scriptoriumadmin
  • Joined on 2026-03-01
scriptoriumadmin synced commits to refs/pull/49295/head 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
b0402e3bc5 test(proxy): pin extraction state and fields out of a refused request's failure log
cd4769a363 fix(proxy): redact the logged messages of a request refused for its model
10795ef3b4 fix(proxy): skip pre-call guardrails for a model the proxy cannot route
Compare 168 commits »
scriptoriumadmin synced commits to refs/pull/49292/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 75 commits »
scriptoriumadmin synced commits to refs/pull/49291/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 91 commits »
scriptoriumadmin synced commits to refs/pull/49337/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:36 +00:00
7fe6b1de34 fix(proxy)!: ignore stored general_settings keys no settings API manages (#48967)
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)
cc142a8191 fix(cost): add deepgram/streaming/nova-3-medical and update stale Nova-3 streaming rates (#49733)
Compare 55 commits »
scriptoriumadmin synced commits to refs/pull/49267/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:35 +00:00
f8f12a270a test(integration): repair stale contract fixtures (#49700)
508a98586e fix(databricks): join plain text blocks for non-Claude json_object requests (#49385)
f91774e2f9 fix(fireworks): keep developer items in place for models that accept a later system message (#49399)
a2ab27373f fix(proxy): count the context_management edits /v1/messages applies on every bridged provider (#49234)
Compare 18 commits »
scriptoriumadmin synced commits to refs/pull/49274/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:35 +00:00
216041e243 feat(decisions): add Parallel AI web-grounded decisions (#49188)
08b951a814 fix(vllm): list hosted_vllm wildcard models when the server has no api key (#40066)
2a94bb3835 fix(spend): bill web search interception follow-ups once under the outer request (#49762)
be50cbe9d8 fix(responses)!: authorize and decode comparison response IDs (#49402)
Compare 63 commits »
scriptoriumadmin synced commits to refs/pull/49288/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:35 +00:00
a2d27881e8 fix(bedrock): reserve DeepSeek V3.2 output capacity and date GovCloud West Llama 3 (#49732)
7fe6b1de34 fix(proxy)!: ignore stored general_settings keys no settings API manages (#48967)
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 63 commits »
scriptoriumadmin synced commits to refs/pull/49271/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:35 +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 159 commits »
scriptoriumadmin synced commits to refs/pull/49261/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:35 +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/49244/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:35 +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 64 commits »
scriptoriumadmin synced commits to refs/pull/49283/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:35 +00:00
f8f12a270a test(integration): repair stale contract fixtures (#49700)
508a98586e fix(databricks): join plain text blocks for non-Claude json_object requests (#49385)
f91774e2f9 fix(fireworks): keep developer items in place for models that accept a later system message (#49399)
a2ab27373f fix(proxy): count the context_management edits /v1/messages applies on every bridged provider (#49234)
Compare 80 commits »
scriptoriumadmin synced commits to refs/pull/49288/head at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:35 +00:00
3d26f2fe22 test(proxy): type the probe tests and route real requests where no call count is asserted
a1005c590d feat(proxy): add a probe that asks route_request whether a request's model routes
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 158 commits »
scriptoriumadmin synced commits to refs/pull/49289/head at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:35 +00:00
b1ebdab063 fix(proxy): run enterprise folder guardrails and stop naming skipped guardrails as applied
e5a1eb365f fix(proxy): check an MCP call's skip against the guardrail's MCP pre-call event
ce788bc180 fix(proxy): redact extraction state and field texts a skipped guardrail would have scanned
7cdf7fcfd7 fix(proxy): run parallel guardrails before an operator hook and Custom Code guardrails for a refused model
2554230b12 feat(proxy): let pre_call_hook skip built-in guardrails for a model routing refuses
Compare 163 commits »
scriptoriumadmin synced commits to refs/pull/49234/head at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:35 +00:00
c63d2c4397 test(azure_ai): record the Azure inference request with respx instead of appending to a list
81ca2f309d test(azure_ai): compare the count's betas with the betas Azure inference sends
Compare 2 commits »
scriptoriumadmin synced commits to refs/pull/49273/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:35 +00:00
6254860560 test(e2e): drive the Codex CLI through LiteLLM, command round trip (#49374)
6a7a469287 fix(vertex_ai): map Anthropic context overflow errors (#36963)
640a87f70d fix(gemini): resend once with the placeholder signature when the other backend rejects a replayed thought signature (#49697)
0bd677afef test(integration): look up streamed Responses spend rows by the client-facing id (#49752)
Compare 109 commits »
scriptoriumadmin synced commits to refs/pull/49266/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:35 +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/49289/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:35 +00:00
b1ebdab063 fix(proxy): run enterprise folder guardrails and stop naming skipped guardrails as applied
e5a1eb365f fix(proxy): check an MCP call's skip against the guardrail's MCP pre-call event
ce788bc180 fix(proxy): redact extraction state and field texts a skipped guardrail would have scanned
7cdf7fcfd7 fix(proxy): run parallel guardrails before an operator hook and Custom Code guardrails for a refused model
Compare 164 commits »
scriptoriumadmin synced commits to refs/pull/49260/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:35 +00:00
6254860560 test(e2e): drive the Codex CLI through LiteLLM, command round trip (#49374)
6a7a469287 fix(vertex_ai): map Anthropic context overflow errors (#36963)
640a87f70d fix(gemini): resend once with the placeholder signature when the other backend rejects a replayed thought signature (#49697)
0bd677afef test(integration): look up streamed Responses spend rows by the client-facing id (#49752)
Compare 52 commits »
scriptoriumadmin synced commits to refs/pull/49285/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:35 +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 156 commits »
scriptoriumadmin synced commits to refs/pull/49224/head at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:34 +00:00
348b82fd33 refactor(guardrails): tighten the CollieAi wrapper and its tests