feat(focus): add GCS destination for FOCUS export#29751
Merged
Sameerlite merged 6 commits intoJun 8, 2026
Merged
Conversation
Contributor
Greptile SummaryThis PR adds
Confidence Score: 5/5Safe to merge; the change is well-scoped, auth credential handling is correct, and the new code path is fully covered by mock unit tests. The implementation is a clean, narrow addition that reuses existing infrastructure. The credential-precedence fix is properly guarded and verified by regression tests. The only notable limitation is the 5 MB ceiling inherent to GCS simple media uploads, which is the same pattern already in use elsewhere in the codebase. No files require special attention, though gcs_destination.py's use of uploadType=media is worth a second look if large FOCUS payloads are expected in production.
|
| Filename | Overview |
|---|---|
| litellm/integrations/focus/destinations/gcs_destination.py | New FocusGCSDestination class reusing GCSBucketBase auth; correctly guards against overwriting global GCS_PATH_SERVICE_ACCOUNT; upload uses uploadType=media (5 MB GCS simple-upload ceiling) |
| litellm/integrations/focus/destinations/factory.py | Adds GCS branch to create() and _resolve_config(); filters None values before passing to FocusGCSDestination so the global GCS_PATH_SERVICE_ACCOUNT is preserved when FOCUS_GCS_PATH_SERVICE_ACCOUNT is absent |
| litellm/integrations/focus/destinations/init.py | Exports FocusGCSDestination alongside existing destinations; no issues |
| tests/test_litellm/integrations/focus/test_focus_gcs_destination.py | 8 new unit tests covering upload, error handling, object key layout, and credential-precedence regression; all mock-only with no real network calls |
Reviews (2): Last reviewed commit: "style: apply Black formatting to factory..." | Re-trigger Greptile
![greptile-apps[bot]](https://avatars.githubusercontent.com/in/867647?s=60&v=4){kind=small}
Codecov Report❌ Patch coverage is
📢 Thoughts on this report? Let us know! |
Contributor
Author
pghuge-cloudwiz
force-pushed
the
feat/focus-gcs-destination
branch
from
540c7df to
78b9e96
Compare
Sameerlite
changed the base branch from
litellm_internal_staging
to
litellm_oss_staging_080626
Sameerlite
merged commit b93656f
into
BerriAI:litellm_oss_staging_080626
68 of 70 checks passed
7 tasks
mateo-berri
pushed a commit
that referenced
this pull request
Jun 8, 2026
* feat(bedrock_mantle): add SigV4/IAM auth to Responses API route (fixes #29665) (#29788) * feat(responses): add default no-op sign_request to BaseResponsesAPIConfig * feat(responses): call sign_request after body is final, send signed bytes when signed * feat(bedrock_mantle): add SigV4 sign_request via composed BaseAWSLLM (bearer path) * test(bedrock_mantle): cover SigV4 access-key, AssumeRole, body bytes, region/auth consistency * feat(bedrock_mantle): defer auth to sign_request; validate_environment no longer requires bearer * docs(bedrock_mantle): document SigV4 + Bearer auth on Responses route * test(responses): cover fake-stream signing order and mantle bearer arg/env precedence * fix(bedrock_mantle): wrap all botocore credential errors with both-paths guidance * fix(bedrock_mantle): catch specific credential errors, not all BotoCoreError, so STS transport failures are not masked * fix(bedrock_mantle): sign the compact Responses route too, not just create * fix(github-copilot): route per-model on /v1/responses based on model info (#29747) * feat(focus): add GCS destination for FOCUS export (#29751) * test: add failing tests for FocusGCSDestination * feat: add FocusGCSDestination reusing GCSBucketBase auth * feat: register FocusGCSDestination in factory; export from __init__ * fix(focus): preserve GCS_PATH_SERVICE_ACCOUNT when service_account_json not in config * style: apply Black formatting to gcs_destination and tests * style: apply Black formatting to factory.py * fix(bedrock): omit empty additionalModelRequestFields and system from Converse API payload (#29565) Amazon Nova Pro (and other strict Bedrock models) return 400 Malformed input request when additionalModelRequestFields: {} or system: [] are present in the payload. Both fields are optional in CommonRequestObject (total=False) and must be omitted rather than sent as empty structures. Co-authored-by: shin-berri <[email protected]> Co-authored-by: yuneng-jiang <[email protected]> Co-authored-by: Claude Sonnet 4.6 <[email protected]> * fix(proxy): recognize *.cognitiveservices.azure.com as OpenAI-compatible in pass-through cost tracking (#29730) * fix(proxy): recognize *.cognitiveservices.azure.com as OpenAI-compatible Azure OpenAI resources created via the newer "Azure AI Foundry" / Cognitive Services pathway live on `*.cognitiveservices.azure.com` subdomains, not the older `openai.azure.com`. Both are valid Azure OpenAI surfaces in production today. The OpenAI pass-through cost-tracking handler hard-codes only the older hostname in five places (four `is_openai_*_route` methods on OpenAIPassthroughLoggingHandler, plus is_openai_route on PassThroughEndpointLogging). As a result, calls from newer Azure deployments are silently classified as "not an OpenAI route", the dispatch into the cost-tracking handler is skipped, and tokens/cost never get extracted into LiteLLM_SpendLogs — the row gets written with prompt_tokens=0, completion_tokens=0, spend=0, model='unknown'. Reproduced 2026-06-04 against a real Azure OpenAI deployment on `*.cognitiveservices.azure.com` proxied through LiteLLM v1.88.0. Fix: factor the hostname check into a single helper `_is_openai_compatible_host` listing all three recognized surfaces (api.openai.com, openai.azure.com, cognitiveservices.azure.com), and have all five call sites delegate to it. Purely additive — never weakens recognition for the originally-supported hostnames. Adds a test `test_is_openai_route_recognizes_cognitiveservices_azure_com` that exercises all four `is_openai_*_route` static methods against `*.cognitiveservices.azure.com` URLs (positive cases per route + a small cross-route negative to confirm route-specific path matching still works on the new hostname). Out of scope for this PR (separate followup): - `openai_passthrough_handler` calls chat/completions `transform_response` on Responses API payloads (`output:` not `choices:`), which throws inside the dispatch and drops the SpendLogs row entirely. Recognized + tracked separately. * ci: trigger fresh run Empty commit to re-run checks. The previous auth-and-jwt failure was a transient HuggingFace Hub 429 rate-limit hitting tokenizer downloads in tests/proxy_unit_tests/test_custom_tokenizer_bug.py — unrelated to this PR's scope (hostname recognition in pass-through cost tracking). No code change. --------- Co-authored-by: shin-berri <[email protected]> Co-authored-by: yuneng-jiang <[email protected]> * fix(responses): preserve forced-function tool_choice name in Responses to Chat transform (#29812) The Responses API forces a specific function with a top-level name ({"type": "function", "name": "X"}), but _transform_tool_choice only handled the nested Chat Completions shape and fell through to returning "required" for the flat form, silently dropping the function name and degrading a forced function call to force-any-tool. Map the flat Responses shape to the nested Chat shape, keeping the "required" fallback when no name is present. * Preserve x-anthropic-billing-header system blocks for first-party Anthropic (#29584) * Preserve x-anthropic-billing-header system blocks for first-party Anthropic PR #20951 strips system blocks beginning with "x-anthropic-billing-header:" for every Anthropic target. That block is how the first-party Anthropic API recognizes Claude Code subscription (OAuth) traffic, so dropping it makes requests that carry only that block, such as the auto-mode tool-safety classifier, fail with a misleading 429 rate_limit_error; normal turns still work because they also carry the "You are Claude Code" identity block. Gate the strip behind should_strip_billing_metadata(), defaulting to False on the first-party AnthropicConfig and AnthropicMessagesConfig so the block is kept, and overridden to True on the providers that reach these transforms and reject the block (Bedrock platform, Vertex, Azure for the chat path; Minimax, Azure, DeepSeek for the messages path). Behavior for those providers is unchanged. * Strip billing header on Bedrock invoke and Vertex messages pass-through Two more subclasses reach the gated strip but inherited keep-by-default. AmazonAnthropicClaudeConfig (Bedrock invoke) calls AnthropicConfig.transform_request, which calls translate_system_message, and VertexAIPartnerModelsAnthropicMessagesConfig (Vertex messages pass-through) calls super().transform_anthropic_messages_request. Override should_strip_billing_metadata() to True on both. Add a parametrized test asserting the flag for every first-party base (False) and provider subclass (True), covering all overrides, plus a translate_system_message regression test for the Bedrock invoke path. * fix(cache): log hashed cache keys (#29890) * fix(ui): save routing groups as list (#29889) * Revert "fix(ui): save routing groups as list (#29889)" (#29928) This reverts commit 9b1f78f. * feat(parasail): add Parasail as a JSON-configured OpenAI-compatible provider (#29842) * feat(parasail): add Parasail as a JSON-configured OpenAI-compatible provider Registers parasail in the openai_like JSON provider loader with both /v1/chat/completions and /v1/responses support. Parasail's Responses API rejects store:true and any request that omits store, so the loader gains a force_store_false special_handling flag; the parasail entry sets it and the generated Responses config overrides store=false on every call. This keeps callers from hitting "State storage not supported" and matches what Parasail's docs require. Adds the PARASAIL enum value, listing under openai_compatible_providers, provider documentation at docs/my-website/docs/providers/parasail.md, and a focused unit test file under tests/test_litellm/llms/parasail/ that covers JSON registration, chat URL construction, Responses URL construction with PARASAIL_API_BASE override, and the force_store_false regression