chore(ci): promote internal staging to main#28292
Merged
Merged
Conversation
) * fix(proxy): gate team allowed_passthrough_routes to proxy admins allowed_passthrough_routes short-circuits the role-based route gate, so the keys endpoints already restrict it to proxy admins. The team writers (/team/new, /team/update) had no equivalent check, letting an org admin (a non-proxy-admin who clears the route gate and _verify_team_access) self-grant pass-through routes on their team. Lift the keys check into a shared helper and apply it to both team endpoints. Resolves LIT-3019 * docs(proxy): note view-only admins are intentionally excluded from passthrough gate Clarifies the proxy-admin guard per review feedback; no behavior change. Refs LIT-3019
…-1 spend (#28110) * fix(tests): stabilize image-edit VCR cassettes to stop live gpt-image-1 spend The image-edit cassettes for ``gpt-image-1`` were accumulating >50 episodes and being refused by the persister (``tests/_vcr_redis_persister.py``), so every CI run was hitting the real OpenAI endpoint. The async parametrize was the clearest tell: ``test_openai_image_edit_litellm_sdk[True]`` cached to 1 entry, but the ``[False]`` (async) sibling grew to 51 entries and never replayed. Two non-deterministic sources were fueling the growth, both fixed here. After this patch, the cassettes settle at one episode per unique call and replay for the 24-hour TTL like every other suite. 1. Pin httpx's multipart boundary at the source. The existing ``_normalize_multipart_boundary`` rewrites the boundary in the ``Content-Type`` header reliably, but on the async transport path the body is not always a contiguous ``bytes`` object when ``before_record_request`` runs, so the body-side replacement silently no-ops and the recorded cassette retains the random ``boundary=<hex>`` string. The next CI run gets a fresh random boundary, the ``safe_body`` matcher misses, and ``record_mode="new_episodes"`` appends another episode. Wrapping ``httpx._multipart.MultipartStream.__init__`` so it always uses ``vcr-static-boundary`` when no boundary is supplied eliminates the variance for both sync and async paths and leaves the normalizer in place as a backstop. Exposed as ``pin_httpx_multipart_boundary`` so other multipart-heavy suites (audio, ocr, batches) can adopt the same fixture later. 2. Pass raw ``bytes`` (not ``BytesIO`` streams) through the image-edit fixtures. A ``BytesIO`` whose file pointer is at EOF after the first multipart upload silently encodes an empty image on the next SDK / Router retry — yet another divergent body that VCR records as a new episode. ``bytes`` are immutable and position-less, so retries re-encode an identical payload every time. This is also a small production-correctness improvement: a customer passing ``BytesIO`` today would hit the same empty-body retry bug. The BytesIO-specific smoke test (``test_openai_image_edit_with_bytesio``) is preserved by giving ``get_test_images_as_bytesio`` its own factory instead of aliasing the bytes one. 3. Add ``scripts/flush_image_edit_vcr_cassettes.py`` — a one-shot Redis SCAN/DEL helper that clears the bloated pre-fix cassettes under ``litellm:vcr:cassette:tests/image_gen_tests/test_image_edits/*``. Without this, the next CI run still loads the existing 51-entry cassette, the new fixed-boundary body still doesn't match any of the stale entries, the persister still refuses to save, and the bleed continues. Run once with the production ``CASSETTE_REDIS_URL`` after merge (dry-run by default). * DIAGNOSTIC: log VCR body mismatches + per-episode body hashes Temporary observability boost so we can root-cause why ``test_image_edits.py`` async parametrizes still record fresh episodes on every CI run even though the multipart boundary is now pinned (sync parametrizes cache cleanly as VCR HIT). The matcher currently raises ``AssertionError("request bodies differ")`` with zero context, so we cannot tell whether the live body genuinely varies, the matcher is comparing a bytes object to a stream object, or the normalizer is silently skipping the body because it is not bytes/str. Three logs added; the first two are worth keeping permanently, the third is intended to be reverted after the diagnosis lands: 1. ``_safe_body_matcher`` now emits a structured stderr block on mismatch (type of each side, length, SHA-256, first divergent byte offset, ±100-byte window). Always-on -- mismatches are signal, not noise, and the existing per-test verdict already logs once per test. PERMANENT. 2. ``_normalize_multipart_boundary`` now logs to stderr when the body type is not bytes/bytearray/str -- the silent ``else: return`` branch was masking exactly the case we suspect is firing on async (httpx ``MultipartStream`` handed to vcrpy before the body is read). PERMANENT. 3. ``_RedisPersister.save_cassette`` now logs every episode's body SHA-256, length, and 120-byte preview at save time. This lets two consecutive CI runs be diffed: if the same test records a different hash run-to-run, the live body genuinely varies; if both runs record the same hash but the matcher still misses, the bug is in the matcher itself. TEMPORARY -- revert once the async variance is identified and fixed. Once a single ``image_gen_testing`` CI run produces these logs, revert this commit (or just the persister hash block) with a force push so the cassette save path is not noisy in steady-state. * DIAGNOSTIC: route VCR diagnostics through per-PID files (bypass xdist capture) Re-push of the diagnostic logging from the previous commit, this time wired so the output actually survives to the CI log. xdist captures stdout/stderr from every passing test in the worker process; the body-matcher and normalizer-skip diagnostics fire from inside vcrpy machinery during the test, so for any test that ultimately passes (which is all of them once the cassettes are recorded), the diagnostic lines are silently swallowed. Fix: write each diagnostic line to a per-PID file under ``test-results/vcr-diagnostics/<pid>.log`` instead of writing to stderr. The controller's ``pytest_terminal_summary`` aggregates those files and writes them through ``terminalreporter.write_line``, which is not subject to per-test capture. As a bonus, ``test-results/`` is already collected by the ``store_test_results`` step in CircleCI, so the raw per-worker logs survive as build artifacts even after the test session ends. Three call sites updated: 1. ``_emit_body_mismatch_diagnostic`` (matcher) -- writes the structured type/length/sha/window block via ``vcr_diag_write_line``. 2. ``_normalize_multipart_boundary`` -- logs the silent-skip path (body not bytes/bytearray/str) the same way. 3. ``_maybe_log_episode_body_hashes`` (persister) -- replaces the ``_log.warning`` calls (which the root-logger config also swallows in CI) with ``vcr_diag_write_line``. Image-gen conftest is the only suite wired to dump the aggregated log at session end. Other suites can opt in by adding ``emit_vcr_diagnostic_log(terminalreporter)`` to their own ``pytest_terminal_summary``. The diagnostic dir is cleared at the start of each session (controller-only) so a local rerun does not mix output from prior runs. Same revert plan as the previous diagnostic commit: keep the matcher + normalizer skip diagnostics permanently (they only fire on signal events), revert the persister body-hash dump once the async variance is identified. * fix(tests): coalesce iterable request bodies before matching/recording Root cause of the residual async image-edit cassette leak. The diagnostic run for ``ba3915d9`` printed: [vcr-safe-body-matcher] request body mismatch body[a]: type='list_iterator' length=unknown sha256=N/A body[b]: type='list_iterator' length=unknown sha256=N/A httpx's async transport hands vcrpy a ``request.body`` that is a ``list_iterator`` over multipart chunks rather than a contiguous ``bytes`` blob. Two consequences: 1. ``_safe_body_matcher`` compares the two iterator objects with ``==``, which is identity comparison for arbitrary iterators - semantically identical multipart bodies never compare equal, and ``record_mode="new_episodes"`` appends a new episode on every CI run until the cassette crosses ``MAX_EPISODES_PER_CASSETTE`` and the persister refuses to save (this is exactly what the OVERFLOW warning has been catching). 2. ``_normalize_multipart_boundary`` short-circuits its ``else: return`` branch because the body is neither bytes nor str, so any residual random boundary characters in the body bytes are never rewritten. Sync requests do not hit this code path: httpx's sync transport hands vcrpy a single ``bytes`` body, so ``==`` works and the boundary normalizer runs as intended. That is why ``test_openai_image_edit_litellm_sdk[True]`` records to ``entries=1`` and replays cleanly while ``[False]`` (async) kept growing by one episode per run. Fix: add ``_materialize_iterable_body`` which coalesces an iterable ``request.body`` into ``bytes`` in-place. Call it from two places: * The top of ``_before_record_request``, so the boundary normalizer and the cassette serializer both see bytes from then on. * The top of ``_safe_body_matcher``, as defense in depth in case a future vcrpy code path invokes the matcher without first going through ``_before_record_request``. The vcrpy ``Request`` is a wrapper used for matching and recording; the underlying httpx transport sends its own request body separately, so replacing the iterator on the vcrpy wrapper does not starve the live HTTP send. After this lands the async parametrizes should flip from ``[VCR MISS:RECORDED] entries=N+1`` to ``[VCR HIT] entries=N`` on the next CI run, matching the sync side and dropping the residual ~$3/day to $0. * fix(tests): handle bytes_iterator + never leave an exhausted body Follow-up to 8e08272. The previous attempt at coalescing iterable request bodies bailed out (``return`` without writing ``request.body``) whenever it could not classify the chunk type. That was the wrong failure mode for one critical case: vcrpy sometimes presents the body as ``iter(some_bytes)``, whose Python type is ``bytes_iterator`` and which yields ``int`` byte values (0-255), not byte chunks. The old code saw an ``int`` chunk, hit the ``else: return`` branch, and left ``request.body`` pointing at the now-exhausted iterator. The post-fix diagnostic run made this loud: [vcr-safe-body-matcher] request body mismatch body[a]: type='bytes_iterator' length=unknown sha256=N/A body[b]: type='bytes_iterator' length=unknown sha256=N/A Every async image-edit test then ballooned from entries=2 to entries=10 in that single CI run -- the exhausted iterator meant the live multipart upload went out as an empty body, OpenAI returned 400, the SDK + flaky retries fired, each retry got a fresh iterator that my hook exhausted again, and ``new_episodes`` recorded each failed attempt as a new cassette episode. This patch: * Recognizes ``bytes_iterator`` (chunks are ``int``) and reconstructs the buffer via ``bytes(chunks)``. * Keeps the existing ``list_iterator``-over-bytes-chunks handling via ``b"".join(...)``. * **Always writes a bytes value back to ``request.body`` after consuming the iterator.** If the chunk shape is unrecognized, ``request.body`` is set to ``b""`` rather than left as an exhausted iterator. That is wrong in the sense of "we lost the body" but right in the sense of "the failure mode is now visible (live API call sends empty body and fails fast) instead of invisible (corrupt cassette grows silently)". Combined with the matcher diagnostic, any future regression in this code path will surface in the CI log immediately. Local verification covers ``bytes_iterator``, ``list_iterator`` over bytes chunks, generator over bytes chunks, empty iterator, already-bytes (idempotent), identical-content iterator equality in the matcher (now matches), and differing-content iterator inequality (still raises). * fix(tests): clear vcrpy's sticky _was_iter flag so materialized bodies stay bytes Actual root cause of the async image-edit cassette leak. The previous diagnostic run produced this dead giveaway: [vcr-episode-body-hash] ... episode[0]: body type='bytes_iterator' is not bytes/bytearray/str -- cannot hash [vcr-safe-body-matcher] request body mismatch body[a]: type='bytes_iterator' length=unknown sha256=N/A body[b]: type='bytes_iterator' length=unknown sha256=N/A Both sides of the matcher were ``bytes_iterator`` **after** the materializer had supposedly converted them to bytes. That made no sense until I read vcrpy's ``Request`` class. vcrpy's ``Request`` keeps two private flags that are set in ``__init__`` from the original body's type and **never cleared by the setter**: def __init__(self, method, uri, body, headers): self._was_file = hasattr(body, "read") self._was_iter = _is_nonsequence_iterator(body) ... @Property def body(self): if self._was_file: return BytesIO(self._body) if self._was_iter: return iter(self._body) return self._body @body.setter def body(self, value): if isinstance(value, str): value = value.encode("utf-8") self._body = value # <-- does NOT touch _was_iter / _was_file So when httpx's async transport hands vcrpy an iterator body, ``_was_iter`` becomes ``True`` and stays there forever. Even after ``_materialize_iterable_body`` writes plain bytes via ``request.body = out``, the next read of ``.body`` re-wraps the stored bytes in ``iter()`` -- producing a fresh ``bytes_iterator`` that compares unequal to any other ``bytes_iterator`` via object identity. The matcher missed every time, the cassette grew by one episode per run, and the persister saw the same iterator type when trying to hash the body for the diagnostic log. Fix: after writing the materialized bytes, also force ``_was_iter`` and ``_was_file`` to ``False``. vcrpy exposes no public API for this, so we touch the private flags directly -- acknowledged as a pragmatic test-only hack with a clear unit boundary (the only call site is ``_materialize_iterable_body``). Local repro reproduces the exact production setup: ``Request('POST', url, iter(b'multipart-content'), {})`` on two sides, runs the matcher, asserts HIT. Verified the matcher hits on identical content and still raises on differing content. Should be the last fix needed. Existing cassettes that contain oddly-shaped bodies (lists of int chunks, etc. from the previous ``_was_iter=True`` save path) still match because the materializer canonicalises both sides to bytes before comparison -- no fourth re-flush required. * revert(tests): drop the temp per-episode body-hash diagnostic Removed now that 1c51ad1 has confirmed the root cause (vcrpy's sticky ``_was_iter`` flag making the body getter re-wrap stored bytes in ``iter()`` on every access). The hash dump did its job -- the post-1c51ad13 image_gen_testing run shows all five async image-edit tests as ``[VCR HIT]`` with stable entry counts and zero billing errors -- and is too noisy to keep on by default (over 100 lines per session at steady state). Kept permanently: * ``_safe_body_matcher`` mismatch diagnostic in ``_vcr_conftest_common.py``. Only fires on a body mismatch, which is signal worth surfacing whenever it happens. * ``_normalize_multipart_boundary`` "skipped" log line. Same rationale -- only fires when the body shape is something the normalizer cannot rewrite in place. * The ``test-results/vcr-diagnostics/<pid>.log`` per-PID file plumbing (``vcr_diag_write_line`` / ``emit_vcr_diagnostic_log``). Useful for any future diagnostic that needs to bypass xdist stdout/stderr capture; cheap to keep. * chore(tests): delete unused flush script + wire VCR diagnostic dump everywhere * Remove ``scripts/flush_image_edit_vcr_cassettes.py``. It was a one-shot helper for the initial cassette flush; the iterator and ``_was_iter`` fixes mean no future flush should be required, and the script was never run anywhere (the actual flushes happened inside the CI conftest via the temp hacks that have since been reverted). * The matcher mismatch + normalizer skip diagnostics already write per-PID files for every suite that imports the shared VCR plumbing, but ``emit_vcr_diagnostic_log`` -- the controller-side dump that surfaces those files into the CI log at session end -- was only wired into ``image_gen_tests``. Add the one-line call to the 12 sibling conftests that already use VCR so the diagnostics surface in any suite's terminal output if a body matcher ever misses. No new output in steady state -- the dump is a no-op when no diagnostics were recorded that session. * chore(tests): trim non-essential comments per project comment policy Strips docstrings, inline comments, and block comments that this PR introduced where the code itself was already self-evident. Keeps the few lines that document non-obvious behaviour (raw-bytes-not-BytesIO rationale on the image fixtures, the per-PID-files-bypass-xdist note on the diagnostic directory). Touches only comments this PR added -- no pre-existing comment is removed. Net: -161 lines of comment/docstring across 3 files, no code behaviour change. * chore(tests): forward **kwargs in pin_httpx_multipart_boundary wrapper Defensive against future httpx MultipartStream.