scriptoriumadmin
  • Joined on 2026-03-01
scriptoriumadmin synced commits to refs/pull/40983/merge at scriptoriumadmin/litellm from mirror 2026-10-02 02:13:07 +00:00
321be01877 fix(caching): write the response-cache SET to Redis at once instead of on the post-call batch (#43973)
f67caac8d4 feat(ui): filter tags by name and description on the Tag Management page (#42949)
ae60fd1b2f feat(providers): add Cortecs as an OpenAI-compatible provider (#43872)
424bfd8758 feat(e2e): record each e2e test's steps, starting with ProxyClient (#42393)
Compare 56 commits »
scriptoriumadmin synced commits to refs/pull/41004/merge at scriptoriumadmin/litellm from mirror 2026-10-02 02:13:07 +00:00
6f123b7083 test(proxy): migrate DB and Redis backed proxy tests into tests/integration (#43996)
d96477abce fix(proxy): preserve decision request bodies under token limits (#43920)
c2ae483782 fix(bedrock): add beta for thinking display updates (#43832)
4b06d04334 test(anthropic): native /v1/messages reasoning integration tests built on a captured Claude Code request (#43361)
Compare 72 commits »
scriptoriumadmin synced commits to refs/pull/40924/merge at scriptoriumadmin/litellm from mirror 2026-10-02 02:13:07 +00:00
48b653bca1 Merge remote-tracking branch 'origin/main' into litellm_tencent_ui_dropdown
6f123b7083 test(proxy): migrate DB and Redis backed proxy tests into tests/integration (#43996)
d96477abce fix(proxy): preserve decision request bodies under token limits (#43920)
c2ae483782 fix(bedrock): add beta for thinking display updates (#43832)
Compare 71 commits »
scriptoriumadmin synced commits to refs/pull/40965/merge at scriptoriumadmin/litellm from mirror 2026-10-02 02:13:07 +00:00
3a11192f68 fix(cost-map): reprice fireworks deepseek v4.1 flash to the 2026-10-01 pricing update (#44024)
b4bb2a77a2 test: inject the HIBP client and the MCP loop clock so two backend tests stop flaking (#44007)
5107f205a0 refactor: clean up fresh tech debt from 2026-09-30 (#43993)
0980f756bd fix(guardrails): scan Responses API input in Azure Text Moderation (#43965)
Compare 26 commits »
scriptoriumadmin synced commits to refs/pull/40966/merge at scriptoriumadmin/litellm from mirror 2026-10-02 02:13:07 +00:00
3a11192f68 fix(cost-map): reprice fireworks deepseek v4.1 flash to the 2026-10-01 pricing update (#44024)
b4bb2a77a2 test: inject the HIBP client and the MCP loop clock so two backend tests stop flaking (#44007)
5107f205a0 refactor: clean up fresh tech debt from 2026-09-30 (#43993)
0980f756bd fix(guardrails): scan Responses API input in Azure Text Moderation (#43965)
Compare 26 commits »
scriptoriumadmin synced commits to refs/pull/40998/merge at scriptoriumadmin/litellm from mirror 2026-10-02 02:13:07 +00:00
b4bb2a77a2 test: inject the HIBP client and the MCP loop clock so two backend tests stop flaking (#44007)
5107f205a0 refactor: clean up fresh tech debt from 2026-09-30 (#43993)
0980f756bd fix(guardrails): scan Responses API input in Azure Text Moderation (#43965)
19842da059 fix(guardrails): scan Responses API input in Azure Prompt Shield (#43786)
Compare 26 commits »
scriptoriumadmin synced commits to refs/pull/40999/merge at scriptoriumadmin/litellm from mirror 2026-10-02 02:13:07 +00:00
321be01877 fix(caching): write the response-cache SET to Redis at once instead of on the post-call batch (#43973)
f67caac8d4 feat(ui): filter tags by name and description on the Tag Management page (#42949)
ae60fd1b2f feat(providers): add Cortecs as an OpenAI-compatible provider (#43872)
