGRATED_PAGES, so the sidebar and
deep links never resolve to it and the route is unreachable. Each was a thin
wrapper that handed the shared view empty or no-op props (empty modelData with
a no-op setModelData, hardcoded empty organizations, no-op
setUserRole/setUserEmail), so reaching one would render a degraded page in any
case. The real wrapper belongs in the PR that flips each page into
MIGRATED_PAGES, written with eyes on it and a test

This continues the dead-scaffolding cleanup from #28891. The shared components
these wrappers rendered (ModelsAndEndpointsView, OrganizationFilters) stay,
since the legacy ?page= switch in app/page.tsx and src/components still import
them

* fix(ui/mcp): reset OAuth state on create-server modal close so a prior server's token no longer leaks into the next add-server session (#30000)

* fix(ui/mcp): reset OAuth hook state on modal close so a prior server's token no longer leaks into the next add-server session

* fix(ui/mcp): clear in-flight OAuth guard on reset and reset form/tools on modal close so nothing leaks on a parent-driven dismiss

* fix(mcp): allow team access-group grants in OAuth authorize/token access check (#30041)

* fix(mcp): honor team access-group grants in OAuth authorize/token access check

* test(mcp): mock build_effective_auth_contexts in non-admin authorize tests for isolation

* docs(security): require a reproduction video for vulnerability reports (#30048) (#30063)

With AI models capable of automated vulnerability discovery now publicly
available, we expect a large increase in report volume, much of it
unverified. Requiring a video of the exploit running against a live
instance raises the bar for submissions and keeps triage focused on
reproducible issues. Reports without a video will be closed and reopened
if one is added later.

Co-authored-by: stuxf <[email protected]>

* feat(ui): add admin flag to disable in-product UI nudges for everyone (#29796)

* feat(ui): add admin flag to disable in-product UI nudges for everyone

Admins can now suppress the survey and Claude Code feedback popups for
all users via a single disable_ui_nudges UI setting, instead of relying
on each user dismissing them individually.

* fix(ui): suppress nudges while ui settings are loading

Gate nudgesDisabled on the ui-settings loading state so an admin with
disable_ui_nudges on doesn't see the survey prompt flash, and the
getInProductNudgesCall fetch doesn't fire, on a cold page load before
the flag resolves. Falls back to showing nudges if the fetch errors.

* test(ui): wrap CreateKeyPage test in QueryClientProvider

page.tsx now calls useUISettings (react-query), which needs a
QueryClient that layout.tsx supplies in production but the test did
not. Add the provider and mock getUiSettings so the query resolves.

* chore(ui): remove dead dashboard files and unused dependencies (#30047)

* chore(ui): remove dead dashboard files and unused dependencies

knip flagged seven orphaned source/config files with no importers and
five declared dependencies that nothing in the tree uses. Removing them
shrinks the dashboard bundle's source surface and keeps the manifest
honest; vite stays installed transitively via vitest, so test tooling is
unaffected.

* fix(ci): restore serverRootPath.config.ts referenced by SERVER_ROOT_PATH workflow

The dead-code sweep removed e2e_tests/serverRootPath.config.ts, but its spec
(tests/login/serverRootPathRedirect.spec.ts) and the test_server_root_path.yml
workflow step still depend on it, so the redirect e2e job failed to load a
config that no longer existed.

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593) (#30009)

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593)

After replace_model_in_jsonl, body.model is a stripped provider id. Reverse-mapping it via resolve_model_name_from_model_id is first-match on model_list and caused false 403s when multiple deployments share the same stripped name. Use target_model_names from the unified file id instead.

Co-authored-by: Cursor <[email protected]>

* fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)

Restores the reverse-lookup for the JSONL body.model fallback path so that
legacy/pre-target_model_names managed files still map stripped provider IDs
back to proxy aliases before auth. Also cleans up redundant `or None`.

Co-Authored-By: Claude Sonnet 4.6 <[email protected]>

* Revert "fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)"

This reverts commit 30d2e96f77ef521ccaaf2193fe554980380eb669.

---------

Co-authored-by: Cursor <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>

* Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI (#30064)

* Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI

Adds cost map entries for claude-fable-5 ($10/$50 per MTok, 1M context,
128K output, adaptive thinking only) on the Anthropic API, Bedrock
converse (base, global, and us/eu geo inference profiles at the 10%
regional premium), Vertex AI, and Azure AI (Microsoft Foundry, which
serves Fable 5 with the full 1M context window unlike Opus 4.8).

Registers anthropic.claude-fable-5 in BEDROCK_CONVERSE_MODELS, lists the
model in the setup wizard, and extends the reasoning effort e2e grid.
The Bedrock, Vertex, and Azure grid cells carry fail_reason markers
until the CI accounts are provisioned: Bedrock needs the provider data
sharing opt-in Fable 5 requires, and the Foundry resource needs a
claude-fable-5 deployment.

The first-party entry carries provider_specific_entry {us: 1.1} for the
inference_geo premium and deliberately no fast multiplier since Fable 5
has no fast mode.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Drop removed sampling params for Claude 4.7+ when drop_params is set

Fable 5, Opus 4.7, and Opus 4.8 removed sampling params: the API rejects
top_p, top_k, and any temperature other than 1 with a 400. LiteLLM was
forwarding them even with drop_params enabled because the Anthropic and
Bedrock converse transformations passed temperature/top_p through
unconditionally.

Mirror the GPT-5/o-series handling: temperature=1 still passes through,
other values and any top_p are dropped when drop_params is set, and
without drop_params a clean client-side UnsupportedParamsError tells the
caller how to opt in, instead of surfacing the raw provider error.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Drive sampling param gating from the cost map and cover top_k

Greptile review follow-ups on the sampling param fix: the restriction for
Fable 5 / Opus 4.7 / 4.8 is now declared as supports_sampling_params: false
on every affected cost map entry (perplexity excluded; that route is
OpenAI-compatible and maps sampling params upstream) and read back through
a tri-state map lookup, keeping the name check only as a fallback for
provider-routed ids whose hosted map entries predate the flag, the same
layering supports_adaptive_thinking uses. top_k bypasses map_openai_params
as a provider-specific kwarg, so it is gated at the shared
AnthropicConfig.transform_request boundary (direct, Bedrock invoke, Vertex,
Azure) and in the Bedrock converse _handle_top_k_value path, with
drop_params threaded through the converse transform helpers.

Also updates the reasoning effort grid cell count assertion for the four
Fable 5 rows added on this branch (29 x 11 cells).

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Declare supports_sampling_params in the cost map schema

The model map validation schema uses additionalProperties: false, so the
new flag must be declared for the 28 entries that carry it; this was the
one failing job (misc / Run tests) on the previous commit.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* fix(bedrock): gate top_k=0 on converse to match Anthropic boundary

Truthiness check let top_k=0 silently disappear on models that removed
sampling params, while AnthropicConfig.transform_request treats 0 as
present and raises UnsupportedParamsError (or drops when drop_params is
set). Switch to 'is not None' so converse, direct Anthropic, invoke,
Vertex, and Azure all behave the same for top_k=0.

---------

Co-authored-by: Cursor Agent <[email protected]>

* fix(proxy): coerce litellm_settings.max_budget env var to float

When max_budget is set in litellm_settings via os.environ/MAX_BUDGET,
the env var resolves to a string and the generic setattr branch in
ProxyConfig.load_config stored it as-is, so the startup check
litellm.max_budget > 0 raised TypeError. The earlier fix (#23855) only
covered the CLI initialize() path. Coerce the value to float in the
settings loop, matching the existing max_internal_user_budget handling.

Fixes #26696.

---------

Co-authored-by: milan-berri <[email protected]>
Co-authored-by: Cursor <[email protected]>
Co-authored-by: ryan-crabbe-berri <[email protected]>
Co-authored-by: michelligabriele <[email protected]>
Co-authored-by: tin-berri <[email protected]>
Co-authored-by: yuneng-jiang <[email protected]>
Co-authored-by: stuxf <[email protected]>
Co-authored-by: Sameer Kankute <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>
Co-authored-by: Mateo Wang <[email protected]>

* fix(router): don't drop bedrock pass-through deployments using IAM credentials (#30111)

* Fix Bedrock passthrough deployment dropped when using IAM credentials

Bedrock deployments with use_in_pass_through enabled and IAM/OIDC auth
(aws_role_name, no api_key) hit the generic pass-through branch in
Router._initialize_deployment_for_pass_through, which calls
set_pass_through_credentials and raises "api_key is required". The
exception drops the deployment from the router entirely, breaking both
passthrough and normal routing for that model.

Skip the credential store write when no api_key is set; the bedrock
passthrough route resolves AWS credentials at request time via
BedrockConverseLLM.get_credentials(), not the passthrough credential
store, so there is nothing to register here.

Fixes #27728.

* Reset passthrough credentials singleton before api_key credential test

The test reads the module-level passthrough_endpoint_router singleton,
so a stale "openai" entry written by an earlier test in the same
process could make the assertion pass without exercising the code path.
Clearing the credentials dict up front makes the test order-independent.

* fix(sdk): stop mirroring reasoning_content in provider_specific_fields (#30110)

The dict-to-response conversion path mirrored reasoning_content into
provider_specific_fields, while live provider transforms (Anthropic's
_build_provider_specific_fields) only set it top-level on the Message.
Cache-replayed messages therefore serialized differently from live
ones, breaking disk cache key stability for multi-turn conversations
with extended thinking.

The mirror was added for DeepSeek before Message.reasoning_content
existed as a top-level attribute. The top-level field is still set by
the converter, so DeepSeek's request-side promotion is unaffected.

Fixes #27337.

* fix(mcp): coerce mcp_server_cost_info values to float at ingest (#30109)

* fix(mcp): coerce mcp_server_cost_info values to float at ingest

YAML 1.1 parses scientific notation without a decimal point
(e.g. 7e-05) as a string, and MCPServerCostInfo is a TypedDict with no
runtime validation, so a string-typed default_cost_per_query from
config.yaml flowed through the proxy untouched and crashed the MCP
server settings page with '.toFixed is not a function'. Normalize
mcp_server_cost_info on both the config and DB load paths, dropping
non-numeric values with a warning instead of failing the server load.

Fixes #27097.

* fix(mcp): drop non-numeric default_cost_per_query instead of nulling it

Keeping the key with a None value still exposes a null to the UI,
which can crash .toFixed formatting when the consumer checks key
existence rather than truthiness. Delete the key on coercion failure,
matching how non-numeric per-tool cost entries are already omitted.

* fix(proxy): count embedding and text completion tokens toward TPM limits (#30105)

* fix(proxy): count embedding and text completion tokens toward TPM limits

The parallel request limiters only read token usage off ModelResponse,
so EmbeddingResponse and TextCompletionResponse objects left
total_tokens at 0 and the per key, user, team, and end user TPM
counters never incremented. Requests to /v1/embeddings and
/v1/completions were effectively free against any tpm_limit. In the v3
limiter this was worse: the post-call reconciliation computed actual
usage as 0 and refunded the pre-call reservation made at request time.

Broaden the isinstance checks to accept EmbeddingResponse and
TextCompletionResponse, which both expose a Usage object, at the four
per-scope sites in parallel_request_limiter.py and at the usage
extraction in parallel_request_limiter_v3.py. ResponsesAPIResponse was
already covered in v3 via BaseLiteLLMOpenAIResponseObject.

Fixes #27738.

* test(proxy): cover v1 limiter TPM counting for embedding and text completion responses

Exercise the broadened isinstance sites in parallel_request_limiter.py
by asserting that async_log_success_event adds total_tokens to the per
key, user, team, and end user TPM counters for EmbeddingResponse and
TextCompletionResponse objects. The counters are pre-seeded at zero so
the assertion is exactly the increment; on the pre-fix code these
responses left total_tokens at 0 and the test fails.

* fix(openai): forward client headers on the text completion path (#30103)

* fix(openai): forward client headers on the text completion path

litellm.completion() merges caller headers with extra_headers, but the
text-completion-openai branch never passed the merged dict to
openai_text_completions.completion(), and the handler only used its
headers argument for logging. Pass the merged headers through the call
site and set them as extra_headers on the outgoing request, mirroring
the chat completion handler, so x-* client headers forwarded by the
proxy reach the provider on /v1/completions.

Fixes #27410.

* Drop redundant extra_headers assignment and fix test module collision

completion() merges extra_headers into headers before the
text-completion-openai branch, and the handler now sets the merged
headers as extra_headers on the request, so the branch-local
optional_params["extra_headers"] assignment was a dead duplicate.
Removing it keeps the assignment in one place while both entry paths
(litellm.text_completion and direct handler callers) still forward
headers; a new regression test pins the extra_headers kwarg path.

Also rename the test module to test_completion_handler.py since its
basename collided with tests/test_litellm/llms/bedrock/batches/
test_handler.py and broke pytest collection.

* fix(bedrock): route Anthropic-shape count_tokens to InvokeModel and base64-encode the body (#30102)

* fix(bedrock): route Anthropic-shape count_tokens to InvokeModel

POST /v1/messages/count_tokens with Anthropic content blocks
({"type": "text"|"tool_use"|...}) was routed to the Converse input of
the Bedrock CountTokens API. The Converse transform copies list content
through verbatim, so Bedrock rejected the request with a 400 and the
caller silently fell back to the local tokenizer, returning counts that
can be off by ~50% on tool-heavy payloads.

_detect_input_type now routes messages whose content blocks carry a
"type" key (Anthropic shape) to the invokeModel input, which forwards
the body verbatim. The invokeModel body is now base64-encoded as the
CountTokens API requires (InvokeModelTokensRequest.body is a
base64-encoded blob), and Anthropic Messages bodies get the
anthropic_version and max_tokens fields Bedrock validates against.

Fixes #27632.

* refactor(bedrock): name the CountTokens max_tokens placeholder

Replace the magic 1024 with a module-level
DEFAULT_ANTHROPIC_INVOKE_MODEL_MAX_TOKENS constant so the intent is
explicit and t…

…T-3593) (BerriAI#30009)

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593)

After replace_model_in_jsonl, body.model is a stripped provider id. Reverse-mapping it via resolve_model_name_from_model_id is first-match on model_list and caused false 403s when multiple deployments share the same stripped name. Use target_model_names from the unified file id instead.

Co-authored-by: Cursor <[email protected]>

* fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)

Restores the reverse-lookup for the JSONL body.model fallback path so that
legacy/pre-target_model_names managed files still map stripped provider IDs
back to proxy aliases before auth. Also cleans up redundant `or None`.

Co-Authored-By: Claude Sonnet 4.6 <[email protected]>

* Revert "fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)"

This reverts commit 30d2e96.

---------

Co-authored-by: Cursor <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>

* fix(mcp): report scoped server name during initialize (#29865)

* fix mcp scoped server name

* Update litellm/proxy/_experimental/mcp_server/mcp_context.py

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* test(mcp): cover scoped server name in the SSE initialize handler

---------

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* fix(ui): show all session logs in the drawer, not just the first 50 (#29795)

* fix(ui): show newest session logs first

* test(ui): keep session log pagination coverage

* fix(ui): show all session logs in the drawer, not just the first page

The session detail drawer fetched session logs via sessionSpendLogsCall
without page/page_size, so it only ever received the backend default of one
page (50 rows). Sessions with more than 50 calls had the rest unreachable in
the UI (#29153).

sessionSpendLogsCall now takes page/page_size, and the drawer fetches the
first page, reads total_pages, then fetches the remaining pages and
accumulates them before the existing client-side sort. This keeps the single
continuous list (and the selected-log lookup and keyboard navigation, which
all assume the full session) correct. Fetching is bounded by a page cap, and
the sidebar shows a "showing most recent N" note if a session exceeds it.

The rows are lightweight metadata (the endpoint excludes messages/response),
so the full set is small; request/response bodies are still loaded per log on
demand.

* fix(ui): default session drawer to most recent log, newest first

Open a session with its most recent log selected, and order the sidebar
newest-first to match the all-sessions logs overview. MCP calls stay
grouped last. The latest log by time is computed explicitly, since the
MCP grouping means it is not always the first row.

* Apply fetching pages in batches suggestion from @greptile-apps[bot]

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* fix(ui): derive session total from accumulated rows when backend omits it

Compute the session total after all pages are fetched, falling back to the
accumulated row count rather than the first page's. Guards the truncation
note against a backend response that omits total but spans multiple pages.

---------

Co-authored-by: Yufeng He <[email protected]>
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* fix(proxy): handle Mistral multipart passthrough (#29927)

* fix(proxy): handle Mistral multipart passthrough

* chore: satisfy passthrough ci formatting

* test(proxy): cover Mistral passthrough in CI shard

* fix(vertex_ai): use REP host for context caching on eu/us multi-region endpoints (#29573)

Context caching built the cachedContents URL as
https://{location}-aiplatform.googleapis.com, which is an invalid host for the
eu/us multi-region endpoints and returns 404. The inference path already
resolves these to the REP host (https://aiplatform.{geo}.rep.googleapis.com)
via get_vertex_base_url(); reuse that helper in
_get_token_and_url_context_caching so caching uses the same host as inference.

Adds tests covering the eu/us multi-region cachedContents URLs (v1 and
v1beta1).

Fixes #29571

* Support per-model encrypted content affinity config (#29760)

Co-authored-by: shin-berri <[email protected]>
Co-authored-by: yuneng-jiang <[email protected]>

* fix: propagate upstream status code in proxy API exception handler (#29402)

* fix: propagate upstream status code in proxy API exception handler

When Google GenAI / Vertex returns a 404 for deprecated or missing
models via streamGenerateContent, the exception was falling through to
a generic handler that defaulted to 500. Now provider exceptions
carrying a valid HTTP status_code correctly propagate it through to
the ProxyException.

* fix: apply black formatting to common_request_processing.py

* fix: tighten status code range to 400-599 and deduplicate ProxyException raise

* fix(tests): use valid vertex_location in context caching tests

Replace "test_location" (contains underscore) with "us-central1" so tests
pass the regex validation added in get_vertex_base_url().

Co-Authored-By: Claude Sonnet 4.6 <[email protected]>

* feat(sdk): add xAI OAuth provider (#29866)

* Add xAI OAuth provider

* Update oauth.py

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* Fix xAI OAuth CI failures

* Add xAI OAuth coverage tests

* Move xAI OAuth coverage tests to core utils

* Address xAI OAuth review comments

* Prevent xAI OAuth api_base token exfiltration

* Treat blank xAI OAuth api keys as absent

* Wrap invalid xAI OAuth JSON responses

* Use xAI OAuth behind explicit flag

---------

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* fix(proxy) #27734 allow clearing budget_duration and team_member fields by sending null on /key/update and /team/update (#27751)

* fix(proxy): allow clearing budget_duration and team_member fields by sending null on /key/update and /team/update

Fixes #27734

Sending null for budget_duration, team_member_budget,
team_member_budget_duration, team_member_rpm_limit, or
team_member_tpm_limit via /key/update or /team/update returned 200 OK
but silently ignored the null value. The fields remained unchanged in
the database.

Root causes:
- /key/update: prepare_key_update_data() popped budget_duration from the
  update dict but never re-added it (or budget_reset_at) when the value
  was None.
- /team/update: _set_budget_reset_at() only acted when budget_duration
  was non-None, leaving a stale budget_reset_at in the DB.
- /team/update: team_member_* null values bypassed the budget table
  update entirely because should_create_budget() requires at least one
  non-None field.

* test(proxy): cover no-budget-row path in clear_team_member_budget_fields

* fix(presidio): unmask PII tokens in Anthropic native SSE streaming bytes (#30028)

* fix(presidio): unmask PII tokens in Anthropic native SSE streaming bytes

When output_parse_pii=true on the Anthropic native path (anthropic/claude-*),
response chunks arrive as raw bytes in SSE format. _stream_pii_unmasking was
yielding those bytes unchanged, so <PERSON_1> tokens were never replaced with
the original values before reaching the caller.

Add _unmask_sse_bytes_chunk to parse each data: line, find content_block_delta
/ text_delta events, and apply _unmask_pii_text before re-encoding. Wire it
into _stream_pii_unmasking so bytes chunks are unmasked when pii_tokens exist.

* fix(presidio): handle CRLF line endings and non-ASCII PII in SSE unmask

Strip trailing \r before the [DONE] guard so CRLF-terminated SSE chunks
don't bypass it and silently swallow a JSONDecodeError. Add
ensure_ascii=False to json.dumps so non-ASCII replacement values like
accented names are preserved as UTF-8 on the wire rather than being
\uXXXX-escaped. Add regression tests for both cases.

* feat(bedrock_mantle): path-aware Responses routing (/v1/responses vs /openai/v1/responses) (#29925)

* feat(bedrock_mantle): path-aware Responses routing (/v1/responses vs /openai/v1/responses)

Bedrock Mantle serves the Responses API on two upstream paths:
  - gpt frontier models (gpt-5.5 / gpt-5.4) on /openai/v1/responses
  - every other Responses-capable model (e.g. gpt-oss) on the standard /v1/responses

BedrockMantleResponsesAPIConfig gains a `use_openai_path` flag; the provider gate in
utils.py picks the path per model: openai.gpt-* (non gpt-oss) -> /openai/v1/responses;
any model declared mode=responses (price-map entry or user model_info) -> /v1/responses;
everything else returns None and keeps the existing chat-completions emulation.

Adds gpt-5.5 / gpt-5.4 price-map entries, registry wiring, and the routing-matrix tests.

* feat(bedrock_mantle): data-driven frontier routing via use_openai_responses_path

Addresses the Greptile review point that frontier detection should be a
price-map field rather than a hardcoded name match. The gate now routes a
model to /openai/v1/responses when its price-map entry declares
use_openai_responses_path, so a frontier model whose name does not follow the
openai.gpt- convention can be onboarded by JSON alone. The name-convention
check is kept as a fallback that needs no price-map entry, which preserves
zero-change routing for a future gpt-6 before its entry loads. gpt-5.5 / gpt-5.4
get the flag in both price maps. Adds tests for the data-driven flag path and
for the flag presence on the gpt-5.x entries; both branches are mutation-tested.

* test(model_prices): allow use_openai_responses_path in price-map schema

The model_prices_and_context_window.json schema validator
(test_aaamodel_prices_and_context_window_json_is_valid) enforces
additionalProperties: false, so the new use_openai_responses_path flag on the
gpt-5.5 / gpt-5.4 entries failed validation. Add it to the schema as a boolean,
alongside the other supports_* / capability flags.

* Add Tensormesh serverless models to the model cost map (#30037)

* Add Tensormesh serverless models to the model cost map

* Flag reasoning support on the Tensormesh models that expose thinking mode

* fix(proxy): invalidate stale key spend counter after budget reset or manual spend update (#30001)

* fix(proxy): reconcile stale key spend counter after budget reset

* fix(proxy): invalidate stale key spend counter after budget reset or manual spend update

* fix(proxy): remove read-time stale counter reconciliation to prevent budget bypass

* revert: undo unrelated formatting changes in enterprise directory

* test(proxy): add unit test for key spend update invalidating counter

* test(proxy): fix mocked update_data and hash token expectations in unit test

* fix(proxy): use Responses-API transformer in pass-through cost tracking (#29728)

The `elif is_responses:` branch of `openai_passthrough_handler` was
calling the chat-completions `transform_response` on a Responses API
payload. The chat-completions transformer expects `choices: [...]`
in the raw response; the Responses API uses `output: [...]` and
`usage.input_tokens` / `usage.output_tokens` (not
`prompt_tokens` / `completion_tokens`). The result was a
KeyError 'choices' deep inside `convert_to_model_response_object`,
swallowed by the surrounding `except Exception` in the handler, and
the SpendLogs row was written by the fallback path with zeroed-out
tokens, spend, and model.

This bug silently undercounts cost for every successful pass-through
call to either OpenAI's `/v1/responses` or Azure's
`/openai/v1/responses` (deployments configured for the Responses
API). Reproduced 2026-06-04 against a real Azure OpenAI Responses
API deployment proxied through LiteLLM v1.88.0.

Fix: use the dedicated
`OpenAIResponsesAPIConfig.transform_response_api_response` for the
Responses branch. This transformer already exists in LiteLLM
(`litellm/llms/openai/responses/transformation.py`) and knows the
Responses-API on-the-wire shape. `litellm.completion_cost` already
handles `ResponsesAPIResponse` natively with `call_type="responses"`,
so no downstream changes are needed.

Tests:

  test_responses_api_uses_responses_transformer_not_chat_completions
    NEW. Real regression test — exercises the openai_passthrough_handler
    with a real-shaped Responses payload (no `choices`, has `output`
    and Responses-API `usage` keys) and NO mocked `get_provider_config`.
    Pre-fix: raises KeyError 'choices' inside the chat-completions
    transformer (the bug). Post-fix: returns a ResponsesAPIResponse,
    completion_cost is called with call_type="responses" and a
    ResponsesAPIResponse instance (asserted).
    Verified to fail on un-fixed handler + pass on fixed handler
    before commit.

  test_responses_api_cost_tracking
    UPDATED. Old test mocked `get_provider_config` (no longer called
    in the responses branch post-fix). Now mocks the Responses
    transformer directly (`OpenAIResponsesAPIConfig.transform_response_api_response`)
    to test the downstream cost-calc contract.

Out of scope for this PR (separate followup):
  - Recognizing *.cognitiveservices.azure.com (the newer Azure
    OpenAI hostname) in the is_openai_*_route checks. Separate PR.

Co-authored-by: shin-berri <[email protected]>
Co-authored-by: yuneng-jiang <[email protected]>

* fix(skills): execute DB skills by matching the litellm_skill_ tool name prefix (#30116)

Skill IDs are generated as litellm_skill_<uuid> and the model-facing
tool name is the sanitized skill ID, but the post-call execution gates
in SkillsInjectionHook only ran tools whose name starts with "skill_",
so DB skills were silently returned to the client as raw tool calls.

Fixes #28122.

Co-authored-by: Cursor <[email protected]>

* fix(anthropic): synthesize content_block_start when Responses stream omits output_item.added (#30115)

* fix(team): reserve team budget raises for proxy admins on /team/update (#30030)

The caller's PERSONAL max_budget was the wrong yardstick for /team/update: a
team's spend ceiling has nothing to do with the admin's own key budget. That
comparison was an unintended side effect of reusing _check_user_team_limits()
(which exists for the /team/new path) and broke the UI, which re-sends the
unchanged budget on every save.

New behavior on /team/update for standalone teams:
- A team admin (already authorized via _verify_team_access) may freely KEEP or
  LOWER the team budget, and change models/tpm/rpm, without being gated by their
  personal limits.
- GROWING a team's spend ceiling is a budget-authority action reserved for proxy
  admins -> 403 for team admins. "Growing" covers both raising max_budget above
  the team's current finite value and removing the cap entirely (max_budget=null,
  detected via model_fields_set so an explicit null is distinguished from an
  omitted field). For a team that currently has no cap, setting a finite value is
  a restriction and is allowed.
- Org-scoped teams remain governed by _check_org_team_limits() (capped by the
  org budget).

Also reverts the #29525 existing_team_max_budget workaround in
_check_user_team_limits() back to the create-only form; /team/new still enforces
the creator's personal caps.

docs(access_control): resolve the contradiction in the team-admin section —
team admins can keep/lower the budget and manage rate limits/models, but cannot
raise the team budget (proxy-admin only).

tests: unit + behavior coverage for raise-blocked, cap-removal-blocked (team
admin), raise/removal allowed (proxy admin), uncapped-team restriction allowed,
keep/lower/resend allowed, and unchanged create-path guards.

Co-authored-by: Cursor <[email protected]>

* test(ui): data-driven App Router migration E2E smoke (default + server-root-path) (#29974)

* test(ui): add a data-driven App Router migration E2E smoke

Add a growing Playwright smoke for migrated pages: for each segment it deep-links
to the path route, asserts the URL and that the dashboard shell rendered, then
clicks off to a legacy page and asserts navigation still works. Driven by
e2e_tests/fixtures/migratedPages.ts, so adding a page is one line.

Runs in two situations against the same proxy: the default mount (npm run
e2e:migration) and a non-root SERVER_ROOT_PATH mount (npm run e2e:migration:root).
globalSetup now logs in at `${SERVER_ROOT_PATH}/ui/login` so the admin storage
state is valid under a prefix. Seeded with api-reference; append the rest as their
migrations merge.

* test(ui): support headed slow-motion + watch pauses in the migration smoke

Honor SLOWMO in the server-root-path config (the default config already did),
and add an env-gated E2E_WATCH_MS pause so a headed run lingers on each state.
Both are no-ops by default, so CI behavior is unchanged.

* test(ui): make the migration smoke a sidebar-click user journey

Rework the smoke from deep-linking to a real navigation journey: start at the
landing page, click the migrated page in the sidebar (expanding submenus for
nested items), assert the path route rendered, reload it (the check a wrong
server_root_path breaks), bounce to a legacy page and back, and — once two pages
are migrated — navigate directly between two migrated pages. Verifies via URL +
shell render, driven by the same fixture list.

* test(ui): address review on the migration smoke

Escape ROOT and segment before interpolating them into RegExp URL matchers so a
future segment containing regex metacharacters can't silently widen the match.
Make the server-root-path config fail fast when SERVER_ROOT_PATH is unset instead
of silently re-running the default mount and passing without exercising the prefix.

* test(ui): drop unused watch helper and fix stale smoke README

* test(ui): run the migration smoke under a server root path in CI

* test(ui): harden + instrument the server-root-path proxy reboot in CI

* test(ui): run the server-root-path migration smoke as its own CI job

Replace the in-place proxy reboot in e2e_ui_testing with a dedicated
e2e_ui_testing_server_root_path job that boots the proxy once with
SERVER_ROOT_PATH=/litellm, matching how every other proxy variant in the
config gets its own job rather than killing and relaunching the live proxy.

The reboot was failing deterministically: after pkill -9 and relaunch the
prefixed proxy never came back up on :4000 (connection refused), so the smoke
never ran. The readiness step that was supposed to surface the cause could
never reach its boot-log tail because CircleCI runs steps under bash -eo
pipefail and the preceding `curl -sv ... | tail` aborted the step with curl's
exit 7. Booting the proxy as the job's own background step lets any boot crash
land in that step's log instead of being swallowed.

The default e2e_ui_testing job is unchanged aside from dropping the reboot,
prefixed-readiness, and prefixed-smoke steps; the migration smoke still runs at
the root mount there via the default Playwright config.

* fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through (#24232)

* fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through

* test: mock post_call_response_headers_hook in audio speech route tests

* chore(ui): remove dead App Router route stubs under (dashboard) (#30045)

models-and-endpoints, organizations, and virtual-keys each had a page.tsx
route under (dashboard)/ that is not in MIGRATED_PAGES, so the sidebar and
deep links never resolve to it and the route is unreachable. Each was a thin
wrapper that handed the shared view empty or no-op props (empty modelData with
a no-op setModelData, hardcoded empty organizations, no-op
setUserRole/setUserEmail), so reaching one would render a degraded page in any
case. The real wrapper belongs in the PR that flips each page into
MIGRATED_PAGES, written with eyes on it and a test

This continues the dead-scaffolding cleanup from #28891. The shared components
these wrappers rendered (ModelsAndEndpointsView, OrganizationFilters) stay,
since the legacy ?page= switch in app/page.tsx and src/components still import
them

* fix(ui/mcp): reset OAuth state on create-server modal close so a prior server's token no longer leaks into the next add-server session (#30000)

* fix(ui/mcp): reset OAuth hook state on modal close so a prior server's token no longer leaks into the next add-server session

* fix(ui/mcp): clear in-flight OAuth guard on reset and reset form/tools on modal close so nothing leaks on a parent-driven dismiss

* fix(mcp): allow team access-group grants in OAuth authorize/token access check (#30041)

* fix(mcp): honor team access-group grants in OAuth authorize/token access check

* test(mcp): mock build_effective_auth_contexts in non-admin authorize tests for isolation

* docs(security): require a reproduction video for vulnerability reports (#30048) (#30063)

With AI models capable of automated vulnerability discovery now publicly
available, we expect a large increase in report volume, much of it
unverified. Requiring a video of the exploit running against a live
instance raises the bar for submissions and keeps triage focused on
reproducible issues. Reports without a video will be closed and reopened
if one is added later.

Co-authored-by: stuxf <[email protected]>

* feat(ui): add admin flag to disable in-product UI nudges for everyone (#29796)

* feat(ui): add admin flag to disable in-product UI nudges for everyone

Admins can now suppress the survey and Claude Code feedback popups for
all users via a single disable_ui_nudges UI setting, instead of relying
on each user dismissing them individually.

* fix(ui): suppress nudges while ui settings are loading

Gate nudgesDisabled on the ui-settings loading state so an admin with
disable_ui_nudges on doesn't see the survey prompt flash, and the
getInProductNudgesCall fetch doesn't fire, on a cold page load before
the flag resolves. Falls back to showing nudges if the fetch errors.

* test(ui): wrap CreateKeyPage test in QueryClientProvider

page.tsx now calls useUISettings (react-query), which needs a
QueryClient that layout.tsx supplies in production but the test did
not. Add the provider and mock getUiSettings so the query resolves.

* chore(ui): remove dead dashboard files and unused dependencies (#30047)

* chore(ui): remove dead dashboard files and unused dependencies

knip flagged seven orphaned source/config files with no importers and
five declared dependencies that nothing in the tree uses. Removing them
shrinks the dashboard bundle's source surface and keeps the manifest
honest; vite stays installed transitively via vitest, so test tooling is
unaffected.

* fix(ci): restore serverRootPath.config.ts referenced by SERVER_ROOT_PATH workflow

The dead-code sweep removed e2e_tests/serverRootPath.config.ts, but its spec
(tests/login/serverRootPathRedirect.spec.ts) and the test_server_root_path.yml
workflow step still depend on it, so the redirect e2e job failed to load a
config that no longer existed.

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593) (#30009)

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593)

After replace_model_in_jsonl, body.model is a stripped provider id. Reverse-mapping it via resolve_model_name_from_model_id is first-match on model_list and caused false 403s when multiple deployments share the same stripped name. Use target_model_names from the unified file id instead.

Co-authored-by: Cursor <[email protected]>

* fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)

Restores the reverse-lookup for the JSONL body.model fallback path so that
legacy/pre-target_model_names managed files still map stripped provider IDs
back to proxy aliases before auth. Also cleans up redundant `or None`.

Co-Authored-By: Claude Sonnet 4.6 <[email protected]>

* Revert "fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)"

This reverts commit 30d2e96f77ef521ccaaf2193fe554980380eb669.

---------

Co-authored-by: Cursor <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>

* Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI (#30064)

* Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI

Adds cost map entries for claude-fable-5 ($10/$50 per MTok, 1M context,
128K output, adaptive thinking only) on the Anthropic API, Bedrock
converse (base, global, and us/eu geo inference profiles at the 10%
regional premium), Vertex AI, and Azure AI (Microsoft Foundry, which
serves Fable 5 with the full 1M context window unlike Opus 4.8).

Registers anthropic.claude-fable-5 in BEDROCK_CONVERSE_MODELS, lists the
model in the setup wizard, and extends the reasoning effort e2e grid.
The Bedrock, Vertex, and Azure grid cells carry fail_reason markers
until the CI accounts are provisioned: Bedrock needs the provider data
sharing opt-in Fable 5 requires, and the Foundry resource needs a
claude-fable-5 deployment.

The first-party entry carries provider_specific_entry {us: 1.1} for the
inference_geo premium and deliberately no fast multiplier since Fable 5
has no fast mode.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Drop removed sampling params for Claude 4.7+ when drop_params is set

Fable 5, Opus 4.7, and Opus 4.8 removed sampling params: the API rejects
top_p, top_k, and any temperature other than 1 with a 400. LiteLLM was
forwarding them even with drop_params enabled because the Anthropic and
Bedrock converse transformations passed temperature/top_p through
unconditionally.

Mirror the GPT-5/o-series handling: temperature=1 still passes through,
other values and any top_p are dropped when drop_params is set, and
without drop_params a clean client-side UnsupportedParamsError tells the
caller how to opt in, instead of surfacing the raw provider error.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Drive sampling param gating from the cost map and cover top_k

Greptile review follow-ups on the sampling param fix: the restriction for
Fable 5 / Opus 4.7 / 4.8 is now declared as supports_sampling_params: false
on every affected cost map entry (perplexity excluded; that route is
OpenAI-compatible and maps sampling params upstream) and read back through
a tri-state map lookup, keeping the name check only as a fallback for
provider-routed ids whose hosted map entries predate the flag, the same
layering supports_adaptive_thinking uses. top_k bypasses map_openai_params
as a provider-specific kwarg, so it is gated at the shared
AnthropicConfig.transform_request boundary (direct, Bedrock invoke, Vertex,
Azure) and in the Bedrock converse _handle_top_k_value path, with
drop_params threaded through the converse transform helpers.

Also updates the reasoning effort grid cell count assertion for the four
Fable 5 rows added on this branch (29 x 11 cells).

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Declare supports_sampling_params in the cost map schema

The model map validation schema uses additionalProperties: false, so the
new flag must be declared for the 28 entries that carry it; this was the
one failing job (misc / Run tests) on the previous commit.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* fix(bedrock): gate top_k=0 on converse to match Anthropic boundary

Truthiness check let top_k=0 silently disappear on models that removed
sampling params, while AnthropicConfig.transform_request treats 0 as
present and raises UnsupportedParamsError (or drops when drop_params is
set). Switch to 'is not None' so converse, direct Anthropic, invoke,
Vertex, and Azure all behave the same for top_k=0.

---------

Co-authored-by: Cursor Agent <[email protected]>

* fix(anthropic): avoid index -1 content_block_delta in messages stream

When a /v1/messages request is routed through the Responses API
adapter, AnthropicResponsesStreamWrapper only emits content_block_start
on response.output_item.added. Some upstreams (LMStudio for example)
never send that event, so the text delta handler fell back to
_current_block_index, which starts at -1, and clients received
content_block_delta events with index -1 and no preceding
content_block_start. Anthropic SDKs then fail with "text part -1 not
found"

The text delta handler now synthesizes a content_block_start with a
fresh block index whenever the delta references an unregistered item_id
or no block is open yet, and registers the item_id so follow-up deltas
reuse the same index

Addresses the /v1/messages defect in #27442

* Make test sys.path shim resolve relative to the file, not the CWD

os.path.abspath("../../../../../../..") depends on where pytest is
invoked from; anchoring on os.path.dirname(__file__) makes the import
work from any working directory. Also corrects the depth: the repo root
is six levels above this file, not seven.

---------

Co-authored-by: milan-berri <[email protected]>
Co-authored-by: Cursor <[email protected]>
Co-authored-by: ryan-crabbe-berri <[email protected]>
Co-authored-by: michelligabriele <[email protected]>
Co-authored-by: tin-berri <[email protected]>
Co-authored-by: yuneng-jiang <[email protected]>
Co-authored-by: stuxf <[email protected]>
Co-authored-by: Sameer Kankute <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>
Co-authored-by: Mateo Wang <[email protected]>

* fix: enable compact-2026-01-12 beta header for vertex_ai provider (#30114)

* fix(team): reserve team budget raises for proxy admins on /team/update (#30030)

The caller's PERSONAL max_budget was the wrong yardstick for /team/update: a
team's spend ceiling has nothing to do with the admin's own key budget. That
comparison was an unintended side effect of reusing _check_user_team_limits()
(which exists for the /team/new path) and broke the UI, which re-sends the
unchanged budget on every save.

New behavior on /team/update for standalone teams:
- A team admin (already authorized via _verify_team_access) may freely KEEP or
  LOWER the team budget, and change models/tpm/rpm, without being gated by their
  personal limits.
- GROWING a team's spend ceiling is a budget-authority action reserved for proxy
  admins -> 403 for team admins. "Growing" covers both raising max_budget above
  the team's current finite value and removing the cap entirely (max_budget=null,
  detected via model_fields_set so an explicit null is distinguished from an
  omitted field). For a team that currently has no cap, setting a finite value is
  a restriction and is allowed.
- Org-scoped teams remain governed by _check_org_team_limits() (capped by the
  org budget).

