scriptoriumadmin

scriptoriumadmin synced commits to refs/pull/29878/merge at scriptoriumadmin/litellm from mirror 2026-11-05 07:38:28 +00:00

a0adc810e8 Merge e81a958e90 into 44b85d0c5c

44b85d0c5c fix(cost_calculator): keep regional and speed multipliers for per-call custom prices and log the billed per-call entry (#50063)

b401ac6aaf fix(cost): bill Batch cached tokens at the Standard cache price when a row has no Batch cache price (#50062)

85fdea0fd1 fix(guardrails): apply guardrail masks to Bedrock InvokeModel Claude requests and replies (#49947)

74783d38ea fix(github_copilot): let per-user connections work with a custom GitHub client ID (#50116)

Compare 43 commits »

scriptoriumadmin synced commits to refs/pull/30325/merge at scriptoriumadmin/litellm from mirror 2026-11-05 07:38:28 +00:00

c53595957c Merge 66c930a230 into 5c60824024

5c60824024 test(providers): expect 503 server_is_overloaded for an upstream overload (#50154)

71fc204495 test(routing): expect 503 server_is_overloaded for an upstream overload (#50155)

c5da69cd13 feat(ui): show model deprecation banner on the models page (#50080)

429f814a04 fix(cost_map): fill missing Claude capability fields from the family baseline (#49815)

Compare 64 commits »

scriptoriumadmin synced commits to refs/pull/15071/merge at scriptoriumadmin/litellm from mirror 2026-11-05 07:38:28 +00:00

d2895c3dd7 Merge 8911a14eaa into df78b16941

df78b16941 feat(openai): bill gov.api.openai.com FedRAMP endpoint with 1.1x uplift (#49951)

83be155b65 feat(cost-map): add together_ai/moonshotai/Kimi-K3.1-Pro from the Together models API (#50069)

f56f0f0809 fix(gemini): point gemini-2.5-pro and gemini-2.5-flash at the models Google reroutes them to (#50064)

03c26c6e07 chore(cost-map): rolling registry sync for xAI, Fireworks, Azure and Gemini (#50028)

Compare 15 commits »

scriptoriumadmin synced commits to refs/pull/30051/merge at scriptoriumadmin/litellm from mirror 2026-11-05 07:38:28 +00:00

c65fd0d9af Merge 2147f1cb34 into 574f06594b

574f06594b chore(cost-map): add fireworks kimi k3.1 pro serverless pricing (#50095)

8ab0321816 fix(proxy): charge a video's provider-reported cost once, on the first poll that sees it completed (#49824)

e69da69891 feat: update EmpirioLabs models in model_prices_and_context_window.json (#49980)

e9e745797c ci: run the OSV scan and unit tests on stable, rc and lts branches (#50086)

Compare 61 commits »

scriptoriumadmin synced commits to refs/pull/29456/merge at scriptoriumadmin/litellm from mirror 2026-11-05 07:38:28 +00:00

2c96a382ce Merge 56d15266e4 into c5da69cd13

c5da69cd13 feat(ui): show model deprecation banner on the models page (#50080)

429f814a04 fix(cost_map): fill missing Claude capability fields from the family baseline (#49815)

dc741a6e16 fix(ui): let team admins edit models on team service account keys (#49970)

42b4cfc5bf fix(nvidia_riva): send the api key exactly once by calling riva over grpc directly (#50140)

Compare 89 commits »

scriptoriumadmin synced commits to refs/pull/29290/merge at scriptoriumadmin/litellm from mirror 2026-11-05 07:38:28 +00:00

5ae585549f Merge 7bb7b3d1c5 into 4e769d153a

4e769d153a fix(auth): align cloud credential loading and expiry with the Python SDKs (#49589)

97aae6c65e fix(bedrock): remove GovCloud Kimi K3 bedrock_mantle rows (#50117)

d38c5143ae test(skills): drop the archive rejection test whose zip-byte ids differ across xdist workers (#50118)

732a50318b feat(proxy): authenticate billing metrics with a cognito bearer token (#49852)

Compare 36 commits »

scriptoriumadmin synced commits to main at scriptoriumadmin/litellm from mirror 2026-11-05 07:38:25 +00:00

3f4dc93b40 feat(skills)!: add portable Agent Skills Hub API (#50159)

b4a8bc715f test(translation): expect thinking usage fields on Bedrock responses (#50181)

728c687418 fix(mistral): a named tool_choice is dropped, the model picks any tool (#39737)