__init__ adding new optional kwargs. Without the forward, the wrapper would silently drop them. No behaviour change today. * chore(tests): canonicalize VCR matchers and surface shouldn't-happen branches Bundles the "follow-up cleanup PR" into this one so it does not get lost. Four small changes: 1. Introduce ``_canonical_body(req) -> (bytes, pre_type)`` and route ``_safe_body_matcher`` through it. The matcher now operates on bytes by construction; the "compare two iterator objects via ``==`` and silently get object-identity semantics" failure mode (which cost us this entire PR to diagnose) is structurally impossible to reintroduce. ``pre_type`` is the body type *before* canonicalization, surfaced by the mismatch diagnostic so a future regression involving a new body shape is still visible. 2. Add a structured diagnostic to ``_key_fingerprint_matcher``. It was previously raising a bare ``AssertionError("API key fingerprints differ")`` with zero context -- exactly the anti-pattern the body matcher had before this PR. 3. Surface "shouldn't-happen" branches via ``vcr_diag_write_line``: * ``_strip_image_b64_payloads`` -- logs when ``response``, ``response['body']``, or ``response['body']['string']`` arrives in an unexpected shape (vcrpy contract violation). * ``_compute_key_fingerprint`` -- logs the ``"no-key"`` fallback with the request method/URL so a stripped-auth-header bug is visible instead of masked. * ``_canonical_body`` -- logs its own empty-bytes fallback when a body has a shape ``_materialize_iterable_body`` did not handle. 4. Re-introduce per-episode body-hash logging in ``_RedisPersister.save_cassette`` (was reverted in 927c554 as "noisy"). Quantified cost: ~25 KB of CI log per session at peak, ~ms-scale CPU, zero output in steady state (no save = no log). Trade-off favours keeping it: lets two consecutive CI runs be diffed by body hash, which is how we will spot the next regression in the same class. All call sites still work: local repro confirms iter==iter HIT, iter!=iter raises, plain-bytes HIT, body-hash log emits via the same per-PID file plumbing as the matcher diagnostics. * chore(tests): symmetrize diag-log cleanup across every VCR-using conftest ``image_gen_tests/conftest.py`` was the only suite that cleared ``test-results/vcr-diagnostics/*.log`` at session start. The other 12 VCR-using conftests inherited any stale per-PID logs from a previous local run and would dump them in the terminal summary -- harmless in CI (fresh container) but confusing locally when running multiple suites in sequence. Extracts the cleanup into a ``reset_vcr_diag_dir`` helper in ``tests/_vcr_conftest_common.py`` and calls it from every VCR-using conftest's ``pytest_configure``. Same single source of truth, no inline duplication. * fix(tests): gate body materialization on __next__ and strip PR comments aiohttp/vcrpy stores the json kwarg as a dict; _materialize_iterable_body was iterating it via __iter__ and joining the keys, replacing the request body with concatenated key names ("textlanguageentities"). Gate on __next__ so containers (dict/list/tuple) are left alone — only single-use iterators like httpx's bytes_iterator / list_iterator are materialized. Log diagnostic line when chunk type is unrecognized. * fix(tests): JSON-encode dict bodies in canonical_body for stable matching aiohttp stubs store the json kwarg as a dict; the fallback that compared all dicts as b"" caused concurrent presidio analyze calls to be served the wrong cassette episode. JSON-encode with sort_keys for stable bytes. * fix(tests): guard emit_vcr_diagnostic_log against multi-conftest re-emission Co-authored-by: Yassin Kortam <[email protected]> * fix(tests): globalize multipart-boundary pin + stabilize whisper fixtures Diagnostic shows audio_testing was silently re-recording 50+ live Whisper episodes per CI run (over MAX_EPISODES_PER_CASSETTE, so the persister refused to save). Two changes: * Move the session-autouse _pin_multipart_boundary fixture into the shared _vcr_conftest_common module so every VCR-using suite picks it up via a single import. image_gen had it inline; the other 12 suites silently lacked it. * Replace the module-level open("rb") audio file handles in test_whisper with cached bytes + a per-call (filename, bytes, mimetype) tuple, mirroring the image_edits raw-bytes pattern. Stops the file-pointer- at-EOF bug where the second test got an empty multipart body. * chore(tests): drop per-episode body-hash dump and redundant emit guard --------- Co-authored-by: shin-berri <[email protected]> Co-authored-by: yuneng-jiang <[email protected]> Co-authored-by: Cursor Agent <[email protected]> Co-authored-by: Yassin Kortam <[email protected]>
…28172) * fix(bedrock/cohere): wrap embedding_types as list in map_openai_params Bedrock Cohere expects embedding_types as a JSON array but encoding_format was passed through as a raw string, causing: Malformed input request: #/embedding_types: expected type: JSONArray, found: String * test(bedrock/cohere): assert embedding_types is sent as JSON array --------- Co-authored-by: Ishaan Jaffer <[email protected]>
…dels (#28191) * fix(tests): use gpt-realtime in realtime guardrails test OpenAI shut down gpt-4o-realtime-preview-2024-12-17 on 2026-05-07, so the live OpenAI realtime guardrails integration test now fails with model_not_found (session.created never arrives, _wait_for_event times out). Point OPENAI_REALTIME_URL at the current GA model, gpt-realtime. Scope limited to this test: the pricing-catalog JSON keeps the retired entries intentionally (historical cost calc + separate Azure timeline), and the Azure realtime cost-calc test is unaffected. * fix(tests): mock nvidia_nim rerank instead of hitting EOL'd endpoint NVIDIA reached end-of-life for the hosted nvidia/llama-3.2-nv-rerankqa-1b-v2 rerank API on 2026-05-18 with no published replacement, so the live BaseLLMRerankTest.test_basic_rerank for nvidia_nim now returns HTTP 410 ("Gone"). NVIDIA's hosted catalog rotates on a schedule, so swapping in another live model would only defer the failure. Override test_basic_rerank in TestNvidiaNim to mock the sync/async HTTP transport (same pattern as test_nvidia_nim_rerank_ranking_endpoint in this file) and inject a fake NVIDIA_NIM_API_KEY via monkeypatch. The request/response transformation and cost calculation stay covered offline. Scope limited to nvidia_nim; other BaseLLMRerankTest providers untouched. * fix(tests): migrate remaining realtime tests off shut-down gpt-4o-realtime-preview OpenAI's 2026-05-07 shutdown removed the entire gpt-4o-realtime-preview family, including the undated 'gpt-4o-realtime-preview' alias (not just the dated snapshot fixed earlier). Three live tests still connected with the dead alias and failed with messages_received=1 (an error event instead of session.created): - test_openai_realtime_simple.py: get_model() -> gpt-realtime (drives TestOpenAIRealtime.test_realtime_connection / test_realtime_with_query_params) - test_openai_realtime.py: test_openai_realtime_direct_call_no_intent and test_openai_realtime_direct_call_with_intent -> openai/gpt-realtime (the with_intent test shares the same dead alias even though it was not in the failing set this run) Mocked unit tests (test_realtime_query_params_construction, test_realtime_query_params_use_normalized_model_name) are left as-is: they never hit the network and assert string plumbing only. Also fixes test_text_message_blocked_by_guardrail_no_ai_response, which now connects (the earlier URL swap worked) but tripped a model-wording-brittle assertion. The guardrail flow asks the model to voice the block message verbatim; gpt-4o-realtime-preview complied (output contained 'blocked'), gpt-realtime refuses verbatim-repeat instructions ('I'm sorry, but I can't repeat that message.'). Since the original user message is blocked before it reaches OpenAI, the refusal is still a safe outcome. Assertion #3 now accepts both voicing and refusal, and adds a hard check that the blocked phrase never leaks into AI output.
…ms (#28158) * fix(caching): replay openai/responses bridge cache hits as chat streams When chat completions route through openai/responses, cached ModelResponse payloads under aresponses keys were deserialized as ResponsesAPIResponse (500) or re-translated as responses events (empty streaming deltas). Deserialize chat-shaped cache entries as acompletion and bypass the responses stream iterator for cached CustomStreamWrapper replay. Co-authored-by: Cursor <[email protected]> * fix(caching): map responses bridge call_type for sync vs async stream replay Co-authored-by: Yassin Kortam <[email protected]> * fix: handle ModelResponse cache return in responses bridge and drop dead acompletion check Co-authored-by: Yassin Kortam <[email protected]> * fix(caching): detect chat cache hits via object field before choices fallback Prefer chat.completion object type over the broad choices-key heuristic so Responses API cached payloads are not misclassified if their schema changes. Co-authored-by: Cursor <[email protected]> * test(caching): cover responses bridge cache-hit paths in CI-tracked test suite The new bridge cache replay logic in caching_handler.py and the preformatted-stream guard in litellm_responses_transformation/handler.py were exercised only by tests under tests/local_testing/, which the responses-caching-types and misc shards do not run. Codecov flagged the patch as 29.72% covered. Add equivalent unit tests under tests/test_litellm/ so the responses, caching, types, and misc shards execute them and ship their coverage data to Codecov: - _is_chat_completion_cached_dict happy/sad paths - aresponses streaming bridge cache hit -> CustomStreamWrapper - responses non-streaming bridge cache hit -> ModelResponse - legacy ResponsesAPIResponse stream + non-stream replay - _is_preformatted_cached_chat_stream true/false - completion/acompletion early return on cached ModelResponse - completion/acompletion skip rewrap on preformatted cached stream * fix: add negative guard on object field in _is_chat_completion_cached_dict Co-authored-by: Yassin Kortam <[email protected]> * fix(vcr): treat corrupt cassette payloads as cache miss * test: bump EOL'd NVIDIA rerank and OpenAI realtime models in CI The NVIDIA hosted rerank endpoint for nvidia/llama-3_2-nv-rerankqa-1b-v2 reached end-of-life on 2026-05-18 and now returns HTTP 410 Gone, breaking TestNvidiaNim::test_basic_rerank. Switch to nvidia/nv-rerankqa-mistral-4b-v3, which is still hosted on the NVIDIA API catalog and is already listed in model_prices_and_context_window.json. OpenAI also retired the gpt-4o-realtime-preview-2024-12-17 model used by test_realtime_guardrails_openai (now returns model_not_found). Switch the realtime test URL to the GA gpt-realtime alias. Unrelated to the responses-bridge cache fix in this PR, but committing here to unblock CI per maintainer guidance. Co-authored-by: Mateo Wang <[email protected]> * test(realtime): switch retired gpt-4o-realtime-preview to gpt-realtime OpenAI removed gpt-4o-realtime-preview and all its date snapshots on 2026-05-18 (every variant now returns model_not_found), breaking the live-WebSocket OpenAI realtime tests in CI: - test_openai_realtime_direct_call_no_intent - test_openai_realtime_direct_call_with_intent - TestOpenAIRealtime.test_realtime_connection - TestOpenAIRealtime.test_realtime_with_query_params Point each of those to the current GA alias gpt-realtime (verified live). Pure unit/mock tests that just assert the string value (e.g. in test_realtime_query_params_construction and the test_realtime_query_params_use_normalized_model_name mock) are left alone since they do not depend on model availability. Also relax the AI-response assertion in test_text_message_blocked_by_guardrail_no_ai_response: gpt-realtime occasionally produces a polite refusal ("I'm sorry, but I can't say that") when the cancel arrives after the model has already started generating, which is the expected outcome (no real AI content) but does not contain the words 'blocked' or 'guardrail'. The primary guardrail behaviour (guardrail_violation error event + transcript_delta block message) is still asserted unchanged. Co-authored-by: Mateo Wang <[email protected]> * test(nvidia_nim): mock rerank live API instead of hitting EOL'd endpoint NVIDIA reached end-of-life for the hosted nvidia/llama-3.2-nv-rerankqa-1b-v2 rerank API on 2026-05-18 (returns HTTP 410 Gone), and the proposed replacement nv-rerankqa-mistral-4b-v3 returns HTTP 404 for the CI account, breaking TestNvidiaNim::test_basic_rerank. Override test_basic_rerank to mock the HTTP transport (same pattern as test_nvidia_nim_rerank_ranking_endpoint above) so the request/response transformation and cost calculation stay covered without depending on NVIDIA's hosted catalog rotation. The model identifier reverts to the original llama-3.2-nv-rerankqa-1b-v2 since the request never leaves the test process. --------- Co-authored-by: Cursor <[email protected]> Co-authored-by: Yassin Kortam <[email protected]> Co-authored-by: mateo-berri <[email protected]> Co-authored-by: Mateo Wang <[email protected]>
* fix(opentelemetry): JSON-serialize dict metadata fields for OTEL span attributes (#27451) (#27455) Squash-merged by litellm-agent from Anai-Guo's PR. * feat(dashscope): add embeddings and reranks(qwen3-rerank) support via OpenAI-compatible endpoint (#27508) Squash-merged by litellm-agent from yimao's PR. * fix(vertex_ai/gemini): raise BadRequestError when image_url or url fi… (#24550) Squash-merged by litellm-agent from krisxia0506's PR. * fix(vertex_ai): raise error on mid-stream 429/error chunks instead of silently swallowing (#23711) Squash-merged by litellm-agent from krisxia0506's PR. * fix: raise BadRequestError for file content blocks missing 'file' sub… (#24503) Squash-merged by litellm-agent from krisxia0506's PR. * Fix Gemini MIME detection for extensionless GCS URIs (#27278) Squash-merged by litellm-agent from krisxia0506's PR. * fix(vertex_ai/partner_models): drop unused vertexai SDK gate from count_tokens (closes #28084) (#28107) Squash-merged by litellm-agent from voidborne-d's PR. * feat(chart): add support for autoscaling behavior in HPA (#27990) Squash-merged by litellm-agent from FabrizioCafolla's PR. * feat(proxy): add blocked flag to models for pause/resume from the UI (#27927) Squash-merged by litellm-agent from Cyberfilo's PR. * fix: pass socket timeouts to Redis cluster clients (#27920) Squash-merged by litellm-agent from tomdee's PR. * Fix/cache token (#28009) Squash-merged by litellm-agent from escon1004's PR. * fix(deepseek): forward reasoning_content in multi-turn thinking mode conversations (#28080) Squash-merged by litellm-agent from Divyansh8321's PR. * fix(guardrails): return HTTP 400 instead of 500 for blocked requests (#27617) * fix: reset org and tag budgets (#27326) * reset org budgets * reset tag budgets --------- Co-authored-by: Michael Riad Zaky <[email protected]> * fix(ui): omit allowed_routes from key edit save when unchanged (#27553) * fix(ui): omit allowed_routes from key edit save when unchanged When a team admin opens Edit Settings on a key with key_type=AI APIs and saves without changing anything, the UI re-sends the existing allowed_routes value, which the backend's _check_allowed_routes_caller_permission gate rejects for non-proxy-admins (LIT-2681). Strip allowed_routes from the patch in handleSubmit when it deep-equals the original keyData.allowed_routes. The backend treats absence as "leave alone," so no-op saves now succeed for non-admins. Admins explicitly editing the field still send the new value. * fix(ui): order-insensitive allowed_routes diff + cover null-original case Address Greptile review: - Switch the "is allowed_routes unchanged" check to a Set-based comparison so a server-side reorder of the array doesn't register as a user edit and re-trigger LIT-2681. - Add two regression tests: (1) keyData.allowed_routes is null and the form is untouched — patch should strip the field; (2) server returned routes in a different order than the user originally entered — patch should still recognize the value as unchanged. * chore(ui): strip ticket refs and tighten comments in key edit fix - Remove internal-tracker references from in-code comments - Tighten the WHY comment in handleSubmit to two lines - Drop redundant test-block comments — test names already describe the case * fix(ui): annotate