Commit graph

50724 commits

Author SHA1 Message Date
Mateo Wang
80b0a875dc
Merge pull request #41673 from BerriAI/litellm_deprecate_litellm_proxy_entrypoint
feat(cli): deprecate the litellm-proxy entrypoint in favour of lite
2026-09-17 14:54:47 -07:00
kerry
6858663fd2 test: share the video cost expectation helper and trim the gate workflow triggers
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-17 21:51:06 +00:00
kerry
bdd9335116 docs(e2e): list the govcloud bedrock test as a coverage matrix row
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-17 21:51:02 +00:00
mateo-berri
255190ca35 Merge remote-tracking branch 'origin/main' into litellm_fix_image_edits_bracketed_alias 2026-09-17 14:49:54 -07:00
kerry
c988a5002b ci: gate changed tests against a mutated cost map
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-17 21:49:16 +00:00
kerry
ccff1fa95f test: derive the remaining cost-map pins from the catalog entry
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-17 21:49:16 +00:00
kerry
4b45fd5f44 docs(e2e): drop govcloud keys from the contributing starter env
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-17 21:47:21 +00:00
yassin
16500bdf07 fix(proxy): cap Transcribe pricing media downloads by size and concurrency
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-17 21:41:33 +00:00
mateo-berri
36b471ff24 Merge commit '1dd4c13815' into litellm_bedrock_openai_no_cachepoint 2026-09-17 14:36:33 -07:00
yucheng
54bf3e9bd9 Merge remote-tracking branch 'origin/main' into litellm_prompt_injection_async_llm_check 2026-09-17 21:36:27 +00:00
yucheng
b4f71df2d2 refactor(proxy): move llm_api_check moderation dispatch to its own PR
Keeps this branch scoped to running the prompt injection heuristics off the event loop

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-17 21:36:13 +00:00
kerry
5aec6d7bb6 test(e2e): assert govcloud file content round-trips the uploaded record
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-17 21:31:33 +00:00
kerry
733a8a482e ci(auto-merge): stop requiring Greptile and Bugbot on price sync pull requests
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-17 21:28:25 +00:00
Yassin Kortam
bc9f4fec5b
Merge pull request #41542 from BerriAI/litellm_bedrock_realtime_sdk_0_11
fix(bedrock): support aws-sdk-bedrock-runtime 0.10/0.11 in Bedrock Realtime
2026-09-17 14:26:39 -07:00
Yassin Kortam
1b4739c415
Merge pull request #41493 from BerriAI/litellm_bridge_mid_conversation_system_turns
fix(anthropic-bridge): convert mid-conversation system turns to user turns on /v1/messages to chat completions
2026-09-17 14:25:36 -07:00
mateo-berri
ec0e6dd98a feat(cli): deprecate the litellm-proxy entrypoint in favour of lite 2026-09-17 14:05:31 -07:00
mateo-berri
a440d6d452 refactor(cli): rename lite autoroute up/down to start/stop 2026-09-17 14:05:20 -07:00
yassin
664688f337 fix(proxy): do not carry a zero team default cap onto a new member budget row
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-17 21:00:31 +00:00
yassin
6e84ff0cb2 fix(bedrock): keep raw SDK import failure out of the realtime client error
Log the underlying ImportError server side and send the client only the installed
version, the supported range and the install hint

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-17 20:57:28 +00:00
kerry
f5940bcee4 Merge remote-tracking branch 'origin/main' into litellm_remove_brittle_price_pinning_tests 2026-09-17 20:52:32 +00:00
yassin
2801614878 fix(proxy): bill Transcribe jobs by media length and refuse media LiteLLM cannot measure
Amazon Transcribe bills every second of the media file, silence included, while the
transcript's last end_time stops at the last word, so pricing from the transcript
undercharged. After a job completes, download Media.MediaFileUri from S3 with the
proxy's credentials and read its length with libsndfile. Formats libsndfile cannot
read (mp4, m4a, webm, amr) and custom language models under LanguageIdSettings are
refused before signing. The S3 signature is only sent to hosts in the AWS partition

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-17 20:52:10 +00:00
yassin
e73b8d49da fix(proxy): seed a new member budget row from the team default cap
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-17 20:49:58 +00:00
yuneng-jiang
1dd4c13815
Merge pull request #41374 from BerriAI/litellm_fix_guardrail_lifecycle_untimed_entries
fix(ui): keep untimed guardrail entries on the request lifecycle
2026-09-17 13:44:18 -07:00
mateo
8d760679f6 refactor(ui): drop JSDoc example from DocsMenu
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-17 20:35:05 +00:00
yuneng-jiang
efce8b0485
Merge pull request #41373 from BerriAI/litellm_fix_integration_conftest_import
fix(tests): resolve the integration support package without run.py's PYTHONPATH
2026-09-17 13:34:05 -07:00
yassin
a56390ed09 Merge remote-tracking branch 'origin/main' into litellm_bedrock_realtime_sdk_0_11
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

# Conflicts:
#	uv.lock
2026-09-17 20:32:59 +00:00
ryan-crabbe-berri
5396810bb6 fix(management_v1): authorize bulk member budget writes off the writer and reject unschedulable reset windows
The roster the authorization check reads came from the routed reader, so a
replica lagging behind a team-admin demotion could still grant that caller
member-budget writes. Pin that read to the writer, as the model reconcile does.

