scriptoriumadmin
  • Joined on 2026-03-01
scriptoriumadmin synced commits to refs/pull/42737/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:35 +00:00
ddb8a14ee9 feat(skills): add a litellm-setup agent skill (#47731)
41c4c3788e test(routing): audit #46601 (#48910)
567383c503 feat(proxy)!: model family and access group entries in model_max_budget (#47722)
7d79824391 fix(gemini): preserve every grounding web source (#48745)
Compare 171 commits »
scriptoriumadmin synced commits to refs/pull/42876/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:35 +00:00
ff5bf4826d fix(count_tokens)!: audit #47441 and keep the framed estimate for Bedrock count models from the cost map (#48805)
9b1d69e32c fix(images): normalize absent images in async edits (#48872)
7abff3dd63 fix(mistral): replay assistant reasoning as a Mistral thinking chunk (#48778)
20427f4555 chore(cost-map): add fireworks spot serverless router rows from the prices api (#48858)
Compare 135 commits »
scriptoriumadmin synced commits to refs/pull/42950/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:35 +00:00
dfd9ad4103 fix(responses)!: bill partial usage on mid-stream failures and report bridged /v1/messages failures to the proxy (#47537)
a604c89059 fix(ui): bundle the Aria avatar so it loads in every deployment (#48890)
aa769fbc69 fix(streaming): surface upstream abort as server errors (LIT-10159) (#48328)
1f68cc5649 refactor(rust-bridge): require the native extension (#48852)
Compare 134 commits »
scriptoriumadmin synced commits to refs/pull/42683/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:35 +00:00
e32d8a4d03 fix(responses): reject or drop Responses params the chat completions bridge cannot translate (#48655)
df9091deb6 fix(responses): skip failed spend-log turns when rebuilding a session from previous_response_id (#48647)
c7c895db45 fix(proxy)!: paginate customer lists and usage filters (#48700)
7acdf9f00d fix(anthropic): count search results and reject unsupported token-count blocks (#48699)
Compare 120 commits »
scriptoriumadmin synced commits to refs/pull/42539/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:35 +00:00
356069d2ed test(mcp): audit #47422 (#48821)
3507781735 test(proxy): audit #47352 (#48804)
295d79fc7d feat(cli): keep the ChatGPT login with lite codex --subscription (#48741)
0ceca31081 feat(proxy): per-provider and per-model rpm/tpm requirements for enforce_project_model_quota (#47693)
Compare 58 commits »
scriptoriumadmin synced commits to refs/pull/42417/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:35 +00:00
d009dc184a fix(cost): pass only per-second rates to native /v1/messages cost tracking
a66dc50efb test(json_fragment_accumulator): assert peak allocation instead of a drain timing ratio (#43370)
cbf4e40d38 fix(proxy)!: stop labelling management and health rejections as auth failures (#48739)
a11e76fe8f fix(google_genai): read one-object and null spellings of repeated fields in countTokens and generateContent (#48771)
Compare 2357 commits »
scriptoriumadmin synced commits to refs/pull/42466/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:35 +00:00
ddb8a14ee9 feat(skills): add a litellm-setup agent skill (#47731)
41c4c3788e test(routing): audit #46601 (#48910)
567383c503 feat(proxy)!: model family and access group entries in model_max_budget (#47722)
7d79824391 fix(gemini): preserve every grounding web source (#48745)
Compare 171 commits »
scriptoriumadmin synced commits to refs/pull/42417/head at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:34 +00:00
d009dc184a fix(cost): pass only per-second rates to native /v1/messages cost tracking
e4d6586b87 fix(anthropic): bill a deployment's per-second rate only on the native /v1/messages route
6628372b1b fix(cost): price a /v1/messages call off the response time the proxy reports
d48b42afa4 Merge origin/main and bill the deployment rate once in the per-second tests
c6ca22ebc5 fix(guardrails)!: make hide-secrets honor skip_tool_message_in_guardrail (#48689)
Compare 2678 commits »
scriptoriumadmin synced commits to refs/pull/42188/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:34 +00:00
cbf4e40d38 fix(proxy)!: stop labelling management and health rejections as auth failures (#48739)
a11e76fe8f fix(google_genai): read one-object and null spellings of repeated fields in countTokens and generateContent (#48771)
764a7a6536 fix(context_management)!: count the system prompt toward the clear_tool_uses input_tokens trigger (#47857)
de42b67252 fix(proxy)!: enforce an end user's per-model budget from their linked budget (#48815)
Compare 226 commits »
scriptoriumadmin synced commits to refs/pull/42068/head at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:34 +00:00
80aec726f0 chore(ui): resolve WebSocket pretty-view merge conflicts
scriptoriumadmin synced commits to refs/pull/41983/head at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:34 +00:00
