scriptoriumadmin
  • Joined on 2026-03-01
scriptoriumadmin synced commits to refs/pull/49378/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:37 +00:00
5114e1c515 test(mlflow): fake only the MLflow client in the failure event test
25844098bf fix(logging): scrub the prompt out of SDK failure logs when message logging is redacted
91aa6a16b2 fix(logging): replace a pydantic input_value whole instead of walking each cut
Compare 4 commits »
scriptoriumadmin synced commits to refs/pull/49380/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:37 +00:00
c920180bac fix(otel): keep only the request text per span so a failed request's span can be freed
c8601d733b fix(logging): apply a callback's own message redaction to its failure events
4fa1e66e4a fix(proxy): scrub the prompt out of proxy failure hook errors when message logging is redacted
5114e1c515 test(mlflow): fake only the MLflow client in the failure event test
Compare 7 commits »
scriptoriumadmin synced commits to refs/pull/49381/head at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:37 +00:00
98f95187d8 fix(proxy): keep the request's redaction opt-in on proxy-only failure logs
c8601d733b fix(logging): apply a callback's own message redaction to its failure events
c920180bac fix(otel): keep only the request text per span so a failed request's span can be freed
4fa1e66e4a fix(proxy): scrub the prompt out of proxy failure hook errors when message logging is redacted
5114e1c515 test(mlflow): fake only the MLflow client in the failure event test
Compare 7 commits »
scriptoriumadmin synced commits to refs/pull/49379/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:37 +00:00
5114e1c515 test(mlflow): fake only the MLflow client in the failure event test
c920180bac fix(otel): keep only the request text per span so a failed request's span can be freed
25844098bf fix(logging): scrub the prompt out of SDK failure logs when message logging is redacted
4fa1e66e4a fix(proxy): scrub the prompt out of proxy failure hook errors when message logging is redacted
Compare 6 commits »
scriptoriumadmin synced commits to refs/pull/49379/head at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:37 +00:00
c920180bac fix(otel): keep only the request text per span so a failed request's span can be freed
4fa1e66e4a fix(proxy): scrub the prompt out of proxy failure hook errors when message logging is redacted
5114e1c515 test(mlflow): fake only the MLflow client in the failure event test
25844098bf fix(logging): scrub the prompt out of SDK failure logs when message logging is redacted
91aa6a16b2 fix(logging): replace a pydantic input_value whole instead of walking each cut
Compare 5 commits »
scriptoriumadmin synced commits to refs/pull/49377/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:37 +00:00
7fe6b1de34 fix(proxy)!: ignore stored general_settings keys no settings API manages (#48967)
91aa6a16b2 fix(logging): replace a pydantic input_value whole instead of walking each cut
523b87ec71 fix(proxy): charge budget windows when the cached key or team expired before the request ended (#47608)
10b3deae0d build(deps): allow huggingface-hub 2.x (#49056)
Compare 65 commits »
scriptoriumadmin synced commits to refs/pull/49377/head at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:37 +00:00
91aa6a16b2 fix(logging): replace a pydantic input_value whole instead of walking each cut
scriptoriumadmin synced commits to refs/pull/49373/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:37 +00:00
fcef9cd0a3 feat(videos): serve custom_provider_map BaseVideoConfig providers on /v1/videos (#49785)
34314a99f0 fix(messages): make rust messages copy python messages behaviour (#49611)
5e08cb0e63 test(messages): add rust vs python messages parity characterization suite (#49610)
216041e243 feat(decisions): add Parallel AI web-grounded decisions (#49188)
Compare 148 commits »
scriptoriumadmin synced commits to refs/pull/49323/head at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:36 +00:00
6ef3c0e056 fix(guardrails): read only the admin opt-out settings for a global Lakera guardrail on a Gemini body
a00a45541f Merge branch 'litellm_passthrough_auth_guardrails' into litellm_lakera_v2_gemini_contents
1a5b56c9a2 fix(guardrails): read Responses messages in legacy Lakera and skip bodies it can't read on pass-through
264f65bfa8 Merge branch 'litellm_passthrough_auth_guardrails' into litellm_lakera_v2_gemini_contents
de63702f08 fix(guardrails): tolerate pass-through bodies request setup hasn't normalized
Compare 111 commits »
scriptoriumadmin synced commits to refs/pull/49360/head at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:36 +00:00
aad396f15c Merge remote-tracking branch 'origin/main' into litellm_usage_export_key_user_metadata
acd084ab38 fix(mcp): answer bare OPTIONS on MCP routes without running LiteLLM auth (#49497)
e8e2fad99d fix(usage-export): only populate key and user metadata for admin view and strip credential and SCIM slots
81969e4afc refactor(ui): move admin and settings text onto i18n (#49546)
b84493d9a7 fix(proxy): log each endpoint's own call type on failed audio, moderation, image, and rerank spend rows (#49684)
Compare 50 commits »
scriptoriumadmin synced commits to refs/pull/49348/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:36 +00:00
10b3deae0d build(deps): allow huggingface-hub 2.x (#49056)
