scriptoriumadmin
  • Joined on 2026-03-01
scriptoriumadmin synced commits to refs/pull/48518/head at scriptoriumadmin/litellm from mirror 2026-10-28 06:24:37 +00:00
516f0feab5 Revert "ci(spend-logs-guard): read the diff from the pulls/files API instead of fetching PR commits"
36da4fe034 ci(spend-logs-guard): read the diff from the pulls/files API instead of fetching PR commits
943f902e92 ci(spend-logs-guard): flatten paginated reviews with jq, check out the base ref
cf88f410b1 ci: spend-logs-guard requires kerry-berri approval on LiteLLM_SpendLogs schema and migration changes
Compare 4 commits »
scriptoriumadmin synced commits to refs/pull/48520/merge at scriptoriumadmin/litellm from mirror 2026-10-28 06:24:37 +00:00
0c361389e7 docs(auth): note that the Token Authorization scheme comes from Deepgram SDKs
0ce6fabe13 refactor(auth): read WebSocket keys with the shared Authorization parser
795e622c63 test(passthrough): let pytest-timeout guard the relay test instead of a 5s wait_for
88d6a61d74 feat(auth): accept a Token Authorization header on the Deepgram WebSocket route
Compare 6 commits »
scriptoriumadmin synced commits to refs/pull/48520/head at scriptoriumadmin/litellm from mirror 2026-10-28 06:24:37 +00:00
0c361389e7 docs(auth): note that the Token Authorization scheme comes from Deepgram SDKs
0ce6fabe13 refactor(auth): read WebSocket keys with the shared Authorization parser
88d6a61d74 feat(auth): accept a Token Authorization header on the Deepgram WebSocket route
363cc0da04 fix(passthrough): bill a WebSocket session whose client hangs up mid-stream
Compare 4 commits »
scriptoriumadmin synced commits to refs/pull/48517/merge at scriptoriumadmin/litellm from mirror 2026-10-28 06:24:37 +00:00
21ab2cb87b test: update stale integration and guardrail e2e tests to intended behavior (#48665)
15eca24fc2 fix(guardrails)!: redact secrets in tool traffic and system prompts (#47122)
b9e4298506 fix: preserve media across Responses and Gemini conversions (#48484)
696ff615d4 feat(morph): support open models and cached input pricing (#48676)
Compare 73 commits »
scriptoriumadmin synced commits to refs/pull/48506/merge at scriptoriumadmin/litellm from mirror 2026-10-28 06:24:37 +00:00
0a1dbc0fb4 refactor(mcp): drop the experimental label from the MCP server and client paths (#48513)
55a0a25080 refactor(proxy): give database shutdown one lifespan owner
0657ed46cf fix(langfuse_otel)!: derive trace-level name, input, output and tags on traces litellm starts (#42705)
14193435b8 refactor(anthropic): rename llms/anthropic/pass_through to llms/anthropic/messages (#48510)
Compare 28 commits »
scriptoriumadmin synced commits to refs/pull/48507/head at scriptoriumadmin/litellm from mirror 2026-10-28 06:24:37 +00:00
2465cddf22 refactor(proxy): inject grouped database repositories
55a0a25080 refactor(proxy): give database shutdown one lifespan owner
Compare 2 commits »
scriptoriumadmin synced commits to refs/pull/48507/merge at scriptoriumadmin/litellm from mirror 2026-10-28 06:24:37 +00:00
0a1dbc0fb4 refactor(mcp): drop the experimental label from the MCP server and client paths (#48513)
2465cddf22 refactor(proxy): inject grouped database repositories
55a0a25080 refactor(proxy): give database shutdown one lifespan owner
Compare 30 commits »
scriptoriumadmin synced commits to refs/pull/48463/merge at scriptoriumadmin/litellm from mirror 2026-10-28 06:24:36 +00:00
14193435b8 refactor(anthropic): rename llms/anthropic/pass_through to llms/anthropic/messages (#48510)
cfe0100e1f fix(router): preserve tag fail-open policy through affinity and cooldown (#48470)
aa33b052d2 fix(messages): honor OpenAI stop_sequences (#37118) (#48534)
74ce6d1d66 fix(databricks): reuse base OAuth for decisions (#48395) (#48527)
Compare 13 commits »
scriptoriumadmin synced commits to refs/pull/48462/merge at scriptoriumadmin/litellm from mirror 2026-10-28 06:24:36 +00:00
9b2fc9db40 test: remove checks that pin implementation details and add a shadcn testing rule (#48663)
cb70bc560e fix(streaming): dict-usage arm drops prompt_tokens_details/completion_tokens_details its sibling arms preserve (#36678)
8f31c7171d fix(router): keep a lone deployment warm under router allowed_fails unless the policy names the exception (#48644)
a53ea5bd77 fix(proxy): keep every startup line JSON when json_logs is on (#47035)
Compare 101 commits »
scriptoriumadmin synced commits to refs/pull/48460/merge at scriptoriumadmin/litellm from mirror 2026-10-28 06:24:36 +00:00
707257c357 fix(ollama): preserve tool call IDs in continuation requests
cfe0100e1f fix(router): preserve tag fail-open policy through affinity and cooldown (#48470)
aa33b052d2 fix(messages): honor OpenAI stop_sequences (#37118) (#48534)