in both the caller-sent-store=true and caller-omitted cases. * fix(parasail): register in provider_endpoints_support, drop in-repo docs Greptile review feedback. The provider doc belongs in the litellm-docs repo, not this one's docs/my-website tree; removing it here. Adds the parasail entry to provider_endpoints_support.json so the check_provider_folders_documented.py CI check passes (chat_completions and responses true; others false). * fix: normalize Anthropic passthrough server tool usage (#29827) * test(anthropic): cover server_tool_use dict cost tracking * fix: normalize Anthropic server tool usage (cherry picked from commit 982f726) * fix: keep server tool usage subscriptable (cherry picked from commit 70280b9) --------- Co-authored-by: Genmin <[email protected]> * fix(proxy): fix typo generic_role_mappoings -> generic_role_mappings in ui_sso.py (#29753) Co-authored-by: shin-berri <[email protected]> Co-authored-by: yuneng-jiang <[email protected]> * feat(proxy): add disable_budget_reservation general setting (#27639) (#29493) * feat(proxy): add disable_budget_reservation general setting (#27639) * feat(proxy): register disable_budget_reservation in ConfigGeneralSettings (#27639) * docs(proxy): document disable_budget_reservation concurrency tradeoff (#27639) * ci: re-trigger flaky docker build (prisma generate ECONNRESET) * fix(proxy): warn and document budget enforcement tradeoff when disable_budget_reservation is set (#27639) * feat(gemini_tts): adding support to Gemini TTS languageCode parameters (#29623) * Adding support to Gemini TTS Language Code parameters * Mapping Gemini TTS languageCode param in Docstring * Use snake_case for language_code input keyMapping Gemini TTS languageCode param in Docstring * Restoring files modified under enterprise/litellm_enterprise due to lint/formatting checks --------- Co-authored-by: João Garrido <[email protected]> * feat(guardrails): capture user and model metadata in CrowdStrike AIDR (#29517) * fix(proxy): require OpenAI path segment for shared Azure Cognitive Services domains Address Greptile review: the `*.cognitiveservices.azure.com` / `*.openai.azure.com` domains are shared by every Azure Cognitive Service (Speech, Vision, Language, ...), so a hostname-only substring match misclassified non-OpenAI Azure traffic as OpenAI routes. - Replace the substring host test with suffix matching (rejects look-alike domains like cognitiveservices.azure.com.attacker.example). - Add `_is_openai_compatible_url` that requires an OpenAI-style path marker (`/openai/` or `/v1/`) on the shared Azure domains, and use it in PassThroughEndpointLogging.is_openai_route (previously hostname-only). - Add negative tests for Azure Speech/Vision paths and look-alike domains. Co-Authored-By: Claude Opus 4.8 <[email protected]> * fix: support Responses input in Redis semantic cache (#29581) * fix: support responses input in redis semantic cache * test: cover redis semantic prompt extraction * test: handle blank redis semantic text fallbacks * chore: remove async cache dead statement * test: cover redis semantic cache miss paths * fix: filter sensitive cache lookup kwargs * chore: rerun ci after huggingface rate limit * chore(ui): regenerate dashboard API types (npm run gen:api) Sync src/lib/http/schema.d.ts with the proxy OpenAPI spec: adds the disable_budget_reservation general-settings field and picks up the RateLimitError docstring reindent. Fixes the gen:api CI drift check. Co-Authored-By: Claude Opus 4.8 <[email protected]> * test(bedrock): assert empty additionalModelRequestFields is omitted The Converse transformer now drops an empty additionalModelRequestFields block instead of sending it as `{}`. Update test_bedrock_top_k_param so models without top_k support (llama3) assert the key is absent rather than equal to an empty dict. Co-Authored-By: Claude Opus 4.8 <[email protected]> --------- Co-authored-by: Kent <[email protected]> Co-authored-by: codgician <[email protected]> Co-authored-by: Praveen Ghuge <[email protected]> Co-authored-by: Roi <[email protected]> Co-authored-by: shin-berri <[email protected]> Co-authored-by: yuneng-jiang <[email protected]> Co-authored-by: Claude Sonnet 4.6 <[email protected]> Co-authored-by: Liam Scott <[email protected]> Co-authored-by: abhay23-AI <[email protected]> Co-authored-by: Ceder Dens <[email protected]> Co-authored-by: 冯基魁 <[email protected]> Co-authored-by: Kai Huang <[email protected]> Co-authored-by: rinto <[email protected]> Co-authored-by: Genmin <[email protected]> Co-authored-by: Arnav Bhilwariya <[email protected]> Co-authored-by: Armaan Sandhu <[email protected]> Co-authored-by: João Garrido <[email protected]> Co-authored-by: João Garrido <[email protected]> Co-authored-by: Kenan Yildirim <[email protected]> Co-authored-by: Dávid Balatoni <[email protected]>
michaelxer
pushed a commit
to michaelxer/litellm
that referenced
this pull request
Jun 17, 2026
* feat(bedrock_mantle): add SigV4/IAM auth to Responses API route (fixes BerriAI#29665) (BerriAI#29788) * feat(responses): add default no-op sign_request to BaseResponsesAPIConfig * feat(responses): call sign_request after body is final, send signed bytes when signed * feat(bedrock_mantle): add SigV4 sign_request via composed BaseAWSLLM (bearer path) * test(bedrock_mantle): cover SigV4 access-key, AssumeRole, body bytes, region/auth consistency * feat(bedrock_mantle): defer auth to sign_request; validate_environment no longer requires bearer * docs(bedrock_mantle): document SigV4 + Bearer auth on Responses route * test(responses): cover fake-stream signing order and mantle bearer arg/env precedence * fix(bedrock_mantle): wrap all botocore credential errors with both-paths guidance * fix(bedrock_mantle): catch specific credential errors, not all BotoCoreError, so STS transport failures are not masked * fix(bedrock_mantle): sign the compact Responses route too, not just create * fix(github-copilot): route per-model on /v1/responses based on model info (BerriAI#29747) * feat(focus): add GCS destination for FOCUS export (BerriAI#29751) * test: add failing tests for FocusGCSDestination * feat: add FocusGCSDestination reusing GCSBucketBase auth * feat: register FocusGCSDestination in factory; export from __init__ * fix(focus): preserve GCS_PATH_SERVICE_ACCOUNT when service_account_json not in config * style: apply Black formatting to gcs_destination and tests * style: apply Black formatting to factory.py * fix(bedrock): omit empty additionalModelRequestFields and system from Converse API payload (BerriAI#29565) Amazon Nova Pro (and other strict Bedrock models) return 400 Malformed input request when additionalModelRequestFields: {} or system: [] are present in the payload. Both fields are optional in CommonRequestObject (total=False) and must be omitted rather than sent as empty structures. Co-authored-by: shin-berri <[email protected]> Co-authored-by: yuneng-jiang <[email protected]> Co-authored-by: Claude Sonnet 4.6 <[email protected]> * fix(proxy): recognize *.cognitiveservices.azure.com as OpenAI-compatible in pass-through cost tracking (BerriAI#29730) * fix(proxy): recognize *.cognitiveservices.azure.com as OpenAI-compatible Azure OpenAI resources created via the newer "Azure AI Foundry" / Cognitive Services pathway live on `*.cognitiveservices.azure.com` subdomains, not the older `openai.azure.com`. Both are valid Azure OpenAI surfaces in production today. The OpenAI pass-through cost-tracking handler hard-codes only the older hostname in five places (four `is_openai_*_route` methods on OpenAIPassthroughLoggingHandler, plus is_openai_route on PassThroughEndpointLogging). As a result, calls from newer Azure deployments are silently classified as "not an OpenAI route", the dispatch into the cost-tracking handler is skipped, and tokens/cost never get extracted into LiteLLM_SpendLogs — the row gets written with prompt_tokens=0, completion_tokens=0, spend=0, model='unknown'. Reproduced 2026-06-04 against a real Azure OpenAI deployment on `*.cognitiveservices.azure.com` proxied through LiteLLM v1.88.0. Fix: factor the hostname check into a single helper `_is_openai_compatible_host` listing all three recognized surfaces (api.openai.com, openai.azure.com, cognitiveservices.azure.com), and have all five call sites delegate to it. Purely additive — never weakens recognition for the originally-supported hostnames. Adds a test `test_is_openai_route_recognizes_cognitiveservices_azure_com` that exercises all four `is_openai_*_route` static methods against `*.cognitiveservices.azure.com` URLs (positive cases per route + a small cross-route negative to confirm route-specific path matching still works on the new hostname). Out of scope for this PR (separate followup): - `openai_passthrough_handler` calls chat/completions `transform_response` on Responses API payloads (`output:` not `choices:`), which throws inside the dispatch and drops the SpendLogs row entirely. Recognized + tracked separately. * ci: trigger fresh run Empty commit to re-run checks. The previous auth-and-jwt failure was a transient HuggingFace Hub 429 rate-limit hitting tokenizer downloads in tests/proxy_unit_tests/test_custom_tokenizer_bug.py — unrelated to this PR's scope (hostname recognition in pass-through cost tracking). No code change. --------- Co-authored-by: shin-berri <[email protected]> Co-authored-by: yuneng-jiang <[email protected]> * fix(responses): preserve forced-function tool_choice name in Responses to Chat transform (BerriAI#29812) The Responses API forces a specific function with a top-level name ({"type": "function", "name": "X"}), but _transform_tool_choice only handled the nested Chat Completions shape and fell through to returning "required" for the flat form, silently dropping the function name and degrading a forced function call to force-any-tool. Map the flat Responses shape to the nested Chat shape, keeping the "required" fallback when no name is present. * Preserve x-anthropic-billing-header system blocks for first-party Anthropic (BerriAI#29584) * Preserve x-anthropic-billing-header system blocks for first-party Anthropic PR BerriAI#20951 strips system blocks beginning with "x-anthropic-billing-header:" for every Anthropic target. That block is how the first-party Anthropic API recognizes Claude Code subscription (OAuth) traffic, so dropping it makes requests that carry only that block, such as the auto-mode tool-safety classifier, fail with a misleading 429 rate_limit_error; normal turns still work because they also carry the "You are Claude Code" identity block. Gate the strip behind should_strip_billing_metadata(), defaulting to False on the first-party AnthropicConfig and AnthropicMessagesConfig so the block is kept, and overridden to True on the providers that reach these transforms and reject the block (Bedrock platform, Vertex, Azure for the chat path; Minimax, Azure, DeepSeek for the messages path). Behavior for those providers is unchanged. * Strip billing header on Bedrock invoke and Vertex messages pass-through Two more subclasses reach the gated strip but inherited keep-by-default. AmazonAnthropicClaudeConfig (Bedrock invoke) calls AnthropicConfig.transform_request, which calls translate_system_message, and VertexAIPartnerModelsAnthropicMessagesConfig (Vertex messages pass-through) calls super().transform_anthropic_messages_request. Override should_strip_billing_metadata() to True on both. Add a parametrized test asserting the flag for every first-party base (False) and provider subclass (True), covering all overrides, plus a translate_system_message regression test for the Bedrock invoke path. * fix(cache): log hashed cache keys (BerriAI#29890) * fix(ui): save routing groups as list (BerriAI#29889) * Revert "fix(ui): save routing groups as list (BerriAI#29889)" (BerriAI#29928) This reverts commit 9b1f78f. * feat(parasail): add Parasail as a JSON-configured OpenAI-compatible provider (BerriAI#29842) * feat(parasail): add Parasail as a JSON-configured OpenAI-compatible provider Registers parasail in the openai_like JSON provider loader with both /v1/chat/completions and /v1/responses support. Parasail's Responses API rejects store:true and any request that omits store, so the loader gains a force_store_false special_handling flag; the parasail entry sets it and the generated Responses config overrides store=false on every call. This keeps callers from hitting "State storage not supported" and matches what Parasail's docs require. Adds the PARASAIL enum value, listing under openai_compatible_providers, provider documentation at docs/my-website/docs/providers/parasail.md, and a focused unit test file under tests/test_litellm/llms/parasail/ that covers JSON registration, chat URL construction, Responses URL construction with PARASAIL_API_BASE override, and the force_store_false regression in both the caller-sent-store=true and caller-omitted cases. * fix(parasail): register in provider_endpoints_support, drop in-repo docs Greptile review feedback. The provider doc belongs in the litellm-docs repo, not this one's docs/my-website tree; removing it here. Adds the parasail entry to provider_endpoints_support.json so the check_provider_folders_documented.py CI check passes (chat_completions and responses true; others false). * fix: normalize Anthropic passthrough server tool usage (BerriAI#29827) * test(anthropic): cover server_tool_use dict cost tracking * fix: normalize Anthropic server tool usage (cherry picked from commit 982f726) * fix: keep server tool usage subscriptable (cherry picked from commit 70280b9) --------- Co-authored-by: Genmin <[email protected]> * fix(proxy): fix typo generic_role_mappoings -> generic_role_mappings in ui_sso.py (BerriAI#29753) Co-authored-by: shin-berri <[email protected]> Co-authored-by: yuneng-jiang <[email protected]> * feat(proxy): add disable_budget_reservation general setting (BerriAI#27639) (BerriAI#29493) * feat(proxy): add disable_budget_reservation general setting (BerriAI#27639) * feat(proxy): register disable_budget_reservation in ConfigGeneralSettings (BerriAI#27639) * docs(proxy): document disable_budget_reservation concurrency tradeoff (BerriAI#27639) * ci: re-trigger flaky docker build (prisma generate ECONNRESET) * fix(proxy): warn and document budget enforcement tradeoff when disable_budget_reservation is set (BerriAI#27639) * feat(gemini_tts): adding support to Gemini TTS languageCode parameters (BerriAI#29623) * Adding support to Gemini TTS Language Code parameters * Mapping Gemini TTS languageCode param in Docstring * Use snake_case for language_code input keyMapping Gemini TTS languageCode param in Docstring * Restoring files modified under enterprise/litellm_enterprise due to lint/formatting checks --------- Co-authored-by: João Garrido <[email protected]> * feat(guardrails): capture user and model metadata in CrowdStrike AIDR (BerriAI#29517) * fix(proxy): require OpenAI path segment for shared Azure Cognitive Services domains Address Greptile review: the `*.cognitiveservices.azure.com` / `*.openai.azure.com` domains are shared by every Azure Cognitive Service (Speech, Vision, Language, ...), so a hostname-only substring match misclassified non-OpenAI Azure traffic as OpenAI routes. - Replace the substring host test with suffix matching (rejects look-alike domains like cognitiveservices.azure.com.attacker.example). - Add `_is_openai_compatible_url` that requires an OpenAI-style path marker (`/openai/` or `/v1/`) on the shared Azure domains, and use it in PassThroughEndpointLogging.is_openai_route (previously hostname-only). - Add negative tests for Azure Speech/Vision paths and look-alike domains. Co-Authored-By: Claude Opus 4.8 <[email protected]> * fix: support Responses input in Redis semantic cache (BerriAI#29581) * fix: support responses input in redis semantic cache * test: cover redis semantic prompt extraction * test: handle blank redis semantic text fallbacks * chore: remove async cache dead statement * test: cover redis semantic cache miss paths * fix: filter sensitive cache lookup kwargs * chore: rerun ci after huggingface rate limit * chore(ui): regenerate dashboard API types (npm run gen:api) Sync src/lib/http/schema.d.ts with the proxy OpenAPI spec: adds the disable_budget_reservation general-settings field and picks up the RateLimitError docstring reindent. Fixes the gen:api CI drift check. Co-Authored-By: Claude Opus 4.8 <[email protected]> * test(bedrock): assert empty additionalModelRequestFields is omitted The Converse transformer now drops an empty additionalModelRequestFields block instead of sending it as `{}`. Update test_bedrock_top_k_param so models without top_k support (llama3) assert the key is absent rather than equal to an empty dict. Co-Authored-By: Claude Opus 4.8 <[email protected]> --------- Co-authored-by: Kent <[email protected]> Co-authored-by: codgician <[email protected]> Co-authored-by: Praveen Ghuge <[email protected]> Co-authored-by: Roi <[email protected]> Co-authored-by: shin-berri <[email protected]> Co-authored-by: yuneng-jiang <[email protected]> Co-authored-by: Claude Sonnet 4.6 <[email protected]> Co-authored-by: Liam Scott <[email protected]> Co-authored-by: abhay23-AI <[email protected]> Co-authored-by: Ceder Dens <[email protected]> Co-authored-by: 冯基魁 <[email protected]> Co-authored-by: Kai Huang <[email protected]> Co-authored-by: rinto <[email protected]> Co-authored-by: Genmin <[email protected]> Co-authored-by: Arnav Bhilwariya <[email protected]> Co-authored-by: Armaan Sandhu <[email protected]> Co-authored-by: João Garrido <[email protected]> Co-authored-by: João Garrido <[email protected]> Co-authored-by: Kenan Yildirim <[email protected]> Co-authored-by: Dávid Balatoni <[email protected]>
michaelxer
pushed a commit
to michaelxer/litellm
that referenced
this pull request
Jun 17, 2026
* feat(bedrock_mantle): add SigV4/IAM auth to Responses API route (fixes BerriAI#29665) (BerriAI#29788) * feat(responses): add default no-op sign_request to BaseResponsesAPIConfig * feat(responses): call sign_request after body is final, send signed bytes when signed * feat(bedrock_mantle): add SigV4 sign_request via composed BaseAWSLLM (bearer path) * test(bedrock_mantle): cover SigV4 access-key, AssumeRole, body bytes, region/auth consistency * feat(bedrock_mantle): defer auth to sign_request; validate_environment no longer requires bearer * docs(bedrock_mantle): document SigV4 + Bearer auth on Responses route * test(responses): cover fake-stream signing order and mantle bearer arg/env precedence * fix(bedrock_mantle): wrap all botocore credential errors with both-paths guidance * fix(bedrock_mantle): catch specific credential errors, not all BotoCoreError, so STS transport failures are not masked * fix(bedrock_mantle): sign the compact Responses route too, not just create * fix(github-copilot): route per-model on /v1/responses based on model info (BerriAI#29747) * feat(focus): add GCS destination for FOCUS export (BerriAI#29751) * test: add failing tests for FocusGCSDestination * feat: add FocusGCSDestination reusing GCSBucketBase auth * feat: register FocusGCSDestination in factory; export from __init__ * fix(focus): preserve GCS_PATH_SERVICE_ACCOUNT when service_account_json not in config * style: apply Black formatting to gcs_destination and tests * style: apply Black formatting to factory.py * fix(bedrock): omit empty additionalModelRequestFields and system from Converse API payload (BerriAI#29565) Amazon Nova Pro (and other strict Bedrock models) return 400 Malformed input request when additionalModelRequestFields: {} or system: [] are present in the payload. Both fields are optional in CommonRequestObject (total=False) and must be omitted rather than sent as empty structures. Co-authored-by: shin-berri <[email protected]> Co-authored-by: yuneng-jiang <[email protected]> Co-authored-by: Claude Sonnet 4.6 <[email protected]> * fix(proxy): recognize *.cognitiveservices.azure.com as OpenAI-compatible in pass-through cost tracking (BerriAI#29730) * fix(proxy): recognize *.cognitiveservices.azure.com as OpenAI-compatible Azure OpenAI resources created via the newer "Azure AI Foundry" / Cognitive Services pathway live on `*.cognitiveservices.azure.com` subdomains, not the older `openai.azure.com`. Both are valid Azure OpenAI surfaces in production today. The OpenAI pass-through cost-tracking