Set<string> generic in allowed_routes diff to fix tsc * fix(guardrails): return HTTP 400 instead of 500 for guardrail-blocked requests GuardrailRaisedException and BlockedPiiEntityError both lacked a status_code attribute. When these exceptions reached the proxy exception handler (getattr(e, 'status_code', 500)), the fallback defaulted to HTTP 500 — making intentional guardrail blocks indistinguishable from server errors and causing unnecessary client retries. Changes: - Add status_code=400 (keyword-only) to GuardrailRaisedException - Add status_code=400 (keyword-only) to BlockedPiiEntityError - Update _is_guardrail_intervention() to recognize both exceptions so downstream loggers record 'guardrail_intervened' instead of 'guardrail_failed_to_respond' - Add 6 unit tests for default/custom status codes and getattr pattern - Strengthen existing blocked-action test with status_code assertion Fixes #24348 --------- Co-authored-by: Michael-RZ-Berri <[email protected]> Co-authored-by: Michael Riad Zaky <[email protected]> Co-authored-by: ryan-crabbe-berri <[email protected]> Co-authored-by: Krrish Dholakia <[email protected]> * fix(router/proxy): address Greptile P1+P2 review comments on PR #28161 - router: raise ServiceUnavailableError (503) instead of RouterRateLimitErrorBasic (429) when a specifically-addressed deployment is administratively blocked; 429 misleads retry-enabled clients into spinning forever against a paused model - proxy_server: compute get_fully_blocked_model_names() once before both branches in model_list() instead of duplicating the call in each branch - deepseek: upgrade silent debug log to warning when injecting placeholder reasoning_content so callers are clearly notified of degraded multi-turn quality - tests: update two blocked-deployment assertions to expect ServiceUnavailableError Co-authored-by: Cursor <[email protected]> * fix: address bug detection findings (cache token order, mutable defaults) Co-authored-by: Yassin Kortam <[email protected]> * fix: address bugs in async pass-through, anthropic cache token detection, rerank tests - async_get_available_deployment_for_pass_through: enforce blocked check on specific deployments - cost_calculator: detect anthropic-style usage by attribute presence (not truthiness) to avoid mixing OpenAI cached_tokens into anthropic normalization when read=0 - dashscope rerank tests: pass request to httpx.Response constructions for consistency Co-authored-by: Yassin Kortam <[email protected]> * fix code qa * fix(vertex_ai/gemini): strip MIME parameters from GCS contentType GCS object metadata's contentType field can include parameters such as 'text/html; charset=utf-8'. Strip them in _apply_gemini_mime_type_aliases so downstream get_file_extension_from_mime_type sees a bare MIME type. Co-authored-by: Yassin Kortam <[email protected]> * fix(vertex_ai/gemini): clarify mime-type error message string concatenation Co-authored-by: Yassin Kortam <[email protected]> --------- Co-authored-by: Tai An <[email protected]> Co-authored-by: Vincent <[email protected]> Co-authored-by: Kris Xia <[email protected]> Co-authored-by: d 🔹 <[email protected]> Co-authored-by: Fabrizio Cafolla <[email protected]> Co-authored-by: Filippo Menghi <[email protected]> Co-authored-by: Tom Denham <[email protected]> Co-authored-by: escon1004 <[email protected]> Co-authored-by: Divyansh Singhal <[email protected]> Co-authored-by: robin-fiddler <[email protected]> Co-authored-by: Michael-RZ-Berri <[email protected]> Co-authored-by: Michael Riad Zaky <[email protected]> Co-authored-by: ryan-crabbe-berri <[email protected]> Co-authored-by: Krrish Dholakia <[email protected]> Co-authored-by: Cursor <[email protected]> Co-authored-by: Yassin Kortam <[email protected]>
#28155) * feat(prometheus): add user_email and user_alias to user budget metrics User budget Prometheus gauges now expose human-readable labels alongside user_id, matching team and API key budget metrics for Grafana filtering. Co-authored-by: Cursor <[email protected]> * fix(prometheus): gate user budget email/alias labels behind opt-in flag Address greptile review: adding labels to existing metrics is a breaking cardinality change. Gate behind prometheus_user_budget_label_include_email_alias=True (default: False) so existing dashboards and recording rules are unaffected. Co-authored-by: Cursor <[email protected]> --------- Co-authored-by: Cursor <[email protected]>
* test(callbacks): TEMP diagnostic probe for callback-leak flake Hardened leak detector (sample N, flag sustained monotonic per-type growth, normalize instance addresses) + a temporary always-fail probe on test_check_num_callbacks_on_lowest_latency that dumps the per-type series and raw reprs via the JUnit failure message, to settle real-leak vs bounded-pollution on CCI. Diagnostic block is clearly marked and will be reverted before the PR. * test(callbacks): harden proxy callback-leak detector, drop diagnostic CCI diagnostic confirmed the 85->95 jump is a bounded one-time registration from the test's own switch to latency-based-routing (+LowestLatencyLoggingHandler, +SlackAlerting), flat at 95 for 2.5 min under load — not a leak. Final detector: settle past the deliberate config/update, sample N times, flag only sustained monotonic per-type growth, normalize instance addresses, name the leaking type on failure. Removes the temporary always-fail probe. * test(callbacks): address review - drop redundant settle, close terminal-burst blind spot - test_check_num_callbacks: remove leftover sleep(30) before sleep(SETTLE_SECONDS) (60s -> 30s dead wait). - Add _terminal_suspects + _detect_leaks_confirmed: when monotonic net growth is confined to the final interval (escapes the >=2-interval guard), take one confirmation sample. A real ongoing leak keeps climbing and is flagged; a one-time terminal registration plateaus and is ignored.
…rror (#28202) * fix(bedrock): sanitize batch metadata to prevent Pydantic ValidationError Proxy guardrail hooks (Model Armor, OpenAI Moderations) and internal processing inject non-string values (dicts, floats) into the request metadata. When the Bedrock batch handler passes this metadata directly to LiteLLMBatch (which inherits OpenAI's Batch Pydantic model with metadata: Dict[str, str]), Pydantic raises a ValidationError. This causes the router retry loop to re-submit the same Bedrock job multiple times before ultimately failing. Add _get_openai_compatible_batch_metadata() that serializes non-string values to JSON strings via safe_dumps, skips None values and internal logging keys, ensuring the response object always validates. * test(bedrock): add tests for batch metadata sanitization Covers _get_openai_compatible_batch_metadata: string passthrough, dict/float serialization, None/internal key exclusion, and LiteLLMBatch compatibility. --------- Co-authored-by: Noah Nistler <[email protected]>
…e tools (#28200) * fix(deepseek): route messages api through anthropic config Add a DeepSeek-specific Anthropic Messages config so deepseek/... models use the native messages endpoint and preserve thinking blocks. Strip Anthropic custom tool type markers that DeepSeek rejects while keeping hosted tool types intact. * fix(deepseek): normalize anthropic messages api base Handle OpenAI-style DeepSeek api_base values ending in /v1 or /v1/messages by stripping those suffixes before adding the /anthropic messages path. * chore(deepseek): format messages transformation * chore(deepseek): add test package markers * fix(deepseek): tighten anthropic url path check and fall back to DEEPSEEK_API_BASE Author: mateo-berri <[email protected]> * fix(tests): normalize smart quotes in realtime guardrail refusal check gpt-realtime nondeterministically returns refusals with Unicode curly apostrophes (e.g. 'I’m sorry, but I can’t assist with that.'), but the safe_markers tuple in test_text_message_blocked_by_guardrail_no_ai_response only contains straight ASCII apostrophes. The substring match then fails even though the response is a clear refusal, flipping CI red. Normalize the AI text to ASCII quotes before the marker check so both straight and curly variants count as safe outcomes. * fix(deepseek): drop redundant anthropic v1/messages endswith check * fix(deepseek): strip /beta suffix in anthropic messages URL normalization Co-authored-by: Yassin Kortam <[email protected]> --------- Co-authored-by: Felipe Rodrigues Gare Carnielli <[email protected]> Co-authored-by: Cursor Agent <[email protected]> Co-authored-by: Yassin Kortam <[email protected]>
…ing (#28156) * feat(ui): add Interactions API support to playground with streaming Adds /v1beta/interactions as a selectable endpoint in the UI playground. Uses SSE streaming (stream=true) and parses content.delta events for real-time output. Co-authored-by: Cursor <[email protected]> * fix(interactions): remove forced gemini provider so all providers work via interactions API Proxy endpoint was hardcoding custom_llm_provider="gemini" before routing, preventing non-Gemini models from using the litellm_responses bridge. Also reverts the UI Gemini-only model filter. Co-authored-by: Cursor <[email protected]> * fix(interactions): fix streaming for non-gemini providers via bridge Two bugs in LiteLLMResponsesInteractionsStreamingIterator: 1. content.delta was emitted without "type":"text" in delta dict, so the UI type-check always failed and no tokens were displayed 2. First OutputTextDeltaEvent was silently dropped (used to emit content.start with empty text); fixed by handling ResponsePartAddedEvent for content.start so text deltas go directly to content.delta Co-authored-by: Cursor <[email protected]> * undo unrelated changes * fix(ui): extract model from top-level field in interactions bridge events Co-authored-by: Yassin Kortam <[email protected]> * test(interactions): remove tautological gemini-provider assertion The test_no_forced_gemini_provider_in_request_data check only asserted against dict literals it had just constructed, so it always passed and did not exercise the create_interaction endpoint. The endpoint deliberately defaults custom_llm_provider to gemini, so the assertion was also factually incorrect. Drop the misleading test. Co-authored-by: Yassin Kortam <[email protected]> * fix(interactions): use ContentPartAddedEvent and guard interaction.start ordering - ResponsePartAddedEvent corresponds to reasoning summary parts, not text content parts. Use ContentPartAddedEvent which is the event emitted before text output deltas (type response.content_part.added). - Mirror the OutputTextDeltaEvent ordering guard: if interaction.start has not been sent yet, emit it first before content.start to honor the documented event ordering contract. Co-authored-by: Yassin Kortam <[email protected]> * test(interactions): cover ContentPartAddedEvent ordering and no-op paths * fix(tests): treat corrupt VCR cassette payloads as cache miss + use gpt-realtime in OpenAI realtime guardrails test VCR redis persister was raising UnicodeDecodeError on cached payloads that fail to UTF-8 decode (e.g. legacy entries written by another version of the persister), failing tests at fixture setup instead of degrading to a cache miss. Wrap decode+deserialize in a try/except so corrupt cache entries are treated as CassetteNotFoundError, surfacing the failure via the existing _record_cache_failure / VCRCassetteCacheWarning path. OpenAI shut down gpt-4o-realtime-preview-2024-12-17 (and the entire gpt-4o-realtime-preview family) on 2026-05-07. The live realtime guardrails integration test now fails with model_not_found instead of receiving session.created. Point OPENAI_REALTIME_URL at the current GA model gpt-realtime, and relax the assertion in test_text_message_blocked_by_guardrail_no_ai_response to also accept the model's refusal-to-repeat the block message (gpt-realtime declines verbatim-repeat instructions, which is still a safe outcome since the original user message was blocked before reaching OpenAI). The BLOCKED_PHRASE leak check is preserved as a hard invariant. * fix(tests): migrate realtime + nvidia_nim rerank tests off shut-down upstream models OpenAI shut down the entire gpt-4o-realtime-preview family (including the undated alias) on 2026-05-07. The live realtime tests still connected with that dead alias and failed with messages_received=1 (an error event 'The model gpt-4o-realtime-preview does not exist' instead of session.created). Point the live OpenAI realtime tests at gpt-realtime, the current GA realtime model: - test_openai_realtime_simple.py: get_model() -> gpt-realtime - test_openai_realtime.py: test_openai_realtime_direct_call_no_intent and test_openai_realtime_direct_call_with_intent -> openai/gpt-realtime Mocked unit tests (test_realtime_query_params_construction, test_realtime_query_params_use_normalized_model_name) are left as-is: they never hit the network and assert string plumbing only. NVIDIA reached end-of-life for the hosted nvidia/llama-3.2-nv-rerankqa-1b-v2 rerank API on 2026-05-18 with no published replacement, so the live BaseLLMRerankTest.test_basic_rerank for nvidia_nim now returns HTTP 410 ('Gone'). NVIDIA's hosted catalog rotates on a schedule, so swapping in another live model would only defer the failure. Override test_basic_rerank in TestNvidiaNim to mock the sync/async HTTP transport (same pattern as test_nvidia_nim_rerank_ranking_endpoint in this file) and inject a fake NVIDIA_NIM_API_KEY via monkeypatch. The request/response transformation and cost calculation stay covered offline. * test(callbacks): harden flaky proxy callback-leak detector The proxy callback-leak detector (test_check_num_callbacks_on_lowest_latency) was failing on this PR with 'abs(85 - 95) <= 4' — a bounded one-time registration jump caused by switching to latency-based-routing (+LowestLatencyLoggingHandler, +SlackAlerting). The count then plateaus under load, so this is pollution from the test's own config update, not a leak. Replace the brittle two-sample diff threshold with a sampler that settles past the deliberate config switch and only flags sustained monotonic per-type growth, with a terminal-burst confirmation pass for leaks that would otherwise escape the >=2-interval guard. Normalizes instance addresses so identical callbacks at different memory locations collapse, and names the leaking type on failure. * fix(interactions): preserve first text token when both start events are missing When OutputTextDeltaEvent arrived before any ResponseCreatedEvent or ContentPartAddedEvent, the double-fallback path emitted interaction.start and silently dropped the first delta's text — the second delta's content.start carried only that chunk's delta, and the first token never made it to any content.delta event consumed by the UI. Queue a content.start that carries the first delta's text alongside the interaction.start emission, and drain pending events before pulling the next upstream chunk. * chore(ui): remove unused InteractionOutput/InteractionResponse interfaces Co-authored-by: Yassin Kortam <[email protected]> --------- Co-authored-by: Cursor <[email protected]> Co-authored-by: Yassin Kortam <[email protected]> Co-authored-by: mateo-berri <[email protected]>
…mGenerateContent (#27444) (#28213) * fix(proxy): decode bytes and pass-through SSE for Google-native streamGenerateContent (#27444) * fix(proxy): address Greptile review on Google-native SSE bytes path Remove unreachable try/except around SSE pass-through yield and add a unit test covering pre-formatted SSE bytes, terminator padding, and non-SSE byte fallback wrapping. Co-authored-by: Cursor <[email protected]> --------- Co-authored-by: Tai An <[email protected]> Co-authored-by: Cursor <[email protected]>
#28189) * refactor(bedrock/sagemaker): switch to lazy loading for response stream shapes - Replace eager loading of BEDROCK_RESPONSE_STREAM_SHAPE and SAGEMAKER_RESPONSE_STREAM_SHAPE with lazy loading via get_bedrock_response_stream_shape() and get_sagemaker_response_stream_shape() respectively. - This change optimizes performance by avoiding unnecessary imports and logging warnings unless the response stream shapes are actually needed. - Update relevant classes and tests to utilize the new lazy loading functions, ensuring consistent behavior across the codebase. * test(bedrock/sagemaker): add fixtures to clear response stream shape cache - Introduced `_reset_bedrock_response_stream_shape_cache` and `_reset_sagemaker_response_stream_shape_cache` fixtures to prevent lru_cache leakage between tests in their respective modules. - Updated tests to utilize these fixtures, ensuring that the response stream shape cache is cleared before and after each test run. - Added `pytest.importorskip("botocore")` to ensure that tests are skipped if the botocore library is not available.