3577aa2d94 test(translation): expect thinking usage fields on Bedrock messages (#50179)

74493f39fb test(translation): expect thinking usage fields on Bedrock chat (#50175)

Compare 73 commits »

scriptoriumadmin synced new reference lts/1.108.x to scriptoriumadmin/litellm from mirror 2026-11-05 07:38:25 +00:00

scriptoriumadmin synced commits to lts/1.108.x at scriptoriumadmin/litellm from mirror 2026-11-05 07:38:25 +00:00

scriptoriumadmin synced commits to litellm_zscaler-last-user-turn at scriptoriumadmin/litellm from mirror 2026-11-05 07:38:24 +00:00

scriptoriumadmin synced new reference litellm_zscaler-last-user-turn to scriptoriumadmin/litellm from mirror 2026-11-05 07:38:24 +00:00

scriptoriumadmin synced commits to litellm_vertex_root_union_json_schema at scriptoriumadmin/litellm from mirror 2026-11-05 07:38:24 +00:00

2add6a0629 fix(vertex-ai): keep parameters for Vertex batch rows and Vertex countTokens

47d9c8bab8 fix(vertex-ai): resolve long root $ref chains without recursion

Compare 2 commits »

scriptoriumadmin synced new reference litellm_vertex-cache-prefix-47046 to scriptoriumadmin/litellm from mirror 2026-11-05 07:38:24 +00:00

scriptoriumadmin synced commits to litellm_websearch_capped_turn_answer at scriptoriumadmin/litellm from mirror 2026-11-05 07:38:24 +00:00

3180391bf6 chore: merge main into litellm_websearch_capped_turn_answer

83be155b65 feat(cost-map): add together_ai/moonshotai/Kimi-K3.1-Pro from the Together models API (#50069)

f56f0f0809 fix(gemini): point gemini-2.5-pro and gemini-2.5-flash at the models Google reroutes them to (#50064)

03c26c6e07 chore(cost-map): rolling registry sync for xAI, Fireworks, Azure and Gemini (#50028)

80b18d165b chore(proxy): use neutral example names for baggage tag mappings (#50011)

Compare 283 commits »

scriptoriumadmin synced commits to litellm_vertex-cache-prefix-47046 at scriptoriumadmin/litellm from mirror 2026-11-05 07:38:24 +00:00

scriptoriumadmin synced commits to litellm_test_model_endpoint at scriptoriumadmin/litellm from mirror 2026-11-05 07:38:23 +00:00

262dc5f5d7 fix(health): cancel the provider call when the during-call hook rejects a turn, hand /v1/messages replies to the post-call hook as the dict they are

0f7ed4a169 fix(health): run during-call and post-call hooks on /health/test_model turns, match 72 as a whole number in Fahrenheit

53d3f13297 Merge remote-tracking branch 'origin/main' into litellm_test_model_endpoint

42b4cfc5bf fix(nvidia_riva): send the api key exactly once by calling riva over grpc directly (#50140)

5e91bc8e86 fix(ui): send a team admin's member key edits on the first save (#50007)

Compare 78 commits »

scriptoriumadmin synced new reference litellm_translation_sync_20261104_coverage to scriptoriumadmin/litellm from mirror 2026-11-05 07:38:23 +00:00

scriptoriumadmin synced commits to litellm_user_new_custom_id_validation at scriptoriumadmin/litellm from mirror 2026-11-05 07:38:23 +00:00

dc44926af1 fix(scim): preserve opaque IDs during user provisioning

3bf3c7db6e fix(users): preserve retries for existing-user upserts

feeb401896 fix(users): return precise conflicts without retrying them

5ad27b1e61 fix(users): validate custom IDs and reject concurrent duplicate creation

44b85d0c5c fix(cost_calculator): keep regional and speed multipliers for per-call custom prices and log the billed per-call entry (#50063)

Compare 50 commits »

scriptoriumadmin synced new reference litellm_store_prompts_key_team to scriptoriumadmin/litellm from mirror 2026-11-05 07:38:23 +00:00

scriptoriumadmin synced commits to litellm_topbar_rebuild_evidence_1104 at scriptoriumadmin/litellm from mirror 2026-11-05 07:38:23 +00:00

87ca67b860 docs: capture transparent workspace trigger

4a80d8a253 docs: verify compact header and text-only switcher

525ccc3f0b docs: capture simplified workspace menu

a91f05035c docs: capture selected Aria icon

95174dab3f docs: capture final Aria workspace and notification hierarchy

Compare 5 commits »