fix(responses): route and translate managed code_interpreter container ids on /v1/responses - #30936
Closed
wasimat404 wants to merge 431 commits into
Closed
fix(responses): route and translate managed code_interpreter container ids on /v1/responses#30936wasimat404 wants to merge 431 commits into
wasimat404 wants to merge 431 commits into
Conversation
…_table (BerriAI#29684) In Pydantic v2, Optional[T] without a default is a required field. Any row with budget_id=null triggered a validation error and returned 401. Co-authored-by: Florent Chenebault <florent.chenebault@lifen.fr>
test_custom_tokenizer_bug.py loaded Xenova/llama-3-tokenizer from HuggingFace Hub at test time, so it flaked on shared CI runners whenever HF returned 429 Too Many Requests; the surfaced LocalEntryNotFoundError made it look like a connectivity bug. Rewrite the suite to mock the one network boundary (litellm.utils.Tokenizer.from_pretrained) while running the proxy's real extraction-and-selection path. The regression test now asserts the configured identifier from model_info.custom_tokenizer actually reaches from_pretrained and that the response reports the huggingface tokenizer, which the previous llama-3-named test could not distinguish from the default path. A control test pins the no-custom-tokenizer case to the OpenAI tokenizer with from_pretrained asserted unused. Verified by reintroducing the original bug (model_info left unpopulated from the deployment): the regression test fails (from_pretrained called 0 times) while the control stays green.
…erriAI#29700) * test(proxy): stop running real-DB tests in GitHub Actions unit jobs GitHub Actions unit jobs were spinning up a Postgres service container, but the only active tests that touched it either used the DB incidentally (a cargo-culted prisma_client.connect()) or were genuine integration tests mislabeled as unit. Mock the incidental ones so the proxy-db job needs no container, and move the tests that genuinely need a database (proxy management behavior, master-key-not-persisted, schema-migration sync) to CircleCI, which is already the real-infrastructure lane. * test(proxy): restore no-unexpected-startup-writes canary in master-key test Greptile noted the hash-match assertion no longer catches other unexpected startup writes (a default key, a rotation artifact). The CircleCI job gives each run a fresh DB, so a clean startup must leave the table empty; add that canary back alongside the precise master-key assertion.
* fix(ui): only flag bare fetch() outside React Query queryFn/mutationFn The frontend lint rule banned every fetch() call by static AST name match, so a fetch wrapped in a React Query queryFn/mutationFn tripped it just like a loose fetch in a component. esquery (no-restricted-syntax) can't express "has ancestor", so this replaces that selector with a small custom rule (local/no-bare-fetch) that exempts a fetch lexically inside a queryFn or mutationFn and reports everything else. Re-baselined eslint-suppressions.json under the new rule id (same 44 files / 331 violations) so existing code keeps its grandfathered suppressions. Adds a RuleTester suite covering wrapped (valid) vs unwrapped, the standalone *Api.ts function pattern, queryKey, and computed-key cases. * chore(ui): remove the bare-fetch lint rule Drop the fetch lint gate (and its 331 grandfathered suppressions) ahead of the networking refactor. The plan is to centralize all fetching in a single shared http client and enforce that with a location-based rule, so keeping a fetch rule in place now would only block CI while functions are routed through the new client. Removing it unblocks that work; the location-based rule lands with the client in a follow-up.
* restore an explicit no-match policy * fix(jwt): fix AUTO_REGISTER sentinel bypass, race condition, and inline import comment - AUTO_REGISTER now evicts stale __NO_MAPPING__ sentinel instead of silently returning None when cached under a prior fallback_team_mapping config - Race condition in _auto_register_jwt_mapping: catch P2002 unique-constraint violation on concurrent creates, fetch the winning mapping, proceed cleanly - Added comment on inline generate_key_helper_fn import explaining the circular dependency (key_management_endpoints imports user_api_key_auth at line 51) - 3 new tests: stale sentinel eviction, race condition winner fallback, and the existing auto_register happy path Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(jwt): cache __NO_MAPPING__ sentinel before raising 403 in REJECT mode REJECT mode was raising HTTPException immediately on a DB miss without writing the __NO_MAPPING__ sentinel, causing every subsequent rejected request to re-query the DB. Write the sentinel first so repeated rejections are served from cache within virtual_key_mapping_cache_ttl. Adds test asserting DB is not hit on the second reject after a cache-warm miss. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(jwt): enforce no-match policy when prisma_client is None The early `if prisma_client is None: return None` guard ran before the no-match policy check, silently bypassing REJECT and AUTO_REGISTER — every JWT client fell through to team auth regardless of configuration. Fix: treat prisma_client=None as a definitive DB miss and fall through to the same policy block as a real miss. REJECT now raises 403, AUTO_REGISTER raises 500 with a clear message (can't create keys without a DB), FALLBACK_TEAM_MAPPING returns None unchanged. Adds three tests: REJECT/403 with no DB, FALLBACK returns None with no DB, AUTO_REGISTER/500 with no DB. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(jwt): consistent AUTO_REGISTER on cached sentinel; clean up race orphans Addresses Greptile review on PR BerriAI#25570 cherry-pick. 1. Inconsistent AUTO_REGISTER when __NO_MAPPING__ sentinel is cached: The cached-sentinel branch silently returned None when prisma_client was None, while the fresh path raised HTTP 500 under the same config. Same request, different access-control outcome depending on cache state. Both paths now raise the same 500. 2. Orphaned virtual keys from race-condition losers: On unique-constraint conflict, generate_key_helper_fn had already persisted an unrestricted virtual key in LiteLLM_VerificationToken with the cleartext in request memory. Under sustained concurrency these accumulated indefinitely. The loser now deletes its orphan before falling back to the winner's mapping; failure to delete is logged but does not fail the request. Also corrects a latent FK bug surfaced while fixing BerriAI#2: the mapping row was storing the plaintext key in LiteLLM_JWTKeyMapping.token, but that column FKs to the hashed LiteLLM_VerificationToken.token — now hashed at the call site. Tests: - updated test_auto_register_creates_key_and_mapping to assert the hashed token is stored, not the plaintext - updated test_auto_register_race_condition_unique_conflict to assert the orphan is deleted with the correct hashed token - added test_auto_register_raises_500_when_sentinel_cached_and_no_db - added test_auto_register_race_conflict_tolerates_delete_failure Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(jwt): close REJECT bypass when JWT omits the configured claim field A JWT presented without the configured `virtual_key_claim_field` previously returned None at the `claim_value is None` guard before the `unregistered_jwt_client_behavior` check ran. A caller who knows the configured claim-field name could bypass REJECT by simply omitting that field and falling through to team-based JWT auth. Apply the no-match policy on a missing claim: - REJECT → 403 - AUTO_REGISTER → 403 (no stable identity to map; refuse rather than create a sentinel-keyed record) - FALLBACK_TEAM_MAPPING → return None (unchanged, backward-compatible) Adds three tests covering each branch of the missing-claim path. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(jwt): AUTO_REGISTER inherits team_id so keys are bounded by team limits Auto-registered virtual keys were created with no team, model, route, rate, or budget constraints — broader access than the standard team-based JWT auth path the same client would have taken. Under AUTO_REGISTER, resolve the team_id from the JWT (via the operator-configured team_id_jwt_field / team_id_default) and stamp it on the new key. Downstream auth then applies the team's budget/models/tpm/rpm/allowed_routes via the existing virtual-key flow. Policy when team_id_jwt_field is configured: - JWT carries team claim → stamp resolved team_id - JWT lacks claim + team_id_default set → stamp default - JWT lacks claim + no default → 403 (refuse to create an unbounded key) When neither team_id_jwt_field nor team_id_default is configured, the operator has explicitly opted out of team-based limits — the auto-created key has no team_id (matches what team-auth would do in the same config). Adds 4 tests covering each branch. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(jwt): make AUTO_REGISTER functional in prod; raise on missing winner Two correctness fixes flagged by Greptile on the AUTO_REGISTER path: 1. generate_key_helper_fn was called without table_name="key". Without that, the helper falls into the user-upsert branch (table_name in (None, "user")) and tries to insert into LiteLLM_UserTable with user_id=None, which hits the NOT NULL @id constraint. AUTO_REGISTER would never have succeeded in production. Now passes table_name="key" explicitly, matching the /key/generate caller. 2. When the race loser refetches the winner's mapping and gets None (winner row concurrently deleted), the previous code returned None — and the caller in _resolve_jwt_to_virtual_key then fell through to less- restrictive team-based JWT auth, silently bypassing the configured AUTO_REGISTER policy. Now raises HTTP 503 so the caller retries against a stable state rather than getting unintended fallback access. Adds one test for the 503 winner-vanishes path. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(jwt): defer AUTO_REGISTER until JWT policy is enforced by auth_builder Closes the JWT policy bypass on the AUTO_REGISTER path flagged by veria-ai. Before: when unregistered_jwt_client_behavior=auto_register and the JWT's claim was unmapped, _resolve_jwt_to_virtual_key validated the JWT signature and then immediately created a virtual key + mapping. JWTAuthManager.auth_builder never ran for the first request (the new key short-circuited the team-auth path), and every subsequent request hit the cached mapping — so custom_validate, RBAC, scope_mappings, and user_allowed_email_domain were never enforced for auto-registered clients. After: _resolve_jwt_to_virtual_key returns a _PendingAutoRegister signal instead of creating the key. The caller in _user_api_key_auth_builder runs JWTAuthManager.auth_builder, then — only on a validated, policy-passing result — calls _auto_register_jwt_mapping with the team_id / user_id from that result. The created key inherits team + user limits from the validated identity, and future cache hits load that already-policy-checked key. Also drops the interim _resolve_inherited_team_id helper that pulled team_id from raw JWT claims — same bypass risk; team_id now comes exclusively from auth_builder. Tests: - Rewrote two existing tests to assert _resolve_jwt_to_virtual_key returns _PendingAutoRegister (no key created yet) for both the fresh-DB-miss and stale-sentinel branches - Added a contract test that _auto_register_jwt_mapping stamps the validated team_id/user_id onto generate_key_helper_fn - Removed four stale team-binding tests that exercised the prior raw-claim helper Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * Update user_api_key_auth.py * fix(jwt): cache proxy-admin AUTO_REGISTER path to avoid repeated DB lookups Cache-miss regression introduced by the deferred-auto-register refactor: when a JWT under AUTO_REGISTER resolved to a proxy admin, the is_proxy_admin early-return in _user_api_key_auth_builder ran *before* the pending auto-register cache-write block. Result: no cache entry, so every subsequent proxy-admin request re-queried get_jwt_key_mapping_object indefinitely. Fix: write a __JWT_PROXY_ADMIN__ sentinel to user_api_key_cache before the early return when a pending auto-register existed. _resolve_jwt_to_virtual_key treats that sentinel as "skip mapping, fall through to auth_builder", so future requests from the same JWT identity hit the cache instead of the DB. auth_builder still runs full JWT policy on every request — only the mapping DB lookup is short-circuited. Adds one test asserting the sentinel cache-hit returns None without hitting prisma_client.db.litellm_jwtkeymapping.find_first. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(proxy): stamp org context on JWT auto-registered keys AUTO_REGISTER keys were created with team_id and user_id only, so org budget checks were skipped after switching to the key-scoped path. Co-authored-by: Cursor <cursoragent@cursor.com> --------- Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com> Co-authored-by: Cursor <cursoragent@cursor.com>