…onents (#25847) * [Refactor] UI - Spend Logs: consolidate filter state, extract components, remove dead code - Lift filter state into index.tsx and pass to hook (removes selectedX vars + sync useEffect) - Move main useQuery into useLogFilterLogic hook (removes isMainQueryEnabled toggle) - Delete dead RequestViewer component (300 lines, replaced by LogDetailsDrawer) - Extract LogsTableToolbar component (search, date range, pagination, live tail) - Extract filter options config to filter_options.ts - Remove dead code: handleRefresh, handleSelectLog, handleCloseDrawer, formatTimeUnit, showFilters/showColumnDropdown state, dropdownRef/filtersRef * Fix PR feedback: use antd Switch instead of Tremor in new file, fix typo * Collapse dual-path filtering into single React Query All 10 filter keys now go through the useQuery — the imperative performSearch / debouncedSearch / backendFilteredLogs path is deleted. Filter values are debounced via useDebouncedValue(300ms) before hitting the query key so text inputs don't fire per-keystroke. Removed: performSearch, debouncedSearch, backendFilteredLogs, lastSearchTimestamp, hasBackendFilters, clientDerivedFilteredLogs, the sort/page/time refetch useEffect, and the filteredLogs chooser memo. * Clean up remaining smells: remove isFetchingDeferred, internalize selectedTimeInterval, fix circular import - Remove useDeferredValue/isButtonLoading — pass logsQuery.isFetching directly - Move selectedTimeInterval into LogsTableToolbar as internal state - Move PaginatedResponse type from index.tsx to log_filter_logic.tsx * Fix quick-select dropdown overlapping sidebar * Fix stale quick-select label after Reset Filters Move selectedTimeInterval back to parent so handleFilterReset can reset it to the 24-hour default. The toolbar receives it as a prop. * refactor useLogFilterLogic tests for controlled-hook + backend-query shape The hook no longer owns filter state or does client-side filtering — it receives filters/setFilters as props and drives filteredLogs from a useQuery over uiSpendLogsCall. Reshape the tests around that contract: introduce a controlled harness that owns filter state, collapse the 10 per-filter assertions into a single it.each over filterKey → API param, and drop the client-side passthrough tests (the .min test file and the "return all logs when no filters" / "empty when logs null" cases) that no longer correspond to any hook behavior. * cover new useLogFilterLogic invariants: activeTab gate, filterByCurrentUser fallback, debounce negative, partial merge Follow-up to the test refactor. Adds coverage for invariants the refactored hook contract introduced but that the first pass didn't assert: - query enablement: expand the single accessToken-null case into an it.each over all four credential props (accessToken, token, userRole, userID), plus a separate test for activeTab !== "request logs" - filterByCurrentUser: when true with a blank User ID filter, the outbound request carries user_id = userID - debounce: also assert the negative case — no call in the first 100ms after a filter change (first waiting out the initial mount fire) - handleFilterChange: partial updates merge without clobbering other filter keys (protects the spread + default-fill semantics) - handleFilterReset: calls setCurrentPage(1) alongside restoring filters * fix typo dropping the live-tail banner border Tailwind silently ignores unknown classes, so border-greem-200 was leaving the auto-refresh banner with only its bg-green-50 fill and no outline. * memoize columns and derived table data in SpendLogsTable The table's columns array, four-pass data pipeline, and sort-change handler were all being rebuilt on every parent render. That made every filter click re-instance all 23 TanStack-Table columns, re-run filter/reduce/map over all rows, and recreate per-row click closures — all before the intentional 300ms debounce timer even got a chance to fire. Local measurement (40 rows, dev mode): filter click → query fires: 1957ms → 1217ms (−38%) Wrap createColumns in useMemo keyed on sortBy/sortOrder, hoist onSortChange into a useCallback, and move the searchedLogs / sessionComposition / sessionRepresentativeMap / filteredData derivations into a single useMemo keyed on filteredLogs.data + searchTerm. These were pre-existing issues on main — not regressions from the hook refactor — but the refactor made them user-visible because the new query debounce put render cost on the critical path. * apply dropdown filters instantly, debounce only text inputs Dropdown selects now bypass the 300ms debounce so a click updates the table immediately. Text inputs (Key Hash, Error Message, Request ID, User ID) still debounce. handleFilterReset also clears the pending debounced value so a half-typed text filter can't re-fire after reset. * fix(ui/spend-logs): restore lost loading/debounce behavior + cover dropped tests Regressions from the spend-logs-view refactor: - debounce the 'Public model / search tool' text filter (was firing a backend query per keystroke) via TEXT_FILTER_KEYS - restore Fetch-button smoothing through table repaint using useDeferredValue on the rendered data (explicit staleness) - show AntDLoadingSpinner during the auth-resolve phase instead of a blank screen on first load - only live-tail-poll while the tab is visible (refetchIntervalInBackground: false) - extract getLiveTailRefetchInterval helper for the poll decision Tests: - LogDetailContent: retries display (>0 / 0 / absent), overhead-absent - log_filter_logic: regression guard that the public-model filter debounces; getLiveTailRefetchInterval unit tests - logs_utils: getTimeRangeDisplay quick-select window labels * test(ui/spend-logs): cover the cold-load auth-not-ready spinner guard Asserts SpendLogsTable shows a loading spinner (not a blank screen) while credentials are unresolved, and renders the table once present.
…#28281) * fix(tests): replace shut-down gpt-4o-audio-preview with gpt-audio-1.5 OpenAI shut down gpt-4o-audio-preview on 2026-05-07, so the live audio calls in test_stream_chunk_builder_openai_audio_output_usage and test_standard_logging_payload_audio now hard-fail with a model-not-found error on every PR. The error was not "openai-internal", so the except block swallowed it and execution fell through to an unbound completion/response (UnboundLocalError). Switch both tests to gpt-audio-1.5, OpenAI's recommended successor (GA, not deprecated, already present in the litellm cost map so the response_cost assertion still resolves). Also broaden the except to skip with the real error in the reason instead of crashing, so a transient upstream blip can't reintroduce the UnboundLocalError. * fix(tests): narrow audio-test skip to model-not-found, re-raise the rest Address review feedback: an unconditional skip on any exception would silently mask a litellm-internal regression in the audio path (broken param transformation, serialization, bad header) instead of failing CI. Skip only on the upstream-unavailable class (model_not_found / "does not exist" / openai-internal) and re-raise everything else, so genuine regressions still fail loudly. The UnboundLocalError is still fixed because the handler either skips or raises - it never falls through. * fix(tests): add budget_exceeded to expected Interaction status enum Staging added budget_exceeded to the Interaction OpenAPI status enum; the staging merge into this branch picked up the spec change but not the matching test update, so test_status_enum_values failed in CI. Align the test's expected list (exact-match by design) with the live spec. * fix(tests): mock HTTP fetch in test_img_url_token_counter The test parameterized a live third-party image URL (blog.purpureus.net) which now 404s, causing get_image_dimensions to fall through to its base64 decode path and crash with 'not enough values to unpack' on every PR run. Mock safe_get with a tiny 1x1 PNG so the URL branch is still exercised without any network dependency. * fix(tests): swap gpt-4o-audio-preview to gpt-audio-1.5 in test_gpt4o_audio OpenAI shut down gpt-4o-audio-preview on 2026-05-07, so both live tests in test_gpt4o_audio.py (test_audio_output_from_model and test_audio_input_to_model) hard-fail model_not_found on every PR. Swap the hardcoded model to OpenAI's successor gpt-audio-1.5 (same chat-completions audio surface; already in the litellm cost map). Mirror the narrowed-skip pattern from the prior audio fixes: skip on model_not_found / does-not-exist / openai-internal, re-raise everything else so genuine litellm regressions still fail CI loudly.
* bump: version 0.4.72 → 0.4.73 * bump: version 1.86.0 → 1.87.0 * uv lock
Contributor
|
Too many files changed for review. ( |
|
|
Contributor
ryan-crabbe-berri
approved these changes
May 19, 2026
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
| api_key: effectiveFilters[FILTER_KEYS.KEY_HASH] || undefined, | ||
| team_id: effectiveFilters[FILTER_KEYS.TEAM_ID] || undefined, | ||
| request_id: effectiveFilters[FILTER_KEYS.REQUEST_ID] || undefined, | ||
| user_id: effectiveFilters[FILTER_KEYS.USER_ID] || (filterByCurrentUser ? userID ?? undefined : undefined), |
Codecov Report❌ Patch coverage is 📢 Thoughts on this report? Let us know! |
Contributor
There was a problem hiding this comment.
CodeQL found more than 20 potential problems in the proposed changes. Check the Files changed tab for more details.
- Add `_set_team_attributes_on_span` helper to stamp team_id/team_alias onto any span, ensuring these attributes are not limited to the root litellm_request span - Add `_set_team_attributes_from_kwargs` helper to extract team metadata from the standard_logging_object in kwargs and apply them to a span - Apply team attributes to raw request spans via `_maybe_log_raw_request` so downstream consumers can filter traces by team without needing the root span - Apply team attributes to guardrail spans so guardrail activity can be correlated to teams in tracing backends - Apply team attributes to exception logging spans to preserve team context during failure paths - Add comprehensive unit tests covering all new helpers, including edge cases where metadata or standard_logging_object is absent Co-authored-by: Yassin Kortam <[email protected]>
* Add day 0 support for gemini 3.5 flash * Fix pricing * Fix greptile review * Fix failing test * Fix tests * Fix: revert tool removing logic * fix greptile and test --------- Co-authored-by: mateo-berri <[email protected]>
* Add support for environment variable in interactions api * Add sdk support for gemini create agent * Add agents endpoint support via proxy * Add outputs of each api * Add routing for model and agents param * Remove redundant condition in get_provider_agents_api_config LlmProviders.GEMINI.value is literally the string "gemini", so the second clause of the or was checking the exact same thing as the first. Co-authored-by: Sameer Kankute <[email protected]> * fix: forward query-param credentials to list/get/delete/versions Gemini agent endpoints The list_gemini_agents, get_gemini_agent, delete_gemini_agent, and list_gemini_agent_versions endpoints previously constructed a hardcoded data dict with no mechanism to pass provider credentials. Unlike create_gemini_agent (POST, reads litellm_params_template from body), these GET/DELETE endpoints gave no way for multi-tenant callers to supply a per-request api_key or other LiteLLM params. Fix: - Add _merge_query_params_into_data() helper that reads query parameters from the request and merges them into the data dict without overwriting already-set keys (e.g. path params like 'name'). - Support a JSON-encoded litellm_params_template query parameter (matching the POST body pattern) as well as flat key=value pairs (e.g. api_key=AIza...). - Apply the helper in all four affected endpoints. - Add 13 unit tests covering the helper and each endpoint. Co-authored-by: Sameer Kankute <[email protected]> * fix: pass model=None for managed agent proxy endpoints to prevent agent name polluting data["model"] Endpoints acreate_agent, aget_agent, adelete_agent, and alist_agent_versions were passing model=<agent_name> to base_process_llm_request. This caused common_processing_pre_call_logic to write the agent name into self.data["model"], which then triggered spurious model-alias mapping, rate-limiting lookups, and logging tied to a non-existent model deployment. The agent name is already carried in data["name"] and is passed correctly to the SDK functions (litellm.interactions.agents.*). There is no reason to also set model=<agent_name>; the correct value is model=None for all five managed-agent management routes. Adds tests/test_litellm/proxy/google_endpoints/test_managed_agents_model_param.py to verify all five managed-agent endpoints pass model=None. Co-authored-by: Sameer Kankute <[email protected]> * fix: address greptile P1/P2 review comments P1 (router.py): Restore fallback/retry support for acreate_interaction and create_interaction. Both were silently moved to _init_interactions_api_endpoints (direct call, no fallbacks). Moved them back to _ageneric_api_call_with_fallbacks so users with configured fallback models keep retry behaviour. P1 security (agents_endpoints.py): Remove flat query-param credential path (e.g. ?api_key=AIza...) from _merge_query_params_into_data. Credentials in URL query strings appear verbatim in server access logs, CDN edge logs, and browser history. Only the JSON-encoded litellm_params_template query param (matching the POST body pattern) is retained. P2 (interactions/http_handler.py): Extract _BaseHTTPHandler with shared _handle_error, _sync_client, and _async_client helpers. InteractionsHTTPHandler now extends _BaseHTTPHandler. The _async_client reads the provider from litellm_params instead of hardcoding GEMINI. P2 (interactions/agents/http_handler.py): AgentsHTTPHandler now extends InteractionsHTTPHandler (which inherits _BaseHTTPHandler) so all shared HTTP infrastructure is reused rather than duplicated. Removes the hardcoded LlmProviders.GEMINI from the async client path. Co-authored-by: Cursor <[email protected]> * fix: address CI failures from greptile review fixes - black: format interactions/agents/main.py and utils.py - tests: update test_gemini_agents_endpoints.py to match new _merge_query_params_into_data behaviour (flat credential params are rejected; only JSON-encoded litellm_params_template is accepted) - ci: add test_gemini_agents_endpoints.py to endpoints-and-responses shard in test-unit-proxy-db.yml so assert-shard-coverage passes - tests: add _initialize_managed_agents_endpoints and _init_managed_agents_api_endpoints test coverage so router_code_coverage passes; also fix TestRouterCreateInteractionRouting to reflect that acreate_interaction now correctly routes through _ageneric_api_call_with_fallbacks (restoring fallback support) Co-authored-by: Cursor <[email protected]> * fix: remove InteractionsHTTPHandler._handle_error override to fix type errors AgentsHTTPHandler extends InteractionsHTTPHandler and calls self._handle_error(provider_config=agents_api_config) where agents_api_config is BaseAgentsAPIConfig. Python MRO resolved _handle_error to InteractionsHTTPHandler._handle_error which expected BaseInteractionsAPIConfig, causing 10 mypy arg-type errors in interactions/agents/http_handler.py. Removing the redundant override lets both classes inherit _BaseHTTPHandler._handle_error (provider_config: Any) which is structurally correct for both config types. Co-authored-by: Cursor <[email protected]> * fix: agent-only interactions and managed agents provider routing Resolve None custom_llm_provider in agents HTTP client lookup and set custom_llm_provider on GenericLiteLLMParams for all agent CRUD paths. Stop mapping agent names to proxy model routing; route interactions through _init_interactions_api_endpoints with fallbacks only when model is set. Consolidate duplicate router elif branches for interaction APIs. Co-authored-by: Cursor <[email protected]> * Fix greptile review * test(agents): add unit tests for managed agents SDK and HTTP handler Adds coverage for the new `litellm.interactions.agents` surface area: - main.py: sync/async entry points (create/list/get/delete/list_versions), provider config lookup, logging-obj helper, async error wrapping - http_handler.py: every CRUD method (sync + async paths), `_is_async` dispatch branches, and provider error mapping through GeminiAgentsConfig - utils.py: get_provider_agents_api_config for supported / unsupported providers Brings patch coverage on these files from <25% to ~100% so codecov/patch is satisfied. Co-authored-by: Mateo Wang <[email protected]> * docs(gemini-agents): fix misleading credential-passing examples in GET/DELETE docstrings (#28293) The four GET/DELETE endpoint docstrings (list_gemini_agents, get_gemini_agent, delete_gemini_agent, list_gemini_agent_versions) documented passing per-request credentials as flat query parameters (e.g. ?api_key=AIza...). However, _merge_query_params_into_data only reads the JSON-encoded litellm_params_template query parameter and intentionally ignores flat params (URL query strings appear verbatim in access logs, browser history, and Referer headers). Callers following the documented curl examples would have their credentials silently dropped and hit auth failures against Gemini. Update the examples to use the supported JSON-encoded litellm_params_template query parameter, matching _merge_query_params_into_data's own docstring. Co-authored-by: Cursor Agent <[email protected]> Co-authored-by: Mateo Wang <[email protected]> * refactor(agents): rename provider-agnostic agent response types Move GeminiAgent{ListResponse,DeleteResult,VersionsResponse} to provider-neutral names (AgentListResponse, AgentDeleteResult, AgentVersionsResponse) so the BaseAgentsAPIConfig interface no longer references Gemini-specific type names. * fix(gemini-agents): close veria-flagged credential-escalation gaps Two high-severity findings from the veria-ai PR review are addressed: 1. **api_base override could leak the shared Gemini key** GeminiAgentsConfig.validate_environment falls back to GOOGLE_API_KEY / GEMINI_API_KEY when no api_key is supplied. Combined with caller-controlled api_base on the proxy CRUD endpoints, an authenticated user could redirect the outbound request to an attacker-controlled host and capture the operator's shared Gemini key from the x-goog-api-key header. The config now refuses env-fallback whenever api_base is explicitly overridden. 2. **Managed-agent CRUD exposed to ordinary LLM keys** The new /v1beta/agents routes live in google_routes (i.e. llm_api_routes), so any non-admin LLM key can reach them. Unlike /v1beta/models/...: generateContent these endpoints are NOT model-routed and have no model_list-supplied credentials, so env-fallback would let any LLM key list / create / delete agents inside the operator's Gemini project. Each endpoint now calls _enforce_caller_supplied_provider_key, which requires non-admin callers to supply their own Gemini api_key via litellm_params_template. Proxy admins keep the env-fallback convenience. Tests cover non-admin rejection, admin allow-through, the api_base override guard, and SDK env-fallback when api_base is not overridden. Co-authored-by: Mateo Wang <[email protected]> * test(router): restore strict assert_called_once_with on interactions default-provider test --------- Co-authored-by: Cursor Agent <[email protected]> Co-authored-by: Sameer Kankute <[email protected]> Co-authored-by: mateo-berri <[email protected]> Co-authored-by: Mateo Wang <[email protected]>
mateo-berri
approved these changes
May 19, 2026
blake-hamm
added a commit
to blake-hamm/bhamm-lab
that referenced
this pull request
Jun 16, 2026
…to v1.89.0 (#200)
This PR contains the following updates:
| Package | Update | Change |
|---|---|---|
| [https://github.com/BerriAI/litellm.git](https://github.com/BerriAI/litellm) | minor | `v1.85.1` → `v1.89.0` |
---
> ⚠️ **Warning**
>
> Some dependencies could not be looked up. Check the [Dependency Dashboard](issues/155) for more information.
