scriptoriumadmin
  • Joined on 2026-03-01
scriptoriumadmin synced commits to refs/pull/40967/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:47:20 +00:00
36e8ca43a8 test(guardrails): type the masking guardrail test helpers
19336aa6bb fix(guardrails): scan a streamed web search query as text like the non-streaming reply
8ea884d7e4 test(guardrails): type the legacy hook stream test helpers
e6715ba090 fix(guardrails): show a legacy post-call hook the web search result blocks of a /v1/messages stream
f980d76d35 fix(guardrails): deliver a legacy post-call hook's tool-call rewrites on streams instead of discarding the stream rewrite
Compare 74 commits »
scriptoriumadmin synced commits to refs/pull/40701/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:47:20 +00:00
032342d2b7 fix(responses): resume background response streams with stream and starting_after (#48819)
dff474e450 fix(responses): replay the original Responses item order, phase, and boundaries on the next chat turn (#48912)
3f01341f0a fix(health)!: openai realtime health check reports healthy with a missing or invalid api key (#41233)
904c092ffe feat(providers): add BigModel support and model pricing (#48563)
Compare 86 commits »
scriptoriumadmin synced commits to refs/pull/40683/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:47:20 +00:00
4212f1af27 fix(passthrough): forward OpenAI-Beta and default agents=v1 on the OpenAI passthrough (#49009)
ebf84f8649 fix(caching): read the cache key's model group from the router's metadata for the call (#48917)
41602e318d fix(proxy): stream a guardrail block on /v1/messages as Anthropic events (#49010)
444423a5ca fix(cost): bill a deployment's per-second rates on native Anthropic /v1/messages (#42417)
Compare 148 commits »
scriptoriumadmin synced commits to refs/pull/39977/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:47:19 +00:00
e93e01ca4b fix(ci): build base native extension for OpenAPI lint (#49136)
fd8b89fbec fix(mcp)!: restore upstream-token admission for legacy delegate servers (#48939)
dfcfa0b043 fix(anthropic): match text and pdf media types case-insensitively and detect downloaded pdfs by signature
d8f162ea22 fix(guardrails): allow MCP call modes on the generic guardrail API (#48060)
Compare 94 commits »
scriptoriumadmin synced commits to refs/pull/40066/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:47:19 +00:00
42ee801409 fix(proxy): answer model lists from cached listings first and share one listing per server
83d52c7646 fix(proxy): try every configured wildcard route before listing any wildcard's models in the file credential lookup
1f03ebc983 fix(proxy): stop the file credential lookup at the first match before listing wildcard models
22e417363a fix(proxy): run model discovery on its own thread pool and keep credential lookups off the event loop
42303949e1 Merge remote-tracking branch 'origin/main' into litellm_wildcard_discovery_provider_config
Compare 171 commits »
scriptoriumadmin synced commits to refs/pull/40248/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:47:19 +00:00
c213234783 feat(vertex_ai)!: use HTTP/2 httpx client for search_api vector store (#40631)
ead221995e refactor(router): move router callers onto the entry points and invert the proxy imports (#48847)
57f6e1b39f fix(proxy): keep the litellm command light so spawned workers answer uvicorn's first health ping (#45039)
3057c47d6d fix(caching): keep reasoning, citations, and audio on streamed cache hits (#32096)
Compare 172 commits »
scriptoriumadmin synced commits to refs/pull/40171/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:47:19 +00:00
fd8b89fbec fix(mcp)!: restore upstream-token admission for legacy delegate servers (#48939)
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)
Compare 168 commits »
scriptoriumadmin synced commits to refs/pull/40092/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:47:19 +00:00
c431501979 fix(ui): merge main and preserve Chinese navigation
23595f7fe5 fix(bedrock): backfill published regional service tier prices (#49113)
85af2f65c9 refactor(helm)!: connect both charts to a separately deployed Lens (#49169)
44cd858697 fix(cost): bill the requested model's rates when the response names an unpriced model (#48900)
a7030a5a2c fix(vertex_ai): batch Claude models in Anthropic's native row shape (#45715)
Compare 405 commits »
scriptoriumadmin synced commits to refs/pull/40066/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:47:19 +00:00
83d52c7646 fix(proxy): try every configured wildcard route before listing any wildcard's models in the file credential lookup
c21e576a07 refactor(types): replace Any with proven types in 14 files (#48928)
e73f06ecdc ci: run the dashboard API types and Terraform endpoint checks on every change that can alter the spec (#49022)