…erriAI#29723) * refactor(ui): add shared HTTP client and pin raw fetch() to one file Introduce src/lib/http/client.ts, a single typed wrapper that owns the only fetch() in the dashboard. It centralizes the base URL, the auth header, error parsing (deriveErrorMessage), non-2xx -> thrown ApiError, and JSON parsing, and is framework-agnostic (no React) so it can run from client and, later, server components. The base URL, auth header name and the logout side effect are injected through createApiClient. networking.tsx builds one configured apiClient and the 29 functions whose boilerplate maps exactly to the client's default behavior (canonical deriveErrorMessage + handleError + res.json() template) now call it instead of hand-rolling fetch. Names, signatures, return types and error behavior are unchanged; this is a pure refactor that drops ~440 lines. The no-restricted-syntax fetch rule now points at the client and a files: ["src/lib/http/**"] override makes that the only place fetch() is allowed. Re-baselined eslint-suppressions.json: networking.tsx fetch suppressions drop 270 -> 241; no other rule's counts change. The remaining networking.tsx fetches and the ~61 scattered component/hook fetches diverge from the default client behavior (text() error bodies, no res.ok check, no handleError side effect) and stay grandfathered for a follow-up burndown. * fix(ui): make the HTTP client tolerate non-JSON error bodies The non-2xx branch parsed the error body with response.json(), so a gateway returning HTML (502/503 from a reverse proxy) threw a SyntaxError before onError fired or ApiError was built, dropping the user-facing notification. This matched the old per-function behavior, but the client is now the single error path so it is the right place to harden. Read the body as text once, try JSON.parse for the existing deriveErrorMessage path, and fall back to the raw text (or the HTTP status) otherwise. The success path stays strict json() so return types are unchanged. * fix(ui): await the returned apiClient promise in 6 migrated functions The codemod rendered the `return response.json()` tail as `return apiClient.x()` without `await`. Inside the surrounding try/catch that returns an unawaited promise, so the catch never runs and its console.error log is dropped on failure; 4 of the 6 were `return await response.json()` originally, so this restores their exact behavior. Use `return await apiClient.x()` in all six. * refactor(ui): widen onError type and handle empty success bodies Address review notes on the shared client. Type onError as (message: string) => void | Promise<void> so the fire-and-forget async contract (networking passes the async handleError) is explicit rather than silently discarded by void. On the success path, read the body as text and return undefined for an empty body (e.g. a 204 No Content) instead of throwing a SyntaxError, while still parsing non-empty bodies strictly so a malformed JSON response surfaces rather than being masked. Add tests for the 204 case.
…AI#29731) * fix(proxy): stop team model name corruption on edit (BerriAI#28382) (BerriAI#29001) Team-scoped ("Team-BYOK") models store an internal routing key model_name_{team_id}_{uuid} in the model_name column and the user-facing name in model_info.team_public_model_name. The internal name leaked into /v1, /v2, and /model/info responses; the dashboard bound its edit form to it, so any non-rename save (e.g. a TPM tweak) PATCHed the internal name back. The update path then treated it as a rename, overwriting team_public_model_name and rewriting the team's models[] ACL with the mangled string -- breaking team key calls with team_model_access_denied. Two-layer fix: - Read path (root cause): add _translate_model_name_for_response and apply it in model_info_v2 and _get_proxy_model_info so /v1, /v2, and /model/info surface the public name for team-scoped rows. The DB column and router index keep the internal name as the routing key; this is a presentation-layer swap on a shallow copy (never mutates input). - Write path (defense in depth): harden _get_public_model_name so a value matching the internal shape, or a no-op against the current DB column, is never treated as a rename -- for both the top-level model_name and an explicit model_info.team_public_model_name. Tests: regression for the reported scenario, full branch coverage of _get_public_model_name, two internal-shape guard cases, an end-to-end PATCH through _update_team_model_in_db (asserts the team ACL is untouched), and four response-translation cases. 60 passed (model management), 181 passed (proxy server). * fix(ui): key Agent Builder agent selection on model_info.id (BerriAI#29729) * fix(ui): key Agent Builder agent selection on model_info.id Once team-scoped BYOK models can share a public name (the backend now returns the public name on /model/info instead of the internal routing key), selecting agents by model_name collides. Key selection, create, update and delete on the stable model_info.id instead, falling back to model_name only for config-defined agents that have no id. * fix(ui): add name-match fallback to post-create agent selection If the just-created agent's id is not yet present in the re-fetched list, try matching by name before falling back to the first agent. Addresses greptile review on BerriAI#29729. --------- Co-authored-by: tushar8408 <32977767+tushar8408@users.noreply.github.com>
… routing to on-premise models (BerriAI#29531) * feat(guardrails): add sensitive data routing to on-premise models When a guardrail detects sensitive data, route to an on-premise model instead of blocking or redacting. All subsequent requests in that session continue routing to the same model (sticky routing). New config options for guardrails: - on_sensitive_data: 'block' (default) or 'route' - sensitive_data_route_to_model: target model for rerouting - sticky_session_routing: persist routing for session (default: true) New exception SensitiveDataRouteException triggers rerouting when raised by guardrails. The proxy catches it, stores the routing decision in cache, and modifies the request's model field. New hook _PROXY_SensitiveDataRoutingHandler checks incoming requests against cached routing decisions and applies sticky routing. https://claude.ai/code/session_01SQd4isBa3UyouRoGVou9dK * fix: black formatting for custom_guardrail.py https://claude.ai/code/session_01SQd4isBa3UyouRoGVou9dK * test: improve test coverage for sensitive data routing feature Add additional tests for: - Cache key format and TTL constants - Session ID extraction from multiple locations - Custom guardrail initialization with routing config - Exception string representation and custom messages - Redis cache paths including fallback behavior - Edge cases in pre-call hook https://claude.ai/code/session_01SQd4isBa3UyouRoGVou9dK * fix: use correct GuardrailRaisedException parameters Replace invalid 'source' parameter with 'guardrail_name' to match the exception's actual signature. https://claude.ai/code/session_01SQd4isBa3UyouRoGVou9dK * test: move sensitive data routing tests to hooks directory Move test file to align with source code structure. https://claude.ai/code/session_01SQd4isBa3UyouRoGVou9dK * fix(guardrails): honor sticky_session_routing flag and scope session routing per API key Propagate sticky_session_routing through SensitiveDataRouteException so a guardrail configured with sticky_session_routing=False reroutes only the triggering request without persisting a session override. Scope the routing cache key to the requesting API key so sessions from different tenants cannot collide, and warn when sticky routing is requested but the hook is not registered. * refactor(guardrails): dedupe session-id extraction and drop redundant import Extract the shared session-id lookup into get_session_id_from_request_data so the sensitive-data routing hook and CustomGuardrail no longer keep two identical copies of the logic. Remove the redundant local import of GuardrailRaisedException in handle_sensitive_data_detection, and document that detection_info is surfaced in request metadata and logs so it must not carry raw sensitive values. * fix(guardrails): guard None user_api_key_dict in sensitive data route handler * fix(responses): send application/json Content-Type on responses DELETE OpenAI's responses DELETE endpoint now rejects requests that arrive without a Content-Type header, defaulting them to application/octet-stream and returning 'Unsupported content type: application/octet-stream'. The delete handler sent no body and therefore no Content-Type, so the request failed. Declare application/json on the delete request, matching the OpenAI SDK. * fix(guardrails): backfill in-memory cache after redis hit in sensitive data routing When _get_routed_model resolves a routing override from Redis it now also populates the local in-memory cache. Without the write-back, a non-writing instance that only ever reads from Redis would lose the sticky routing decision the moment Redis became unavailable, silently reverting sensitive sessions to the default model. * fix(guardrails): scope sticky sensitive-data routing to JWT principal Keyless auth (JWT and similar) has no api_key, so every such caller shared the "default" cache namespace. One authenticated user could reuse another user's session_id, trip the guardrail, and silently force the other user's subsequent requests onto the cached on-prem model for the TTL. Resolve the routing tenant from the api_key when present, otherwise from a stable principal built from the user/team/org identity, before reading or writing the session route. * fix(guardrails): require route target model when on_sensitive_data='route' * fix(guardrails): mark user_api_key_dict Optional in sensitive-data route handler * fix(guardrails): use remaining redis ttl for local backfill and str env default * fix(guardrails): graceful block when routing configured but no session_id handle_sensitive_data_detection promised to raise only SensitiveDataRouteException or GuardrailRaisedException, but when routing was configured and the request had no session_id it let a ValueError from raise_sensitive_data_route_exception propagate, surfacing as an HTTP 500 instead of a block. Fall back to a graceful block in that case so the documented contract holds. * fix(guardrails): run remaining guardrails after sensitive-data reroute Defer the SensitiveDataRouteException until every guardrail in the pre-call loop has run, so downstream security guardrails are no longer skipped when an earlier guardrail triggers routing. The first reroute wins and a later guardrail that blocks still propagates. Also normalize on_sensitive_data to lowercase like sibling on_* config fields so case-insensitive values are accepted. * fix(guardrails): classify sensitive-data reroute as guardrail intervention * fix(guardrails): record sensitive-data reroute as prometheus intervention not error * fix(guardrails): record service span for routing guardrail and move case-normalizer to base params Drop the early continue so a guardrail that signals sensitive-data routing still emits its PROXY_PRE_CALL service span like every other callback. Move the lowercase normalizer onto BaseLitellmParams so on_sensitive_data is normalized consistently when BaseLitellmParams is constructed directly, matching the cross-field route->model validator that already lives on the base.
