scriptoriumadmin

scriptoriumadmin synced commits to refs/pull/47271/head at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:29 +00:00

f93285a70e test(responses): cover abrupt reasoning stream termination and caching edge cases

scriptoriumadmin synced commits to refs/pull/47271/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:29 +00:00

dcfc7cbc5a Merge f93285a70e into d7620c77a1

d7620c77a1 fix(openai): drop unsupported reasoning effort for gpt-6.1-sol (#43935)

40e4ade6a6 feat(proxy): opt-in self-serve budget edits for key owners on /key/update (#44763)

714d84acb6 fix(cost-map): add fireworks minimax m3.1 flash standard prices (#47371)

037e805b97 build(deps): bump aiohttp to 3.14.5 to clear osv-scan (#47369)

Compare 35 commits »

scriptoriumadmin synced commits to refs/pull/47272/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:29 +00:00

58b1397fab Merge 08f7628cf3 into d7620c77a1

d7620c77a1 fix(openai): drop unsupported reasoning effort for gpt-6.1-sol (#43935)

40e4ade6a6 feat(proxy): opt-in self-serve budget edits for key owners on /key/update (#44763)

714d84acb6 fix(cost-map): add fireworks minimax m3.1 flash standard prices (#47371)

037e805b97 build(deps): bump aiohttp to 3.14.5 to clear osv-scan (#47369)

Compare 33 commits »

scriptoriumadmin synced commits to refs/pull/47274/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:29 +00:00

db7525206e Merge 080145ff81 into b2f0f4d54c

b2f0f4d54c fix(vertex-ai): drop floor deprecation_date from gemini-4-argon (#47404)

365d7342c0 fix(prometheus): label deployment failures with the deployment's provider instead of None (#47384)

1212260ab1 fix(logging): report the cost-map entry billing used in model_map_information (#47182)

c0d88b46c9 fix(azure): cache the remaining per-request Entra credentials and keep token refresh off the event loop (#47348)

Compare 43 commits »

scriptoriumadmin synced commits to refs/pull/47276/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:29 +00:00

400ac6a568 Merge 31cb43bf09 into 89a194bbd0

89a194bbd0 test(integration): hold the upstream until the disconnect is settled before reading its spend row (#47303)

3e18a4b55d fix(router): record cooled deployments on the all-cooled failure row (#47120)

2e427c6247 chore(deps): require anyio>=4.14.0 to rule out the lock-waiter deadlock (#47378)

f07596a5fd fix(helm): stop litellm-helm from injecting placeholder models into every install (#47056)

Compare 37 commits »

scriptoriumadmin synced commits to refs/pull/47278/head at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:29 +00:00

622d018f56 build(make): build make bootstrap venvs on CI's Python 3.12

scriptoriumadmin synced commits to refs/pull/47278/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:29 +00:00

4cb1e52cb9 Merge 622d018f56 into 0e7c4908bb

0e7c4908bb fix(proxy): price the estimated input tokens on a client-cancelled (499) request's spend row (#47436)

1660c8ba1f feat(key_management)!: apply default_key_generate_params.allowed_routes on key generation (#41236)

c6c303a618 fix(batches): apply the Vertex regional endpoint uplift to batch cost (#47466)

783cf06f31 fix(sdk): decide MCP gateway routing without importing the proxy handler (#45961)

Compare 83 commits »

scriptoriumadmin synced commits to refs/pull/47279/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:29 +00:00

9507fa927e Merge b0549b50e7 into b2f0f4d54c

b2f0f4d54c fix(vertex-ai): drop floor deprecation_date from gemini-4-argon (#47404)

365d7342c0 fix(prometheus): label deployment failures with the deployment's provider instead of None (#47384)

1212260ab1 fix(logging): report the cost-map entry billing used in model_map_information (#47182)

c0d88b46c9 fix(azure): cache the remaining per-request Entra credentials and keep token refresh off the event loop (#47348)

Compare 43 commits »

scriptoriumadmin synced commits to refs/pull/47280/head at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:29 +00:00

6c509fc57f fix(rust-bridge): stamp num_retries and timeout on async native failures

213f9f2f0d refactor(rust-bridge): serve the Python cache around native calls

Compare 2 commits »

scriptoriumadmin synced commits to refs/pull/47281/head at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:29 +00:00

c682c05396 refactor(host): declare each hook point once and fold Python hook stages generically

d99b7c4727 fix(rust-bridge): share provider resolution across route dispatch and execution

42286b9cf7 refactor(rust-bridge): detect Python-only features in the catalog instead of Rust declines

ca21e2572f refactor(rust-bridge): decide native routing in the catalog, drop the bypass predicates

ce0dbe60df chore(cost-map): add fireworks minimax m3.1 flash priority prices from the prices api (#47346)

Compare 22 commits »

scriptoriumadmin synced commits to refs/pull/47235/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:28 +00:00

92d0b35970 Merge 9679f4aca6 into b2f0f4d54c

b2f0f4d54c fix(vertex-ai): drop floor deprecation_date from gemini-4-argon (#47404)

365d7342c0 fix(prometheus): label deployment failures with the deployment's provider instead of None (#47384)

