scriptoriumadmin

scriptoriumadmin synced commits to refs/pull/46648/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:10 +00:00

9cb0b9458a Merge 5376a5c684 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/46650/head at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:10 +00:00

dd1c9ec2ec feat(proxy)!: classify agent key requests as agent spans in logs

scriptoriumadmin synced commits to refs/pull/46653/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:10 +00:00

38de2cc901 Merge cd61746354 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 13 commits »

scriptoriumadmin synced commits to refs/pull/46654/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:10 +00:00

c668d14fac Merge e698b09442 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 13 commits »

scriptoriumadmin synced commits to refs/pull/46655/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:10 +00:00

beb5d39b03 Merge 8e6a54cfb3 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/46661/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:10 +00:00

9fc6730700 Merge 607d3fff6f into c82e8244a5

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 24 commits »

scriptoriumadmin synced commits to refs/pull/46626/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:09 +00:00

7c4331c5b3 Merge a0bfdc85d3 into 0675c22d56

0675c22d56 refactor(rust): inline chat provider resolution (#47218)

97e9300577 refactor(rust): inline Messages provider resolution (#47217)

bfcb9a028f refactor(rust): update OCR route orchestration (#47216)

ede6d97785 refactor(rust): separate responses provider resolution (#47215)

Compare 18 commits »

scriptoriumadmin synced commits to refs/pull/46635/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:09 +00:00

7412ede90b Merge 7fd7d43973 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/46595/head at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:09 +00:00

b1a8c0515a feat(rust): serve Bedrock Mantle responses natively

870647a186 feat(rust): serve Databricks GPT responses natively

a59efcb4e7 feat(rust): serve Fireworks AI responses natively

b31b55075b feat(rust): serve xAI and hosted vLLM responses natively

7d92a021fe feat(rust): serve Azure OpenAI responses natively

Compare 15 commits »

scriptoriumadmin synced commits to refs/pull/46595/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:09 +00:00

3486f005a6 Merge b1a8c0515a into 37162b8765

37162b8765 Merge 870647a186 into da743227ec

da743227ec Merge a59efcb4e7 into 9c3a8ea881

9c3a8ea881 Merge b31b55075b into f5c33663f7

f5c33663f7 Merge 7d92a021fe into ce6afebeda

Compare 22 commits »

scriptoriumadmin synced commits to refs/pull/46599/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:09 +00:00

b344797bda Merge 0b5376db36 into 2d181e6633

0b5376db36 fix(proxy): strip credential names and URL-encode credential routes in UI

2d181e6633 fix(token_counter): count DeepSeek V4 text with DeepSeek's own tokenizer (#47353)

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)

Compare 84 commits »

scriptoriumadmin synced commits to refs/pull/46605/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:09 +00:00

b01796eb96 Merge 64b8d8a8d3 into e6b253bdab

e6b253bdab Merge c682c05396 into 2fd2645252

2fd2645252 Merge d99b7c4727 into 015af0dc74

015af0dc74 Merge 42286b9cf7 into f4ece263cc

f4ece263cc Merge ca21e2572f into da80552897

Compare 104 commits »

scriptoriumadmin synced commits to refs/pull/46608/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:09 +00:00

2cc4b3ffd3 Merge a7f248c28e into 2d181e6633

2d181e6633 fix(token_counter): count DeepSeek V4 text with DeepSeek's own tokenizer (#47353)

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)

Compare 90 commits »

scriptoriumadmin synced commits to refs/pull/46625/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:09 +00:00

c308e96f75 Merge 7c8da00db3 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 96 commits »

scriptoriumadmin synced commits to refs/pull/46590/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:09 +00:00

37162b8765 Merge 870647a186 into da743227ec

da743227ec Merge a59efcb4e7 into 9c3a8ea881

9c3a8ea881 Merge b31b55075b into f5c33663f7

f5c33663f7 Merge 7d92a021fe into ce6afebeda

ce6afebeda Merge a2bbc45c71 into 39a5c3b8a2

Compare 20 commits »

scriptoriumadmin synced commits to refs/pull/46593/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:09 +00:00

028d83c379 Merge 3b0e9a8784 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 13 commits »

scriptoriumadmin synced commits to refs/pull/46599/head at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:09 +00:00

0b5376db36 fix(proxy): strip credential names and URL-encode credential routes in UI

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

6c4c134f23 fix(secret_managers)!: resolve oidc/file and oidc/env refs in admin-configured api_key per request (#47341)

923b7d1784 test(integration): read router cooldown failure rows from the proxy that served them (#47457)

ca329a7f13 chore(bedrock): add Model EOL deprecation dates for Palmyra X4, X5 and Pegasus v1.2 (#47462)

Compare 429 commits »

scriptoriumadmin synced commits to refs/pull/46601/head at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:09 +00:00

dc0b5ec510 fix(anthropic): reject a false, null or empty thinking budget on adaptive Claude

8b3d991712 Merge remote-tracking branch 'origin/main' into litellm_reasoning_effort_levels_every_route

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 115 commits »

scriptoriumadmin synced commits to refs/pull/46605/head at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:09 +00:00

64b8d8a8d3 refactor(rust-bridge): serve the Python cache around native calls

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

Compare 23 commits »

scriptoriumadmin synced commits to refs/pull/46610/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:09 +00:00

b29047e5b1 Merge 58b5df4aa0 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 »