scriptoriumadmin
  • Joined on 2026-03-01
scriptoriumadmin synced commits to refs/pull/48592/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:09 +00:00
1218776180 refactor(proxy): inject deployment warning ignores through repositories
85979d0125 test(rust): include NativeDatabase in bridge API surface
Compare 117 commits »
scriptoriumadmin synced commits to refs/pull/48597/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:09 +00:00
87cb2f5b28 linting issues fixed
444423a5ca fix(cost): bill a deployment's per-second rates on native Anthropic /v1/messages (#42417)
cd42694b48 feat(providers): add Kyma API as an OpenAI-compatible provider (#48756)
3e3362d461 fix(cohere): price native Cohere embed calls on Foundry relays and the Cohere passthrough (#48978)
Compare 182 commits »
scriptoriumadmin synced commits to refs/pull/48597/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:09 +00:00
87cb2f5b28 linting issues fixed
scriptoriumadmin synced commits to refs/pull/48583/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:09 +00:00
9a68573e9b fix(responses): keep each Codex tool once when its tool list repeats across turns (#49006)
3c1eb73a06 fix(proxy)!: list every priced Vertex family under a vertex_ai/* grant (#41959)
65d912fc2e feat(responses): support Codex client tool_search on Anthropic and other bridged providers (#48972)
ec7162aea2 fix(cost_map): mark fireworks_ai/minimax-m3 as vision and pin capabilities verified against live calls (#43390)
Compare 228 commits »
scriptoriumadmin synced commits to refs/pull/48580/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:08 +00:00
ccc56d27ad fix(azure): add batch prices to the unversioned o3, o4-mini, o3-mini, gpt-4o and gpt-4o-mini rows (#49182)
b91fc92b6d fix(router): cap the default OTPM reservation and reconcile token counters after each call (#49054)
342ce6ae4a feat(zai): support response_format and max_completion_tokens, add glm-5v-turbo pricing (#48335)
733cfeba93 fix(cost): bill a provider reported usage.cost on every path unless the deployment is priced (#48953)
Compare 207 commits »
scriptoriumadmin synced commits to refs/pull/48579/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:08 +00:00
d8f162ea22 fix(guardrails): allow MCP call modes on the generic guardrail API (#48060)
1a2b443a32 ci: run the extensions integration group with 48 workers (#49134)
8d441ebc15 test(otel): give the Langfuse destination tests the otel callback's stdout exporter (#49129)
4ce724e3df fix(caching): key cached async clients by a per-loop token instead of id(loop) (#48877)
Compare 222 commits »
scriptoriumadmin synced commits to refs/pull/48575/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:07 +00:00
d8f162ea22 fix(guardrails): allow MCP call modes on the generic guardrail API (#48060)
1a2b443a32 ci: run the extensions integration group with 48 workers (#49134)
8d441ebc15 test(otel): give the Langfuse destination tests the otel callback's stdout exporter (#49129)
4ce724e3df fix(caching): key cached async clients by a per-loop token instead of id(loop) (#48877)
Compare 143 commits »
scriptoriumadmin synced commits to refs/pull/48553/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:05 +00:00
d8f162ea22 fix(guardrails): allow MCP call modes on the generic guardrail API (#48060)
1a2b443a32 ci: run the extensions integration group with 48 workers (#49134)
8d441ebc15 test(otel): give the Langfuse destination tests the otel callback's stdout exporter (#49129)
4ce724e3df fix(caching): key cached async clients by a per-loop token instead of id(loop) (#48877)
Compare 134 commits »
scriptoriumadmin synced commits to refs/pull/48573/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:05 +00:00
2e5cc9e08f fix(proxy)!: honor litellm_settings.drop_params for Claude Code and Codex requests (#49058)
4a4c9cf7e3 feat(guardrails): opt-in response_masked_data on PANW Prisma AIRS block (#46219)
e63fc85b7b fix(anthropic): keep Mistral thinking text on streaming /v1/messages (#49059)
c213234783 feat(vertex_ai)!: use HTTP/2 httpx client for search_api vector store (#40631)
Compare 214 commits »
scriptoriumadmin synced commits to refs/pull/48542/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:04 +00:00
ccc56d27ad fix(azure): add batch prices to the unversioned o3, o4-mini, o3-mini, gpt-4o and gpt-4o-mini rows (#49182)
b91fc92b6d fix(router): cap the default OTPM reservation and reconcile token counters after each call (#49054)
342ce6ae4a feat(zai): support response_format and max_completion_tokens, add glm-5v-turbo pricing (#48335)
733cfeba93 fix(cost): bill a provider reported usage.cost on every path unless the deployment is priced (#48953)
Compare 324 commits »
scriptoriumadmin synced commits to refs/pull/48548/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:04 +00:00
67ae3fb527 fix(websearch)!: keep the provider prefix on the agentic follow-up model (#38885)
0cf2bb7296 fix(openai): warn when the GPT-5 reasoning effort gate drops a level under drop_params (#47761)
71babd931b fix(llms): move later developer messages for models declared system-first (#48897)