424bfd8758 feat(e2e): record each e2e test's steps, starting with ProxyClient (#42393)
Compare 56 commits »
scriptoriumadmin synced commits to refs/pull/40698/merge at scriptoriumadmin/litellm from mirror 2026-10-02 02:13:06 +00:00
a308a8e579 feat(guardrails): honor litellm_params.timeout in every HTTP guardrail (#43134)
ae05f7d2c1 test(e2e): typed per-test metadata for the e2e suite (#42044)
321be01877 fix(caching): write the response-cache SET to Redis at once instead of on the post-call batch (#43973)
f67caac8d4 feat(ui): filter tags by name and description on the Tag Management page (#42949)
Compare 58 commits »
scriptoriumadmin synced commits to refs/pull/40775/head at scriptoriumadmin/litellm from mirror 2026-10-02 02:13:06 +00:00
6daf0b7136 fix(bedrock): refuse or drop a non-string reasoning_effort before the native chat completions call
2f27eb3f36 test(bedrock): harden the runtime chat completions audit cells
4ee7ff4315 test(bedrock): audit the native GPT chat completions route on the integration rig
578f26edba fix(bedrock): route model_id overrides to Converse and never send an empty bearer natively
dae29c138b fix(bedrock): route overlong GPT version digits to Converse and send native chat completions to the runtime endpoint
Compare 25 commits »
scriptoriumadmin synced commits to refs/pull/40739/merge at scriptoriumadmin/litellm from mirror 2026-10-02 02:13:06 +00:00
ae05f7d2c1 test(e2e): typed per-test metadata for the e2e suite (#42044)
321be01877 fix(caching): write the response-cache SET to Redis at once instead of on the post-call batch (#43973)
f67caac8d4 feat(ui): filter tags by name and description on the Tag Management page (#42949)
ae60fd1b2f feat(providers): add Cortecs as an OpenAI-compatible provider (#43872)
Compare 64 commits »
scriptoriumadmin synced commits to refs/pull/40784/merge at scriptoriumadmin/litellm from mirror 2026-10-02 02:13:06 +00:00
4b1d9bf148 test(e2e): keep 1ms-timeout deployments off the provider cache (#44082)
03743ae020 feat(proxy): add LITELLM_DISABLE_LAZY_ROUTES to register optional routers at startup (#43911)
46196339d2 feat(ui): add test trace, tracing key and otel endpoints to tracing setup (#44090)
0f6a06a6b9 feat: add litellm.agent() to run claude code, codex, opencode and deep agents through the ai gateway (#43885)
Compare 89 commits »
scriptoriumadmin synced commits to refs/pull/40803/merge at scriptoriumadmin/litellm from mirror 2026-10-02 02:13:06 +00:00
ae05f7d2c1 test(e2e): typed per-test metadata for the e2e suite (#42044)
321be01877 fix(caching): write the response-cache SET to Redis at once instead of on the post-call batch (#43973)
f67caac8d4 feat(ui): filter tags by name and description on the Tag Management page (#42949)
ae60fd1b2f feat(providers): add Cortecs as an OpenAI-compatible provider (#43872)
Compare 57 commits »
scriptoriumadmin synced commits to refs/pull/40852/merge at scriptoriumadmin/litellm from mirror 2026-10-02 02:13:06 +00:00
5107f205a0 refactor: clean up fresh tech debt from 2026-09-30 (#43993)
0980f756bd fix(guardrails): scan Responses API input in Azure Text Moderation (#43965)
19842da059 fix(guardrails): scan Responses API input in Azure Prompt Shield (#43786)
6d7d183a80 feat(lens): investigate sampled traces and retain batch results (#43942)
Compare 42 commits »
scriptoriumadmin synced commits to refs/pull/40859/merge at scriptoriumadmin/litellm from mirror 2026-10-02 02:13:06 +00:00