---
### Release Notes
<details>
<summary>BerriAI/litellm (https://github.com/BerriAI/litellm.git)</summary>
### [`v1.89.0`](https://github.com/BerriAI/litellm/releases/tag/v1.89.0)
[Compare Source](https://github.com/BerriAI/litellm/compare/v1.88.2...v1.89.0)
#### 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:v1.89.0
```
**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/v1.89.0/cosign.pub \
ghcr.io/berriai/litellm:v1.89.0
```
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
- test(responses): bump deprecated gemini-3-pro-preview to gemini-3.1-pro-preview by [@​mateo-berri](https://github.com/mateo-berri) in [#​29433](https://github.com/BerriAI/litellm/pull/29433)
- fix: map mistral/ministral-8b-latest in model price map by [@​mateo-berri](https://github.com/mateo-berri) in [#​29453](https://github.com/BerriAI/litellm/pull/29453)
- fix(datadog): split oversized batches on 413 instead of re-queueing forever by [@​yassin-berriai](https://github.com/yassin-berriai) in [#​29444](https://github.com/BerriAI/litellm/pull/29444)
- feat(otel): allowlist team\_metadata sub-keys promoted to baggage by [@​yassin-berriai](https://github.com/yassin-berriai) in [#​29442](https://github.com/BerriAI/litellm/pull/29442)
- fix: stop use\_chat\_completions\_api flag from leaking into provider request body by [@​mateo-berri](https://github.com/mateo-berri) in [#​29447](https://github.com/BerriAI/litellm/pull/29447)
- fix(anthropic, fireworks): inline legacy $ref defs in tool schemas by [@​milan-berri](https://github.com/milan-berri) in [#​28646](https://github.com/BerriAI/litellm/pull/28646)
- fix(proxy): omit OpenAI \[DONE] on google-genai streamGenerateContent by [@​Sameerlite](https://github.com/Sameerlite) in [#​29426](https://github.com/BerriAI/litellm/pull/29426)
- ci(release): create stable/X.Y.x line branch on X.Y.0 tags by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​29457](https://github.com/BerriAI/litellm/pull/29457)
- fix(vector-stores): support engines URL for Vertex AI Search by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​27885](https://github.com/BerriAI/litellm/pull/27885)
- fix(ui): render caller-supplied filter options in caller order by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​29462](https://github.com/BerriAI/litellm/pull/29462)
- fix(batches): skip unnecessary batch input file reads by [@​Sameerlite](https://github.com/Sameerlite) in [#​29114](https://github.com/BerriAI/litellm/pull/29114)
- docs(agents): clarify when to create new test files by [@​Sameerlite](https://github.com/Sameerlite) in [#​29472](https://github.com/BerriAI/litellm/pull/29472)
- Litellm OSS Staging by [@​Sameerlite](https://github.com/Sameerlite) in [#​29161](https://github.com/BerriAI/litellm/pull/29161)
- fix(mcp): clear allowed\_tools and tool overrides on MCP server edit by [@​Sameerlite](https://github.com/Sameerlite) in [#​29411](https://github.com/BerriAI/litellm/pull/29411)
- Litellm OSS Staging 010626 by [@​Sameerlite](https://github.com/Sameerlite) in [#​29422](https://github.com/BerriAI/litellm/pull/29422)
- fix(ci): make CircleCI rerun-failed-tests collect tests when 2+ test files fail by [@​mateo-berri](https://github.com/mateo-berri) in [#​29475](https://github.com/BerriAI/litellm/pull/29475)
- feat(a2a): watsonx Orchestrate agent provider by [@​Sameerlite](https://github.com/Sameerlite) in [#​29410](https://github.com/BerriAI/litellm/pull/29410)
- fix(azure\_ai): strip tool-level extra fields on 400 and retry by [@​Sameerlite](https://github.com/Sameerlite) in [#​29479](https://github.com/BerriAI/litellm/pull/29479)
- fix(docs): remove fixed dimensions from README hero image by [@​mateo-berri](https://github.com/mateo-berri) in [#​29496](https://github.com/BerriAI/litellm/pull/29496)
- Litellm oss staging by [@​Sameerlite](https://github.com/Sameerlite) in [#​29492](https://github.com/BerriAI/litellm/pull/29492)
- fix: small CLAUDE.md nits by [@​mateo-berri](https://github.com/mateo-berri) in [#​29504](https://github.com/BerriAI/litellm/pull/29504)
- Add MCP semantic conventions to otelv2 by [@​yassin-berriai](https://github.com/yassin-berriai) in [#​29468](https://github.com/BerriAI/litellm/pull/29468)
- fix(passthrough): emit otel guardrail span when a guardrail blocks by [@​yassin-berriai](https://github.com/yassin-berriai) in [#​29470](https://github.com/BerriAI/litellm/pull/29470)
- fix(proxy): strip NUL bytes from spend log payloads to prevent PostgreSQL 22P05 by [@​milan-berri](https://github.com/milan-berri) in [#​29515](https://github.com/BerriAI/litellm/pull/29515)
- \[internal copy of [#​28008](https://github.com/BerriAI/litellm/issues/28008)] Support MCP OAuth passthrough and issuer-scoped JWT auth by [@​mateo-berri](https://github.com/mateo-berri) in [#​28356](https://github.com/BerriAI/litellm/pull/28356)
- feat(vector-stores): forward per-request params to Vertex AI Search by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​29459](https://github.com/BerriAI/litellm/pull/29459)
- feat(proxy): add per-MCP-server RPM rate limiting for keys and teams by [@​Sameerlite](https://github.com/Sameerlite) in [#​29482](https://github.com/BerriAI/litellm/pull/29482)
- fix(tests): drop module-level test calls that break local\_testing collection by [@​mateo-berri](https://github.com/mateo-berri) in [#​29520](https://github.com/BerriAI/litellm/pull/29520)
- feat(agents): add LangFlow agent provider with A2A session bridging by [@​Sameerlite](https://github.com/Sameerlite) in [#​28963](https://github.com/BerriAI/litellm/pull/28963)
- fix(ui/agents): make A2A skill tags enterable and validated by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​29512](https://github.com/BerriAI/litellm/pull/29512)
- \[internal copy of [#​29232](https://github.com/BerriAI/litellm/issues/29232)] feat: route future Claude models to Anthropic provider via pattern matching by [@​mateo-berri](https://github.com/mateo-berri) in [#​29239](https://github.com/BerriAI/litellm/pull/29239)
- fix(tests): drop import-time completion call in test\_register\_model by [@​mateo-berri](https://github.com/mateo-berri) in [#​29521](https://github.com/BerriAI/litellm/pull/29521)
- test: stabilize batch VCR coverage and stop live upload/network leaks by [@​mateo-berri](https://github.com/mateo-berri) in [#​29477](https://github.com/BerriAI/litellm/pull/29477)
- \[internal copy of [#​29003](https://github.com/BerriAI/litellm/issues/29003)] fix(vertex\_ai): use user-supplied api\_base as is for Model Garden OpenAI-compat path by [@​mateo-berri](https://github.com/mateo-berri) in [#​29530](https://github.com/BerriAI/litellm/pull/29530)
- feat(proxy): native /health/drain preStop hook for graceful shutdown by [@​yassin-berriai](https://github.com/yassin-berriai) in [#​29439](https://github.com/BerriAI/litellm/pull/29439)
- fix(auth): preserve 401 status for expired JWTs in OTel traces by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​29510](https://github.com/BerriAI/litellm/pull/29510)
- fix(otel): capture 401 error details in management endpoint spans by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​29535](https://github.com/BerriAI/litellm/pull/29535)
- test(proxy/utils): pin bottom-of-file helper behavior by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​29509](https://github.com/BerriAI/litellm/pull/29509)
- test(proxy/utils): pin PrismaClient and spend-update behavior by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​29488](https://github.com/BerriAI/litellm/pull/29488)
- test(proxy/utils): pin ProxyLogging behavior by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​29485](https://github.com/BerriAI/litellm/pull/29485)
- fix: missing span for guardrail passthrough by [@​yassin-berriai](https://github.com/yassin-berriai) in [#​29552](https://github.com/BerriAI/litellm/pull/29552)
- fix(auth): let internal users view search tools by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​29542](https://github.com/BerriAI/litellm/pull/29542)
- fix: missing mcp otel attributes by [@​yassin-berriai](https://github.com/yassin-berriai) in [#​29554](https://github.com/BerriAI/litellm/pull/29554)
- fix(proxy): resolve managed video model ids for auth by [@​shivamrawat1](https://github.com/shivamrawat1) in [#​29545](https://github.com/BerriAI/litellm/pull/29545)
- fix(key\_generate): allow team members to create keys on org-scoped teams by [@​milan-berri](https://github.com/milan-berri) in [#​29310](https://github.com/BerriAI/litellm/pull/29310)
- test(pass-through): move Gemini pass-through tests to gemini-3.1-flash-lite by [@​mateo-berri](https://github.com/mateo-berri) in [#​29595](https://github.com/BerriAI/litellm/pull/29595)
- Litellm oss staging 030626 by [@​Sameerlite](https://github.com/Sameerlite) in [#​29578](https://github.com/BerriAI/litellm/pull/29578)
- Fix : a2a bugs 030626 by [@​Sameerlite](https://github.com/Sameerlite) in [#​29566](https://github.com/BerriAI/litellm/pull/29566)
- \[internal copy of [#​29533](https://github.com/BerriAI/litellm/issues/29533)] fix(anthropic/adapter): emit thinking block for reasoning\_content-only streaming chunks by [@​mateo-berri](https://github.com/mateo-berri) in [#​29600](https://github.com/BerriAI/litellm/pull/29600)
- ci: reproduce default-Windows wheel install to guard MAX\_PATH by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​29597](https://github.com/BerriAI/litellm/pull/29597)
- fix(vertex): strip output\_config.effort for Vertex Claude models that reject it (Haiku 4.5) by [@​mateo-berri](https://github.com/mateo-berri) in [#​29585](https://github.com/BerriAI/litellm/pull/29585)
- Litellm websocket improvements by [@​Sameerlite](https://github.com/Sameerlite) in [#​29563](https://github.com/BerriAI/litellm/pull/29563)
- feat(arize/phoenix): OpenInference rendering parity — tool\_calls, cost, passthrough I/O, session/user, multimodal, cache tokens by [@​milan-berri](https://github.com/milan-berri) in [#​28800](https://github.com/BerriAI/litellm/pull/28800)
- \[internal copy of [#​29550](https://github.com/BerriAI/litellm/issues/29550)] fix: passthrough endpoints duplicate logs by [@​mateo-berri](https://github.com/mateo-berri) in [#​29598](https://github.com/BerriAI/litellm/pull/29598)
- fix(ci): keep coverage rename green when a parallel node runs no tests by [@​mateo-berri](https://github.com/mateo-berri) in [#​29608](https://github.com/BerriAI/litellm/pull/29608)
- test(vcr): close out the remaining VCR live-call leaks by [@​mateo-berri](https://github.com/mateo-berri) in [#​29603](https://github.com/BerriAI/litellm/pull/29603)
- fix(key\_generate): exempt UI/CLI session tokens from the budget ceiling for team keys by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​29612](https://github.com/BerriAI/litellm/pull/29612)
- fix(realtime): allow null transcripts in stream logging payloads by [@​milan-berri](https://github.com/milan-berri) in [#​29625](https://github.com/BerriAI/litellm/pull/29625)
- build(ui): migrate eslint to flat config + bump eslint-config-next to 16 by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​29626](https://github.com/BerriAI/litellm/pull/29626)
- fix(key\_generate): scope session-token team-key budget exemption to caller-supplied team\_id by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​29641](https://github.com/BerriAI/litellm/pull/29641)
- fix(proxy): disable proxy buffering on streaming SSE responses by [@​mateo-berri](https://github.com/mateo-berri) in [#​29557](https://github.com/BerriAI/litellm/pull/29557)
- fix(mcp): gate /public/mcp\_hub strictly on litellm.public\_mcp\_servers by [@​michelligabriele](https://github.com/michelligabriele) in [#​27764](https://github.com/BerriAI/litellm/pull/27764)
- ci(ui): frontend-lint job enforcing prettier + eslint on changed files by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​29633](https://github.com/BerriAI/litellm/pull/29633)
- fix(gemini): googleSearch + server-side tools and googleMaps JSON schema by [@​Sameerlite](https://github.com/Sameerlite) in [#​29582](https://github.com/BerriAI/litellm/pull/29582)
- fix(proxy): passthrough 404 when SERVER\_ROOT\_PATH is set by [@​Sameerlite](https://github.com/Sameerlite) in [#​29658](https://github.com/BerriAI/litellm/pull/29658)
- fix(gemini-realtime): use GA event names for Pipecat 1.3.x compatibility by [@​Sameerlite](https://github.com/Sameerlite) in [#​29662](https://github.com/BerriAI/litellm/pull/29662)
- Litellm oss staging 040626 by [@​Sameerlite](https://github.com/Sameerlite) in [#​29671](https://github.com/BerriAI/litellm/pull/29671)
- style(ui): prettier formatting pass over the dashboard by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​29622](https://github.com/BerriAI/litellm/pull/29622)
- chore: ignore prettier dashboard reformat in git blame by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​29695](https://github.com/BerriAI/litellm/pull/29695)
- fix(helm): Enable Backend Deployment to mount Gateway config.yaml by [@​tin-berri](https://github.com/tin-berri) in [#​29605](https://github.com/BerriAI/litellm/pull/29605)
- \[internal copy of [#​29277](https://github.com/BerriAI/litellm/issues/29277)] fix(proxy): add default=None to LiteLLM\_TeamMembership.litellm\_budget\_table by [@​mateo-berri](https://github.com/mateo-berri) in [#​29684](https://github.com/BerriAI/litellm/pull/29684)
- test: make custom\_tokenizer proxy tests hermetic by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​29643](https://github.com/BerriAI/litellm/pull/29643)
- test(proxy): stop running real-DB tests in GitHub Actions unit jobs by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​29700](https://github.com/BerriAI/litellm/pull/29700)
- chore(ui): remove the bare-fetch lint rule by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​29712](https://github.com/BerriAI/litellm/pull/29712)
- Litellm jwt mapping virtualkeys by [@​shivamrawat1](https://github.com/shivamrawat1) in [#​28510](https://github.com/BerriAI/litellm/pull/28510)
- refactor(ui): shared HTTP client + location-pinned fetch() lint rule by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​29723](https://github.com/BerriAI/litellm/pull/29723)
- fix(proxy): stop team BYOK model name corruption on model edit by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​29731](https://github.com/BerriAI/litellm/pull/29731)