handler hard-codes only the older hostname in five places (four `is_openai_*_route` methods on OpenAIPassthroughLoggingHandler, plus is_openai_route on PassThroughEndpointLogging). As a result, calls from newer Azure deployments are silently classified as "not an OpenAI route", the dispatch into the cost-tracking handler is skipped, and tokens/cost never get extracted into LiteLLM_SpendLogs — the row gets written with prompt_tokens=0, completion_tokens=0, spend=0, model='unknown'. Reproduced 2026-06-04 against a real Azure OpenAI deployment on `*.cognitiveservices.azure.com` proxied through LiteLLM v1.88.0. Fix: factor the hostname check into a single helper `_is_openai_compatible_host` listing all three recognized surfaces (api.openai.com, openai.azure.com, cognitiveservices.azure.com), and have all five call sites delegate to it. Purely additive — never weakens recognition for the originally-supported hostnames. Adds a test `test_is_openai_route_recognizes_cognitiveservices_azure_com` that exercises all four `is_openai_*_route` static methods against `*.cognitiveservices.azure.com` URLs (positive cases per route + a small cross-route negative to confirm route-specific path matching still works on the new hostname). Out of scope for this PR (separate followup): - `openai_passthrough_handler` calls chat/completions `transform_response` on Responses API payloads (`output:` not `choices:`), which throws inside the dispatch and drops the SpendLogs row entirely. Recognized + tracked separately. * ci: trigger fresh run Empty commit to re-run checks. The previous auth-and-jwt failure was a transient HuggingFace Hub 429 rate-limit hitting tokenizer downloads in tests/proxy_unit_tests/test_custom_tokenizer_bug.py — unrelated to this PR's scope (hostname recognition in pass-through cost tracking). No code change. --------- Co-authored-by: shin-berri <[email protected]> Co-authored-by: yuneng-jiang <[email protected]> * fix(responses): preserve forced-function tool_choice name in Responses to Chat transform (BerriAI#29812) The Responses API forces a specific function with a top-level name ({"type": "function", "name": "X"}), but _transform_tool_choice only handled the nested Chat Completions shape and fell through to returning "required" for the flat form, silently dropping the function name and degrading a forced function call to force-any-tool. Map the flat Responses shape to the nested Chat shape, keeping the "required" fallback when no name is present. * Preserve x-anthropic-billing-header system blocks for first-party Anthropic (BerriAI#29584) * Preserve x-anthropic-billing-header system blocks for first-party Anthropic PR BerriAI#20951 strips system blocks beginning with "x-anthropic-billing-header:" for every Anthropic target. That block is how the first-party Anthropic API recognizes Claude Code subscription (OAuth) traffic, so dropping it makes requests that carry only that block, such as the auto-mode tool-safety classifier, fail with a misleading 429 rate_limit_error; normal turns still work because they also carry the "You are Claude Code" identity block. Gate the strip behind should_strip_billing_metadata(), defaulting to False on the first-party AnthropicConfig and AnthropicMessagesConfig so the block is kept, and overridden to True on the providers that reach these transforms and reject the block (Bedrock platform, Vertex, Azure for the chat path; Minimax, Azure, DeepSeek for the messages path). Behavior for those providers is unchanged. * Strip billing header on Bedrock invoke and Vertex messages pass-through Two more subclasses reach the gated strip but inherited keep-by-default. AmazonAnthropicClaudeConfig (Bedrock invoke) calls AnthropicConfig.transform_request, which calls translate_system_message, and VertexAIPartnerModelsAnthropicMessagesConfig (Vertex messages pass-through) calls super().transform_anthropic_messages_request. Override should_strip_billing_metadata() to True on both. Add a parametrized test asserting the flag for every first-party base (False) and provider subclass (True), covering all overrides, plus a translate_system_message regression test for the Bedrock invoke path. * fix(cache): log hashed cache keys (BerriAI#29890) * fix(ui): save routing groups as list (BerriAI#29889) * Revert "fix(ui): save routing groups as list (BerriAI#29889)" (BerriAI#29928) This reverts commit 9b1f78f. * feat(parasail): add Parasail as a JSON-configured OpenAI-compatible provider (BerriAI#29842) * feat(parasail): add Parasail as a JSON-configured OpenAI-compatible provider Registers parasail in the openai_like JSON provider loader with both /v1/chat/completions and /v1/responses support. Parasail's Responses API rejects store:true and any request that omits store, so the loader gains a force_store_false special_handling flag; the parasail entry sets it and the generated Responses config overrides store=false on every call. This keeps callers from hitting "State storage not supported" and matches what Parasail's docs require. Adds the PARASAIL enum value, listing under openai_compatible_providers, provider documentation at docs/my-website/docs/providers/parasail.md, and a focused unit test file under tests/test_litellm/llms/parasail/ that covers JSON registration, chat URL construction, Responses URL construction with PARASAIL_API_BASE override, and the force_store_false regression in both the caller-sent-store=true and caller-omitted cases. * fix(parasail): register in provider_endpoints_support, drop in-repo docs Greptile review feedback. The provider doc belongs in the litellm-docs repo, not this one's docs/my-website tree; removing it here. Adds the parasail entry to provider_endpoints_support.json so the check_provider_folders_documented.py CI check passes (chat_completions and responses true; others false). * fix: normalize Anthropic passthrough server tool usage (BerriAI#29827) * test(anthropic): cover server_tool_use dict cost tracking * fix: normalize Anthropic server tool usage (cherry picked from commit 982f726) * fix: keep server tool usage subscriptable (cherry picked from commit 70280b9) --------- Co-authored-by: Genmin <[email protected]> * fix(proxy): fix typo generic_role_mappoings -> generic_role_mappings in ui_sso.py (BerriAI#29753) Co-authored-by: shin-berri <[email protected]> Co-authored-by: yuneng-jiang <[email protected]> * feat(proxy): add disable_budget_reservation general setting (BerriAI#27639) (BerriAI#29493) * feat(proxy): add disable_budget_reservation general setting (BerriAI#27639) * feat(proxy): register disable_budget_reservation in ConfigGeneralSettings (BerriAI#27639) * docs(proxy): document disable_budget_reservation concurrency tradeoff (BerriAI#27639) * ci: re-trigger flaky docker build (prisma generate ECONNRESET) * fix(proxy): warn and document budget enforcement tradeoff when disable_budget_reservation is set (BerriAI#27639) * feat(gemini_tts): adding support to Gemini TTS languageCode parameters (BerriAI#29623) * Adding support to Gemini TTS Language Code parameters * Mapping Gemini TTS languageCode param in Docstring * Use snake_case for language_code input keyMapping Gemini TTS languageCode param in Docstring * Restoring files modified under enterprise/litellm_enterprise due to lint/formatting checks --------- Co-authored-by: João Garrido <[email protected]> * feat(guardrails): capture user and model metadata in CrowdStrike AIDR (BerriAI#29517) * fix(proxy): require OpenAI path segment for shared Azure Cognitive Services domains Address Greptile review: the `*.cognitiveservices.azure.com` / `*.openai.azure.com` domains are shared by every Azure Cognitive Service (Speech, Vision, Language, ...), so a hostname-only substring match misclassified non-OpenAI Azure traffic as OpenAI routes. - Replace the substring host test with suffix matching (rejects look-alike domains like cognitiveservices.azure.com.attacker.example). - Add `_is_openai_compatible_url` that requires an OpenAI-style path marker (`/openai/` or `/v1/`) on the shared Azure domains, and use it in PassThroughEndpointLogging.is_openai_route (previously hostname-only). - Add negative tests for Azure Speech/Vision paths and look-alike domains. Co-Authored-By: Claude Opus 4.8 <[email protected]> * fix: support Responses input in Redis semantic cache (BerriAI#29581) * fix: support responses input in redis semantic cache * test: cover redis semantic prompt extraction * test: handle blank redis semantic text fallbacks * chore: remove async cache dead statement * test: cover redis semantic cache miss paths * fix: filter sensitive cache lookup kwargs * chore: rerun ci after huggingface rate limit * chore(ui): regenerate dashboard API types (npm run gen:api) Sync src/lib/http/schema.d.ts with the proxy OpenAPI spec: adds the disable_budget_reservation general-settings field and picks up the RateLimitError docstring reindent. Fixes the gen:api CI drift check. Co-Authored-By: Claude Opus 4.8 <[email protected]> * test(bedrock): assert empty additionalModelRequestFields is omitted The Converse transformer now drops an empty additionalModelRequestFields block instead of sending it as `{}`. Update test_bedrock_top_k_param so models without top_k support (llama3) assert the key is absent rather than equal to an empty dict. Co-Authored-By: Claude Opus 4.8 <[email protected]> --------- Co-authored-by: Kent <[email protected]> Co-authored-by: codgician <[email protected]> Co-authored-by: Praveen Ghuge <[email protected]> Co-authored-by: Roi <[email protected]> Co-authored-by: shin-berri <[email protected]> Co-authored-by: yuneng-jiang <[email protected]> Co-authored-by: Claude Sonnet 4.6 <[email protected]> Co-authored-by: Liam Scott <[email protected]> Co-authored-by: abhay23-AI <[email protected]> Co-authored-by: Ceder Dens <[email protected]> Co-authored-by: 冯基魁 <[email protected]> Co-authored-by: Kai Huang <[email protected]> Co-authored-by: rinto <[email protected]> Co-authored-by: Genmin <[email protected]> Co-authored-by: Arnav Bhilwariya <[email protected]> Co-authored-by: Armaan Sandhu <[email protected]> Co-authored-by: João Garrido <[email protected]> Co-authored-by: João Garrido <[email protected]> Co-authored-by: Kenan Yildirim <[email protected]> Co-authored-by: Dávid Balatoni <[email protected]>
