scriptoriumadmin
  • Joined on 2026-03-01
scriptoriumadmin synced commits to refs/pull/45599/merge at scriptoriumadmin/litellm from mirror 2026-11-01 07:03:49 +00:00
6e27da8af9 fix(router): inspect image content without translating routed requests (#49371)
34b6256d52 fix(streaming): normalize stop after OpenAI-compatible tool calls (#49388)
c8c0248ac7 test(integration): size restart-mid-burst timeouts from the proxy boot budget (#49376)
bfef2e1e56 fix(messages): price a native /v1/messages body as served unless its provider reports its own cost (#49356)
Compare 26 commits »
scriptoriumadmin synced commits to refs/pull/45612/merge at scriptoriumadmin/litellm from mirror 2026-11-01 07:03:49 +00:00
a1c5829f6b fix(bedrock): raise GovCloud West Llama 3 max output to the model card 8K (#49543)
f4f5e2c80f fix(cost-map): add 2026-11-04 deprecation_date to together_ai Qwen3.8-2.4T-A95B (#49542)
68dbf54b09 chore(e2e): remove the unused arize_phoenix callback from the stage mirror config (#49538)
0f4d5c6ad0 feat(ovalix)!: scan files, tool calls and tool results (#49309)
Compare 123 commits »
scriptoriumadmin synced commits to refs/pull/45633/merge at scriptoriumadmin/litellm from mirror 2026-11-01 07:03:49 +00:00
a713ed6bab fix(gemini): add thought_signature_in_tool_call_id to keep tool call ids short for clients that cap them (#47692)
febd340120 fix(guardrails)!: keep the upstream error when a /v1/messages stream ends in one (#49088)
27fbcd9895 fix(anthropic): map pause_turn and return refusal explanations on chat and responses (#49192)
281bf4e48b ci(circleci): clone the public repo over HTTPS so main jobs stop failing at checkout (#49394)
Compare 253 commits »
scriptoriumadmin synced commits to refs/pull/45619/merge at scriptoriumadmin/litellm from mirror 2026-11-01 07:03:49 +00:00
c8c0248ac7 test(integration): size restart-mid-burst timeouts from the proxy boot budget (#49376)
bfef2e1e56 fix(messages): price a native /v1/messages body as served unless its provider reports its own cost (#49356)
7b4bdde96e fix(cost): keep upstream_usage_cost on the Responses stream logging copy so bridged /v1/messages rows price their tokens (#49365)
1595adfb2f docs(model-catalog): explain meter, band, channel and When (#49447)
Compare 250 commits »
scriptoriumadmin synced commits to refs/pull/45395/merge at scriptoriumadmin/litellm from mirror 2026-11-01 07:03:49 +00:00
60fc121ce8 test(a2a): replace the third-party agent e2e test with an integration test (#49541)
1b3da63703 test: move Sail, Weave and Presidio e2e tests to integration tests (#49533)
187f936cb3 fix(proxy)!: support reload with multiple workers (#45909)
a1c5829f6b fix(bedrock): raise GovCloud West Llama 3 max output to the model card 8K (#49543)
Compare 163 commits »
scriptoriumadmin synced commits to refs/pull/45423/head at scriptoriumadmin/litellm from mirror 2026-11-01 07:03:49 +00:00
c690783b04 test(streaming): drive refusal-only deltas through the real stream parsers
scriptoriumadmin synced commits to refs/pull/45423/merge at scriptoriumadmin/litellm from mirror 2026-11-01 07:03:49 +00:00
da71a03f6e fix(proxy): trace model list requests with the caller's traceparent (#49141)
c4b01b2ac8 fix(decisions)!: honor a deployment's own supports_audio_input and supports_video_input flags (#49207)
3fc7969e8b perf(logging): skip the base64 regex on plain text and copy a few large strings inline (#49228)
57090e94a4 feat!: add Hostinger Router as an OpenAI-compatible provider (#44863)
Compare 93 commits »