Also reverts the #29525 existing_team_max_budget workaround in
_check_user_team_limits() back to the create-only form; /team/new still enforces
the creator's personal caps.

docs(access_control): resolve the contradiction in the team-admin section —
team admins can keep/lower the budget and manage rate limits/models, but cannot
raise the team budget (proxy-admin only).

tests: unit + behavior coverage for raise-blocked, cap-removal-blocked (team
admin), raise/removal allowed (proxy admin), uncapped-team restriction allowed,
keep/lower/resend allowed, and unchanged create-path guards.

Co-authored-by: Cursor <[email protected]>

* test(ui): data-driven App Router migration E2E smoke (default + server-root-path) (#29974)

* test(ui): add a data-driven App Router migration E2E smoke

Add a growing Playwright smoke for migrated pages: for each segment it deep-links
to the path route, asserts the URL and that the dashboard shell rendered, then
clicks off to a legacy page and asserts navigation still works. Driven by
e2e_tests/fixtures/migratedPages.ts, so adding a page is one line.

Runs in two situations against the same proxy: the default mount (npm run
e2e:migration) and a non-root SERVER_ROOT_PATH mount (npm run e2e:migration:root).
globalSetup now logs in at `${SERVER_ROOT_PATH}/ui/login` so the admin storage
state is valid under a prefix. Seeded with api-reference; append the rest as their
migrations merge.

* test(ui): support headed slow-motion + watch pauses in the migration smoke

Honor SLOWMO in the server-root-path config (the default config already did),
and add an env-gated E2E_WATCH_MS pause so a headed run lingers on each state.
Both are no-ops by default, so CI behavior is unchanged.

* test(ui): make the migration smoke a sidebar-click user journey

Rework the smoke from deep-linking to a real navigation journey: start at the
landing page, click the migrated page in the sidebar (expanding submenus for
nested items), assert the path route rendered, reload it (the check a wrong
server_root_path breaks), bounce to a legacy page and back, and — once two pages
are migrated — navigate directly between two migrated pages. Verifies via URL +
shell render, driven by the same fixture list.

* test(ui): address review on the migration smoke

Escape ROOT and segment before interpolating them into RegExp URL matchers so a
future segment containing regex metacharacters can't silently widen the match.
Make the server-root-path config fail fast when SERVER_ROOT_PATH is unset instead
of silently re-running the default mount and passing without exercising the prefix.

* test(ui): drop unused watch helper and fix stale smoke README

* test(ui): run the migration smoke under a server root path in CI

* test(ui): harden + instrument the server-root-path proxy reboot in CI

* test(ui): run the server-root-path migration smoke as its own CI job

Replace the in-place proxy reboot in e2e_ui_testing with a dedicated
e2e_ui_testing_server_root_path job that boots the proxy once with
SERVER_ROOT_PATH=/litellm, matching how every other proxy variant in the
config gets its own job rather than killing and relaunching the live proxy.

The reboot was failing deterministically: after pkill -9 and relaunch the
prefixed proxy never came back up on :4000 (connection refused), so the smoke
never ran. The readiness step that was supposed to surface the cause could
never reach its boot-log tail because CircleCI runs steps under bash -eo
pipefail and the preceding `curl -sv ... | tail` aborted the step with curl's
exit 7. Booting the proxy as the job's own background step lets any boot crash
land in that step's log instead of being swallowed.

The default e2e_ui_testing job is unchanged aside from dropping the reboot,
prefixed-readiness, and prefixed-smoke steps; the migration smoke still runs at
the root mount there via the default Playwright config.

* fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through (#24232)

* fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through

* test: mock post_call_response_headers_hook in audio speech route tests

* chore(ui): remove dead App Router route stubs under (dashboard) (#30045)

models-and-endpoints, organizations, and virtual-keys each had a page.tsx
route under (dashboard)/ that is not in MIGRATED_PAGES, so the sidebar and
deep links never resolve to it and the route is unreachable. Each was a thin
wrapper that handed the shared view empty or no-op props (empty modelData with
a no-op setModelData, hardcoded empty organizations, no-op
setUserRole/setUserEmail), so reaching one would render a degraded page in any
case. The real wrapper belongs in the PR that flips each page into
MIGRATED_PAGES, written with eyes on it and a test

This continues the dead-scaffolding cleanup from #28891. The shared components
these wrappers rendered (ModelsAndEndpointsView, OrganizationFilters) stay,
since the legacy ?page= switch in app/page.tsx and src/components still import
them

* fix(ui/mcp): reset OAuth state on create-server modal close so a prior server's token no longer leaks into the next add-server session (#30000)

* fix(ui/mcp): reset OAuth hook state on modal close so a prior server's token no longer leaks into the next add-server session

* fix(ui/mcp): clear in-flight OAuth guard on reset and reset form/tools on modal close so nothing leaks on a parent-driven dismiss

* fix(mcp): allow team access-group grants in OAuth authorize/token access check (#30041)

* fix(mcp): honor team access-group grants in OAuth authorize/token access check

* test(mcp): mock build_effective_auth_contexts in non-admin authorize tests for isolation

* docs(security): require a reproduction video for vulnerability reports (#30048) (#30063)

With AI models capable of automated vulnerability discovery now publicly
available, we expect a large increase in report volume, much of it
unverified. Requiring a video of the exploit running against a live
instance raises the bar for submissions and keeps triage focused on
reproducible issues. Reports without a video will be closed and reopened
if one is added later.

Co-authored-by: stuxf <[email protected]>

* feat(ui): add admin flag to disable in-product UI nudges for everyone (#29796)

* feat(ui): add admin flag to disable in-product UI nudges for everyone

Admins can now suppress the survey and Claude Code feedback popups for
all users via a single disable_ui_nudges UI setting, instead of relying
on each user dismissing them individually.

* fix(ui): suppress nudges while ui settings are loading

Gate nudgesDisabled on the ui-settings loading state so an admin with
disable_ui_nudges on doesn't see the survey prompt flash, and the
getInProductNudgesCall fetch doesn't fire, on a cold page load before
the flag resolves. Falls back to showing nudges if the fetch errors.

* test(ui): wrap CreateKeyPage test in QueryClientProvider

page.tsx now calls useUISettings (react-query), which needs a
QueryClient that layout.tsx supplies in production but the test did
not. Add the provider and mock getUiSettings so the query resolves.

* chore(ui): remove dead dashboard files and unused dependencies (#30047)

* chore(ui): remove dead dashboard files and unused dependencies

knip flagged seven orphaned source/config files with no importers and
five declared dependencies that nothing in the tree uses. Removing them
shrinks the dashboard bundle's source surface and keeps the manifest
honest; vite stays installed transitively via vitest, so test tooling is
unaffected.

* fix(ci): restore serverRootPath.config.ts referenced by SERVER_ROOT_PATH workflow

The dead-code sweep removed e2e_tests/serverRootPath.config.ts, but its spec
(tests/login/serverRootPathRedirect.spec.ts) and the test_server_root_path.yml
workflow step still depend on it, so the redirect e2e job failed to load a
config that no longer existed.

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593) (#30009)

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593)

After replace_model_in_jsonl, body.model is a stripped provider id. Reverse-mapping it via resolve_model_name_from_model_id is first-match on model_list and caused false 403s when multiple deployments share the same stripped name. Use target_model_names from the unified file id instead.

Co-authored-by: Cursor <[email protected]>

* fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)

Restores the reverse-lookup for the JSONL body.model fallback path so that
legacy/pre-target_model_names managed files still map stripped provider IDs
back to proxy aliases before auth. Also cleans up redundant `or None`.

Co-Authored-By: Claude Sonnet 4.6 <[email protected]>

* Revert "fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)"

This reverts commit 30d2e96f77ef521ccaaf2193fe554980380eb669.

---------

Co-authored-by: Cursor <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>

* Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI (#30064)

* Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI

Adds cost map entries for claude-fable-5 ($10/$50 per MTok, 1M context,
128K output, adaptive thinking only) on the Anthropic API, Bedrock
converse (base, global, and us/eu geo inference profiles at the 10%
regional premium), Vertex AI, and Azure AI (Microsoft Foundry, which
serves Fable 5 with the full 1M context window unlike Opus 4.8).

Registers anthropic.claude-fable-5 in BEDROCK_CONVERSE_MODELS, lists the
model in the setup wizard, and extends the reasoning effort e2e grid.
The Bedrock, Vertex, and Azure grid cells carry fail_reason markers
until the CI accounts are provisioned: Bedrock needs the provider data
sharing opt-in Fable 5 requires, and the Foundry resource needs a
claude-fable-5 deployment.

The first-party entry carries provider_specific_entry {us: 1.1} for the
inference_geo premium and deliberately no fast multiplier since Fable 5
has no fast mode.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Drop removed sampling params for Claude 4.7+ when drop_params is set

Fable 5, Opus 4.7, and Opus 4.8 removed sampling params: the API rejects
top_p, top_k, and any temperature other than 1 with a 400. LiteLLM was
forwarding them even with drop_params enabled because the Anthropic and
Bedrock converse transformations passed temperature/top_p through
unconditionally.

Mirror the GPT-5/o-series handling: temperature=1 still passes through,
other values and any top_p are dropped when drop_params is set, and
without drop_params a clean client-side UnsupportedParamsError tells the
caller how to opt in, instead of surfacing the raw provider error.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Drive sampling param gating from the cost map and cover top_k

Greptile review follow-ups on the sampling param fix: the restriction for
Fable 5 / Opus 4.7 / 4.8 is now declared as supports_sampling_params: false
on every affected cost map entry (perplexity excluded; that route is
OpenAI-compatible and maps sampling params upstream) and read back through
a tri-state map lookup, keeping the name check only as a fallback for
provider-routed ids whose hosted map entries predate the flag, the same
layering supports_adaptive_thinking uses. top_k bypasses map_openai_params
as a provider-specific kwarg, so it is gated at the shared
AnthropicConfig.transform_request boundary (direct, Bedrock invoke, Vertex,
Azure) and in the Bedrock converse _handle_top_k_value path, with
drop_params threaded through the converse transform helpers.

Also updates the reasoning effort grid cell count assertion for the four
Fable 5 rows added on this branch (29 x 11 cells).

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Declare supports_sampling_params in the cost map schema

The model map validation schema uses additionalProperties: false, so the
new flag must be declared for the 28 entries that carry it; this was the
one failing job (misc / Run tests) on the previous commit.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* fix(bedrock): gate top_k=0 on converse to match Anthropic boundary

Truthiness check let top_k=0 silently disappear on models that removed
sampling params, while AnthropicConfig.transform_request treats 0 as
present and raises UnsupportedParamsError (or drops when drop_params is
set). Switch to 'is not None' so converse, direct Anthropic, invoke,
Vertex, and Azure all behave the same for top_k=0.

---------

Co-authored-by: Cursor Agent <[email protected]>

* fix: enable compact-2026-01-12 beta header for vertex_ai provider

The vertex_ai block in anthropic_beta_headers_config.json mapped
compact-2026-01-12 to null, so update_headers_with_filtered_beta
stripped the header before the request reached Vertex while the
compact_20260112 context edit stayed in the body, and Vertex rejected
the request with HTTP 400. Vertex rawPredict accepts the header, and
the bedrock and databricks blocks already forward it. Mirrors #21867,
which enabled context-1m-2025-08-07 for vertex_ai the same way.

Fixes #27290.

---------

Co-authored-by: milan-berri <[email protected]>
Co-authored-by: Cursor <[email protected]>
Co-authored-by: ryan-crabbe-berri <[email protected]>
Co-authored-by: michelligabriele <[email protected]>
Co-authored-by: tin-berri <[email protected]>
Co-authored-by: yuneng-jiang <[email protected]>
Co-authored-by: stuxf <[email protected]>
Co-authored-by: Sameer Kankute <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>
Co-authored-by: Mateo Wang <[email protected]>

* fix(proxy): coerce litellm_settings.max_budget env var to float (#30113)

* fix(team): reserve team budget raises for proxy admins on /team/update (#30030)

The caller's PERSONAL max_budget was the wrong yardstick for /team/update: a
team's spend ceiling has nothing to do with the admin's own key budget. That
comparison was an unintended side effect of reusing _check_user_team_limits()
(which exists for the /team/new path) and broke the UI, which re-sends the
unchanged budget on every save.

New behavior on /team/update for standalone teams:
- A team admin (already authorized via _verify_team_access) may freely KEEP or
  LOWER the team budget, and change models/tpm/rpm, without being gated by their
  personal limits.
- GROWING a team's spend ceiling is a budget-authority action reserved for proxy
  admins -> 403 for team admins. "Growing" covers both raising max_budget above
  the team's current finite value and removing the cap entirely (max_budget=null,
  detected via model_fields_set so an explicit null is distinguished from an
  omitted field). For a team that currently has no cap, setting a finite value is
  a restriction and is allowed.
- Org-scoped teams remain governed by _check_org_team_limits() (capped by the
  org budget).

Also reverts the #29525 existing_team_max_budget workaround in
_check_user_team_limits() back to the create-only form; /team/new still enforces
the creator's personal caps.

docs(access_control): resolve the contradiction in the team-admin section —
team admins can keep/lower the budget and manage rate limits/models, but cannot
raise the team budget (proxy-admin only).

tests: unit + behavior coverage for raise-blocked, cap-removal-blocked (team
admin), raise/removal allowed (proxy admin), uncapped-team restriction allowed,
keep/lower/resend allowed, and unchanged create-path guards.

Co-authored-by: Cursor <[email protected]>

* test(ui): data-driven App Router migration E2E smoke (default + server-root-path) (#29974)

* test(ui): add a data-driven App Router migration E2E smoke

Add a growing Playwright smoke for migrated pages: for each segment it deep-links
to the path route, asserts the URL and that the dashboard shell rendered, then
clicks off to a legacy page and asserts navigation still works. Driven by
e2e_tests/fixtures/migratedPages.ts, so adding a page is one line.

Runs in two situations against the same proxy: the default mount (npm run
e2e:migration) and a non-root SERVER_ROOT_PATH mount (npm run e2e:migration:root).
globalSetup now logs in at `${SERVER_ROOT_PATH}/ui/login` so the admin storage
state is valid under a prefix. Seeded with api-reference; append the rest as their
migrations merge.

* test(ui): support headed slow-motion + watch pauses in the migration smoke

Honor SLOWMO in the server-root-path config (the default config already did),
and add an env-gated E2E_WATCH_MS pause so a headed run lingers on each state.
Both are no-ops by default, so CI behavior is unchanged.

* test(ui): make the migration smoke a sidebar-click user journey

Rework the smoke from deep-linking to a real navigation journey: start at the
landing page, click the migrated page in the sidebar (expanding submenus for
nested items), assert the path route rendered, reload it (the check a wrong
server_root_path breaks), bounce to a legacy page and back, and — once two pages
are migrated — navigate directly between two migrated pages. Verifies via URL +
shell render, driven by the same fixture list.

* test(ui): address review on the migration smoke

Escape ROOT and segment before interpolating them into RegExp URL matchers so a
future segment containing regex metacharacters can't silently widen the match.
Make the server-root-path config fail fast when SERVER_ROOT_PATH is unset instead
of silently re-running the default mount and passing without exercising the prefix.

* test(ui): drop unused watch helper and fix stale smoke README

* test(ui): run the migration smoke under a server root path in CI

* test(ui): harden + instrument the server-root-path proxy reboot in CI

* test(ui): run the server-root-path migration smoke as its own CI job

Replace the in-place proxy reboot in e2e_ui_testing with a dedicated
e2e_ui_testing_server_root_path job that boots the proxy once with
SERVER_ROOT_PATH=/litellm, matching how every other proxy variant in the
config gets its own job rather than killing and relaunching the live proxy.

The reboot was failing deterministically: after pkill -9 and relaunch the
prefixed proxy never came back up on :4000 (connection refused), so the smoke
never ran. The readiness step that was supposed to surface the cause could
never reach its boot-log tail because CircleCI runs steps under bash -eo
pipefail and the preceding `curl -sv ... | tail` aborted the step with curl's
exit 7. Booting the proxy as the job's own background step lets any boot crash
land in that step's log instead of being swallowed.

The default e2e_ui_testing job is unchanged aside from dropping the reboot,
prefixed-readiness, and prefixed-smoke steps; the migration smoke still runs at
the root mount there via the default Playwright config.

* fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through (#24232)

* fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through

* test: mock post_call_response_headers_hook in audio speech route tests

* chore(ui): remove dead App Router route stubs under (dashboard) (#30045)

models-and-endpoints, organizations, and virtual-keys each had a page.tsx
route under (dashboard)/ that is not in MIGRATED_PAGES, so the sidebar and
deep links never resolve to it and the route is unreachable. Each was a thin
wrapper that handed the shared view empty or no-op props (empty modelData with
a no-op setModelData, hardcoded empty organizations, no-op
setUserRole/setUserEmail), so reaching one would render a degraded page in any
case. The real wrapper belongs in the PR that flips each page into
MIGRATED_PAGES, written with eyes on it and a test

This continues the dead-scaffolding cleanup from #28891. The shared components
these wrappers rendered (ModelsAndEndpointsView, OrganizationFilters) stay,
since the legacy ?page= switch in app/page.tsx and src/components still import
them

* fix(ui/mcp): reset OAuth state on create-server modal close so a prior server's token no longer leaks into the next add-server session (#30000)

* fix(ui/mcp): reset OAuth hook state on modal close so a prior server's token no longer leaks into the next add-server session

* fix(ui/mcp): clear in-flight OAuth guard on reset and reset form/tools on modal close so nothing leaks on a parent-driven dismiss

* fix(mcp): allow team access-group grants in OAuth authorize/token access check (#30041)

* fix(mcp): honor team access-group grants in OAuth authorize/token access check

* test(mcp): mock build_effective_auth_contexts in non-admin authorize tests for isolation

* docs(security): require a reproduction video for vulnerability reports (#30048) (#30063)

With AI models capable of automated vulnerability discovery now publicly
available, we expect a large increase in report volume, much of it
unverified. Requiring a video of the exploit running against a live
instance raises the bar for submissions and keeps triage focused on
reproducible issues. Reports without a video will be closed and reopened
if one is added later.

Co-authored-by: stuxf <[email protected]>

* feat(ui): add admin flag to disable in-product UI nudges for everyone (#29796)

* feat(ui): add admin flag to disable in-product UI nudges for everyone

Admins can now suppress the survey and Claude Code feedback popups for
all users via a single disable_ui_nudges UI setting, instead of relying
on each user dismissing them individually.

* fix(ui): suppress nudges while ui settings are loading

Gate nudgesDisabled on the ui-settings loading state so an admin with
disable_ui_nudges on doesn't see the survey prompt flash, and the
getInProductNudgesCall fetch doesn't fire, on a cold page load before
the flag resolves. Falls back to showing nudges if the fetch errors.

* test(ui): wrap CreateKeyPage test in QueryClientProvider

page.tsx now calls useUISettings (react-query), which needs a
QueryClient that layout.tsx supplies in production but the test did
not. Add the provider and mock getUiSettings so the query resolves.

* chore(ui): remove dead dashboard files and unused dependencies (#30047)

* chore(ui): remove dead dashboard files and unused dependencies

knip flagged seven orphaned source/config files with no importers and
five declared dependencies that nothing in the tree uses. Removing them
shrinks the dashboard bundle's source surface and keeps the manifest
honest; vite stays installed transitively via vitest, so test tooling is
unaffected.

* fix(ci): restore serverRootPath.config.ts referenced by SERVER_ROOT_PATH workflow

The dead-code sweep removed e2e_tests/serverRootPath.config.ts, but its spec
(tests/login/serverRootPathRedirect.spec.ts) and the test_server_root_path.yml
workflow step still depend on it, so the redirect e2e job failed to load a
config that no longer existed.

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593) (#30009)

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593)

After replace_model_in_jsonl, body.model is a stripped provider id. Reverse-mapping it via resolve_model_name_from_model_id is first-match on model_list and caused false 403s when multiple deployments share the same stripped name. Use target_model_names from the unified file id instead.

Co-authored-by: Cursor <[email protected]>

* fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)

Restores the reverse-lookup for the JSONL body.model fallback path so that
legacy/pre-target_model_names managed files still map stripped provider IDs
back to proxy aliases before auth. Also cleans up redundant `or None`.

Co-Authored-By: Claude Sonnet 4.6 <[email protected]>

* Revert "fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)"

This reverts commit 30d2e96f77ef521ccaaf2193fe554980380eb669.

---------

Co-authored-by: Cursor <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>

* Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI (#30064)

* Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI

Adds cost map entries for claude-fable-5 ($10/$50 per MTok, 1M context,
128K output, adaptive thinking only) on the Anthropic API, Bedrock
converse (base, global, and us/eu geo inference profiles at the 10%
regional premium), Vertex AI, and Azure AI (Microsoft Foundry, which
serves Fable 5 with the full 1M context window unlike Opus 4.8).

Registers anthropic.claude-fable-5 in BEDROCK_CONVERSE_MODELS, lists the
model in the setup wizard, and extends the reasoning effort e2e grid.
The Bedrock, Vertex, and Azure grid cells carry fail_reason markers
until the CI accounts are provisioned: Bedrock needs the provider data
sharing opt-in Fable 5 requires, and the Foundry resource needs a
claude-fable-5 deployment.

The first-party entry carries provider_specific_entry {us: 1.1} for the
inference_geo premium and deliberately no fast multiplier since Fable 5
has no fast mode.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Drop removed sampling params for Claude 4.7+ when drop_params is set

Fable 5, Opus 4.7, and Opus 4.8 removed sampling params: the API rejects
top_p, top_k, and any temperature other than 1 with a 400. LiteLLM was
forwarding them even with drop_params enabled because the Anthropic and
Bedrock converse transformations passed temperature/top_p through
unconditionally.

Mirror the GPT-5/o-series handling: temperature=1 still passes through,
other values and any top_p are dropped when drop_params is set, and
without drop_params a clean client-side UnsupportedParamsError tells the
caller how to opt in, instead of surfacing the raw provider error.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Drive sampling param gating from the cost map and cover top_k

Greptile review follow-ups on the sampling param fix: the restriction for
Fable 5 / Opus 4.7 / 4.8 is now declared as supports_sampling_params: false
on every affected cost map entry (perplexity excluded; that route is
OpenAI-compatible and maps sampling params upstream) and read back through
a tri-state map lookup, keeping the name check only as a fallback for
provider-routed ids whose hosted map entries predate the flag, the same
layering supports_adaptive_thinking uses. top_k bypasses map_openai_params
as a provider-specific kwarg, so it is gated at the shared
AnthropicConfig.transform_request boundary (direct, Bedrock invoke, Vertex,
Azure) and in the Bedrock converse _handle_top_k_value path, with
drop_params threaded through the converse transform helpers.

Also updates the reasoning effort grid cell count assertion for the four
Fable 5 rows added on this branch (29 x 11 cells).

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Declare supports_sampling_params in the cost map schema

The model map validation schema uses additionalProperties: false, so the
new flag must be declared for the 28 entries that carry it; this was the
one failing job (misc / Run tests) on the previous commit.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* fix(bedrock): gate top_k=0 on converse to match Anthropic boundary

Truthiness check let top_k=0 silently disappear on models that removed
sampling params, while AnthropicConfig.transform_request treats 0 as
present and raises UnsupportedParamsError (or drops when drop_params is
set). Switch to 'is not None' so converse, direct Anthropic, invoke,
Vertex, and Azure all behave the same for top_k=0.

---------

Co-authored-by: Cursor Agent <[email protected]>

* fix(proxy): coerce litellm_settings.max_budget env var to float

When max_budget is set in litellm_settings via os.environ/MAX_BUDGET,
the env var resolves to a string and the generic setattr branch in
ProxyConfig.load_config stored it as-is, so the startup check
litellm.max_budget > 0 raised TypeError. The earlier fix (#23855) only
covered the CLI initialize() path. Coerce the value to float in the
settings loop, matching the existing max_internal_user_budget handling.

Fixes #26696.

---------

Co-authored-by: milan-berri <[email protected]>
Co-authored-by: Cursor <[email protected]>
Co-authored-by: ryan-crabbe-berri <[email protected]>
Co-authored-by: michelligabriele <[email protected]>
Co-authored-by: tin-berri <[email protected]>
Co-authored-by: yuneng-jiang <[email protected]>
Co-authored-by: stuxf <[email protected]>
Co-authored-by: Sameer Kankute <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>
Co-authored-by: Mateo Wang <[email protected]>

* fix(router): don't drop bedrock pass-through deployments using IAM credentials (#30111)

* Fix Bedrock passthrough deployment dropped when using IAM credentials

Bedrock deployments with use_in_pass_through enabled and IAM/OIDC auth
(aws_role_name, no api_key) hit the generic pass-through branch in
Router._initialize_deployment_for_pass_through, which calls
set_pass_through_credentials and raises "api_key is required". The
exception drops the deployment from the router entirely, breaking both
passthrough and normal routing for that model.

Skip the credential store write when no api_key is set; the bedrock
passthrough route resolves AWS credentials at request time via
BedrockConverseLLM.get_credentials(), not the passthrough credential
store, so there is nothing to register here.

Fixes #27728.

* Reset passthrough credentials singleton before api_key credential test

The test reads the module-level passthrough_endpoint_router singleton,
so a stale "openai" entry written by an earlier test in the same
process could make the assertion pass without exercising the code path.
Clearing the credentials dict up front makes the test order-independent.

* fix(sdk): stop mirroring reasoning_content in provider_specific_fields (#30110)

The dict-to-response conversion path mirrored reasoning_content into
provider_specific_fields, while live provider transforms (Anthropic's
_build_provider_specific_fields) only set it top-level on the Message.
Cache-replayed messages therefore serialized differently from live
ones, breaking disk cache key stability for multi-turn conversations
with extended thinking.

The mirror was added for DeepSeek before Message.reasoning_content
existed as a top-level attribute. The top-level field is still set by
the converter, so DeepSeek's request-side promotion is unaffected.

Fixes #27337.

* fix(mcp): coerce mcp_server_cost_info values to float at ingest (#30109)

* fix(mcp): coerce mcp_server_cost_info values to float at ingest

YAML 1.1 parses scientific notation without a decimal point
(e.g. 7e-05) as a string, and MCPServerCostInfo is a TypedDict with no
runtime validation, so a string-typed default_cost_per_query from
config.yaml flowed through the proxy untouched and crashed the MCP
server settings page with '.toFixed is not a function'. Normalize
mcp_server_cost_info on both the config and DB load paths, dropping
non-numeric values with a warning instead of failing the server load.

Fixes #27097.

* fix(mcp): drop non-numeric default_cost_per_query instead of nulling it

Keeping the key with a None value still exposes a null to the UI,
which can crash .toFixed formatting when the consumer checks key
existence rather than truthiness. Delete the key on coercion failure,
matching how non-numeric per-tool cost entries are already omitted.

* fix(proxy): count embedding and text completion tokens toward TPM limits (#30105)

* fix(proxy): count embedding and text completion tokens toward TPM limits

The parallel request limiters only read token usage off ModelResponse,
so EmbeddingResponse and TextCompletionResponse objects left
total_tokens at 0 and the per key, user, team, and end user TPM
counters never incremented. Requests to /v1/embeddings and
/v1/completions were effectively free against any tpm_limit. In the v3
limiter this was worse: the post-call reconciliation computed actual
usage as 0 and refunded the pre-call reservation made at request time.

Broaden the isinstance checks to accept EmbeddingResponse and
TextCompletionResponse, which both expose a Usage object, at the four
per-scope sites in parallel_request_limiter.py and at the usage
extraction in parallel_request_limiter_v3.py. ResponsesAPIResponse was
already covered in v3 via BaseLiteLLMOpenAIResponseObject.

Fixes #27738.

* test(proxy): cover v1 limiter TPM counting for embedding and text completion responses

Exercise the broadened isinstance sites in parallel_request_limiter.py
by asserting that async_log_success_event adds total_tokens to the per
key, user, team, and end user TPM counters for EmbeddingResponse and
TextCompletionResponse objects. The counters are pre-seeded at zero so
the assertion is exactly the increment; on the pre-fix code these
responses left total_tokens at 0 and the test fails.

* fix(openai): forward client headers on the text completion path (#30103)

* fix(openai): forward client headers on the text completion path

litellm.completion() merges caller headers with extra_headers, but the
text-completion-openai branch never passed the merged dict to
openai_text_completions.completion(), and the handler only used its
headers argument for logging. Pass the merged headers through the call
site and set them as extra_headers on the outgoing request, mirroring
the chat completion handler, so x-* client headers forwarded by the
proxy reach the provider on /v1/completions.

Fixes #27410.

* Drop redundant extra_headers assignment and fix test module collision

completion() merges extra_headers into headers before the
text-completion-openai branch, and the handler now sets the merged
headers as extra_headers on the request, so the branch-local
optional_params["extra_headers"] assignment was a dead duplicate.
Removing it keeps the assignment in one place while both entry paths
(litellm.text_completion and direct handler callers) still forward
headers; a new regression test pins the extra_headers kwarg path.

Also rename the test module to test_completion_handler.py since its
basename collided with tests/test_litellm/llms/bedrock/batches/
test_handler.py and broke pytest collection.

* fix(bedrock): route Anthropic-shape count_tokens to InvokeModel and base64-encode the body (#30102)

* fix(bedrock): route Anthropic-shape count_tokens to InvokeModel

POST /v1/messages/count_tokens with Anthropic content blocks
({"type": "text"|"tool_use"|...}) was routed to the Converse input of
the Bedrock CountTokens API. The Converse transform copies list content
through verbatim, so Bedrock rejected the request with a 400 and the
caller silently fell back to the local tokenizer, returning counts that
can be off by ~50% on tool-heavy payloads.

_detect_input_type now routes messages whose content blocks carry a
"type" key (Anthropic shape) to the invokeModel input, which forwards
the body verbatim. The invokeModel body is now base64-encoded as the
CountTokens API requires (InvokeModelTokensRequest.body is a
base64-encoded blob), and Anthropic Messages bodies get the
anthropic_version and max_tokens fields Bedrock validates against.

Fixes #27632.

* refactor(bedrock): name the CountTokens max_tokens placeholder

Replace the magic 1024 with a module-level
DEFAULT_ANTHROPIC_INVOKE_MODEL_MAX_TOKENS constant so the intent is
explicit and t…

…T-3593) (BerriAI#30009)

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593)

After replace_model_in_jsonl, body.model is a stripped provider id. Reverse-mapping it via resolve_model_name_from_model_id is first-match on model_list and caused false 403s when multiple deployments share the same stripped name. Use target_model_names from the unified file id instead.

Co-authored-by: Cursor <[email protected]>

* fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)

Restores the reverse-lookup for the JSONL body.model fallback path so that
legacy/pre-target_model_names managed files still map stripped provider IDs
back to proxy aliases before auth. Also cleans up redundant `or None`.

Co-Authored-By: Claude Sonnet 4.6 <[email protected]>

* Revert "fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)"

This reverts commit 30d2e96.

---------

Co-authored-by: Cursor <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>

* fix(mcp): report scoped server name during initialize (#29865)

* fix mcp scoped server name

* Update litellm/proxy/_experimental/mcp_server/mcp_context.py

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* test(mcp): cover scoped server name in the SSE initialize handler

---------

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* fix(ui): show all session logs in the drawer, not just the first 50 (#29795)

* fix(ui): show newest session logs first

* test(ui): keep session log pagination coverage

* fix(ui): show all session logs in the drawer, not just the first page

The session detail drawer fetched session logs via sessionSpendLogsCall
without page/page_size, so it only ever received the backend default of one
page (50 rows). Sessions with more than 50 calls had the rest unreachable in
the UI (#29153).

sessionSpendLogsCall now takes page/page_size, and the drawer fetches the
first page, reads total_pages, then fetches the remaining pages and
accumulates them before the existing client-side sort. This keeps the single
continuous list (and the selected-log lookup and keyboard navigation, which
all assume the full session) correct. Fetching is bounded by a page cap, and
the sidebar shows a "showing most recent N" note if a session exceeds it.

The rows are lightweight metadata (the endpoint excludes messages/response),
so the full set is small; request/response bodies are still loaded per log on
demand.

* fix(ui): default session drawer to most recent log, newest first

Open a session with its most recent log selected, and order the sidebar
newest-first to match the all-sessions logs overview. MCP calls stay
grouped last. The latest log by time is computed explicitly, since the
MCP grouping means it is not always the first row.

* Apply fetching pages in batches suggestion from @greptile-apps[bot]

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* fix(ui): derive session total from accumulated rows when backend omits it

Compute the session total after all pages are fetched, falling back to the
accumulated row count rather than the first page's. Guards the truncation
note against a backend response that omits total but spans multiple pages.

---------

Co-authored-by: Yufeng He <[email protected]>
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* fix(proxy): handle Mistral multipart passthrough (#29927)

* fix(proxy): handle Mistral multipart passthrough

* chore: satisfy passthrough ci formatting

* test(proxy): cover Mistral passthrough in CI shard

* fix(vertex_ai): use REP host for context caching on eu/us multi-region endpoints (#29573)

Context caching built the cachedContents URL as
https://{location}-aiplatform.googleapis.com, which is an invalid host for the
eu/us multi-region endpoints and returns 404. The inference path already
resolves these to the REP host (https://aiplatform.{geo}.rep.googleapis.com)
via get_vertex_base_url(); reuse that helper in
_get_token_and_url_context_caching so caching uses the same host as inference.

Adds tests covering the eu/us multi-region cachedContents URLs (v1 and
v1beta1).

Fixes #29571

* Support per-model encrypted content affinity config (#29760)

Co-authored-by: shin-berri <[email protected]>
Co-authored-by: yuneng-jiang <[email protected]>

* fix: propagate upstream status code in proxy API exception handler (#29402)

* fix: propagate upstream status code in proxy API exception handler

When Google GenAI / Vertex returns a 404 for deprecated or missing
models via streamGenerateContent, the exception was falling through to
a generic handler that defaulted to 500. Now provider exceptions
carrying a valid HTTP status_code correctly propagate it through to
the ProxyException.

* fix: apply black formatting to common_request_processing.py

* fix: tighten status code range to 400-599 and deduplicate ProxyException raise

* fix(tests): use valid vertex_location in context caching tests

Replace "test_location" (contains underscore) with "us-central1" so tests
pass the regex validation added in get_vertex_base_url().

Co-Authored-By: Claude Sonnet 4.6 <[email protected]>

* feat(sdk): add xAI OAuth provider (#29866)

* Add xAI OAuth provider

* Update oauth.py

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* Fix xAI OAuth CI failures

* Add xAI OAuth coverage tests

* Move xAI OAuth coverage tests to core utils

* Address xAI OAuth review comments

* Prevent xAI OAuth api_base token exfiltration

* Treat blank xAI OAuth api keys as absent

* Wrap invalid xAI OAuth JSON responses

* Use xAI OAuth behind explicit flag

---------

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* fix(proxy) #27734 allow clearing budget_duration and team_member fields by sending null on /key/update and /team/update (#27751)

* fix(proxy): allow clearing budget_duration and team_member fields by sending null on /key/update and /team/update

Fixes #27734

Sending null for budget_duration, team_member_budget,
team_member_budget_duration, team_member_rpm_limit, or
team_member_tpm_limit via /key/update or /team/update returned 200 OK
but silently ignored the null value. The fields remained unchanged in
the database.

Root causes:
- /key/update: prepare_key_update_data() popped budget_duration from the
  update dict but never re-added it (or budget_reset_at) when the value
  was None.
- /team/update: _set_budget_reset_at() only acted when budget_duration
  was non-None, leaving a stale budget_reset_at in the DB.
- /team/update: team_member_* null values bypassed the budget table
  update entirely because should_create_budget() requires at least one
  non-None field.

* test(proxy): cover no-budget-row path in clear_team_member_budget_fields

* fix(presidio): unmask PII tokens in Anthropic native SSE streaming bytes (#30028)

* fix(presidio): unmask PII tokens in Anthropic native SSE streaming bytes

When output_parse_pii=true on the Anthropic native path (anthropic/claude-*),
response chunks arrive as raw bytes in SSE format. _stream_pii_unmasking was
yielding those bytes unchanged, so <PERSON_1> tokens were never replaced with
the original values before reaching the caller.

Add _unmask_sse_bytes_chunk to parse each data: line, find content_block_delta
/ text_delta events, and apply _unmask_pii_text before re-encoding. Wire it
into _stream_pii_unmasking so bytes chunks are unmasked when pii_tokens exist.

* fix(presidio): handle CRLF line endings and non-ASCII PII in SSE unmask

Strip trailing \r before the [DONE] guard so CRLF-terminated SSE chunks
don't bypass it and silently swallow a JSONDecodeError. Add
ensure_ascii=False to json.dumps so non-ASCII replacement values like
accented names are preserved as UTF-8 on the wire rather than being
\uXXXX-escaped. Add regression tests for both cases.

* feat(bedrock_mantle): path-aware Responses routing (/v1/responses vs /openai/v1/responses) (#29925)

* feat(bedrock_mantle): path-aware Responses routing (/v1/responses vs /openai/v1/responses)

Bedrock Mantle serves the Responses API on two upstream paths:
  - gpt frontier models (gpt-5.5 / gpt-5.4) on /openai/v1/responses
  - every other Responses-capable model (e.g. gpt-oss) on the standard /v1/responses

BedrockMantleResponsesAPIConfig gains a `use_openai_path` flag; the provider gate in
utils.py picks the path per model: openai.gpt-* (non gpt-oss) -> /openai/v1/responses;
any model declared mode=responses (price-map entry or user model_info) -> /v1/responses;
everything else returns None and keeps the existing chat-completions emulation.

Adds gpt-5.5 / gpt-5.4 price-map entries, registry wiring, and the routing-matrix tests.

* feat(bedrock_mantle): data-driven frontier routing via use_openai_responses_path

Addresses the Greptile review point that frontier detection should be a
price-map field rather than a hardcoded name match. The gate now routes a
model to /openai/v1/responses when its price-map entry declares
use_openai_responses_path, so a frontier model whose name does not follow the
openai.gpt- convention can be onboarded by JSON alone. The name-convention
check is kept as a fallback that needs no price-map entry, which preserves
zero-change routing for a future gpt-6 before its entry loads. gpt-5.5 / gpt-5.4
get the flag in both price maps. Adds tests for the data-driven flag path and
for the flag presence on the gpt-5.x entries; both branches are mutation-tested.

* test(model_prices): allow use_openai_responses_path in price-map schema

The model_prices_and_context_window.json schema validator
(test_aaamodel_prices_and_context_window_json_is_valid) enforces
additionalProperties: false, so the new use_openai_responses_path flag on the
gpt-5.5 / gpt-5.4 entries failed validation. Add it to the schema as a boolean,
alongside the other supports_* / capability flags.

* Add Tensormesh serverless models to the model cost map (#30037)

* Add Tensormesh serverless models to the model cost map

* Flag reasoning support on the Tensormesh models that expose thinking mode

* fix(proxy): invalidate stale key spend counter after budget reset or manual spend update (#30001)

* fix(proxy): reconcile stale key spend counter after budget reset

* fix(proxy): invalidate stale key spend counter after budget reset or manual spend update

* fix(proxy): remove read-time stale counter reconciliation to prevent budget bypass

* revert: undo unrelated formatting changes in enterprise directory

* test(proxy): add unit test for key spend update invalidating counter

* test(proxy): fix mocked update_data and hash token expectations in unit test

* fix(proxy): use Responses-API transformer in pass-through cost tracking (#29728)

The `elif is_responses:` branch of `openai_passthrough_handler` was
calling the chat-completions `transform_response` on a Responses API
payload. The chat-completions transformer expects `choices: [...]`
in the raw response; the Responses API uses `output: [...]` and
`usage.input_tokens` / `usage.output_tokens` (not
`prompt_tokens` / `completion_tokens`). The result was a
KeyError 'choices' deep inside `convert_to_model_response_object`,
swallowed by the surrounding `except Exception` in the handler, and
the SpendLogs row was written by the fallback path with zeroed-out
tokens, spend, and model.