…BerriAI#27707) * feat(proxy/hooks): add ProxyHTTPRateLimitError + provider resolver Introduces a small helper layer used by every proxy-side rate-limit hook so that the 429 they raise carries a populated llm_provider / model — instead of an empty exception.llm_provider that downstream loggers (Prometheus failure metric, observability callbacks) read as 'no provider attribution'. ProxyHTTPRateLimitError inherits from both fastapi.HTTPException (so the proxy server still renders it as a 429) and litellm.exceptions.RateLimitError (so isinstance checks and PrometheusLogger._get_exception_class_name pick up llm_provider). We deliberately don't call RateLimitError.__init__ — it constructs an httpx.Response we don't need and would just add failure surface; attribute parity is what downstream consumers care about. resolve_llm_provider_for_rate_limit() wraps litellm.get_llm_provider defensively. Internal limiter hooks fire from async_pre_call_hook — well before get_llm_provider runs anywhere else in the request lifecycle — so we have to call it ourselves at raise time. If the model is missing or unparseable (alias, router-only model) we fall back to llm_provider='litellm_proxy' rather than letting a second exception leak out and break the request path. Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com> * fix(proxy/hooks): populate llm_provider on parallel-request 429s Both v1 and v3 parallel-request limiters fired bare HTTPException(429) from inside async_pre_call_hook. The downstream Prometheus failure metric reads exception.llm_provider via _get_exception_class_name — the empty value showed up as exception_class='HTTPException' and left model_id='None' on the time series. Threads requested_model through every raise site in: * parallel_request_limiter.py: - check_key_in_limits (the per-key/per-model/per-user/per-team/ per-customer over-limit path) - raise_rate_limit_error (zero-limit + global_max_parallel_requests paths) — now takes an optional requested_model kwarg * parallel_request_limiter_v3.py: - _handle_rate_limit_error (the OVER_LIMIT translator), called from both the should_rate_limit pre-check and the TPM reservation path Resolved via resolve_llm_provider_for_rate_limit so unknown / missing models silently fall back to llm_provider='litellm_proxy' instead of breaking the request path with a second exception. Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com> * fix(proxy/hooks): populate llm_provider on dynamic-rate-limit 429s Same plumbing change as the parallel limiters, applied to both dynamic_rate_limiter (v1) and dynamic_rate_limiter_v3: * v1: TPM-zero and RPM-zero paths in async_pre_call_hook now resolve data['model'] -> (model, llm_provider) once and pass it into both raises. * v3: All three raise sites in _check_rate_limits — the model_saturation_check enforced raise, the priority_model enforced raise, and the fail-closed unknown-descriptor branch — now attribute the 429 to the actual provider. Falls back to llm_provider='litellm_proxy' when the model can't be resolved. Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com> * fix(proxy/hooks): populate llm_provider on batch-rate-limit 429s batch_rate_limiter._raise_rate_limit_error now takes a requested_model kwarg threaded from data['model'] in _check_and_increment_batch_counters. The batch-creation 429 is what gets raised when the input file's tokens/requests count would push the per-key TPM/RPM window over its limit. Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com> * fix(proxy/hooks): populate llm_provider on budget/iterations 429s Final batch of internal raise sites — the user/session-budget and max-iterations hooks. Same pattern: resolve data['model'] once at raise time, attach to ProxyHTTPRateLimitError so Prometheus and observability callbacks can attribute the 429. Hooks updated: * max_budget_limiter (per-user max_budget exceeded) * max_iterations_limiter (per-session agent iteration cap) * max_budget_per_session_limiter (per-session dollar cap) All three fall back to llm_provider='litellm_proxy' when data['model'] is missing or unparseable. Drops the now-unused HTTPException import from each module. Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com> * test(proxy/hooks): pin provider field on internal rate-limit 429s Regression coverage for the 'provider field missing' bug across every proxy-side rate-limit hook + the helper layer: * ProxyHTTPRateLimitError class shape (HTTPException + RateLimitError, dict-detail stringification, None-provider normalization). * resolve_llm_provider_for_rate_limit happy paths (gpt-4o-mini, anthropic/..., bedrock/...) plus all three fallback branches (None, '', unknown name) plus a 'get_llm_provider raises' case that asserts we swallow the secondary exception. * For each limiter (parallel v1/v3, dynamic v1/v3, batch, max_budget, max_iterations, max_budget_per_session): assert the raised exception is a RateLimitError carrying the resolved model + llm_provider, and a sibling test that asserts the fallback path returns 'litellm_proxy' without leaking a second exception. * Two PrometheusLogger._get_exception_class_name pins so the Prometheus failure metric label flips from 'HTTPException' to 'Openai.ProxyHTTPRateLimitError' (or 'Litellm_proxy.*' on fallback) — that's what dashboards consume. Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com> * perf(proxy/hooks): defer provider resolution to over-limit branches * fix: use error_message in raise_rate_limit_error to avoid literal 'None' in detail * Consolidate rate_limiter_utils imports in dynamic_rate_limiter * fix(proxy): set num_retries/max_retries on ProxyHTTPRateLimitError ProxyHTTPRateLimitError inherits from RateLimitError but did not call RateLimitError.__init__, so num_retries/max_retries were never set. When Starlette's HTTPException lacks __str__, MRO falls through to RateLimitError.__str__, which unconditionally reads these attributes and raises AttributeError during logging/traceback formatting. Initialize them to None defensively. * fix(mypy): silence base-class status_code conflict on ProxyHTTPRateLimitError HTTPException declares 'status_code: int' while openai.RateLimitError (via APIStatusError) declares 'status_code: Literal[429] = 429'. Mypy flags the multi-base override as [misc] in CI lint. The runtime semantics are fine (we set self.status_code in __init__), so silence the class-level annotation conflict with a targeted ignore. Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com> --------- Co-authored-by: Cursor Agent <cursoragent@cursor.com> Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com>
…ta for codex compatibility (BerriAI#29489) * fix(vertex/anthropic): handle namespace tools and strip client_metadata for codex compatibility * fix(anthropic): cast nested namespace tools to fix mypy error, skip nameless flat tools
* Add OAuth M2M support for A2A agents targeting Databricks Apps Databricks App endpoints reject static bearer tokens and require a short-lived OAuth token minted via the workspace OIDC token endpoint. A2A agents could previously only authenticate outbound with static_headers or client header passthrough, so Databricks App agents could not be registered. Agents configured with a databricks_oauth block in litellm_params now mint and cache a client_credentials token and attach it as the outbound Authorization header on both message/send and message/stream calls, overriding any statically configured Authorization. * Add tests covering Databricks App OAuth token error paths Cover the HTTP status error, transport error, non-object JSON body, and invalid expires_in fallback branches in the token cache so the failure handling is locked in by regression tests. * Harden Databricks App OAuth token cache Cap the cache TTL at the token's own lifetime so a token whose validity is shorter than the refresh buffer is never cached and served stale; include a digest of client_secret in the cache key so a rotated secret mints a fresh token instead of reusing the old one; and prune the per-key lock when its cached token is evicted so the lock map stays bounded by the live key set. * Clear per-key locks on Databricks OAuth cache flush * fix(a2a/databricks): mint OAuth token via Basic auth header, not unsupported auth= kwarg litellm's AsyncHTTPHandler.post (what get_async_httpx_client returns) has no auth parameter, so minting a Databricks App OAuth token raised "AsyncHTTPHandler.post() got an unexpected keyword argument 'auth'" before any network call ever left the proxy, breaking the feature end to end. The handler also calls raise_for_status() internally and re-raises a MaskedHTTPStatusError (a subclass of httpx.HTTPStatusError), so the explicit raise_for_status() after post() was dead code. Build the HTTP Basic Authorization header by hand and pass it via headers, which is what the Databricks workspace OIDC token endpoint documents for client authentication. The token-cache tests now model the real handler contract with create_autospec so the rejected auth= signature is enforced; the previous mocks accepted any kwargs and silently hid the bug. Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com> * Prune Databricks OAuth lock on the short-lived-token path When expires_in is below the refresh buffer the token is intentionally not cached, so _remove_key never runs for that key and the per-key lock created by _get_lock leaked permanently. Drop the lock in that branch so _locks stays bounded by the live key set, and assert the cleanup in the short-lived-token test * Gate A2A Databricks OAuth on the databricks_oauth block at the call site Make the gating explicit where the header is applied so it is clear that only agents configured with a databricks_oauth block enter the OAuth path; every other agent is left untouched. Add a regression test asserting a non-Databricks agent never invokes the token resolver. --------- Co-authored-by: Cursor Agent <cursoragent@cursor.com> Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com>
…iAI#29702) * fix(anthropic): route Claude Opus 4.8 through adaptive thinking Opus 4.8 uses the same adaptive thinking contract as 4.6/4.7 (thinking.type=adaptive plus output_config.effort), but _is_adaptive_thinking_model only recognized 4.6/4.7 by name and otherwise leaned on the supports_adaptive_thinking cost-map flag. The Bedrock, Vertex, and Azure 4.8 entries don't carry that flag, so a bedrock/us.anthropic.claude-opus-4-8 request fell back to the legacy thinking.type=enabled shape and Bedrock rejected it with "thinking.type.enabled is not supported for this model". Add _is_claude_4_8_model and wire it in next to the existing 4.6/4.7 matchers in the adaptive-thinking detection, the effort=max gate, and the supported-params check, so every provider path treats 4.8 as adaptive regardless of whether its cost-map entry advertises the flag. * refactor(anthropic): drive Opus 4.8 adaptive thinking from the cost map Replace the _is_claude_4_8_model name matcher with cost-map data. Add supports_adaptive_thinking to every Opus 4.8 provider variant (Bedrock regional/global, Vertex, Azure) in both the root and bundled cost maps, and move the prefix-resolving capability lookup (_supports_model_capability) down to AnthropicModelInfo so _is_adaptive_thinking_model reads the flag through the bedrock/invoke/, bedrock/, and vertex_ai/ prefixes. The 4.6/4.7 name checks stay as a fallback since their provider entries don't carry the flag yet. A pure data fix is not enough on its own: _supports_factory doesn't strip the us.anthropic./invoke/ prefixes, so bedrock/invoke/us.anthropic.claude-opus-4-8 would still miss the flag without the resolver change. Add a cost-map guardrail test asserting every claude-opus-4-8 variant carries the flag, so a future variant added without it fails CI instead of silently sending the legacy thinking.type=enabled shape that the provider rejects.