scriptoriumadmin synced commits to refs/pull/45478/head at scriptoriumadmin/litellm from mirror 2026-11-01 07:03:49 +00:00
ca60485755 style: drop redundant comment and add Final on #45470 regression test
5bf30a6e11 fix(anthropic): preserve assistant text order around tool_use in Responses adapter
187f936cb3 fix(proxy)!: support reload with multiple workers (#45909)
a1c5829f6b fix(bedrock): raise GovCloud West Llama 3 max output to the model card 8K (#49543)
f4f5e2c80f fix(cost-map): add 2026-11-04 deprecation_date to together_ai Qwen3.8-2.4T-A95B (#49542)
Compare 83 commits »
scriptoriumadmin synced commits to refs/pull/45478/merge at scriptoriumadmin/litellm from mirror 2026-11-01 07:03:49 +00:00
ca60485755 style: drop redundant comment and add Final on #45470 regression test
5bf30a6e11 fix(anthropic): preserve assistant text order around tool_use in Responses adapter
187f936cb3 fix(proxy)!: support reload with multiple workers (#45909)
a1c5829f6b fix(bedrock): raise GovCloud West Llama 3 max output to the model card 8K (#49543)
Compare 84 commits »
scriptoriumadmin synced commits to refs/pull/45383/merge at scriptoriumadmin/litellm from mirror 2026-11-01 07:03:49 +00:00
d2321581ec fix(cohere): emit streamed tool calls from v2 tool-call-start and tool-call-delta chunks (#47794)
f7b2cd0000 fix(anthropic): answer 400 naming a non-string role or tool call id instead of 500 (#49237)
c43a1addf2 refactor(router): extract PythonCore behind RouterCore and pass the router its config (#49119)
a5f980600c fix(a2a): answer proxy refusals on /a2a POST routes as JSON-RPC errors (#49476)
Compare 178 commits »
scriptoriumadmin synced commits to refs/pull/45512/merge at scriptoriumadmin/litellm from mirror 2026-11-01 07:03:49 +00:00
60fc121ce8 test(a2a): replace the third-party agent e2e test with an integration test (#49541)
1b3da63703 test: move Sail, Weave and Presidio e2e tests to integration tests (#49533)
187f936cb3 fix(proxy)!: support reload with multiple workers (#45909)
a1c5829f6b fix(bedrock): raise GovCloud West Llama 3 max output to the model card 8K (#49543)
Compare 154 commits »
scriptoriumadmin synced commits to refs/pull/45609/merge at scriptoriumadmin/litellm from mirror 2026-11-01 07:03:49 +00:00
bfef2e1e56 fix(messages): price a native /v1/messages body as served unless its provider reports its own cost (#49356)
7b4bdde96e fix(cost): keep upstream_usage_cost on the Responses stream logging copy so bridged /v1/messages rows price their tokens (#49365)
1595adfb2f docs(model-catalog): explain meter, band, channel and When (#49447)
3cb2e60de0 fix(cost): split a provider-reported total between input and output by the cost map rate ratio (#49357)
Compare 28 commits »
scriptoriumadmin synced commits to refs/pull/45662/head at scriptoriumadmin/litellm from mirror 2026-11-01 07:03:49 +00:00
c532b3ae11 feat(providers): add Wally as an OpenAI-compatible provider
1595adfb2f docs(model-catalog): explain meter, band, channel and When (#49447)
3cb2e60de0 fix(cost): split a provider-reported total between input and output by the cost map rate ratio (#49357)
b2647116ca chore(cost-map): add openai gpt-6-astra-law from the pricing page (#49444)
8ff495be96 fix(proxy): price OpenAI pass-through /v1/decisions calls like native Decisions (#49392)
Compare 48 commits »
scriptoriumadmin synced commits to refs/pull/45662/merge at scriptoriumadmin/litellm from mirror 2026-11-01 07:03:49 +00:00
c532b3ae11 feat(providers): add Wally as an OpenAI-compatible provider
1595adfb2f docs(model-catalog): explain meter, band, channel and When (#49447)