koladefaj
pushed a commit
to koladefaj/litellm
that referenced
this pull request
Jun 17, 2026
* feat(bedrock_mantle): add SigV4/IAM auth to Responses API route (fixes BerriAI#29665) (BerriAI#29788) * feat(responses): add default no-op sign_request to BaseResponsesAPIConfig * feat(responses): call sign_request after body is final, send signed bytes when signed * feat(bedrock_mantle): add SigV4 sign_request via composed BaseAWSLLM (bearer path) * test(bedrock_mantle): cover SigV4 access-key, AssumeRole, body bytes, region/auth consistency * feat(bedrock_mantle): defer auth to sign_request; validate_environment no longer requires bearer * docs(bedrock_mantle): document SigV4 + Bearer auth on Responses route * test(responses): cover fake-stream signing order and mantle bearer arg/env precedence * fix(bedrock_mantle): wrap all botocore credential errors with both-paths guidance * fix(bedrock_mantle): catch specific credential errors, not all BotoCoreError, so STS transport failures are not masked * fix(bedrock_mantle): sign the compact Responses route too, not just create * fix(github-copilot): route per-model on /v1/responses based on model info (BerriAI#29747) * feat(focus): add GCS destination for FOCUS export (BerriAI#29751) * test: add failing tests for FocusGCSDestination * feat: add FocusGCSDestination reusing GCSBucketBase auth * feat: register FocusGCSDestination in factory; export from __init__ * fix(focus): preserve GCS_PATH_SERVICE_ACCOUNT when service_account_json not in config * style: apply Black formatting to gcs_destination and tests * style: apply Black formatting to factory.py * fix(bedrock): omit empty additionalModelRequestFields and system from Converse API payload (BerriAI#29565) Amazon Nova Pro (and other strict Bedrock models) return 400 Malformed input request when additionalModelRequestFields: {} or system: [] are present in the payload. Both fields are optional in CommonRequestObject (total=False) and must be omitted rather than sent as empty structures. Co-authored-by: shin-berri <[email protected]> Co-authored-by: yuneng-jiang <[email protected]> Co-authored-by: Claude Sonnet 4.6 <[email protected]> * fix(proxy): recognize *.cognitiveservices.azure.com as OpenAI-compatible in pass-through cost tracking (BerriAI#29730) * fix(proxy): recognize *.cognitiveservices.azure.com as OpenAI-compatible Azure OpenAI resources created via the newer "Azure AI Foundry" / Cognitive Services pathway live on `*.cognitiveservices.azure.com` subdomains, not the older `openai.azure.com`. Both are valid Azure OpenAI surfaces in production today. The OpenAI pass-through cost-tracking handler hard-codes only the older hostname in five places (four `is_openai_*_route` methods on OpenAIPassthroughLoggingHandler, plus is_openai_route on PassThroughEndpointLogging). As a result, calls from newer Azure deployments are silently classified as "not an OpenAI route", the dispatch into the cost-tracking handler is skipped, and tokens/cost never get extracted into LiteLLM_SpendLogs — the row gets written with prompt_tokens=0, completion_tokens=0, spend=0, model='unknown'. Reproduced 2026-06-04 against a real Azure OpenAI deployment on `*.cognitiveservices.azure.com` proxied through LiteLLM v1.88.0. Fix: factor the hostname check into a single helper `_is_openai_compatible_host` listing all three recognized surfaces (api.openai.com, openai.azure.com, cognitiveservices.azure.com), and have all five call sites delegate to it. Purely additive — never weakens recognition for the originally-supported hostnames. Adds a test `test_is_openai_route_recognizes_cognitiveservices_azure_com` that exercises all four `is_openai_*_route` static methods against `*.cognitiveservices.azure.com` URLs (positive cases per route + a small cross-route negative to confirm route-specific path matching still works on the new hostname). Out of scope for this PR (separate followup): - `openai_passthrough_handler` calls chat/completions `transform_response` on Responses API payloads (`output:` not `choices:`), which throws inside the dispatch and drops the SpendLogs row entirely. Recognized + tracked separately. * ci: trigger fresh run Empty commit to re-run checks. The previous auth-and-jwt failure was a transient HuggingFace Hub 429 rate-limit hitting tokenizer downloads in tests/proxy_unit_tests/test_custom_tokenizer_bug.py — unrelated to this PR's scope (hostname recognition in pass-through cost tracking). No code change. --------- Co-authored-by: shin-berri <[email protected]> Co-authored-by: yuneng-jiang <[email protected]> * fix(responses): preserve forced-function tool_choice name in Responses to Chat transform (BerriAI#29812) The Responses API forces a specific function with a top-level name ({"type": "function", "name": "X"}), but _transform_tool_choice only handled the nested Chat Completions shape and fell through to returning "required" for the flat form, silently dropping the function name and degrading a forced function call to force-any-tool. Map the flat Responses shape to the nested Chat shape, keeping the "required" fallback when no name is present. * Preserve x-anthropic-billing-header system blocks for first-party Anthropic (BerriAI#29584) * Preserve x-anthropic-billing-header system blocks for first-party Anthropic PR BerriAI#20951 strips system blocks beginning with "x-anthropic-billing-header:" for every Anthropic target. That block is how the first-party Anthropic API recognizes Claude Code subscription (OAuth) traffic, so dropping it makes requests that carry only that block, such as the auto-mode tool-safety classifier, fail with a misleading 429 rate_limit_error; normal turns still work because they also carry the "You are Claude Code" identity block. Gate the strip behind should_strip_billing_metadata(), defaulting to False on the first-party AnthropicConfig and AnthropicMessagesConfig so the block is kept, and overridden to True on the providers that reach these transforms and reject the block (Bedrock platform, Vertex, Azure for the chat path; Minimax, Azure, DeepSeek for the messages path). Behavior for those providers is unchanged. * Strip billing header on Bedrock invoke and Vertex messages pass-through Two more subclasses reach the gated strip but inherited keep-by-default. AmazonAnthropicClaudeConfig (Bedrock invoke) calls AnthropicConfig.transform_request, which calls translate_system_message, and VertexAIPartnerModelsAnthropicMessagesConfig (Vertex messages pass-through) calls super().transform_anthropic_messages_request. Override should_strip_billing_metadata() to True on both. Add a parametrized test asserting the flag for every first-party base (False) and provider subclass (True), covering all overrides, plus a translate_system_message regression test for the Bedrock invoke path. * fix(cache): log hashed cache keys (BerriAI#29890) * fix(ui): save routing groups as list (BerriAI#29889) * Revert "fix(ui): save routing groups as list (BerriAI#29889)" (BerriAI#29928) This reverts commit 9b1f78f. * feat(parasail): add Parasail as a JSON-configured OpenAI-compatible provider (BerriAI#29842) * feat(parasail): add Parasail as a JSON-configured OpenAI-compatible provider Registers parasail in the openai_like JSON provider loader with both /v1/chat/completions and /v1/responses support. Parasail's Responses API rejects store:true and any request that omits store, so the loader gains a force_store_false special_handling flag; the parasail entry sets it and the generated Responses config overrides store=false on every call. This keeps callers from hitting "State storage not supported" and matches what Parasail's docs require. Adds the PARASAIL enum value, listing under openai_compatible_providers, provider documentation at docs/my-website/docs/providers/parasail.md, and a focused unit test file under tests/test_litellm/llms/parasail/ that covers JSON registration, chat URL construction, Responses URL construction with PARASAIL_API_BASE override, and the force_store_false regression in both the caller-sent-store=true and caller-omitted cases. * fix(parasail): register in provider_endpoints_support, drop in-repo docs Greptile review feedback. The provider doc belongs in the litellm-docs repo, not this one's docs/my-website tree; removing it here. Adds the parasail entry to provider_endpoints_support.json so the check_provider_folders_documented.py CI check passes (chat_completions and responses true; others false). * fix: normalize Anthropic passthrough server tool usage (BerriAI#29827) * test(anthropic): cover server_tool_use dict cost tracking * fix: normalize Anthropic server tool usage (cherry picked from commit 982f726) * fix: keep server tool usage subscriptable (cherry picked from commit 70280b9) --------- Co-authored-by: Genmin <[email protected]> * fix(proxy): fix typo generic_role_mappoings -> generic_role_mappings in ui_sso.py (BerriAI#29753) Co-authored-by: shin-berri <[email protected]> Co-authored-by: yuneng-jiang <[email protected]> * feat(proxy): add disable_budget_reservation general setting (BerriAI#27639) (BerriAI#29493) * feat(proxy): add disable_budget_reservation general setting (BerriAI#27639) * feat(proxy): register disable_budget_reservation in ConfigGeneralSettings (BerriAI#27639) * docs(proxy): document disable_budget_reservation concurrency tradeoff (BerriAI#27639) * ci: re-trigger flaky docker build (prisma generate ECONNRESET) * fix(proxy): warn and document budget enforcement tradeoff when disable_budget_reservation is set (BerriAI#27639) * feat(gemini_tts): adding support to Gemini TTS languageCode parameters (BerriAI#29623) * Adding support to Gemini TTS Language Code parameters * Mapping Gemini TTS languageCode param in Docstring * Use snake_case for language_code input keyMapping Gemini TTS languageCode param in Docstring * Restoring files modified under enterprise/litellm_enterprise due to lint/formatting checks --------- Co-authored-by: João Garrido <[email protected]> * feat(guardrails): capture user and model metadata in CrowdStrike AIDR (BerriAI#29517) * fix(proxy): require OpenAI