- \[internal copy of [#​29511](https://github.com/BerriAI/litellm/issues/29511)] feat(guardrails): add sensitive data routing to on-premise models by [@​mateo-berri](https://github.com/mateo-berri) in [#​29531](https://github.com/BerriAI/litellm/pull/29531)
- fix(proxy/hooks): populate llm\_provider on internal rate-limit errors by [@​mateo-berri](https://github.com/mateo-berri) in [#​27707](https://github.com/BerriAI/litellm/pull/27707)
- fix(vertex/anthropic): handle namespace tools and strip client\_metadata for codex compatibility by [@​Sameerlite](https://github.com/Sameerlite) in [#​29489](https://github.com/BerriAI/litellm/pull/29489)
- Support OAuth M2M for Databricks Apps A2A agents by [@​mateo-berri](https://github.com/mateo-berri) in [#​29586](https://github.com/BerriAI/litellm/pull/29586)
- fix: small CLAUDE.md nit by [@​mateo-berri](https://github.com/mateo-berri) in [#​29749](https://github.com/BerriAI/litellm/pull/29749)
- fix(anthropic): route Claude Opus 4.8 through adaptive thinking by [@​mateo-berri](https://github.com/mateo-berri) in [#​29702](https://github.com/BerriAI/litellm/pull/29702)
- fix(proxy): persist oauth2\_flow on MCP server registration by [@​michelligabriele](https://github.com/michelligabriele) in [#​29690](https://github.com/BerriAI/litellm/pull/29690)
- \[internal copy of [#​27491](https://github.com/BerriAI/litellm/issues/27491)] fix(realtime): Fix Realtime Audio Token Cost Tracking by [@​mateo-berri](https://github.com/mateo-berri) in [#​29722](https://github.com/BerriAI/litellm/pull/29722)
- fix(galileo): use ingest traces API and standard logging payload by [@​Sameerlite](https://github.com/Sameerlite) in [#​29651](https://github.com/BerriAI/litellm/pull/29651)
- fix(auth): expand all-team-models sentinel in can\_key\_call\_model for batch validation by [@​Sameerlite](https://github.com/Sameerlite) in [#​29746](https://github.com/BerriAI/litellm/pull/29746)
- test(vcr): stop refreshing cassette TTL on read so cassettes lapse after 24h by [@​mateo-berri](https://github.com/mateo-berri) in [#​29784](https://github.com/BerriAI/litellm/pull/29784)
- test(ci): record/replay OpenAI image gen so the spend E2E isn't outage-bound by [@​mateo-berri](https://github.com/mateo-berri) in [#​29787](https://github.com/BerriAI/litellm/pull/29787)
- fix(ui): route MCP playground auth by oauth2 mode instead of token\_url by [@​tin-berri](https://github.com/tin-berri) in [#​29714](https://github.com/BerriAI/litellm/pull/29714)
- refactor(ui): centralize proxy base URL resolution into tested resolver by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​29793](https://github.com/BerriAI/litellm/pull/29793)
- Litellm oss staging 050626 by [@​Sameerlite](https://github.com/Sameerlite) in [#​29774](https://github.com/BerriAI/litellm/pull/29774)
- test(google): add google-genai SDK proxy integration tests by [@​Sameerlite](https://github.com/Sameerlite) in [#​29781](https://github.com/BerriAI/litellm/pull/29781)
- fix(jwt): use resolved DB user\_id for spend on legacy email match by [@​milan-berri](https://github.com/milan-berri) in [#​29217](https://github.com/BerriAI/litellm/pull/29217)
- feat(ui): generate dashboard API types from the proxy OpenAPI spec by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​29816](https://github.com/BerriAI/litellm/pull/29816)
- fix(proxy): drop deleted team BYOK model name from team.models by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​29820](https://github.com/BerriAI/litellm/pull/29820)
- feat(mcp): per-server env vars with global + per-user scopes by [@​mateo-berri](https://github.com/mateo-berri) in [#​28917](https://github.com/BerriAI/litellm/pull/28917)
- refactor(ui): route behavior-preserving networking calls through apiClient by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​29806](https://github.com/BerriAI/litellm/pull/29806)
- fix(mcp): persist Tools-tab MCP OAuth token to DB by [@​tin-berri](https://github.com/tin-berri) in [#​29809](https://github.com/BerriAI/litellm/pull/29809)
- fix(ui): require new expiration when regenerating an expired key by [@​milan-berri](https://github.com/milan-berri) in [#​29838](https://github.com/BerriAI/litellm/pull/29838)
- refactor(ui): route query-building networking calls through apiClient by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​29815](https://github.com/BerriAI/litellm/pull/29815)
- Make the image-gen record/replay proxy report cache mode and per-request HIT/MISS by [@​mateo-berri](https://github.com/mateo-berri) in [#​29802](https://github.com/BerriAI/litellm/pull/29802)
- feat(proxy): hot-reload .env in dev when running with --reload by [@​mateo-berri](https://github.com/mateo-berri) in [#​29783](https://github.com/BerriAI/litellm/pull/29783)
- fix(ui): stop MCP playground tool calls from sending twice by [@​tin-berri](https://github.com/tin-berri) in [#​29821](https://github.com/BerriAI/litellm/pull/29821)
- feat(fal\_ai): add Nano Banana / Gemini 2.5 Flash Image generation support by [@​mateo-berri](https://github.com/mateo-berri) in [#​29798](https://github.com/BerriAI/litellm/pull/29798)
- Title: Fix managed batch cancel credential resolution by [@​shivamrawat1](https://github.com/shivamrawat1) in [#​29734](https://github.com/BerriAI/litellm/pull/29734)
- Title: fix(proxy): resolve vector store file list credentials from team deployments by [@​shivamrawat1](https://github.com/shivamrawat1) in [#​29739](https://github.com/BerriAI/litellm/pull/29739)
- refactor: convert AWS and GCP Terraform stacks into reusable modules … by [@​yassin-berriai](https://github.com/yassin-berriai) in [#​28103](https://github.com/BerriAI/litellm/pull/28103)
- chore(ui): build ui for release by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​29853](https://github.com/BerriAI/litellm/pull/29853)
- fix(terraform/gcp): prompt for image\_registry in DeployStack one-click by [@​yassin-berriai](https://github.com/yassin-berriai) in [#​29852](https://github.com/BerriAI/litellm/pull/29852)
- fix(terraform/gcp): abandon SQL user on destroy by [@​yassin-berriai](https://github.com/yassin-berriai) in [#​29855](https://github.com/BerriAI/litellm/pull/29855)
- Extend the record/replay proxy to chat, embeddings, moderations, rerank, and Anthropic by [@​mateo-berri](https://github.com/mateo-berri) in [#​29847](https://github.com/BerriAI/litellm/pull/29847)
- chore(deps): bump deps by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​29860](https://github.com/BerriAI/litellm/pull/29860)
- chore(ci): promote internal staging to main by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​29861](https://github.com/BerriAI/litellm/pull/29861)
- fix: 400 on Anthropic context overflow; seed identity on failed auth by [@​yassin-berriai](https://github.com/yassin-berriai) in [#​29848](https://github.com/BerriAI/litellm/pull/29848)
- chore(ci): promote internal staging to main by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​29862](https://github.com/BerriAI/litellm/pull/29862)
- chore(release): patch v1.89.0-rc.1 with [#​30064](https://github.com/BerriAI/litellm/issues/30064) (Claude Fable 5) for v1.89.0-rc.2 by [@​mateo-berri](https://github.com/mateo-berri) in [#​30143](https://github.com/BerriAI/litellm/pull/30143)
**Full Changelog**: <https://github.com/BerriAI/litellm/compare/v1.88.0...v1.89.0>
### [`v1.88.2`](https://github.com/BerriAI/litellm/releases/tag/v1.88.2)
[Compare Source](https://github.com/BerriAI/litellm/compare/v1.88.1...v1.88.2)
#### 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:v1.88.2
```
**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/v1.88.2/cosign.pub \
ghcr.io/berriai/litellm:v1.88.2
```
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
- chore(release): backport Fable 5, batch-file auth, CrowdStrike AIDR, Mantle Responses SigV4, and NetApp streaming-cost fix to stable/1.88.x and cut 1.88.2 by [@​mateo-berri](https://github.com/mateo-berri) in [#​30144](https://github.com/BerriAI/litellm/pull/30144)
- chore(release): backport DB-resilience, passthrough, model-info, budget, and deps fixes to stable/1.88.x by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​30408](https://github.com/BerriAI/litellm/pull/30408)
**Full Changelog**: <https://github.com/BerriAI/litellm/compare/v1.88.1...v1.88.2>
### [`v1.88.1`](https://github.com/BerriAI/litellm/releases/tag/v1.88.1)
[Compare Source](https://github.com/BerriAI/litellm/compare/v1.88.0...v1.88.1)
#### 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`](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:v1.88.1
```
**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/v1.88.1/cosign.pub \
ghcr.io/berriai/litellm:v1.88.1
```
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
- build(deps): bump pyjwt to 2.13.0 and ws override to 8.20.1 (1.88.x) by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​29987](https://github.com/BerriAI/litellm/pull/29987)
- chore(release): bump version to 1.88.1 by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​29989](https://github.com/BerriAI/litellm/pull/29989)
**Full Changelog**: <https://github.com/BerriAI/litellm/compare/v1.88.0...v1.88.1>
### [`v1.88.0`](https://github.com/BerriAI/litellm/releases/tag/v1.88.0)
[Compare Source](https://github.com/BerriAI/litellm/compare/v1.87.3...v1.88.0)
#### 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:v1.88.0
```
**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/v1.88.0/cosign.pub \
ghcr.io/berriai/litellm:v1.88.0
```
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(proxy): gate team allowed\_passthrough\_routes to proxy admins by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​28097](https://github.com/BerriAI/litellm/pull/28097)
- fix(tests): stabilize image-edit VCR cassettes to stop live gpt-image-1 spend by [@​mateo-berri](https://github.com/mateo-berri) in [#​28110](https://github.com/BerriAI/litellm/pull/28110)
- fix(bedrock/cohere): send embedding\_types as JSON array, not string by [@​ishaan-berri](https://github.com/ishaan-berri) in [#​28172](https://github.com/BerriAI/litellm/pull/28172)
- fix(tests): migrate realtime + rerank tests off shut-down upstream models by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​28191](https://github.com/BerriAI/litellm/pull/28191)
- fix(caching): replay openai/responses bridge cache hits as chat streams by [@​Sameerlite](https://github.com/Sameerlite) in [#​28158](https://github.com/BerriAI/litellm/pull/28158)
- Litellm oss staging by [@​Sameerlite](https://github.com/Sameerlite) in [#​28161](https://github.com/BerriAI/litellm/pull/28161)
- feat(prometheus): add user\_email and user\_alias to user budget metrics by [@​Sameerlite](https://github.com/Sameerlite) in [#​28155](https://github.com/BerriAI/litellm/pull/28155)
- test(callbacks): harden flaky proxy callback-leak detector by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​28195](https://github.com/BerriAI/litellm/pull/28195)
- fix(bedrock): sanitize batch metadata to prevent Pydantic ValidationError by [@​mateo-berri](https://github.com/mateo-berri) in [#​28202](https://github.com/BerriAI/litellm/pull/28202)
- fix(deepseek): use native /anthropic/v1/messages endpoint and sanitize tools by [@​mateo-berri](https://github.com/mateo-berri) in [#​28200](https://github.com/BerriAI/litellm/pull/28200)
- feat(ui): add Interactions API endpoint to playground with SSE streaming by [@​Sameerlite](https://github.com/Sameerlite) in [#​28156](https://github.com/BerriAI/litellm/pull/28156)
- fix(proxy): decode bytes and pass-through SSE for Google-native streamGenerateContent ([#​27444](https://github.com/BerriAI/litellm/issues/27444)) by [@​Sameerlite](https://github.com/Sameerlite) in [#​28213](https://github.com/BerriAI/litellm/pull/28213)
- refactor(bedrock/sagemaker): switch to lazy loading for response stre… by [@​harish-berri](https://github.com/harish-berri) in [#​28189](https://github.com/BerriAI/litellm/pull/28189)
- \[Refactor] UI - Spend Logs: consolidate filter state and extract components by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​25847](https://github.com/BerriAI/litellm/pull/25847)
- fix(tests): replace shut-down gpt-4o-audio-preview with gpt-audio-1.5 by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​28281](https://github.com/BerriAI/litellm/pull/28281)
- chore(ci): bump versions by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​28287](https://github.com/BerriAI/litellm/pull/28287)
- feat: propagate team\_id and team\_alias to all child OTEL spans by [@​yassin-berriai](https://github.com/yassin-berriai) in [#​28273](https://github.com/BerriAI/litellm/pull/28273)
- Day 0 support : Gemini 3.5 Flash by [@​Sameerlite](https://github.com/Sameerlite) in [#​28268](https://github.com/BerriAI/litellm/pull/28268)
- Gemini managed agents support by [@​Sameerlite](https://github.com/Sameerlite) in [#​28270](https://github.com/BerriAI/litellm/pull/28270)
- chore(ci): promote internal staging to main by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​28292](https://github.com/BerriAI/litellm/pull/28292)
- feat(gemini): add gemini-3.1-flash-lite model cost map by [@​Sameerlite](https://github.com/Sameerlite) in [#​28320](https://github.com/BerriAI/litellm/pull/28320)
- fix(spend\_counter): seed Redis counter via SET NX to prevent cross-pod double-seed by [@​milan-berri](https://github.com/milan-berri) in [#​27854](https://github.com/BerriAI/litellm/pull/27854)
- fix(proxy): normalize batch file IDs before ManagedObjectTable write by [@​Sameerlite](https://github.com/Sameerlite) in [#​28339](https://github.com/BerriAI/litellm/pull/28339)
- fix(router): use forwarded model\_id for native Azure container IDs by [@​Sameerlite](https://github.com/Sameerlite) in [#​27921](https://github.com/BerriAI/litellm/pull/27921)
- fix(ui): restore log filter loading indicator by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​28282](https://github.com/BerriAI/litellm/pull/28282)
- test(e2e): migrate runner to uv, add All Proxy Models key test by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​28313](https://github.com/BerriAI/litellm/pull/28313)
- feat(ui): team passthrough routes create parity + edit load fix by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​28098](https://github.com/BerriAI/litellm/pull/28098)