321be01877 fix(caching): write the response-cache SET to Redis at once instead of on the post-call batch (#43973)
f67caac8d4 feat(ui): filter tags by name and description on the Tag Management page (#42949)
ae60fd1b2f feat(providers): add Cortecs as an OpenAI-compatible provider (#43872)
424bfd8758 feat(e2e): record each e2e test's steps, starting with ProxyClient (#42393)
Compare 71 commits »
scriptoriumadmin synced commits to refs/pull/40775/merge at scriptoriumadmin/litellm from mirror 2026-10-02 02:13:06 +00:00
6daf0b7136 fix(bedrock): refuse or drop a non-string reasoning_effort before the native chat completions call
d729f975aa bump: litellm-enterprise 0.1.72 -> 0.1.73, litellm-proxy-extras 0.4.103 -> 0.4.104 (#44126)
2b51f2f941 fix(ui): split the KeyActivityPanel condition chains to bring the lint budget back under its ceiling (#44114)
1eadd7aba0 fix(ui): label lens trace services as agents (#44116)
Compare 85 commits »
scriptoriumadmin synced commits to refs/pull/40825/merge at scriptoriumadmin/litellm from mirror 2026-10-02 02:13:06 +00:00
6f123b7083 test(proxy): migrate DB and Redis backed proxy tests into tests/integration (#43996)
d96477abce fix(proxy): preserve decision request bodies under token limits (#43920)
c2ae483782 fix(bedrock): add beta for thinking display updates (#43832)
4b06d04334 test(anthropic): native /v1/messages reasoning integration tests built on a captured Claude Code request (#43361)
Compare 70 commits »
scriptoriumadmin synced commits to refs/pull/40690/merge at scriptoriumadmin/litellm from mirror 2026-10-02 02:13:06 +00:00
03743ae020 feat(proxy): add LITELLM_DISABLE_LAZY_ROUTES to register optional routers at startup (#43911)
46196339d2 feat(ui): add test trace, tracing key and otel endpoints to tracing setup (#44090)
0f6a06a6b9 feat: add litellm.agent() to run claude code, codex, opencode and deep agents through the ai gateway (#43885)
610576d247 fix(bedrock): accept Converse messages with no content key (#43936)
Compare 4591 commits »
scriptoriumadmin synced commits to refs/pull/40710/merge at scriptoriumadmin/litellm from mirror 2026-10-02 02:13:06 +00:00
ac8c5aa4b9 fix(cost-map): add perplexity, openrouter, voyage and nebius models and fix registry metadata (#43907)
ba8cd1ee31 fix(router): keep silent_model out of embedding provider requests (#44064)
65a316fc92 ci(circleci): test Redis behavior against local Redis and print short tracebacks (#44062)
0da00d4b2e test(e2e): bill Sail windows that synchronous calls can still use (#44058)
Compare 51 commits »
scriptoriumadmin synced commits to refs/pull/40712/head at scriptoriumadmin/litellm from mirror 2026-10-02 02:13:06 +00:00
162d60cf38 style(google_genai): ruff format and tz-aware fixed timestamp
849baa8f8f chore(google_genai): shorten comments
9d40dc7b26 perf(google_genai): read only the two location keys instead of dumping every param
b67dbfa948 test(google_genai): use a fixed timestamp in the logging helper
8c2f3616cb test: keep the vertex_location assertion message on one line for ruff format
Compare 158 commits »
scriptoriumadmin synced commits to refs/pull/40712/merge at scriptoriumadmin/litellm from mirror 2026-10-02 02:13:06 +00:00
162d60cf38 style(google_genai): ruff format and tz-aware fixed timestamp
849baa8f8f chore(google_genai): shorten comments
3a11192f68 fix(cost-map): reprice fireworks deepseek v4.1 flash to the 2026-10-01 pricing update (#44024)
9d40dc7b26 perf(google_genai): read only the two location keys instead of dumping every param
Compare 50 commits »