…ken Cost Tracking (BerriAI#29722) * Normalize Realtime usage dict keys before ResponseAPIUsage transform * Test usage transform for Realtime versus tokens_details keys * Avoid usage_input dict in-place * Fix audio cost calculation * fix(responses): forward output audio_tokens into completion usage details Pass audio_tokens from output_tokens_details into CompletionTokensDetailsWrapper so cost can use output_cost_per_audio_token. Support dict output details like prompt path. Extend tests for Realtime and mixed completion audio. Co-authored-by: Cursor <cursoragent@cursor.com> * Fix audio token usage formatting * style: Black-format Realtime usage and completion usage merge Resolve combine_usage_objects and responses/utils wrapping for CI black --check. Restore model_fields comments above completion_tokens_details merge loop. Co-authored-by: Cursor <cursoragent@cursor.com> * Add test to cover combined usage objects * Fix merge conflict with test cases Removed unnecessary import statement and cleaned up assertions in test. * fix(cost_calculator): remove dead None guard in completion_tokens_details combiner --------- Co-authored-by: Liam McDonald <lmcdonald@godaddy.com> Co-authored-by: Cursor <cursoragent@cursor.com>
…riAI#29651) * fix(galileo): use ingest traces API and standard logging payload Switch hosted Galileo logging to /ingest/traces with nested trace/span payloads, read metrics from standard_logging_object, and include cost and total tokens on trace metrics. Co-authored-by: Cursor <cursoragent@cursor.com> * fix(galileo): route username/password auth to v2 traces ingest Hosted Galileo no longer serves /observe/ingest; JWT login should post the same trace payload to /v2/projects/{project_id}/traces. Co-authored-by: Cursor <cursoragent@cursor.com> * fix(galileo): address Greptile review on logging and timestamps Use debug-level logs for per-request Galileo callback messages and fall back to start_time/end_time when standard_logging_object omits startTime/endTime. Co-authored-by: Cursor <cursoragent@cursor.com> * feat(galileo): add Galileo to proxy UI callback configuration Expose Galileo in the admin callback selector and config APIs so credentials can be configured through the dashboard instead of YAML only. Co-authored-by: Cursor <cursoragent@cursor.com> * fix(galileo): align response type logging with Langfuse Mirror Langfuse input/output handling for rerank, speech, transcription, realtime, pass-through, and other response types so Galileo ingest no longer skips supported call types. Co-authored-by: Cursor <cursoragent@cursor.com> * fix(galileo): redact trace payload in debug logs and format with black Avoid logging prompts and model responses in flush debug output while keeping structural metadata for troubleshooting. Co-authored-by: Cursor <cursoragent@cursor.com> * fix(galileo): stop logging full trace payload in debug output Log only flush URL and trace count so prompts and model responses are not written to application logs when debug logging is enabled. Co-authored-by: Cursor <cursoragent@cursor.com> * Fix Galileo token totals and prompt messages --------- Co-authored-by: Cursor <cursoragent@cursor.com>
…batch validation (BerriAI#29746) * fix(auth): expand all-team-models sentinel in can_key_call_model Keys with models=["all-team-models"] were denied during batch JSONL model validation because can_key_call_model matched the literal string against the model name. Add _resolve_key_models_for_auth_check to expand the sentinel to team_models before the check, consistent with get_key_models in model_checks.py and the completion-route bypass. Co-authored-by: Cursor <cursoragent@cursor.com> * docs(auth): document empty team_models unrestricted access behavior; add regression test Adds a docstring note to _resolve_key_models_for_auth_check explaining that when team_models is empty, all-team-models resolves to [] which is treated as unrestricted access (consistent with get_key_models behavior on other auth paths). Adds a test to lock in this behavior. * fix(auth): deny all-team-models access when key has no team_id A key configured with models=["all-team-models"] but no team_id could previously resolve to an empty allowlist, which _check_model_access_helper treats as unrestricted access. Now the sentinel is only expanded when team_id is set; otherwise the unresolved sentinel stays in the model list and causes a deny (no real model name matches it). Same fix applied to get_key_models in model_checks.py for consistency across batch and non-batch auth paths. * style: black format model_checks.py * Fix batch all-team-models auth * style: black format batch_rate_limiter.py * fix(test): add tool_use_system_prompt_tokens to model prices schema validator * fix(batch): catch get_team_object errors to avoid 404 escaping batch auth * fix(batch): apply per-member model scope check after team auth in batch validation * Fail closed on batch team auth fetch errors * test(batch): cover team_object grant and member-scope denial in batch auth --------- Co-authored-by: Cursor <cursoragent@cursor.com> Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
…ter 24h (BerriAI#29784) The Redis cassette persister slid the 24h TTL forward on every successful read, so any cassette replayed at least once per day never expired. With CI running more than once a day that means a recorded response is replayed forever and the suite never re-hits the provider, so a changed request or response contract goes undetected indefinitely. Drop the refresh-on-read. The TTL now counts down from the last write, so a cassette lapses 24h after it was recorded and the next run past that point re-records live and catches provider drift. Per-commit runs in between still replay from cache; only the one boundary-crossing run goes live.
…e-bound (BerriAI#29787) * test(ci): record/replay OpenAI image gen so the spend E2E isn't outage-bound The dockerized spend test test_key_info_spend_values_image_generation curls the proxy for a gpt-image-1 image, which wildcard-routes to real api.openai.com on every commit; an OpenAI outage then reddens unrelated PRs and each run pays for an image. Add an in-repo record/replay reverse proxy (tests/_openai_record_replay_proxy.py) that sits between the proxy and OpenAI. The first run, and the first after the recording lapses, records live; subsequent runs replay from the shared Redis cassette store. The proxy keeps its real separate-process HTTP topology; only the image model's api_base is pointed at the recorder in CI via IMAGE_GEN_RECORDER_BASE_URL, which is unset elsewhere so it falls back to api.openai.com. Recordings lapse 24h after write and are never refreshed on read, matching the VCR persister contract, so provider drift is still caught. Replayed responses drop upstream framing/server headers (content-length, transfer-encoding, content-encoding, date, server) so the re-serving layer recomputes them, honoring the Bedrock content-length lesson. * test(ci): close recorder http client on app shutdown Add a Starlette lifespan that closes the self-created httpx.AsyncClient on teardown, and leave caller-injected clients untouched so reuse across create_app calls is not broken. Covers the unclosed-client ResourceWarning raised in review.
BerriAI#29714) Interactive PKCE and OBO servers were mislabeled as M2M, so passthrough never showed the Authorize gate; classify by oauth2_flow + delegate_auth_to_upstream instead.
…er (BerriAI#29793) * refactor(ui): centralize proxy base URL resolution into tested resolver The API base URL join logic was hand-rolled inside networking.tsx and re-derived inline at hundreds of call sites, with no test coverage and a latent double-slash bug when the base carried a trailing slash. This pulls the join into a single pure resolveApiBase() with full unit coverage and routes the existing resolution through it, also de-duplicating the env precedence ladder that was copied in two places. * test(ui): assert root-path redirect joins prefix exactly once The existing toContain check accepts a doubled separator; tighten it to a strict prefix match plus a no-double-slash assertion so a regression in the resolveApiBase origin+SERVER_ROOT_PATH join is caught end-to-end.
* Mark xAI models retiring on 2026-05-15 (BerriAI#28788) Per https://docs.x.ai/developers/migration/may-15-retirement, xAI is retiring the following slugs on 2026-05-15 (auto-redirect to grok-4.3 with various reasoning efforts; callers continuing to use the old slugs will be billed at grok-4.3 pricing): grok-4-1-fast-reasoning{,-latest} -> grok-4.3 (low effort) grok-4-1-fast-non-reasoning{,-latest} -> grok-4.3 (none) grok-4-fast-reasoning -> grok-4.3 (low effort) grok-4-fast-non-reasoning -> grok-4.3 (none) grok-4-0709 -> grok-4.3 (low effort) grok-code-fast-1{,-0825} -> grok-build-0.1 grok-3 -> grok-4.3 (none) Only the direct xai/ slugs are tagged; third-party hosts (azure_ai, oci, vercel_ai_gateway, perplexity/xai) run their own schedules. The grok-3 retirement list explicitly names only the base grok-3 slug — the -mini / -fast / -beta / -latest variants are not listed, so they remain untouched. * feat(moonshot): advertise json_schema response support on live models (BerriAI#29683) litellm.responses() already routes Moonshot through the responses->chat-completions bridge, and Moonshot honors response_format json_schema on chat completions. The cost-map entries left supports_response_schema unset, so discovery layers that gate on that flag dropped Moonshot from structured-output / responses listings even though the capability works end to end. Set supports_response_schema on the nine models currently live on api.moonshot.ai: kimi-k2.5, kimi-k2.6, the moonshot-v1 8k/32k/128k text and vision-preview variants, and moonshot-v1-auto. Verified against the live API that each honors json_schema and that litellm.responses() returns schema-valid structured output through the bridge. * chore(moonshot): mark models retired from api.moonshot.ai as deprecated (BerriAI#29685) Thirteen Moonshot/Kimi models in the cost map no longer resolve on api.moonshot.ai (all return 404). Stamp each with its deprecation_date from platform.kimi.ai/docs/models rather than deleting the entries, so historical cost calculation keeps resolving the names while tooling can surface the retirement. Dates: kimi-thinking-preview 2025-11-11; kimi-latest and its 8k/32k/128k context variants 2026-01-28; the kimi-k2 preview/turbo/thinking series 2026-05-25; the moonshot-v1 -0430 snapshots use their own 2024-04-30 snapshot date (Moonshot publishes no discontinuation date for them). * fix(moonshot): drop temperature for reasoning models (kimi-k2.5/k2.6) (BerriAI#29687) Kimi reasoning models reject every temperature except 1; a request with temperature=0.2 returns "invalid temperature: only 1 is allowed for this model". litellm only clamped temperature into [0.3, 1], so any value below 1 still 400'd. Drop the temperature param entirely for reasoning models (gated on supports_reasoning, the same signal transform_request already uses) so the model default is used; the non-reasoning moonshot-v1 models keep the existing clamp. Co-authored-by: Sameer Kankute <sameer@berri.ai> * feat(mcp): add per-server timeout configuration (BerriAI#29672) * feat(mcp): add per-server timeout configuration * fix(mcp): address timeout field review comments - use is not None guard instead of or for 0.0 edge case - copy timeout in both LiteLLM_MCPServerTable constructions (health check path + _build_mcp_server_table) - add timeout Float? column to all three