- fix(mcp): JWT on tools/list and REST tools/call server resolution by [@​Sameerlite](https://github.com/Sameerlite) in [#​28227](https://github.com/BerriAI/litellm/pull/28227)
- feat(interactions): migrate to Google Interactions API steps schema (May 2026) by [@​Sameerlite](https://github.com/Sameerlite) in [#​28153](https://github.com/BerriAI/litellm/pull/28153)
- test(ui-e2e): admin key creation with a specific proxy model by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​28365](https://github.com/BerriAI/litellm/pull/28365)
- fix(vertex\_ai): omit function\_call id on Vertex Gemini 3.5+ tool turns by [@​Sameerlite](https://github.com/Sameerlite) in [#​28324](https://github.com/BerriAI/litellm/pull/28324)
- feat(mcp): allow native MCP OAuth support for cursor by [@​Sameerlite](https://github.com/Sameerlite) in [#​28327](https://github.com/BerriAI/litellm/pull/28327)
- fix(interactions): never drop streamed text deltas; always emit terminal completion by [@​mateo-berri](https://github.com/mateo-berri) in [#​28394](https://github.com/BerriAI/litellm/pull/28394)
- fix(proxy): expose Prisma idle/connect timeout + extra DB URL params by [@​yassin-berriai](https://github.com/yassin-berriai) in [#​28395](https://github.com/BerriAI/litellm/pull/28395)
- Litellm oss staging 1 by [@​Sameerlite](https://github.com/Sameerlite) in [#​28337](https://github.com/BerriAI/litellm/pull/28337)
- fix: serialize guardrail\_response to JSON in OTEL traces by [@​yassin-berriai](https://github.com/yassin-berriai) in [#​28362](https://github.com/BerriAI/litellm/pull/28362)
- chore(ci): merge dev branch by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​28314](https://github.com/BerriAI/litellm/pull/28314)
- test(realtime): expect session.created as xAI realtime initial event by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​28424](https://github.com/BerriAI/litellm/pull/28424)
- feat(tests): behavior-pinning harness + Key Tier-1 matrix by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​28321](https://github.com/BerriAI/litellm/pull/28321)
- fix(proxy): hydrate wildcard discovery credentials ([#​28284](https://github.com/BerriAI/litellm/issues/28284)) - CCI Run by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​28419](https://github.com/BerriAI/litellm/pull/28419)
- Litellm oss staging 04 21 2026 2 by [@​Sameerlite](https://github.com/Sameerlite) in [#​26569](https://github.com/BerriAI/litellm/pull/26569)
- chore(ci): merge dev branch by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​28290](https://github.com/BerriAI/litellm/pull/28290)
- fix(vertex\_gemma): strip `context_management` from request body by [@​mateo-berri](https://github.com/mateo-berri) in [#​28438](https://github.com/BerriAI/litellm/pull/28438)
- fix(logging): recalculate cost after router retry failures by [@​milan-berri](https://github.com/milan-berri) in [#​28476](https://github.com/BerriAI/litellm/pull/28476)
- fix(otel): emit guardrail span on violation, surface status + categories by [@​yassin-berriai](https://github.com/yassin-berriai) in [#​28364](https://github.com/BerriAI/litellm/pull/28364)
- test(proxy): behavior-pinning matrix for team management endpoints by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​28441](https://github.com/BerriAI/litellm/pull/28441)
- test(vertex\_ai): tolerate transient 500 in google maps grounding test by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​28503](https://github.com/BerriAI/litellm/pull/28503)
- fix(docker): restore npm to non\_root builder image by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​28519](https://github.com/BerriAI/litellm/pull/28519)
- chore(ci): bump deps by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​28524](https://github.com/BerriAI/litellm/pull/28524)
- build(deps-dev): bump black to 26.3.1 and apply formatting by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​28525](https://github.com/BerriAI/litellm/pull/28525)
- chore(deps): bump deps by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​28528](https://github.com/BerriAI/litellm/pull/28528)
- test(e2e): forward LITELLM\_LICENSE to UI e2e proxy by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​28398](https://github.com/BerriAI/litellm/pull/28398)
- Add granian as a ASGI compliant web server. Provider better throughput stability, by [@​harish-berri](https://github.com/harish-berri) in [#​26027](https://github.com/BerriAI/litellm/pull/26027)
- Fix conflicts and UI by [@​Sameerlite](https://github.com/Sameerlite) in [#​28477](https://github.com/BerriAI/litellm/pull/28477)
- Add error\_description and hint for oauth flows by [@​Sameerlite](https://github.com/Sameerlite) in [#​28471](https://github.com/BerriAI/litellm/pull/28471)
- feat(mcp): Add tool call and tool list support via UI for Oauth mcps by [@​Sameerlite](https://github.com/Sameerlite) in [#​28454](https://github.com/BerriAI/litellm/pull/28454)
- feat(proxy): persist allowlisted OIDC claims in CLI SSO poll by [@​Sameerlite](https://github.com/Sameerlite) in [#​28463](https://github.com/BerriAI/litellm/pull/28463)
- fix(responses): use OpenAI SSEDecoder for Responses API streaming by [@​Sameerlite](https://github.com/Sameerlite) in [#​28566](https://github.com/BerriAI/litellm/pull/28566)
- Litellm oss staging 2 by [@​Sameerlite](https://github.com/Sameerlite) in [#​28582](https://github.com/BerriAI/litellm/pull/28582)
- \[internal copy of [#​28269](https://github.com/BerriAI/litellm/issues/28269)] Codex cli jwt team alias by [@​mateo-berri](https://github.com/mateo-berri) in [#​28621](https://github.com/BerriAI/litellm/pull/28621)
- fix(check\_licenses): read PEP 639 license-expression metadata by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​28529](https://github.com/BerriAI/litellm/pull/28529)
- test(proxy): behavior-pinning matrix for tier-2/3 key + team management endpoints by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​28620](https://github.com/BerriAI/litellm/pull/28620)
- chore(test): remove dead old Playwright e2e suite by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​28632](https://github.com/BerriAI/litellm/pull/28632)
- fix(sagemaker): send native Cohere embed payload to Cohere SageMaker endpoints by [@​milan-berri](https://github.com/milan-berri) in [#​28613](https://github.com/BerriAI/litellm/pull/28613)
- style: apply black formatting to fix lint CI (LIT-3274) ([#​28639](https://github.com/BerriAI/litellm/issues/28639)) by [@​krrish-berri-2](https://github.com/krrish-berri-2) in [#​28641](https://github.com/BerriAI/litellm/pull/28641)
- fix(bedrock): decouple STS region from Bedrock aws\_region\_name by [@​milan-berri](https://github.com/milan-berri) in [#​28245](https://github.com/BerriAI/litellm/pull/28245)
- test(streaming): tolerate Vertex 429 wrapped in MidStreamFallbackError by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​28669](https://github.com/BerriAI/litellm/pull/28669)
- feat(guardrails): add Microsoft Purview DLP guardrail by [@​Sameerlite](https://github.com/Sameerlite) in [#​24966](https://github.com/BerriAI/litellm/pull/24966)
- fix(mcp): forward upstream initialize instructions on cold gateway init by [@​milan-berri](https://github.com/milan-berri) in [#​28231](https://github.com/BerriAI/litellm/pull/28231)
- chore(ci): promote internal staging to main by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​28680](https://github.com/BerriAI/litellm/pull/28680)
- CI: copy of [#​25177](https://github.com/BerriAI/litellm/issues/25177) (OCI GenAI: embeddings, streaming/reasoning fixes, model catalog) by [@​mateo-berri](https://github.com/mateo-berri) in [#​28223](https://github.com/BerriAI/litellm/pull/28223)
- Encrypt callback\_vars in key/team metadata in DB by [@​Michael-RZ-Berri](https://github.com/Michael-RZ-Berri) in [#​27141](https://github.com/BerriAI/litellm/pull/27141)
- perf: reduce per-request and per-chunk overhead across Anthropic streaming hot paths by [@​yassin-berriai](https://github.com/yassin-berriai) in [#​28289](https://github.com/BerriAI/litellm/pull/28289)
- feat(azure): add Speech STT config support by [@​ishaan-berri](https://github.com/ishaan-berri) in [#​27482](https://github.com/BerriAI/litellm/pull/27482)
- test(proxy): phase-4 payload behavior pinning for tier-2/3 key + team management endpoints by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​28681](https://github.com/BerriAI/litellm/pull/28681)
- feat(prometheus): emit per-token-type detail metrics (LIT-3220) ([#​28372](https://github.com/BerriAI/litellm/issues/28372)) by [@​ishaan-berri](https://github.com/ishaan-berri) in [#​28378](https://github.com/BerriAI/litellm/pull/28378)
- fix(otel): stamp http.response.status\_code on all error responses by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​28405](https://github.com/BerriAI/litellm/pull/28405)
- chore(ui): build ui by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​28707](https://github.com/BerriAI/litellm/pull/28707)
- fix(helm): drop main- prefix from default image tag by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​28710](https://github.com/BerriAI/litellm/pull/28710)
- test(model\_prices): allow audio\_transcription\_config in schema by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​28708](https://github.com/BerriAI/litellm/pull/28708)
- chore(ci): promote internal staging to main by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​28709](https://github.com/BerriAI/litellm/pull/28709)
- fix(team): refresh team cache on team\_model\_add/delete (LIT-3244) by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​28683](https://github.com/BerriAI/litellm/pull/28683)
- fix(ui/add-model): stop vertex\_ai-anthropic\_models from leaking into Anthropic dropdown by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​28723](https://github.com/BerriAI/litellm/pull/28723)
- Fix spend logs v2 route permissions by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​28705](https://github.com/BerriAI/litellm/pull/28705)
- fix(proxy): Bedrock Knowledge Base pass-through: preserve SigV4 headers and signed request body by [@​milan-berri](https://github.com/milan-berri) in [#​27526](https://github.com/BerriAI/litellm/pull/27526)
- chore(tests): migrate Bedrock CI to AWS account [`9412775`](https://github.com/BerriAI/litellm/commit/941277531214) by [@​mateo-berri](https://github.com/mateo-berri) in [#​28728](https://github.com/BerriAI/litellm/pull/28728)
- fix(otel): export SERVER span on management-endpoint success without http\_request by [@​yassin-berriai](https://github.com/yassin-berriai) in [#​28794](https://github.com/BerriAI/litellm/pull/28794)
- chore(ci): merge dev branch by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​28801](https://github.com/BerriAI/litellm/pull/28801)
- chore(ci): merge dev branch by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​28657](https://github.com/BerriAI/litellm/pull/28657)
- fix(ui): show 2-decimal precision for max\_budget on key overview by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​28809](https://github.com/BerriAI/litellm/pull/28809)
- feat(proxy): allow `llm_api_routes` virtual keys to list MCP servers by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​28442](https://github.com/BerriAI/litellm/pull/28442)
- chore(ci): merge dev branch by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​28807](https://github.com/BerriAI/litellm/pull/28807)
- fix(team): keep team\_alias cache in sync on \_cache\_team\_object writes by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​28737](https://github.com/BerriAI/litellm/pull/28737)
- chore(ci): merge dev branch by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​28822](https://github.com/BerriAI/litellm/pull/28822)
- ci: daily oss-agent-shin canonical branch by [@​ishaan-berri](https://github.com/ishaan-berri) in [#​28829](https://github.com/BerriAI/litellm/pull/28829)
- test(proxy): add harness for proxy\_server.py behavior-pinning by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​28827](https://github.com/BerriAI/litellm/pull/28827)
- feat(openai): apply regional-processing cost uplift for EU/US data residency by [@​mateo-berri](https://github.com/mateo-berri) in [#​28626](https://github.com/BerriAI/litellm/pull/28626)
- chore(admin-ui): regenerate static export with trailingSlash: true by [@​mateo-berri](https://github.com/mateo-berri) in [#​28112](https://github.com/BerriAI/litellm/pull/28112)
- fix(azure): preserve AD token refresh in v1 OpenAI client path by [@​mateo-berri](https://github.com/mateo-berri) in [#​28627](https://github.com/BerriAI/litellm/pull/28627)
- fix(ui): route API Reference back to query-param page by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​28726](https://github.com/BerriAI/litellm/pull/28726)
- fix(model-edit): allow clearing custom pricing on wildcard models by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​28719](https://github.com/BerriAI/litellm/pull/28719)
- fix(tests/vcr): make Redis cassette cache replay deterministically (zero VCR misses on consecutive runs) by [@​mateo-berri](https://github.com/mateo-berri) in [#​28826](https://github.com/BerriAI/litellm/pull/28826)
- fix(proxy): strip LiteLLM policy tracking from OpenAI batch metadata by [@​shivamrawat1](https://github.com/shivamrawat1) in [#​28425](https://github.com/BerriAI/litellm/pull/28425)
- Litellm OpenAI double prefix bug by [@​shivamrawat1](https://github.com/shivamrawat1) in [#​28661](https://github.com/BerriAI/litellm/pull/28661)
- Litellm oss staging 250526 by [@​Sameerlite](https://github.com/Sameerlite) in [#​28770](https://github.com/BerriAI/litellm/pull/28770)
- fix(bedrock): align toolUse/toolSpec names and allow hyphens by [@​Sameerlite](https://github.com/Sameerlite) in [#​28874](https://github.com/BerriAI/litellm/pull/28874)
- fix(realtime): send TEXT frames and valid guardrail session.update by [@​Sameerlite](https://github.com/Sameerlite) in [#​28848](https://github.com/BerriAI/litellm/pull/28848)
- fix(mcp): extend key access-group union to MCP servers by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​28890](https://github.com/BerriAI/litellm/pull/28890)
- fix(galileo): support hosted v2 spans API and string output extraction by [@​Sameerlite](https://github.com/Sameerlite) in [#​28771](https://github.com/BerriAI/litellm/pull/28771)