1212260ab1 fix(logging): report the cost-map entry billing used in model_map_information (#47182)

c0d88b46c9 fix(azure): cache the remaining per-request Entra credentials and keep token refresh off the event loop (#47348)

Compare 43 commits »

scriptoriumadmin synced commits to refs/pull/47236/head at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:28 +00:00

f692921b04 feat(loadtest): bifrost as a third side of the full-feature run

d4e10685f5 feat(loadtest): s3stub -max-string keeps long runs' logs in memory

0fec539445 feat(loadtest): full-feature mode with recorded-data verification

365257678f fix(gateway): stop hooks pinning connection read buffers for a stream's life

0faa5b2bee fix(gateway): find anthropic stream usage by event name (#47206)

Compare 20 commits »

scriptoriumadmin synced commits to refs/pull/47237/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:28 +00:00

4dce8a4eeb Merge 3f591eeeb2 into 2e427c6247

2e427c6247 chore(deps): require anyio>=4.14.0 to rule out the lock-waiter deadlock (#47378)

f07596a5fd fix(helm): stop litellm-helm from injecting placeholder models into every install (#47056)

d7620c77a1 fix(openai): drop unsupported reasoning effort for gpt-6.1-sol (#43935)

40e4ade6a6 feat(proxy): opt-in self-serve budget edits for key owners on /key/update (#44763)

Compare 39 commits »

scriptoriumadmin synced commits to refs/pull/47250/head at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:28 +00:00

fc456d4ff9 style: single-assignment candidate resolution in bare-name dispatch (LIT010)

4850de6bfa style: ruff-format the mcp shadow gate test

cc9b07f7db fix(mcp): bare-name dispatch cannot resolve through a foreign server's prefix-qualified name

581b7d1a02 fix(vertex-ai): drop floor deprecation_date from gemini-3.8-flash (#47294)

1a77147fad fix(azure): set azure/container code interpreter session price from the azure openai pricing page (#47292)

Compare 14 commits »

scriptoriumadmin synced commits to refs/pull/47233/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:28 +00:00

4d9c6f3569 Merge d158b888b8 into b2f0f4d54c

b2f0f4d54c fix(vertex-ai): drop floor deprecation_date from gemini-4-argon (#47404)

365d7342c0 fix(prometheus): label deployment failures with the deployment's provider instead of None (#47384)

1212260ab1 fix(logging): report the cost-map entry billing used in model_map_information (#47182)

c0d88b46c9 fix(azure): cache the remaining per-request Entra credentials and keep token refresh off the event loop (#47348)

Compare 43 commits »

scriptoriumadmin synced commits to refs/pull/47237/head at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:28 +00:00

3f591eeeb2 style: scope pyright disables to the untyped fields-set call site (basedpyright ceiling)

61c200ac1e style: annotate the self-update payload as a read-only object mapping (reportExplicitAny)

bc14992545 test: assert the allowed self-edit path returns clean (test-quality TQ001)

582f337aad style: split the aliased AbstractSet import (ruff I001)

90094d53c7 style: annotate self-update gate params with read-only views (LIT001)

Compare 18 commits »

scriptoriumadmin synced commits to refs/pull/47239/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:28 +00:00

f6337ce0d5 Merge 2bfcbaae04 into b40bd7bf03

b40bd7bf03 Merge pull request #47344 from BerriAI/litellm_backport_47067_stable_1_104_x

c47b760253 test(proxy): import Final in the line's batch endpoint tests

d11f438e3d bump: version 1.104.4

e87e661118 fix(proxy): authorize the public name of a team-scoped model on batch retrieve/cancel (#47067)

Compare 5 commits »

scriptoriumadmin synced commits to refs/pull/47249/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:28 +00:00

46ab0acf28 Merge 2ff4574d08 into 8b9cd12a89

8b9cd12a89 test: catch regressions in the validation lines #44798 added (#47420)

3fa1587f43 fix(logging): do not stamp a provider handoff when pre_call runs for a proxy-only failure (#47456)

f98168e73d test(e2e/perf): read the memory baseline after a one minute warm-up (#47455)

b2eda10bef perf(router): resolve deployment usage limits once per deployment instead of every request (#47393)

Compare 70 commits »

scriptoriumadmin synced commits to refs/pull/47245/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:28 +00:00

057338492c Merge eb26ac4756 into da80552897

da80552897 test(translation): add sonnet 5.5 converse and gemini direct cross-model mid rows (#47328)

c4d24ec2f1 test(integration): remove BUG skips for 3 tests that pass on main (#47364)

daa133da5c fix(mcp)!: bill both model calls of a chat completions MCP auto-execute on one spend row (#47422)

7b82b2a3c3 feat(bedrock): route token counts from model metadata (#47441)

Compare 95 commits »

scriptoriumadmin synced commits to refs/pull/47246/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:28 +00:00

772a0fb8eb Merge 1cd9e5a6f4 into 3fa1587f43

3fa1587f43 fix(logging): do not stamp a provider handoff when pre_call runs for a proxy-only failure (#47456)

f98168e73d test(e2e/perf): read the memory baseline after a one minute warm-up (#47455)

b2eda10bef perf(router): resolve deployment usage limits once per deployment instead of every request (#47393)

ece1627408 fix(vertex-ai): drop floor deprecation_date from gemini-3.8-live (#47447)

Compare 69 commits »