schema.prisma files - extend round-trip test to cover _build_mcp_server_table direction - add test for zero timeout not treated as falsy * fix(mcp): forward timeout in _build_temporary_mcp_server_record * fix(mcp): return 504 instead of 500 when per-server timeout fires * test(mcp): add 504 timeout regression test; fix black formatting * Add jp. Bedrock cross-region inference profile for claude-opus-4-7 (BerriAI#28567) * fix(thinking): handle None thinking param in is_thinking_enabled (BerriAI#28598) Squash-merged by litellm-agent from Terrajlz's PR. * feat(helm): support tpl rendering in podAnnotations (BerriAI#28609) Squash-merged by litellm-agent from devauxbr's PR. * Forward custom_llm_provider through the Responses API bridge (Fixes BerriAI#28505) (BerriAI#28575) * Forward custom_llm_provider through the Responses API bridge (Fixes BerriAI#28505) When a Chat Completions request to a GPT-5.4+ model contains both `tools` and `reasoning_effort`, `completion()` auto-routes through `responses_api_bridge`. The bridge handler called `litellm.responses()` / `litellm.aresponses()` without forwarding the already-resolved `custom_llm_provider`, so the downstream call re-invoked `get_llm_provider()` with `custom_llm_provider=None` and stripped a second provider prefix from a `provider/provider/model` deployment string. For a deployment configured as `openai/openai/openai/gpt-5.5`, the bridge flow sent `openai/gpt-5.5` to the upstream API instead of the correct `openai/openai/gpt-5.5`. Upstream APIs that enforce model-name allow-lists rejected this as `key_model_access_denied`. Fix: pass the locally-resolved `custom_llm_provider` into both the sync `responses()` and async `aresponses()` calls so the downstream `_resolve_model_provider_for_responses` sees an explicit provider and skips the second prefix-strip. New regression test `tests/test_litellm/completion_extras/test_responses_bridge_provider_propagation.py` pins both call sites: each must forward `custom_llm_provider`. * fix(28505): set custom_llm_provider on request_data instead of as duplicate kwarg Greptile flagged that the previous patch passed custom_llm_provider as an explicit kwarg to responses()/aresponses() while request_data already carried it via the spread of sanitized_litellm_params, which would raise TypeError: got multiple values for keyword argument on every real bridge call. Switches to assigning request_data['custom_llm_provider'] before the call so the resolved provider wins over whatever sanitized_litellm_params spread in, without duplicating the kwarg. Updates the regression test to seed request_data with a sentinel custom_llm_provider so it actually exercises the overwrite path (the previous test mocked transform_request with a minimal dict and never hit the conflict). * chore: trigger shin-agent re-eval on retargeted staging base * chore: trigger shin-agent re-eval against updated Greptile state * Add jp. Bedrock cross-region inference profile for claude-opus-4-7 AWS Bedrock documents jp.anthropic.claude-opus-4-7 alongside the existing us./eu./au./global. profiles for Claude Opus 4.7 (ap-northeast-1 Tokyo / ap-northeast-3 Osaka), but the entry is missing from model_prices_and_context_window.json. Tokyo-region users currently get an "unknown model" error when routing through the JP geo profile. Adds the entry to both the canonical file and the bundled backup, mirroring the recent pattern for sonnet-4-6 (BerriAI#27831). Pricing matches the other regional profiles (10% premium over base/global). Regression test pins all six documented profiles (base, global, us, eu, au, jp) and asserts pricing parity between jp. and au. variants. Source: https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-opus-4-7.html --------- Co-authored-by: Terrajlz <info@jouleselectrictech.com> Co-authored-by: Bruno Devaux <devaux.br@gmail.com> Co-authored-by: Sameer Kankute <sameer@berri.ai> * feat(soniox): add soniox audio transcription integration (BerriAI#29508) * feat(openmeter): add OPENMETER_TRUST_REQUEST_USER to prevent forged attribution (BerriAI#29650) The OpenMeter callback resolves the CloudEvent subject from kwargs["user"] first, then falls back to the key-bound user_api_key_user_id. For multi-tenant proxy deployments, a client can set `"user": "..."` in the request body and cause their usage to be attributed to that arbitrary string — a billing-attribution forgery risk. Adds OPENMETER_TRUST_REQUEST_USER env var (default "true" for backward compatibility). When set to "false", the request-supplied `user` field is ignored and the subject is resolved solely from user_api_key_user_id. Matches the existing env-var-driven config pattern in this file (OPENMETER_API_KEY, OPENMETER_API_ENDPOINT, OPENMETER_EVENT_TYPE). * feat(search): add you_com as a search provider (BerriAI#28370) * feat(search): add you_com as a search provider Registers You.com Search API as a first-class `search_provider` in the `search_tools` registry, alongside Tavily, Exa, Perplexity, etc. - New adapter: litellm/llms/you_com/search/transformation.py - POSTs to https://ydc-index.io/v1/search - Auth: X-API-Key from YOUCOM_API_KEY (or explicit api_key) - Maps Perplexity unified spec: max_results -> count, search_domain_filter -> include_domains, country -> country - Flattens results.web + results.news into a single SearchResult list; snippet prefers snippets[0], falls back to description; page_age -> date - Registry: SearchProviders.YOU_COM in litellm/types/utils.py and wired into ProviderConfigManager.get_provider_search_config() - Pricing entry: model_prices_and_context_window.json (placeholder $0.0; happy to adjust to maintainers' preferred public number) - Docs: example router config snippet and example proxy yaml updated - Tests: tests/search_tests/test_you_com_search.py - 5 mocked tests (payload shape, domain filter mapping, snippet fallback, news flattening, missing-api-key error) Refs upstream expansion signal: BerriAI#15942 * review fixups: normalize api_base, lowercase country, scope env-var to test Addresses Greptile inline review comments on BerriAI#28370: - get_complete_url: strip trailing slashes from api_base *before* the endswith("/v1/search") check, so a custom base like ".../v1/search/" doesn't become ".../v1/search/v1/search". - transform_search_request: .lower() country before sending, matching Tavily's convention so callers using the unified spec form ("US") get consistent behavior across providers. - Tests: replace direct os.environ writes with an autouse monkeypatch fixture so YOUCOM_API_KEY is set per-test and removed afterwards. The missing-key test now uses monkeypatch.delenv. New test asserts the trailing-slash normalization above. Reverts the ARCHITECTURE.md / example yaml edits per the reviewer note that documentation changes belong in the litellm-docs repo. * support keyless free tier (api.you.com/v1/agents/search) as default You.com offers an IP-throttled keyless endpoint that returns the same response shape as the keyed one (~100 queries/day, no signup). This is a significant onboarding lever - mirrors the keyless DuckDuckGo/SearXNG providers already in the search_tools registry. Behavior: - YOUCOM_API_KEY set -> keyed: POST https://ydc-index.io/v1/search (X-API-Key header) - no key -> free: POST https://api.you.com/v1/agents/search (no auth) - YOUCOM_API_BASE override -> honored as-is Tests: - New: test_you_com_search_keyless_free_tier - asserts URL + absence of X-API-Key when no key is configured. - New: test_you_com_search_validate_environment_keyless - asserts the config no longer raises when the key is absent. - Removed: test_you_com_search_raises_without_api_key (the precondition no longer holds). - Existing payload/domain-filter/etc tests still cover keyed mode via the autouse YOUCOM_API_KEY fixture. Verified both endpoints accept POST + return identical JSON shape: results.web[] / results.news[] with title, url, snippets, description, page_age. * register you_com in provider_endpoints_support.json Adding `litellm/llms/you_com/` requires a corresponding entry in provider_endpoints_support.json or the code-quality/check_provider_folders_documented CI check fails. Follows the compact tavily/serper pattern - endpoints: { search: true }. Local run of the check now reports "All 114 provider folders are documented". * move tests under tests/test_litellm/llms/ so CI exercises them The litellm CI workflows scope unit tests to `tests/test_litellm/...` (see test-unit-llm-providers.yml: `tests/test_litellm/llms` path), so tests living under `tests/search_tests/` are never run in CI - which is why codecov reports 0% patch coverage for the new adapter even though the unit tests exist and pass locally. Move test_you_com_search.py into `tests/test_litellm/llms/you_com/` so the test-unit-llm-providers job picks it up. 7/7 tests still pass at the new location. (Sibling search-only providers - tavily, exa_ai, brave, etc. - still live only in `tests/search_tests/` and would benefit from the same move, but that is out of scope for this PR.) * fix(you_com): pin Accept-Encoding: identity to dodge keyless gzip bug The keyless free-tier endpoint (api.you.com/v1/agents/search) advertises Content-Encoding: gzip but returns a body that httpx's decoder rejects with `zlib.error: Error -3 while decompressing data: incorrect header check`, surfacing as litellm.APIConnectionError in user code. curl works because it doesn't request compression by default. Pin Accept-Encoding: identity in validate_environment so the upstream server skips compression entirely. Harmless on the keyed endpoint (ydc-index.io/v1/search) which negotiates content-encoding correctly. The header uses setdefault so a caller-supplied Accept-Encoding still takes precedence. (Server-side bug has been flagged to the You.com team separately - once fixed there, this workaround can be removed.) New unit test: test_you_com_search_pins_identity_accept_encoding. --------- Co-authored-by: Sameer Kankute <sameer@berri.ai> * docs: fix README typo (BerriAI#29419) Correct clear spelling mistakes in documentation without changing behavior. Confidence: high Scope-risk: narrow Tested: git diff --check; uvx codespell on changed files Not-tested: Full docs build not run; text-only changes * Fix(langfuse): pass httpx_client to Langfuse in langfuse_prompt_management to respect SSL_VERIFY (BerriAI#29480) * fix(langfuse): pass ssl_verify to Langfuse httpx client * fix_langfuse_ * add unit tests * addressed comments --------- Co-authored-by: shin-berri <shin-laptop@berri.ai> Co-authored-by: yuneng-jiang <yuneng@berri.ai> * feat(models): add minimax/MiniMax-M3 to model cost map (BerriAI#29412) Add MiniMax's new flagship MiniMax-M3 to the native minimax provider: 512K context, 128K max output, native multimodal (supports_vision), reasoning, prompt caching. Pricing (USD/M tokens): input 0.6 / output 2.4 / cache read 0.12. M3 has no active prompt-cache-write tier, so cache_creation_input_token_cost is omitted. Updated both the root model_prices_and_context_window.json (remote source) and the bundled litellm/model_prices_and_context_window_backup.json (local fallback), keeping them in sync. * fix(logging): handle ResponseCompletedEvent in anthropic_messages streaming spend log (BerriAI#29394) * fix(logging): handle ResponseCompletedEvent in anthropic_messages streaming spend log * fix(logging): extend terminal event handling to ResponseIncompleteEvent and ResponseFailedEvent; fix return type annotation * feat(provider): Add Neosantara provider as OpenAI Compatible (BerriAI#29646) * Add