This bug silently undercounts cost for every successful pass-through
call to either OpenAI's `/v1/responses` or Azure's
`/openai/v1/responses` (deployments configured for the Responses
API). Reproduced 2026-06-04 against a real Azure OpenAI Responses
API deployment proxied through LiteLLM v1.88.0.

Fix: use the dedicated
`OpenAIResponsesAPIConfig.transform_response_api_response` for the
Responses branch. This transformer already exists in LiteLLM
(`litellm/llms/openai/responses/transformation.py`) and knows the
Responses-API on-the-wire shape. `litellm.completion_cost` already
handles `ResponsesAPIResponse` natively with `call_type="responses"`,
so no downstream changes are needed.

Tests:

  test_responses_api_uses_responses_transformer_not_chat_completions
    NEW. Real regression test — exercises the openai_passthrough_handler
    with a real-shaped Responses payload (no `choices`, has `output`
    and Responses-API `usage` keys) and NO mocked `get_provider_config`.
    Pre-fix: raises KeyError 'choices' inside the chat-completions
    transformer (the bug). Post-fix: returns a ResponsesAPIResponse,
    completion_cost is called with call_type="responses" and a
    ResponsesAPIResponse instance (asserted).
    Verified to fail on un-fixed handler + pass on fixed handler
    before commit.

  test_responses_api_cost_tracking
    UPDATED. Old test mocked `get_provider_config` (no longer called
    in the responses branch post-fix). Now mocks the Responses
    transformer directly (`OpenAIResponsesAPIConfig.transform_response_api_response`)
    to test the downstream cost-calc contract.

Out of scope for this PR (separate followup):
  - Recognizing *.cognitiveservices.azure.com (the newer Azure
    OpenAI hostname) in the is_openai_*_route checks. Separate PR.

Co-authored-by: shin-berri <[email protected]>
Co-authored-by: yuneng-jiang <[email protected]>

* fix(skills): execute DB skills by matching the litellm_skill_ tool name prefix (#30116)

Skill IDs are generated as litellm_skill_<uuid> and the model-facing
tool name is the sanitized skill ID, but the post-call execution gates
in SkillsInjectionHook only ran tools whose name starts with "skill_",
so DB skills were silently returned to the client as raw tool calls.

Fixes #28122.

Co-authored-by: Cursor <[email protected]>

* fix(anthropic): synthesize content_block_start when Responses stream omits output_item.added (#30115)

* fix(team): reserve team budget raises for proxy admins on /team/update (#30030)

The caller's PERSONAL max_budget was the wrong yardstick for /team/update: a
team's spend ceiling has nothing to do with the admin's own key budget. That
comparison was an unintended side effect of reusing _check_user_team_limits()
(which exists for the /team/new path) and broke the UI, which re-sends the
unchanged budget on every save.

New behavior on /team/update for standalone teams:
- A team admin (already authorized via _verify_team_access) may freely KEEP or
  LOWER the team budget, and change models/tpm/rpm, without being gated by their
  personal limits.
- GROWING a team's spend ceiling is a budget-authority action reserved for proxy
  admins -> 403 for team admins. "Growing" covers both raising max_budget above
  the team's current finite value and removing the cap entirely (max_budget=null,
  detected via model_fields_set so an explicit null is distinguished from an
  omitted field). For a team that currently has no cap, setting a finite value is
  a restriction and is allowed.
- Org-scoped teams remain governed by _check_org_team_limits() (capped by the
  org budget).

Also reverts the #29525 existing_team_max_budget workaround in
_check_user_team_limits() back to the create-only form; /team/new still enforces
the creator's personal caps.

docs(access_control): resolve the contradiction in the team-admin section —
team admins can keep/lower the budget and manage rate limits/models, but cannot
raise the team budget (proxy-admin only).

tests: unit + behavior coverage for raise-blocked, cap-removal-blocked (team
admin), raise/removal allowed (proxy admin), uncapped-team restriction allowed,
keep/lower/resend allowed, and unchanged create-path guards.

Co-authored-by: Cursor <[email protected]>

* test(ui): data-driven App Router migration E2E smoke (default + server-root-path) (#29974)

* test(ui): add a data-driven App Router migration E2E smoke

Add a growing Playwright smoke for migrated pages: for each segment it deep-links
to the path route, asserts the URL and that the dashboard shell rendered, then
clicks off to a legacy page and asserts navigation still works. Driven by
e2e_tests/fixtures/migratedPages.ts, so adding a page is one line.

Runs in two situations against the same proxy: the default mount (npm run
e2e:migration) and a non-root SERVER_ROOT_PATH mount (npm run e2e:migration:root).
globalSetup now logs in at `${SERVER_ROOT_PATH}/ui/login` so the admin storage
state is valid under a prefix. Seeded with api-reference; append the rest as their
migrations merge.

* test(ui): support headed slow-motion + watch pauses in the migration smoke

Honor SLOWMO in the server-root-path config (the default config already did),
and add an env-gated E2E_WATCH_MS pause so a headed run lingers on each state.
Both are no-ops by default, so CI behavior is unchanged.

* test(ui): make the migration smoke a sidebar-click user journey

Rework the smoke from deep-linking to a real navigation journey: start at the
landing page, click the migrated page in the sidebar (expanding submenus for
nested items), assert the path route rendered, reload it (the check a wrong
server_root_path breaks), bounce to a legacy page and back, and — once two pages
are migrated — navigate directly between two migrated pages. Verifies via URL +
shell render, driven by the same fixture list.

* test(ui): address review on the migration smoke

Escape ROOT and segment before interpolating them into RegExp URL matchers so a
future segment containing regex metacharacters can't silently widen the match.
Make the server-root-path config fail fast when SERVER_ROOT_PATH is unset instead
of silently re-running the default mount and passing without exercising the prefix.

* test(ui): drop unused watch helper and fix stale smoke README

* test(ui): run the migration smoke under a server root path in CI

* test(ui): harden + instrument the server-root-path proxy reboot in CI

* test(ui): run the server-root-path migration smoke as its own CI job

Replace the in-place proxy reboot in e2e_ui_testing with a dedicated
e2e_ui_testing_server_root_path job that boots the proxy once with
SERVER_ROOT_PATH=/litellm, matching how every other proxy variant in the
config gets its own job rather than killing and relaunching the live proxy.

The reboot was failing deterministically: after pkill -9 and relaunch the
prefixed proxy never came back up on :4000 (connection refused), so the smoke
never ran. The readiness step that was supposed to surface the cause could
never reach its boot-log tail because CircleCI runs steps under bash -eo
pipefail and the preceding `curl -sv ... | tail` aborted the step with curl's
exit 7. Booting the proxy as the job's own background step lets any boot crash
land in that step's log instead of being swallowed.

The default e2e_ui_testing job is unchanged aside from dropping the reboot,
prefixed-readiness, and prefixed-smoke steps; the migration smoke still runs at
the root mount there via the default Playwright config.

* fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through (#24232)

* fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through

* test: mock post_call_response_headers_hook in audio speech route tests

* chore(ui): remove dead App Router route stubs under (dashboard) (#30045)

models-and-endpoints, organizations, and virtual-keys each had a page.tsx
route under (dashboard)/ that is not in MIGRATED_PAGES, so the sidebar and
deep links never resolve to it and the route is unreachable. Each was a thin
wrapper that handed the shared view empty or no-op props (empty modelData with
a no-op setModelData, hardcoded empty organizations, no-op
setUserRole/setUserEmail), so reaching one would render a degraded page in any
case. The real wrapper belongs in the PR that flips each page into
MIGRATED_PAGES, written with eyes on it and a test

This continues the dead-scaffolding cleanup from #28891. The shared components
these wrappers rendered (ModelsAndEndpointsView, OrganizationFilters) stay,
since the legacy ?page= switch in app/page.tsx and src/components still import
them

* fix(ui/mcp): reset OAuth state on create-server modal close so a prior server's token no longer leaks into the next add-server session (#30000)

* fix(ui/mcp): reset OAuth hook state on modal close so a prior server's token no longer leaks into the next add-server session

* fix(ui/mcp): clear in-flight OAuth guard on reset and reset form/tools on modal close so nothing leaks on a parent-driven dismiss

* fix(mcp): allow team access-group grants in OAuth authorize/token access check (#30041)

* fix(mcp): honor team access-group grants in OAuth authorize/token access check

* test(mcp): mock build_effective_auth_contexts in non-admin authorize tests for isolation

* docs(security): require a reproduction video for vulnerability reports (#30048) (#30063)

With AI models capable of automated vulnerability discovery now publicly
available, we expect a large increase in report volume, much of it
unverified. Requiring a video of the exploit running against a live
instance raises the bar for submissions and keeps triage focused on
reproducible issues. Reports without a video will be closed and reopened
if one is added later.

Co-authored-by: stuxf <[email protected]>

* feat(ui): add admin flag to disable in-product UI nudges for everyone (#29796)

* feat(ui): add admin flag to disable in-product UI nudges for everyone

Admins can now suppress the survey and Claude Code feedback popups for
all users via a single disable_ui_nudges UI setting, instead of relying
on each user dismissing them individually.

* fix(ui): suppress nudges while ui settings are loading

Gate nudgesDisabled on the ui-settings loading state so an admin with
disable_ui_nudges on doesn't see the survey prompt flash, and the
getInProductNudgesCall fetch doesn't fire, on a cold page load before
the flag resolves. Falls back to showing nudges if the fetch errors.

* test(ui): wrap CreateKeyPage test in QueryClientProvider

page.tsx now calls useUISettings (react-query), which needs a
QueryClient that layout.tsx supplies in production but the test did
not. Add the provider and mock getUiSettings so the query resolves.

* chore(ui): remove dead dashboard files and unused dependencies (#30047)

* chore(ui): remove dead dashboard files and unused dependencies

knip flagged seven orphaned source/config files with no importers and
five declared dependencies that nothing in the tree uses. Removing them
shrinks the dashboard bundle's source surface and keeps the manifest
honest; vite stays installed transitively via vitest, so test tooling is
unaffected.

* fix(ci): restore serverRootPath.config.ts referenced by SERVER_ROOT_PATH workflow

The dead-code sweep removed e2e_tests/serverRootPath.config.ts, but its spec
(tests/login/serverRootPathRedirect.spec.ts) and the test_server_root_path.yml
workflow step still depend on it, so the redirect e2e job failed to load a
config that no longer existed.

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593) (#30009)

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593)

After replace_model_in_jsonl, body.model is a stripped provider id. Reverse-mapping it via resolve_model_name_from_model_id is first-match on model_list and caused false 403s when multiple deployments share the same stripped name. Use target_model_names from the unified file id instead.

Co-authored-by: Cursor <[email protected]>

* fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)

Restores the reverse-lookup for the JSONL body.model fallback path so that
legacy/pre-target_model_names managed files still map stripped provider IDs
back to proxy aliases before auth. Also cleans up redundant `or None`.

Co-Authored-By: Claude Sonnet 4.6 <[email protected]>

* Revert "fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)"

This reverts commit 30d2e96f77ef521ccaaf2193fe554980380eb669.

---------

Co-authored-by: Cursor <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>

* Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI (#30064)

* Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI

Adds cost map entries for claude-fable-5 ($10/$50 per MTok, 1M context,
128K output, adaptive thinking only) on the Anthropic API, Bedrock
converse (base, global, and us/eu geo inference profiles at the 10%
regional premium), Vertex AI, and Azure AI (Microsoft Foundry, which
serves Fable 5 with the full 1M context window unlike Opus 4.8).

Registers anthropic.claude-fable-5 in BEDROCK_CONVERSE_MODELS, lists the
model in the setup wizard, and extends the reasoning effort e2e grid.
The Bedrock, Vertex, and Azure grid cells carry fail_reason markers
until the CI accounts are provisioned: Bedrock needs the provider data
sharing opt-in Fable 5 requires, and the Foundry resource needs a
claude-fable-5 deployment.

The first-party entry carries provider_specific_entry {us: 1.1} for the
inference_geo premium and deliberately no fast multiplier since Fable 5
has no fast mode.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Drop removed sampling params for Claude 4.7+ when drop_params is set

Fable 5, Opus 4.7, and Opus 4.8 removed sampling params: the API rejects
top_p, top_k, and any temperature other than 1 with a 400. LiteLLM was
forwarding them even with drop_params enabled because the Anthropic and
Bedrock converse transformations passed temperature/top_p through
unconditionally.

Mirror the GPT-5/o-series handling: temperature=1 still passes through,
other values and any top_p are dropped when drop_params is set, and
without drop_params a clean client-side UnsupportedParamsError tells the
caller how to opt in, instead of surfacing the raw provider error.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Drive sampling param gating from the cost map and cover top_k

Greptile review follow-ups on the sampling param fix: the restriction for
Fable 5 / Opus 4.7 / 4.8 is now declared as supports_sampling_params: false
on every affected cost map entry (perplexity excluded; that route is
OpenAI-compatible and maps sampling params upstream) and read back through
a tri-state map lookup, keeping the name check only as a fallback for
provider-routed ids whose hosted map entries predate the flag, the same
layering supports_adaptive_thinking uses. top_k bypasses map_openai_params
as a provider-specific kwarg, so it is gated at the shared
AnthropicConfig.transform_request boundary (direct, Bedrock invoke, Vertex,
Azure) and in the Bedrock converse _handle_top_k_value path, with
drop_params threaded through the converse transform helpers.

Also updates the reasoning effort grid cell count assertion for the four
Fable 5 rows added on this branch (29 x 11 cells).

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Declare supports_sampling_params in the cost map schema

The model map validation schema uses additionalProperties: false, so the
new flag must be declared for the 28 entries that carry it; this was the
one failing job (misc / Run tests) on the previous commit.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* fix(bedrock): gate top_k=0 on converse to match Anthropic boundary

Truthiness check let top_k=0 silently disappear on models that removed
sampling params, while AnthropicConfig.transform_request treats 0 as
present and raises UnsupportedParamsError (or drops when drop_params is
set). Switch to 'is not None' so converse, direct Anthropic, invoke,
Vertex, and Azure all behave the same for top_k=0.

---------

Co-authored-by: Cursor Agent <[email protected]>

* fix(anthropic): avoid index -1 content_block_delta in messages stream

When a /v1/messages request is routed through the Responses API
adapter, AnthropicResponsesStreamWrapper only emits content_block_start
on response.output_item.added. Some upstreams (LMStudio for example)
never send that event, so the text delta handler fell back to
_current_block_index, which starts at -1, and clients received
content_block_delta events with index -1 and no preceding
content_block_start. Anthropic SDKs then fail with "text part -1 not
found"

The text delta handler now synthesizes a content_block_start with a
fresh block index whenever the delta references an unregistered item_id
or no block is open yet, and registers the item_id so follow-up deltas
reuse the same index

Addresses the /v1/messages defect in #27442

* Make test sys.path shim resolve relative to the file, not the CWD

os.path.abspath("../../../../../../..") depends on where pytest is
invoked from; anchoring on os.path.dirname(__file__) makes the import
work from any working directory. Also corrects the depth: the repo root
is six levels above this file, not seven.

---------

Co-authored-by: milan-berri <[email protected]>
Co-authored-by: Cursor <[email protected]>
Co-authored-by: ryan-crabbe-berri <[email protected]>
Co-authored-by: michelligabriele <[email protected]>
Co-authored-by: tin-berri <[email protected]>
Co-authored-by: yuneng-jiang <[email protected]>
Co-authored-by: stuxf <[email protected]>
Co-authored-by: Sameer Kankute <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>
Co-authored-by: Mateo Wang <[email protected]>

* fix: enable compact-2026-01-12 beta header for vertex_ai provider (#30114)

* fix(team): reserve team budget raises for proxy admins on /team/update (#30030)

The caller's PERSONAL max_budget was the wrong yardstick for /team/update: a
team's spend ceiling has nothing to do with the admin's own key budget. That
comparison was an unintended side effect of reusing _check_user_team_limits()
(which exists for the /team/new path) and broke the UI, which re-sends the
unchanged budget on every save.

New behavior on /team/update for standalone teams:
- A team admin (already authorized via _verify_team_access) may freely KEEP or
  LOWER the team budget, and change models/tpm/rpm, without being gated by their
  personal limits.
- GROWING a team's spend ceiling is a budget-authority action reserved for proxy
  admins -> 403 for team admins. "Growing" covers both raising max_budget above
  the team's current finite value and removing the cap entirely (max_budget=null,
  detected via model_fields_set so an explicit null is distinguished from an
  omitted field). For a team that currently has no cap, setting a finite value is
  a restriction and is allowed.
- Org-scoped teams remain governed by _check_org_team_limits() (capped by the
  org budget).

Also reverts the #29525 existing_team_max_budget workaround in
_check_user_team_limits() back to the create-only form; /team/new still enforces
the creator's personal caps.

docs(access_control): resolve the contradiction in the team-admin section —
team admins can keep/lower the budget and manage rate limits/models, but cannot
raise the team budget (proxy-admin only).

tests: unit + behavior coverage for raise-blocked, cap-removal-blocked (team
admin), raise/removal allowed (proxy admin), uncapped-team restriction allowed,
keep/lower/resend allowed, and unchanged create-path guards.

Co-authored-by: Cursor <[email protected]>

* test(ui): data-driven App Router migration E2E smoke (default + server-root-path) (#29974)

* test(ui): add a data-driven App Router migration E2E smoke

Add a growing Playwright smoke for migrated pages: for each segment it deep-links
to the path route, asserts the URL and that the dashboard shell rendered, then
clicks off to a legacy page and asserts navigation still works. Driven by
e2e_tests/fixtures/migratedPages.ts, so adding a page is one line.

Runs in two situations against the same proxy: the default mount (npm run
e2e:migration) and a non-root SERVER_ROOT_PATH mount (npm run e2e:migration:root).
globalSetup now logs in at `${SERVER_ROOT_PATH}/ui/login` so the admin storage
state is valid under a prefix. Seeded with api-reference; append the rest as their
migrations merge.

* test(ui): support headed slow-motion + watch pauses in the migration smoke

Honor SLOWMO in the server-root-path config (the default config already did),
and add an env-gated E2E_WATCH_MS pause so a headed run lingers on each state.
Both are no-ops by default, so CI behavior is unchanged.

* test(ui): make the migration smoke a sidebar-click user journey

Rework the smoke from deep-linking to a real navigation journey: start at the
landing page, click the migrated page in the sidebar (expanding submenus for
nested items), assert the path route rendered, reload it (the check a wrong
server_root_path breaks), bounce to a legacy page and back, and — once two pages
are migrated — navigate directly between two migrated pages. Verifies via URL +
shell render, driven by the same fixture list.

* test(ui): address review on the migration smoke

Escape ROOT and segment before interpolating them into RegExp URL matchers so a
future segment containing regex metacharacters can't silently widen the match.
Make the server-root-path config fail fast when SERVER_ROOT_PATH is unset instead
of silently re-running the default mount and passing without exercising the prefix.

* test(ui): drop unused watch helper and fix stale smoke README

* test(ui): run the migration smoke under a server root path in CI

* test(ui): harden + instrument the server-root-path proxy reboot in CI

* test(ui): run the server-root-path migration smoke as its own CI job

Replace the in-place proxy reboot in e2e_ui_testing with a dedicated
e2e_ui_testing_server_root_path job that boots the proxy once with
SERVER_ROOT_PATH=/litellm, matching how every other proxy variant in the
config gets its own job rather than killing and relaunching the live proxy.

The reboot was failing deterministically: after pkill -9 and relaunch the
prefixed proxy never came back up on :4000 (connection refused), so the smoke
never ran. The readiness step that was supposed to surface the cause could
never reach its boot-log tail because CircleCI runs steps under bash -eo
pipefail and the preceding `curl -sv ... | tail` aborted the step with curl's
exit 7. Booting the proxy as the job's own background step lets any boot crash
land in that step's log instead of being swallowed.

The default e2e_ui_testing job is unchanged aside from dropping the reboot,
prefixed-readiness, and prefixed-smoke steps; the migration smoke still runs at
the root mount there via the default Playwright config.

* fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through (#24232)

* fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through

* test: mock post_call_response_headers_hook in audio speech route tests

* chore(ui): remove dead App Router route stubs under (dashboard) (#30045)

models-and-endpoints, organizations, and virtual-keys each had a page.tsx
route under (dashboard)/ that is not in MIGRATED_PAGES, so the sidebar and
deep links never resolve to it and the route is unreachable. Each was a thin
wrapper that handed the shared view empty or no-op props (empty modelData with
a no-op setModelData, hardcoded empty organizations, no-op
setUserRole/setUserEmail), so reaching one would render a degraded page in any
case. The real wrapper belongs in the PR that flips each page into
MIGRATED_PAGES, written with eyes on it and a test

This continues the dead-scaffolding cleanup from #28891. The shared components
these wrappers rendered (ModelsAndEndpointsView, OrganizationFilters) stay,
since the legacy ?page= switch in app/page.tsx and src/components still import
them

* fix(ui/mcp): reset OAuth state on create-server modal close so a prior server's token no longer leaks into the next add-server session (#30000)

* fix(ui/mcp): reset OAuth hook state on modal close so a prior server's token no longer leaks into the next add-server session

* fix(ui/mcp): clear in-flight OAuth guard on reset and reset form/tools on modal close so nothing leaks on a parent-driven dismiss

* fix(mcp): allow team access-group grants in OAuth authorize/token access check (#30041)

* fix(mcp): honor team access-group grants in OAuth authorize/token access check

* test(mcp): mock build_effective_auth_contexts in non-admin authorize tests for isolation

* docs(security): require a reproduction video for vulnerability reports (#30048) (#30063)

With AI models capable of automated vulnerability discovery now publicly
available, we expect a large increase in report volume, much of it
unverified. Requiring a video of the exploit running against a live
instance raises the bar for submissions and keeps triage focused on
reproducible issues. Reports without a video will be closed and reopened
if one is added later.

Co-authored-by: stuxf <[email protected]>

* feat(ui): add admin flag to disable in-product UI nudges for everyone (#29796)

* feat(ui): add admin flag to disable in-product UI nudges for everyone

Admins can now suppress the survey and Claude Code feedback popups for
all users via a single disable_ui_nudges UI setting, instead of relying
on each user dismissing them individually.

* fix(ui): suppress nudges while ui settings are loading

Gate nudgesDisabled on the ui-settings loading state so an admin with
disable_ui_nudges on doesn't see the survey prompt flash, and the
getInProductNudgesCall fetch doesn't fire, on a cold page load before
the flag resolves. Falls back to showing nudges if the fetch errors.

* test(ui): wrap CreateKeyPage test in QueryClientProvider

page.tsx now calls useUISettings (react-query), which needs a
QueryClient that layout.tsx supplies in production but the test did
not. Add the provider and mock getUiSettings so the query resolves.

* chore(ui): remove dead dashboard files and unused dependencies (#30047)

* chore(ui): remove dead dashboard files and unused dependencies

knip flagged seven orphaned source/config files with no importers and
five declared dependencies that nothing in the tree uses. Removing them
shrinks the dashboard bundle's source surface and keeps the manifest
honest; vite stays installed transitively via vitest, so test tooling is
unaffected.

* fix(ci): restore serverRootPath.config.ts referenced by SERVER_ROOT_PATH workflow

The dead-code sweep removed e2e_tests/serverRootPath.config.ts, but its spec
(tests/login/serverRootPathRedirect.spec.ts) and the test_server_root_path.yml
workflow step still depend on it, so the redirect e2e job failed to load a
config that no longer existed.

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593) (#30009)

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593)

After replace_model_in_jsonl, body.model is a stripped provider id. Reverse-mapping it via resolve_model_name_from_model_id is first-match on model_list and caused false 403s when multiple deployments share the same stripped name. Use target_model_names from the unified file id instead.

Co-authored-by: Cursor <[email protected]>

* fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)

Restores the reverse-lookup for the JSONL body.model fallback path so that
legacy/pre-target_model_names managed files still map stripped provider IDs
back to proxy aliases before auth. Also cleans up redundant `or None`.

Co-Authored-By: Claude Sonnet 4.6 <[email protected]>

* Revert "fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)"

This reverts commit 30d2e96f77ef521ccaaf2193fe554980380eb669.

---------

Co-authored-by: Cursor <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>

* Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI (#30064)

* Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI

Adds cost map entries for claude-fable-5 ($10/$50 per MTok, 1M context,
128K output, adaptive thinking only) on the Anthropic API, Bedrock
converse (base, global, and us/eu geo inference profiles at the 10%
regional premium), Vertex AI, and Azure AI (Microsoft Foundry, which
serves Fable 5 with the full 1M context window unlike Opus 4.8).

Registers anthropic.claude-fable-5 in BEDROCK_CONVERSE_MODELS, lists the
model in the setup wizard, and extends the reasoning effort e2e grid.
The Bedrock, Vertex, and Azure grid cells carry fail_reason markers
until the CI accounts are provisioned: Bedrock needs the provider data
sharing opt-in Fable 5 requires, and the Foundry resource needs a
claude-fable-5 deployment.

The first-party entry carries provider_specific_entry {us: 1.1} for the
inference_geo premium and deliberately no fast multiplier since Fable 5
has no fast mode.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Drop removed sampling params for Claude 4.7+ when drop_params is set

Fable 5, Opus 4.7, and Opus 4.8 removed sampling params: the API rejects
top_p, top_k, and any temperature other than 1 with a 400. LiteLLM was
forwarding them even with drop_params enabled because the Anthropic and
Bedrock converse transformations passed temperature/top_p through
unconditionally.

Mirror the GPT-5/o-series handling: temperature=1 still passes through,
other values and any top_p are dropped when drop_params is set, and
without drop_params a clean client-side UnsupportedParamsError tells the
caller how to opt in, instead of surfacing the raw provider error.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Drive sampling param gating from the cost map and cover top_k

Greptile review follow-ups on the sampling param fix: the restriction for
Fable 5 / Opus 4.7 / 4.8 is now declared as supports_sampling_params: false
on every affected cost map entry (perplexity excluded; that route is
OpenAI-compatible and maps sampling params upstream) and read back through
a tri-state map lookup, keeping the name check only as a fallback for
provider-routed ids whose hosted map entries predate the flag, the same
layering supports_adaptive_thinking uses. top_k bypasses map_openai_params
as a provider-specific kwarg, so it is gated at the shared
AnthropicConfig.transform_request boundary (direct, Bedrock invoke, Vertex,
Azure) and in the Bedrock converse _handle_top_k_value path, with
drop_params threaded through the converse transform helpers.

Also updates the reasoning effort grid cell count assertion for the four
Fable 5 rows added on this branch (29 x 11 cells).

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Declare supports_sampling_params in the cost map schema

The model map validation schema uses additionalProperties: false, so the
new flag must be declared for the 28 entries that carry it; this was the
one failing job (misc / Run tests) on the previous commit.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* fix(bedrock): gate top_k=0 on converse to match Anthropic boundary

Truthiness check let top_k=0 silently disappear on models that removed
sampling params, while AnthropicConfig.transform_request treats 0 as
present and raises UnsupportedParamsError (or drops when drop_params is
set). Switch to 'is not None' so converse, direct Anthropic, invoke,
Vertex, and Azure all behave the same for top_k=0.

---------

Co-authored-by: Cursor Agent <[email protected]>

* fix: enable compact-2026-01-12 beta header for vertex_ai provider

The vertex_ai block in anthropic_beta_headers_config.json mapped
compact-2026-01-12 to null, so update_headers_with_filtered_beta
stripped the header before the request reached Vertex while the
compact_20260112 context edit stayed in the body, and Vertex rejected
the request with HTTP 400. Vertex rawPredict accepts the header, and
the bedrock and databricks blocks already forward it. Mirrors #21867,
which enabled context-1m-2025-08-07 for vertex_ai the same way.

Fixes #27290.

---------

Co-authored-by: milan-berri <[email protected]>
Co-authored-by: Cursor <[email protected]>
Co-authored-by: ryan-crabbe-berri <[email protected]>
Co-authored-by: michelligabriele <[email protected]>
Co-authored-by: tin-berri <[email protected]>
Co-authored-by: yuneng-jiang <[email protected]>
Co-authored-by: stuxf <[email protected]>
Co-authored-by: Sameer Kankute <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>
Co-authored-by: Mateo Wang <[email protected]>

* fix(proxy): coerce litellm_settings.max_budget env var to float (#30113)

* fix(team): reserve team budget raises for proxy admins on /team/update (#30030)

The caller's PERSONAL max_budget was the wrong yardstick for /team/update: a
team's spend ceiling has nothing to do with the admin's own key budget. That
comparison was an unintended side effect of reusing _check_user_team_limits()
(which exists for the /team/new path) and broke the UI, which re-sends the
unchanged budget on every save.

New behavior on /team/update for standalone teams:
- A team admin (already authorized via _verify_team_access) may freely KEEP or
  LOWER the team budget, and change models/tpm/rpm, without being gated by their
  personal limits.
- GROWING a team's spend ceiling is a budget-authority action reserved for proxy
  admins -> 403 for team admins. "Growing" covers both raising max_budget above
  the team's current finite value and removing the cap entirely (max_budget=null,
  detected via model_fields_set so an explicit null is distinguished from an
  omitted field). For a team that currently has no cap, setting a finite value is
  a restriction and is allowed.
- Org-scoped teams remain governed by _check_org_team_limits() (capped by the
  org budget).

Also reverts the #29525 existing_team_max_budget workaround in
_check_user_team_limits() back to the create-only form; /team/new still enforces
the creator's personal caps.

docs(access_control): resolve the contradiction in the team-admin section —
team admins can keep/lower the budget and manage rate limits/models, but cannot
raise the team budget (proxy-admin only).

tests: unit + behavior coverage for raise-blocked, cap-removal-blocked (team
admin), raise/removal allowed (proxy admin), uncapped-team restriction allowed,
keep/lower/resend allowed, and unchanged create-path guards.

Co-authored-by: Cursor <[email protected]>

* test(ui): data-driven App Router migration E2E smoke (default + server-root-path) (#29974)

* test(ui): add a data-driven App Router migration E2E smoke

Add a growing Playwright smoke for migrated pages: for each segment it deep-links
to the path route, asserts the URL and that the dashboard shell rendered, then
clicks off to a legacy page and asserts navigation still works. Driven by
e2e_tests/fixtures/migratedPages.ts, so adding a page is one line.

Runs in two situations against the same proxy: the default mount (npm run
e2e:migration) and a non-root SERVER_ROOT_PATH mount (npm run e2e:migration:root).
globalSetup now logs in at `${SERVER_ROOT_PATH}/ui/login` so the admin storage
state is valid under a prefix. Seeded with api-reference; append the rest as their
migrations merge.

* test(ui): support headed slow-motion + watch pauses in the migration smoke

Honor SLOWMO in the server-root-path config (the default config already did),
and add an env-gated E2E_WATCH_MS pause so a headed run lingers on each state.
Both are no-ops by default, so CI behavior is unchanged.

* test(ui): make the migration smoke a sidebar-click user journey

Rework the smoke from deep-linking to a real navigation journey: start at the
landing page, click the migrated page in the sidebar (expanding submenus for
nested items), assert the path route rendered, reload it (the check a wrong
server_root_path breaks), bounce to a legacy page and back, and — once two pages
are migrated — navigate directly between two migrated pages. Verifies via URL +
shell render, driven by the same fixture list.

* test(ui): address review on the migration smoke

Escape ROOT and segment before interpolating them into RegExp URL matchers so a
future segment containing regex metacharacters can't silently widen the match.
Make the server-root-path config fail fast when SERVER_ROOT_PATH is unset instead
of silently re-running the default mount and passing without exercising the prefix.

* test(ui): drop unused watch helper and fix stale smoke README

* test(ui): run the migration smoke under a server root path in CI

* test(ui): harden + instrument the server-root-path proxy reboot in CI

* test(ui): run the server-root-path migration smoke as its own CI job

Replace the in-place proxy reboot in e2e_ui_testing with a dedicated
e2e_ui_testing_server_root_path job that boots the proxy once with
SERVER_ROOT_PATH=/litellm, matching how every other proxy variant in the
config gets its own job rather than killing and relaunching the live proxy.

The reboot was failing deterministically: after pkill -9 and relaunch the
prefixed proxy never came back up on :4000 (connection refused), so the smoke
never ran. The readiness step that was supposed to surface the cause could
never reach its boot-log tail because CircleCI runs steps under bash -eo
pipefail and the preceding `curl -sv ... | tail` aborted the step with curl's
exit 7. Booting the proxy as the job's own background step lets any boot crash
land in that step's log instead of being swallowed.

The default e2e_ui_testing job is unchanged aside from dropping the reboot,
prefixed-readiness, and prefixed-smoke steps; the migration smoke still runs at
the root mount there via the default Playwright config.

* fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through (#24232)

* fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through

* test: mock post_call_response_headers_hook in audio speech route tests

* chore(ui): remove dead App Router route stubs under (dashboard) (#30045)

models-and-endpoints, organizations, and virtual-keys each had a page.tsx
route under (dashboard)/ that is not in MIGRATED_PAGES, so the sidebar and
deep links never resolve to it and the route is unreachable. Each was a thin
wrapper that handed the shared view empty or no-op props (empty modelData with
a no-op setModelData, hardcoded empty organizations, no-op
setUserRole/setUserEmail), so reaching one would render a degraded page in any
case. The real wrapper belongs in the PR that flips each page into
MIGRATED_PAGES, written with eyes on it and a test

This continues the dead-scaffolding cleanup from #28891. The shared components
these wrappers rendered (ModelsAndEndpointsView, OrganizationFilters) stay,
since the legacy ?page= switch in app/page.tsx and src/components still import
them

* fix(ui/mcp): reset OAuth state on create-server modal close so a prior server's token no longer leaks into the next add-server session (#30000)

* fix(ui/mcp): reset OAuth hook state on modal close so a prior server's token no longer leaks into the next add-server session

* fix(ui/mcp): clear in-flight OAuth guard on reset and reset form/tools on modal close so nothing leaks on a parent-driven dismiss

* fix(mcp): allow team access-group grants in OAuth authorize/token access check (#30041)

* fix(mcp): honor team access-group grants in OAuth authorize/token access check

* test(mcp): mock build_effective_auth_contexts in non-admin authorize tests for isolation

* docs(security): require a reproduction video for vulnerability reports (#30048) (#30063)

With AI models capable of automated vulnerability discovery now publicly
available, we expect a large increase in report volume, much of it
unverified. Requiring a video of the exploit running against a live
instance raises the bar for submissions and keeps triage focused on
reproducible issues. Reports without a video will be closed and reopened
if one is added later.

Co-authored-by: stuxf <[email protected]>

* feat(ui): add admin flag to disable in-product UI nudges for everyone (#29796)

* feat(ui): add admin flag to disable in-product UI nudges for everyone

Admins can now suppress the survey and Claude Code feedback popups for
all users via a single disable_ui_nudges UI setting, instead of relying
on each user dismissing them individually.

* fix(ui): suppress nudges while ui settings are loading

Gate nudgesDisabled on the ui-settings loading state so an admin with
disable_ui_nudges on doesn't see the survey prompt flash, and the
getInProductNudgesCall fetch doesn't fire, on a cold page load before
the flag resolves. Falls back to showing nudges if the fetch errors.

* test(ui): wrap CreateKeyPage test in QueryClientProvider

page.tsx now calls useUISettings (react-query), which needs a
QueryClient that layout.tsx supplies in production but the test did
not. Add the provider and mock getUiSettings so the query resolves.

* chore(ui): remove dead dashboard files and unused dependencies (#30047)

* chore(ui): remove dead dashboard files and unused dependencies

knip flagged seven orphaned source/config files with no importers and
five declared dependencies that nothing in the tree uses. Removing them
shrinks the dashboard bundle's source surface and keeps the manifest
honest; vite stays installed transitively via vitest, so test tooling is
unaffected.

* fix(ci): restore serverRootPath.config.ts referenced by SERVER_ROOT_PATH workflow

The dead-code sweep removed e2e_tests/serverRootPath.config.ts, but its spec
(tests/login/serverRootPathRedirect.spec.ts) and the test_server_root_path.yml
workflow step still depend on it, so the redirect e2e job failed to load a
config that no longer existed.

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593) (#30009)

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593)

After replace_model_in_jsonl, body.model is a stripped provider id. Reverse-mapping it via resolve_model_name_from_model_id is first-match on model_list and caused false 403s when multiple deployments share the same stripped name. Use target_model_names from the unified file id instead.

Co-authored-by: Cursor <[email protected]>

* fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)

Restores the reverse-lookup for the JSONL body.model fallback path so that
legacy/pre-target_model_names managed files still map stripped provider IDs
back to proxy aliases before auth. Also cleans up redundant `or None`.

Co-Authored-By: Claude Sonnet 4.6 <[email protected]>

* Revert "fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)"

This reverts commit 30d2e96f77ef521ccaaf2193fe554980380eb669.

---------

Co-authored-by: Cursor <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>

* Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI (#30064)

* Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI

Adds cost map entries for claude-fable-5 ($10/$50 per MTok, 1M context,
128K output, adaptive thinking only) on the Anthropic API, Bedrock
converse (base, global, and us/eu geo inference profiles at the 10%
regional premium), Vertex AI, and Azure AI (Microsoft Foundry, which
serves Fable 5 with the full 1M context window unlike Opus 4.8).

Registers anthropic.claude-fable-5 in BEDROCK_CONVERSE_MODELS, lists the
model in the setup wizard, and extends the reasoning effort e2e grid.
The Bedrock, Vertex, and Azure grid cells carry fail_reason markers
until the CI accounts are provisioned: Bedrock needs the provider data
sharing opt-in Fable 5 requires, and the Foundry resource needs a
claude-fable-5 deployment.

The first-party entry carries provider_specific_entry {us: 1.1} for the
inference_geo premium and deliberately no fast multiplier since Fable 5
has no fast mode.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Drop removed sampling params for Claude 4.7+ when drop_params is set

Fable 5, Opus 4.7, and Opus 4.8 removed sampling params: the API rejects
top_p, top_k, and any temperature other than 1 with a 400. LiteLLM was
forwarding them even with drop_params enabled because the Anthropic and
Bedrock converse transformations passed temperature/top_p through
unconditionally.

Mirror the GPT-5/o-series handling: temperature=1 still passes through,
other values and any top_p are dropped when drop_params is set, and
without drop_params a clean client-side UnsupportedParamsError tells the
caller how to opt in, instead of surfacing the raw provider error.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Drive sampling param gating from the cost map and cover top_k

Greptile review follow-ups on the sampling param fix: the restriction for
Fable 5 / Opus 4.7 / 4.8 is now declared as supports_sampling_params: false
on every affected cost map entry (perplexity excluded; that route is
OpenAI-compatible and maps sampling params upstream) and read back through
a tri-state map lookup, keeping the name check only as a fallback for
provider-routed ids whose hosted map entries predate the flag, the same
layering supports_adaptive_thinking uses. top_k bypasses map_openai_params
as a provider-specific kwarg, so it is gated at the shared
AnthropicConfig.transform_request boundary (direct, Bedrock invoke, Vertex,
Azure) and in the Bedrock converse _handle_top_k_value path, with
drop_params threaded through the converse transform helpers.

Also updates the reasoning effort grid cell count assertion for the four
Fable 5 rows added on this branch (29 x 11 cells).

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Declare supports_sampling_params in the cost map schema

The model map validation schema uses additionalProperties: false, so the
new flag must be declared for the 28 entries that carry it; this was the
one failing job (misc / Run tests) on the previous commit.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* fix(bedrock): gate top_k=0 on converse to match Anthropic boundary

Truthiness check let top_k=0 silently disappear on models that removed
sampling params, while AnthropicConfig.transform_request treats 0 as
present and raises UnsupportedParamsError (or drops when drop_params is
set). Switch to 'is not None' so converse, direct Anthropic, invoke,
Vertex, and Azure all behave the same for top_k=0.

---------

Co-authored-by: Cursor Agent <[email protected]>

* fix(proxy): coerce litellm_settings.max_budget env var to float

When max_budget is set in litellm_settings via os.environ/MAX_BUDGET,
the env var resolves to a string and the generic setattr branch in
ProxyConfig.load_config stored it as-is, so the startup check
litellm.max_budget > 0 raised TypeError. The earlier fix (#23855) only
covered the CLI initialize() path. Coerce the value to float in the
settings loop, matching the existing max_internal_user_budget handling.

Fixes #26696.

---------

Co-authored-by: milan-berri <[email protected]>
Co-authored-by: Cursor <[email protected]>
Co-authored-by: ryan-crabbe-berri <[email protected]>
Co-authored-by: michelligabriele <[email protected]>
Co-authored-by: tin-berri <[email protected]>
Co-authored-by: yuneng-jiang <[email protected]>
Co-authored-by: stuxf <[email protected]>
Co-authored-by: Sameer Kankute <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>
Co-authored-by: Mateo Wang <[email protected]>

* fix(router): don't drop bedrock pass-through deployments using IAM credentials (#30111)

* Fix Bedrock passthrough deployment dropped when using IAM credentials

Bedrock deployments with use_in_pass_through enabled and IAM/OIDC auth
(aws_role_name, no api_key) hit the generic pass-through branch in
Router._initialize_deployment_for_pass_through, which calls
set_pass_through_credentials and raises "api_key is required". The
exception drops the deployment from the router entirely, breaking both
passthrough and normal routing for that model.

Skip the credential store write when no api_key is set; the bedrock
passthrough route resolves AWS credentials at request time via
BedrockConverseLLM.get_credentials(), not the passthrough credential
store, so there is nothing to register here.

Fixes #27728.

* Reset passthrough credentials singleton before api_key credential test

The test reads the module-level passthrough_endpoint_router singleton,
so a stale "openai" entry written by an earlier test in the same
process could make the assertion pass without exercising the code path.
Clearing the credentials dict up front makes the test order-independent.

* fix(sdk): stop mirroring reasoning_content in provider_specific_fields (#30110)

The dict-to-response conversion path mirrored reasoning_content into
provider_specific_fields, while live provider transforms (Anthropic's
_build_provider_specific_fields) only set it top-level on the Message.
Cache-replayed messages therefore serialized differently from live
ones, breaking disk cache key stability for multi-turn conversations
with extended thinking.

The mirror was added for DeepSeek before Message.reasoning_content
existed as a top-level attribute. The top-level field is still set by
the converter, so DeepSeek's request-side promotion is unaffected.

Fixes #27337.

* fix(mcp): coerce mcp_server_cost_info values to float at ingest (#30109)

* fix(mcp): coerce mcp_server_cost_info values to float at ingest

YAML 1.1 parses scientific notation without a decimal point
(e.g. 7e-05) as a string, and MCPServerCostInfo is a TypedDict with no
runtime validation, so a string-typed default_cost_per_query from
config.yaml flowed through the proxy untouched and crashed the MCP
server settings page with '.toFixed is not a function'. Normalize
mcp_server_cost_info on both the config and DB load paths, dropping
non-numeric values with a warning instead of failing the server load.

Fixes #27097.

* fix(mcp): drop non-numeric default_cost_per_query instead of nulling it

Keeping the key with a None value still exposes a null to the UI,
which can crash .toFixed formatting when the consumer checks key
existence rather than truthiness. Delete the key on coercion failure,
matching how non-numeric per-tool cost entries are already omitted.

* fix(proxy): count embedding and text completion tokens toward TPM limits (#30105)

* fix(proxy): count embedding and text completion tokens toward TPM limits

The parallel request limiters only read token usage off ModelResponse,
so EmbeddingResponse and TextCompletionResponse objects left
total_tokens at 0 and the per key, user, team, and end user TPM
counters never incremented. Requests to /v1/embeddings and
/v1/completions were effectively free against any tpm_limit. In the v3
limiter this was worse: the post-call reconciliation computed actual
usage as 0 and refunded the pre-call reservation made at request time.

Broaden the isinstance checks to accept EmbeddingResponse and
TextCompletionResponse, which both expose a Usage object, at the four
per-scope sites in parallel_request_limiter.py and at the usage
extraction in parallel_request_limiter_v3.py. ResponsesAPIResponse was
already covered in v3 via BaseLiteLLMOpenAIResponseObject.

Fixes #27738.

* test(proxy): cover v1 limiter TPM counting for embedding and text completion responses

Exercise the broadened isinstance sites in parallel_request_limiter.py
by asserting that async_log_success_event adds total_tokens to the per
key, user, team, and end user TPM counters for EmbeddingResponse and
TextCompletionResponse objects. The counters are pre-seeded at zero so
the assertion is exactly the increment; on the pre-fix code these
responses left total_tokens at 0 and the test fails.

* fix(openai): forward client headers on the text completion path (#30103)

* fix(openai): forward client headers on the text completion path

litellm.completion() merges caller headers with extra_headers, but the
text-completion-openai branch never passed the merged dict to
openai_text_completions.completion(), and the handler only used its
headers argument for logging. Pass the merged headers through the call
site and set them as extra_headers on the outgoing request, mirroring
the chat completion handler, so x-* client headers forwarded by the
proxy reach the provider on /v1/completions.

Fixes #27410.

* Drop redundant extra_headers assignment and fix test module collision

completion() merges extra_headers into headers before the
text-completion-openai branch, and the handler now sets the merged
headers as extra_headers on the request, so the branch-local
optional_params["extra_headers"] assignment was a dead duplicate.
Removing it keeps the assignment in one place while both entry paths
(litellm.text_completion and direct handler callers) still forward
headers; a new regression test pins the extra_headers kwarg path.

Also rename the test module to test_completion_handler.py since its
basename collided with tests/test_litellm/llms/bedrock/batches/
test_handler.py and broke pytest collection.

* fix(bedrock): route Anthropic-shape count_tokens to InvokeModel and base64-encode the body (#30102)

* fix(bedrock): route Anthropic-shape count_tokens to InvokeModel

POST /v1/messages/count_tokens with Anthropic content blocks
({"type": "text"|"tool_use"|...}) was routed to the Converse input of
the Bedrock CountTokens API. The Converse transform copies list content
through verbatim, so Bedrock rejected the request with a 400 and the
caller silently fell back to the local tokenizer, returning counts that
can be off by ~50% on tool-heavy payloads.

_detect_input_type now routes messages whose content blocks carry a
"type" key (Anthropic shape) to the invokeModel input, which forwards
the body verbatim. The invokeModel body is now base64-encoded as the
CountTokens API requires (InvokeModelTokensRequest.body is a
base64-encoded blob), and Anthropic Messages bodies get the
anthropic_version and max_tokens fields Bedrock validates against.

Fixes #27632.

* refactor(bedrock): name the CountTokens max_tokens placeholder

Replace the magic 1024 with a module-level
DEFAULT_ANTHROPIC_INVOKE_MODEL_MAX_TOKENS constant so the intent is
explicit and t…

…T-3593) (BerriAI#30009)

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593)

After replace_model_in_jsonl, body.model is a stripped provider id. Reverse-mapping it via resolve_model_name_from_model_id is first-match on model_list and caused false 403s when multiple deployments share the same stripped name. Use target_model_names from the unified file id instead.

Co-authored-by: Cursor <[email protected]>

* fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)

Restores the reverse-lookup for the JSONL body.model fallback path so that
legacy/pre-target_model_names managed files still map stripped provider IDs
back to proxy aliases before auth. Also cleans up redundant `or None`.

Co-Authored-By: Claude Sonnet 4.6 <[email protected]>

* Revert "fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)"

This reverts commit 30d2e96.

---------

Co-authored-by: Cursor <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>

* fix(mcp): report scoped server name during initialize (#29865)

* fix mcp scoped server name

* Update litellm/proxy/_experimental/mcp_server/mcp_context.py

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* test(mcp): cover scoped server name in the SSE initialize handler

---------

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* fix(ui): show all session logs in the drawer, not just the first 50 (#29795)

* fix(ui): show newest session logs first

* test(ui): keep session log pagination coverage

* fix(ui): show all session logs in the drawer, not just the first page

The session detail drawer fetched session logs via sessionSpendLogsCall
without page/page_size, so it only ever received the backend default of one
page (50 rows). Sessions with more than 50 calls had the rest unreachable in
the UI (#29153).

sessionSpendLogsCall now takes page/page_size, and the drawer fetches the
first page, reads total_pages, then fetches the remaining pages and
accumulates them before the existing client-side sort. This keeps the single
continuous list (and the selected-log lookup and keyboard navigation, which
all assume the full session) correct. Fetching is bounded by a page cap, and
the sidebar shows a "showing most recent N" note if a session exceeds it.

The rows are lightweight metadata (the endpoint excludes messages/response),
so the full set is small; request/response bodies are still loaded per log on
demand.

* fix(ui): default session drawer to most recent log, newest first

Open a session with its most recent log selected, and order the sidebar
newest-first to match the all-sessions logs overview. MCP calls stay
grouped last. The latest log by time is computed explicitly, since the
MCP grouping means it is not always the first row.

* Apply fetching pages in batches suggestion from @greptile-apps[bot]

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* fix(ui): derive session total from accumulated rows when backend omits it

Compute the session total after all pages are fetched, falling back to the
accumulated row count rather than the first page's. Guards the truncation
note against a backend response that omits total but spans multiple pages.

---------

Co-authored-by: Yufeng He <[email protected]>
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* fix(proxy): handle Mistral multipart passthrough (#29927)

* fix(proxy): handle Mistral multipart passthrough

* chore: satisfy passthrough ci formatting

* test(proxy): cover Mistral passthrough in CI shard

* fix(vertex_ai): use REP host for context caching on eu/us multi-region endpoints (#29573)

Context caching built the cachedContents URL as
https://{location}-aiplatform.googleapis.com, which is an invalid host for the
eu/us multi-region endpoints and returns 404. The inference path already
resolves these to the REP host (https://aiplatform.{geo}.rep.googleapis.com)
via get_vertex_base_url(); reuse that helper in
_get_token_and_url_context_caching so caching uses the same host as inference.

Adds tests covering the eu/us multi-region cachedContents URLs (v1 and
v1beta1).

Fixes #29571

* Support per-model encrypted content affinity config (#29760)

Co-authored-by: shin-berri <[email protected]>
Co-authored-by: yuneng-jiang <[email protected]>

* fix: propagate upstream status code in proxy API exception handler (#29402)

* fix: propagate upstream status code in proxy API exception handler

When Google GenAI / Vertex returns a 404 for deprecated or missing
models via streamGenerateContent, the exception was falling through to
a generic handler that defaulted to 500. Now provider exceptions
carrying a valid HTTP status_code correctly propagate it through to
the ProxyException.

* fix: apply black formatting to common_request_processing.py

* fix: tighten status code range to 400-599 and deduplicate ProxyException raise

* fix(tests): use valid vertex_location in context caching tests

Replace "test_location" (contains underscore) with "us-central1" so tests
pass the regex validation added in get_vertex_base_url().

Co-Authored-By: Claude Sonnet 4.6 <[email protected]>

* feat(sdk): add xAI OAuth provider (#29866)

* Add xAI OAuth provider

* Update oauth.py

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* Fix xAI OAuth CI failures

* Add xAI OAuth coverage tests

* Move xAI OAuth coverage tests to core utils

* Address xAI OAuth review comments

* Prevent xAI OAuth api_base token exfiltration

* Treat blank xAI OAuth api keys as absent

* Wrap invalid xAI OAuth JSON responses

* Use xAI OAuth behind explicit flag

---------

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* fix(proxy) #27734 allow clearing budget_duration and team_member fields by sending null on /key/update and /team/update (#27751)

* fix(proxy): allow clearing budget_duration and team_member fields by sending null on /key/update and /team/update

Fixes #27734

Sending null for budget_duration, team_member_budget,
team_member_budget_duration, team_member_rpm_limit, or
team_member_tpm_limit via /key/update or /team/update returned 200 OK
but silently ignored the null value. The fields remained unchanged in
the database.

Root causes:
- /key/update: prepare_key_update_data() popped budget_duration from the
  update dict but never re-added it (or budget_reset_at) when the value
  was None.
- /team/update: _set_budget_reset_at() only acted when budget_duration
  was non-None, leaving a stale budget_reset_at in the DB.
- /team/update: team_member_* null values bypassed the budget table
  update entirely because should_create_budget() requires at least one
  non-None field.

* test(proxy): cover no-budget-row path in clear_team_member_budget_fields

* fix(presidio): unmask PII tokens in Anthropic native SSE streaming bytes (#30028)

* fix(presidio): unmask PII tokens in Anthropic native SSE streaming bytes

When output_parse_pii=true on the Anthropic native path (anthropic/claude-*),
response chunks arrive as raw bytes in SSE format. _stream_pii_unmasking was
yielding those bytes unchanged, so <PERSON_1> tokens were never replaced with
the original values before reaching the caller.

Add _unmask_sse_bytes_chunk to parse each data: line, find content_block_delta
/ text_delta events, and apply _unmask_pii_text before re-encoding. Wire it
into _stream_pii_unmasking so bytes chunks are unmasked when pii_tokens exist.

* fix(presidio): handle CRLF line endings and non-ASCII PII in SSE unmask

Strip trailing \r before the [DONE] guard so CRLF-terminated SSE chunks
don't bypass it and silently swallow a JSONDecodeError. Add
ensure_ascii=False to json.dumps so non-ASCII replacement values like
accented names are preserved as UTF-8 on the wire rather than being
\uXXXX-escaped. Add regression tests for both cases.

* feat(bedrock_mantle): path-aware Responses routing (/v1/responses vs /openai/v1/responses) (#29925)

* feat(bedrock_mantle): path-aware Responses routing (/v1/responses vs /openai/v1/responses)

Bedrock Mantle serves the Responses API on two upstream paths:
  - gpt frontier models (gpt-5.5 / gpt-5.4) on /openai/v1/responses
  - every other Responses-capable model (e.g. gpt-oss) on the standard /v1/responses

BedrockMantleResponsesAPIConfig gains a `use_openai_path` flag; the provider gate in
utils.py picks the path per model: openai.gpt-* (non gpt-oss) -> /openai/v1/responses;
any model declared mode=responses (price-map entry or user model_info) -> /v1/responses;
everything else returns None and keeps the existing chat-completions emulation.

Adds gpt-5.5 / gpt-5.4 price-map entries, registry wiring, and the routing-matrix tests.

* feat(bedrock_mantle): data-driven frontier routing via use_openai_responses_path

Addresses the Greptile review point that frontier detection should be a
price-map field rather than a hardcoded name match. The gate now routes a
model to /openai/v1/responses when its price-map entry declares
use_openai_responses_path, so a frontier model whose name does not follow the
openai.gpt- convention can be onboarded by JSON alone. The name-convention
check is kept as a fallback that needs no price-map entry, which preserves
zero-change routing for a future gpt-6 before its entry loads. gpt-5.5 / gpt-5.4
get the flag in both price maps. Adds tests for the data-driven flag path and
for the flag presence on the gpt-5.x entries; both branches are mutation-tested.

* test(model_prices): allow use_openai_responses_path in price-map schema

The model_prices_and_context_window.json schema validator
(test_aaamodel_prices_and_context_window_json_is_valid) enforces
additionalProperties: false, so the new use_openai_responses_path flag on the
gpt-5.5 / gpt-5.4 entries failed validation. Add it to the schema as a boolean,
alongside the other supports_* / capability flags.

* Add Tensormesh serverless models to the model cost map (#30037)

* Add Tensormesh serverless models to the model cost map

* Flag reasoning support on the Tensormesh models that expose thinking mode

* fix(proxy): invalidate stale key spend counter after budget reset or manual spend update (#30001)

* fix(proxy): reconcile stale key spend counter after budget reset

* fix(proxy): invalidate stale key spend counter after budget reset or manual spend update

* fix(proxy): remove read-time stale counter reconciliation to prevent budget bypass

* revert: undo unrelated formatting changes in enterprise directory

* test(proxy): add unit test for key spend update invalidating counter

* test(proxy): fix mocked update_data and hash token expectations in unit test

* fix(proxy): use Responses-API transformer in pass-through cost tracking (#29728)

The `elif is_responses:` branch of `openai_passthrough_handler` was
calling the chat-completions `transform_response` on a Responses API
payload. The chat-completions transformer expects `choices: [...]`
in the raw response; the Responses API uses `output: [...]` and
`usage.input_tokens` / `usage.output_tokens` (not
`prompt_tokens` / `completion_tokens`). The result was a
KeyError 'choices' deep inside `convert_to_model_response_object`,
swallowed by the surrounding `except Exception` in the handler, and
the SpendLogs row was written by the fallback path with zeroed-out
tokens, spend, and model.

This bug silently undercounts cost for every successful pass-through
call to either OpenAI's `/v1/responses` or Azure's
`/openai/v1/responses` (deployments configured for the Responses
API). Reproduced 2026-06-04 against a real Azure OpenAI Responses
API deployment proxied through LiteLLM v1.88.0.

Fix: use the dedicated
`OpenAIResponsesAPIConfig.transform_response_api_response` for the
Responses branch. This transformer already exists in LiteLLM
(`litellm/llms/openai/responses/transformation.py`) and knows the
Responses-API on-the-wire shape. `litellm.completion_cost` already
handles `ResponsesAPIResponse` natively with `call_type="responses"`,
so no downstream changes are needed.

Tests:

  test_responses_api_uses_responses_transformer_not_chat_completions
    NEW. Real regression test — exercises the openai_passthrough_handler
    with a real-shaped Responses payload (no `choices`, has `output`
    and Responses-API `usage` keys) and NO mocked `get_provider_config`.
    Pre-fix: raises KeyError 'choices' inside the chat-completions
    transformer (the bug). Post-fix: returns a ResponsesAPIResponse,
    completion_cost is called with call_type="responses" and a
    ResponsesAPIResponse instance (asserted).
    Verified to fail on un-fixed handler + pass on fixed handler
    before commit.

  test_responses_api_cost_tracking
    UPDATED. Old test mocked `get_provider_config` (no longer called
    in the responses branch post-fix). Now mocks the Responses
    transformer directly (`OpenAIResponsesAPIConfig.transform_response_api_response`)
    to test the downstream cost-calc contract.

Out of scope for this PR (separate followup):
  - Recognizing *.cognitiveservices.azure.com (the newer Azure
    OpenAI hostname) in the is_openai_*_route checks. Separate PR.

Co-authored-by: shin-berri <[email protected]>
Co-authored-by: yuneng-jiang <[email protected]>

* fix(skills): execute DB skills by matching the litellm_skill_ tool name prefix (#30116)

Skill IDs are generated as litellm_skill_<uuid> and the model-facing
tool name is the sanitized skill ID, but the post-call execution gates
in SkillsInjectionHook only ran tools whose name starts with "skill_",
so DB skills were silently returned to the client as raw tool calls.

Fixes #28122.

Co-authored-by: Cursor <[email protected]>

* fix(anthropic): synthesize content_block_start when Responses stream omits output_item.added (#30115)

* fix(team): reserve team budget raises for proxy admins on /team/update (#30030)

The caller's PERSONAL max_budget was the wrong yardstick for /team/update: a
team's spend ceiling has nothing to do with the admin's own key budget. That
comparison was an unintended side effect of reusing _check_user_team_limits()
(which exists for the /team/new path) and broke the UI, which re-sends the
unchanged budget on every save.

New behavior on /team/update for standalone teams:
- A team admin (already authorized via _verify_team_access) may freely KEEP or
  LOWER the team budget, and change models/tpm/rpm, without being gated by their
  personal limits.
- GROWING a team's spend ceiling is a budget-authority action reserved for proxy
  admins -> 403 for team admins. "Growing" covers both raising max_budget above
  the team's current finite value and removing the cap entirely (max_budget=null,
  detected via model_fields_set so an explicit null is distinguished from an
  omitted field). For a team that currently has no cap, setting a finite value is
  a restriction and is allowed.
- Org-scoped teams remain governed by _check_org_team_limits() (capped by the
  org budget).

Also reverts the #29525 existing_team_max_budget workaround in
_check_user_team_limits() back to the create-only form; /team/new still enforces
the creator's personal caps.

docs(access_control): resolve the contradiction in the team-admin section —
team admins can keep/lower the budget and manage rate limits/models, but cannot
raise the team budget (proxy-admin only).

tests: unit + behavior coverage for raise-blocked, cap-removal-blocked (team
admin), raise/removal allowed (proxy admin), uncapped-team restriction allowed,
keep/lower/resend allowed, and unchanged create-path guards.

Co-authored-by: Cursor <[email protected]>

* test(ui): data-driven App Router migration E2E smoke (default + server-root-path) (#29974)

* test(ui): add a data-driven App Router migration E2E smoke

Add a growing Playwright smoke for migrated pages: for each segment it deep-links
to the path route, asserts the URL and that the dashboard shell rendered, then
clicks off to a legacy page and asserts navigation still works. Driven by
e2e_tests/fixtures/migratedPages.ts, so adding a page is one line.

Runs in two situations against the same proxy: the default mount (npm run
e2e:migration) and a non-root SERVER_ROOT_PATH mount (npm run e2e:migration:root).
globalSetup now logs in at `${SERVER_ROOT_PATH}/ui/login` so the admin storage
state is valid under a prefix. Seeded with api-reference; append the rest as their
migrations merge.

* test(ui): support headed slow-motion + watch pauses in the migration smoke

Honor SLOWMO in the server-root-path config (the default config already did),
and add an env-gated E2E_WATCH_MS pause so a headed run lingers on each state.
Both are no-ops by default, so CI behavior is unchanged.

* test(ui): make the migration smoke a sidebar-click user journey

Rework the smoke from deep-linking to a real navigation journey: start at the
landing page, click the migrated page in the sidebar (expanding submenus for
nested items), assert the path route rendered, reload it (the check a wrong
server_root_path breaks), bounce to a legacy page and back, and — once two pages
are migrated — navigate directly between two migrated pages. Verifies via URL +
shell render, driven by the same fixture list.

* test(ui): address review on the migration smoke

Escape ROOT and segment before interpolating them into RegExp URL matchers so a
future segment containing regex metacharacters can't silently widen the match.
Make the server-root-path config fail fast when SERVER_ROOT_PATH is unset instead
of silently re-running the default mount and passing without exercising the prefix.

* test(ui): drop unused watch helper and fix stale smoke README

* test(ui): run the migration smoke under a server root path in CI

* test(ui): harden + instrument the server-root-path proxy reboot in CI

* test(ui): run the server-root-path migration smoke as its own CI job

Replace the in-place proxy reboot in e2e_ui_testing with a dedicated
e2e_ui_testing_server_root_path job that boots the proxy once with
SERVER_ROOT_PATH=/litellm, matching how every other proxy variant in the
config gets its own job rather than killing and relaunching the live proxy.

The reboot was failing deterministically: after pkill -9 and relaunch the
prefixed proxy never came back up on :4000 (connection refused), so the smoke
never ran. The readiness step that was supposed to surface the cause could
never reach its boot-log tail because CircleCI runs steps under bash -eo
pipefail and the preceding `curl -sv ... | tail` aborted the step with curl's
exit 7. Booting the proxy as the job's own background step lets any boot crash
land in that step's log instead of being swallowed.

The default e2e_ui_testing job is unchanged aside from dropping the reboot,
prefixed-readiness, and prefixed-smoke steps; the migration smoke still runs at
the root mount there via the default Playwright config.

* fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through (#24232)

* fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through

* test: mock post_call_response_headers_hook in audio speech route tests

* chore(ui): remove dead App Router route stubs under (dashboard) (#30045)

models-and-endpoints, organizations, and virtual-keys each had a page.tsx
route under (dashboard)/ that is not in MIGRATED_PAGES, so the sidebar and
deep links never resolve to it and the route is unreachable. Each was a thin
wrapper that handed the shared view empty or no-op props (empty modelData with
a no-op setModelData, hardcoded empty organizations, no-op
setUserRole/setUserEmail), so reaching one would render a degraded page in any
case. The real wrapper belongs in the PR that flips each page into
MIGRATED_PAGES, written with eyes on it and a test

This continues the dead-scaffolding cleanup from #28891. The shared components
these wrappers rendered (ModelsAndEndpointsView, OrganizationFilters) stay,
since the legacy ?page= switch in app/page.tsx and src/components still import
them

* fix(ui/mcp): reset OAuth state on create-server modal close so a prior server's token no longer leaks into the next add-server session (#30000)

* fix(ui/mcp): reset OAuth hook state on modal close so a prior server's token no longer leaks into the next add-server session

* fix(ui/mcp): clear in-flight OAuth guard on reset and reset form/tools on modal close so nothing leaks on a parent-driven dismiss

* fix(mcp): allow team access-group grants in OAuth authorize/token access check (#30041)

* fix(mcp): honor team access-group grants in OAuth authorize/token access check

* test(mcp): mock build_effective_auth_contexts in non-admin authorize tests for isolation

* docs(security): require a reproduction video for vulnerability reports (#30048) (#30063)

With AI models capable of automated vulnerability discovery now publicly
available, we expect a large increase in report volume, much of it
unverified. Requiring a video of the exploit running against a live
instance raises the bar for submissions and keeps triage focused on
reproducible issues. Reports without a video will be closed and reopened
if one is added later.

Co-authored-by: stuxf <[email protected]>

* feat(ui): add admin flag to disable in-product UI nudges for everyone (#29796)

* feat(ui): add admin flag to disable in-product UI nudges for everyone

Admins can now suppress the survey and Claude Code feedback popups for
all users via a single disable_ui_nudges UI setting, instead of relying
on each user dismissing them individually.

* fix(ui): suppress nudges while ui settings are loading

Gate nudgesDisabled on the ui-settings loading state so an admin with
disable_ui_nudges on doesn't see the survey prompt flash, and the
getInProductNudgesCall fetch doesn't fire, on a cold page load before
the flag resolves. Falls back to showing nudges if the fetch errors.

* test(ui): wrap CreateKeyPage test in QueryClientProvider

page.tsx now calls useUISettings (react-query), which needs a
QueryClient that layout.tsx supplies in production but the test did
not. Add the provider and mock getUiSettings so the query resolves.

* chore(ui): remove dead dashboard files and unused dependencies (#30047)

* chore(ui): remove dead dashboard files and unused dependencies

knip flagged seven orphaned source/config files with no importers and
five declared dependencies that nothing in the tree uses. Removing them
shrinks the dashboard bundle's source surface and keeps the manifest
honest; vite stays installed transitively via vitest, so test tooling is
unaffected.

* fix(ci): restore serverRootPath.config.ts referenced by SERVER_ROOT_PATH workflow

The dead-code sweep removed e2e_tests/serverRootPath.config.ts, but its spec
(tests/login/serverRootPathRedirect.spec.ts) and the test_server_root_path.yml
workflow step still depend on it, so the redirect e2e job failed to load a
config that no longer existed.

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593) (#30009)

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593)

After replace_model_in_jsonl, body.model is a stripped provider id. Reverse-mapping it via resolve_model_name_from_model_id is first-match on model_list and caused false 403s when multiple deployments share the same stripped name. Use target_model_names from the unified file id instead.

Co-authored-by: Cursor <[email protected]>

* fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)

Restores the reverse-lookup for the JSONL body.model fallback path so that
legacy/pre-target_model_names managed files still map stripped provider IDs
back to proxy aliases before auth. Also cleans up redundant `or None`.

Co-Authored-By: Claude Sonnet 4.6 <[email protected]>

* Revert "fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)"

This reverts commit 30d2e96f77ef521ccaaf2193fe554980380eb669.

---------

Co-authored-by: Cursor <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>

* Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI (#30064)

* Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI

Adds cost map entries for claude-fable-5 ($10/$50 per MTok, 1M context,
128K output, adaptive thinking only) on the Anthropic API, Bedrock
converse (base, global, and us/eu geo inference profiles at the 10%
regional premium), Vertex AI, and Azure AI (Microsoft Foundry, which
serves Fable 5 with the full 1M context window unlike Opus 4.8).

Registers anthropic.claude-fable-5 in BEDROCK_CONVERSE_MODELS, lists the
model in the setup wizard, and extends the reasoning effort e2e grid.
The Bedrock, Vertex, and Azure grid cells carry fail_reason markers
until the CI accounts are provisioned: Bedrock needs the provider data
sharing opt-in Fable 5 requires, and the Foundry resource needs a
claude-fable-5 deployment.

The first-party entry carries provider_specific_entry {us: 1.1} for the
inference_geo premium and deliberately no fast multiplier since Fable 5
has no fast mode.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Drop removed sampling params for Claude 4.7+ when drop_params is set

Fable 5, Opus 4.7, and Opus 4.8 removed sampling params: the API rejects
top_p, top_k, and any temperature other than 1 with a 400. LiteLLM was
forwarding them even with drop_params enabled because the Anthropic and
Bedrock converse transformations passed temperature/top_p through
unconditionally.

Mirror the GPT-5/o-series handling: temperature=1 still passes through,
other values and any top_p are dropped when drop_params is set, and
without drop_params a clean client-side UnsupportedParamsError tells the
caller how to opt in, instead of surfacing the raw provider error.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Drive sampling param gating from the cost map and cover top_k

Greptile review follow-ups on the sampling param fix: the restriction for
Fable 5 / Opus 4.7 / 4.8 is now declared as supports_sampling_params: false
on every affected cost map entry (perplexity excluded; that route is
OpenAI-compatible and maps sampling params upstream) and read back through
a tri-state map lookup, keeping the name check only as a fallback for
provider-routed ids whose hosted map entries predate the flag, the same
layering supports_adaptive_thinking uses. top_k bypasses map_openai_params
as a provider-specific kwarg, so it is gated at the shared
AnthropicConfig.transform_request boundary (direct, Bedrock invoke, Vertex,
Azure) and in the Bedrock converse _handle_top_k_value path, with
drop_params threaded through the converse transform helpers.

Also updates the reasoning effort grid cell count assertion for the four
Fable 5 rows added on this branch (29 x 11 cells).

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Declare supports_sampling_params in the cost map schema

The model map validation schema uses additionalProperties: false, so the
new flag must be declared for the 28 entries that carry it; this was the
one failing job (misc / Run tests) on the previous commit.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* fix(bedrock): gate top_k=0 on converse to match Anthropic boundary

Truthiness check let top_k=0 silently disappear on models that removed
sampling params, while AnthropicConfig.transform_request treats 0 as
present and raises UnsupportedParamsError (or drops when drop_params is
set). Switch to 'is not None' so converse, direct Anthropic, invoke,
Vertex, and Azure all behave the same for top_k=0.

---------

Co-authored-by: Cursor Agent <[email protected]>

* fix(anthropic): avoid index -1 content_block_delta in messages stream

When a /v1/messages request is routed through the Responses API
adapter, AnthropicResponsesStreamWrapper only emits content_block_start
on response.output_item.added. Some upstreams (LMStudio for example)
never send that event, so the text delta handler fell back to
_current_block_index, which starts at -1, and clients received
content_block_delta events with index -1 and no preceding
content_block_start. Anthropic SDKs then fail with "text part -1 not
found"

The text delta handler now synthesizes a content_block_start with a
fresh block index whenever the delta references an unregistered item_id
or no block is open yet, and registers the item_id so follow-up deltas
reuse the same index

Addresses the /v1/messages defect in #27442

* Make test sys.path shim resolve relative to the file, not the CWD

os.path.abspath("../../../../../../..") depends on where pytest is
invoked from; anchoring on os.path.dirname(__file__) makes the import
work from any working directory. Also corrects the depth: the repo root
is six levels above this file, not seven.

---------

Co-authored-by: milan-berri <[email protected]>
Co-authored-by: Cursor <[email protected]>
Co-authored-by: ryan-crabbe-berri <[email protected]>
Co-authored-by: michelligabriele <[email protected]>
Co-authored-by: tin-berri <[email protected]>
Co-authored-by: yuneng-jiang <[email protected]>
Co-authored-by: stuxf <[email protected]>
Co-authored-by: Sameer Kankute <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>
Co-authored-by: Mateo Wang <[email protected]>

* fix: enable compact-2026-01-12 beta header for vertex_ai provider (#30114)

* fix(team): reserve team budget raises for proxy admins on /team/update (#30030)

The caller's PERSONAL max_budget was the wrong yardstick for /team/update: a
team's spend ceiling has nothing to do with the admin's own key budget. That
comparison was an unintended side effect of reusing _check_user_team_limits()
(which exists for the /team/new path) and broke the UI, which re-sends the
unchanged budget on every save.

New behavior on /team/update for standalone teams:
- A team admin (already authorized via _verify_team_access) may freely KEEP or
  LOWER the team budget, and change models/tpm/rpm, without being gated by their
  personal limits.
- GROWING a team's spend ceiling is a budget-authority action reserved for proxy
  admins -> 403 for team admins. "Growing" covers both raising max_budget above
  the team's current finite value and removing the cap entirely (max_budget=null,
  detected via model_fields_set so an explicit null is distinguished from an
  omitted field). For a team that currently has no cap, setting a finite value is
  a restriction and is allowed.
- Org-scoped teams remain governed by _check_org_team_limits() (capped by the
  org budget).

Also reverts the #29525 existing_team_max_budget workaround in
_check_user_team_limits() back to the create-only form; /team/new still enforces
the creator's personal caps.

docs(access_control): resolve the contradiction in the team-admin section —
team admins can keep/lower the budget and manage rate limits/models, but cannot
raise the team budget (proxy-admin only).

tests: unit + behavior coverage for raise-blocked, cap-removal-blocked (team
admin), raise/removal allowed (proxy admin), uncapped-team restriction allowed,
keep/lower/resend allowed, and unchanged create-path guards.

Co-authored-by: Cursor <[email protected]>

* test(ui): data-driven App Router migration E2E smoke (default + server-root-path) (#29974)

* test(ui): add a data-driven App Router migration E2E smoke

Add a growing Playwright smoke for migrated pages: for each segment it deep-links
to the path route, asserts the URL and that the dashboard shell rendered, then
clicks off to a legacy page and asserts navigation still works. Driven by
e2e_tests/fixtures/migratedPages.ts, so adding a page is one line.

Runs in two situations against the same proxy: the default mount (npm run
e2e:migration) and a non-root SERVER_ROOT_PATH mount (npm run e2e:migration:root).
globalSetup now logs in at `${SERVER_ROOT_PATH}/ui/login` so the admin storage
state is valid under a prefix. Seeded with api-reference; append the rest as their
migrations merge.

* test(ui): support headed slow-motion + watch pauses in the migration smoke

Honor SLOWMO in the server-root-path config (the default config already did),
and add an env-gated E2E_WATCH_MS pause so a headed run lingers on each state.
Both are no-ops by default, so CI behavior is unchanged.

* test(ui): make the migration smoke a sidebar-click user journey

Rework the smoke from deep-linking to a real navigation journey: start at the
landing page, click the migrated page in the sidebar (expanding submenus for
nested items), assert the path route rendered, reload it (the check a wrong
server_root_path breaks), bounce to a legacy page and back, and — once two pages
are migrated — navigate directly between two migrated pages. Verifies via URL +
shell render, driven by the same fixture list.

* test(ui): address review on the migration smoke

Escape ROOT and segment before interpolating them into RegExp URL matchers so a
future segment containing regex metacharacters can't silently widen the match.
Make the server-root-path config fail fast when SERVER_ROOT_PATH is unset instead
of silently re-running the default mount and passing without exercising the prefix.

* test(ui): drop unused watch helper and fix stale smoke README

* test(ui): run the migration smoke under a server root path in CI

* test(ui): harden + instrument the server-root-path proxy reboot in CI

* test(ui): run the server-root-path migration smoke as its own CI job

Replace the in-place proxy reboot in e2e_ui_testing with a dedicated
e2e_ui_testing_server_root_path job that boots the proxy once with
SERVER_ROOT_PATH=/litellm, matching how every other proxy variant in the
config gets its own job rather than killing and relaunching the live proxy.

The reboot was failing deterministically: after pkill -9 and relaunch the
prefixed proxy never came back up on :4000 (connection refused), so the smoke
never ran. The readiness step that was supposed to surface the cause could
never reach its boot-log tail because CircleCI runs steps under bash -eo
pipefail and the preceding `curl -sv ... | tail` aborted the step with curl's
exit 7. Booting the proxy as the job's own background step lets any boot crash
land in that step's log instead of being swallowed.

The default e2e_ui_testing job is unchanged aside from dropping the reboot,
prefixed-readiness, and prefixed-smoke steps; the migration smoke still runs at
the root mount there via the default Playwright config.

* fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through (#24232)

* fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through

* test: mock post_call_response_headers_hook in audio speech route tests

* chore(ui): remove dead App Router route stubs under (dashboard) (#30045)

models-and-endpoints, organizations, and virtual-keys each had a page.tsx
route under (dashboard)/ that is not in MIGRATED_PAGES, so the sidebar and
deep links never resolve to it and the route is unreachable. Each was a thin
wrapper that handed the shared view empty or no-op props (empty modelData with
a no-op setModelData, hardcoded empty organizations, no-op
setUserRole/setUserEmail), so reaching one would render a degraded page in any
case. The real wrapper belongs in the PR that flips each page into
MIGRATED_PAGES, written with eyes on it and a test

This continues the dead-scaffolding cleanup from #28891. The shared components
these wrappers rendered (ModelsAndEndpointsView, OrganizationFilters) stay,
since the legacy ?page= switch in app/page.tsx and src/components still import
them

* fix(ui/mcp): reset OAuth state on create-server modal close so a prior server's token no longer leaks into the next add-server session (#30000)

* fix(ui/mcp): reset OAuth hook state on modal close so a prior server's token no longer leaks into the next add-server session

* fix(ui/mcp): clear in-flight OAuth guard on reset and reset form/tools on modal close so nothing leaks on a parent-driven dismiss

* fix(mcp): allow team access-group grants in OAuth authorize/token access check (#30041)

* fix(mcp): honor team access-group grants in OAuth authorize/token access check

* test(mcp): mock build_effective_auth_contexts in non-admin authorize tests for isolation

* docs(security): require a reproduction video for vulnerability reports (#30048) (#30063)

With AI models capable of automated vulnerability discovery now publicly
available, we expect a large increase in report volume, much of it
unverified. Requiring a video of the exploit running against a live
instance raises the bar for submissions and keeps triage focused on
reproducible issues. Reports without a video will be closed and reopened
if one is added later.

Co-authored-by: stuxf <[email protected]>

* feat(ui): add admin flag to disable in-product UI nudges for everyone (#29796)

* feat(ui): add admin flag to disable in-product UI nudges for everyone

Admins can now suppress the survey and Claude Code feedback popups for
all users via a single disable_ui_nudges UI setting, instead of relying
on each user dismissing them individually.

* fix(ui): suppress nudges while ui settings are loading

Gate nudgesDisabled on the ui-settings loading state so an admin with
disable_ui_nudges on doesn't see the survey prompt flash, and the
getInProductNudgesCall fetch doesn't fire, on a cold page load before
the flag resolves. Falls back to showing nudges if the fetch errors.

* test(ui): wrap CreateKeyPage test in QueryClientProvider

page.tsx now calls useUISettings (react-query), which needs a
QueryClient that layout.tsx supplies in production but the test did
not. Add the provider and mock getUiSettings so the query resolves.

* chore(ui): remove dead dashboard files and unused dependencies (#30047)

* chore(ui): remove dead dashboard files and unused dependencies

knip flagged seven orphaned source/config files with no importers and
five declared dependencies that nothing in the tree uses. Removing them
shrinks the dashboard bundle's source surface and keeps the manifest
honest; vite stays installed transitively via vitest, so test tooling is
unaffected.

* fix(ci): restore serverRootPath.config.ts referenced by SERVER_ROOT_PATH workflow

The dead-code sweep removed e2e_tests/serverRootPath.config.ts, but its spec
(tests/login/serverRootPathRedirect.spec.ts) and the test_server_root_path.yml
workflow step still depend on it, so the redirect e2e job failed to load a
config that no longer existed.

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593) (#30009)

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593)

After replace_model_in_jsonl, body.model is a stripped provider id. Reverse-mapping it via resolve_model_name_from_model_id is first-match on model_list and caused false 403s when multiple deployments share the same stripped name. Use target_model_names from the unified file id instead.

Co-authored-by: Cursor <[email protected]>

* fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)

Restores the reverse-lookup for the JSONL body.model fallback path so that
legacy/pre-target_model_names managed files still map stripped provider IDs
back to proxy aliases before auth. Also cleans up redundant `or None`.

Co-Authored-By: Claude Sonnet 4.6 <[email protected]>

* Revert "fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)"

This reverts commit 30d2e96f77ef521ccaaf2193fe554980380eb669.

---------

Co-authored-by: Cursor <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>

* Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI (#30064)

* Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI

Adds cost map entries for claude-fable-5 ($10/$50 per MTok, 1M context,
128K output, adaptive thinking only) on the Anthropic API, Bedrock
converse (base, global, and us/eu geo inference profiles at the 10%
regional premium), Vertex AI, and Azure AI (Microsoft Foundry, which
serves Fable 5 with the full 1M context window unlike Opus 4.8).

Registers anthropic.claude-fable-5 in BEDROCK_CONVERSE_MODELS, lists the
model in the setup wizard, and extends the reasoning effort e2e grid.
The Bedrock, Vertex, and Azure grid cells carry fail_reason markers
until the CI accounts are provisioned: Bedrock needs the provider data
sharing opt-in Fable 5 requires, and the Foundry resource needs a
claude-fable-5 deployment.

The first-party entry carries provider_specific_entry {us: 1.1} for the
inference_geo premium and deliberately no fast multiplier since Fable 5
has no fast mode.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Drop removed sampling params for Claude 4.7+ when drop_params is set

Fable 5, Opus 4.7, and Opus 4.8 removed sampling params: the API rejects
top_p, top_k, and any temperature other than 1 with a 400. LiteLLM was
forwarding them even with drop_params enabled because the Anthropic and
Bedrock converse transformations passed temperature/top_p through
unconditionally.

Mirror the GPT-5/o-series handling: temperature=1 still passes through,
other values and any top_p are dropped when drop_params is set, and
without drop_params a clean client-side UnsupportedParamsError tells the
caller how to opt in, instead of surfacing the raw provider error.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Drive sampling param gating from the cost map and cover top_k

Greptile review follow-ups on the sampling param fix: the restriction for
Fable 5 / Opus 4.7 / 4.8 is now declared as supports_sampling_params: false
on every affected cost map entry (perplexity excluded; that route is
OpenAI-compatible and maps sampling params upstream) and read back through
a tri-state map lookup, keeping the name check only as a fallback for
provider-routed ids whose hosted map entries predate the flag, the same
layering supports_adaptive_thinking uses. top_k bypasses map_openai_params
as a provider-specific kwarg, so it is gated at the shared
AnthropicConfig.transform_request boundary (direct, Bedrock invoke, Vertex,
Azure) and in the Bedrock converse _handle_top_k_value path, with
drop_params threaded through the converse transform helpers.

Also updates the reasoning effort grid cell count assertion for the four
Fable 5 rows added on this branch (29 x 11 cells).

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Declare supports_sampling_params in the cost map schema

The model map validation schema uses additionalProperties: false, so the
new flag must be declared for the 28 entries that carry it; this was the
one failing job (misc / Run tests) on the previous commit.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* fix(bedrock): gate top_k=0 on converse to match Anthropic boundary

Truthiness check let top_k=0 silently disappear on models that removed
sampling params, while AnthropicConfig.transform_request treats 0 as
present and raises UnsupportedParamsError (or drops when drop_params is
set). Switch to 'is not None' so converse, direct Anthropic, invoke,
Vertex, and Azure all behave the same for top_k=0.

---------

Co-authored-by: Cursor Agent <[email protected]>

* fix: enable compact-2026-01-12 beta header for vertex_ai provider

The vertex_ai block in anthropic_beta_headers_config.json mapped
compact-2026-01-12 to null, so update_headers_with_filtered_beta
stripped the header before the request reached Vertex while the
compact_20260112 context edit stayed in the body, and Vertex rejected
the request with HTTP 400. Vertex rawPredict accepts the header, and
the bedrock and databricks blocks already forward it. Mirrors #21867,
which enabled context-1m-2025-08-07 for vertex_ai the same way.

Fixes #27290.

---------

Co-authored-by: milan-berri <[email protected]>
Co-authored-by: Cursor <[email protected]>
Co-authored-by: ryan-crabbe-berri <[email protected]>
Co-authored-by: michelligabriele <[email protected]>
Co-authored-by: tin-berri <[email protected]>
Co-authored-by: yuneng-jiang <[email protected]>
Co-authored-by: stuxf <[email protected]>
Co-authored-by: Sameer Kankute <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>
Co-authored-by: Mateo Wang <[email protected]>

* fix(proxy): coerce litellm_settings.max_budget env var to float (#30113)

* fix(team): reserve team budget raises for proxy admins on /team/update (#30030)

The caller's PERSONAL max_budget was the wrong yardstick for /team/update: a
team's spend ceiling has nothing to do with the admin's own key budget. That
comparison was an unintended side effect of reusing _check_user_team_limits()
(which exists for the /team/new path) and broke the UI, which re-sends the
unchanged budget on every save.

New behavior on /team/update for standalone teams:
- A team admin (already authorized via _verify_team_access) may freely KEEP or
  LOWER the team budget, and change models/tpm/rpm, without being gated by their
  personal limits.
- GROWING a team's spend ceiling is a budget-authority action reserved for proxy
  admins -> 403 for team admins. "Growing" covers both raising max_budget above
  the team's current finite value and removing the cap entirely (max_budget=null,
  detected via model_fields_set so an explicit null is distinguished from an
  omitted field). For a team that currently has no cap, setting a finite value is
  a restriction and is allowed.
- Org-scoped teams remain governed by _check_org_team_limits() (capped by the
  org budget).

Also reverts the #29525 existing_team_max_budget workaround in
_check_user_team_limits() back to the create-only form; /team/new still enforces
the creator's personal caps.

docs(access_control): resolve the contradiction in the team-admin section —
team admins can keep/lower the budget and manage rate limits/models, but cannot
raise the team budget (proxy-admin only).

tests: unit + behavior coverage for raise-blocked, cap-removal-blocked (team
admin), raise/removal allowed (proxy admin), uncapped-team restriction allowed,
keep/lower/resend allowed, and unchanged create-path guards.

Co-authored-by: Cursor <[email protected]>

* test(ui): data-driven App Router migration E2E smoke (default + server-root-path) (#29974)

* test(ui): add a data-driven App Router migration E2E smoke

Add a growing Playwright smoke for migrated pages: for each segment it deep-links
to the path route, asserts the URL and that the dashboard shell rendered, then
clicks off to a legacy page and asserts navigation still works. Driven by
e2e_tests/fixtures/migratedPages.ts, so adding a page is one line.

Runs in two situations against the same proxy: the default mount (npm run
e2e:migration) and a non-root SERVER_ROOT_PATH mount (npm run e2e:migration:root).
globalSetup now logs in at `${SERVER_ROOT_PATH}/ui/login` so the admin storage
state is valid under a prefix. Seeded with api-reference; append the rest as their
migrations merge.

* test(ui): support headed slow-motion + watch pauses in the migration smoke

Honor SLOWMO in the server-root-path config (the default config already did),
and add an env-gated E2E_WATCH_MS pause so a headed run lingers on each state.
Both are no-ops by default, so CI behavior is unchanged.

* test(ui): make the migration smoke a sidebar-click user journey

Rework the smoke from deep-linking to a real navigation journey: start at the
landing page, click the migrated page in the sidebar (expanding submenus for
nested items), assert the path route rendered, reload it (the check a wrong
server_root_path breaks), bounce to a legacy page and back, and — once two pages
are migrated — navigate directly between two migrated pages. Verifies via URL +
shell render, driven by the same fixture list.

* test(ui): address review on the migration smoke

Escape ROOT and segment before interpolating them into RegExp URL matchers so a
future segment containing regex metacharacters can't silently widen the match.
Make the server-root-path config fail fast when SERVER_ROOT_PATH is unset instead
of silently re-running the default mount and passing without exercising the prefix.

* test(ui): drop unused watch helper and fix stale smoke README

* test(ui): run the migration smoke under a server root path in CI

* test(ui): harden + instrument the server-root-path proxy reboot in CI

* test(ui): run the server-root-path migration smoke as its own CI job

Replace the in-place proxy reboot in e2e_ui_testing with a dedicated
e2e_ui_testing_server_root_path job that boots the proxy once with
SERVER_ROOT_PATH=/litellm, matching how every other proxy variant in the
config gets its own job rather than killing and relaunching the live proxy.

The reboot was failing deterministically: after pkill -9 and relaunch the
prefixed proxy never came back up on :4000 (connection refused), so the smoke
never ran. The readiness step that was supposed to surface the cause could
never reach its boot-log tail because CircleCI runs steps under bash -eo
pipefail and the preceding `curl -sv ... | tail` aborted the step with curl's
exit 7. Booting the proxy as the job's own background step lets any boot crash
land in that step's log instead of being swallowed.

The default e2e_ui_testing job is unchanged aside from dropping the reboot,
prefixed-readiness, and prefixed-smoke steps; the migration smoke still runs at
the root mount there via the default Playwright config.

* fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through (#24232)

* fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through

* test: mock post_call_response_headers_hook in audio speech route tests

* chore(ui): remove dead App Router route stubs under (dashboard) (#30045)

models-and-endpoints, organizations, and virtual-keys each had a page.tsx
route under (dashboard)/ that is not in MIGRATED_PAGES, so the sidebar and
deep links never resolve to it and the route is unreachable. Each was a thin
wrapper that handed the shared view empty or no-op props (empty modelData with
a no-op setModelData, hardcoded empty organizations, no-op
setUserRole/setUserEmail), so reaching one would render a degraded page in any
case. The real wrapper belongs in the PR that flips each page into
MIGRATED_PAGES, written with eyes on it and a test

This continues the dead-scaffolding cleanup from #28891. The shared components
these wrappers rendered (ModelsAndEndpointsView, OrganizationFilters) stay,
since the legacy ?page= switch in app/page.tsx and src/components still import
them

* fix(ui/mcp): reset OAuth state on create-server modal close so a prior server's token no longer leaks into the next add-server session (#30000)

* fix(ui/mcp): reset OAuth hook state on modal close so a prior server's token no longer leaks into the next add-server session

* fix(ui/mcp): clear in-flight OAuth guard on reset and reset form/tools on modal close so nothing leaks on a parent-driven dismiss

* fix(mcp): allow team access-group grants in OAuth authorize/token access check (#30041)

* fix(mcp): honor team access-group grants in OAuth authorize/token access check

* test(mcp): mock build_effective_auth_contexts in non-admin authorize tests for isolation

* docs(security): require a reproduction video for vulnerability reports (#30048) (#30063)

With AI models capable of automated vulnerability discovery now publicly
available, we expect a large increase in report volume, much of it
unverified. Requiring a video of the exploit running against a live
instance raises the bar for submissions and keeps triage focused on
reproducible issues. Reports without a video will be closed and reopened
if one is added later.

Co-authored-by: stuxf <[email protected]>

* feat(ui): add admin flag to disable in-product UI nudges for everyone (#29796)

* feat(ui): add admin flag to disable in-product UI nudges for everyone

Admins can now suppress the survey and Claude Code feedback popups for
all users via a single disable_ui_nudges UI setting, instead of relying
on each user dismissing them individually.

* fix(ui): suppress nudges while ui settings are loading

Gate nudgesDisabled on the ui-settings loading state so an admin with
disable_ui_nudges on doesn't see the survey prompt flash, and the
getInProductNudgesCall fetch doesn't fire, on a cold page load before
the flag resolves. Falls back to showing nudges if the fetch errors.

* test(ui): wrap CreateKeyPage test in QueryClientProvider

page.tsx now calls useUISettings (react-query), which needs a
QueryClient that layout.tsx supplies in production but the test did
not. Add the provider and mock getUiSettings so the query resolves.

* chore(ui): remove dead dashboard files and unused dependencies (#30047)

* chore(ui): remove dead dashboard files and unused dependencies

knip flagged seven orphaned source/config files with no importers and
five declared dependencies that nothing in the tree uses. Removing them
shrinks the dashboard bundle's source surface and keeps the manifest
honest; vite stays installed transitively via vitest, so test tooling is
unaffected.

* fix(ci): restore serverRootPath.config.ts referenced by SERVER_ROOT_PATH workflow

The dead-code sweep removed e2e_tests/serverRootPath.config.ts, but its spec
(tests/login/serverRootPathRedirect.spec.ts) and the test_server_root_path.yml
workflow step still depend on it, so the redirect e2e job failed to load a
config that no longer existed.

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593) (#30009)

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593)

After replace_model_in_jsonl, body.model is a stripped provider id. Reverse-mapping it via resolve_model_name_from_model_id is first-match on model_list and caused false 403s when multiple deployments share the same stripped name. Use target_model_names from the unified file id instead.

Co-authored-by: Cursor <[email protected]>

* fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)

Restores the reverse-lookup for the JSONL body.model fallback path so that
legacy/pre-target_model_names managed files still map stripped provider IDs
back to proxy aliases before auth. Also cleans up redundant `or None`.

Co-Authored-By: Claude Sonnet 4.6 <[email protected]>

* Revert "fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)"

This reverts commit 30d2e96f77ef521ccaaf2193fe554980380eb669.

---------

Co-authored-by: Cursor <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>

* Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI (#30064)

* Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI

Adds cost map entries for claude-fable-5 ($10/$50 per MTok, 1M context,
128K output, adaptive thinking only) on the Anthropic API, Bedrock
converse (base, global, and us/eu geo inference profiles at the 10%
regional premium), Vertex AI, and Azure AI (Microsoft Foundry, which
serves Fable 5 with the full 1M context window unlike Opus 4.8).

Registers anthropic.claude-fable-5 in BEDROCK_CONVERSE_MODELS, lists the
model in the setup wizard, and extends the reasoning effort e2e grid.
The Bedrock, Vertex, and Azure grid cells carry fail_reason markers
until the CI accounts are provisioned: Bedrock needs the provider data
sharing opt-in Fable 5 requires, and the Foundry resource needs a
claude-fable-5 deployment.

The first-party entry carries provider_specific_entry {us: 1.1} for the
inference_geo premium and deliberately no fast multiplier since Fable 5
has no fast mode.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Drop removed sampling params for Claude 4.7+ when drop_params is set

Fable 5, Opus 4.7, and Opus 4.8 removed sampling params: the API rejects
top_p, top_k, and any temperature other than 1 with a 400. LiteLLM was
forwarding them even with drop_params enabled because the Anthropic and
Bedrock converse transformations passed temperature/top_p through
unconditionally.

Mirror the GPT-5/o-series handling: temperature=1 still passes through,
other values and any top_p are dropped when drop_params is set, and
without drop_params a clean client-side UnsupportedParamsError tells the
caller how to opt in, instead of surfacing the raw provider error.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Drive sampling param gating from the cost map and cover top_k

Greptile review follow-ups on the sampling param fix: the restriction for
Fable 5 / Opus 4.7 / 4.8 is now declared as supports_sampling_params: false
on every affected cost map entry (perplexity excluded; that route is
OpenAI-compatible and maps sampling params upstream) and read back through
a tri-state map lookup, keeping the name check only as a fallback for
provider-routed ids whose hosted map entries predate the flag, the same
layering supports_adaptive_thinking uses. top_k bypasses map_openai_params
as a provider-specific kwarg, so it is gated at the shared
AnthropicConfig.transform_request boundary (direct, Bedrock invoke, Vertex,
Azure) and in the Bedrock converse _handle_top_k_value path, with
drop_params threaded through the converse transform helpers.

Also updates the reasoning effort grid cell count assertion for the four
Fable 5 rows added on this branch (29 x 11 cells).

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Declare supports_sampling_params in the cost map schema

The model map validation schema uses additionalProperties: false, so the
new flag must be declared for the 28 entries that carry it; this was the
one failing job (misc / Run tests) on the previous commit.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* fix(bedrock): gate top_k=0 on converse to match Anthropic boundary

Truthiness check let top_k=0 silently disappear on models that removed
sampling params, while AnthropicConfig.transform_request treats 0 as
present and raises UnsupportedParamsError (or drops when drop_params is
set). Switch to 'is not None' so converse, direct Anthropic, invoke,
Vertex, and Azure all behave the same for top_k=0.

---------

Co-authored-by: Cursor Agent <[email protected]>

* fix(proxy): coerce litellm_settings.max_budget env var to float

When max_budget is set in litellm_settings via os.environ/MAX_BUDGET,
the env var resolves to a string and the generic setattr branch in
ProxyConfig.load_config stored it as-is, so the startup check
litellm.max_budget > 0 raised TypeError. The earlier fix (#23855) only
covered the CLI initialize() path. Coerce the value to float in the
settings loop, matching the existing max_internal_user_budget handling.

Fixes #26696.

---------

Co-authored-by: milan-berri <[email protected]>
Co-authored-by: Cursor <[email protected]>
Co-authored-by: ryan-crabbe-berri <[email protected]>
Co-authored-by: michelligabriele <[email protected]>
Co-authored-by: tin-berri <[email protected]>
Co-authored-by: yuneng-jiang <[email protected]>
Co-authored-by: stuxf <[email protected]>
Co-authored-by: Sameer Kankute <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>
Co-authored-by: Mateo Wang <[email protected]>

* fix(router): don't drop bedrock pass-through deployments using IAM credentials (#30111)

* Fix Bedrock passthrough deployment dropped when using IAM credentials

Bedrock deployments with use_in_pass_through enabled and IAM/OIDC auth
(aws_role_name, no api_key) hit the generic pass-through branch in
Router._initialize_deployment_for_pass_through, which calls
set_pass_through_credentials and raises "api_key is required". The
exception drops the deployment from the router entirely, breaking both
passthrough and normal routing for that model.

Skip the credential store write when no api_key is set; the bedrock
passthrough route resolves AWS credentials at request time via
BedrockConverseLLM.get_credentials(), not the passthrough credential
store, so there is nothing to register here.

Fixes #27728.

* Reset passthrough credentials singleton before api_key credential test

The test reads the module-level passthrough_endpoint_router singleton,
so a stale "openai" entry written by an earlier test in the same
process could make the assertion pass without exercising the code path.
Clearing the credentials dict up front makes the test order-independent.

* fix(sdk): stop mirroring reasoning_content in provider_specific_fields (#30110)

The dict-to-response conversion path mirrored reasoning_content into
provider_specific_fields, while live provider transforms (Anthropic's
_build_provider_specific_fields) only set it top-level on the Message.
Cache-replayed messages therefore serialized differently from live
ones, breaking disk cache key stability for multi-turn conversations
with extended thinking.

The mirror was added for DeepSeek before Message.reasoning_content
existed as a top-level attribute. The top-level field is still set by
the converter, so DeepSeek's request-side promotion is unaffected.

Fixes #27337.

* fix(mcp): coerce mcp_server_cost_info values to float at ingest (#30109)

* fix(mcp): coerce mcp_server_cost_info values to float at ingest

YAML 1.1 parses scientific notation without a decimal point
(e.g. 7e-05) as a string, and MCPServerCostInfo is a TypedDict with no
runtime validation, so a string-typed default_cost_per_query from
config.yaml flowed through the proxy untouched and crashed the MCP
server settings page with '.toFixed is not a function'. Normalize
mcp_server_cost_info on both the config and DB load paths, dropping
non-numeric values with a warning instead of failing the server load.

Fixes #27097.

* fix(mcp): drop non-numeric default_cost_per_query instead of nulling it

Keeping the key with a None value still exposes a null to the UI,
which can crash .toFixed formatting when the consumer checks key
existence rather than truthiness. Delete the key on coercion failure,
matching how non-numeric per-tool cost entries are already omitted.

* fix(proxy): count embedding and text completion tokens toward TPM limits (#30105)

* fix(proxy): count embedding and text completion tokens toward TPM limits

The parallel request limiters only read token usage off ModelResponse,
so EmbeddingResponse and TextCompletionResponse objects left
total_tokens at 0 and the per key, user, team, and end user TPM
counters never incremented. Requests to /v1/embeddings and
/v1/completions were effectively free against any tpm_limit. In the v3
limiter this was worse: the post-call reconciliation computed actual
usage as 0 and refunded the pre-call reservation made at request time.

Broaden the isinstance checks to accept EmbeddingResponse and
TextCompletionResponse, which both expose a Usage object, at the four
per-scope sites in parallel_request_limiter.py and at the usage
extraction in parallel_request_limiter_v3.py. ResponsesAPIResponse was
already covered in v3 via BaseLiteLLMOpenAIResponseObject.

Fixes #27738.

* test(proxy): cover v1 limiter TPM counting for embedding and text completion responses

Exercise the broadened isinstance sites in parallel_request_limiter.py
by asserting that async_log_success_event adds total_tokens to the per
key, user, team, and end user TPM counters for EmbeddingResponse and
TextCompletionResponse objects. The counters are pre-seeded at zero so
the assertion is exactly the increment; on the pre-fix code these
responses left total_tokens at 0 and the test fails.

* fix(openai): forward client headers on the text completion path (#30103)

* fix(openai): forward client headers on the text completion path

litellm.completion() merges caller headers with extra_headers, but the
text-completion-openai branch never passed the merged dict to
openai_text_completions.completion(), and the handler only used its
headers argument for logging. Pass the merged headers through the call
site and set them as extra_headers on the outgoing request, mirroring
the chat completion handler, so x-* client headers forwarded by the
proxy reach the provider on /v1/completions.

Fixes #27410.

* Drop redundant extra_headers assignment and fix test module collision

completion() merges extra_headers into headers before the
text-completion-openai branch, and the handler now sets the merged
headers as extra_headers on the request, so the branch-local
optional_params["extra_headers"] assignment was a dead duplicate.
Removing it keeps the assignment in one place while both entry paths
(litellm.text_completion and direct handler callers) still forward
headers; a new regression test pins the extra_headers kwarg path.

Also rename the test module to test_completion_handler.py since its
basename collided with tests/test_litellm/llms/bedrock/batches/
test_handler.py and broke pytest collection.

* fix(bedrock): route Anthropic-shape count_tokens to InvokeModel and base64-encode the body (#30102)

* fix(bedrock): route Anthropic-shape count_tokens to InvokeModel

POST /v1/messages/count_tokens with Anthropic content blocks
({"type": "text"|"tool_use"|...}) was routed to the Converse input of
the Bedrock CountTokens API. The Converse transform copies list content
through verbatim, so Bedrock rejected the request with a 400 and the
caller silently fell back to the local tokenizer, returning counts that
can be off by ~50% on tool-heavy payloads.

_detect_input_type now routes messages whose content blocks carry a
"type" key (Anthropic shape) to the invokeModel input, which forwards
the body verbatim. The invokeModel body is now base64-encoded as the
CountTokens API requires (InvokeModelTokensRequest.body is a
base64-encoded blob), and Anthropic Messages bodies get the
anthropic_version and max_tokens fields Bedrock validates against.

Fixes #27632.

* refactor(bedrock): name the CountTokens max_tokens placeholder

Replace the magic 1024 with a module-level
DEFAULT_ANTHROPIC_INVOKE_MODEL_MAX_TOKENS constant so the intent is
explicit and t…

…T-3593) (BerriAI#30009)

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593)

After replace_model_in_jsonl, body.model is a stripped provider id. Reverse-mapping it via resolve_model_name_from_model_id is first-match on model_list and caused false 403s when multiple deployments share the same stripped name. Use target_model_names from the unified file id instead.

Co-authored-by: Cursor <[email protected]>

* fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)

Restores the reverse-lookup for the JSONL body.model fallback path so that
legacy/pre-target_model_names managed files still map stripped provider IDs
back to proxy aliases before auth. Also cleans up redundant `or None`.

Co-Authored-By: Claude Sonnet 4.6 <[email protected]>

* Revert "fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)"

This reverts commit 30d2e96.

---------

Co-authored-by: Cursor <[email protected]>
Co-authored-by: Claude Sonnet 4.6 <[email protected]>
(cherry picked from commit 2cd7e87)

…T-3593) (BerriAI#30009)

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593)

After replace_model_in_jsonl, body.model is a stripped provider id. Reverse-mapping it via resolve_model_name_from_model_id is first-match on model_list and caused false 403s when multiple deployments share the same stripped name. Use target_model_names from the unified file id instead.

Co-authored-by: Cursor <[email protected]>

* fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)

Restores the reverse-lookup for the JSONL body.model fallback path so that
legacy/pre-target_model_names managed files still map stripped provider IDs
back to proxy aliases before auth. Also cleans up redundant `or None`.


* Revert "fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)"

This reverts commit 30d2e96.

---------

Co-authored-by: Cursor <[email protected]>

* fix(mcp): report scoped server name during initialize (#29865)

* fix mcp scoped server name

* Update litellm/proxy/_experimental/mcp_server/mcp_context.py

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* test(mcp): cover scoped server name in the SSE initialize handler

---------

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* fix(ui): show all session logs in the drawer, not just the first 50 (#29795)

* fix(ui): show newest session logs first

* test(ui): keep session log pagination coverage

* fix(ui): show all session logs in the drawer, not just the first page

The session detail drawer fetched session logs via sessionSpendLogsCall
without page/page_size, so it only ever received the backend default of one
page (50 rows). Sessions with more than 50 calls had the rest unreachable in
the UI (#29153).

sessionSpendLogsCall now takes page/page_size, and the drawer fetches the
first page, reads total_pages, then fetches the remaining pages and
accumulates them before the existing client-side sort. This keeps the single
continuous list (and the selected-log lookup and keyboard navigation, which
all assume the full session) correct. Fetching is bounded by a page cap, and
the sidebar shows a "showing most recent N" note if a session exceeds it.

The rows are lightweight metadata (the endpoint excludes messages/response),
so the full set is small; request/response bodies are still loaded per log on
demand.

* fix(ui): default session drawer to most recent log, newest first

Open a session with its most recent log selected, and order the sidebar
newest-first to match the all-sessions logs overview. MCP calls stay
grouped last. The latest log by time is computed explicitly, since the
MCP grouping means it is not always the first row.

* Apply fetching pages in batches suggestion from @greptile-apps[bot]

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* fix(ui): derive session total from accumulated rows when backend omits it

Compute the session total after all pages are fetched, falling back to the
accumulated row count rather than the first page's. Guards the truncation
note against a backend response that omits total but spans multiple pages.

---------

Co-authored-by: Yufeng He <[email protected]>
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* fix(proxy): handle Mistral multipart passthrough (#29927)

* fix(proxy): handle Mistral multipart passthrough

* chore: satisfy passthrough ci formatting

* test(proxy): cover Mistral passthrough in CI shard

* fix(vertex_ai): use REP host for context caching on eu/us multi-region endpoints (#29573)

Context caching built the cachedContents URL as
https://{location}-aiplatform.googleapis.com, which is an invalid host for the
eu/us multi-region endpoints and returns 404. The inference path already
resolves these to the REP host (https://aiplatform.{geo}.rep.googleapis.com)
via get_vertex_base_url(); reuse that helper in
_get_token_and_url_context_caching so caching uses the same host as inference.

Adds tests covering the eu/us multi-region cachedContents URLs (v1 and
v1beta1).

Fixes #29571

* Support per-model encrypted content affinity config (#29760)

Co-authored-by: shin-berri <[email protected]>
Co-authored-by: yuneng-jiang <[email protected]>

* fix: propagate upstream status code in proxy API exception handler (#29402)

* fix: propagate upstream status code in proxy API exception handler

When Google GenAI / Vertex returns a 404 for deprecated or missing
models via streamGenerateContent, the exception was falling through to
a generic handler that defaulted to 500. Now provider exceptions
carrying a valid HTTP status_code correctly propagate it through to
the ProxyException.

* fix: apply black formatting to common_request_processing.py

* fix: tighten status code range to 400-599 and deduplicate ProxyException raise

* fix(tests): use valid vertex_location in context caching tests

Replace "test_location" (contains underscore) with "us-central1" so tests
pass the regex validation added in get_vertex_base_url().


* feat(sdk): add xAI OAuth provider (#29866)

* Add xAI OAuth provider

* Update oauth.py

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* Fix xAI OAuth CI failures

* Add xAI OAuth coverage tests

* Move xAI OAuth coverage tests to core utils

* Address xAI OAuth review comments

* Prevent xAI OAuth api_base token exfiltration

* Treat blank xAI OAuth api keys as absent

* Wrap invalid xAI OAuth JSON responses

* Use xAI OAuth behind explicit flag

---------

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* fix(proxy) #27734 allow clearing budget_duration and team_member fields by sending null on /key/update and /team/update (#27751)

* fix(proxy): allow clearing budget_duration and team_member fields by sending null on /key/update and /team/update

Fixes #27734

Sending null for budget_duration, team_member_budget,
team_member_budget_duration, team_member_rpm_limit, or
team_member_tpm_limit via /key/update or /team/update returned 200 OK
but silently ignored the null value. The fields remained unchanged in
the database.

Root causes:
- /key/update: prepare_key_update_data() popped budget_duration from the
  update dict but never re-added it (or budget_reset_at) when the value
  was None.
- /team/update: _set_budget_reset_at() only acted when budget_duration
  was non-None, leaving a stale budget_reset_at in the DB.
- /team/update: team_member_* null values bypassed the budget table
  update entirely because should_create_budget() requires at least one
  non-None field.

* test(proxy): cover no-budget-row path in clear_team_member_budget_fields

* fix(presidio): unmask PII tokens in Anthropic native SSE streaming bytes (#30028)

* fix(presidio): unmask PII tokens in Anthropic native SSE streaming bytes

When output_parse_pii=true on the Anthropic native path (anthropic/claude-*),
response chunks arrive as raw bytes in SSE format. _stream_pii_unmasking was
yielding those bytes unchanged, so <PERSON_1> tokens were never replaced with
the original values before reaching the caller.

Add _unmask_sse_bytes_chunk to parse each data: line, find content_block_delta
/ text_delta events, and apply _unmask_pii_text before re-encoding. Wire it
into _stream_pii_unmasking so bytes chunks are unmasked when pii_tokens exist.

* fix(presidio): handle CRLF line endings and non-ASCII PII in SSE unmask

Strip trailing \r before the [DONE] guard so CRLF-terminated SSE chunks
don't bypass it and silently swallow a JSONDecodeError. Add
ensure_ascii=False to json.dumps so non-ASCII replacement values like
accented names are preserved as UTF-8 on the wire rather than being
\uXXXX-escaped. Add regression tests for both cases.

* feat(bedrock_mantle): path-aware Responses routing (/v1/responses vs /openai/v1/responses) (#29925)

* feat(bedrock_mantle): path-aware Responses routing (/v1/responses vs /openai/v1/responses)

Bedrock Mantle serves the Responses API on two upstream paths:
  - gpt frontier models (gpt-5.5 / gpt-5.4) on /openai/v1/responses
  - every other Responses-capable model (e.g. gpt-oss) on the standard /v1/responses

BedrockMantleResponsesAPIConfig gains a `use_openai_path` flag; the provider gate in
utils.py picks the path per model: openai.gpt-* (non gpt-oss) -> /openai/v1/responses;
any model declared mode=responses (price-map entry or user model_info) -> /v1/responses;
everything else returns None and keeps the existing chat-completions emulation.

Adds gpt-5.5 / gpt-5.4 price-map entries, registry wiring, and the routing-matrix tests.

* feat(bedrock_mantle): data-driven frontier routing via use_openai_responses_path

Addresses the Greptile review point that frontier detection should be a
price-map field rather than a hardcoded name match. The gate now routes a
model to /openai/v1/responses when its price-map entry declares
use_openai_responses_path, so a frontier model whose name does not follow the
openai.gpt- convention can be onboarded by JSON alone. The name-convention
check is kept as a fallback that needs no price-map entry, which preserves
zero-change routing for a future gpt-6 before its entry loads. gpt-5.5 / gpt-5.4
get the flag in both price maps. Adds tests for the data-driven flag path and
for the flag presence on the gpt-5.x entries; both branches are mutation-tested.

* test(model_prices): allow use_openai_responses_path in price-map schema

The model_prices_and_context_window.json schema validator
(test_aaamodel_prices_and_context_window_json_is_valid) enforces
additionalProperties: false, so the new use_openai_responses_path flag on the
gpt-5.5 / gpt-5.4 entries failed validation. Add it to the schema as a boolean,
alongside the other supports_* / capability flags.

* Add Tensormesh serverless models to the model cost map (#30037)

* Add Tensormesh serverless models to the model cost map

* Flag reasoning support on the Tensormesh models that expose thinking mode

* fix(proxy): invalidate stale key spend counter after budget reset or manual spend update (#30001)

* fix(proxy): reconcile stale key spend counter after budget reset

* fix(proxy): invalidate stale key spend counter after budget reset or manual spend update

* fix(proxy): remove read-time stale counter reconciliation to prevent budget bypass

* revert: undo unrelated formatting changes in enterprise directory

* test(proxy): add unit test for key spend update invalidating counter

* test(proxy): fix mocked update_data and hash token expectations in unit test

* fix(proxy): use Responses-API transformer in pass-through cost tracking (#29728)

The `elif is_responses:` branch of `openai_passthrough_handler` was
calling the chat-completions `transform_response` on a Responses API
payload. The chat-completions transformer expects `choices: [...]`
in the raw response; the Responses API uses `output: [...]` and
`usage.input_tokens` / `usage.output_tokens` (not
`prompt_tokens` / `completion_tokens`). The result was a
KeyError 'choices' deep inside `convert_to_model_response_object`,
swallowed by the surrounding `except Exception` in the handler, and
the SpendLogs row was written by the fallback path with zeroed-out
tokens, spend, and model.

This bug silently undercounts cost for every successful pass-through
call to either OpenAI's `/v1/responses` or Azure's
`/openai/v1/responses` (deployments configured for the Responses
API). Reproduced 2026-06-04 against a real Azure OpenAI Responses
API deployment proxied through LiteLLM v1.88.0.

Fix: use the dedicated
`OpenAIResponsesAPIConfig.transform_response_api_response` for the
Responses branch. This transformer already exists in LiteLLM
(`litellm/llms/openai/responses/transformation.py`) and knows the
Responses-API on-the-wire shape. `litellm.completion_cost` already
handles `ResponsesAPIResponse` natively with `call_type="responses"`,
so no downstream changes are needed.

Tests:

  test_responses_api_uses_responses_transformer_not_chat_completions
    NEW. Real regression test — exercises the openai_passthrough_handler
    with a real-shaped Responses payload (no `choices`, has `output`
    and Responses-API `usage` keys) and NO mocked `get_provider_config`.
    Pre-fix: raises KeyError 'choices' inside the chat-completions
    transformer (the bug). Post-fix: returns a ResponsesAPIResponse,
    completion_cost is called with call_type="responses" and a
    ResponsesAPIResponse instance (asserted).
    Verified to fail on un-fixed handler + pass on fixed handler
    before commit.

  test_responses_api_cost_tracking
    UPDATED. Old test mocked `get_provider_config` (no longer called
    in the responses branch post-fix). Now mocks the Responses
    transformer directly (`OpenAIResponsesAPIConfig.transform_response_api_response`)
    to test the downstream cost-calc contract.

Out of scope for this PR (separate followup):
  - Recognizing *.cognitiveservices.azure.com (the newer Azure
    OpenAI hostname) in the is_openai_*_route checks. Separate PR.

Co-authored-by: shin-berri <[email protected]>
Co-authored-by: yuneng-jiang <[email protected]>

* fix(skills): execute DB skills by matching the litellm_skill_ tool name prefix (#30116)

Skill IDs are generated as litellm_skill_<uuid> and the model-facing
tool name is the sanitized skill ID, but the post-call execution gates
in SkillsInjectionHook only ran tools whose name starts with "skill_",
so DB skills were silently returned to the client as raw tool calls.

Fixes #28122.

Co-authored-by: Cursor <[email protected]>

* fix(anthropic): synthesize content_block_start when Responses stream omits output_item.added (#30115)

* fix(team): reserve team budget raises for proxy admins on /team/update (#30030)

The caller's PERSONAL max_budget was the wrong yardstick for /team/update: a
team's spend ceiling has nothing to do with the admin's own key budget. That
comparison was an unintended side effect of reusing _check_user_team_limits()
(which exists for the /team/new path) and broke the UI, which re-sends the
unchanged budget on every save.

New behavior on /team/update for standalone teams:
- A team admin (already authorized via _verify_team_access) may freely KEEP or
  LOWER the team budget, and change models/tpm/rpm, without being gated by their
  personal limits.
- GROWING a team's spend ceiling is a budget-authority action reserved for proxy
  admins -> 403 for team admins. "Growing" covers both raising max_budget above
  the team's current finite value and removing the cap entirely (max_budget=null,
  detected via model_fields_set so an explicit null is distinguished from an
  omitted field). For a team that currently has no cap, setting a finite value is
  a restriction and is allowed.
- Org-scoped teams remain governed by _check_org_team_limits() (capped by the
  org budget).

Also reverts the #29525 existing_team_max_budget workaround in
_check_user_team_limits() back to the create-only form; /team/new still enforces
the creator's personal caps.

docs(access_control): resolve the contradiction in the team-admin section —
team admins can keep/lower the budget and manage rate limits/models, but cannot
raise the team budget (proxy-admin only).

tests: unit + behavior coverage for raise-blocked, cap-removal-blocked (team
admin), raise/removal allowed (proxy admin), uncapped-team restriction allowed,
keep/lower/resend allowed, and unchanged create-path guards.

Co-authored-by: Cursor <[email protected]>

* test(ui): data-driven App Router migration E2E smoke (default + server-root-path) (#29974)

* test(ui): add a data-driven App Router migration E2E smoke

Add a growing Playwright smoke for migrated pages: for each segment it deep-links
to the path route, asserts the URL and that the dashboard shell rendered, then
clicks off to a legacy page and asserts navigation still works. Driven by
e2e_tests/fixtures/migratedPages.ts, so adding a page is one line.

Runs in two situations against the same proxy: the default mount (npm run
e2e:migration) and a non-root SERVER_ROOT_PATH mount (npm run e2e:migration:root).
globalSetup now logs in at `${SERVER_ROOT_PATH}/ui/login` so the admin storage
state is valid under a prefix. Seeded with api-reference; append the rest as their
migrations merge.

* test(ui): support headed slow-motion + watch pauses in the migration smoke

Honor SLOWMO in the server-root-path config (the default config already did),
and add an env-gated E2E_WATCH_MS pause so a headed run lingers on each state.
Both are no-ops by default, so CI behavior is unchanged.

* test(ui): make the migration smoke a sidebar-click user journey

Rework the smoke from deep-linking to a real navigation journey: start at the
landing page, click the migrated page in the sidebar (expanding submenus for
nested items), assert the path route rendered, reload it (the check a wrong
server_root_path breaks), bounce to a legacy page and back, and — once two pages
are migrated — navigate directly between two migrated pages. Verifies via URL +
shell render, driven by the same fixture list.

* test(ui): address review on the migration smoke

Escape ROOT and segment before interpolating them into RegExp URL matchers so a
future segment containing regex metacharacters can't silently widen the match.
Make the server-root-path config fail fast when SERVER_ROOT_PATH is unset instead
of silently re-running the default mount and passing without exercising the prefix.

* test(ui): drop unused watch helper and fix stale smoke README

* test(ui): run the migration smoke under a server root path in CI

* test(ui): harden + instrument the server-root-path proxy reboot in CI

* test(ui): run the server-root-path migration smoke as its own CI job

Replace the in-place proxy reboot in e2e_ui_testing with a dedicated
e2e_ui_testing_server_root_path job that boots the proxy once with
SERVER_ROOT_PATH=/litellm, matching how every other proxy variant in the
config gets its own job rather than killing and relaunching the live proxy.

The reboot was failing deterministically: after pkill -9 and relaunch the
prefixed proxy never came back up on :4000 (connection refused), so the smoke
never ran. The readiness step that was supposed to surface the cause could
never reach its boot-log tail because CircleCI runs steps under bash -eo
pipefail and the preceding `curl -sv ... | tail` aborted the step with curl's
exit 7. Booting the proxy as the job's own background step lets any boot crash
land in that step's log instead of being swallowed.

The default e2e_ui_testing job is unchanged aside from dropping the reboot,
prefixed-readiness, and prefixed-smoke steps; the migration smoke still runs at
the root mount there via the default Playwright config.

* fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through (#24232)

* fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through

* test: mock post_call_response_headers_hook in audio speech route tests

* chore(ui): remove dead App Router route stubs under (dashboard) (#30045)

models-and-endpoints, organizations, and virtual-keys each had a page.tsx
route under (dashboard)/ that is not in MIGRATED_PAGES, so the sidebar and
deep links never resolve to it and the route is unreachable. Each was a thin
wrapper that handed the shared view empty or no-op props (empty modelData with
a no-op setModelData, hardcoded empty organizations, no-op
setUserRole/setUserEmail), so reaching one would render a degraded page in any
case. The real wrapper belongs in the PR that flips each page into
MIGRATED_PAGES, written with eyes on it and a test

This continues the dead-scaffolding cleanup from #28891. The shared components
these wrappers rendered (ModelsAndEndpointsView, OrganizationFilters) stay,
since the legacy ?page= switch in app/page.tsx and src/components still import
them

* fix(ui/mcp): reset OAuth state on create-server modal close so a prior server's token no longer leaks into the next add-server session (#30000)

* fix(ui/mcp): reset OAuth hook state on modal close so a prior server's token no longer leaks into the next add-server session

* fix(ui/mcp): clear in-flight OAuth guard on reset and reset form/tools on modal close so nothing leaks on a parent-driven dismiss

* fix(mcp): allow team access-group grants in OAuth authorize/token access check (#30041)

* fix(mcp): honor team access-group grants in OAuth authorize/token access check

* test(mcp): mock build_effective_auth_contexts in non-admin authorize tests for isolation

* docs(security): require a reproduction video for vulnerability reports (#30048) (#30063)

With AI models capable of automated vulnerability discovery now publicly
available, we expect a large increase in report volume, much of it
unverified. Requiring a video of the exploit running against a live
instance raises the bar for submissions and keeps triage focused on
reproducible issues. Reports without a video will be closed and reopened
if one is added later.

Co-authored-by: stuxf <[email protected]>

* feat(ui): add admin flag to disable in-product UI nudges for everyone (#29796)

* feat(ui): add admin flag to disable in-product UI nudges for everyone

Admins can now suppress the survey and Claude Code feedback popups for
all users via a single disable_ui_nudges UI setting, instead of relying
on each user dismissing them individually.

* fix(ui): suppress nudges while ui settings are loading

Gate nudgesDisabled on the ui-settings loading state so an admin with
disable_ui_nudges on doesn't see the survey prompt flash, and the
getInProductNudgesCall fetch doesn't fire, on a cold page load before
the flag resolves. Falls back to showing nudges if the fetch errors.

* test(ui): wrap CreateKeyPage test in QueryClientProvider

page.tsx now calls useUISettings (react-query), which needs a
QueryClient that layout.tsx supplies in production but the test did
not. Add the provider and mock getUiSettings so the query resolves.

* chore(ui): remove dead dashboard files and unused dependencies (#30047)

* chore(ui): remove dead dashboard files and unused dependencies

knip flagged seven orphaned source/config files with no importers and
five declared dependencies that nothing in the tree uses. Removing them
shrinks the dashboard bundle's source surface and keeps the manifest
honest; vite stays installed transitively via vitest, so test tooling is
unaffected.

* fix(ci): restore serverRootPath.config.ts referenced by SERVER_ROOT_PATH workflow

The dead-code sweep removed e2e_tests/serverRootPath.config.ts, but its spec
(tests/login/serverRootPathRedirect.spec.ts) and the test_server_root_path.yml
workflow step still depend on it, so the redirect e2e job failed to load a
config that no longer existed.

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593) (#30009)

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593)

After replace_model_in_jsonl, body.model is a stripped provider id. Reverse-mapping it via resolve_model_name_from_model_id is first-match on model_list and caused false 403s when multiple deployments share the same stripped name. Use target_model_names from the unified file id instead.

Co-authored-by: Cursor <[email protected]>

* fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)

Restores the reverse-lookup for the JSONL body.model fallback path so that
legacy/pre-target_model_names managed files still map stripped provider IDs
back to proxy aliases before auth. Also cleans up redundant `or None`.


* Revert "fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)"

This reverts commit 30d2e96f77ef521ccaaf2193fe554980380eb669.

---------

Co-authored-by: Cursor <[email protected]>

* Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI (#30064)

* Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI

Adds cost map entries for claude-fable-5 ($10/$50 per MTok, 1M context,
128K output, adaptive thinking only) on the Anthropic API, Bedrock
converse (base, global, and us/eu geo inference profiles at the 10%
regional premium), Vertex AI, and Azure AI (Microsoft Foundry, which
serves Fable 5 with the full 1M context window unlike Opus 4.8).

Registers anthropic.claude-fable-5 in BEDROCK_CONVERSE_MODELS, lists the
model in the setup wizard, and extends the reasoning effort e2e grid.
The Bedrock, Vertex, and Azure grid cells carry fail_reason markers
until the CI accounts are provisioned: Bedrock needs the provider data
sharing opt-in Fable 5 requires, and the Foundry resource needs a
claude-fable-5 deployment.

The first-party entry carries provider_specific_entry {us: 1.1} for the
inference_geo premium and deliberately no fast multiplier since Fable 5
has no fast mode.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Drop removed sampling params for Claude 4.7+ when drop_params is set

Fable 5, Opus 4.7, and Opus 4.8 removed sampling params: the API rejects
top_p, top_k, and any temperature other than 1 with a 400. LiteLLM was
forwarding them even with drop_params enabled because the Anthropic and
Bedrock converse transformations passed temperature/top_p through
unconditionally.

Mirror the GPT-5/o-series handling: temperature=1 still passes through,
other values and any top_p are dropped when drop_params is set, and
without drop_params a clean client-side UnsupportedParamsError tells the
caller how to opt in, instead of surfacing the raw provider error.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Drive sampling param gating from the cost map and cover top_k

Greptile review follow-ups on the sampling param fix: the restriction for
Fable 5 / Opus 4.7 / 4.8 is now declared as supports_sampling_params: false
on every affected cost map entry (perplexity excluded; that route is
OpenAI-compatible and maps sampling params upstream) and read back through
a tri-state map lookup, keeping the name check only as a fallback for
provider-routed ids whose hosted map entries predate the flag, the same
layering supports_adaptive_thinking uses. top_k bypasses map_openai_params
as a provider-specific kwarg, so it is gated at the shared
AnthropicConfig.transform_request boundary (direct, Bedrock invoke, Vertex,
Azure) and in the Bedrock converse _handle_top_k_value path, with
drop_params threaded through the converse transform helpers.

Also updates the reasoning effort grid cell count assertion for the four
Fable 5 rows added on this branch (29 x 11 cells).

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Declare supports_sampling_params in the cost map schema

The model map validation schema uses additionalProperties: false, so the
new flag must be declared for the 28 entries that carry it; this was the
one failing job (misc / Run tests) on the previous commit.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* fix(bedrock): gate top_k=0 on converse to match Anthropic boundary

Truthiness check let top_k=0 silently disappear on models that removed
sampling params, while AnthropicConfig.transform_request treats 0 as
present and raises UnsupportedParamsError (or drops when drop_params is
set). Switch to 'is not None' so converse, direct Anthropic, invoke,
Vertex, and Azure all behave the same for top_k=0.

---------

Co-authored-by: Cursor Agent <[email protected]>

* fix(anthropic): avoid index -1 content_block_delta in messages stream

When a /v1/messages request is routed through the Responses API
adapter, AnthropicResponsesStreamWrapper only emits content_block_start
on response.output_item.added. Some upstreams (LMStudio for example)
never send that event, so the text delta handler fell back to
_current_block_index, which starts at -1, and clients received
content_block_delta events with index -1 and no preceding
content_block_start. Anthropic SDKs then fail with "text part -1 not
found"

The text delta handler now synthesizes a content_block_start with a
fresh block index whenever the delta references an unregistered item_id
or no block is open yet, and registers the item_id so follow-up deltas
reuse the same index

Addresses the /v1/messages defect in #27442

* Make test sys.path shim resolve relative to the file, not the CWD

os.path.abspath("../../../../../../..") depends on where pytest is
invoked from; anchoring on os.path.dirname(__file__) makes the import
work from any working directory. Also corrects the depth: the repo root
is six levels above this file, not seven.

---------

Co-authored-by: milan-berri <[email protected]>
Co-authored-by: Cursor <[email protected]>
Co-authored-by: ryan-crabbe-berri <[email protected]>
Co-authored-by: michelligabriele <[email protected]>
Co-authored-by: tin-berri <[email protected]>
Co-authored-by: yuneng-jiang <[email protected]>
Co-authored-by: stuxf <[email protected]>
Co-authored-by: Sameer Kankute <[email protected]>
Co-authored-by: Mateo Wang <[email protected]>

* fix: enable compact-2026-01-12 beta header for vertex_ai provider (#30114)

* fix(team): reserve team budget raises for proxy admins on /team/update (#30030)

The caller's PERSONAL max_budget was the wrong yardstick for /team/update: a
team's spend ceiling has nothing to do with the admin's own key budget. That
comparison was an unintended side effect of reusing _check_user_team_limits()
(which exists for the /team/new path) and broke the UI, which re-sends the
unchanged budget on every save.

New behavior on /team/update for standalone teams:
- A team admin (already authorized via _verify_team_access) may freely KEEP or
  LOWER the team budget, and change models/tpm/rpm, without being gated by their
  personal limits.
- GROWING a team's spend ceiling is a budget-authority action reserved for proxy
  admins -> 403 for team admins. "Growing" covers both raising max_budget above
  the team's current finite value and removing the cap entirely (max_budget=null,
  detected via model_fields_set so an explicit null is distinguished from an
  omitted field). For a team that currently has no cap, setting a finite value is
  a restriction and is allowed.
- Org-scoped teams remain governed by _check_org_team_limits() (capped by the
  org budget).

Also reverts the #29525 existing_team_max_budget workaround in
_check_user_team_limits() back to the create-only form; /team/new still enforces
the creator's personal caps.

docs(access_control): resolve the contradiction in the team-admin section —
team admins can keep/lower the budget and manage rate limits/models, but cannot
raise the team budget (proxy-admin only).

tests: unit + behavior coverage for raise-blocked, cap-removal-blocked (team
admin), raise/removal allowed (proxy admin), uncapped-team restriction allowed,
keep/lower/resend allowed, and unchanged create-path guards.

Co-authored-by: Cursor <[email protected]>

* test(ui): data-driven App Router migration E2E smoke (default + server-root-path) (#29974)

* test(ui): add a data-driven App Router migration E2E smoke

Add a growing Playwright smoke for migrated pages: for each segment it deep-links
to the path route, asserts the URL and that the dashboard shell rendered, then
clicks off to a legacy page and asserts navigation still works. Driven by
e2e_tests/fixtures/migratedPages.ts, so adding a page is one line.

Runs in two situations against the same proxy: the default mount (npm run
e2e:migration) and a non-root SERVER_ROOT_PATH mount (npm run e2e:migration:root).
globalSetup now logs in at `${SERVER_ROOT_PATH}/ui/login` so the admin storage
state is valid under a prefix. Seeded with api-reference; append the rest as their
migrations merge.

* test(ui): support headed slow-motion + watch pauses in the migration smoke

Honor SLOWMO in the server-root-path config (the default config already did),
and add an env-gated E2E_WATCH_MS pause so a headed run lingers on each state.
Both are no-ops by default, so CI behavior is unchanged.

* test(ui): make the migration smoke a sidebar-click user journey

Rework the smoke from deep-linking to a real navigation journey: start at the
landing page, click the migrated page in the sidebar (expanding submenus for
nested items), assert the path route rendered, reload it (the check a wrong
server_root_path breaks), bounce to a legacy page and back, and — once two pages
are migrated — navigate directly between two migrated pages. Verifies via URL +
shell render, driven by the same fixture list.

* test(ui): address review on the migration smoke

Escape ROOT and segment before interpolating them into RegExp URL matchers so a
future segment containing regex metacharacters can't silently widen the match.
Make the server-root-path config fail fast when SERVER_ROOT_PATH is unset instead
of silently re-running the default mount and passing without exercising the prefix.

* test(ui): drop unused watch helper and fix stale smoke README

* test(ui): run the migration smoke under a server root path in CI

* test(ui): harden + instrument the server-root-path proxy reboot in CI

* test(ui): run the server-root-path migration smoke as its own CI job

Replace the in-place proxy reboot in e2e_ui_testing with a dedicated
e2e_ui_testing_server_root_path job that boots the proxy once with
SERVER_ROOT_PATH=/litellm, matching how every other proxy variant in the
config gets its own job rather than killing and relaunching the live proxy.

The reboot was failing deterministically: after pkill -9 and relaunch the
prefixed proxy never came back up on :4000 (connection refused), so the smoke
never ran. The readiness step that was supposed to surface the cause could
never reach its boot-log tail because CircleCI runs steps under bash -eo
pipefail and the preceding `curl -sv ... | tail` aborted the step with curl's
exit 7. Booting the proxy as the job's own background step lets any boot crash
land in that step's log instead of being swallowed.

The default e2e_ui_testing job is unchanged aside from dropping the reboot,
prefixed-readiness, and prefixed-smoke steps; the migration smoke still runs at
the root mount there via the default Playwright config.

* fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through (#24232)

* fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through

* test: mock post_call_response_headers_hook in audio speech route tests

* chore(ui): remove dead App Router route stubs under (dashboard) (#30045)

models-and-endpoints, organizations, and virtual-keys each had a page.tsx
route under (dashboard)/ that is not in MIGRATED_PAGES, so the sidebar and
deep links never resolve to it and the route is unreachable. Each was a thin
wrapper that handed the shared view empty or no-op props (empty modelData with
a no-op setModelData, hardcoded empty organizations, no-op
setUserRole/setUserEmail), so reaching one would render a degraded page in any
case. The real wrapper belongs in the PR that flips each page into
MIGRATED_PAGES, written with eyes on it and a test

This continues the dead-scaffolding cleanup from #28891. The shared components
these wrappers rendered (ModelsAndEndpointsView, OrganizationFilters) stay,
since the legacy ?page= switch in app/page.tsx and src/components still import
them

* fix(ui/mcp): reset OAuth state on create-server modal close so a prior server's token no longer leaks into the next add-server session (#30000)

* fix(ui/mcp): reset OAuth hook state on modal close so a prior server's token no longer leaks into the next add-server session

* fix(ui/mcp): clear in-flight OAuth guard on reset and reset form/tools on modal close so nothing leaks on a parent-driven dismiss

* fix(mcp): allow team access-group grants in OAuth authorize/token access check (#30041)

* fix(mcp): honor team access-group grants in OAuth authorize/token access check

* test(mcp): mock build_effective_auth_contexts in non-admin authorize tests for isolation

* docs(security): require a reproduction video for vulnerability reports (#30048) (#30063)

With AI models capable of automated vulnerability discovery now publicly
available, we expect a large increase in report volume, much of it
unverified. Requiring a video of the exploit running against a live
instance raises the bar for submissions and keeps triage focused on
reproducible issues. Reports without a video will be closed and reopened
if one is added later.

Co-authored-by: stuxf <[email protected]>

* feat(ui): add admin flag to disable in-product UI nudges for everyone (#29796)

* feat(ui): add admin flag to disable in-product UI nudges for everyone

Admins can now suppress the survey and Claude Code feedback popups for
all users via a single disable_ui_nudges UI setting, instead of relying
on each user dismissing them individually.

* fix(ui): suppress nudges while ui settings are loading

Gate nudgesDisabled on the ui-settings loading state so an admin with
disable_ui_nudges on doesn't see the survey prompt flash, and the
getInProductNudgesCall fetch doesn't fire, on a cold page load before
the flag resolves. Falls back to showing nudges if the fetch errors.

* test(ui): wrap CreateKeyPage test in QueryClientProvider

page.tsx now calls useUISettings (react-query), which needs a
QueryClient that layout.tsx supplies in production but the test did
not. Add the provider and mock getUiSettings so the query resolves.

* chore(ui): remove dead dashboard files and unused dependencies (#30047)

* chore(ui): remove dead dashboard files and unused dependencies

knip flagged seven orphaned source/config files with no importers and
five declared dependencies that nothing in the tree uses. Removing them
shrinks the dashboard bundle's source surface and keeps the manifest
honest; vite stays installed transitively via vitest, so test tooling is
unaffected.

* fix(ci): restore serverRootPath.config.ts referenced by SERVER_ROOT_PATH workflow

The dead-code sweep removed e2e_tests/serverRootPath.config.ts, but its spec
(tests/login/serverRootPathRedirect.spec.ts) and the test_server_root_path.yml
workflow step still depend on it, so the redirect e2e job failed to load a
config that no longer existed.

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593) (#30009)

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593)

After replace_model_in_jsonl, body.model is a stripped provider id. Reverse-mapping it via resolve_model_name_from_model_id is first-match on model_list and caused false 403s when multiple deployments share the same stripped name. Use target_model_names from the unified file id instead.

Co-authored-by: Cursor <[email protected]>

* fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)

Restores the reverse-lookup for the JSONL body.model fallback path so that
legacy/pre-target_model_names managed files still map stripped provider IDs
back to proxy aliases before auth. Also cleans up redundant `or None`.


* Revert "fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)"

This reverts commit 30d2e96f77ef521ccaaf2193fe554980380eb669.

---------

Co-authored-by: Cursor <[email protected]>

* Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI (#30064)

* Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI

Adds cost map entries for claude-fable-5 ($10/$50 per MTok, 1M context,
128K output, adaptive thinking only) on the Anthropic API, Bedrock
converse (base, global, and us/eu geo inference profiles at the 10%
regional premium), Vertex AI, and Azure AI (Microsoft Foundry, which
serves Fable 5 with the full 1M context window unlike Opus 4.8).

Registers anthropic.claude-fable-5 in BEDROCK_CONVERSE_MODELS, lists the
model in the setup wizard, and extends the reasoning effort e2e grid.
The Bedrock, Vertex, and Azure grid cells carry fail_reason markers
until the CI accounts are provisioned: Bedrock needs the provider data
sharing opt-in Fable 5 requires, and the Foundry resource needs a
claude-fable-5 deployment.

The first-party entry carries provider_specific_entry {us: 1.1} for the
inference_geo premium and deliberately no fast multiplier since Fable 5
has no fast mode.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Drop removed sampling params for Claude 4.7+ when drop_params is set

Fable 5, Opus 4.7, and Opus 4.8 removed sampling params: the API rejects
top_p, top_k, and any temperature other than 1 with a 400. LiteLLM was
forwarding them even with drop_params enabled because the Anthropic and
Bedrock converse transformations passed temperature/top_p through
unconditionally.

Mirror the GPT-5/o-series handling: temperature=1 still passes through,
other values and any top_p are dropped when drop_params is set, and
without drop_params a clean client-side UnsupportedParamsError tells the
caller how to opt in, instead of surfacing the raw provider error.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Drive sampling param gating from the cost map and cover top_k

Greptile review follow-ups on the sampling param fix: the restriction for
Fable 5 / Opus 4.7 / 4.8 is now declared as supports_sampling_params: false
on every affected cost map entry (perplexity excluded; that route is
OpenAI-compatible and maps sampling params upstream) and read back through
a tri-state map lookup, keeping the name check only as a fallback for
provider-routed ids whose hosted map entries predate the flag, the same
layering supports_adaptive_thinking uses. top_k bypasses map_openai_params
as a provider-specific kwarg, so it is gated at the shared
AnthropicConfig.transform_request boundary (direct, Bedrock invoke, Vertex,
Azure) and in the Bedrock converse _handle_top_k_value path, with
drop_params threaded through the converse transform helpers.

Also updates the reasoning effort grid cell count assertion for the four
Fable 5 rows added on this branch (29 x 11 cells).

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Declare supports_sampling_params in the cost map schema

The model map validation schema uses additionalProperties: false, so the
new flag must be declared for the 28 entries that carry it; this was the
one failing job (misc / Run tests) on the previous commit.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* fix(bedrock): gate top_k=0 on converse to match Anthropic boundary

Truthiness check let top_k=0 silently disappear on models that removed
sampling params, while AnthropicConfig.transform_request treats 0 as
present and raises UnsupportedParamsError (or drops when drop_params is
set). Switch to 'is not None' so converse, direct Anthropic, invoke,
Vertex, and Azure all behave the same for top_k=0.

---------

Co-authored-by: Cursor Agent <[email protected]>

* fix: enable compact-2026-01-12 beta header for vertex_ai provider

The vertex_ai block in anthropic_beta_headers_config.json mapped
compact-2026-01-12 to null, so update_headers_with_filtered_beta
stripped the header before the request reached Vertex while the
compact_20260112 context edit stayed in the body, and Vertex rejected
the request with HTTP 400. Vertex rawPredict accepts the header, and
the bedrock and databricks blocks already forward it. Mirrors #21867,
which enabled context-1m-2025-08-07 for vertex_ai the same way.

Fixes #27290.

---------

Co-authored-by: milan-berri <[email protected]>
Co-authored-by: Cursor <[email protected]>
Co-authored-by: ryan-crabbe-berri <[email protected]>
Co-authored-by: michelligabriele <[email protected]>
Co-authored-by: tin-berri <[email protected]>
Co-authored-by: yuneng-jiang <[email protected]>
Co-authored-by: stuxf <[email protected]>
Co-authored-by: Sameer Kankute <[email protected]>
Co-authored-by: Mateo Wang <[email protected]>

* fix(proxy): coerce litellm_settings.max_budget env var to float (#30113)

* fix(team): reserve team budget raises for proxy admins on /team/update (#30030)

The caller's PERSONAL max_budget was the wrong yardstick for /team/update: a
team's spend ceiling has nothing to do with the admin's own key budget. That
comparison was an unintended side effect of reusing _check_user_team_limits()
(which exists for the /team/new path) and broke the UI, which re-sends the
unchanged budget on every save.

New behavior on /team/update for standalone teams:
- A team admin (already authorized via _verify_team_access) may freely KEEP or
  LOWER the team budget, and change models/tpm/rpm, without being gated by their
  personal limits.
- GROWING a team's spend ceiling is a budget-authority action reserved for proxy
  admins -> 403 for team admins. "Growing" covers both raising max_budget above
  the team's current finite value and removing the cap entirely (max_budget=null,
  detected via model_fields_set so an explicit null is distinguished from an
  omitted field). For a team that currently has no cap, setting a finite value is
  a restriction and is allowed.
- Org-scoped teams remain governed by _check_org_team_limits() (capped by the
  org budget).

Also reverts the #29525 existing_team_max_budget workaround in
_check_user_team_limits() back to the create-only form; /team/new still enforces
the creator's personal caps.

docs(access_control): resolve the contradiction in the team-admin section —
team admins can keep/lower the budget and manage rate limits/models, but cannot
raise the team budget (proxy-admin only).

tests: unit + behavior coverage for raise-blocked, cap-removal-blocked (team
admin), raise/removal allowed (proxy admin), uncapped-team restriction allowed,
keep/lower/resend allowed, and unchanged create-path guards.

Co-authored-by: Cursor <[email protected]>

* test(ui): data-driven App Router migration E2E smoke (default + server-root-path) (#29974)

* test(ui): add a data-driven App Router migration E2E smoke

Add a growing Playwright smoke for migrated pages: for each segment it deep-links
to the path route, asserts the URL and that the dashboard shell rendered, then
clicks off to a legacy page and asserts navigation still works. Driven by
e2e_tests/fixtures/migratedPages.ts, so adding a page is one line.

Runs in two situations against the same proxy: the default mount (npm run
e2e:migration) and a non-root SERVER_ROOT_PATH mount (npm run e2e:migration:root).
globalSetup now logs in at `${SERVER_ROOT_PATH}/ui/login` so the admin storage
state is valid under a prefix. Seeded with api-reference; append the rest as their
migrations merge.

* test(ui): support headed slow-motion + watch pauses in the migration smoke

Honor SLOWMO in the server-root-path config (the default config already did),
and add an env-gated E2E_WATCH_MS pause so a headed run lingers on each state.
Both are no-ops by default, so CI behavior is unchanged.

* test(ui): make the migration smoke a sidebar-click user journey

Rework the smoke from deep-linking to a real navigation journey: start at the
landing page, click the migrated page in the sidebar (expanding submenus for
nested items), assert the path route rendered, reload it (the check a wrong
server_root_path breaks), bounce to a legacy page and back, and — once two pages
are migrated — navigate directly between two migrated pages. Verifies via URL +
shell render, driven by the same fixture list.

* test(ui): address review on the migration smoke

Escape ROOT and segment before interpolating them into RegExp URL matchers so a
future segment containing regex metacharacters can't silently widen the match.
Make the server-root-path config fail fast when SERVER_ROOT_PATH is unset instead
of silently re-running the default mount and passing without exercising the prefix.

* test(ui): drop unused watch helper and fix stale smoke README

* test(ui): run the migration smoke under a server root path in CI

* test(ui): harden + instrument the server-root-path proxy reboot in CI

* test(ui): run the server-root-path migration smoke as its own CI job

Replace the in-place proxy reboot in e2e_ui_testing with a dedicated
e2e_ui_testing_server_root_path job that boots the proxy once with
SERVER_ROOT_PATH=/litellm, matching how every other proxy variant in the
config gets its own job rather than killing and relaunching the live proxy.

The reboot was failing deterministically: after pkill -9 and relaunch the
prefixed proxy never came back up on :4000 (connection refused), so the smoke
never ran. The readiness step that was supposed to surface the cause could
never reach its boot-log tail because CircleCI runs steps under bash -eo
pipefail and the preceding `curl -sv ... | tail` aborted the step with curl's
exit 7. Booting the proxy as the job's own background step lets any boot crash
land in that step's log instead of being swallowed.

The default e2e_ui_testing job is unchanged aside from dropping the reboot,
prefixed-readiness, and prefixed-smoke steps; the migration smoke still runs at
the root mount there via the default Playwright config.

* fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through (#24232)

* fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through

* test: mock post_call_response_headers_hook in audio speech route tests

* chore(ui): remove dead App Router route stubs under (dashboard) (#30045)

models-and-endpoints, organizations, and virtual-keys each had a page.tsx
route under (dashboard)/ that is not in MIGRATED_PAGES, so the sidebar and
deep links never resolve to it and the route is unreachable. Each was a thin
wrapper that handed the shared view empty or no-op props (empty modelData with
a no-op setModelData, hardcoded empty organizations, no-op
setUserRole/setUserEmail), so reaching one would render a degraded page in any
case. The real wrapper belongs in the PR that flips each page into
MIGRATED_PAGES, written with eyes on it and a test

This continues the dead-scaffolding cleanup from #28891. The shared components
these wrappers rendered (ModelsAndEndpointsView, OrganizationFilters) stay,
since the legacy ?page= switch in app/page.tsx and src/components still import
them

* fix(ui/mcp): reset OAuth state on create-server modal close so a prior server's token no longer leaks into the next add-server session (#30000)

* fix(ui/mcp): reset OAuth hook state on modal close so a prior server's token no longer leaks into the next add-server session

* fix(ui/mcp): clear in-flight OAuth guard on reset and reset form/tools on modal close so nothing leaks on a parent-driven dismiss

* fix(mcp): allow team access-group grants in OAuth authorize/token access check (#30041)

* fix(mcp): honor team access-group grants in OAuth authorize/token access check

* test(mcp): mock build_effective_auth_contexts in non-admin authorize tests for isolation

* docs(security): require a reproduction video for vulnerability reports (#30048) (#30063)

With AI models capable of automated vulnerability discovery now publicly
available, we expect a large increase in report volume, much of it
unverified. Requiring a video of the exploit running against a live
instance raises the bar for submissions and keeps triage focused on
reproducible issues. Reports without a video will be closed and reopened
if one is added later.

Co-authored-by: stuxf <[email protected]>

* feat(ui): add admin flag to disable in-product UI nudges for everyone (#29796)

* feat(ui): add admin flag to disable in-product UI nudges for everyone

Admins can now suppress the survey and Claude Code feedback popups for
all users via a single disable_ui_nudges UI setting, instead of relying
on each user dismissing them individually.

* fix(ui): suppress nudges while ui settings are loading

Gate nudgesDisabled on the ui-settings loading state so an admin with
disable_ui_nudges on doesn't see the survey prompt flash, and the
getInProductNudgesCall fetch doesn't fire, on a cold page load before
the flag resolves. Falls back to showing nudges if the fetch errors.

* test(ui): wrap CreateKeyPage test in QueryClientProvider

page.tsx now calls useUISettings (react-query), which needs a
QueryClient that layout.tsx supplies in production but the test did
not. Add the provider and mock getUiSettings so the query resolves.

* chore(ui): remove dead dashboard files and unused dependencies (#30047)

* chore(ui): remove dead dashboard files and unused dependencies

knip flagged seven orphaned source/config files with no importers and
five declared dependencies that nothing in the tree uses. Removing them
shrinks the dashboard bundle's source surface and keeps the manifest
honest; vite stays installed transitively via vitest, so test tooling is
unaffected.

* fix(ci): restore serverRootPath.config.ts referenced by SERVER_ROOT_PATH workflow

The dead-code sweep removed e2e_tests/serverRootPath.config.ts, but its spec
(tests/login/serverRootPathRedirect.spec.ts) and the test_server_root_path.yml
workflow step still depend on it, so the redirect e2e job failed to load a
config that no longer existed.

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593) (#30009)

* fix(proxy): authorize batch files using upload target_model_names (LIT-3593)

After replace_model_in_jsonl, body.model is a stripped provider id. Reverse-mapping it via resolve_model_name_from_model_id is first-match on model_list and caused false 403s when multiple deployments share the same stripped name. Use target_model_names from the unified file id instead.

Co-authored-by: Cursor <[email protected]>

* fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)

Restores the reverse-lookup for the JSONL body.model fallback path so that
legacy/pre-target_model_names managed files still map stripped provider IDs
back to proxy aliases before auth. Also cleans up redundant `or None`.


* Revert "fix(proxy): restore resolve_model_name_from_model_id for JSONL fallback path (LIT-3593)"

This reverts commit 30d2e96f77ef521ccaaf2193fe554980380eb669.

---------

Co-authored-by: Cursor <[email protected]>

* Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI (#30064)

* Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI

Adds cost map entries for claude-fable-5 ($10/$50 per MTok, 1M context,
128K output, adaptive thinking only) on the Anthropic API, Bedrock
converse (base, global, and us/eu geo inference profiles at the 10%
regional premium), Vertex AI, and Azure AI (Microsoft Foundry, which
serves Fable 5 with the full 1M context window unlike Opus 4.8).

Registers anthropic.claude-fable-5 in BEDROCK_CONVERSE_MODELS, lists the
model in the setup wizard, and extends the reasoning effort e2e grid.
The Bedrock, Vertex, and Azure grid cells carry fail_reason markers
until the CI accounts are provisioned: Bedrock needs the provider data
sharing opt-in Fable 5 requires, and the Foundry resource needs a
claude-fable-5 deployment.

The first-party entry carries provider_specific_entry {us: 1.1} for the
inference_geo premium and deliberately no fast multiplier since Fable 5
has no fast mode.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Drop removed sampling params for Claude 4.7+ when drop_params is set

Fable 5, Opus 4.7, and Opus 4.8 removed sampling params: the API rejects
top_p, top_k, and any temperature other than 1 with a 400. LiteLLM was
forwarding them even with drop_params enabled because the Anthropic and
Bedrock converse transformations passed temperature/top_p through
unconditionally.

Mirror the GPT-5/o-series handling: temperature=1 still passes through,
other values and any top_p are dropped when drop_params is set, and
without drop_params a clean client-side UnsupportedParamsError tells the
caller how to opt in, instead of surfacing the raw provider error.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Drive sampling param gating from the cost map and cover top_k

Greptile review follow-ups on the sampling param fix: the restriction for
Fable 5 / Opus 4.7 / 4.8 is now declared as supports_sampling_params: false
on every affected cost map entry (perplexity excluded; that route is
OpenAI-compatible and maps sampling params upstream) and read back through
a tri-state map lookup, keeping the name check only as a fallback for
provider-routed ids whose hosted map entries predate the flag, the same
layering supports_adaptive_thinking uses. top_k bypasses map_openai_params
as a provider-specific kwarg, so it is gated at the shared
AnthropicConfig.transform_request boundary (direct, Bedrock invoke, Vertex,
Azure) and in the Bedrock converse _handle_top_k_value path, with
drop_params threaded through the converse transform helpers.

Also updates the reasoning effort grid cell count assertion for the four
Fable 5 rows added on this branch (29 x 11 cells).

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* Declare supports_sampling_params in the cost map schema

The model map validation schema uses additionalProperties: false, so the
new flag must be declared for the 28 entries that carry it; this was the
one failing job (misc / Run tests) on the previous commit.

https://claude.ai/code/session_01MZarYYT3aS7DxaNjoax6Gm

* fix(bedrock): gate top_k=0 on converse to match Anthropic boundary

Truthiness check let top_k=0 silently disappear on models that removed
sampling params, while AnthropicConfig.transform_request treats 0 as
present and raises UnsupportedParamsError (or drops when drop_params is
set). Switch to 'is not None' so converse, direct Anthropic, invoke,
Vertex, and Azure all behave the same for top_k=0.

---------

Co-authored-by: Cursor Agent <[email protected]>

* fix(proxy): coerce litellm_settings.max_budget env var to float

When max_budget is set in litellm_settings via os.environ/MAX_BUDGET,
the env var resolves to a string and the generic setattr branch in
ProxyConfig.load_config stored it as-is, so the startup check
litellm.max_budget > 0 raised TypeError. The earlier fix (#23855) only
covered the CLI initialize() path. Coerce the value to float in the
settings loop, matching the existing max_internal_user_budget handling.

Fixes #26696.

---------

Co-authored-by: milan-berri <[email protected]>
Co-authored-by: Cursor <[email protected]>
Co-authored-by: ryan-crabbe-berri <[email protected]>
Co-authored-by: michelligabriele <[email protected]>
Co-authored-by: tin-berri <[email protected]>
Co-authored-by: yuneng-jiang <[email protected]>
Co-authored-by: stuxf <[email protected]>
Co-authored-by: Sameer Kankute <[email protected]>
Co-authored-by: Mateo Wang <[email protected]>

* fix(router): don't drop bedrock pass-through deployments using IAM credentials (#30111)

* Fix Bedrock passthrough deployment dropped when using IAM credentials

Bedrock deployments with use_in_pass_through enabled and IAM/OIDC auth
(aws_role_name, no api_key) hit the generic pass-through branch in
Router._initialize_deployment_for_pass_through, which calls
set_pass_through_credentials and raises "api_key is required". The
exception drops the deployment from the router entirely, breaking both
passthrough and normal routing for that model.

Skip the credential store write when no api_key is set; the bedrock
passthrough route resolves AWS credentials at request time via
BedrockConverseLLM.get_credentials(), not the passthrough credential
store, so there is nothing to register here.

Fixes #27728.

* Reset passthrough credentials singleton before api_key credential test

The test reads the module-level passthrough_endpoint_router singleton,
so a stale "openai" entry written by an earlier test in the same
process could make the assertion pass without exercising the code path.
Clearing the credentials dict up front makes the test order-independent.

* fix(sdk): stop mirroring reasoning_content in provider_specific_fields (#30110)

The dict-to-response conversion path mirrored reasoning_content into
provider_specific_fields, while live provider transforms (Anthropic's
_build_provider_specific_fields) only set it top-level on the Message.
Cache-replayed messages therefore serialized differently from live
ones, breaking disk cache key stability for multi-turn conversations
with extended thinking.

The mirror was added for DeepSeek before Message.reasoning_content
existed as a top-level attribute. The top-level field is still set by
the converter, so DeepSeek's request-side promotion is unaffected.

Fixes #27337.

* fix(mcp): coerce mcp_server_cost_info values to float at ingest (#30109)

* fix(mcp): coerce mcp_server_cost_info values to float at ingest

YAML 1.1 parses scientific notation without a decimal point
(e.g. 7e-05) as a string, and MCPServerCostInfo is a TypedDict with no
runtime validation, so a string-typed default_cost_per_query from
config.yaml flowed through the proxy untouched and crashed the MCP
server settings page with '.toFixed is not a function'. Normalize
mcp_server_cost_info on both the config and DB load paths, dropping
non-numeric values with a warning instead of failing the server load.

Fixes #27097.

* fix(mcp): drop non-numeric default_cost_per_query instead of nulling it

Keeping the key with a None value still exposes a null to the UI,
which can crash .toFixed formatting when the consumer checks key
existence rather than truthiness. Delete the key on coercion failure,
matching how non-numeric per-tool cost entries are already omitted.

* fix(proxy): count embedding and text completion tokens toward TPM limits (#30105)

* fix(proxy): count embedding and text completion tokens toward TPM limits

The parallel request limiters only read token usage off ModelResponse,
so EmbeddingResponse and TextCompletionResponse objects left
total_tokens at 0 and the per key, user, team, and end user TPM
counters never incremented. Requests to /v1/embeddings and
/v1/completions were effectively free against any tpm_limit. In the v3
limiter this was worse: the post-call reconciliation computed actual
usage as 0 and refunded the pre-call reservation made at request time.

Broaden the isinstance checks to accept EmbeddingResponse and
TextCompletionResponse, which both expose a Usage object, at the four
per-scope sites in parallel_request_limiter.py and at the usage
extraction in parallel_request_limiter_v3.py. ResponsesAPIResponse was
already covered in v3 via BaseLiteLLMOpenAIResponseObject.

Fixes #27738.

* test(proxy): cover v1 limiter TPM counting for embedding and text completion responses

Exercise the broadened isinstance sites in parallel_request_limiter.py
by asserting that async_log_success_event adds total_tokens to the per
key, user, team, and end user TPM counters for EmbeddingResponse and
TextCompletionResponse objects. The counters are pre-seeded at zero so
the assertion is exactly the increment; on the pre-fix code these
responses left total_tokens at 0 and the test fails.

* fix(openai): forward client headers on the text completion path (#30103)

* fix(openai): forward client headers on the text completion path

litellm.completion() merges caller headers with extra_headers, but the
text-completion-openai branch never passed the merged dict to
openai_text_completions.completion(), and the handler only used its
headers argument for logging. Pass the merged headers through the call
site and set them as extra_headers on the outgoing request, mirroring
the chat completion handler, so x-* client headers forwarded by the
proxy reach the provider on /v1/completions.

Fixes #27410.

* Drop redundant extra_headers assignment and fix test module collision

completion() merges extra_headers into headers before the
text-completion-openai branch, and the handler now sets the merged
headers as extra_headers on the request, so the branch-local
optional_params["extra_headers"] assignment was a dead duplicate.
Removing it keeps the assignment in one place while both entry paths
(litellm.text_completion and direct handler callers) still forward
headers; a new regression test pins the extra_headers kwarg path.

Also rename the test module to test_completion_handler.py since its
basename collided with tests/test_litellm/llms/bedrock/batches/
test_handler.py and broke pytest collection.

* fix(bedrock): route Anthropic-shape count_tokens to InvokeModel and base64-encode the body (#30102)

* fix(bedrock): route Anthropic-shape count_tokens to InvokeModel

POST /v1/messages/count_tokens with Anthropic content blocks
({"type": "text"|"tool_use"|...}) was routed to the Converse input of
the Bedrock CountTokens API. The Converse transform copies list content
through verbatim, so Bedrock rejected the request with a 400 and the
caller silently fell back to the local tokenizer, returning counts that
can be off by ~50% on tool-heavy payloads.

_detect_input_type now routes messages whose content blocks carry a
"type" key (Anthropic shape) to the invokeModel input, which forwards
the body verbatim. The invokeModel body is now base64-encoded as the
CountTokens API requires (InvokeModelTokensRequest.body is a
base64-encoded blob), and Anthropic Messages bodies get the
anthropic_version and max_tokens fields Bedrock validates against.

Fixes #27632.

* refactor(bedrock): name the CountTokens max_tokens placeholder

Replace the magic 1024 with a module-level
DEFAULT_ANTHROPIC_INVOKE_MODEL_MAX_TOKENS constant so the intent is
explicit and there is a single place to update if Bedrock's InvokeModel
schema ever changes. Module-local rather than litellm/constants.py
because the value is only a schema-validation placeholder for token
counting, not a user-tunable generation default.

* Add above-512k pricing tier for MiniMax-M3 and correct its base rates (#30095)

* Add above-512k pricing tier support for MiniMax-M3

MiniMax-M3 doubles its per-token rates once a prompt exceeds 512k
input tokens. The tiered cost parser already handles arbitrary
thresholds, but get_model_info only copies whitelisted keys from
ModelIn…

…to v1.90.0 (#232)

This PR contains the following updates:

| Package | Update | Change |
|---|---|---|
| [https://github.com/BerriAI/litellm.git](https://github.com/BerriAI/litellm) | minor | `v1.89.4` → `v1.90.0` |

---

### Release Notes

<details>
<summary>BerriAI/litellm (https://github.com/BerriAI/litellm.git)</summary>

### [`v1.90.0`](https://github.com/BerriAI/litellm/releases/tag/v1.90.0)

[Compare Source](BerriAI/litellm@v1.89.4...v1.90.0-rc.1)

#### Verify Docker Image Signature

All LiteLLM Docker images are signed with [cosign](https://docs.sigstore.dev/cosign/overview/). Every release is signed with the same key introduced in [commit `0112e53`](BerriAI/litellm@0112e53).

**Verify using the pinned commit hash (recommended):**

A commit hash is cryptographically immutable, so this is the strongest way to ensure you are using the original signing key:

```bash
cosign verify \
  --key https://raw.githubusercontent.com/BerriAI/litellm/0112e53046018d726492c814b3644b7d376029d0/cosign.pub \
  ghcr.io/berriai/litellm:v1.90.0
```

**Verify using the release tag (convenience):**

Tags are protected in this repository and resolve to the same key. This option is easier to read but relies on tag protection rules:

```bash
cosign verify \
  --key https://raw.githubusercontent.com/BerriAI/litellm/v1.90.0/cosign.pub \
  ghcr.io/berriai/litellm:v1.90.0
```

Expected output:

```
The following checks were performed on each of these signatures:
  - The cosign claims were validated
  - The signatures were verified against the specified public key
```

***

#### What's Changed

- fix(responses-bridge): map system-only chat request to system input item by [@&#8203;milan-berri](https://github.com/milan-berri) in [#&#8203;29817](BerriAI/litellm#29817)
- feat(bedrock): forward strict and additionalProperties to Converse toolSpec by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;29814](BerriAI/litellm#29814)
- fix(mcp): highlight MCP cards red when the logged-in user is missing per-user env vars by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;29856](BerriAI/litellm#29856)
- feat(ui): add budget duration to edit team member form by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;29717](BerriAI/litellm#29717)
- fix(ui): make workflow runs page fill full width by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29868](BerriAI/litellm#29868)
- feat: standardize rate limit errors with category, rate\_limit\_type, model, and llm\_provider fields by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;27687](BerriAI/litellm#27687)
- fix(ui): default guardrails page to the Guardrails tab by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29872](BerriAI/litellm#29872)
- docs(readme): add Deploy on AWS/GCP Terraform section and fix deploy button rendering by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;29879](BerriAI/litellm#29879)
- refactor(bedrock): build Converse toolSpec via a BedrockToolSpec dict subclass by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;29869](BerriAI/litellm#29869)
- feat(litellm): add models and repository layers by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;29686](BerriAI/litellm#29686)
- feat(ui): include internal routes in the dashboard's generated OpenAPI types by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;29885](BerriAI/litellm#29885)
- feat(proxy): publish /v2/model/info in Swagger OpenAPI spec by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;29900](BerriAI/litellm#29900)
- refactor(ui): single source of truth for migrated-page routing by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;29949](BerriAI/litellm#29949)
- fix(ui/model-hub): render provider icons on the public model hub by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29958](BerriAI/litellm#29958)
- fix(ui): keep create guardrail modal open on outside click by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29871](BerriAI/litellm#29871)
- fix(ui): label default key type as "Full Access" on key edit page by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29870](BerriAI/litellm#29870)
- fix(ui): unify migrated-route URLs and migrate the API Reference page by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;29953](BerriAI/litellm#29953)
- fix(mcp): let non-creator users OAuth into OBO-mode MCP servers from the Tools page by [@&#8203;tin-berri](https://github.com/tin-berri) in [#&#8203;29867](BerriAI/litellm#29867)
- Litellm oss staging 080626 by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;29932](BerriAI/litellm#29932)
- feat(galileo): add health check support for UI callback test by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;29908](BerriAI/litellm#29908)
- fix(model-management): allow deleting a BYOK model after its team is deleted by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29875](BerriAI/litellm#29875)
- feat(jwt-auth): opt-in fallback to DB team on unresolved JWT claim by [@&#8203;milan-berri](https://github.com/milan-berri) in [#&#8203;28913](BerriAI/litellm#28913)
- fix(team\_endpoints): don't block /team/update on unchanged team budget by [@&#8203;milan-berri](https://github.com/milan-berri) in [#&#8203;29525](BerriAI/litellm#29525)
- fix(fireworks): enable tool calling for glm-5p1 in model cost map by [@&#8203;milan-berri](https://github.com/milan-berri) in [#&#8203;29697](BerriAI/litellm#29697)
- fix(vertex): propagate Vertex AI metadata in streaming success callbacks by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;29899](BerriAI/litellm#29899)
- fix(ui): show team projects to internal users on key creation by [@&#8203;milan-berri](https://github.com/milan-berri) in [#&#8203;28855](BerriAI/litellm#28855)
- build(deps): bump pyjwt to 2.13.0 and ws override to 8.20.1 by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29982](BerriAI/litellm#29982)
- fix(team-management): delete a team's BYOK models when the team is deleted by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29977](BerriAI/litellm#29977)
- feat(vantage): include organization metadata in FOCUS Tags export by [@&#8203;milan-berri](https://github.com/milan-berri) in [#&#8203;28184](BerriAI/litellm#28184)
- fix(guardrails): read CrowdStrike AIDR identity from both metadata bags by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29991](BerriAI/litellm#29991)
- fix(mcp): mirror upstream token lifetime instead of forcing a 1h OBO expiry by [@&#8203;tin-berri](https://github.com/tin-berri) in [#&#8203;29951](BerriAI/litellm#29951)
- feat(azure\_ai): add MAI-Image-2.5 image generation support by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;29688](BerriAI/litellm#29688)
- fix(mcp): load MCP tool configuration tools via the OBO/passthrough-aware GET path by [@&#8203;tin-berri](https://github.com/tin-berri) in [#&#8203;29960](BerriAI/litellm#29960)
- fix(team): reserve team budget raises for proxy admins on /team/update by [@&#8203;milan-berri](https://github.com/milan-berri) in [#&#8203;30030](BerriAI/litellm#30030)
- test(ui): data-driven App Router migration E2E smoke (default + server-root-path) by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;29974](BerriAI/litellm#29974)
- fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through by [@&#8203;michelligabriele](https://github.com/michelligabriele) in [#&#8203;24232](BerriAI/litellm#24232)
- chore(ui): remove dead App Router route stubs under (dashboard) by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30045](BerriAI/litellm#30045)
- fix(ui/mcp): reset OAuth state on create-server modal close so a prior server's token no longer leaks into the next add-server session by [@&#8203;tin-berri](https://github.com/tin-berri) in [#&#8203;30000](BerriAI/litellm#30000)
- fix(mcp): allow team access-group grants in OAuth authorize/token access check by [@&#8203;tin-berri](https://github.com/tin-berri) in [#&#8203;30041](BerriAI/litellm#30041)
- docs(security): require a reproduction video for vulnerability reports by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30063](BerriAI/litellm#30063)
- feat(ui): add admin flag to disable in-product UI nudges for everyone by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;29796](BerriAI/litellm#29796)
- chore(ui): remove dead dashboard files and unused dependencies by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30047](BerriAI/litellm#30047)
- fix(proxy): authorize batch files using upload target\_model\_names (LIT-3593) by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30009](BerriAI/litellm#30009)
- Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30064](BerriAI/litellm#30064)
- Add Claude Fable 5 cost map entries (data-only hotfix for the hosted map) by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30076](BerriAI/litellm#30076)
- fix(caching): restore stored prompt\_tokens on embedding cache hits instead of recomputing by [@&#8203;michelligabriele](https://github.com/michelligabriele) in [#&#8203;30046](BerriAI/litellm#30046)
- Litellm oss 090626 by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30021](BerriAI/litellm#30021)
- fix(proxy): self-heal startup/reload prisma reads on engine disconnect by [@&#8203;michelligabriele](https://github.com/michelligabriele) in [#&#8203;28803](BerriAI/litellm#28803)
- chore(ui): make knip recognize .mjs scripts and openapi-typescript by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30052](BerriAI/litellm#30052)
- fix(register\_model): preserve built-in cache pricing when registering custom overrides under unmapped keys by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30044](BerriAI/litellm#30044)
- \[internal copy of [#&#8203;28007](BerriAI/litellm#28007)] Fix/gcp model garden streaming by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;28363](BerriAI/litellm#28363)
- feat(cli): per-agent `lite claude` / `codex` / `opencode` commands that wrap coding agents through the proxy by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;29850](BerriAI/litellm#29850)
- fix(callbacks): forward callback\_settings to callback initializers and guard consumers against non-dict values by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30161](BerriAI/litellm#30161)
- fix(mcp): drop orphaned per-user credential rows when an MCP server is deleted by [@&#8203;tin-berri](https://github.com/tin-berri) in [#&#8203;30141](BerriAI/litellm#30141)
- fix(proxy): recover from cached-plan errors by reconnecting the Prisma client by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;29983](BerriAI/litellm#29983)
- feat(proxy): add option to disable server-side prepared statements for DB lookups by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;29984](BerriAI/litellm#29984)
- fix(release): stop backport releases from overwriting the latest badge by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30005](BerriAI/litellm#30005)
- feat: add conventional commits and coding guidelines by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30159](BerriAI/litellm#30159)
- fix(proxy): return 5xx on DB infra errors during auth; reserve 401 for genuine auth failures by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;29986](BerriAI/litellm#29986)
- fix(ui): dev server 404s on migrated-page links because uiBase hardcodes /ui by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30169](BerriAI/litellm#30169)
- refactor(ui): consolidate dashboard to one shell in the (dashboard) layout by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30166](BerriAI/litellm#30166)
- fix(proxy): align /v1/model/info with router deployments by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30025](BerriAI/litellm#30025)
- fix: completion\_cost AttributeError on streaming Anthropic web\_search responses ([#&#8203;26153](BerriAI/litellm#26153)) by [@&#8203;ishaan-berri](https://github.com/ishaan-berri) in [#&#8203;27346](BerriAI/litellm#27346)
- \[internal copy of [#&#8203;30137](BerriAI/litellm#30137)] perf(realtime): eliminate redundant per-frame JSON work on OpenAI realtime relay by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30142](BerriAI/litellm#30142)
- feat(bedrock): aws\_bedrock\_project\_id for bedrock-mantle project / workspace association by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30163](BerriAI/litellm#30163)
- chore(hooks): enforce Conventional Commits and Conventional Branches by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30174](BerriAI/litellm#30174)
- feat(rate-limiter): allow opting out of v3 TPM reservation and Redis circuit breaker by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30211](BerriAI/litellm#30211)
- feat(spend\_logs): opt-in native Postgres partitioning for SpendLogs retention by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;29466](BerriAI/litellm#29466)
- feat(ui): migrate playground to path routing and colocate its files by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30185](BerriAI/litellm#30185)
- feat(ui): migrate projects and access-groups to path routes by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30226](BerriAI/litellm#30226)
- fix(proxy): coalesce NULL rollup metrics in aggregated daily-activity by [@&#8203;michelligabriele](https://github.com/michelligabriele) in [#&#8203;30151](BerriAI/litellm#30151)
- fix(anthropic\_passthrough): resolve costing model from message\_start chunk, litellm\_params and model\_group instead of 'unknown' by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30160](BerriAI/litellm#30160)
- feat(ui): migrate budgets, workflows, and guardrails-monitor to path routes by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30236](BerriAI/litellm#30236)
- feat(ui): migrate mcp-servers, search-tools, tag-management, vector-stores, and memory to path routes by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30261](BerriAI/litellm#30261)
- fix(a2a): forward agent\_extra\_headers through completion bridge by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;28277](BerriAI/litellm#28277)
- fix(gemini-live): forward audio buffer commit and correct Vertex PCM rate by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;29946](BerriAI/litellm#29946)
- fix(proxy): skip double-wrapping unified batch output file ids on retrieve by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30011](BerriAI/litellm#30011)
- feat: litellm oss 110626 by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30202](BerriAI/litellm#30202)
- fix(docker): copy only runtime artifacts into the final image by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30243](BerriAI/litellm#30243)
- feat(proxy): enforce key/team guardrails on bedrock passthrough routes by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30194](BerriAI/litellm#30194)
- feat(gemini): forward web search tools in image generation by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30119](BerriAI/litellm#30119)
- fix: bedrock mantle fixes by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30083](BerriAI/litellm#30083)
- feat(proxy): add require\_managed\_files setting for file uploads by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30186](BerriAI/litellm#30186)
- fix(mcp): honor server\_id for REST tool calls with shared upstream URLs by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30184](BerriAI/litellm#30184)
- fix(responses): presidio PII masking for Azure WebSocket and streaming by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30003](BerriAI/litellm#30003)
- feat(passthrough): add configurable pass-through request timeouts by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30266](BerriAI/litellm#30266)
- fix(google\_genai): preserve complete SSE events in Vertex/Gemini image streaming by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30270](BerriAI/litellm#30270)
- fix(proxy): populate access\_via\_team\_ids on /v1/model/info by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30274](BerriAI/litellm#30274)
- chore(oss): litellm oss staging 120626 by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30292](BerriAI/litellm#30292)
- feat(ui): migrate policies, guardrails, prompts, tool-policies, and skills to path routes by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30263](BerriAI/litellm#30263)
- feat(ui): migrate caching, cost-tracking, transform-request, ui-theme, and logs to path routes by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30267](BerriAI/litellm#30267)
- fix(ui): gate dashboard layout on ui config load so deep links work under SERVER\_ROOT\_PATH by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30312](BerriAI/litellm#30312)
- feat(ui): migrate admin-panel, logging-and-alerts, model-hub-table, and usage to path routes by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30268](BerriAI/litellm#30268)
- fix(otel): cap metric attribute cardinality with include/exclude lists by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30257](BerriAI/litellm#30257)
- fix(proxy): grace-period key rotation 401s; return deprecated-key lookup result directly by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30327](BerriAI/litellm#30327)
- chore(deps): bump vitest, brace-expansion, pypdf and tornado by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30220](BerriAI/litellm#30220)
- refactor(ui): remove unreachable /chat page by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30178](BerriAI/litellm#30178)
- feat(ui): migrate agents and router-settings to path routes by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30323](BerriAI/litellm#30323)
- feat: strengthen coding conventions in CLAUDE.md by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30333](BerriAI/litellm#30333)
- feat(ui): cut the users page over to the /ui/users path route by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30334](BerriAI/litellm#30334)
- feat: ruff strict-rule suppressions baseline gate by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30303](BerriAI/litellm#30303)
- feat(guardrails): add Cisco AI Defense integration ([#&#8203;28249](BerriAI/litellm#28249)) by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30338](BerriAI/litellm#30338)
- chore(ui): remove dead UI components unreferenced by any page by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30340](BerriAI/litellm#30340)
- ci: add osv-scanner lockfile scan workflow by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30222](BerriAI/litellm#30222)
- fix(otel): record full error message on standard exception event in otel v2 by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30380](BerriAI/litellm#30380)
- test(fireworks): mock whisper transcription tests instead of live calls by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30391](BerriAI/litellm#30391)
- build(ui): pin esbuild to 0.28.1 via overrides by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30390](BerriAI/litellm#30390)
- feat(ui): cut the organizations page over to the /ui/organizations path route by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30336](BerriAI/litellm#30336)
- fix(proxy): support SMTP implicit SSL (port 465) by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30395](BerriAI/litellm#30395)
- fix(mcp): default Linear MCP registry entry to streamable HTTP by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30396](BerriAI/litellm#30396)
- fix(ui): stop Virtual Keys page from infinite render loop by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30397](BerriAI/litellm#30397)
- fix(streaming): guard raise\_on\_model\_repetition against empty choices by [@&#8203;shivamrawat1](https://github.com/shivamrawat1) in [#&#8203;30485](BerriAI/litellm#30485)
- feat(otel-v2): emit the 6 gen\_ai.client.\* metrics at parity with v1 by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30326](BerriAI/litellm#30326)
- fix(mcp): drop phantom 401 span on delegated OAuth2 tool calls by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30494](BerriAI/litellm#30494)
- feat(ui): cut the teams page over to the /ui/teams path route by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30343](BerriAI/litellm#30343)
- fix(integrations): cap Anthropic cache\_control injection at 4 blocks by [@&#8203;shivamrawat1](https://github.com/shivamrawat1) in [#&#8203;30480](BerriAI/litellm#30480)
- chore(codecov): add Batches, Videos, and Realtime components by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30517](BerriAI/litellm#30517)
- test(batches): move orphan tests into tests/test\_litellm for CI coverage by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30510](BerriAI/litellm#30510)
- fix(guardrails): run pre\_call hook once for model-level guardrails by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30543](BerriAI/litellm#30543)
- fix(guardrails): stop re-initializing DB guardrails on every poll by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30542](BerriAI/litellm#30542)
- chore(oss): litellm oss staging 150626 by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30463](BerriAI/litellm#30463)
- ci(lint): add blanket-noqa, dataclass-default, and unused-noqa Ruff rules by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30516](BerriAI/litellm#30516)
- ci: ratchet lint and type-check gates (ruff preview, ANN, mypy, basedpyright) by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30379](BerriAI/litellm#30379)
- fix(proxy): allow internal roles to access vector store CRUD routes by [@&#8203;shivamrawat1](https://github.com/shivamrawat1) in [#&#8203;30503](BerriAI/litellm#30503)
- fix(otel): stamp gen\_ai.input/output.messages on v2 spans by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30548](BerriAI/litellm#30548)
- fix(otel): export v2 gen\_ai client metrics to the configured meter provider by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30549](BerriAI/litellm#30549)
- fix(bedrock): preserve cache\_control for ARN models in /v1/messages adapter by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;29823](BerriAI/litellm#29823)
- fix: greatly increase basedpyright slack by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30563](BerriAI/litellm#30563)
- fix(budget): recompute budget\_reset\_at when budget\_duration changes on /budget/update by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30555](BerriAI/litellm#30555)
- fix(otel): accept UPPER\_SNAKE\_CASE OTEL\_INSTRUMENTATION\_GENAI\_CAPTURE\_MESSAGE\_CONTENT in v2 by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30562](BerriAI/litellm#30562)
- chore(lint): remove PLR0915 too-many-statements ruff rule by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30574](BerriAI/litellm#30574)
- ci(lint): ratcheted type-discipline gate (mutable collections, casts, guards, kwargs, suppressions) by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30500](BerriAI/litellm#30500)
- feat(proxy): add verification\_uri\_complete to CLI SSO device flow by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30571](BerriAI/litellm#30571)
- chore: litellm oss staging160626 by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30527](BerriAI/litellm#30527)
- fix(guardrails): return 400 not 500 when AIM blocks a request by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30573](BerriAI/litellm#30573)
- ci(lint): grandfather any-discipline with a per-file ratchet budget (50% headroom) by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30582](BerriAI/litellm#30582)
- fix(audio): don't override explicit response\_format with verbose\_json by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30599](BerriAI/litellm#30599)
- fix(anthropic): price and surface response service\_tier in cost tracking by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30558](BerriAI/litellm#30558)
- feat: add dev and wildcard proxy configs for local testing by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30556](BerriAI/litellm#30556)
- fix(proxy): list public team model name in /v1/models by [@&#8203;ishaan-berri](https://github.com/ishaan-berri) in [#&#8203;30588](BerriAI/litellm#30588)
- ci: drop mypy entirely, standardize type checking on basedpyright by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30648](BerriAI/litellm#30648)
- feat(guardrails): surface OpenAI moderation violation\_categories on guardrail traces by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30659](BerriAI/litellm#30659)
- fix(proxy): resolve list files credentials from team BYOK deployments by [@&#8203;shivamrawat1](https://github.com/shivamrawat1) in [#&#8203;30495](BerriAI/litellm#30495)
- feat(proxy): add --max\_requests\_before\_restart\_jitter to stagger worker restarts by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30601](BerriAI/litellm#30601)
- fix(health): correct bedrock embedding health checks by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30583](BerriAI/litellm#30583)
- test: harden remaining pass-through CI flakes (image-gen spend poll, ruby assistants timeout) by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30685](BerriAI/litellm#30685)
- test(pass\_through): harden vertex spendlog poll against transient empty reads by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30683](BerriAI/litellm#30683)
- fix(cost): stop non-string service\_tier from silently dropping cost tracking by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30690](BerriAI/litellm#30690)
- feat(proxy): warn at startup when custom\_auth skips common\_checks enforcement by [@&#8203;tin-berri](https://github.com/tin-berri) in [#&#8203;30665](BerriAI/litellm#30665)
- fix(pod\_lock): release cron lock by matching async\_set\_cache JSON encoding by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30600](BerriAI/litellm#30600)
- ci: run a local fake OpenAI endpoint instead of the shared Railway mock by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30695](BerriAI/litellm#30695)
- ci(windows): pin uv to Python 3.11 so it ignores the preinstalled 3.14 by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30704](BerriAI/litellm#30704)
- feat(ui): migrate models page to App Router path route by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30677](BerriAI/litellm#30677)
- refactor(ui): remove orphaned pass-through-settings route by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30692](BerriAI/litellm#30692)
- fix(cost): stop non-string response service\_tier from dropping cost tracking by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30706](BerriAI/litellm#30706)
- feat(agent-shin): automated PR/issue triage, low-quality auto-close, and review-gate label lifecycle by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30433](BerriAI/litellm#30433)
- chore: litellm oss 170626 by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30637](BerriAI/litellm#30637)
- fix(bedrock\_mantle): add SigV4 fallback to chat completions auth by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30714](BerriAI/litellm#30714)
- feat(search): add TinyFish as search provider by [@&#8203;simantak-dabhade](https://github.com/simantak-dabhade) in [#&#8203;30634](BerriAI/litellm#30634)
- feat(ui): migrate old usage report to App Router path route by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30694](BerriAI/litellm#30694)
- fix(proxy): enforce budgets against authoritative DB spend when the cross-pod counter is stale by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30684](BerriAI/litellm#30684)
- chore(ci): remove Agent Shin pull\_request\_target workflows by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30784](BerriAI/litellm#30784)
- chore: litellm oss staging by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30745](BerriAI/litellm#30745)
- ci(zizmor): also run on litellm\_internal\_staging by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30789](BerriAI/litellm#30789)
- fix(test): drop references to removed Agent Shin workflows by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30791](https://github.com/BerriAI/litellm/pull/30791)
- chore: remove in-product survey and Claude Code feedback nudges by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30773](https://github.com/BerriAI/litellm/pull/30773)
- feat(ui): migrate api-keys landing to App Router path route by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30699](https://github.com/BerriAI/litellm/pull/30699)
- feat(proxy): configurable response headers and login-page hint by [@&#8203;yucheng-berri](https://github.com/yucheng-berri) in [#&#8203;30792](https://github.com/BerriAI/litellm/pull/30792)
- ci(zizmor): gate PRs on medium+ findings and clear existing ones by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30797](https://github.com/BerriAI/litellm/pull/30797)
- fix(proxy): use e.request\_data for logging\_obj in ModifyResponseException streaming passthrough by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30800](https://github.com/BerriAI/litellm/pull/30800)
- chore: make pr template linear portion clearer by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30766](https://github.com/BerriAI/litellm/pull/30766)
- chore(typing): add boto3/botocore stubs so basedpyright resolves the AWS SDK by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30815](https://github.com/BerriAI/litellm/pull/30815)
- fix(otel): one v2 logger owns the global provider; scope tenant OTLP creds per exporter by [@&#8203;yucheng-berri](https://github.com/yucheng-berri) in [#&#8203;30590](https://github.com/BerriAI/litellm/pull/30590)
- fix(passthrough): recover output tokens for interrupted anthropic streams by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30787](https://github.com/BerriAI/litellm/pull/30787)
- fix(proxy): record partial spend on the failure row for interrupted streams by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30788](https://github.com/BerriAI/litellm/pull/30788)
- fix(ui): repoint dead usage guide link to cost tracking docs by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30859](https://github.com/BerriAI/litellm/pull/30859)
- fix(ui): warn that team models are deleted in the delete-team modal by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29990](https://github.com/BerriAI/litellm/pull/29990)
- feat(caching): add valkey-semantic cache backend and fix semantic cache scope keys by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30675](https://github.com/BerriAI/litellm/pull/30675)
- test(ui): isolate OldTeams delete-warning tests from leaked mock by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30871](https://github.com/BerriAI/litellm/pull/30871)
- feat: add lint-gate target and truncation-proof summary to the strict ruff gate by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30877](https://github.com/BerriAI/litellm/pull/30877)
- chore(ui): rebuild ui for release by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30894](https://github.com/BerriAI/litellm/pull/30894)
- chore(ci): bump deps by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30899](https://github.com/BerriAI/litellm/pull/30899)
- fix(watsonx): wrap string embedding input in array for WatsonX API by [@&#8203;shivamrawat1](https://github.com/shivamrawat1) in [#&#8203;30897](https://github.com/BerriAI/litellm/pull/30897)
- test: point router/completion/triton tests at the local fake OpenAI endpoint by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30900](https://github.com/BerriAI/litellm/pull/30900)
- feat(sandbox): e2b code execution primitive by [@&#8203;krrish-berri-2](https://github.com/krrish-berri-2) in [#&#8203;30898](https://github.com/BerriAI/litellm/pull/30898)
- fix(ui): source api-keys identity from useAuthorized to stop "User ID is not set" by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30903](https://github.com/BerriAI/litellm/pull/30903)
- chore(ui): rebuild ui by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30906](https://github.com/BerriAI/litellm/pull/30906)
- chore(ci): promote internal staging to main by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30907](https://github.com/BerriAI/litellm/pull/30907)
- fix(redis): prevent forcing SSLConnection when ssl=False in connection pool by [@&#8203;Jacopos311](https://github.com/Jacopos311) in [#&#8203;30770](https://github.com/BerriAI/litellm/pull/30770)
- fix(proxy): log UI setup failures instead of silently swallowing by [@&#8203;sarvesh1327](https://github.com/sarvesh1327) in [#&#8203;30819](https://github.com/BerriAI/litellm/pull/30819)

#### New Contributors

- [@&#8203;simantak-dabhade](https://github.com/simantak-dabhade) made their first contribution in [#&#8203;30634](BerriAI/litellm#30634)
- [@&#8203;Jacopos311](https://github.com/Jacopos311) made their first contribution in [#&#8203;30770](https://github.com/BerriAI/litellm/pull/30770)
- [@&#8203;sarvesh1327](https://github.com/sarvesh1327) made their first contribution in [#&#8203;30819](https://github.com/BerriAI/litellm/pull/30819)

**Full Changelog**: <BerriAI/litellm@v1.89.0...v1.90.0>

</details>

---

### Configuration

📅 **Schedule**: (UTC)

- Branch creation
  - At any time (no schedule defined)
- Automerge
  - At any time (no schedule defined)

🚦 **Automerge**: Disabled by config. Please merge this manually once you are satisfied.

♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox.

🔕 **Ignore**: Close this PR and you won't be reminded about this update again.

---

 - [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check this box

---

This PR has been generated by [Mend Renovate](https://github.com/renovatebot/renovate).
<!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiI0My4yMjAuMCIsInVwZGF0ZWRJblZlciI6IjQzLjIyMC4wIiwidGFyZ2V0QnJhbmNoIjoibWFpbiIsImxhYmVscyI6WyJkZXBlbmRlbmNpZXMiXX0=-->

Co-authored-by: Renovate Bot <[email protected]>
Reviewed-on: https://codeberg.org/blake-hamm/bhamm-lab/pulls/232

This PR contains the following updates:

| Package | Type | Update | Change |
|---|---|---|---|
| [ghcr.io/berriai/litellm](https://images.chainguard.dev/directory/image/wolfi-base/overview) ([source](https://github.com/BerriAI/litellm)) | final | minor | `v1.85.1` → `v1.90.0` |

---

### Release Notes

<details>
<summary>BerriAI/litellm (ghcr.io/berriai/litellm)</summary>

### [`v1.90.0`](https://github.com/BerriAI/litellm/releases/tag/v1.90.0)

[Compare Source](https://github.com/BerriAI/litellm/compare/v1.90.0...v1.90.0)

##### Verify Docker Image Signature

All LiteLLM Docker images are signed with [cosign](https://docs.sigstore.dev/cosign/overview/). Every release is signed with the same key introduced in [commit `0112e53`](https://github.com/BerriAI/litellm/commit/0112e53046018d726492c814b3644b7d376029d0).

**Verify using the pinned commit hash (recommended):**

A commit hash is cryptographically immutable, so this is the strongest way to ensure you are using the original signing key:

```bash
cosign verify \
  --key https://raw.githubusercontent.com/BerriAI/litellm/0112e53046018d726492c814b3644b7d376029d0/cosign.pub \
  ghcr.io/berriai/litellm:v1.90.0
```

**Verify using the release tag (convenience):**

Tags are protected in this repository and resolve to the same key. This option is easier to read but relies on tag protection rules:

```bash
cosign verify \
  --key https://raw.githubusercontent.com/BerriAI/litellm/v1.90.0/cosign.pub \
  ghcr.io/berriai/litellm:v1.90.0
```

Expected output:

```
The following checks were performed on each of these signatures:
  - The cosign claims were validated
  - The signatures were verified against the specified public key
```