path segment for shared Azure Cognitive Services domains Address Greptile review: the `*.cognitiveservices.azure.com` / `*.openai.azure.com` domains are shared by every Azure Cognitive Service (Speech, Vision, Language, ...), so a hostname-only substring match misclassified non-OpenAI Azure traffic as OpenAI routes. - Replace the substring host test with suffix matching (rejects look-alike domains like cognitiveservices.azure.com.attacker.example). - Add `_is_openai_compatible_url` that requires an OpenAI-style path marker (`/openai/` or `/v1/`) on the shared Azure domains, and use it in PassThroughEndpointLogging.is_openai_route (previously hostname-only). - Add negative tests for Azure Speech/Vision paths and look-alike domains. Co-Authored-By: Claude Opus 4.8 <[email protected]> * fix: support Responses input in Redis semantic cache (BerriAI#29581) * fix: support responses input in redis semantic cache * test: cover redis semantic prompt extraction * test: handle blank redis semantic text fallbacks * chore: remove async cache dead statement * test: cover redis semantic cache miss paths * fix: filter sensitive cache lookup kwargs * chore: rerun ci after huggingface rate limit * chore(ui): regenerate dashboard API types (npm run gen:api) Sync src/lib/http/schema.d.ts with the proxy OpenAPI spec: adds the disable_budget_reservation general-settings field and picks up the RateLimitError docstring reindent. Fixes the gen:api CI drift check. Co-Authored-By: Claude Opus 4.8 <[email protected]> * test(bedrock): assert empty additionalModelRequestFields is omitted The Converse transformer now drops an empty additionalModelRequestFields block instead of sending it as `{}`. Update test_bedrock_top_k_param so models without top_k support (llama3) assert the key is absent rather than equal to an empty dict. Co-Authored-By: Claude Opus 4.8 <[email protected]> --------- Co-authored-by: Kent <[email protected]> Co-authored-by: codgician <[email protected]> Co-authored-by: Praveen Ghuge <[email protected]> Co-authored-by: Roi <[email protected]> Co-authored-by: shin-berri <[email protected]> Co-authored-by: yuneng-jiang <[email protected]> Co-authored-by: Claude Sonnet 4.6 <[email protected]> Co-authored-by: Liam Scott <[email protected]> Co-authored-by: abhay23-AI <[email protected]> Co-authored-by: Ceder Dens <[email protected]> Co-authored-by: 冯基魁 <[email protected]> Co-authored-by: Kai Huang <[email protected]> Co-authored-by: rinto <[email protected]> Co-authored-by: Genmin <[email protected]> Co-authored-by: Arnav Bhilwariya <[email protected]> Co-authored-by: Armaan Sandhu <[email protected]> Co-authored-by: João Garrido <[email protected]> Co-authored-by: João Garrido <[email protected]> Co-authored-by: Kenan Yildirim <[email protected]> Co-authored-by: Dávid Balatoni <[email protected]>
factnn
pushed a commit
to factnn/litellm
that referenced
this pull request
Jun 18, 2026
* feat(bedrock_mantle): add SigV4/IAM auth to Responses API route (fixes BerriAI#29665) (BerriAI#29788) * feat(responses): add default no-op sign_request to BaseResponsesAPIConfig * feat(responses): call sign_request after body is final, send signed bytes when signed * feat(bedrock_mantle): add SigV4 sign_request via composed BaseAWSLLM (bearer path) * test(bedrock_mantle): cover SigV4 access-key, AssumeRole, body bytes, region/auth consistency * feat(bedrock_mantle): defer auth to sign_request; validate_environment no longer requires bearer * docs(bedrock_mantle): document SigV4 + Bearer auth on Responses route * test(responses): cover fake-stream signing order and mantle bearer arg/env precedence * fix(bedrock_mantle): wrap all botocore credential errors with both-paths guidance * fix(bedrock_mantle): catch specific credential errors, not all BotoCoreError, so STS transport failures are not masked * fix(bedrock_mantle): sign the compact Responses route too, not just create * fix(github-copilot): route per-model on /v1/responses based on model info (BerriAI#29747) * feat(focus): add GCS destination for FOCUS export (BerriAI#29751) * test: add failing tests for FocusGCSDestination * feat: add FocusGCSDestination reusing GCSBucketBase auth * feat: register FocusGCSDestination in factory; export from __init__ * fix(focus): preserve GCS_PATH_SERVICE_ACCOUNT when service_account_json not in config * style: apply Black formatting to gcs_destination and tests * style: apply Black formatting to factory.py * fix(bedrock): omit empty additionalModelRequestFields and system from Converse API payload (BerriAI#29565) Amazon Nova Pro (and other strict Bedrock models) return 400 Malformed input request when additionalModelRequestFields: {} or system: [] are present in the payload. Both fields are optional in CommonRequestObject (total=False) and must be omitted rather than sent as empty structures. Co-authored-by: shin-berri <[email protected]> Co-authored-by: yuneng-jiang <[email protected]> Co-authored-by: Claude Sonnet 4.6 <[email protected]> * fix(proxy): recognize *.cognitiveservices.azure.com as OpenAI-compatible in pass-through cost tracking (BerriAI#29730) * fix(proxy): recognize *.cognitiveservices.azure.com as OpenAI-compatible Azure OpenAI resources created via the newer "Azure AI Foundry" / Cognitive Services pathway live on `*.cognitiveservices.azure.com` subdomains, not the older `openai.azure.com`. Both are valid Azure OpenAI surfaces in production today. The OpenAI pass-through cost-tracking handler hard-codes only the older hostname in five places (four `is_openai_*_route` methods on OpenAIPassthroughLoggingHandler, plus is_openai_route on PassThroughEndpointLogging). As a result, calls from newer Azure deployments are silently classified as "not an OpenAI route", the dispatch into the cost-tracking handler is skipped, and tokens/cost never get extracted into LiteLLM_SpendLogs — the row gets written with prompt_tokens=0, completion_tokens=0, spend=0, model='unknown'. Reproduced 2026-06-04 against a real Azure OpenAI deployment on `*.cognitiveservices.azure.com` proxied through LiteLLM v1.88.0. Fix: factor the hostname check into a single helper `_is_openai_compatible_host` listing all three recognized surfaces (api.openai.com, openai.azure.com, cognitiveservices.azure.com), and have all five call sites delegate to it. Purely additive — never weakens recognition for the originally-supported hostnames. Adds a test `test_is_openai_route_recognizes_cognitiveservices_azure_com` that exercises all four `is_openai_*_route` static methods against `*.cognitiveservices.azure.com` URLs (positive cases per route + a small cross-route negative to confirm route-specific path matching still works on the new hostname). Out of scope for this PR (separate followup): - `openai_passthrough_handler` calls chat/completions `transform_response` on Responses API payloads (`output:` not `choices:`), which throws inside the dispatch and drops the SpendLogs row entirely. Recognized + tracked separately. * ci: trigger fresh run Empty commit to re-run checks. The previous auth-and-jwt failure was a transient HuggingFace Hub 429 rate-limit hitting tokenizer downloads in tests/proxy_unit_tests/test_custom_tokenizer_bug.py — unrelated to this PR's scope (hostname recognition in pass-through cost tracking). No code change. --------- Co-authored-by: shin-berri <[email protected]> Co-authored-by: yuneng-jiang <[email protected]> * fix(responses): preserve forced-function tool_choice name in Responses to Chat transform (BerriAI#29812) The Responses API forces a specific function with a top-level name ({"type": "function", "name": "X"}), but _transform_tool_choice only handled the nested Chat Completions shape and fell through to returning "required" for the flat form, silently dropping the function name and degrading a forced function call to force-any-tool. Map the flat Responses shape to the nested Chat shape, keeping the "required" fallback when no name is present. * Preserve x-anthropic-billing-header system blocks for first-party Anthropic (BerriAI#29584) * Preserve x-anthropic-billing-header system blocks for first-party Anthropic PR BerriAI#20951 strips system blocks beginning with "x-anthropic-billing-header:" for every Anthropic target. That block is how the first-party Anthropic API recognizes Claude Code subscription (OAuth) traffic, so dropping it makes requests that carry only that block, such as the auto-mode tool-safety classifier, fail with a misleading 429 rate_limit_error; normal turns still work because they also carry the "You are Claude Code" identity block. Gate the strip behind should_strip_billing_metadata(), defaulting to False on the first-party AnthropicConfig and AnthropicMessagesConfig so the block is kept, and overridden to True on the providers that reach these transforms and reject the block (Bedrock platform, Vertex, Azure for the chat path; Minimax, Azure, DeepSeek for the messages path). Behavior for those providers is unchanged. * Strip billing header on Bedrock invoke and Vertex messages pass-through Two more subclasses reach the gated strip but inherited keep-by-default. AmazonAnthropicClaudeConfig (Bedrock invoke) calls AnthropicConfig.transform_request, which calls translate_system_message, and VertexAIPartnerModelsAnthropicMessagesConfig (Vertex messages pass-through) calls super().transform_anthropic_messages_request. Override should_strip_billing_metadata() to True on both. Add a parametrized test asserting the flag for every first-party base (False) and provider subclass (True), covering all overrides, plus a translate_system_message regression test for the Bedrock invoke path. * fix(cache): log hashed cache keys (BerriAI#29890) * fix(ui): save routing groups as list (BerriAI#29889) * Revert "fix(ui): save routing groups as list (BerriAI#29889)" (BerriAI#29928) This reverts commit 9b1f78f. * feat(parasail): add Parasail as a JSON-configured OpenAI-compatible provider (BerriAI#29842) * feat(parasail): add Parasail as a JSON-configured OpenAI-compatible provider Registers parasail in the openai_like JSON provider loader with both /v1/chat/completions and /v1/responses support. Parasail's Responses API rejects store:true and any request