3cb2e60de0 fix(cost): split a provider-reported total between input and output by the cost map rate ratio (#49357)
b2647116ca chore(cost-map): add openai gpt-6-astra-law from the pricing page (#49444)
Compare 49 commits »
scriptoriumadmin synced commits to refs/pull/45728/head at scriptoriumadmin/litellm from mirror 2026-11-01 07:03:49 +00:00
285ceba838 fix(router): dedupe strategy selectors by identity so every Router's selector gets registered
60fc121ce8 test(a2a): replace the third-party agent e2e test with an integration test (#49541)
1b3da63703 test: move Sail, Weave and Presidio e2e tests to integration tests (#49533)
187f936cb3 fix(proxy)!: support reload with multiple workers (#45909)
a1c5829f6b fix(bedrock): raise GovCloud West Llama 3 max output to the model card 8K (#49543)
Compare 1639 commits »
scriptoriumadmin synced commits to refs/pull/45526/merge at scriptoriumadmin/litellm from mirror 2026-11-01 07:03:49 +00:00
1595adfb2f docs(model-catalog): explain meter, band, channel and When (#49447)
3cb2e60de0 fix(cost): split a provider-reported total between input and output by the cost map rate ratio (#49357)
b2647116ca chore(cost-map): add openai gpt-6-astra-law from the pricing page (#49444)
8ff495be96 fix(proxy): price OpenAI pass-through /v1/decisions calls like native Decisions (#49392)
Compare 446 commits »
scriptoriumadmin synced commits to refs/pull/45594/merge at scriptoriumadmin/litellm from mirror 2026-11-01 07:03:49 +00:00
febd340120 fix(guardrails)!: keep the upstream error when a /v1/messages stream ends in one (#49088)
27fbcd9895 fix(anthropic): map pause_turn and return refusal explanations on chat and responses (#49192)
281bf4e48b ci(circleci): clone the public repo over HTTPS so main jobs stop failing at checkout (#49394)
cee72ffdd6 fix(proxy): count native Responses WebSocket turn tokens toward key and tag TPM limits (#49257)
Compare 104 commits »
scriptoriumadmin synced commits to refs/pull/45005/merge at scriptoriumadmin/litellm from mirror 2026-11-01 07:03:48 +00:00
e5aa3d32cd fix(proxy): forward a valid metadata.user_id to Anthropic Messages on pass-through routes (#49333)
af070e7cd0 build(deps): bump pyasn1, pypdf and minimatch to clear osv-scan (#49362)
a392a39627 fix(vertex_ai): bill Claude web search per request on deployments priced in model_info (#49160)
d1d6d55063 fix(hosted_vllm): accept the vLLM production-stack router's file and batch objects (#49068)
Compare 431 commits »
scriptoriumadmin synced commits to refs/pull/44944/head at scriptoriumadmin/litellm from mirror 2026-11-01 07:03:48 +00:00
9a4372dd25 Merge branch 'main' into fix/responses-bridge-sequence-number
7143aeeb86 feat(passthrough): add Deepgram streaming text-to-speech WebSocket route (#49282)
3129e44848 ci: cut the weekly rc branch on Monday 3am PT instead of Friday (#49472)
d610dee7d0 docs(pr-template): add a handwritten 1-3 sentence description section (#49475)
ced995df6e fix(logging): drop a first-token time left over from a previous attempt (#47541)
Compare 80 commits »
scriptoriumadmin synced commits to refs/pull/44999/merge at scriptoriumadmin/litellm from mirror 2026-11-01 07:03:48 +00:00
8ff495be96 fix(proxy): price OpenAI pass-through /v1/decisions calls like native Decisions (#49392)
be4f3d36ce feat(accounting): capture request usage through the durable meter (#49133)
a713ed6bab fix(gemini): add thought_signature_in_tool_call_id to keep tool call ids short for clients that cap them (#47692)
febd340120 fix(guardrails)!: keep the upstream error when a /v1/messages stream ends in one (#49088)
Compare 26 commits »