d037d86a94 fix(token_counter)!: keep a loaded Hugging Face tokenizer when a slower download fails (#48916)
Compare 141 commits »
scriptoriumadmin synced commits to refs/pull/48549/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:04 +00:00
ccc56d27ad fix(azure): add batch prices to the unversioned o3, o4-mini, o3-mini, gpt-4o and gpt-4o-mini rows (#49182)
b91fc92b6d fix(router): cap the default OTPM reservation and reconcile token counters after each call (#49054)
342ce6ae4a feat(zai): support response_format and max_completion_tokens, add glm-5v-turbo pricing (#48335)
733cfeba93 fix(cost): bill a provider reported usage.cost on every path unless the deployment is priced (#48953)
Compare 249 commits »
scriptoriumadmin synced commits to refs/pull/48541/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:03 +00:00
c98641fd5a feat(dashscope)!: derive protocol bases from one domain (#47812)
06cdee91da fix(guardrails): scan and rewrite streamed /v1/completions under post_call guardrails (#49035)
961fabbb76 feat(secret_managers): resolve oidc/google api_key references per request (#47703)
6cdb9959df feat(router): opt in to non-chat deployment filtering (#46257)
Compare 70 commits »
scriptoriumadmin synced commits to refs/pull/48535/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:02 +00:00
77064d6c70 feat(vector_stores): add OpenSearch k-NN search as a vector store provider (#47759)
be6d082bdc fix(anthropic)!: send /v1/messages PDF documents to OpenAI-shaped providers as file parts (#47166)
c13ecb3085 fix(exceptions)!: honor status code when mapping OpenAI invalid_request_error exceptions (#32537)
cd58014315 feat(soniox): add realtime speech-to-text on /v1/realtime (#44822)
Compare 160 commits »
scriptoriumadmin synced commits to refs/pull/48520/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:02 +00:00
cd42694b48 feat(providers): add Kyma API as an OpenAI-compatible provider (#48756)
3e3362d461 fix(cohere): price native Cohere embed calls on Foundry relays and the Cohere passthrough (#48978)
e7d3b24d7c fix(logging): mark mirrored silent_model calls with is_silent_experiment in spend logs (#48888)
67ae3fb527 fix(websearch)!: keep the provider prefix on the agentic follow-up model (#38885)
Compare 91 commits »
scriptoriumadmin synced commits to refs/pull/48521/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:02 +00:00
ccc56d27ad fix(azure): add batch prices to the unversioned o3, o4-mini, o3-mini, gpt-4o and gpt-4o-mini rows (#49182)
b91fc92b6d fix(router): cap the default OTPM reservation and reconcile token counters after each call (#49054)
342ce6ae4a feat(zai): support response_format and max_completion_tokens, add glm-5v-turbo pricing (#48335)
733cfeba93 fix(cost): bill a provider reported usage.cost on every path unless the deployment is priced (#48953)
Compare 140 commits »
scriptoriumadmin synced commits to refs/pull/48517/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:01 +00:00
976a63478c fix(http): raise aiohttp max_field_size for large response headers
d302096b5a feat(lite): offer each model group's reasoning efforts in pi, OpenCode and Codex (#48949)
d76db470f9 test: update integration tests left stale by recent product changes (#49143)
24afa12253 chore(caching)!: remove the disk cache backend (#48114)
Compare 114 commits »
scriptoriumadmin synced commits to refs/pull/48517/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:01 +00:00
976a63478c fix(http): raise aiohttp max_field_size for large response headers
d302096b5a feat(lite): offer each model group's reasoning efforts in pi, OpenCode and Codex (#48949)
d76db470f9 test: update integration tests left stale by recent product changes (#49143)
24afa12253 chore(caching)!: remove the disk cache backend (#48114)
60601ca995 feat(pass-through): add eu/jev decision API pass-through with spend tracking (#46875)
Compare 205 commits »
scriptoriumadmin synced commits to refs/pull/48514/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:00 +00:00
5f6d331cb6 Merge remote-tracking branch 'origin/main' into litellm_drop_clear_thinking_with_thinking
dc172438b9 fix(anthropic): keep the clear_thinking edit on models that think by default
b25ea48c4b fix(anthropic)!: drop beta-gated body fields under drop_params (#48793)
1a05aab72a fix(bedrock)!: route region-prefixed embedding models to that region and bill its price (#49072)
784a52de79 test(router_strategy): keep foreign asyncio task noise out of the budget limiter caplog asserts (#43375)
Compare 45 commits »
scriptoriumadmin synced commits to refs/pull/48514/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:00 +00:00
dbcacc7ab7 fix(health): probe only models a partial wildcard serves (#49060)
f32ac94ad1 fix(openai): keep the upstream error body on e.response for OpenAI and Azure errors (#49079)
ccc56d27ad fix(azure): add batch prices to the unversioned o3, o4-mini, o3-mini, gpt-4o and gpt-4o-mini rows (#49182)
b91fc92b6d fix(router): cap the default OTPM reservation and reconcile token counters after each call (#49054)
Compare 116 commits »