1f03ebc983 fix(proxy): stop the file credential lookup at the first match before listing wildcard models
Compare 45 commits »
scriptoriumadmin synced commits to refs/pull/40264/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:47:19 +00:00
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)
342ce6ae4a feat(zai): support response_format and max_completion_tokens, add glm-5v-turbo pricing (#48335)
Compare 113 commits »
scriptoriumadmin synced commits to refs/pull/40092/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:47:19 +00:00
c431501979 fix(ui): merge main and preserve Chinese navigation
23595f7fe5 fix(bedrock): backfill published regional service tier prices (#49113)
85af2f65c9 refactor(helm)!: connect both charts to a separately deployed Lens (#49169)
44cd858697 fix(cost): bill the requested model's rates when the response names an unpriced model (#48900)
Compare 406 commits »
scriptoriumadmin synced commits to refs/pull/39977/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:47:19 +00:00
dfcfa0b043 fix(anthropic): match text and pdf media types case-insensitively and detect downloaded pdfs by signature
108387a9a8 Merge remote-tracking branch 'origin/main' into litellm_lit_6778_snowflake_shared_anthropic_pt
3c7a77e3b0 fix(anthropic): keep the charset of a mixed-case text/plain data URI
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)
Compare 106 commits »
scriptoriumadmin synced commits to refs/pull/39888/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:47:19 +00:00
873f8f9258 fix(proxy): resolve upstream streaming import conflict
4ce724e3df fix(caching): key cached async clients by a per-loop token instead of id(loop) (#48877)
d884167bf2 fix(responses): only merge repeated Codex tools when drop_params is on (#49112)
62b8ee78de ci: run the integration groups on GitHub Actions (#48985)
Compare 73 commits »
scriptoriumadmin synced commits to refs/pull/39864/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:47:18 +00:00
6b58477f86 fix(realtime): map OpenAI TTS voices before the Live voice check, keep outage spend rows, share the playground session config
ec7569040d Merge remote-tracking branch 'origin/main' into litellm_lit_6974_gemini_live_lazy_setup
c98641fd5a feat(dashscope)!: derive protocol bases from one domain (#47812)
e9644a018c fix(realtime): forward any voice to AI Studio Live models that accept it
06cdee91da fix(guardrails): scan and rewrite streamed /v1/completions under post_call guardrails (#49035)
Compare 115 commits »
scriptoriumadmin synced commits to refs/pull/39734/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:47:18 +00:00
85af2f65c9 refactor(helm)!: connect both charts to a separately deployed Lens (#49169)
44cd858697 fix(cost): bill the requested model's rates when the response names an unpriced model (#48900)
a7030a5a2c fix(vertex_ai): batch Claude models in Anthropic's native row shape (#45715)
7aa0393cb6 feat(providers): add CLF AI Gateway as an OpenAI-compatible provider with ten models (#39324)
Compare 172 commits »
scriptoriumadmin synced commits to refs/pull/39864/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:47:18 +00:00
68b5a737a1 fix(anthropic): retry /v1/messages without strict when Claude rejects strict tools under drop_params (#49102)
08b539e6a8 fix(proxy)!: bill streamed /v1/completions without stream_options like chat (#45366)
e93e01ca4b fix(ci): build base native extension for OpenAPI lint (#49136)
fd8b89fbec fix(mcp)!: restore upstream-token admission for legacy delegate servers (#48939)
Compare 85 commits »
scriptoriumadmin synced commits to refs/pull/39868/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:47:18 +00:00
fb6973bad9 fix(passthrough): scope declared provider to pass-through failures and match Google hosts only
scriptoriumadmin synced commits to refs/pull/39888/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:47:18 +00:00
873f8f9258 fix(proxy): resolve upstream streaming import conflict
4ce724e3df fix(caching): key cached async clients by a per-loop token instead of id(loop) (#48877)
d884167bf2 fix(responses): only merge repeated Codex tools when drop_params is on (#49112)
62b8ee78de ci: run the integration groups on GitHub Actions (#48985)
ffcc4f7a70 fix(otel)!: print OTel v2 spans to stdout only when the operator asks (#48723)
Compare 289 commits »
scriptoriumadmin synced commits to refs/pull/39874/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:47:18 +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 274 commits »
scriptoriumadmin synced commits to refs/pull/39881/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:47:18 +00:00
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)
e7d3b24d7c fix(logging): mark mirrored silent_model calls with is_silent_experiment in spend logs (#48888)
Compare 259 commits »