scriptoriumadmin

scriptoriumadmin synced commits to refs/pull/46390/head at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:05 +00:00

6a5ce29e89 fix(proxy): list wildcard aliases that route at a word boundary and ids a sibling serves with the same model

73fd10413f fix(proxy): list only wildcard ids that route back to their deployment and catalog model

28a8b70a26 fix(proxy): list nothing for a catch-all over a mid-word wildcard deployment

92b84d76bc fix(proxy): keep namespace and bare catch-all wildcards on routable listings

d14a5aedc0 fix(proxy): list catalog models through routing-prefix wildcard deployments

Compare 6 commits »

scriptoriumadmin synced commits to refs/pull/46391/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:05 +00:00

a4c3f1ea98 Merge 7ab31611a0 into ce4a6cbf5b

ce4a6cbf5b perf(streaming): cut per-chunk pydantic round trips on openai-compatible streams (#47030)

edf4097baf fix(databricks): stream Claude json_schema answers as text on every streaming path (#47424)

6e90733ffc test(perf): gate the gateway's own overhead header, redis latency and postgres load in the perf cases (#47472)

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

Compare 83 commits »

scriptoriumadmin synced commits to refs/pull/46393/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:05 +00:00

6bb1493bb3 Merge 8e6354e56d into d56ff281de

d56ff281de fix(router): key prompt caching affinity on tools and the /v1/messages system prompt (#46411)

fb555b00dc fix(proxy): price a billed failure row at the deployment's own rate like the success path (#47437)

2196943195 fix(proxy): match partial wildcards against prefix-stripped model ids (#46390)

ce4a6cbf5b perf(streaming): cut per-chunk pydantic round trips on openai-compatible streams (#47030)

Compare 91 commits »

scriptoriumadmin synced commits to refs/pull/46395/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:05 +00:00

d17b133a7f Merge 56ff4548e2 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 45 commits »

scriptoriumadmin synced commits to refs/pull/46323/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:04 +00:00

fb38becc19 Merge ee022c00c4 into c82e8244a5

ee022c00c4 feat(providers): add TeamoRouter as an OpenAI-compatible provider

c82e8244a5 fix(count_tokens)!: count tools the way DeepSeek V4 and Qwen3.5 chat templates render them (#47173)

f8f6a01cae feat(ui): show kubernetes pods on the model page (#44666)

f85926a652 feat(router): keep a session on one kubernetes pod (#44393)

Compare 337 commits »

scriptoriumadmin synced commits to refs/pull/46346/head at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:04 +00:00

4b66de0cd7 refactor(rust-bridge): require the native extension

93dd636fe6 ci: cache the built Rust bridge and reuse it in every uv sync job

868cd06ea9 ci: drop the uv sync retry loop and call uv sync directly

90af729933 fix(cost-map): enable function calling + tool choice for fireworks deepseek-v4p1-flash-1017 (#47326)

c82e8244a5 fix(count_tokens)!: count tools the way DeepSeek V4 and Qwen3.5 chat templates render them (#47173)

Compare 451 commits »

scriptoriumadmin synced commits to refs/pull/46321/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:04 +00:00

2646a32cff Merge 3ba429993c into fad31403db

fad31403db chore(pricing): add github_copilot gpt-4.1 deprecation dates (#47492)

3b2cc34c09 feat(dashscope): add separate explicit and implicit cache pricing (#45567)

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)

Compare 95 commits »

scriptoriumadmin synced commits to refs/pull/46323/head at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:04 +00:00

ee022c00c4 feat(providers): add TeamoRouter as an OpenAI-compatible provider

c82e8244a5 fix(count_tokens)!: count tools the way DeepSeek V4 and Qwen3.5 chat templates render them (#47173)

f8f6a01cae feat(ui): show kubernetes pods on the model page (#44666)

f85926a652 feat(router): keep a session on one kubernetes pod (#44393)

6fc60bc00d feat(router): discover kubernetes pods behind a headless service api_base (#44342)

Compare 506 commits »

scriptoriumadmin synced commits to refs/pull/46330/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:04 +00:00

136e18d7e7 Merge 02568c190b 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 33 commits »

scriptoriumadmin synced commits to refs/pull/46348/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:04 +00:00

d7cd26970f Merge 5e519482ee into c80f1c2ec8

c80f1c2ec8 fix(router)!: count native Responses WebSocket turns toward deployment limits and budgets (#45727)

492272a051 fix(azure): reuse the cached Entra token provider on the Responses path (#46421)

7ef92689da fix(azure): route WebRTC client_secrets and calls to the GA v1 realtime API (#47316)

a2773bdcad fix(azure): route WebRTC client_secrets and calls to the GA v1 realtime API (#47316)

Compare 12 commits »

scriptoriumadmin synced commits to refs/pull/46346/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:04 +00:00

eff8106b8d Merge 4b66de0cd7 into 14b8afc227

14b8afc227 Merge 93dd636fe6 into 2cbf7ca4b9

2cbf7ca4b9 Merge 868cd06ea9 into 90af729933

4b66de0cd7 refactor(rust-bridge): require the native extension

93dd636fe6 ci: cache the built Rust bridge and reuse it in every uv sync job

Compare 454 commits »

scriptoriumadmin synced commits to refs/pull/46351/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:04 +00:00

09e053b8af Merge 20194ba385 into 6762d65eb8

6762d65eb8 fix(vertex_ai): price streamed pass-through calls with the regional uplift (#44795)

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)

d07e3c5cd2 feat(cost-map): add together_ai DeepSeek-V4.1-Flash-1017 (#47291)

Compare 11 commits »

scriptoriumadmin synced commits to refs/pull/46371/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:04 +00:00

5061917598 Merge c846e6d693 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 33 commits »

scriptoriumadmin synced commits to refs/pull/46379/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:04 +00:00

5dcda3d0b1 Merge 402f4a2f41 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 33 commits »

scriptoriumadmin synced commits to refs/pull/46292/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:03 +00:00

483f747d79 Merge 0145332b07 into 0e986e78f0

0e986e78f0 Merge 410daafa11 into 4c684c5cfd

4c684c5cfd Merge e45763a2ef into 24a9cd668b

24a9cd668b Merge bfe921760d into d7b28840eb

d7b28840eb test(integration): read stream stall spend rows from the proxy that served them (#47410)

Compare 57 commits »

scriptoriumadmin synced commits to refs/pull/46304/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:03 +00:00

e602ff3592 Merge 7ed8cf39c6 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 33 commits »

scriptoriumadmin synced commits to refs/pull/46308/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:03 +00:00

1f321f735c Merge edb8d8df36 into 3b2cc34c09

3b2cc34c09 feat(dashscope): add separate explicit and implicit cache pricing (#45567)

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)

Compare 99 commits »

scriptoriumadmin synced commits to refs/pull/46268/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:03 +00:00

ee79c3539a Merge 4d42bb3bde 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/46278/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:03 +00:00

6b14be4e69 Merge 39bc0d1d6c 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 33 commits »

scriptoriumadmin synced commits to refs/pull/46283/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:03 +00:00

24a9cd668b Merge bfe921760d into d7b28840eb

d7b28840eb test(integration): read stream stall spend rows from the proxy that served them (#47410)

09e9193514 fix(cost): bill Gemini audio/image/video prompt tokens at the resolved input rate when no modality rate exists (#47373)

1ef59fab8b test(ui-e2e): read the virtual key from its own pre in the Save your Key dialog (#47408)

77bd7d6de8 test(integration): expect the requested model in streamed Responses events on the arize v2 rig (#47407)

Compare 54 commits »