74ce6d1d66 fix(databricks): reuse base OAuth for decisions (#48395) (#48527)
Compare 64 commits »
scriptoriumadmin synced commits to refs/pull/48460/head at scriptoriumadmin/litellm from mirror 2026-10-28 06:24:36 +00:00
707257c357 fix(ollama): preserve tool call IDs in continuation requests
scriptoriumadmin synced commits to refs/pull/48445/merge at scriptoriumadmin/litellm from mirror 2026-10-28 06:24:36 +00:00
14193435b8 refactor(anthropic): rename llms/anthropic/pass_through to llms/anthropic/messages (#48510)
cfe0100e1f fix(router): preserve tag fail-open policy through affinity and cooldown (#48470)
aa33b052d2 fix(messages): honor OpenAI stop_sequences (#37118) (#48534)
74ce6d1d66 fix(databricks): reuse base OAuth for decisions (#48395) (#48527)
Compare 51 commits »
scriptoriumadmin synced commits to refs/pull/48440/merge at scriptoriumadmin/litellm from mirror 2026-10-28 06:24:36 +00:00
cfe0100e1f fix(router): preserve tag fail-open policy through affinity and cooldown (#48470)
aa33b052d2 fix(messages): honor OpenAI stop_sequences (#37118) (#48534)
74ce6d1d66 fix(databricks): reuse base OAuth for decisions (#48395) (#48527)
e5757934fd fix(azure): add keyless Decisions authentication (#48386) (#48529)
Compare 73 commits »
scriptoriumadmin synced commits to refs/pull/48439/merge at scriptoriumadmin/litellm from mirror 2026-10-28 06:24:36 +00:00
cfe0100e1f fix(router): preserve tag fail-open policy through affinity and cooldown (#48470)
aa33b052d2 fix(messages): honor OpenAI stop_sequences (#37118) (#48534)
74ce6d1d66 fix(databricks): reuse base OAuth for decisions (#48395) (#48527)
e5757934fd fix(azure): add keyless Decisions authentication (#48386) (#48529)
Compare 73 commits »
scriptoriumadmin synced commits to refs/pull/48482/merge at scriptoriumadmin/litellm from mirror 2026-10-28 06:24:36 +00:00
0a1dbc0fb4 refactor(mcp): drop the experimental label from the MCP server and client paths (#48513)
0657ed46cf fix(langfuse_otel)!: derive trace-level name, input, output and tags on traces litellm starts (#42705)
14193435b8 refactor(anthropic): rename llms/anthropic/pass_through to llms/anthropic/messages (#48510)
cfe0100e1f fix(router): preserve tag fail-open policy through affinity and cooldown (#48470)
Compare 61 commits »
scriptoriumadmin synced commits to refs/pull/48477/head at scriptoriumadmin/litellm from mirror 2026-10-28 06:24:36 +00:00
ca8a32e3d3 fix(deps): patch MSAL in extension packaging
7e4cca3f5e docs(helm): explain restricted metrics credentials
6e14f023ea fix(helm): support authenticated ServiceMonitor scrapes
cfe0100e1f fix(router): preserve tag fail-open policy through affinity and cooldown (#48470)
aa33b052d2 fix(messages): honor OpenAI stop_sequences (#37118) (#48534)
Compare 63 commits »
scriptoriumadmin synced commits to refs/pull/48477/merge at scriptoriumadmin/litellm from mirror 2026-10-28 06:24:36 +00:00
3d92124d96 fix(vertex-ai): drop the floor retirement date from gemini-3.1-flash-lite-image (#48587)
32297c9177 fix(logging): match extra_spend_tag_headers case-insensitively (#48620)
02605a14ad fix(anthropic): estimate initial input tokens for bridged message streams (#48618)
5667ac8497 feat(proxy): refuse migrations that existing rows would make fail, before the first one runs (#48493)
Compare 75 commits »
scriptoriumadmin synced commits to refs/pull/48472/head at scriptoriumadmin/litellm from mirror 2026-10-28 06:24:36 +00:00
5434ce4675 fix(guardrails): name the LLM pass-through route's response pipeline up front
80b95eb8c0 refactor(a2a): share the A2A method map with the applied-guardrails stream check
Compare 2 commits »
scriptoriumadmin synced commits to refs/pull/48466/merge at scriptoriumadmin/litellm from mirror 2026-10-28 06:24:36 +00:00
e0d1e64591 feat(router): respect caller output budgets in complexity routing (#48632)
52562c47f8 refactor(proxy-extras): drop the spend-log api_key special case from the row check remedy (#48636)
34c10829b1 fix(ui): percent-encode request id in spend log detail URL (#48630)
9e01b3c37b fix(complexity_router): keep the held user_turn route for Codex compaction requests (#48627)
Compare 90 commits »
scriptoriumadmin synced commits to refs/pull/48479/head at scriptoriumadmin/litellm from mirror 2026-10-28 06:24:36 +00:00
64d3144c23 Merge remote-tracking branch 'origin/main' into litellm-providers/price-sync-aws-bedrock
3d92124d96 fix(vertex-ai): drop the floor retirement date from gemini-3.1-flash-lite-image (#48587)
32297c9177 fix(logging): match extra_spend_tag_headers case-insensitively (#48620)
02605a14ad fix(anthropic): estimate initial input tokens for bridged message streams (#48618)
5667ac8497 feat(proxy): refuse migrations that existing rows would make fail, before the first one runs (#48493)
Compare 76 commits »