scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-10 03:28:53 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 85
53276 commits 3393 branches 1449 tags 5.1 GiB
Commit graph

53276 commits

This branch
This branch
All branches
Author SHA1 Message Date
Yujong Lee
da839d4a11 fix(harness): skip unavailable Rust traces 2026-09-14 14:01:28 -07:00
Yassin Kortam
4123b4bc2b
Merge pull request #41086 from BerriAI/litellm_team_list_org_admin_membership_lit3723 
fix(proxy): keep org admins' own team memberships in other orgs visible on team list
 2026-09-14 13:57:08 -07:00
Yassin Kortam
ee03bad8c6
Merge pull request #41064 from BerriAI/litellm_bedrock_realtime_propagate_provider_failures 
fix(bedrock/realtime): propagate deferred Nova Sonic stream failures to the router
 2026-09-14 13:56:26 -07:00
jesus
f9298d8979 style(tests): drop unrelated formatting churn 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-14 20:56:10 +00:00
yassin
ffeea30f23 test(auth): cover a stale membership write landing after a fresh reload 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-14 20:55:22 +00:00
jesus
efad8deb71 fix(alerting): send llm_exceptions Slack alert for 5xx HTTPException/ProxyException 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-14 20:55:02 +00:00
yucheng
937179bde1 fix(guardrails): never map empty guardrail names onto a sibling id 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-14 20:53:11 +00:00
yucheng
586d51f15e fix(guardrails): skip malformed guardrail entries instead of failing the usage batch 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-14 20:50:41 +00:00
tin-berri
2cad7a49af
Merge pull request #41116 from BerriAI/litellm_auto_router_session_api_access 
fix(proxy): allow LLM API keys to read auto-router sessions
 2026-09-14 13:49:03 -07:00
yucheng
bb52c80d75 merge: main into litellm_lit5285_login_rate_limit_v2
Some checks failed
ai-gateway image / ai-gateway release image (push) Has been cancelled
Details
LiteLLM Rust / rust-lint (push) Has been cancelled
Details
LiteLLM Rust / rust-test (push) Has been cancelled
Details 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-14 20:48:11 +00:00
yassin
abc85ba607 fix(proxy): leave the realtime max_parallel_requests slot to the limiter failure callback when a refusal was logged 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-14 20:47:37 +00:00
yassin
91c964a338 fix(auth): evict the membership cache entry when invalidation lands during the cache write 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-14 20:46:09 +00:00
yucheng
7ebb169a4d fix(guardrails): coalesce usage index rows per request and guardrail, keeping policy linkage 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-14 20:45:47 +00:00
Yassin Kortam
161ae2f3b4
Merge pull request #41107 from BerriAI/litellm_hide_credentials_hint_when_ui_password_set 
fix(proxy): hide default credentials login hint when UI_PASSWORD is set
 2026-09-14 13:44:09 -07:00
Yassin Kortam
43c3dbb312
Merge pull request #41118 from BerriAI/litellm_prometheus_proxy_provider_fallback_constant 
refactor(prometheus): source PROXY_LLM_PROVIDER_FALLBACK from litellm.constants
 2026-09-14 13:40:54 -07:00
Yassin Kortam
97ddb9494e
Merge pull request #40930 from BerriAI/litellm_flat_retry_records 
fix(router): record flat retry attempts and cap retries from attempted_retries
 2026-09-14 13:37:10 -07:00
yucheng
c3f52fe0d5 fix(guardrails): key not_run index rows by the sibling evaluation's guardrail_id 
A not_run entry from the base guardrail only carries guardrail_name, while the
content filter's evaluated entry carries guardrail_id. Keyed apart, one request
listed twice in the monitor for a logging_only guardrail (Not run and Passed).
Resolve the id from a same-name sibling in the payload so the severity pick applies

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-14 20:37:09 +00:00
Tin Chi Lo
3177c37e22 fix(cli): show routed models and session stats for LLM API keys 2026-09-14 13:36:00 -07:00
yassin
c8440b5638 fix(proxy): move credentials hint helper into a leaf html_forms module to clear CodeQL cyclic import 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-14 20:34:58 +00:00
Yassin Kortam
856aedd14a
Merge pull request #40817 from BerriAI/litellm_redis_timeout_log_throttle 
fix(redis): log a timeout streak once per interval instead of one line per cache call
 2026-09-14 13:34:45 -07:00
yassin
9a62a5ebee refactor(prometheus): source PROXY_LLM_PROVIDER_FALLBACK from litellm.constants 
Importing the fallback from litellm.proxy.hooks.rate_limiter_utils at the top
of litellm/integrations/prometheus.py closed an import cycle CodeQL flagged on
#41059 (rate_limiter_utils -> litellm -> ... -> prometheus). Hoist the constant
into litellm/constants.py so both modules read it from a leaf module.

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-14 20:29:35 +00:00
Yassin Kortam
ab09abc3c8
Merge pull request #41115 from BerriAI/litellm_fix_wrapper_async_double_sync_success_handler_main 
fix(utils): stop wrapper_async submitting the sync success handler twice
 2026-09-14 13:28:16 -07:00
Yassin Kortam
963522207d
Merge pull request #41114 from BerriAI/litellm_model_info_skip_jsonable_encoder_main 
perf(proxy): serialize /model/info listing once with orjson
 2026-09-14 13:28:06 -07:00
yassin
4435aa601d fix(proxy): keep JWT agent binding through AUTO_REGISTER key creation 
The virtual key created by AUTO_REGISTER replaced the JWT principal without
the agent_id auth_builder had resolved from agent_id_jwt_field, so agent
policies were skipped on that request and every later mapped-key request.
Pass the bound agent_id into generate_key_helper_fn and onto the returned
principal.

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-14 20:28:02 +00:00
yassin
336ead5106 fix(proxy): import UserNotFoundError in grants resolver from the types module 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-14 20:23:54 +00:00
yassin
1b31be1a9c fix(proxy): leave the realtime max_parallel slot to the success callback when one is enqueued 
Releasing the slot unconditionally from the route raced the limiter's own
success handler on the logging worker: both could read the same stashed
acquisition before either cleared it, and under the integer in-memory
fallback that double-decrements the counter. The route now releases only on
exits without a success callback (pre-call rejection, pre-call cancellation,
and Phase 2 exits without the success stamp), matching the HTTP disconnect
path's ownership rule.

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-14 20:23:23 +00:00
yassin
4ac168b3fc fix(auth): drop in-flight membership load on invalidation so it cannot repopulate the cache 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-14 20:13:39 +00:00
yassin
d7900df73f chore(constants): drop the restating comment above the Bedrock realtime scope keys 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-14 20:13:02 +00:00
yassin
4fee71b7ad fix(proxy): define UserNotFoundError in an import-free types module so no importer sits in the CodeQL cycle 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-14 20:10:36 +00:00
yassin
a4e34d6e1b test(caching): wrap the DualCache fixture line to the 120 character limit 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-14 20:05:14 +00:00
Yassin Kortam
34fe9f71d5
Merge pull request #41059 from BerriAI/litellm_prometheus_pre_call_rate_limit_api_provider 
fix(prometheus): label pre-call rate limit failures with the resolved api_provider
 2026-09-14 13:02:07 -07:00
ryan
2d3b63fb5a fix(proxy): report parent org models on /team/info only to team managers 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-14 20:01:47 +00:00
yassin
bea22df6c2 fix(caching): keep generic add_cache failures at ERROR unless the backend is Redis 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-14 19:59:10 +00:00
yassin
9e870ffd00 fix(proxy): resolve CodeQL findings on team list, sanitize log args and move UserNotFoundError out of the import cycle 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-14 19:57:50 +00:00
yassin
21cd52d508 fix(bedrock/realtime): declare the client websocket scope as a protocol attribute 
CodeQL py/ineffectual-statement flags the bare ellipsis body of the
@property declaration on the RealtimeClientWebSocket protocol. A plain
attribute annotation states the same structural contract without an
expression statement.

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-14 19:55:06 +00:00
yassin
10be7e01d4 fix(router): import retry helpers inside their functions to break CodeQL import cycles 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-14 19:54:00 +00:00
yassin
845596063d fix(prometheus): label pre-call rate limit failures with the resolved api_provider 
Pre-call limiters reject before a deployment is attached to request_data, so
the failure hook could not resolve api_provider for router aliases and emitted
api_provider="None" on litellm_proxy_failed_requests_metric_total and
litellm_proxy_total_requests_metric_total. Fall back to the provider the
limiter already resolved onto RateLimitError.llm_provider, keeping request
data as the first source and ignoring the proxy placeholder.

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-14 19:50:21 +00:00
yassin
81ffc3125f fix(proxy): release realtime max_parallel_requests slot when the task is cancelled during pre-call 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-14 19:50:01 +00:00
yassin
caaf368652 fix(proxy): move credentials hint helper into discovery module to break CodeQL import cycle 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-14 19:48:45 +00:00
yassin
39f6ac4788 perf(proxy): serialize /model/info listing once with orjson 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-14 19:47:51 +00:00
yassin
d13e8dcae2 fix(utils): stop wrapper_async submitting the sync success handler twice 
_client_async_logging_helper re-submitted logging_obj.success_handler to the
executor after _dispatch_success_logging had already done so, running the same
success pipeline twice per async request and racing on shared logging state.

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-14 19:47:43 +00:00
Yassin Kortam
1f8bae7eab
Merge pull request #41058 from BerriAI/litellm_fix_wrapper_async_double_sync_success_handler 
fix(utils): stop wrapper_async submitting the sync success handler twice
 2026-09-14 12:43:32 -07:00
Yassin Kortam
8d5c165547
Merge pull request #41061 from BerriAI/litellm_model_info_skip_jsonable_encoder 
perf(proxy): serialize /model/info listing once with orjson
 2026-09-14 12:43:01 -07:00
Yassin Kortam
b94b8bca21
Merge pull request #41096 from BerriAI/litellm_disable_access_log_paths 
feat(proxy): honor LITELLM_DISABLE_ACCESS_LOG_PATHS to drop noisy uvicorn access log lines
 2026-09-14 12:41:34 -07:00
Yassin Kortam
687cb6cb7a
Merge pull request #40992 from BerriAI/litellm_model_info_team_alias 
fix(ui): show the team alias on the model info page and in its raw JSON
 2026-09-14 12:40:02 -07:00
Yassin Kortam
f67cc62032
Merge pull request #40995 from BerriAI/litellm_all_deployments_cooldown_error 
fix(router): name the all-deployments-in-cooldown error on 429 responses
 2026-09-14 12:39:42 -07:00
ryan
9cdfe311e9 test: assert only the org ceiling /team/info returns 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-14 19:39:18 +00:00
yassin
c4354c248a fix(redis): route the per-TTL pipeline write timeout log through the shared throttle 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-14 19:38:14 +00:00
ryan
5ddb0fe691 fix(ui): keep the team model select loading until /team/info reports the org ceiling 
useTeam seeds its cache from the team list, which has no organization_models, so the select briefly rendered unfiltered. Also drop the Prisma include assertion from the backend test.

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-14 19:38:05 +00:00
Devin AI
2a06ece58c feat(models): mark Fireworks GLM 5.3 Fast router as supporting reasoning and response schema 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-14 19:37:25 +00:00