scriptoriumadmin

scriptoriumadmin synced commits to refs/pull/46707/head at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:12 +00:00

104838d599 refactor: decide the native API format once with plan_route

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 361 commits »

scriptoriumadmin synced commits to refs/pull/46707/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:12 +00:00

d445aeae07 Merge 104838d599 into 8b9cd12a89

104838d599 refactor: decide the native API format once with plan_route

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)

Compare 154 commits »

scriptoriumadmin synced commits to refs/pull/46714/head at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:12 +00:00

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)

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

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

Compare 20 commits »

scriptoriumadmin synced commits to refs/pull/46722/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:12 +00:00

762dd7b766 Merge 108c22115e 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 12 commits »

scriptoriumadmin synced commits to refs/pull/46731/head at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:12 +00:00

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)

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

Compare 21 commits »

scriptoriumadmin synced commits to refs/pull/46739/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:12 +00:00

25873bf3b6 Merge 4a5ce302a3 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 87 commits »

scriptoriumadmin synced commits to refs/pull/46744/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:12 +00:00

56b5e10ef9 Merge f1505863ec into 497f31d43a

f1505863ec feat: add Engy as OpenAI-compatible provider

497f31d43a perf(savings): read deployment pricing from the router's cached model info (#47400)

7b76b2b15f fix(proxy): price the estimated input tokens on a read-timed-out request's spend row (#47435)

93b79d2587 fix(anthropic): apply tool_config cache-control points on chat and /v1/messages (#47394)

Compare 66 commits »

scriptoriumadmin synced commits to refs/pull/46750/head at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:12 +00:00

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)

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

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

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

Compare 19 commits »

scriptoriumadmin synced commits to refs/pull/46750/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:12 +00:00

f4ece263cc Merge ca21e2572f 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/46714/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:12 +00:00

015af0dc74 Merge 42286b9cf7 into f4ece263cc

f4ece263cc Merge ca21e2572f 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)

Compare 98 commits »

scriptoriumadmin synced commits to refs/pull/46716/head at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:12 +00:00

c2e03ade87 refactor: extract execute_messages and execute_responses native executors

104838d599 refactor: decide the native API format once with plan_route

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)

Compare 362 commits »

scriptoriumadmin synced commits to refs/pull/46716/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:12 +00:00

eca9e1a4bc Merge c2e03ade87 into d445aeae07

d445aeae07 Merge 104838d599 into 8b9cd12a89

c2e03ade87 refactor: extract execute_messages and execute_responses native executors

104838d599 refactor: decide the native API format once with plan_route

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

Compare 318 commits »

scriptoriumadmin synced commits to refs/pull/46730/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:12 +00:00

1ffbcc656a Merge 4a3d9107d4 into 90af729933

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)

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

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

Compare 27 commits »

scriptoriumadmin synced commits to refs/pull/46731/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:12 +00:00

2fd2645252 Merge d99b7c4727 into 015af0dc74

015af0dc74 Merge 42286b9cf7 into f4ece263cc

f4ece263cc Merge ca21e2572f 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)

Compare 100 commits »

scriptoriumadmin synced commits to refs/pull/46744/head at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:12 +00:00

f1505863ec feat: add Engy as OpenAI-compatible provider

497f31d43a perf(savings): read deployment pricing from the router's cached model info (#47400)

7b76b2b15f fix(proxy): price the estimated input tokens on a read-timed-out request's spend row (#47435)

93b79d2587 fix(anthropic): apply tool_config cache-control points on chat and /v1/messages (#47394)

f4347d4f50 fix(speech)!: correctly propagate spend logging and usage for Gemini TTS bridge (#44551)

Compare 68 commits »

scriptoriumadmin synced commits to refs/pull/46668/head at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:11 +00:00

5335fde526 test(prometheus): read and write the owned proxy's own database in the expired-key and MCP cells

2c2cc7e2ff Merge origin/main into litellm_prometheus_provider_401_failure_metrics

f4347d4f50 fix(speech)!: correctly propagate spend logging and usage for Gemini TTS bridge (#44551)

6f66b7a201 feat(proxy)!: personal keys inherit MCP server, MCP tool and agent access from the owner's teams (#46293)

ad1f3c5e91 fix(mcp): retry upstream 429 on tools/list and error when every server fails (#46649)

Compare 149 commits »

scriptoriumadmin synced commits to refs/pull/46668/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:11 +00:00

70f33e7cdd Merge 5335fde526 into 93b79d2587

5335fde526 test(prometheus): read and write the owned proxy's own database in the expired-key and MCP cells

93b79d2587 fix(anthropic): apply tool_config cache-control points on chat and /v1/messages (#47394)

2c2cc7e2ff Merge origin/main into litellm_prometheus_provider_401_failure_metrics

f4347d4f50 fix(speech)!: correctly propagate spend logging and usage for Gemini TTS bridge (#44551)

Compare 66 commits »

scriptoriumadmin synced commits to refs/pull/46671/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:11 +00:00

8440d6bbbe Merge 1619f7be92 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/46672/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:11 +00:00

fbd7da321e Merge b2ece49360 into 90af729933

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)

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

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

Compare 25 commits »

scriptoriumadmin synced commits to refs/pull/46674/merge at scriptoriumadmin/litellm from mirror 2026-10-20 05:06:11 +00:00

5c400ec083 Merge bbf5d36a32 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 »