3eee70cb9b Merge remote-tracking branch 'upstream/main' into fix-responses-stream-nulls
cdf73f4683 chore(proxy): remove unused TypeIs import
291999d409 Merge remote-tracking branch 'upstream/main' into fix-responses-stream-nulls
Compare 3 commits »
scriptoriumadmin synced commits to refs/pull/42142/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:34 +00:00
c7c895db45 fix(proxy)!: paginate customer lists and usage filters (#48700)
7acdf9f00d fix(anthropic): count search results and reject unsupported token-count blocks (#48699)
e4832c5d06 fix(cohere): map string stop parameter to list of strings for stop_sequences (#47091)
1171273511 fix(langfuse otel): emit request metadata under langfuse.observation.metadata and langfuse.trace.metadata on the OTEL v2 Langfuse mapper (#42697)
Compare 76 commits »
scriptoriumadmin synced commits to refs/pull/42014/head at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:34 +00:00
125926789b fix(chatgpt): keep the trace-id session marker out of provider params
4004d1f2b2 fix(chatgpt): mark session ids copied from trace_id so explicit ones keep precedence
1896516989 fix(chatgpt): keep trace ids copied into litellm_session_id from outranking prompt_cache_key
5e0fbe14a3 test(chatgpt): type the session id test parameters
141547771a fix(chatgpt): hash cache keys with leading or trailing whitespace so the session header stays valid
Compare 1849 commits »
scriptoriumadmin synced commits to refs/pull/41919/head at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:33 +00:00
1241046c57 fix(topxai): follow current catalogue schema and endpoint generation
4a58d85192 fix(providers): sync TopxAI with current provider registry
94e4ebd63d test(proxy): pin the max_parallel_requests slot release when a streamed /v1/messages MCP auto-execute ends (#47788)
d8a43a7cd3 test(gemini): audit #47542 (#48758)
000d4f6bb3 test(sagemaker): audit #47495 (#48767)
Compare 159 commits »
scriptoriumadmin synced commits to refs/pull/41959/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:33 +00:00
c59c1db2ae chore: re-run CI against current main
bad98c4b02 fix(responses): call the renamed drops_params helper on the compact path (#49030)
b059d8938e refactor(vertex_ai): mark the new Vertex registry sets Final
b7da9a2755 fix(credentials): keep the stored secret when PATCH echoes its masked read-back (#48950)
Compare 2480 commits »
scriptoriumadmin synced commits to refs/pull/41809/head at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:33 +00:00
906339f2ee fix(mcp): freeze new header dicts to satisfy LIT002 type-discipline budget
7b9fa62549 fix(mcp): forward caller's extra headers in true_passthrough auth probe
38b4d31447 test(scim): audit #47544 (#48791)
356069d2ed test(mcp): audit #47422 (#48821)
3507781735 test(proxy): audit #47352 (#48804)
Compare 1880 commits »
scriptoriumadmin synced commits to refs/pull/41809/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:33 +00:00
0f68b9919c fix(guardrails): skip embeddings input in google_text_moderation (#48934)
4e5f585c2a fix(guardrails): scan Responses tool results in texts-mode guardrails (#48827)
83ae1bd63e fix(responses): drop params compact rejects and send Azure compaction to the v1 route (#48876)
4fc2bba1f2 fix(stream): the last usage frame carries litellm's bill in usage.cost (#48955)
Compare 204 commits »
scriptoriumadmin synced commits to refs/pull/41818/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:33 +00:00
a45c2023ce fix(audio): return 400 for unsupported transcription providers (#47971)
a0c9a5993b fix(batches): stop unbillable batches from blocking file deletes and new-batch polling (#48752)
78d6c1aa82 fix(router): pass lifecycle events through on background OpenAI responses streams that cannot fall back (#48817)
ca4a2ba006 fix(router): drop the deployment rpm filter from enable_pre_call_checks (#48873)
Compare 140 commits »
scriptoriumadmin synced commits to refs/pull/41869/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:33 +00:00
ff5bf4826d fix(count_tokens)!: audit #47441 and keep the framed estimate for Bedrock count models from the cost map (#48805)
9b1d69e32c fix(images): normalize absent images in async edits (#48872)
7abff3dd63 fix(mistral): replay assistant reasoning as a Mistral thinking chunk (#48778)
20427f4555 chore(cost-map): add fireworks spot serverless router rows from the prices api (#48858)
Compare 134 commits »
scriptoriumadmin synced commits to refs/pull/41959/head at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:33 +00:00
c59c1db2ae chore: re-run CI against current main
b059d8938e refactor(vertex_ai): mark the new Vertex registry sets Final
20880a6731 fix(health): keep wildcard health picks that only route through a saved custom_llm_provider
e598104c7a fix(health): match wildcard health picks against the provider's own route
bf6da246cf fix(health): only health-check ids the router sends to the provider
Compare 4117 commits »