Neosantara provider * Register Neosantara provider enum * Address Neosantara provider review feedback * Add Neosantara packaged endpoint support --------- Co-authored-by: shin-berri <shin-laptop@berri.ai> Co-authored-by: yuneng-jiang <yuneng@berri.ai> * fix: address greptile and veria review feedback - langfuse: guard httpx_client injection behind version check (>= 2.7.3) - soniox: propagate audio_transcription_duration in _hidden_params for spend tracking - soniox: give SONIOX_API_BASE env var priority over caller-supplied api_base - mcp: replace CancelledError catch with asyncio.wait_for + TimeoutError * chore(mcp): add migration for per-server timeout column * fix(test): add tool_use_system_prompt_tokens to model prices schema validator * fix: mcp timeout test uses real asyncio.wait_for timeout; you_com get_complete_url respects resolved api_key * fix: forward resolved api_key into you_com endpoint selection and apply timeout to soniox polling GETs The search flow resolves api_key in validate_environment but never passed it into get_complete_url, so a programmatic api_key (with no YOUCOM_API_KEY in the env) set the X-API-Key header yet still selected the keyless free-tier endpoint. Forward api_key through both the search entrypoint and the http handler so the keyed endpoint is chosen. HTTPHandler.get/AsyncHTTPHandler.get had no timeout parameter, so the Soniox poll and transcript-fetch GETs silently used the client global default instead of the caller timeout. Add a per-request timeout to get() and forward the configured timeout from the Soniox handler. * fix(soniox): price stt-async-v4 per second so transcriptions are billed The handler stores audio_transcription_duration in _hidden_params, but the model carried only token cost fields and the response has no token usage, so the transcription cost path fell through to cost_per_second and returned $0. An authenticated caller could transcribe Soniox audio without decrementing their budget. Switch the entry to output_cost_per_second at Soniox's published $0.10/hour async rate so the stored duration produces a real charge. * fix(langfuse): use a dedicated httpx client for the SDK injection The httpx_client handed to the Langfuse SDK came from _get_httpx_client(), which returns LiteLLM's globally cached HTTPHandler. If Langfuse closed that client on teardown it would invalidate the shared client used by every other LiteLLM HTTP call. Build a dedicated httpx.Client instead, still resolving SSL verification and client certificate from LiteLLM's configuration. * fix(soniox): prefer caller-supplied api_base over SONIOX_API_BASE env var * fix(cohere): support max_completion_tokens on cohere v2 chat (default route) (BerriAI#29779) * fix(cohere): support max_completion_tokens on cohere v2 chat The default cohere_chat route resolves to CohereV2ChatConfig, which did not list or map max_completion_tokens, so get_optional_params raised UnsupportedParamsError for the standard OpenAI parameter (the modern replacement for the deprecated max_tokens). The v1 config already maps it to cohere's max_tokens; mirror that in v2 and add v2 regression tests. * fix(cohere): make max_completion_tokens take precedence over max_tokens on v2 When both max_tokens and max_completion_tokens are supplied, prefer max_completion_tokens explicitly rather than relying on dict iteration order, and cover both orderings with a regression test. --------- Co-authored-by: Daniel Yudelevich <4537920+yudelevi@users.noreply.github.com> Co-authored-by: hectorc98 <hector.chamorroalvarez@adyen.com> Co-authored-by: Filippo Menghi <113345637+Cyberfilo@users.noreply.github.com> Co-authored-by: Terrajlz <info@jouleselectrictech.com> Co-authored-by: Bruno Devaux <devaux.br@gmail.com> Co-authored-by: Dan Lemon <dan@danlemon.com> Co-authored-by: Saswat <saswatds@users.noreply.github.com> Co-authored-by: Brian Sparker <brainsparker@users.noreply.github.com> Co-authored-by: Zhao73 <156770117+Zhao73@users.noreply.github.com> Co-authored-by: Urain Ahmad Shah <60431964+urainshah@users.noreply.github.com> Co-authored-by: shin-berri <shin-laptop@berri.ai> Co-authored-by: yuneng-jiang <yuneng@berri.ai> Co-authored-by: kape <168134658+kapelame@users.noreply.github.com> Co-authored-by: danisalvaa <159898202+danisalvaa@users.noreply.github.com> Co-authored-by: Just R <remixingmagelang@gmail.com> Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com> Co-authored-by: abhay23-AI <abhaytrivedi22@gmail.com>
…9781) * test(google): add google-genai SDK proxy integration tests for Gemini and Vertex Pin google-genai in the CI dependency group and exercise streaming/non-streaming generate_content through the LiteLLM proxy in the existing unified_google_tests suite. Co-authored-by: Cursor <cursoragent@cursor.com> * fix(test): address Greptile review for google-genai proxy SDK tests Restore GOOGLE_APPLICATION_CREDENTIALS after the module proxy fixture tears down, initialize temp-file tracking on the proxy SDK base class, and skip litellm reload for proxy_genai_sdk tests so the module-scoped proxy server stays consistent. Co-authored-by: Cursor <cursoragent@cursor.com> * fix(test): only load Vertex credentials when keys exist for proxy SDK tests Avoid writing empty GOOGLE_APPLICATION_CREDENTIALS temp files so Vertex tests skip cleanly without credentials, use a session-scoped proxy fixture, and clean up per-test credential temp files. Co-authored-by: Cursor <cursoragent@cursor.com> * chore(test): scope google-genai pin to unified_google_tests only Remove google-genai from the ci dependency group and pin it in tests/unified_google_tests/requirements.txt for local test installs. Co-authored-by: Cursor <cursoragent@cursor.com> * test(google): tie litellm reload skip to proxy fixture dependency Replace the name-based reload guard with a check on whether the test requests the google_genai_proxy_url fixture, so the skip stays correct if the proxy SDK tests are renamed. * fix(test): stop DatabaseURLSettings tests leaking DATABASE_URL into os.environ The autouse env scrubber relied on monkeypatch.delenv, but apply_to_env writes DATABASE_URL straight into os.environ, which monkeypatch never tracks and therefore never undoes. The synthesized writer.example.com URL leaked past the last test in this module and into proxy-infra tests that read DATABASE_URL to decide whether to hit a real database, e.g. test_deprecated_key_grace_period_cache_hit_path, turning an intended skip into a ConnectError. Snapshot and restore the managed vars directly so the original environment is reinstated regardless of how it was mutated. * test(google): drop redundant per-test vertex credential setup The session-scoped google_genai_proxy_url fixture already configures GOOGLE_APPLICATION_CREDENTIALS before the proxy starts, and _require_proxy_sdk skips when credentials are missing, so the per-test _setup_vertex_credentials_if_needed helper and its temp-file tracking never did any work. Remove it to keep the ABC self-contained. * test(google): declare model_config contract on proxy SDK ABC _skip_reason_if_credentials_missing reads self.model_config to pick the provider, but that property was only declared on the sibling BaseGoogleGenAITest. Make the dependency explicit by adding model_config as an abstract property on BaseGoogleGenAIProxySDKTest so the ABC is self-contained and a standalone subclass fails fast instead of hitting an AttributeError. * test(google): narrow streaming error catch to Exception Catching BaseException in the streaming assertion swallowed KeyboardInterrupt and SystemExit, turning a Ctrl-C into a test failure message instead of letting pytest interrupt cleanly. Only genuine runtime errors should be recorded as stream failures, so catch Exception. * test(google): initialize proxy on the same loop that serves it The proxy was initialized via asyncio.run() on the main thread, which creates and tears down a throwaway event loop, while requests were served on a separate loop in the worker thread. Any asyncio primitive bound to the init loop would be unusable once serving started. Run initialize() on the worker thread's loop right before server.serve() so setup and request handling share a single event loop. * test(google): drop redundant google-genai requirements pin google-genai>=1.37.0,<2.0 is already declared in the proxy-runtime extra, which the google_generate_content_endpoint_testing CI job installs via uv sync --all-extras. The standalone tests/unified_google_tests/requirements.txt duplicated that pin with a narrower ==1.37.0 specifier and was never installed by CI, so it added a second source of truth without changing what gets installed. Drop it and rely on the proxy-runtime extra. * chore: revert incidental uv.lock exclude-newer bump The google-genai ci pin was added and then dropped (it is already provided by the proxy-runtime group), but each uv lock recomputed the relative exclude-newer span, leaving only a timestamp bump in uv.lock. Restore it to the base value so this test-only PR carries no lockfile change. --------- Co-authored-by: Cursor <cursoragent@cursor.com> Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com> Co-authored-by: Claude <noreply@anthropic.com>
…rriAI#29217) * fix(jwt): attribute spend to resolved DB user_id on email/sso fuzzy match When user_id_upsert is enabled with JWT auth and a pre-migration user row exists whose user_email matches the JWT email but whose user_id is a UUID, get_user_object resolves the legacy row via fuzzy lookup, but the JWT-claim user_id (the email) still flowed into team-membership lookup, JWTAuthBuilderResult.user_id, UserAPIKeyAuth and the spend tables. Spend was orphaned under a phantom email id; /user/info and the Usage page showed $0 for the legacy user (GH BerriAI#26789). Treat the resolved user_object as the source of truth: add _canonical_user_id_from_db, rebind inside get_objects, and return effective_user_id so auth_builder unpacks it without adding statements. Fixes BerriAI#26789 Co-authored-by: Cursor <cursoragent@cursor.com> * fix(jwt): log user_id rebind at DEBUG to avoid email PII in INFO streams Greptile review on BerriAI#29217: rebinding often logs JWT email claims at INFO. Co-authored-by: Cursor <cursoragent@cursor.com> * test(jwt): update passthrough allowlist mock for 5-tuple get_objects Staging BerriAI#29256 added a test that still mocked get_objects with a 4-tuple; our PR expanded the return to 5 values (effective_user_id). Co-authored-by: Cursor <cursoragent@cursor.com> --------- Co-authored-by: Cursor <cursoragent@cursor.com>
…erriAI#29816) * feat(ui): generate dashboard API types from the proxy OpenAPI spec Introduces the shared type foundation for the dashboard without touching any runtime code. The proxy's FastAPI app is the source of truth; app.openapi() emits the spec and openapi-typescript turns it into src/lib/http/schema.d.ts. Adds an npm run gen:api script (a Python spec dump piped into openapi-typescript) and a Check UI API Types Sync CI job that regenerates the file from the live spec and fails if it drifts, so the committed types can never silently fall out of step with the backend. The generated file is pinned to openapi-typescript 7.13.0 and excluded from prettier, eslint, and knip, and marked linguist-generated so it collapses in diffs. No openapi-fetch and no call-site changes yet; this only makes the types exist. * chore(ui): tidy gen-api-types script per review Write the spec dump inside a with-block and clean up the temp dir in a finally, so repeated local runs don't leave stray ~MB JSON files behind.