that omits store, so the loader gains a force_store_false special_handling flag; the parasail entry sets it and the generated Responses config overrides store=false on every call. This keeps callers from hitting "State storage not supported" and matches what Parasail's docs require. Adds the PARASAIL enum value, listing under openai_compatible_providers, provider documentation at docs/my-website/docs/providers/parasail.md, and a focused unit test file under tests/test_litellm/llms/parasail/ that covers JSON registration, chat URL construction, Responses URL construction with PARASAIL_API_BASE override, and the force_store_false regression in both the caller-sent-store=true and caller-omitted cases. * fix(parasail): register in provider_endpoints_support, drop in-repo docs Greptile review feedback. The provider doc belongs in the litellm-docs repo, not this one's docs/my-website tree; removing it here. Adds the parasail entry to provider_endpoints_support.json so the check_provider_folders_documented.py CI check passes (chat_completions and responses true; others false). * fix: normalize Anthropic passthrough server tool usage (BerriAI#29827) * test(anthropic): cover server_tool_use dict cost tracking * fix: normalize Anthropic server tool usage (cherry picked from commit 982f726) * fix: keep server tool usage subscriptable (cherry picked from commit 70280b9) --------- Co-authored-by: Genmin <[email protected]> * fix(proxy): fix typo generic_role_mappoings -> generic_role_mappings in ui_sso.py (BerriAI#29753) Co-authored-by: shin-berri <[email protected]> Co-authored-by: yuneng-jiang <[email protected]> * feat(proxy): add disable_budget_reservation general setting (BerriAI#27639) (BerriAI#29493) * feat(proxy): add disable_budget_reservation general setting (BerriAI#27639) * feat(proxy): register disable_budget_reservation in ConfigGeneralSettings (BerriAI#27639) * docs(proxy): document disable_budget_reservation concurrency tradeoff (BerriAI#27639) * ci: re-trigger flaky docker build (prisma generate ECONNRESET) * fix(proxy): warn and document budget enforcement tradeoff when disable_budget_reservation is set (BerriAI#27639) * feat(gemini_tts): adding support to Gemini TTS languageCode parameters (BerriAI#29623) * Adding support to Gemini TTS Language Code parameters * Mapping Gemini TTS languageCode param in Docstring * Use snake_case for language_code input keyMapping Gemini TTS languageCode param in Docstring * Restoring files modified under enterprise/litellm_enterprise due to lint/formatting checks --------- Co-authored-by: João Garrido <[email protected]> * feat(guardrails): capture user and model metadata in CrowdStrike AIDR (BerriAI#29517) * fix(proxy): require OpenAI path segment for shared Azure Cognitive Services domains Address Greptile review: the `*.cognitiveservices.azure.com` / `*.openai.azure.com` domains are shared by every Azure Cognitive Service (Speech, Vision, Language, ...), so a hostname-only substring match misclassified non-OpenAI Azure traffic as OpenAI routes. - Replace the substring host test with suffix matching (rejects look-alike domains like cognitiveservices.azure.com.attacker.example). - Add `_is_openai_compatible_url` that requires an OpenAI-style path marker (`/openai/` or `/v1/`) on the shared Azure domains, and use it in PassThroughEndpointLogging.is_openai_route (previously hostname-only). - Add negative tests for Azure Speech/Vision paths and look-alike domains. Co-Authored-By: Claude Opus 4.8 <[email protected]> * fix: support Responses input in Redis semantic cache (BerriAI#29581) * fix: support responses input in redis semantic cache * test: cover redis semantic prompt extraction * test: handle blank redis semantic text fallbacks * chore: remove async cache dead statement * test: cover redis semantic cache miss paths * fix: filter sensitive cache lookup kwargs * chore: rerun ci after huggingface rate limit * chore(ui): regenerate dashboard API types (npm run gen:api) Sync src/lib/http/schema.d.ts with the proxy OpenAPI spec: adds the disable_budget_reservation general-settings field and picks up the RateLimitError docstring reindent. Fixes the gen:api CI drift check. Co-Authored-By: Claude Opus 4.8 <[email protected]> * test(bedrock): assert empty additionalModelRequestFields is omitted The Converse transformer now drops an empty additionalModelRequestFields block instead of sending it as `{}`. Update test_bedrock_top_k_param so models without top_k support (llama3) assert the key is absent rather than equal to an empty dict. Co-Authored-By: Claude Opus 4.8 <[email protected]> --------- Co-authored-by: Kent <[email protected]> Co-authored-by: codgician <[email protected]> Co-authored-by: Praveen Ghuge <[email protected]> Co-authored-by: Roi <[email protected]> Co-authored-by: shin-berri <[email protected]> Co-authored-by: yuneng-jiang <[email protected]> Co-authored-by: Claude Sonnet 4.6 <[email protected]> Co-authored-by: Liam Scott <[email protected]> Co-authored-by: abhay23-AI <[email protected]> Co-authored-by: Ceder Dens <[email protected]> Co-authored-by: 冯基魁 <[email protected]> Co-authored-by: Kai Huang <[email protected]> Co-authored-by: rinto <[email protected]> Co-authored-by: Genmin <[email protected]> Co-authored-by: Arnav Bhilwariya <[email protected]> Co-authored-by: Armaan Sandhu <[email protected]> Co-authored-by: João Garrido <[email protected]> Co-authored-by: João Garrido <[email protected]> Co-authored-by: Kenan Yildirim <[email protected]> Co-authored-by: Dávid Balatoni <[email protected]>
fzowl
pushed a commit
to fzowl/litellm
that referenced
this pull request
Jun 24, 2026
* feat(bedrock_mantle): add SigV4/IAM auth to Responses API route (fixes BerriAI#29665) (BerriAI#29788) * feat(responses): add default no-op sign_request to BaseResponsesAPIConfig * feat(responses): call sign_request after body is final, send signed bytes when signed * feat(bedrock_mantle): add SigV4 sign_request via composed BaseAWSLLM (bearer path) * test(bedrock_mantle): cover SigV4 access-key, AssumeRole, body bytes, region/auth consistency * feat(bedrock_mantle): defer auth to sign_request; validate_environment no longer requires bearer * docs(bedrock_mantle): document SigV4 + Bearer auth on Responses route * test(responses): cover fake-stream signing order and mantle bearer arg/env precedence * fix(bedrock_mantle): wrap all botocore credential errors with both-paths guidance * fix(bedrock_mantle): catch specific credential errors, not all BotoCoreError, so STS transport failures are not masked * fix(bedrock_mantle): sign the compact Responses route too, not just create * fix(github-copilot): route per-model on /v1/responses based on model info (BerriAI#29747) * feat(focus): add GCS destination for FOCUS export (BerriAI#29751) * test: add failing tests for FocusGCSDestination * feat: add FocusGCSDestination reusing GCSBucketBase auth * feat: register FocusGCSDestination in factory; export from __init__ * fix(focus): preserve GCS_PATH_SERVICE_ACCOUNT when service_account_json not in config * style: apply Black formatting to gcs_destination and tests * style: apply Black formatting to factory.py * fix(bedrock): omit empty additionalModelRequestFields and system from Converse API payload (BerriAI#29565) Amazon Nova Pro (and other strict Bedrock models) return 400 Malformed input request when additionalModelRequestFields: {} or system: [] are present in the payload. Both fields are optional in CommonRequestObject (total=False) and must be omitted rather than sent as empty structures. Co-authored-by: shin-berri <[email protected]> Co-authored-by: yuneng-jiang <[email protected]> * fix(proxy): recognize *.cognitiveservices.azure.com as OpenAI-compatible in pass-through cost tracking (BerriAI#29730) * fix(proxy): recognize *.cognitiveservices.azure.com as OpenAI-compatible Azure OpenAI resources created via the newer "Azure AI Foundry" / Cognitive Services pathway live on `*.cognitiveservices.azure.com` subdomains, not the older `openai.azure.com`. Both are valid Azure OpenAI surfaces in production today. The OpenAI pass-through cost-tracking handler hard-codes only the older hostname in five places (four `is_openai_*_route` methods on OpenAIPassthroughLoggingHandler, plus is_openai_route on PassThroughEndpointLogging). As a result, calls from newer Azure deployments are silently classified as "not an OpenAI route", the dispatch into the cost-tracking handler is skipped, and tokens/cost never get extracted into LiteLLM_SpendLogs — the row gets written with prompt_tokens=0, completion_tokens=0, spend=0, model='unknown'. Reproduced 2026-06-04 against a real Azure OpenAI deployment on `*.cognitiveservices.azure.com` proxied through LiteLLM v1.88.0. Fix: factor the hostname check into a single helper `_is_openai_compatible_host` listing all three recognized surfaces (api.openai.com, openai.azure.com, cognitiveservices.azure.com), and have all five call sites delegate to it. Purely additive — never weakens recognition for the originally-supported hostnames. Adds a test `test_is_openai_route_recognizes_cognitiveservices_azure_com` that exercises all four `is_openai_*_route` static methods against `*.cognitiveservices.azure.com` URLs (positive cases per route + a small cross-route negative to confirm route-specific path matching still works on the new hostname). Out of scope for this PR (separate followup): - `openai_passthrough_handler` calls chat/completions `transform_response` on Responses API payloads (`output:` not `choices:`), which throws inside the dispatch and drops the SpendLogs row entirely. Recognized + tracked separately. * ci: trigger fresh run Empty commit to re-run checks. The previous auth-and-jwt failure was a transient HuggingFace Hub 429 rate-limit hitting tokenizer downloads in tests/proxy_unit_tests/test_custom_tokenizer_bug.py — unrelated to this PR's scope (hostname recognition in pass-through cost tracking). No code change. --------- Co-authored-by: shin-berri <[email protected]> Co-authored-by: yuneng-jiang <[email protected]> * fix(responses): preserve forced-function tool_choice name in Responses to Chat transform (BerriAI#29812) The Responses API forces