***

##### What's Changed

- fix(responses-bridge): map system-only chat request to system input item by [@&#8203;milan-berri](https://github.com/milan-berri) in [#&#8203;29817](https://github.com/BerriAI/litellm/pull/29817)
- feat(bedrock): forward strict and additionalProperties to Converse toolSpec by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;29814](https://github.com/BerriAI/litellm/pull/29814)
- fix(mcp): highlight MCP cards red when the logged-in user is missing per-user env vars by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;29856](https://github.com/BerriAI/litellm/pull/29856)
- feat(ui): add budget duration to edit team member form by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;29717](https://github.com/BerriAI/litellm/pull/29717)
- fix(ui): make workflow runs page fill full width by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29868](https://github.com/BerriAI/litellm/pull/29868)
- feat: standardize rate limit errors with category, rate\_limit\_type, model, and llm\_provider fields by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;27687](https://github.com/BerriAI/litellm/pull/27687)
- fix(ui): default guardrails page to the Guardrails tab by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29872](https://github.com/BerriAI/litellm/pull/29872)
- docs(readme): add Deploy on AWS/GCP Terraform section and fix deploy button rendering by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;29879](https://github.com/BerriAI/litellm/pull/29879)
- refactor(bedrock): build Converse toolSpec via a BedrockToolSpec dict subclass by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;29869](https://github.com/BerriAI/litellm/pull/29869)
- feat(litellm): add models and repository layers by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;29686](https://github.com/BerriAI/litellm/pull/29686)
- feat(ui): include internal routes in the dashboard's generated OpenAPI types by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;29885](https://github.com/BerriAI/litellm/pull/29885)
- feat(proxy): publish /v2/model/info in Swagger OpenAPI spec by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;29900](https://github.com/BerriAI/litellm/pull/29900)
- refactor(ui): single source of truth for migrated-page routing by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;29949](https://github.com/BerriAI/litellm/pull/29949)
- fix(ui/model-hub): render provider icons on the public model hub by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29958](https://github.com/BerriAI/litellm/pull/29958)
- fix(ui): keep create guardrail modal open on outside click by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29871](https://github.com/BerriAI/litellm/pull/29871)
- fix(ui): label default key type as "Full Access" on key edit page by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29870](https://github.com/BerriAI/litellm/pull/29870)
- fix(ui): unify migrated-route URLs and migrate the API Reference page by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;29953](https://github.com/BerriAI/litellm/pull/29953)
- fix(mcp): let non-creator users OAuth into OBO-mode MCP servers from the Tools page by [@&#8203;tin-berri](https://github.com/tin-berri) in [#&#8203;29867](https://github.com/BerriAI/litellm/pull/29867)
- Litellm oss staging 080626 by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;29932](https://github.com/BerriAI/litellm/pull/29932)
- feat(galileo): add health check support for UI callback test by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;29908](https://github.com/BerriAI/litellm/pull/29908)
- fix(model-management): allow deleting a BYOK model after its team is deleted by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29875](https://github.com/BerriAI/litellm/pull/29875)
- feat(jwt-auth): opt-in fallback to DB team on unresolved JWT claim by [@&#8203;milan-berri](https://github.com/milan-berri) in [#&#8203;28913](https://github.com/BerriAI/litellm/pull/28913)
- fix(team\_endpoints): don't block /team/update on unchanged team budget by [@&#8203;milan-berri](https://github.com/milan-berri) in [#&#8203;29525](https://github.com/BerriAI/litellm/pull/29525)
- fix(fireworks): enable tool calling for glm-5p1 in model cost map by [@&#8203;milan-berri](https://github.com/milan-berri) in [#&#8203;29697](https://github.com/BerriAI/litellm/pull/29697)
- fix(vertex): propagate Vertex AI metadata in streaming success callbacks by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;29899](https://github.com/BerriAI/litellm/pull/29899)
- fix(ui): show team projects to internal users on key creation by [@&#8203;milan-berri](https://github.com/milan-berri) in [#&#8203;28855](https://github.com/BerriAI/litellm/pull/28855)
- build(deps): bump pyjwt to 2.13.0 and ws override to 8.20.1 by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29982](https://github.com/BerriAI/litellm/pull/29982)
- fix(team-management): delete a team's BYOK models when the team is deleted by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29977](https://github.com/BerriAI/litellm/pull/29977)
- feat(vantage): include organization metadata in FOCUS Tags export by [@&#8203;milan-berri](https://github.com/milan-berri) in [#&#8203;28184](https://github.com/BerriAI/litellm/pull/28184)
- fix(guardrails): read CrowdStrike AIDR identity from both metadata bags by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29991](https://github.com/BerriAI/litellm/pull/29991)
- fix(mcp): mirror upstream token lifetime instead of forcing a 1h OBO expiry by [@&#8203;tin-berri](https://github.com/tin-berri) in [#&#8203;29951](https://github.com/BerriAI/litellm/pull/29951)
- feat(azure\_ai): add MAI-Image-2.5 image generation support by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;29688](https://github.com/BerriAI/litellm/pull/29688)
- fix(mcp): load MCP tool configuration tools via the OBO/passthrough-aware GET path by [@&#8203;tin-berri](https://github.com/tin-berri) in [#&#8203;29960](https://github.com/BerriAI/litellm/pull/29960)
- fix(team): reserve team budget raises for proxy admins on /team/update by [@&#8203;milan-berri](https://github.com/milan-berri) in [#&#8203;30030](https://github.com/BerriAI/litellm/pull/30030)
- test(ui): data-driven App Router migration E2E smoke (default + server-root-path) by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;29974](https://github.com/BerriAI/litellm/pull/29974)
- fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through by [@&#8203;michelligabriele](https://github.com/michelligabriele) in [#&#8203;24232](https://github.com/BerriAI/litellm/pull/24232)
- chore(ui): remove dead App Router route stubs under (dashboard) by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30045](https://github.com/BerriAI/litellm/pull/30045)
- fix(ui/mcp): reset OAuth state on create-server modal close so a prior server's token no longer leaks into the next add-server session by [@&#8203;tin-berri](https://github.com/tin-berri) in [#&#8203;30000](https://github.com/BerriAI/litellm/pull/30000)
- fix(mcp): allow team access-group grants in OAuth authorize/token access check by [@&#8203;tin-berri](https://github.com/tin-berri) in [#&#8203;30041](https://github.com/BerriAI/litellm/pull/30041)
- docs(security): require a reproduction video for vulnerability reports by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30063](https://github.com/BerriAI/litellm/pull/30063)
- feat(ui): add admin flag to disable in-product UI nudges for everyone by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;29796](https://github.com/BerriAI/litellm/pull/29796)
- chore(ui): remove dead dashboard files and unused dependencies by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30047](https://github.com/BerriAI/litellm/pull/30047)
- fix(proxy): authorize batch files using upload target\_model\_names (LIT-3593) by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30009](https://github.com/BerriAI/litellm/pull/30009)
- Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30064](https://github.com/BerriAI/litellm/pull/30064)
- Add Claude Fable 5 cost map entries (data-only hotfix for the hosted map) by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30076](https://github.com/BerriAI/litellm/pull/30076)
- fix(caching): restore stored prompt\_tokens on embedding cache hits instead of recomputing by [@&#8203;michelligabriele](https://github.com/michelligabriele) in [#&#8203;30046](https://github.com/BerriAI/litellm/pull/30046)
- Litellm oss 090626 by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30021](https://github.com/BerriAI/litellm/pull/30021)
- fix(proxy): self-heal startup/reload prisma reads on engine disconnect by [@&#8203;michelligabriele](https://github.com/michelligabriele) in [#&#8203;28803](https://github.com/BerriAI/litellm/pull/28803)
- chore(ui): make knip recognize .mjs scripts and openapi-typescript by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30052](https://github.com/BerriAI/litellm/pull/30052)
- fix(register\_model): preserve built-in cache pricing when registering custom overrides under unmapped keys by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30044](https://github.com/BerriAI/litellm/pull/30044)
- \[internal copy of [#&#8203;28007](https://github.com/BerriAI/litellm/issues/28007)] Fix/gcp model garden streaming by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;28363](https://github.com/BerriAI/litellm/pull/28363)
- feat(cli): per-agent `lite claude` / `codex` / `opencode` commands that wrap coding agents through the proxy by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;29850](https://github.com/BerriAI/litellm/pull/29850)
- fix(callbacks): forward callback\_settings to callback initializers and guard consumers against non-dict values by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30161](https://github.com/BerriAI/litellm/pull/30161)
- fix(mcp): drop orphaned per-user credential rows when an MCP server is deleted by [@&#8203;tin-berri](https://github.com/tin-berri) in [#&#8203;30141](https://github.com/BerriAI/litellm/pull/30141)
- fix(proxy): recover from cached-plan errors by reconnecting the Prisma client by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;29983](https://github.com/BerriAI/litellm/pull/29983)
- feat(proxy): add option to disable server-side prepared statements for DB lookups by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;29984](https://github.com/BerriAI/litellm/pull/29984)
- fix(release): stop backport releases from overwriting the latest badge by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30005](https://github.com/BerriAI/litellm/pull/30005)
- feat: add conventional commits and coding guidelines by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30159](https://github.com/BerriAI/litellm/pull/30159)
- fix(proxy): return 5xx on DB infra errors during auth; reserve 401 for genuine auth failures by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;29986](https://github.com/BerriAI/litellm/pull/29986)
- fix(ui): dev server 404s on migrated-page links because uiBase hardcodes /ui by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30169](https://github.com/BerriAI/litellm/pull/30169)
- refactor(ui): consolidate dashboard to one shell in the (dashboard) layout by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30166](https://github.com/BerriAI/litellm/pull/30166)
- fix(proxy): align /v1/model/info with router deployments by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30025](https://github.com/BerriAI/litellm/pull/30025)
- fix: completion\_cost AttributeError on streaming Anthropic web\_search responses ([#&#8203;26153](https://github.com/BerriAI/litellm/issues/26153)) by [@&#8203;ishaan-berri](https://github.com/ishaan-berri) in [#&#8203;27346](https://github.com/BerriAI/litellm/pull/27346)
- \[internal copy of [#&#8203;30137](https://github.com/BerriAI/litellm/issues/30137)] perf(realtime): eliminate redundant per-frame JSON work on OpenAI realtime relay by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30142](https://github.com/BerriAI/litellm/pull/30142)
- feat(bedrock): aws\_bedrock\_project\_id for bedrock-mantle project / workspace association by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30163](https://github.com/BerriAI/litellm/pull/30163)
- chore(hooks): enforce Conventional Commits and Conventional Branches by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30174](https://github.com/BerriAI/litellm/pull/30174)
- feat(rate-limiter): allow opting out of v3 TPM reservation and Redis circuit breaker by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30211](https://github.com/BerriAI/litellm/pull/30211)
- feat(spend\_logs): opt-in native Postgres partitioning for SpendLogs retention by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;29466](https://github.com/BerriAI/litellm/pull/29466)
- feat(ui): migrate playground to path routing and colocate its files by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30185](https://github.com/BerriAI/litellm/pull/30185)
- feat(ui): migrate projects and access-groups to path routes by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30226](https://github.com/BerriAI/litellm/pull/30226)
- fix(proxy): coalesce NULL rollup metrics in aggregated daily-activity by [@&#8203;michelligabriele](https://github.com/michelligabriele) in [#&#8203;30151](https://github.com/BerriAI/litellm/pull/30151)
- fix(anthropic\_passthrough): resolve costing model from message\_start chunk, litellm\_params and model\_group instead of 'unknown' by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30160](https://github.com/BerriAI/litellm/pull/30160)
- feat(ui): migrate budgets, workflows, and guardrails-monitor to path routes by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30236](https://github.com/BerriAI/litellm/pull/30236)
- feat(ui): migrate mcp-servers, search-tools, tag-management, vector-stores, and memory to path routes by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30261](https://github.com/BerriAI/litellm/pull/30261)
- fix(a2a): forward agent\_extra\_headers through completion bridge by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;28277](https://github.com/BerriAI/litellm/pull/28277)
- fix(gemini-live): forward audio buffer commit and correct Vertex PCM rate by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;29946](https://github.com/BerriAI/litellm/pull/29946)
- fix(proxy): skip double-wrapping unified batch output file ids on retrieve by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30011](https://github.com/BerriAI/litellm/pull/30011)
- feat: litellm oss 110626 by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30202](https://github.com/BerriAI/litellm/pull/30202)
- fix(docker): copy only runtime artifacts into the final image by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30243](https://github.com/BerriAI/litellm/pull/30243)
- feat(proxy): enforce key/team guardrails on bedrock passthrough routes by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30194](https://github.com/BerriAI/litellm/pull/30194)
- feat(gemini): forward web search tools in image generation by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30119](https://github.com/BerriAI/litellm/pull/30119)
- fix: bedrock mantle fixes by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30083](https://github.com/BerriAI/litellm/pull/30083)
- feat(proxy): add require\_managed\_files setting for file uploads by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30186](https://github.com/BerriAI/litellm/pull/30186)
- fix(mcp): honor server\_id for REST tool calls with shared upstream URLs by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30184](https://github.com/BerriAI/litellm/pull/30184)
- fix(responses): presidio PII masking for Azure WebSocket and streaming by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30003](https://github.com/BerriAI/litellm/pull/30003)
- feat(passthrough): add configurable pass-through request timeouts by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30266](https://github.com/BerriAI/litellm/pull/30266)
- fix(google\_genai): preserve complete SSE events in Vertex/Gemini image streaming by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30270](https://github.com/BerriAI/litellm/pull/30270)
- fix(proxy): populate access\_via\_team\_ids on /v1/model/info by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30274](https://github.com/BerriAI/litellm/pull/30274)
- chore(oss): litellm oss staging 120626 by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30292](https://github.com/BerriAI/litellm/pull/30292)
- feat(ui): migrate policies, guardrails, prompts, tool-policies, and skills to path routes by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30263](https://github.com/BerriAI/litellm/pull/30263)
- feat(ui): migrate caching, cost-tracking, transform-request, ui-theme, and logs to path routes by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30267](https://github.com/BerriAI/litellm/pull/30267)
- fix(ui): gate dashboard layout on ui config load so deep links work under SERVER\_ROOT\_PATH by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30312](https://github.com/BerriAI/litellm/pull/30312)
- feat(ui): migrate admin-panel, logging-and-alerts, model-hub-table, and usage to path routes by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30268](https://github.com/BerriAI/litellm/pull/30268)
- fix(otel): cap metric attribute cardinality with include/exclude lists by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30257](https://github.com/BerriAI/litellm/pull/30257)
- fix(proxy): grace-period key rotation 401s; return deprecated-key lookup result directly by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30327](https://github.com/BerriAI/litellm/pull/30327)
- chore(deps): bump vitest, brace-expansion, pypdf and tornado by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30220](https://github.com/BerriAI/litellm/pull/30220)
- refactor(ui): remove unreachable /chat page by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30178](https://github.com/BerriAI/litellm/pull/30178)
- feat(ui): migrate agents and router-settings to path routes by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30323](https://github.com/BerriAI/litellm/pull/30323)
- feat: strengthen coding conventions in CLAUDE.md by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30333](https://github.com/BerriAI/litellm/pull/30333)
- feat(ui): cut the users page over to the /ui/users path route by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30334](https://github.com/BerriAI/litellm/pull/30334)
- feat: ruff strict-rule suppressions baseline gate by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30303](https://github.com/BerriAI/litellm/pull/30303)
- feat(guardrails): add Cisco AI Defense integration ([#&#8203;28249](https://github.com/BerriAI/litellm/issues/28249)) by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30338](https://github.com/BerriAI/litellm/pull/30338)
- chore(ui): remove dead UI components unreferenced by any page by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30340](https://github.com/BerriAI/litellm/pull/30340)
- ci: add osv-scanner lockfile scan workflow by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30222](https://github.com/BerriAI/litellm/pull/30222)
- fix(otel): record full error message on standard exception event in otel v2 by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30380](https://github.com/BerriAI/litellm/pull/30380)
- test(fireworks): mock whisper transcription tests instead of live calls by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30391](https://github.com/BerriAI/litellm/pull/30391)
- build(ui): pin esbuild to 0.28.1 via overrides by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30390](https://github.com/BerriAI/litellm/pull/30390)
- feat(ui): cut the organizations page over to the /ui/organizations path route by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30336](https://github.com/BerriAI/litellm/pull/30336)
- fix(proxy): support SMTP implicit SSL (port 465) by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30395](https://github.com/BerriAI/litellm/pull/30395)
- fix(mcp): default Linear MCP registry entry to streamable HTTP by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30396](https://github.com/BerriAI/litellm/pull/30396)
- fix(ui): stop Virtual Keys page from infinite render loop by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30397](https://github.com/BerriAI/litellm/pull/30397)
- fix(streaming): guard raise\_on\_model\_repetition against empty choices by [@&#8203;shivamrawat1](https://github.com/shivamrawat1) in [#&#8203;30485](https://github.com/BerriAI/litellm/pull/30485)
- feat(otel-v2): emit the 6 gen\_ai.client.\* metrics at parity with v1 by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30326](https://github.com/BerriAI/litellm/pull/30326)
- fix(mcp): drop phantom 401 span on delegated OAuth2 tool calls by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30494](https://github.com/BerriAI/litellm/pull/30494)
- feat(ui): cut the teams page over to the /ui/teams path route by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30343](https://github.com/BerriAI/litellm/pull/30343)
- fix(integrations): cap Anthropic cache\_control injection at 4 blocks by [@&#8203;shivamrawat1](https://github.com/shivamrawat1) in [#&#8203;30480](https://github.com/BerriAI/litellm/pull/30480)
- chore(codecov): add Batches, Videos, and Realtime components by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30517](https://github.com/BerriAI/litellm/pull/30517)
- test(batches): move orphan tests into tests/test\_litellm for CI coverage by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30510](https://github.com/BerriAI/litellm/pull/30510)
- fix(guardrails): run pre\_call hook once for model-level guardrails by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30543](https://github.com/BerriAI/litellm/pull/30543)
- fix(guardrails): stop re-initializing DB guardrails on every poll by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30542](https://github.com/BerriAI/litellm/pull/30542)
- chore(oss): litellm oss staging 150626 by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30463](https://github.com/BerriAI/litellm/pull/30463)
- ci(lint): add blanket-noqa, dataclass-default, and unused-noqa Ruff rules by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30516](https://github.com/BerriAI/litellm/pull/30516)
- ci: ratchet lint and type-check gates (ruff preview, ANN, mypy, basedpyright) by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30379](https://github.com/BerriAI/litellm/pull/30379)
- fix(proxy): allow internal roles to access vector store CRUD routes by [@&#8203;shivamrawat1](https://github.com/shivamrawat1) in [#&#8203;30503](https://github.com/BerriAI/litellm/pull/30503)
- fix(otel): stamp gen\_ai.input/output.messages on v2 spans by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30548](https://github.com/BerriAI/litellm/pull/30548)
- fix(otel): export v2 gen\_ai client metrics to the configured meter provider by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30549](https://github.com/BerriAI/litellm/pull/30549)
- fix(bedrock): preserve cache\_control for ARN models in /v1/messages adapter by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;29823](https://github.com/BerriAI/litellm/pull/29823)
- fix: greatly increase basedpyright slack by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30563](https://github.com/BerriAI/litellm/pull/30563)
- fix(budget): recompute budget\_reset\_at when budget\_duration changes on /budget/update by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30555](https://github.com/BerriAI/litellm/pull/30555)
- fix(otel): accept UPPER\_SNAKE\_CASE OTEL\_INSTRUMENTATION\_GENAI\_CAPTURE\_MESSAGE\_CONTENT in v2 by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30562](https://github.com/BerriAI/litellm/pull/30562)
- chore(lint): remove PLR0915 too-many-statements ruff rule by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30574](https://github.com/BerriAI/litellm/pull/30574)
- ci(lint): ratcheted type-discipline gate (mutable collections, casts, guards, kwargs, suppressions) by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30500](https://github.com/BerriAI/litellm/pull/30500)
- feat(proxy): add verification\_uri\_complete to CLI SSO device flow by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30571](https://github.com/BerriAI/litellm/pull/30571)
- chore: litellm oss staging160626 by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30527](https://github.com/BerriAI/litellm/pull/30527)
- fix(guardrails): return 400 not 500 when AIM blocks a request by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30573](https://github.com/BerriAI/litellm/pull/30573)
- ci(lint): grandfather any-discipline with a per-file ratchet budget (50% headroom) by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30582](https://github.com/BerriAI/litellm/pull/30582)
- fix(audio): don't override explicit response\_format with verbose\_json by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30599](https://github.com/BerriAI/litellm/pull/30599)
- fix(anthropic): price and surface response service\_tier in cost tracking by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30558](https://github.com/BerriAI/litellm/pull/30558)
- feat: add dev and wildcard proxy configs for local testing by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30556](https://github.com/BerriAI/litellm/pull/30556)
- fix(proxy): list public team model name in /v1/models by [@&#8203;ishaan-berri](https://github.com/ishaan-berri) in [#&#8203;30588](https://github.com/BerriAI/litellm/pull/30588)
- ci: drop mypy entirely, standardize type checking on basedpyright by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30648](https://github.com/BerriAI/litellm/pull/30648)
- feat(guardrails): surface OpenAI moderation violation\_categories on guardrail traces by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30659](https://github.com/BerriAI/litellm/pull/30659)
- fix(proxy): resolve list files credentials from team BYOK deployments by [@&#8203;shivamrawat1](https://github.com/shivamrawat1) in [#&#8203;30495](https://github.com/BerriAI/litellm/pull/30495)
- feat(proxy): add --max\_requests\_before\_restart\_jitter to stagger worker restarts by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30601](https://github.com/BerriAI/litellm/pull/30601)
- fix(health): correct bedrock embedding health checks by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30583](https://github.com/BerriAI/litellm/pull/30583)
- test: harden remaining pass-through CI flakes (image-gen spend poll, ruby assistants timeout) by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30685](https://github.com/BerriAI/litellm/pull/30685)
- test(pass\_through): harden vertex spendlog poll against transient empty reads by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30683](https://github.com/BerriAI/litellm/pull/30683)
- fix(cost): stop non-string service\_tier from silently dropping cost tracking by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30690](https://github.com/BerriAI/litellm/pull/30690)
- feat(proxy): warn at startup when custom\_auth skips common\_checks enforcement by [@&#8203;tin-berri](https://github.com/tin-berri) in [#&#8203;30665](https://github.com/BerriAI/litellm/pull/30665)
- fix(pod\_lock): release cron lock by matching async\_set\_cache JSON encoding by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30600](https://github.com/BerriAI/litellm/pull/30600)
- ci: run a local fake OpenAI endpoint instead of the shared Railway mock by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30695](https://github.com/BerriAI/litellm/pull/30695)
- ci(windows): pin uv to Python 3.11 so it ignores the preinstalled 3.14 by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30704](https://github.com/BerriAI/litellm/pull/30704)
- feat(ui): migrate models page to App Router path route by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30677](https://github.com/BerriAI/litellm/pull/30677)
- refactor(ui): remove orphaned pass-through-settings route by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30692](https://github.com/BerriAI/litellm/pull/30692)
- fix(cost): stop non-string response service\_tier from dropping cost tracking by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30706](https://github.com/BerriAI/litellm/pull/30706)
- feat(agent-shin): automated PR/issue triage, low-quality auto-close, and review-gate label lifecycle by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30433](https://github.com/BerriAI/litellm/pull/30433)
- chore: litellm oss 170626 by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30637](https://github.com/BerriAI/litellm/pull/30637)
- fix(bedrock\_mantle): add SigV4 fallback to chat completions auth by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30714](https://github.com/BerriAI/litellm/pull/30714)
- feat(search): add TinyFish as search provider by [@&#8203;simantak-dabhade](https://github.com/simantak-dabhade) in [#&#8203;30634](https://github.com/BerriAI/litellm/pull/30634)
- feat(ui): migrate old usage report to App Router path route by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30694](https://github.com/BerriAI/litellm/pull/30694)
- fix(proxy): enforce budgets against authoritative DB spend when the cross-pod counter is stale by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30684](https://github.com/BerriAI/litellm/pull/30684)
- chore(ci): remove Agent Shin pull\_request\_target workflows by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30784](https://github.com/BerriAI/litellm/pull/30784)
- chore: litellm oss staging by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30745](https://github.com/BerriAI/litellm/pull/30745)
- ci(zizmor): also run on litellm\_internal\_staging by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30789](https://github.com/BerriAI/litellm/pull/30789)
- fix(test): drop references to removed Agent Shin workflows by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30791](https://github.com/BerriAI/litellm/pull/30791)
- chore: remove in-product survey and Claude Code feedback nudges by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30773](https://github.com/BerriAI/litellm/pull/30773)
- feat(ui): migrate api-keys landing to App Router path route by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30699](https://github.com/BerriAI/litellm/pull/30699)
- feat(proxy): configurable response headers and login-page hint by [@&#8203;yucheng-berri](https://github.com/yucheng-berri) in [#&#8203;30792](https://github.com/BerriAI/litellm/pull/30792)
- ci(zizmor): gate PRs on medium+ findings and clear existing ones by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30797](https://github.com/BerriAI/litellm/pull/30797)
- fix(proxy): use e.request\_data for logging\_obj in ModifyResponseException streaming passthrough by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30800](https://github.com/BerriAI/litellm/pull/30800)
- chore: make pr template linear portion clearer by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30766](https://github.com/BerriAI/litellm/pull/30766)
- chore(typing): add boto3/botocore stubs so basedpyright resolves the AWS SDK by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30815](https://github.com/BerriAI/litellm/pull/30815)
- fix(otel): one v2 logger owns the global provider; scope tenant OTLP creds per exporter by [@&#8203;yucheng-berri](https://github.com/yucheng-berri) in [#&#8203;30590](https://github.com/BerriAI/litellm/pull/30590)
- fix(passthrough): recover output tokens for interrupted anthropic streams by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30787](https://github.com/BerriAI/litellm/pull/30787)
- fix(proxy): record partial spend on the failure row for interrupted streams by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30788](https://github.com/BerriAI/litellm/pull/30788)
- fix(ui): repoint dead usage guide link to cost tracking docs by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30859](https://github.com/BerriAI/litellm/pull/30859)
- fix(ui): warn that team models are deleted in the delete-team modal by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29990](https://github.com/BerriAI/litellm/pull/29990)
- feat(caching): add valkey-semantic cache backend and fix semantic cache scope keys by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30675](https://github.com/BerriAI/litellm/pull/30675)
- test(ui): isolate OldTeams delete-warning tests from leaked mock by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30871](https://github.com/BerriAI/litellm/pull/30871)
- feat: add lint-gate target and truncation-proof summary to the strict ruff gate by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30877](https://github.com/BerriAI/litellm/pull/30877)
- chore(ui): rebuild ui for release by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30894](https://github.com/BerriAI/litellm/pull/30894)
- chore(ci): bump deps by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30899](https://github.com/BerriAI/litellm/pull/30899)
- fix(watsonx): wrap string embedding input in array for WatsonX API by [@&#8203;shivamrawat1](https://github.com/shivamrawat1) in [#&#8203;30897](https://github.com/BerriAI/litellm/pull/30897)
- test: point router/completion/triton tests at the local fake OpenAI endpoint by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30900](https://github.com/BerriAI/litellm/pull/30900)
- feat(sandbox): e2b code execution primitive by [@&#8203;krrish-berri-2](https://github.com/krrish-berri-2) in [#&#8203;30898](https://github.com/BerriAI/litellm/pull/30898)
- fix(ui): source api-keys identity from useAuthorized to stop "User ID is not set" by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30903](https://github.com/BerriAI/litellm/pull/30903)
- chore(ui): rebuild ui by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30906](https://github.com/BerriAI/litellm/pull/30906)
- chore(ci): promote internal staging to main by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30907](https://github.com/BerriAI/litellm/pull/30907)
- fix(redis): prevent forcing SSLConnection when ssl=False in connection pool by [@&#8203;Jacopos311](https://github.com/Jacopos311) in [#&#8203;30770](https://github.com/BerriAI/litellm/pull/30770)
- fix(proxy): log UI setup failures instead of silently swallowing by [@&#8203;sarvesh1327](https://github.com/sarvesh1327) in [#&#8203;30819](https://github.com/BerriAI/litellm/pull/30819)

##### New Contributors

- [@&#8203;simantak-dabhade](https://github.com/simantak-dabhade) made their first contribution in [#&#8203;30634](https://github.com/BerriAI/litellm/pull/30634)
- [@&#8203;Jacopos311](https://github.com/Jacopos311) made their first contribution in [#&#8203;30770](https://github.com/BerriAI/litellm/pull/30770)
- [@&#8203;sarvesh1327](https://github.com/sarvesh1327) made their first contribution in [#&#8203;30819](https://github.com/BerriAI/litellm/pull/30819)

**Full Changelog**: <https://github.com/BerriAI/litellm/compare/v1.89.0...v1.90.0>

### [`v1.90.0`](https://github.com/BerriAI/litellm/releases/tag/v1.90.0)

[Compare Source](https://github.com/BerriAI/litellm/compare/v1.89.4...v1.90.0)

##### Verify Docker Image Signature

All LiteLLM Docker images are signed with [cosign](https://docs.sigstore.dev/cosign/overview/). Every release is signed with the same key introduced in [commit `0112e53`](https://github.com/BerriAI/litellm/commit/0112e53046018d726492c814b3644b7d376029d0).

**Verify using the pinned commit hash (recommended):**

A commit hash is cryptographically immutable, so this is the strongest way to ensure you are using the original signing key:

```bash
cosign verify \
  --key https://raw.githubusercontent.com/BerriAI/litellm/0112e53046018d726492c814b3644b7d376029d0/cosign.pub \
  ghcr.io/berriai/litellm:v1.90.0
```

**Verify using the release tag (convenience):**

Tags are protected in this repository and resolve to the same key. This option is easier to read but relies on tag protection rules:

```bash
cosign verify \
  --key https://raw.githubusercontent.com/BerriAI/litellm/v1.90.0/cosign.pub \
  ghcr.io/berriai/litellm:v1.90.0
```

Expected output:

```
The following checks were performed on each of these signatures:
  - The cosign claims were validated
  - The signatures were verified against the specified public key
```

***

##### What's Changed

- fix(responses-bridge): map system-only chat request to system input item by [@&#8203;milan-berri](https://github.com/milan-berri) in [#&#8203;29817](https://github.com/BerriAI/litellm/pull/29817)
- feat(bedrock): forward strict and additionalProperties to Converse toolSpec by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;29814](https://github.com/BerriAI/litellm/pull/29814)
- fix(mcp): highlight MCP cards red when the logged-in user is missing per-user env vars by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;29856](https://github.com/BerriAI/litellm/pull/29856)
- feat(ui): add budget duration to edit team member form by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;29717](https://github.com/BerriAI/litellm/pull/29717)
- fix(ui): make workflow runs page fill full width by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29868](https://github.com/BerriAI/litellm/pull/29868)
- feat: standardize rate limit errors with category, rate\_limit\_type, model, and llm\_provider fields by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;27687](https://github.com/BerriAI/litellm/pull/27687)
- fix(ui): default guardrails page to the Guardrails tab by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29872](https://github.com/BerriAI/litellm/pull/29872)
- docs(readme): add Deploy on AWS/GCP Terraform section and fix deploy button rendering by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;29879](https://github.com/BerriAI/litellm/pull/29879)
- refactor(bedrock): build Converse toolSpec via a BedrockToolSpec dict subclass by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;29869](https://github.com/BerriAI/litellm/pull/29869)
- feat(litellm): add models and repository layers by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;29686](https://github.com/BerriAI/litellm/pull/29686)
- feat(ui): include internal routes in the dashboard's generated OpenAPI types by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;29885](https://github.com/BerriAI/litellm/pull/29885)
- feat(proxy): publish /v2/model/info in Swagger OpenAPI spec by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;29900](https://github.com/BerriAI/litellm/pull/29900)
- refactor(ui): single source of truth for migrated-page routing by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;29949](https://github.com/BerriAI/litellm/pull/29949)
- fix(ui/model-hub): render provider icons on the public model hub by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29958](https://github.com/BerriAI/litellm/pull/29958)
- fix(ui): keep create guardrail modal open on outside click by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29871](https://github.com/BerriAI/litellm/pull/29871)
- fix(ui): label default key type as "Full Access" on key edit page by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29870](https://github.com/BerriAI/litellm/pull/29870)
- fix(ui): unify migrated-route URLs and migrate the API Reference page by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;29953](https://github.com/BerriAI/litellm/pull/29953)
- fix(mcp): let non-creator users OAuth into OBO-mode MCP servers from the Tools page by [@&#8203;tin-berri](https://github.com/tin-berri) in [#&#8203;29867](https://github.com/BerriAI/litellm/pull/29867)
- Litellm oss staging 080626 by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;29932](https://github.com/BerriAI/litellm/pull/29932)
- feat(galileo): add health check support for UI callback test by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;29908](https://github.com/BerriAI/litellm/pull/29908)
- fix(model-management): allow deleting a BYOK model after its team is deleted by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29875](https://github.com/BerriAI/litellm/pull/29875)
- feat(jwt-auth): opt-in fallback to DB team on unresolved JWT claim by [@&#8203;milan-berri](https://github.com/milan-berri) in [#&#8203;28913](https://github.com/BerriAI/litellm/pull/28913)
- fix(team\_endpoints): don't block /team/update on unchanged team budget by [@&#8203;milan-berri](https://github.com/milan-berri) in [#&#8203;29525](https://github.com/BerriAI/litellm/pull/29525)
- fix(fireworks): enable tool calling for glm-5p1 in model cost map by [@&#8203;milan-berri](https://github.com/milan-berri) in [#&#8203;29697](https://github.com/BerriAI/litellm/pull/29697)
- fix(vertex): propagate Vertex AI metadata in streaming success callbacks by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;29899](https://github.com/BerriAI/litellm/pull/29899)
- fix(ui): show team projects to internal users on key creation by [@&#8203;milan-berri](https://github.com/milan-berri) in [#&#8203;28855](https://github.com/BerriAI/litellm/pull/28855)
- build(deps): bump pyjwt to 2.13.0 and ws override to 8.20.1 by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29982](https://github.com/BerriAI/litellm/pull/29982)
- fix(team-management): delete a team's BYOK models when the team is deleted by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29977](https://github.com/BerriAI/litellm/pull/29977)
- feat(vantage): include organization metadata in FOCUS Tags export by [@&#8203;milan-berri](https://github.com/milan-berri) in [#&#8203;28184](https://github.com/BerriAI/litellm/pull/28184)
- fix(guardrails): read CrowdStrike AIDR identity from both metadata bags by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;29991](https://github.com/BerriAI/litellm/pull/29991)
- fix(mcp): mirror upstream token lifetime instead of forcing a 1h OBO expiry by [@&#8203;tin-berri](https://github.com/tin-berri) in [#&#8203;29951](https://github.com/BerriAI/litellm/pull/29951)
- feat(azure\_ai): add MAI-Image-2.5 image generation support by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;29688](https://github.com/BerriAI/litellm/pull/29688)
- fix(mcp): load MCP tool configuration tools via the OBO/passthrough-aware GET path by [@&#8203;tin-berri](https://github.com/tin-berri) in [#&#8203;29960](https://github.com/BerriAI/litellm/pull/29960)
- fix(team): reserve team budget raises for proxy admins on /team/update by [@&#8203;milan-berri](https://github.com/milan-berri) in [#&#8203;30030](https://github.com/BerriAI/litellm/pull/30030)
- test(ui): data-driven App Router migration E2E smoke (default + server-root-path) by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;29974](https://github.com/BerriAI/litellm/pull/29974)
- fix(proxy): extend response headers hook to streaming, TTS, image gen, and pass-through by [@&#8203;michelligabriele](https://github.com/michelligabriele) in [#&#8203;24232](https://github.com/BerriAI/litellm/pull/24232)
- chore(ui): remove dead App Router route stubs under (dashboard) by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30045](https://github.com/BerriAI/litellm/pull/30045)
- fix(ui/mcp): reset OAuth state on create-server modal close so a prior server's token no longer leaks into the next add-server session by [@&#8203;tin-berri](https://github.com/tin-berri) in [#&#8203;30000](https://github.com/BerriAI/litellm/pull/30000)
- fix(mcp): allow team access-group grants in OAuth authorize/token access check by [@&#8203;tin-berri](https://github.com/tin-berri) in [#&#8203;30041](https://github.com/BerriAI/litellm/pull/30041)
- docs(security): require a reproduction video for vulnerability reports by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30063](https://github.com/BerriAI/litellm/pull/30063)
- feat(ui): add admin flag to disable in-product UI nudges for everyone by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;29796](https://github.com/BerriAI/litellm/pull/29796)
- chore(ui): remove dead dashboard files and unused dependencies by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30047](https://github.com/BerriAI/litellm/pull/30047)
- fix(proxy): authorize batch files using upload target\_model\_names (LIT-3593) by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30009](https://github.com/BerriAI/litellm/pull/30009)
- Add Claude Fable 5 across Anthropic, Bedrock, Vertex AI, and Azure AI by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30064](https://github.com/BerriAI/litellm/pull/30064)
- Add Claude Fable 5 cost map entries (data-only hotfix for the hosted map) by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30076](https://github.com/BerriAI/litellm/pull/30076)
- fix(caching): restore stored prompt\_tokens on embedding cache hits instead of recomputing by [@&#8203;michelligabriele](https://github.com/michelligabriele) in [#&#8203;30046](https://github.com/BerriAI/litellm/pull/30046)
- Litellm oss 090626 by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30021](https://github.com/BerriAI/litellm/pull/30021)
- fix(proxy): self-heal startup/reload prisma reads on engine disconnect by [@&#8203;michelligabriele](https://github.com/michelligabriele) in [#&#8203;28803](https://github.com/BerriAI/litellm/pull/28803)
- chore(ui): make knip recognize .mjs scripts and openapi-typescript by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30052](https://github.com/BerriAI/litellm/pull/30052)
- fix(register\_model): preserve built-in cache pricing when registering custom overrides under unmapped keys by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30044](https://github.com/BerriAI/litellm/pull/30044)
- \[internal copy of [#&#8203;28007](https://github.com/BerriAI/litellm/issues/28007)] Fix/gcp model garden streaming by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;28363](https://github.com/BerriAI/litellm/pull/28363)
- feat(cli): per-agent `lite claude` / `codex` / `opencode` commands that wrap coding agents through the proxy by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;29850](https://github.com/BerriAI/litellm/pull/29850)
- fix(callbacks): forward callback\_settings to callback initializers and guard consumers against non-dict values by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30161](https://github.com/BerriAI/litellm/pull/30161)
- fix(mcp): drop orphaned per-user credential rows when an MCP server is deleted by [@&#8203;tin-berri](https://github.com/tin-berri) in [#&#8203;30141](https://github.com/BerriAI/litellm/pull/30141)
- fix(proxy): recover from cached-plan errors by reconnecting the Prisma client by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;29983](https://github.com/BerriAI/litellm/pull/29983)
- feat(proxy): add option to disable server-side prepared statements for DB lookups by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;29984](https://github.com/BerriAI/litellm/pull/29984)
- fix(release): stop backport releases from overwriting the latest badge by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30005](https://github.com/BerriAI/litellm/pull/30005)
- feat: add conventional commits and coding guidelines by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30159](https://github.com/BerriAI/litellm/pull/30159)
- fix(proxy): return 5xx on DB infra errors during auth; reserve 401 for genuine auth failures by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;29986](https://github.com/BerriAI/litellm/pull/29986)
- fix(ui): dev server 404s on migrated-page links because uiBase hardcodes /ui by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30169](https://github.com/BerriAI/litellm/pull/30169)
- refactor(ui): consolidate dashboard to one shell in the (dashboard) layout by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30166](https://github.com/BerriAI/litellm/pull/30166)
- fix(proxy): align /v1/model/info with router deployments by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30025](https://github.com/BerriAI/litellm/pull/30025)
- fix: completion\_cost AttributeError on streaming Anthropic web\_search responses ([#&#8203;26153](https://github.com/BerriAI/litellm/issues/26153)) by [@&#8203;ishaan-berri](https://github.com/ishaan-berri) in [#&#8203;27346](https://github.com/BerriAI/litellm/pull/27346)
- \[internal copy of [#&#8203;30137](https://github.com/BerriAI/litellm/issues/30137)] perf(realtime): eliminate redundant per-frame JSON work on OpenAI realtime relay by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30142](https://github.com/BerriAI/litellm/pull/30142)
- feat(bedrock): aws\_bedrock\_project\_id for bedrock-mantle project / workspace association by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30163](https://github.com/BerriAI/litellm/pull/30163)
- chore(hooks): enforce Conventional Commits and Conventional Branches by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30174](https://github.com/BerriAI/litellm/pull/30174)
- feat(rate-limiter): allow opting out of v3 TPM reservation and Redis circuit breaker by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30211](https://github.com/BerriAI/litellm/pull/30211)
- feat(spend\_logs): opt-in native Postgres partitioning for SpendLogs retention by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;29466](https://github.com/BerriAI/litellm/pull/29466)
- feat(ui): migrate playground to path routing and colocate its files by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30185](https://github.com/BerriAI/litellm/pull/30185)
- feat(ui): migrate projects and access-groups to path routes by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30226](https://github.com/BerriAI/litellm/pull/30226)
- fix(proxy): coalesce NULL rollup metrics in aggregated daily-activity by [@&#8203;michelligabriele](https://github.com/michelligabriele) in [#&#8203;30151](https://github.com/BerriAI/litellm/pull/30151)
- fix(anthropic\_passthrough): resolve costing model from message\_start chunk, litellm\_params and model\_group instead of 'unknown' by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30160](https://github.com/BerriAI/litellm/pull/30160)
- feat(ui): migrate budgets, workflows, and guardrails-monitor to path routes by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30236](https://github.com/BerriAI/litellm/pull/30236)
- feat(ui): migrate mcp-servers, search-tools, tag-management, vector-stores, and memory to path routes by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30261](https://github.com/BerriAI/litellm/pull/30261)
- fix(a2a): forward agent\_extra\_headers through completion bridge by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;28277](https://github.com/BerriAI/litellm/pull/28277)
- fix(gemini-live): forward audio buffer commit and correct Vertex PCM rate by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;29946](https://github.com/BerriAI/litellm/pull/29946)
- fix(proxy): skip double-wrapping unified batch output file ids on retrieve by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30011](https://github.com/BerriAI/litellm/pull/30011)
- feat: litellm oss 110626 by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30202](https://github.com/BerriAI/litellm/pull/30202)
- fix(docker): copy only runtime artifacts into the final image by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30243](https://github.com/BerriAI/litellm/pull/30243)
- feat(proxy): enforce key/team guardrails on bedrock passthrough routes by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30194](https://github.com/BerriAI/litellm/pull/30194)
- feat(gemini): forward web search tools in image generation by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30119](https://github.com/BerriAI/litellm/pull/30119)
- fix: bedrock mantle fixes by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30083](https://github.com/BerriAI/litellm/pull/30083)
- feat(proxy): add require\_managed\_files setting for file uploads by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30186](https://github.com/BerriAI/litellm/pull/30186)
- fix(mcp): honor server\_id for REST tool calls with shared upstream URLs by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30184](https://github.com/BerriAI/litellm/pull/30184)
- fix(responses): presidio PII masking for Azure WebSocket and streaming by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30003](https://github.com/BerriAI/litellm/pull/30003)
- feat(passthrough): add configurable pass-through request timeouts by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30266](https://github.com/BerriAI/litellm/pull/30266)
- fix(google\_genai): preserve complete SSE events in Vertex/Gemini image streaming by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30270](https://github.com/BerriAI/litellm/pull/30270)
- fix(proxy): populate access\_via\_team\_ids on /v1/model/info by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30274](https://github.com/BerriAI/litellm/pull/30274)
- chore(oss): litellm oss staging 120626 by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30292](https://github.com/BerriAI/litellm/pull/30292)
- feat(ui): migrate policies, guardrails, prompts, tool-policies, and skills to path routes by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30263](https://github.com/BerriAI/litellm/pull/30263)
- feat(ui): migrate caching, cost-tracking, transform-request, ui-theme, and logs to path routes by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30267](https://github.com/BerriAI/litellm/pull/30267)
- fix(ui): gate dashboard layout on ui config load so deep links work under SERVER\_ROOT\_PATH by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30312](https://github.com/BerriAI/litellm/pull/30312)
- feat(ui): migrate admin-panel, logging-and-alerts, model-hub-table, and usage to path routes by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30268](https://github.com/BerriAI/litellm/pull/30268)
- fix(otel): cap metric attribute cardinality with include/exclude lists by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30257](https://github.com/BerriAI/litellm/pull/30257)
- fix(proxy): grace-period key rotation 401s; return deprecated-key lookup result directly by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30327](https://github.com/BerriAI/litellm/pull/30327)
- chore(deps): bump vitest, brace-expansion, pypdf and tornado by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30220](https://github.com/BerriAI/litellm/pull/30220)
- refactor(ui): remove unreachable /chat page by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30178](https://github.com/BerriAI/litellm/pull/30178)
- feat(ui): migrate agents and router-settings to path routes by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30323](https://github.com/BerriAI/litellm/pull/30323)
- feat: strengthen coding conventions in CLAUDE.md by [@&#8203;mateo-berri](https://github.com/mateo-berri) in [#&#8203;30333](https://github.com/BerriAI/litellm/pull/30333)
- feat(ui): cut the users page over to the /ui/users path route by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30334](https://github.com/BerriAI/litellm/pull/30334)
- feat: ruff strict-rule suppressions baseline gate by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30303](https://github.com/BerriAI/litellm/pull/30303)
- feat(guardrails): add Cisco AI Defense integration ([#&#8203;28249](https://github.com/BerriAI/litellm/issues/28249)) by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30338](https://github.com/BerriAI/litellm/pull/30338)
- chore(ui): remove dead UI components unreferenced by any page by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30340](https://github.com/BerriAI/litellm/pull/30340)
- ci: add osv-scanner lockfile scan workflow by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30222](https://github.com/BerriAI/litellm/pull/30222)
- fix(otel): record full error message on standard exception event in otel v2 by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30380](https://github.com/BerriAI/litellm/pull/30380)
- test(fireworks): mock whisper transcription tests instead of live calls by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30391](https://github.com/BerriAI/litellm/pull/30391)
- build(ui): pin esbuild to 0.28.1 via overrides by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30390](https://github.com/BerriAI/litellm/pull/30390)
- feat(ui): cut the organizations page over to the /ui/organizations path route by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30336](https://github.com/BerriAI/litellm/pull/30336)
- fix(proxy): support SMTP implicit SSL (port 465) by [@&#8203;yuneng-berri](https://github.com/yuneng-berri) in [#&#8203;30395](https://github.com/BerriAI/litellm/pull/30395)
- fix(mcp): default Linear MCP registry entry to streamable HTTP by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30396](https://github.com/BerriAI/litellm/pull/30396)
- fix(ui): stop Virtual Keys page from infinite render loop by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30397](https://github.com/BerriAI/litellm/pull/30397)
- fix(streaming): guard raise\_on\_model\_repetition against empty choices by [@&#8203;shivamrawat1](https://github.com/shivamrawat1) in [#&#8203;30485](https://github.com/BerriAI/litellm/pull/30485)
- feat(otel-v2): emit the 6 gen\_ai.client.\* metrics at parity with v1 by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30326](https://github.com/BerriAI/litellm/pull/30326)
- fix(mcp): drop phantom 401 span on delegated OAuth2 tool calls by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30494](https://github.com/BerriAI/litellm/pull/30494)
- feat(ui): cut the teams page over to the /ui/teams path route by [@&#8203;ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#&#8203;30343](https://github.com/BerriAI/litellm/pull/30343)
- fix(integrations): cap Anthropic cache\_control injection at 4 blocks by [@&#8203;shivamrawat1](https://github.com/shivamrawat1) in [#&#8203;30480](https://github.com/BerriAI/litellm/pull/30480)
- chore(codecov): add Batches, Videos, and Realtime components by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30517](https://github.com/BerriAI/litellm/pull/30517)
- test(batches): move orphan tests into tests/test\_litellm for CI coverage by [@&#8203;Sameerlite](https://github.com/Sameerlite) in [#&#8203;30510](https://github.com/BerriAI/litellm/pull/30510)
- fix(guardrails): run pre\_call hook once for model-level guardrails by [@&#8203;yassin-berriai](https://github.com/yassin-berriai) in [#&#8203;30543](http…