A budget_duration the reset job can never schedule from, a non-positive one
that leaves the row permanently due or an unparseable one that blew up mid
batch as a 500, is now a 422 naming the row it came from, with nothing written.
The check is the same one /team/member_update and /budget/new already run,
lifted out of validate_budget_duration so both surfaces share it.
2026-09-17 13:31:32 -07:00
yassin
95a2d5088a fix(proxy): keep custom-auth end-user caps under a key default budget
Custom auth callables that already capped an end user keep their cap; the key
default fills only unset limits. The proxy-wide default still reaches an
uncapped custom-auth token, and the missing-budget log strips line breaks

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-17 20:31:26 +00:00
yassin
97c50acc19 fix(proxy): persist a temp budget pair for members without a private budget row
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-17 20:30:29 +00:00
yuneng-jiang
7fb3e73276
Merge pull request #41659 from BerriAI/litellm_/release-version-bump-229f45
chore: bump litellm-proxy-extras 0.4.98 -> 0.4.99
2026-09-17 13:30:19 -07:00
Yuneng Jiang
6544671a31
fix(ui): order each lifecycle phase on its own clock 2026-09-17 13:29:45 -07:00
mateo
ce1a8340c7 refactor(ui): rename HelpLink module to DocsMenu
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-17 20:23:11 +00:00
ryan-crabbe-berri
fbbddb922e
Merge pull request #41488 from BerriAI/litellm_bound_enduser_reset_invalidation
fix(budgets): page end-user cache invalidation after a budget reset
2026-09-17 13:21:23 -07:00
mateo
dcbb77326d chore(proxy): merge origin/main into TypeSafe passthrough
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-17 20:20:16 +00:00
kerry
435ab2ccc0 Merge remote-tracking branch 'origin/main' into litellm_aws_govcloud_partition_gate 2026-09-17 20:16:28 +00:00
mateo
6a76ca0c72 refactor(vertex_ai): remove constant-False is_using_v1beta1_features stub and its dead call sites
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-17 20:16:13 +00:00
kerry
5a5b18550c test(e2e): cover bedrock batch files in govcloud
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-17 20:16:09 +00:00
kerry
fc35b78eb4 ci: drop aws partition hardcode gate
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-17 20:16:07 +00:00
kerry-berri
87650bfe67
Merge pull request #41570 from BerriAI/litellm-providers/price-sync
chore(prices): sync Together AI prices: 6 models, 6 deprecated [sync failed: Google Gemini]
2026-09-17 13:15:52 -07:00
mateo
07d593d831 refactor(interactions): remove expired use_legacy_interactions_schema shim
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-17 20:14:07 +00:00
mateo
54db31726b refactor(prometheus): remove unreferenced metric validators and pretty printers
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-17 20:09:06 +00:00
Yuneng Jiang
139c71f031
bump: litellm-proxy-extras 0.4.98 -> 0.4.99 2026-09-17 13:08:43 -07:00
mateo
5f3fd28f40 chore(ui): remove orphaned useDeleteProject hook and its test
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-17 20:08:08 +00:00
mateo
13d20036cf chore(tests): remove fully commented-out proxy test files and their CI entries
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-17 20:08:08 +00:00
mateo
337bb83ae8 chore(streaming): remove retired ai21/maritalk/baseten/azure raw-bytes handlers and dead palm completion code
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-17 20:07:51 +00:00
mateo
9767063f3d chore(ui): prune stale eslint suppression for key_list.tsx
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-17 20:07:50 +00:00
yassin
67c522fe73 fix(proxy): reject non-finite temp budget increases on team member update
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-17 20:07:33 +00:00
mateo
67b2bdb735 chore(ui): format helpers.ts and prune stale eslint suppressions
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-17 20:07:19 +00:00
mateo
b6c97230cc chore(ui): remove unused access-groups type interfaces
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-17 20:06:41 +00:00
mateo
bec1abd32e refactor(ui): drop unused rolesAllowedToSeeUsage, viewOnlyRoles and isViewOnlyRole exports
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-17 20:06:22 +00:00