a specific function with a top-level name ({"type": "function", "name": "X"}), but _transform_tool_choice only handled the nested Chat Completions shape and fell through to returning "required" for the flat form, silently dropping the function name and degrading a forced function call to force-any-tool. Map the flat Responses shape to the nested Chat shape, keeping the "required" fallback when no name is present. * Preserve x-anthropic-billing-header system blocks for first-party Anthropic (BerriAI#29584) * Preserve x-anthropic-billing-header system blocks for first-party Anthropic PR BerriAI#20951 strips system blocks beginning with "x-anthropic-billing-header:" for every Anthropic target. That block is how the first-party Anthropic API recognizes Claude Code subscription (OAuth) traffic, so dropping it makes requests that carry only that block, such as the auto-mode tool-safety classifier, fail with a misleading 429 rate_limit_error; normal turns still work because they also carry the "You are Claude Code" identity block. Gate the strip behind should_strip_billing_metadata(), defaulting to False on the first-party AnthropicConfig and AnthropicMessagesConfig so the block is kept, and overridden to True on the providers that reach these transforms and reject the block (Bedrock platform, Vertex, Azure for the chat path; Minimax, Azure, DeepSeek for the messages path). Behavior for those providers is unchanged. * Strip billing header on Bedrock invoke and Vertex messages pass-through Two more subclasses reach the gated strip but inherited keep-by-default. AmazonAnthropicClaudeConfig (Bedrock invoke) calls AnthropicConfig.transform_request, which calls translate_system_message, and VertexAIPartnerModelsAnthropicMessagesConfig (Vertex messages pass-through) calls super().transform_anthropic_messages_request. Override should_strip_billing_metadata() to True on both. Add a parametrized test asserting the flag for every first-party base (False) and provider subclass (True), covering all overrides, plus a translate_system_message regression test for the Bedrock invoke path. * fix(cache): log hashed cache keys (BerriAI#29890) * fix(ui): save routing groups as list (BerriAI#29889) * Revert "fix(ui): save routing groups as list (BerriAI#29889)" (BerriAI#29928) This reverts commit 9b1f78f. * feat(parasail): add Parasail as a JSON-configured OpenAI-compatible provider (BerriAI#29842) * feat(parasail): add Parasail as a JSON-configured OpenAI-compatible provider Registers parasail in the openai_like JSON provider loader with both /v1/chat/completions and /v1/responses support. Parasail's Responses API rejects store:true and any request that omits store, so the loader gains a force_store_false special_handling flag; the parasail entry sets it and the generated Responses config overrides store=false on every call. This keeps callers from hitting "State storage not supported" and matches what Parasail's docs require. Adds the PARASAIL enum value, listing under openai_compatible_providers, provider documentation at docs/my-website/docs/providers/parasail.md, and a focused unit test file under tests/test_litellm/llms/parasail/ that covers JSON registration, chat URL construction, Responses URL construction with PARASAIL_API_BASE override, and the force_store_false regression in both the caller-sent-store=true and caller-omitted cases. * fix(parasail): register in provider_endpoints_support, drop in-repo docs Greptile review feedback. The provider doc belongs in the litellm-docs repo, not this one's docs/my-website tree; removing it here. Adds the parasail entry to provider_endpoints_support.json so the check_provider_folders_documented.py CI check passes (chat_completions and responses true; others false). * fix: normalize Anthropic passthrough server tool usage (BerriAI#29827) * test(anthropic): cover server_tool_use dict cost tracking * fix: normalize Anthropic server tool usage (cherry picked from commit 982f726) * fix: keep server tool usage subscriptable (cherry picked from commit 70280b9) --------- Co-authored-by: Genmin <[email protected]> * fix(proxy): fix typo generic_role_mappoings -> generic_role_mappings in ui_sso.py (BerriAI#29753) Co-authored-by: shin-berri <[email protected]> Co-authored-by: yuneng-jiang <[email protected]> * feat(proxy): add disable_budget_reservation general setting (BerriAI#27639) (BerriAI#29493) * feat(proxy): add disable_budget_reservation general setting (BerriAI#27639) * feat(proxy): register disable_budget_reservation in ConfigGeneralSettings (BerriAI#27639) * docs(proxy): document disable_budget_reservation concurrency tradeoff (BerriAI#27639) * ci: re-trigger flaky docker build (prisma generate ECONNRESET) * fix(proxy): warn and document budget enforcement tradeoff when disable_budget_reservation is set (BerriAI#27639) * feat(gemini_tts): adding support to Gemini TTS languageCode parameters (BerriAI#29623) * Adding support to Gemini TTS Language Code parameters * Mapping Gemini TTS languageCode param in Docstring * Use snake_case for language_code input keyMapping Gemini TTS languageCode param in Docstring * Restoring files modified under enterprise/litellm_enterprise due to lint/formatting checks --------- Co-authored-by: João Garrido <[email protected]> * feat(guardrails): capture user and model metadata in CrowdStrike AIDR (BerriAI#29517) * fix(proxy): require OpenAI path segment for shared Azure Cognitive Services domains Address Greptile review: the `*.cognitiveservices.azure.com` / `*.openai.azure.com` domains are shared by every Azure Cognitive Service (Speech, Vision, Language, ...), so a hostname-only substring match misclassified non-OpenAI Azure traffic as OpenAI routes. - Replace the substring host test with suffix matching (rejects look-alike domains like cognitiveservices.azure.com.attacker.example). - Add `_is_openai_compatible_url` that requires an OpenAI-style path marker (`/openai/` or `/v1/`) on the shared Azure domains, and use it in PassThroughEndpointLogging.is_openai_route (previously hostname-only). - Add negative tests for Azure Speech/Vision paths and look-alike domains. * fix: support Responses input in Redis semantic cache (BerriAI#29581) * fix: support responses input in redis semantic cache * test: cover redis semantic prompt extraction * test: handle blank redis semantic text fallbacks * chore: remove async cache dead statement * test: cover redis semantic cache miss paths * fix: filter sensitive cache lookup kwargs * chore: rerun ci after huggingface rate limit * chore(ui): regenerate dashboard API types (npm run gen:api) Sync src/lib/http/schema.d.ts with the proxy OpenAPI spec: adds the disable_budget_reservation general-settings field and picks up the RateLimitError docstring reindent. Fixes the gen:api CI drift check. * test(bedrock): assert empty additionalModelRequestFields is omitted The Converse transformer now drops an empty additionalModelRequestFields block instead of sending it as `{}`. Update test_bedrock_top_k_param so models without top_k support (llama3) assert the key is absent rather than equal to an empty dict. --------- Co-authored-by: Kent <[email protected]> Co-authored-by: codgician <[email protected]> Co-authored-by: Praveen Ghuge <[email protected]> Co-authored-by: Roi <[email protected]> Co-authored-by: shin-berri <[email protected]> Co-authored-by: yuneng-jiang <[email protected]> Co-authored-by: Liam Scott <[email protected]> Co-authored-by: abhay23-AI <[email protected]> Co-authored-by: Ceder Dens <[email protected]> Co-authored-by: 冯基魁 <[email protected]> Co-authored-by: Kai Huang <[email protected]> Co-authored-by: rinto <[email protected]> Co-authored-by: Genmin <[email protected]> Co-authored-by: Arnav Bhilwariya <[email protected]> Co-authored-by: Armaan Sandhu <[email protected]> Co-authored-by: João Garrido <[email protected]> Co-authored-by: João Garrido <[email protected]> Co-authored-by: Kenan Yildirim <[email protected]> Co-authored-by: Dávid Balatoni <[email protected]>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Relevant issues
Docs
Docs update PR: BerriAI/litellm-docs#301 (pghuge-cloudwiz/litellm-docs -> BerriAI/litellm-docs)
Changes to
docs/observability/focus.mdanddocs/proxy/config_settings.md:Pre-Submission checklist
make test-unit@greptileaiand received a Confidence Score of at least 4/5 before requesting a maintainer reviewCI (LiteLLM team)
Branch creation CI run
Link:
CI run for the last commit
Link:
Merge / cherry-pick CI run
Links:
Screenshots / Proof of Fix
Built from source (this branch), seeded 7 dummy spend rows across 3 providers and 3 dates into Postgres, then ran both
export_alland a daily windowed export against a real GCS bucket using Application Default Credentials (no service account JSON).Setup:
Daily export (window: 2026-06-04 00:00 UTC -> 2026-06-05 00:00 UTC):
GCS bucket after export:
Daily file is partitioned under
date=2026-06-04/and the filename encodes the exact 24h window.CSV content of the daily file (2 rows — only 2026-06-04 data, other dates excluded):
Row count matches exactly — 2 rows for 2026-06-04, rows from 2026-06-03 and 2026-06-05 excluded by the time window filter.
Type
New Feature
Changes
Adds
FocusGCSDestination— a native Google Cloud Storage destination for the FOCUS export integration, equivalent to the existing S3 support.The implementation reuses
GCSBucketBasefor authentication (service account JSON or ADC via the existing Vertex token flow) and the sharedasync_httpx_client, keeping new code minimal. The GCS JSON API upload endpoint mirrors howGCSBucketBase._log_json_data_on_gcsworks, but sends raw bytes withContent-Type: application/octet-streaminstead of JSON. Object key layout (date=YYYY-MM-DD/) is identical toFocusS3Destination.Files changed (4):
litellm/integrations/focus/destinations/gcs_destination.py— newFocusGCSDestinationclass (~70 lines)litellm/integrations/focus/destinations/factory.py— adds"gcs"branch tocreate()and_resolve_config()litellm/integrations/focus/destinations/__init__.py— exportsFocusGCSDestinationtests/test_litellm/integrations/focus/test_focus_gcs_destination.py— 8 unit tests (including regression tests for credential precedence)Usage: