scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-05 02:41:56 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 49
50724 commits 3118 branches 1436 tags 4.4 GiB
Commit graph

50724 commits

This branch
This branch
All branches
Author SHA1 Message Date
Devin AI
500790a93a fix(ui): keep every team selectable for org admins in the Team ID selector 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-17 16:25:37 -07:00
Devin AI
59693d5019 fix(ui): only offer team admins the teams they administer in the Team ID selector 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-17 16:25:37 -07:00
Devin AI
a7daa21df7 fix(ui): let admins change a model's team from the model edit page 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-17 16:25:17 -07:00
ryan-crabbe-berri
a282e3c78c refactor(ui): build transformed model rows without in-place mutation 
Greptile flagged the per-second fields for extending the transformer's
mutate-in-a-loop pattern. Map each raw model to a new object instead so no
field is assigned onto a shared reference, and drop the now unused
prefer-const suppression for the file
 2026-09-17 16:24:55 -07:00
ryan
de0047c802 fix(proxy): skip allowlist rewrite when the model name is unchanged 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-17 23:24:26 +00:00
yassin
33531649c3 perf(mcp): count gateway session groups with Counter and pin the oversized initialize peek invariant 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-17 23:20:47 +00:00
ryan-crabbe-berri
10616d7407
Merge pull request #40875 from BerriAI/litellm_cache_leakage_all_models 
fix(ui): list every provider in the cache leakage by-model table
 2026-09-17 16:18:16 -07:00
Devin AI
7d65d9d774 fix(proxy): seed member budget forks from the row the membership points at 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-17 23:17:13 +00:00
ryan
d3f5cde530 fix(proxy): propagate db model renames to key, team, org, project and user model allowlists 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-17 23:11:52 +00:00
Mateo Wang
57d41bda29
Merge pull request #41684 from BerriAI/litellm_wildcard_license_auto_router 
fix(license): let a wildcard allowed_features license grant the auto_router feature
 2026-09-17 16:11:40 -07:00
Mateo Wang
07b5051c0d
Merge pull request #41689 from BerriAI/litellm_responses_bridge_strip_internal_kwargs 
fix(responses): keep the addressed response id off bridged provider requests
 2026-09-17 16:11:04 -07:00
yassin
aacbbe89d6 chore(proxy): regenerate OpenAPI snapshot and dashboard types for the Transcribe route docstring 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-17 23:10:23 +00:00
mateo-berri
1c40e6034d fix(a2a): Entra credentials own the chat route bearer over a stored api_key or authorization header 2026-09-17 16:09:36 -07:00
mateo-berri
7f581f6bc7 fix(router): keep the TypeSafe key off caller-chosen Jev endpoints 2026-09-17 16:09:31 -07:00
yassin
912edaa8cc Merge remote-tracking branch 'origin/main' into litellm_transcribe_passthrough 2026-09-17 23:07:57 +00:00
Mateo Wang
0da001901b
Merge pull request #41672 from BerriAI/litellm_autoroute_start_stop 
feat(cli): rename lite autoroute up/down to start/stop, keeping the old names as deprecated aliases
 2026-09-17 16:07:00 -07:00
yujonglee
ad5998072b
Merge pull request #41690 from BerriAI/litellm_extract_providers 
refactor(rust): extract provider translations
 2026-09-17 16:05:59 -07:00
Devin AI
9d5f65c26c merge: resolve conflict with main, move temp budget patch fields to shared member_budget_patch 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-17 23:04:25 +00:00
ryan-crabbe-berri
f16c4e7a22 fix(team): drop a redundant None check on a non-nullable allowed_models column 2026-09-17 16:00:24 -07:00
ryan-crabbe-berri
29a959b3e8
Merge pull request #41632 from BerriAI/litellm_bulk_team_member_budget_update 
feat(management_v1): bulk update team member budgets
 2026-09-17 15:58:32 -07:00
yassin
ce735f586c fix(proxy): scope Transcribe jobs to the key that started them and charge rewritten media the maximum 
Standard jobs are tagged litellm-owner on StartTranscriptionJob so GetTranscriptionJob
and DeleteTranscriptionJob only work for the owner or a proxy admin, and account-wide
operations need a proxy admin. Media rewritten after job creation is charged the eight
hour maximum, and the success handler takes an injected log dispatch instead of tests
patching its private method

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-17 22:58:15 +00:00
mateo-berri
d3963e5d63 test(cli): pin the up alias port forwarding and the removed-settings stop message 2026-09-17 15:55:50 -07:00
Yujong Lee
6ce78b85a5 refactor(rust): remove core provider reexports 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-17 22:55:15 +00:00
mateo-berri
79029d89f9 test(responses): drop the history docstrings from the bridge regression tests 2026-09-17 15:51:35 -07:00
kerry
91619376d2 test: restore azure ai cached-token billing coverage with derived rates
Some checks failed
LiteLLM Rust / rust-lint (push) Has been cancelled
Details
LiteLLM Rust / rust-test (push) Has been cancelled
Details
LiteLLM Rust / rust-wheel (push) Has been cancelled
Details 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-17 22:49:02 +00:00
Mateo Wang
289c52bcd6
Merge pull request #39512 from BerriAI/litellm_fix_image_edits_bracketed_alias 
fix(images): stop forwarding the raw image[] and mask[] form keys
 2026-09-17 15:48:32 -07:00
Yujong Lee
558022c3dd refactor(rust): extract provider translations 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-17 22:46:02 +00:00
Mateo Wang
fec8231b83
Merge pull request #41419 from BerriAI/litellm_bedrock_openai_no_cachepoint 
fix(bedrock): never emit Converse cachePoint for OpenAI-family models
 2026-09-17 15:43:04 -07:00
ryan-crabbe-berri
f04f0258f7 refactor(team): model the bulk budget audit payload as frozen types 2026-09-17 15:41:06 -07:00
yucheng
e9825f1d26 test(proxy): drive the heuristics responsiveness check without mutable state 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-17 22:39:15 +00:00
mateo-berri
1feaa48705 fix(proxy): log TypeSafe calls that name no model as unknown 2026-09-17 15:37:00 -07:00
yassin
313093a8a0 fix(ui): gate MCP live connections tab to proxy admin tier roles 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-17 22:36:00 +00:00
mateo-berri
ca91751d5b fix(responses): keep the addressed response id off bridged provider requests 
The Responses id security hook keeps the id a client addressed under
`_litellm_addressed_response_id` in the request body so internal retries can
re-authorize it. On a model without a native Responses config that body is
bridged into `completion()` kwargs, the key was treated as a provider param,
and providers rejected it, so every follow-up turn carrying
`previous_response_id` returned 400.

Register the key in `all_litellm_params` so it is dropped before any provider
request, and share one constant between the hook and the param list.
 2026-09-17 15:35:11 -07:00
kerry
0b58281038 Merge remote-tracking branch 'origin/litellm_remove_brittle_price_pinning_tests' into litellm_remove_brittle_price_pinning_tests 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

# Conflicts:
#	tests/test_litellm/proxy/common_utils/test_prompt_cache_pricing.py
 2026-09-17 22:33:53 +00:00
kerry
b054d54bee Merge remote-tracking branch 'origin/litellm_remove_brittle_price_pinning_tests' into litellm_remove_brittle_price_pinning_tests 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

# Conflicts:
#	tests/test_litellm/llms/parallel_ai/test_parallel_ai_search.py
#	tests/test_litellm/proxy/common_utils/test_prompt_cache_pricing.py
#	tests/test_litellm/proxy/test_proxy_utils.py
 2026-09-17 22:33:26 +00:00
kerry
4be0cf96b2 test: treat null long-context rates as absent when deriving cache cost expectations 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-17 22:33:09 +00:00
kerry
9eb6fbc572 test: read cost-map keys the implementation resolves and isolate the tariff test's model_cost copy 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-17 22:32:39 +00:00
yucheng
36844ef301 fix(proxy): clamp prompt injection heuristics worker count to at least one 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-17 22:26:00 +00:00
mateo-berri
4371ddb620 feat(cli): keep lite autoroute up and down as hidden deprecated aliases 2026-09-17 15:25:12 -07:00
kerry
eb2be3758a test: read cost expectations from the catalog row the code bills against 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-17 22:22:24 +00:00
ryan-crabbe-berri
775b83bcf4 refactor(team): drop null limits and ISO-format timestamps in the bulk budget audit payload 2026-09-17 15:19:35 -07:00
kerry
e8f098f38e test: hoist the json import to module scope 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-17 22:18:18 +00:00
kerry
26addc5b39 test: fix remaining cost-map pin and leaked logging event races 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-17 22:17:27 +00:00
ryan-crabbe-berri
909a30d6a1 fix(team): keep a forked member budget's reset window and audit bulk member budget writes 
Forking a shared budget row rebuilt budget_reset_at from the duration, so editing
an unrelated limit restarted the member's window while their spend carried over:
a tpm bump quietly handed them a fresh period. The fork now inherits the source
row's deadline, and only recomputes when the patch actually sets budget_duration.

The bulk member budget route now writes one audit entry per call, a team-scoped
'updated' row carrying every written member's limits before and after, matching
what /team/member_add already records for membership changes. It honors the
litellm-changed-by header like the other audited team routes.
 2026-09-17 15:17:00 -07:00
yassin
a9ab7392ae feat(mcp): show live gateway sessions by AI client and user 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-17 22:15:55 +00:00
mateo-berri
c2fbb11dca fix(license): let a wildcard allowed_features license grant the auto_router feature 2026-09-17 15:08:09 -07:00
kerry
bbde2f8a3a docs(e2e): name the govcloud env vars in the coverage matrix row 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-17 22:07:50 +00:00
Yassin Kortam
356b8d4074
Merge pull request #41444 from zachbernstein-sdx/fix/scim-pagination-count-clamp 
fix(scim): align pagination `count` validation with RFC 7644
 2026-09-17 14:59:22 -07:00
mateo-berri
4669041ae8 fix(a2a): copy registered agent headers so one caller's bearer never reaches the next 
The chat route handed the registry's stored headers dict straight to validate_environment, which wrote the caller's bearer into it, so the next caller of the same agent with no key of their own sent the previous caller's token. The registry lookup now copies the stored headers and validate_environment returns a new dict instead of mutating its input. A regression test drives two completions through one registered agent and asserts the second carries no Authorization and the stored agent is unchanged.
 2026-09-17 14:58:50 -07:00
yassin
4885594a1e fix(proxy): use path-style S3 URLs for dotted Transcribe media buckets 
Virtual-hosted URLs for bucket names containing dots fail TLS verification, so the
media duration fetch failed and completed jobs were charged the eight hour maximum

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
 2026-09-17 21:55:32 +00:00