…AI#29820) Deleting a team-scoped BYOK model left its public name in team.models, so /models with a team key kept listing the now-deleted "ghost" model. delete_model stripped team.models using only litellm_modeltable alias lookups, but models added via /model/new with a team_id never create an alias row; their public name lives only in team.models and model_info.team_public_model_name, so it was never removed. The team cache was also left stale because the delete path skipped _refresh_cached_team. The cleanup now keys off team_public_model_name (falling back to alias keys), runs after the deployment row is deleted, and strips a public name only when no remaining team deployment still backs it, so a load-balanced replica is not revoked and concurrent deletes cannot leave a ghost. The updated team row is refreshed in cache so /models reflects the change immediately
…lient (BerriAI#29806) * refactor(ui): route callbacks/nudges calls through apiClient * refactor(ui): route alerting + key/user/team delete calls through apiClient * fix(ui): late-bind fetch in apiClient so global.fetch swaps take effect createApiClient captured fetch at construction time, so reassigning global.fetch (as tests do) had no effect and a real network call leaked. Resolve fetch per request instead; harmless in production where fetch is never swapped, and required for apiClient-based calls to be testable. * refactor(ui): route behavior-preserving networking calls through apiClient Collapse ~61 hand-rolled fetch() calls whose semantics already match the shared apiClient (auth header, JSON body, json-error + deriveErrorMessage + handleError) into apiClient.get/post/etc. Query-string builders and the divergent error-handling functions (no-check, custom messages, text-error) are intentionally left for a follow-up normalization pass, since converting them changes wire encoding or error behavior. Prunes the now-stale no-restricted-syntax suppressions for the removed fetch calls. * refactor(ui): convert remaining admin/guardrail GETs, guard late-bind fetch Routes adminspendByProvider, adminGlobalActivity, and the three guardrail submission calls (list/approve/reject) through apiClient so they match their already-converted siblings instead of staying on raw fetch. Adds a client.test.ts case that swaps globalThis.fetch after createApiClient() and asserts the swap takes effect, which fails on the pre-fix captured-fetch line and locks in the per-call resolution
…treams (BerriAI#30788) A streaming request that breaks mid-flight, for example on a mid-stream read timeout, still bills the provider for the chunks already delivered, yet the proxy recorded that interrupted request as a zero-spend failure. An earlier revision logged the recovered partial usage through the success path, which mislabeled a failed request as a success and produced a misleading spend row This recovers the partial usage where the failure is actually logged. The streaming handler assembles the usage from the chunks seen so far and stashes it, with its cost, on the logging object before firing the failure handlers. The proxy failure hook lifts that usage and cost onto request_data before the non-serialisable logging object is popped, and the spend-log writer records the real partial spend on the failure row instead of a hardcoded zero; get_logging_payload honors the recovered usage for the token columns and _failure_handler_helper_fn preserves the recovered cost so the non-DB failure loggers stay consistent A request that recovers via a successful fallback is unaffected: the failure hook only fires when the whole request fails, so the fallback's combined-usage success row stays the single source of truth and there is no double counting Resolves LIT-3825 Co-authored-by: veria-ai[bot] <224490171+veria-ai[bot]@users.noreply.github.com>
…#30859) The "View Usage Guide" button on the legacy Usage page (shown when DISABLE_EXPENSIVE_DB_QUERIES is set, i.e. SpendLogs has 1M+ rows) linked to docs/proxy/spending_monitoring, which was removed from the docs and now returns 404. Point it at docs/proxy/cost_tracking, which is live. Fixes LIT-2724
…erriAI#29990) The delete-team confirmation modal warned that a team's keys would be deleted but said nothing about models. BerriAI#29977 made team deletion also delete the team's BYOK models, so the modal copy was understating what gets removed. The warning banner now mentions models alongside keys, and the always-shown confirmation message does too so a team that has models but no keys (the banner only renders when keys exist) still gets warned.
…he scope keys (BerriAI#30675) Adds a "valkey-semantic" cache type so semantic prompt caching can run against Valkey clusters (for example AWS ElastiCache for Valkey) using the valkey-search module. The existing "redis-semantic" backend cannot drive valkey-search. RedisVL gates the connection on a RediSearch module version that valkey-search does not report, and its SemanticCache index declares the prompt as a TEXT field, which valkey-search does not implement. ValkeySemanticCache therefore talks to valkey-search directly over redis-py: it builds a vector index from the field types valkey-search supports (TAG for caller scope, VECTOR for the prompt embedding) and runs KNN queries for retrieval. Prompt extraction, embedding generation, and cached-response parsing are reused from RedisSemanticCache since those are backend agnostic. The redis dependency is imported lazily in the cache dispatch so importing litellm without redis installed still works. It also fixes semantic-cache scope keys so similarity matching works across reworded prompts. get_cache_key() hashed messages / prompt / input into the litellm_cache_key that every semantic backend filters its KNN search on, so a paraphrase landed in a different bucket and never matched, even far above the similarity threshold. For semantic cache types the prompt-bearing params are now excluded from the scope key and the server-set tenant identity (user_api_key, team, org) is appended instead, restoring embedding matching within a tenant while keeping cache entries scoped to the authenticated key / team / org. The three semantic backends share this key, so the same change fixes redis-semantic and qdrant-semantic. Connections resolve from VALKEY_HOST / VALKEY_PORT / VALKEY_PASSWORD, falling back to REDIS_* for drop-in compatibility, and passwordless clusters (IAM or no-auth) are supported. Resolves BerriAI#29121 Fixes BerriAI#29086
…riAI#30871) The deprecated OldTeams component takes only accessToken, userID, userRole and premiumUser; it ignores the teams prop these tests passed and instead populates its table from the mocked teamListCall. The delete-warning block never set teamListCall, and vi.clearAllMocks clears call history but not implementations, so the table rendered the "Legacy Team" (keys.length 2) left behind by the previous block's last test. Both delete tests therefore ran against that leaked team: the keys-present case passed only because the leaked count happened to be 2, and the no-keys case rendered the same warning it asserted should be absent, so it failed. Seed the team through the channel the component actually reads (teamListCall) and drop the props it never consumes, so each test renders exactly the team it declares. The keys-present case now uses a distinctive count so it can no longer pass on a coincidental leak
… ruff gate (BerriAI#30877) * feat: add CI-parity mode and truncation-proof summary to strict ruff gate * refactor: tolerant worktree cleanup and concrete GateInputs types * fix: clean up temp dir when git worktree add fails * fix: align lint-gate with CI by dropping unused --ci-parity path The lint-gate Makefile target invoked ruff_strict_gate.py with --ci-parity, which counted violations on a throwaway merge of base into HEAD against base counts at the base tip. CI in test-linting.yml runs the same script without --ci-parity on a PR-head checkout, taking the gather_fast path that counts on the live tree against base counts at the merge-base. A local pass could therefore disagree with CI. Drop --ci-parity from the Makefile and remove the now-unused gather_ci_parity branch and flag so there is one code path that both local and CI exercise. The docstring claim that CI runs against the synthetic merge ref was also wrong; the workflow checks out github.event.pull_request.head.sha. --------- Co-authored-by: Cursor Agent <cursoragent@cursor.com>
* bump: version 0.1.42 → 0.1.43 * bump: version 1.89.0 → 1.90.0 * adding uv lock
…erriAI#30897) * fix(watsonx): wrap string embedding input in array for WatsonX API WatsonX text/embeddings expects inputs as []string; OpenAI clients often send a single string. Co-authored-by: Cursor <cursoragent@cursor.com> * style(watsonx): format watsonx embed transformation for black Co-authored-by: Cursor <cursoragent@cursor.com> * fix(watsonx): avoid UP006 in embed transformation strict lint gate Use list[str] and branch-based input normalization instead of List and cast so the watsonx embedding change does not add strict ruff UP006 violations. Co-authored-by: Cursor <cursoragent@cursor.com> --------- Co-authored-by: Shivam Rawat <shivamrawat@Shivams-MacBook-Pro.local> Co-authored-by: Cursor <cursoragent@cursor.com>
…ndpoint (BerriAI#30900) * test: point router/completion/triton tests at the local fake OpenAI endpoint The shared Railway-hosted mock (exampleopenaiendpoint-production.up.railway.app) takes down unrelated CI jobs whenever it is unreachable. BerriAI#30695 moved the mounted proxy configs onto a job-local fake server but left these in-Python api_base literals pointing at the dead host, so litellm_router_testing, local_testing_part1, local_testing_part2 and llm_translation_testing still fail with a 404 "Application not found" when Railway is down Resolve the api_base from FAKE_OPENAI_API_BASE (default http://127.0.0.1:8190) through a shared helper, auto-start the canned server from the local_testing and llm_translation conftests when nothing is already serving, and extend the server with a Triton embeddings route and a slow-endpoint delay so the triton and latency-timeout tests run fully offline. The deliberately broken fallback URL is left as-is so fallback handling still has a failing upstream * fix: ignore non-loopback FAKE_OPENAI_API_BASE so the local mock is used in CI * fix: drop 0.0.0.0 from loopback hosts, an unreliable client connect target * fix(tests): keep fake OpenAI mock alive across xdist workers ensure_fake_openai_endpoint registered atexit on the worker that spawned the subprocess, so under -n 4 the first worker to drain its queue would terminate the shared mock while siblings were still hitting it. Detach the child via start_new_session and drop the per-worker teardown; reuse on /health handles re-runs and CI containers clean up themselves