- fix(proxy): exclude proxy\_server\_request from its own body snapshot by [@​michelligabriele](https://github.com/michelligabriele) in [#​28618](https://github.com/BerriAI/litellm/pull/28618)
- \[Feat] Add tool calling support for gemini and vertex ai live api by [@​Sameerlite](https://github.com/Sameerlite) in [#​26590](https://github.com/BerriAI/litellm/pull/26590)
- refactor(ui): remove dead App Router scaffolding in (dashboard)/\* by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​28891](https://github.com/BerriAI/litellm/pull/28891)
- fix(docker): use system Node in componentized builders + retry apk add by [@​yassin-berriai](https://github.com/yassin-berriai) in [#​28888](https://github.com/BerriAI/litellm/pull/28888)
- docs(agents): require consent before writing new third-party names by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​28908](https://github.com/BerriAI/litellm/pull/28908)
- refactor(ui): extract auth state into AuthContext by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​28910](https://github.com/BerriAI/litellm/pull/28910)
- fix(mcp): resolve team.access\_group\_ids → MCP servers by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​28997](https://github.com/BerriAI/litellm/pull/28997)
- test(ui): e2e cover team model edit + admin identity in navbar by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​28652](https://github.com/BerriAI/litellm/pull/28652)
- test(e2e): cover add-fallback flow in Router Settings by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​29069](https://github.com/BerriAI/litellm/pull/29069)
- test(e2e): cover Team-BYOK add-model flow as proxy admin by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​29068](https://github.com/BerriAI/litellm/pull/29068)
- fix(containers): record ownership for service-account keys + fix Prisma Json serialization by [@​Sameerlite](https://github.com/Sameerlite) in [#​28990](https://github.com/BerriAI/litellm/pull/28990)
- test(e2e): cover add-MCP-server flow via discovery → custom form by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​29070](https://github.com/BerriAI/litellm/pull/29070)
- test(e2e): cover AI Hub make-public flow and public model\_hub\_table by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​29071](https://github.com/BerriAI/litellm/pull/29071)
- \[internal copy of [#​28877](https://github.com/BerriAI/litellm/issues/28877)] feat: add support for claude code goal mode for bedrock opus output config by [@​mateo-berri](https://github.com/mateo-berri) in [#​28898](https://github.com/BerriAI/litellm/pull/28898)
- feat(guardrails): wire apply\_guardrail into proxy logging callbacks by [@​Sameerlite](https://github.com/Sameerlite) in [#​28970](https://github.com/BerriAI/litellm/pull/28970)
- chore(ci): merge dev brach by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​29192](https://github.com/BerriAI/litellm/pull/29192)
- perf(streaming): cut per-chunk overhead \~30% on Anthropic + Bedrock hot path by [@​yassin-berriai](https://github.com/yassin-berriai) in [#​28720](https://github.com/BerriAI/litellm/pull/28720)
- fix(proxy): enforce tag budgets for key-level tags by [@​Sameerlite](https://github.com/Sameerlite) in [#​29108](https://github.com/BerriAI/litellm/pull/29108)
- fix(vertex-ai): use DB credentials in video handlers + implement Veo video edit by [@​Sameerlite](https://github.com/Sameerlite) in [#​29098](https://github.com/BerriAI/litellm/pull/29098)
- fix(datadog): drain cost-management queue + opt-in FinOps tag allowlist by [@​michelligabriele](https://github.com/michelligabriele) in [#​28487](https://github.com/BerriAI/litellm/pull/28487)
- feat(helm): split per-component ServiceAccounts for gateway, backend, and UI by [@​yassin-berriai](https://github.com/yassin-berriai) in [#​28712](https://github.com/BerriAI/litellm/pull/28712)
- chore(ci): bump deps ([#​29208](https://github.com/BerriAI/litellm/issues/29208)) by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​29226](https://github.com/BerriAI/litellm/pull/29226)
- fix(tests/vcr): mint Google OAuth tokens live to prevent stale-token replay by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​29229](https://github.com/BerriAI/litellm/pull/29229)
- chore(cookbook): bump Go directive to 1.26.3 in gollem example by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​29234](https://github.com/BerriAI/litellm/pull/29234)
- chore(ci): bump version by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​29242](https://github.com/BerriAI/litellm/pull/29242)
- feat(anthropic): add Claude Opus 4.8 and prune reasoning-effort flags by [@​mateo-berri](https://github.com/mateo-berri) in [#​29238](https://github.com/BerriAI/litellm/pull/29238)
- chore(ci): promote internal staging to main by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​29243](https://github.com/BerriAI/litellm/pull/29243)
- fix(ci): restore real Bedrock batch S3 bucket/role in oai\_misc\_config by [@​mateo-berri](https://github.com/mateo-berri) in [#​29245](https://github.com/BerriAI/litellm/pull/29245)
- fix(guardrails): persist disable\_global\_guardrails on keys by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​29233](https://github.com/BerriAI/litellm/pull/29233)
- test(e2e): cover Team Admin view + member + key flows by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​29072](https://github.com/BerriAI/litellm/pull/29072)
- docs: hand-written CLAUDE.md; remove AGENTS.md, point GEMINI.md at it by [@​mateo-berri](https://github.com/mateo-berri) in [#​29252](https://github.com/BerriAI/litellm/pull/29252)
- fix(teams): expose keys\_count on /v2/team/list and wire UI Resources badge by [@​michelligabriele](https://github.com/michelligabriele) in [#​28502](https://github.com/BerriAI/litellm/pull/28502)
- fix(anthropic): stop injecting unsupported output\_config.effort=xhigh for Claude Code on Sonnet/Opus 4.6 by [@​mateo-berri](https://github.com/mateo-berri) in [#​29304](https://github.com/BerriAI/litellm/pull/29304)
- test(e2e): cover Internal Viewer nav, key, and team-info gating by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​29075](https://github.com/BerriAI/litellm/pull/29075)
- test(e2e): cover Internal User key modal, team info, key page by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​29074](https://github.com/BerriAI/litellm/pull/29074)
- test(e2e): cover navbar Logout flow as proxy admin by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​29076](https://github.com/BerriAI/litellm/pull/29076)
- fix(mcp): resolve key.access\_group\_ids → MCP servers (ungated) by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​29195](https://github.com/BerriAI/litellm/pull/29195)
- fix(router): enforce deployment budgets for dynamically added models by [@​Sameerlite](https://github.com/Sameerlite) in [#​29273](https://github.com/BerriAI/litellm/pull/29273)
- fix(proxy): map stripped batch body.model to proxy alias for auth by [@​Sameerlite](https://github.com/Sameerlite) in [#​29264](https://github.com/BerriAI/litellm/pull/29264)
- feat(mcp): support stateless and stateful clients via session-id routing by [@​Sameerlite](https://github.com/Sameerlite) in [#​26857](https://github.com/BerriAI/litellm/pull/26857)
- fix(bedrock): support tool search results + chat annotations by [@​Sameerlite](https://github.com/Sameerlite) in [#​29120](https://github.com/BerriAI/litellm/pull/29120)
- fix(mcp): ignore stale ids on key save by [@​Sameerlite](https://github.com/Sameerlite) in [#​29128](https://github.com/BerriAI/litellm/pull/29128)
- feat(a2a): well-known agent-card discovery + LangGraph Platform mode by [@​Sameerlite](https://github.com/Sameerlite) in [#​28860](https://github.com/BerriAI/litellm/pull/28860)
- fix(proxy): link passthrough success spans to the SERVER root OTEL span by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​29315](https://github.com/BerriAI/litellm/pull/29315)
- \[internal copy of [#​29089](https://github.com/BerriAI/litellm/issues/29089)] fix: duplicate claude code traces by [@​mateo-berri](https://github.com/mateo-berri) in [#​29311](https://github.com/BerriAI/litellm/pull/29311)
- feat(otel): typed semconv-aligned OpenTelemetry instrumentation by [@​yassin-berriai](https://github.com/yassin-berriai) in [#​28909](https://github.com/BerriAI/litellm/pull/28909)
- tests(proxy\_server): surface current behavior in tests by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​29309](https://github.com/BerriAI/litellm/pull/29309)
- test(e2e): cover Internal User create-key flow when in no teams by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​29083](https://github.com/BerriAI/litellm/pull/29083)
- test(e2e): assert internal-user navbar identity is scoped to that user by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​29077](https://github.com/BerriAI/litellm/pull/29077)
- feat(otel): add team\_metadata, http.route, and model names to inference spans by [@​yassin-berriai](https://github.com/yassin-berriai) in [#​29319](https://github.com/BerriAI/litellm/pull/29319)
- feat(context\_management): compact\_20260112 polyfill for non-Anthropic providers by [@​Sameerlite](https://github.com/Sameerlite) in [#​28868](https://github.com/BerriAI/litellm/pull/28868)
- feat(enterprise): add RESEND\_FROM\_EMAIL for self-hosted Resend sends by [@​shivamrawat1](https://github.com/shivamrawat1) in [#​28830](https://github.com/BerriAI/litellm/pull/28830)
- Revert Bedrock CI back to the reactivated AWS account ([`8886022`](https://github.com/BerriAI/litellm/commit/888602223428)) by [@​mateo-berri](https://github.com/mateo-berri) in [#​29326](https://github.com/BerriAI/litellm/pull/29326)
- fix(mcp): preserve source\_url in GET /v1/mcp/server list responses by [@​shivamrawat1](https://github.com/shivamrawat1) in [#​29249](https://github.com/BerriAI/litellm/pull/29249)
- fix(mcp): preserve omitted fields on PUT /v1/mcp/server partial updates by [@​shivamrawat1](https://github.com/shivamrawat1) in [#​29253](https://github.com/BerriAI/litellm/pull/29253)
- fix(ci): make litellm\_internal\_staging green (logging test + Bedrock Opus 4.7 self-heal) by [@​mateo-berri](https://github.com/mateo-berri) in [#​29344](https://github.com/BerriAI/litellm/pull/29344)
- refactor(proxy/auth): normalize Bearer prefix in safe-hash helper by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​29343](https://github.com/BerriAI/litellm/pull/29343)
- test(reasoning-effort-grid): cover Claude Opus 4.8 across provider routes by [@​mateo-berri](https://github.com/mateo-berri) in [#​29327](https://github.com/BerriAI/litellm/pull/29327)
- fix(guardrails): return HTTP 400 for litellm content filter blocks by [@​shivamrawat1](https://github.com/shivamrawat1) in [#​28418](https://github.com/BerriAI/litellm/pull/28418)
- fix(proxy): restrict vector store index create/delete to proxy admins by [@​shivamrawat1](https://github.com/shivamrawat1) in [#​29202](https://github.com/BerriAI/litellm/pull/29202)
- feat(pass\_through): extend passthrough\_managed\_object\_ids to Azure by [@​Sameerlite](https://github.com/Sameerlite) in [#​29160](https://github.com/BerriAI/litellm/pull/29160)
- fix(proxy): enforce allowed\_passthrough\_routes for auth=true pass-thr… by [@​shivamrawat1](https://github.com/shivamrawat1) in [#​29256](https://github.com/BerriAI/litellm/pull/29256)
- feat(mcp/auth): additive key access-group grants + opt-in member assignment by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​29313](https://github.com/BerriAI/litellm/pull/29313)
- fix(reset\_budget): write only {spend, budget\_reset\_at} and stop pre-zeroing counter by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​29358](https://github.com/BerriAI/litellm/pull/29358)
- test(e2e): cover PROXY\_LOGOUT\_URL redirect on Logout by [@​ryan-crabbe-berri](https://github.com/ryan-crabbe-berri) in [#​29080](https://github.com/BerriAI/litellm/pull/29080)
- fix(ui): break logout redirect loop across dev and proxy origins by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​29360](https://github.com/BerriAI/litellm/pull/29360)
- fix(openai-moderation): wire streaming flags through to unified dispatcher by [@​michelligabriele](https://github.com/michelligabriele) in [#​27324](https://github.com/BerriAI/litellm/pull/27324)
- chore(ci): build ui by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​29366](https://github.com/BerriAI/litellm/pull/29366)
- fix(v3 limiter): cap no-max\_tokens TPM floor at smallest configured limit by [@​michelligabriele](https://github.com/michelligabriele) in [#​28805](https://github.com/BerriAI/litellm/pull/28805)
- fix(e2e): tolerate trailing slash in SERVER\_ROOT\_PATH login redirect by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​29369](https://github.com/BerriAI/litellm/pull/29369)
- chore(deps): bump deps by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​29373](https://github.com/BerriAI/litellm/pull/29373)
- chore(ci): promote internal staging to main by [@​yuneng-berri](https://github.com/yuneng-berri) in [#​29372](https://github.com/BerriAI/litellm/pull/29372)
- chore(release): patch v1.88.0-rc.1 with four staged fixes by [@​mateo-berri](https://github.com/mateo-berri) in [#​29632](https://github.com/BerriAI/litellm/pull/29632)
- chore(release): patch v1.88.0-rc.1 with [#​29612](https://github.com/BerriAI/litellm/issues/29612) (session-token budget-ceiling exemption) by [@​mateo-berri](https://github.com/mateo-berri) in [#​29637](https://github.com/BerriAI/litellm/pull/29637)
- fix(key\_generate): harden GHSA-q775 …
fzowl
pushed a commit
to fzowl/litellm
that referenced
this pull request
Jun 24, 2026
chore(ci): promote internal staging to main
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
9 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
Linear ticket
Pre-Submission checklist
Please complete all items before asking a LiteLLM maintainer to review your PR
tests/test_litellm/directory, Adding at least 1 test is a hard requirement - see detailsmake test-unit@greptileaiand received a Confidence Score of at least 4/5 before requesting a maintainer reviewDelays in PR merge?
If you're seeing a delay in your PR being merged, ping the LiteLLM Team on Slack (#pr-review).
CI (LiteLLM team)
Branch creation CI run
Link:
CI run for the last commit
Link:
Merge / cherry-pick CI run
Links:
Screenshots / Proof of Fix
Type
🆕 New Feature
🐛 Bug Fix
🧹 Refactoring
📖 Documentation
🚄 Infrastructure
✅ Test
Changes