scriptoriumadmin
  • Joined on 2026-03-01
scriptoriumadmin synced commits to refs/pull/47795/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:22 +00:00
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)
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)
Compare 61 commits »
scriptoriumadmin synced commits to refs/pull/47812/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:22 +00:00
7a6519660c fix(dashscope): keep a native DashScope endpoint URL as given for chat and the api base header
6b205fcfc2 fix(dashscope): keep a full DASHSCOPE_API_BASE image URL ahead of the image env var
Compare 2 commits »
scriptoriumadmin synced commits to refs/pull/47816/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:22 +00:00
b5c0bd166f Merge remote-tracking branch 'origin/main' into litellm_deflake_20261021
c87a25a357 feat(proxy)!: general_settings.claude_code_marketplace_auth_required puts the Claude Code marketplace behind a LiteLLM key (#48980)
e8f0735d8a feat(proxy): let a Claude Code gateway user choose the session team (#49001)
c489aa7117 feat(proxy)!: add suppress_startup_output to turn off startup prints (#47708)
bee9f679dc fix(github_copilot): treat a malformed api-key.json like a missing one (#44723)
Compare 367 commits »
scriptoriumadmin synced commits to refs/pull/47817/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:22 +00:00
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)
369f3cb5f0 feat(cost-map): add baseten joey-1 decision model (#49123)
Compare 337 commits »
scriptoriumadmin synced commits to refs/pull/47819/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:22 +00:00
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)
369f3cb5f0 feat(cost-map): add baseten joey-1 decision model (#49123)
Compare 299 commits »
scriptoriumadmin synced commits to refs/pull/47827/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:22 +00:00
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)
369f3cb5f0 feat(cost-map): add baseten joey-1 decision model (#49123)
Compare 336 commits »
scriptoriumadmin synced commits to refs/pull/47830/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:22 +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 289 commits »
scriptoriumadmin synced commits to refs/pull/47833/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:22 +00:00
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)
c87a25a357 feat(proxy)!: general_settings.claude_code_marketplace_auth_required puts the Claude Code marketplace behind a LiteLLM key (#48980)
e8f0735d8a feat(proxy): let a Claude Code gateway user choose the session team (#49001)
Compare 216 commits »
scriptoriumadmin synced commits to refs/pull/47740/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:21 +00:00
896d09b03e fix(batches): store only chat usage extras on batch spend rows
2a852fa95b fix(batches): keep sync logger events at $0 on poller-owned retrieves, pass unparsed provider counts through, log batch usage in chat shape
7c36b6ed20 fix(batches): skip sync loggers on the cost poller's own retrieve and honor exclude_none on provider details
963bff3646 fix(batches): pass through every usage detail field the provider sends
d740675074 fix(batches): log no cost for a batch retrieve that is not final yet
Compare 431 commits »
scriptoriumadmin synced commits to refs/pull/47716/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:21 +00:00
0c55eac4d8 Merge remote-tracking branch 'origin/main' into litellm_internal_copy_40078
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 83 commits »
scriptoriumadmin synced commits to refs/pull/47733/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:21 +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 231 commits »
scriptoriumadmin synced commits to refs/pull/47716/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:21 +00:00
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 91 commits »
scriptoriumadmin synced commits to refs/pull/47735/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:21 +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 235 commits »
scriptoriumadmin synced commits to refs/pull/47761/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:21 +00:00
26b18650a9 fix: read only the built-in catalog when choosing the reasoning drop warning
3e1f31b2dd Merge remote-tracking branch 'origin/main' into litellm_warn_dropped_reasoning_effort
ff22f3de06 build(deps): bump langgraph and tornado and add dated scan ignores to clear osv-scan and image-scan (#48302)
3f5e42d032 fix(proxy): enforce team and key Allowed Vector Stores when no vector store registry is loaded (#48915)
c666df3dac docs(qa): allow focused proof for mechanical PRs (#49031)
Compare 159 commits »
scriptoriumadmin synced commits to refs/pull/47759/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:21 +00:00
cc583a1ce0 fix(vector_stores): refuse a caller index on slash-form OpenSearch stores
5a83e009b3 Merge remote-tracking branch 'origin/main' into litellm_opensearch_vector_store_provider
4cb466e129 fix(vector_stores): refuse opensearch_index_name only on OpenSearch stores, keep the old 400 text
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)
Compare 92 commits »
scriptoriumadmin synced commits to refs/pull/47762/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:21 +00:00
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)
d8f162ea22 fix(guardrails): allow MCP call modes on the generic guardrail API (#48060)
Compare 169 commits »
scriptoriumadmin synced commits to refs/pull/47749/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:21 +00:00
49efac10b7 Merge remote-tracking branch 'origin/main' into litellm_health_scope_like_auth
23377f3b2f test(proxy): pass recorded_model_name in the direct health save tests
ffcc4f7a70 fix(otel)!: print OTel v2 spans to stdout only when the operator asks (#48723)
a54204b583 feat(guardrails): scan sampled stream windows in the background (#48952)
1e7da87e1e fix(otel)!: give key/team Langfuse destinations user, tags and session on OTel v2 without global Langfuse keys (#48718)
Compare 79 commits »
scriptoriumadmin synced commits to refs/pull/47762/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:21 +00:00
4b2490f4e0 test(integration): expect SDK 3's Responses body fields and cache_write_tokens
f9c87d4839 fix(openai): read OPENAI_API_KEY from the env before raising for a missing key, as SDK 2 did
10647ebfcb fix(openai): raise the SDK's own missing-credentials error so callers keep its class and status
9a710306f8 test(openai): accept SDK 2's missing-key message in the unkeyed deployment test
3a3987bfd7 fix(openai): keep SDK 3 from sending OPENAI_ADMIN_KEY on model calls and send Azure Bearer on region and env-key calls
Compare 156 commits »
scriptoriumadmin synced commits to refs/pull/47756/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:21 +00:00
feda51453a fix!: retain unattributed daily activity across reports and exports (#48925)
4bc157e281 feat(proxy): replace the pre-migration row check with a rolled-back dry run of the pending migrations (#48961)
c45b264024 fix(proxy): persist tag spend and drain success callbacks within the shutdown budget (#48988)
c98641fd5a feat(dashscope)!: derive protocol bases from one domain (#47812)
Compare 61 commits »
scriptoriumadmin synced commits to refs/pull/47794/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:21 +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 84 commits »