* feat(sandbox): add e2b code execution primitive Add a provider-agnostic code execution primitive that runs model-generated code in an isolated sandbox and returns the output, with e2b as the first backend over raw httpx (no SDK dependency). Public API: litellm.acode_interpreter_tool (ephemeral create -> run -> delete) plus the low-level lifecycle litellm.acreate_sandbox / arun_code / adelete_sandbox. Each is @client-decorated so operations are logged like litellm.asearch. Backends implement BaseSandboxConfig; resolved via ProviderConfigManager.get_provider_sandbox_config. * fix(sandbox): address review feedback and CI gates - document e2b provider in provider_endpoints_support.json and add a sandbox endpoint definition - regenerate dashboard CallTypes after the sandbox call-type additions - guard explicit timeout=0 instead of coercing it to the default - require a ContainerHandle access token before running code; reject bare-id runs - return False on a 404 delete now that the shared http handler raises for status - skip non-JSON NDJSON lines and cap streamed output to bound memory - move the real-network integration tests out of tests/test_litellm into tests/integration/sandbox * fix(sandbox): satisfy strict ruff gate and scope star-exports - modernize annotations in the new sandbox modules to PEP 585/604 (list/dict, X | None) and drop the now-unnecessary quoted forward refs so the strict-rule budget delta for UP006/UP037/UP045 returns to zero - add __all__ to litellm/sandbox/main.py so 'import *' only re-exports the four public entrypoints instead of leaking module-level imports * fix(sandbox): drop quotes on sandbox config return annotation utils.py uses 'from __future__ import annotations', so the quoted forward ref tripped UP037; the unquoted union is lazily evaluated and keeps the strict-rule delta at zero * chore(sandbox): re-trigger automated review after addressing feedback
… is not set" (BerriAI#30903) The migrated /ui/api-keys route gates rendering on useAuthorized() but read userID from the AuthContext (useAuth), which hydrates asynchronously. On a hard refresh or deep link the route could render UserDashboard before AuthContext had populated userID, so UserDashboard hit its `userID == null` guard and showed "User ID is not set". The legacy index page avoided this by gating on AuthContext's own authLoading; the migration switched the gate to useAuthorized without aligning the identity source. Read identity from useAuthorized (a synchronous cookie decode) so userID is populated whenever the route is authorized. useAuth is kept only for the backfill setters UserDashboard still expects, until the planned AuthContext consolidation removes them. Refs LIT-3687
chore(ci): promote internal staging to main
…r ids on /v1/responses Reusing a LiteLLM-issued container id in tools[].container on a /v1/responses call failed two ways: the composite id was forwarded to the provider verbatim (Azure 400, caps container at 64 chars) and routing fell back to model-name load-balancing (404, wrong deployment). - DeploymentAffinityCheck: pin to the deployment encoded in the container id, mirroring previous_response_id affinity. - update_responses_tools_with_model_file_ids: decode managed container ids to the native provider id in the always-runs pass, so it fires even without a file mapping. Adds routing and translation regression tests. Fixes BerriAI#30781
|
|
Codecov Report❌ Patch coverage is 📢 Thoughts on this report? Let us know! |
wasimat404
marked this pull request as ready for review
June 21, 2026 23:39
Contributor
Greptile SummaryThis PR extends LiteLLM's managed-id pattern to
Confidence Score: 4/5Safe to merge; both changed files are additive and follow existing patterns, with no mutations to shared state or existing behaviour. The routing and translation logic are clearly separated, well-tested, and follow the established managed-id round-trip pattern. The one nuance is a subtle fall-through in priority when a previous_response_id deployment is unhealthy and a container id points elsewhere, but this is an uncommon edge case that does not break the happy path. deployment_affinity_check.py — the fall-through interaction between previous_response_id and container-id affinity when the response deployment is unhealthy deserves a clarifying comment.
|
| Filename | Overview |
|---|---|
| litellm/litellm_core_utils/prompt_templates/common_utils.py | Adds decode_container_ids_in_tools (Pass 1b) to translate managed cntr IDs to native provider IDs before the upstream call; correctly placed before the Pass 2 early-return gate so it fires even when no file mapping is present. |
| litellm/router_utils/pre_call_checks/deployment_affinity_check.py | Adds container-ID affinity routing (1b) inside the enable_responses_api block; iterates tools[], decodes the managed cntr_ id to extract model_id, and pins to the owning deployment. Priority is correctly lower than previous_response_id. |
| tests/test_litellm/llms/test_file_search_responses.py | Adds B4/B5/B6 tests covering managed-string decode, object-container passthrough, and non-managed passthrough for the new Pass 1b translation; all mock-only, no live network calls. |
| tests/test_litellm/router_utils/pre_call_checks/test_deployment_affinity_check.py | Adds test_async_code_interpreter_container_pins_to_owning_deployment; end-to-end through mocked Router, verifies container-id affinity overrides user-key affinity. Well-structured and covers the primary regression scenario from #30781. |
Reviews (1): Last reviewed commit: "fix(responses): use builtin generics in ..." | Re-trigger Greptile
![greptile-apps[bot]](https://avatars.githubusercontent.com/in/867647?s=60&v=4){kind=small}
Comment on lines
+348
to
+381
| # 1b) code_interpreter container affinity (Responses API create calls). | ||
| # A LiteLLM-managed container id (cntr_...) encodes the owning | ||
| # deployment's model_id. Reusing it in tools[].container must pin | ||
| # routing to that deployment, otherwise the call load-balances by | ||
| # model name and lands on a deployment that doesn't own the | ||
| # container (Azure containers are region-local -> 404). Lower | ||
| # priority than previous_response_id, which stays authoritative. | ||
| tools = request_kwargs.get("tools") | ||
| if isinstance(tools, list): | ||
| for tool in tools: | ||
| if not isinstance(tool, dict): | ||
| continue | ||
| if tool.get("type") != "code_interpreter": | ||
| continue | ||
| # container is either a managed id string (cntr_...) or an | ||
| # object for provisioning a new container ({"type": "auto"}), | ||
| # which carries no model_id to pin -> skip non-str values. | ||
| container = tool.get("container") | ||
| if not isinstance(container, str): | ||
| continue | ||
| decoded = ResponsesAPIRequestUtils._decode_container_id(container) | ||
| container_model_id = decoded.get("model_id") | ||
| if container_model_id is None: | ||
| continue | ||
| deployment = self._find_deployment_by_model_id( | ||
| healthy_deployments=typed_healthy_deployments, | ||
| model_id=container_model_id, | ||
| ) | ||
| if deployment is not None: | ||
| verbose_router_logger.debug( | ||
| "DeploymentAffinityCheck: code_interpreter container pinning -> deployment=%s", | ||
| container_model_id, | ||
| ) | ||
| return [deployment] |
Contributor
There was a problem hiding this comment.
When previous_response_id is non-None, decodes to a valid model_id, but the owning deployment is absent from healthy_deployments, the early-return at line 347 is not taken and execution falls through to the container-id affinity check (1b). If the container was created on a different deployment than the response, that deployment gets selected — contradicting the PR's stated rule that previous_response_id is always authoritative. The scenario requires both previous_response_id and a managed container id to be present with different owning deployments while the response deployment is unhealthy, which is an uncommon combination, but worth a comment explaining the designed priority behaviour in this fall-through path.
![veria-ai[bot]](https://avatars.githubusercontent.com/in/1723776?s=60&v=4){kind=small}
| container = tool.get("container") | ||
| if not isinstance(container, str): | ||
| continue | ||
| decoded = ResponsesAPIRequestUtils._decode_container_id(container) |
Contributor
There was a problem hiding this comment.
High: Missing container ownership check
tools[].container is client-controlled, and this path trusts the decoded model_id for routing before common_utils._decode_container_ids_in_tools forwards the decoded native container ID upstream. Unlike the /v1/containers/{container_id} endpoints, /v1/responses does not call assert_user_can_access_container, so a non-admin caller who has another user's container ID can run a code-interpreter follow-up against that container through the proxy. Validate each string tools[].container against the proxy container ownership table before pinning/decoding it, and reject containers not owned by the caller's user/team scope.
Contributor
PR overviewThis pull request updates the /v1/responses flow to route managed code-interpreter requests by container ID and translate proxy-managed container IDs to their native upstream IDs. The changes affect pre-call routing logic for response tools that reference an existing code-interpreter container. There is one open security issue: the /v1/responses path currently trusts a client-supplied tools[].container value for routing and upstream translation without verifying that the caller owns or can access that container. If a non-admin user obtains another user's container ID, they could submit a code-interpreter follow-up against that container through the proxy. No issues have been addressed yet, so the PR still needs an ownership check before this behavior is safe. Open issues (1)
Fixed/addressed: 0 · PR risk: 7/10 |
Contributor
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
| No-ops on the object container form (provision-new) and on non-managed strings: | ||
| ``decode_container_id_to_original`` returns the input unchanged when it isn't managed. | ||
| """ | ||
| from litellm.responses.utils import ResponsesAPIRequestUtils |
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
17 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.
What
Reusing a LiteLLM-issued
code_interpretercontainer id intools[].containeron a follow-up/v1/responsescall currently fails two ways:string_above_max_length. The composite managed id (cntr_+ base64 payload, ~237 chars) is forwarded to the provider verbatim. Azure capstools[].containerat 64 chars and rejects it.Container not found. If the caller strips it to the native id to dodge (1), the id carries no routing payload, so the call load-balances by model name and lands on a deployment that doesn't own the container (Azure containers are region-local).So a container LiteLLM hands back from one
/v1/responsescall can't be reliably reused on the next.Fixes #30781.
Why this shape
The managed-id decode plus model_id routing already exists for container ids in the URL path (
/v1/containers/{id}/..., added in #27921 via_init_containers_api_endpoints). It was never applied to a container id embedded in a/v1/responsesrequest body. This PR extends the same pattern to the body case, split across the two layers where each concern already lives:DeploymentAffinityCheck.async_filter_deploymentsadds a branch that decodes the container id intools[].containerand pins to the encoded deployment, mirroring the existingprevious_response_idaffinity. Kept lower priority thanprevious_response_id, which stays authoritative.update_responses_tools_with_model_file_idsdecodes managed container strings to the native provider id. Placed in the always-runs pass (Pass 1b), before the file-mapping gate returns early, so it fires on the reuse case which has no file mapping. No-ops on the object container form ({"type": "auto"}) and on non-managed strings.Tests
test_async_code_interpreter_container_pins_to_owning_deployment. End-to-end through the Router: provisions a container, forces user-key affinity to the other deployment, asserts the follow-up pins back to the owning deployment via the container id.test_B4/B5/B6intest_file_search_responses.py. Translation through the public entry point: managed id to native, object form untouched, non-managed string untouched.All existing tests in both touched files pass (61 total).
Known limitation
The routing half is verified with a mocked Router (no live Azure). I don't have a multi-deployment Azure setup to run the original repro end to end against a real provider, so the live round-trip is covered by the mocked test rather than an integration test.