scriptoriumadmin
  • Joined on 2026-03-01
scriptoriumadmin synced commits to refs/pull/44070/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:41 +00:00
1176e608b1 test(harness): audit #47530 (#48751)
220a70653e docs(readme): link the LiteLLM OSS Champions program from Contributing (#48734)
f1795e6d44 fix(responses): keep every MCP tool round in streaming follow-up input (#47698)
6fe0263761 fix(ui): prefill the key edit Organization picker from org_id (#39535)
Compare 82 commits »
scriptoriumadmin synced commits to refs/pull/44163/head at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:41 +00:00
2eb57913f2 chore(tokenify): regenerate provider endpoint support matrix
scriptoriumadmin synced commits to refs/pull/44107/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:41 +00:00
59914547d7 fix(gemini): handle regional prefixes and disabled thinking on gemini 3+
dbaae521f9 fix(responses): drop the null created_by OpenAI rejects when output items are replayed (#48783)
b1b5d16f0b docs(adrs): add ADRs for the Python SDK and proxy, starting with provider usage extras (#36668)
be649f66a6 feat(azure_ai): reach Foundry agents through the project Responses API (#47717)
Compare 826 commits »
scriptoriumadmin synced commits to refs/pull/44189/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:41 +00:00
38b4d31447 test(scim): audit #47544 (#48791)
356069d2ed test(mcp): audit #47422 (#48821)
3507781735 test(proxy): audit #47352 (#48804)
295d79fc7d feat(cli): keep the ChatGPT login with lite codex --subscription (#48741)
Compare 61 commits »
scriptoriumadmin synced commits to refs/pull/43874/head at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:40 +00:00
c39b95458e fix(zerogpu): flag vision on gpt-6-luna and qwen3.6-35b-a3b
8696197456 fix(zerogpu): set qwen3.6-35b-a3b context to 262144 and flag its tools and reasoning
ace778d011 fix(zerogpu): flag tools, json_schema and prompt caching on gpt-6-luna
25d56024f9 chore(zerogpu): regenerate provider endpoint support for zerogpu
2e0c6da454 fix(zerogpu): drop the retired max_tokens field from the zerogpu rows
Compare 276 commits »
scriptoriumadmin synced commits to refs/pull/43818/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:40 +00:00
bad98c4b02 fix(responses): call the renamed drops_params helper on the compact path (#49030)
b7da9a2755 fix(credentials): keep the stored secret when PATCH echoes its masked read-back (#48950)
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)
Compare 239 commits »
scriptoriumadmin synced commits to refs/pull/43774/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:39 +00:00
a57d01ab03 fix(terraform): allow responses, realtime and other in-use modes on litellm_model
7c7304c22b feat(providers): add ZeroGPU as an OpenAI-compatible provider (#43874)
ca6c830221 fix(proxy): account for media in combined TPM reservations (#48865)
9675c13cb0 fix(openai)!: send the whole reasoning_effort dict when chat is bridged to Responses (#48807)
Compare 882 commits »
scriptoriumadmin synced commits to refs/pull/43774/head at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:39 +00:00
a57d01ab03 fix(terraform): allow responses, realtime and other in-use modes on litellm_model
7c7304c22b feat(providers): add ZeroGPU as an OpenAI-compatible provider (#43874)
ca6c830221 fix(proxy): account for media in combined TPM reservations (#48865)
9675c13cb0 fix(openai)!: send the whole reasoning_effort dict when chat is bridged to Responses (#48807)
41fcce62ff fix(gemini)!: accept Google's current Managed Agents fields on create and interactions (#48750)
Compare 2093 commits »
scriptoriumadmin synced commits to refs/pull/43502/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:38 +00:00
8c41f0d44d chore: sync with upstream main
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 219 commits »
scriptoriumadmin synced commits to refs/pull/43686/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:38 +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 139 commits »
scriptoriumadmin synced commits to refs/pull/43696/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:38 +00:00
38b4d31447 test(scim): audit #47544 (#48791)
356069d2ed test(mcp): audit #47422 (#48821)
3507781735 test(proxy): audit #47352 (#48804)
295d79fc7d feat(cli): keep the ChatGPT login with lite codex --subscription (#48741)
Compare 77 commits »
scriptoriumadmin synced commits to refs/pull/43697/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:38 +00:00
7aa7948a47 fix(health): ask OpenAI and Azure audio chat models for audio output in the health check probe (#47730)
e4932a4539 test(router): set string fallback targets after Router init in the sdk cooldown cases (#48954)
57c1df8c33 refactor(model-catalog): parse, lower and validate the catalog into typed prices (#48853)
3b9a59348f fix(vertex_ai)!: send the caller's anthropic-version in the Vertex Claude /v1/messages body, not the header (#48814)
Compare 152 commits »
scriptoriumadmin synced commits to refs/pull/43532/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:38 +00:00
b7da9a2755 fix(credentials): keep the stored secret when PATCH echoes its masked read-back (#48950)
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 218 commits »
scriptoriumadmin synced commits to refs/pull/43573/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:38 +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 135 commits »
scriptoriumadmin synced commits to refs/pull/43615/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:38 +00:00
b7da9a2755 fix(credentials): keep the stored secret when PATCH echoes its masked read-back (#48950)
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 228 commits »
scriptoriumadmin synced commits to refs/pull/43691/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:38 +00:00
ca4a2ba006 fix(router): drop the deployment rpm filter from enable_pre_call_checks (#48873)
43ce3e22aa fix(responses)!: answer 400 before counting a lone Responses built-in tool on Claude (#48798)
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)
Compare 136 commits »
scriptoriumadmin synced commits to refs/pull/43659/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:38 +00:00
49ccce7813 test(extraction): audit #47473 (#48898)
7650f766b0 refactor(router): fence the router surface and document the router-core boundary (#48839)
d06b889d41 fix(streaming): keep merged think tags balanced and split SSE lines only on CR/LF (#48755)
ab07b7207e fix(vertex-ai): add batch above 200k and image output batch prices for gemini models (#48945)
Compare 123 commits »
scriptoriumadmin synced commits to refs/pull/43668/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:38 +00:00
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)
019a9de603 fix(logging): stop dumping the request body at every layer under --detailed_debug (#48973)
57f05e56f6 fix(bedrock): omit system prompt from audio transcription and report its token usage (#41565)
Compare 136 commits »
scriptoriumadmin synced commits to refs/pull/43458/head at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:37 +00:00
028a0e5a8b fix(websearch): search only the query inside Claude Code's web search prompt
40ef1e120f Merge remote-tracking branch 'origin/main' into litellm_pr43458_websearch_prefix
aa769fbc69 fix(streaming): surface upstream abort as server errors (LIT-10159) (#48328)
1f68cc5649 refactor(rust-bridge): require the native extension (#48852)
99ac0d3e39 fix(aiohttp_openai): forward service_tier in transform_response (#47263)
Compare 598 commits »
scriptoriumadmin synced commits to refs/pull/43502/head at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:37 +00:00
8c41f0d44d chore: sync with upstream main
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)
764a7a6536 fix(context_management)!: count the system prompt toward the clear_tool_uses input_tokens trigger (#47857)
Compare 220 commits »