scriptoriumadmin
  • Joined on 2026-03-01
scriptoriumadmin synced commits to refs/pull/48563/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:32 +00:00
41c4c3788e test(routing): audit #46601 (#48910)
001a5f2320 Merge remote-tracking branch 'origin/main' into litellm_bigmodel
567383c503 feat(proxy)!: model family and access group entries in model_max_budget (#47722)
7d79824391 fix(gemini): preserve every grounding web source (#48745)
Compare 118 commits »
scriptoriumadmin synced commits to refs/pull/48564/head at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:32 +00:00
f633abb117 Merge remote-tracking branch 'upstream/main' into HEAD
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)
ca24b396da test(nvidia_riva): audit #41021 (#48801)
Compare 103 commits »
scriptoriumadmin synced commits to refs/pull/48564/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:32 +00:00
f633abb117 Merge remote-tracking branch 'upstream/main' into HEAD
38b4d31447 test(scim): audit #47544 (#48791)
356069d2ed test(mcp): audit #47422 (#48821)
3507781735 test(proxy): audit #47352 (#48804)
Compare 106 commits »
scriptoriumadmin synced commits to refs/pull/48556/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:32 +00:00
044f3284ab chore(cheapaimodel): regenerate provider endpoint support after merging main
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)
Compare 74 commits »
scriptoriumadmin synced commits to refs/pull/48556/head at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:32 +00:00
044f3284ab chore(cheapaimodel): regenerate provider endpoint support after merging main
8c050d04e3 Merge BerriAI/litellm main into add-cheapaimodel-provider
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)
Compare 67 commits »
scriptoriumadmin synced commits to refs/pull/48553/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:32 +00:00
4516a251c9 feat(accounting): add accounting contracts, PricingSnapshot and ledger schema (LIT-10193) (#48862)
cf7c35a117 fix(anthropic): map model_context_window_exceeded stop reason to length (#48874)
9007e0fa70 fix(files)!: scope provider and model file lists to the caller's managed files under require_managed_files (#47682)
dfd9ad4103 fix(responses)!: bill partial usage on mid-stream failures and report bridged /v1/messages failures to the proxy (#47537)
Compare 133 commits »
scriptoriumadmin synced commits to refs/pull/48549/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:32 +00:00
ff65785717 fix(router)!: count an explicit allowed_fails of 3 and keep fallback deployments out of cooldown (#46183)
f6f49d16cc feat: add ai& (aiand) provider (#38958)
d84a2d4452 test(spend): audit #47815 (#48774)
4b0aa0f446 fix(cost-map): drop the gpt-5-nano priority input price OpenAI does not sell (#48763)
Compare 79 commits »
scriptoriumadmin synced commits to refs/pull/48507/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:31 +00:00
f871be08d0 docs: group database guidance with migration rules
dd178b2f0e test(proxy): cover reconnect and refresh shutdown barriers
be649f66a6 feat(azure_ai): reach Foundry agents through the project Responses API (#47717)
Compare 213 commits »
scriptoriumadmin synced commits to refs/pull/48541/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:31 +00:00
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)
d9c9d84298 fix(proxy): stop log lines from leaving terminal colors on (#48966)
7aa7948a47 fix(health): ask OpenAI and Azure audio chat models for audio output in the health check probe (#47730)
Compare 196 commits »
scriptoriumadmin synced commits to refs/pull/48514/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:31 +00:00
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 238 commits »
scriptoriumadmin synced commits to refs/pull/48514/head at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:31 +00:00
de22512809 Merge branch 'main' into litellm_drop_clear_thinking_with_thinking
de42b67252 fix(proxy)!: enforce an end user's per-model budget from their linked budget (#48815)
5bd47442fb fix(cli): give lite codex aliases of a Codex-known model that model's catalog entry (#48894)
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)
Compare 263 commits »
scriptoriumadmin synced commits to refs/pull/48535/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:31 +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 102 commits »
scriptoriumadmin synced commits to refs/pull/48533/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:31 +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 156 commits »
scriptoriumadmin synced commits to refs/pull/48521/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:31 +00:00
554d3bebbb refactor(passthrough): trim the Deepgram speak helpers to what the route needs
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)
Compare 218 commits »
scriptoriumadmin synced commits to refs/pull/48521/head at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:31 +00:00
554d3bebbb refactor(passthrough): trim the Deepgram speak helpers to what the route needs
527f48755b fix(cost-map): drop mode from the Aura rows so Deepgram isn't listed as supporting /v1/audio/speech
d6b3d4f486 fix(deepgram): match only list channel_index in Results frames, as before the match rewrite
65c272337b fix(passthrough): bill a client frame whose upstream send is cancelled
df41566be9 test(passthrough): bill the speak relay tests through the real success handler
Compare 203 commits »
scriptoriumadmin synced commits to refs/pull/48520/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:31 +00:00
784b1fdb01 docs(auth): note that the Token Authorization scheme comes from Deepgram SDKs
b618285468 refactor(auth): read WebSocket keys with the shared Authorization parser
75c063124a feat(auth): accept a Token Authorization header on the Deepgram WebSocket route
cf7c35a117 fix(anthropic): map model_context_window_exceeded stop reason to length (#48874)
Compare 181 commits »
scriptoriumadmin synced commits to refs/pull/48520/head at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:31 +00:00
784b1fdb01 docs(auth): note that the Token Authorization scheme comes from Deepgram SDKs
b618285468 refactor(auth): read WebSocket keys with the shared Authorization parser
75c063124a feat(auth): accept a Token Authorization header on the Deepgram WebSocket route
Compare 3 commits »
scriptoriumadmin synced commits to refs/pull/48519/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:31 +00:00
c9257c005e refactor(passthrough): drop the _send_to_client docstring
cf7c35a117 fix(anthropic): map model_context_window_exceeded stop reason to length (#48874)
9007e0fa70 fix(files)!: scope provider and model file lists to the caller's managed files under require_managed_files (#47682)
dfd9ad4103 fix(responses)!: bill partial usage on mid-stream failures and report bridged /v1/messages failures to the proxy (#47537)
Compare 128 commits »
scriptoriumadmin synced commits to refs/pull/48519/head at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:31 +00:00
c9257c005e refactor(passthrough): drop the _send_to_client docstring
scriptoriumadmin synced commits to refs/pull/48517/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:31 +00:00
3b9a59348f fix(vertex_ai)!: send the caller's anthropic-version in the Vertex Claude /v1/messages body, not the header (#48814)
07d314beb5 test(responses): audit #47445 (#48902)
77cad6e903 test(proxy): audit #46997 (#48918)
e1580b7b83 refactor(images): remove dall-e-2 and dall-e-3 code paths (#48703)
Compare 143 commits »