cc142a8191 fix(cost): add deepgram/streaming/nova-3-medical and update stale Nova-3 streaming rates (#49733)
250af8f027 fix(spend)!: save streamed /v1/responses spend rows under the encrypted resp_ id the client received (#49493)
4ede2c012f feat(model_info): add supports_continuation capability flag for Gemini long decode continuation (#49500)
Compare 34 commits »
scriptoriumadmin synced commits to refs/pull/49347/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:36 +00:00
a0b1edc0a0 fix(providers): trim prompt_cache_breakpoint to what each API takes under drop_params (#49064)
16ee2c71a7 fix(proxy): keep provider fields on streamed chat completion chunks (#49398)
33457d3ac9 fix(proxy): check the model in every OpenAI websocket passthrough frame (#48979)
40e4e512d0 fix(anthropic): stream azure_ai natively on an Azure OpenAI host on /v1/messages (#49216)
Compare 12 commits »
scriptoriumadmin synced commits to refs/pull/49324/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:36 +00:00
3b7d942bad refactor(proxy): drop a docstring that repeats the pass-through header try block
a9670e88db fix(proxy): keep a pass-through response when a recorded guardrail value can't be encoded
6ef3c0e056 fix(guardrails): read only the admin opt-out settings for a global Lakera guardrail on a Gemini body
4afb8292d5 Merge branch 'litellm_lakera_v2_gemini_contents' into litellm_passthrough_applied_guardrails_header
Compare 139 commits »
scriptoriumadmin synced commits to refs/pull/49323/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:36 +00:00
6ef3c0e056 fix(guardrails): read only the admin opt-out settings for a global Lakera guardrail on a Gemini body
1a5b56c9a2 fix(guardrails): read Responses messages in legacy Lakera and skip bodies it can't read on pass-through
a00a45541f Merge branch 'litellm_passthrough_auth_guardrails' into litellm_lakera_v2_gemini_contents
264f65bfa8 Merge branch 'litellm_passthrough_auth_guardrails' into litellm_lakera_v2_gemini_contents
Compare 112 commits »
scriptoriumadmin synced commits to refs/pull/49324/head at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:36 +00:00
3b7d942bad refactor(proxy): drop a docstring that repeats the pass-through header try block
a9670e88db fix(proxy): keep a pass-through response when a recorded guardrail value can't be encoded
4afb8292d5 Merge branch 'litellm_lakera_v2_gemini_contents' into litellm_passthrough_applied_guardrails_header
6ef3c0e056 fix(guardrails): read only the admin opt-out settings for a global Lakera guardrail on a Gemini body
a00a45541f Merge branch 'litellm_passthrough_auth_guardrails' into litellm_lakera_v2_gemini_contents
Compare 138 commits »
scriptoriumadmin synced commits to refs/pull/49322/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:36 +00:00
20cb3ea439 test(integration): repair release qualification timing and labels (#49737)
1a5b56c9a2 fix(guardrails): read Responses messages in legacy Lakera and skip bodies it can't read on pass-through
94b5b6386a fix(bedrock): send native structured output for json_schema on Claude models that cannot force a tool (#49703)
183212e8be feat(anthropic): pick the beta allowlist row per deployment and surface input_transformations (#49689)
Compare 100 commits »
scriptoriumadmin synced commits to refs/pull/49322/head at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:36 +00:00
1a5b56c9a2 fix(guardrails): read Responses messages in legacy Lakera and skip bodies it can't read on pass-through
de63702f08 fix(guardrails): tolerate pass-through bodies request setup hasn't normalized
1d956d84d1 fix(proxy): tell a provider reply from a custom API's JSON by the type of its fields
c7928956d1 fix(proxy): read an Anthropic message as a provider reply in the post-call scan
83eb02cb31 fix(proxy): read JSON field names in what a post-call guardrail scans outside a provider's envelope
Compare 92 commits »
scriptoriumadmin synced commits to refs/pull/49300/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:36 +00:00
10b3deae0d build(deps): allow huggingface-hub 2.x (#49056)
cc142a8191 fix(cost): add deepgram/streaming/nova-3-medical and update stale Nova-3 streaming rates (#49733)
250af8f027 fix(spend)!: save streamed /v1/responses spend rows under the encrypted resp_ id the client received (#49493)
4ede2c012f feat(model_info): add supports_continuation capability flag for Gemini long decode continuation (#49500)
Compare 34 commits »
scriptoriumadmin synced commits to refs/pull/49298/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:36 +00:00
10b3deae0d build(deps): allow huggingface-hub 2.x (#49056)
cc142a8191 fix(cost): add deepgram/streaming/nova-3-medical and update stale Nova-3 streaming rates (#49733)
250af8f027 fix(spend)!: save streamed /v1/responses spend rows under the encrypted resp_ id the client received (#49493)
4ede2c012f feat(model_info): add supports_continuation capability flag for Gemini long decode continuation (#49500)
Compare 34 commits »
scriptoriumadmin synced commits to refs/pull/49295/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:36 +00:00
8d967e99ea fix(proxy): keep a skipped guardrail out of the logged applied guardrails
38795d0cfc fix(proxy): redact a refused request as soon as the pre-call walk ends
b1ebdab063 fix(proxy): run enterprise folder guardrails and stop naming skipped guardrails as applied
b0402e3bc5 test(proxy): pin extraction state and fields out of a refused request's failure log
Compare 169 commits »