scriptoriumadmin
  • Joined on 2026-03-01
scriptoriumadmin synced commits to refs/pull/40188/head at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:17 +00:00
e070ba501a fix(token_counter): support OpenAI 'input_audio' content blocks
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 627 commits »
scriptoriumadmin synced commits to refs/pull/40248/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:17 +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 116 commits »
scriptoriumadmin synced commits to refs/pull/40188/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:17 +00:00
b96c1f30a6 feat(ocr)!: support outputContentFormat=markdown for Azure Document Intelligence (#48926)
e070ba501a fix(token_counter): support OpenAI 'input_audio' content blocks
a2ef18b257 test(unit): keep unix socket paths in unit tests under the macOS AF_UNIX limit (#45040)
56e60d3b7d feat(router): daily_reset_time picks when deployment rpd and tpd daily limits start over (#48957)
Compare 479 commits »
scriptoriumadmin synced commits to refs/pull/40171/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:17 +00:00
d9aae590e3 fix(chatgpt): derive the upstream session id from prompt_cache_key (#42014)
74392efbd4 fix(otel): label configured pass-through routes litellm.passthrough and read the operation from the upstream (#48675)
4fa860b64c fix(vertex-ai): preserve image size aspect ratios (#48463)
208ef99b88 fix(images): honor max_retries and prevent Router retry amplification (#48705)
Compare 61 commits »
scriptoriumadmin synced commits to refs/pull/40066/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:17 +00:00
d69da65a6a fix(proxy): list wildcard models off the event loop, so a hung provider no longer stalls other requests
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 1425 commits »
scriptoriumadmin synced commits to refs/pull/40066/head at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:17 +00:00
d69da65a6a fix(proxy): list wildcard models off the event loop, so a hung provider no longer stalls other requests
7a575fea15 fix(discovery): cache only timed-out model listings, so a fast failure is tried again on the next call
4e109a03e9 fix(vllm): skip the placeholder key, honor deployment TLS and headers, and retry failed listings after a minute
1009886009 fix(vllm): list hosted_vllm models from the server chat uses, with a bounded wait
e44c8de305 Merge branch 'main' into litellm_wildcard_discovery_provider_config
Compare 1327 commits »
scriptoriumadmin synced commits to refs/pull/40011/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:17 +00:00
cfc651dcd5 fix(http): honor transport settings for Rust WebSockets (#47968)
6c0585b8f1 build(rust): upgrade reqwest to 0.13 and move MCP out of litellm-http (#48039)
38b4d31447 test(scim): audit #47544 (#48791)
356069d2ed test(mcp): audit #47422 (#48821)
Compare 117 commits »
scriptoriumadmin synced commits to refs/pull/40004/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:17 +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 110 commits »
scriptoriumadmin synced commits to refs/pull/39977/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:17 +00:00
6bdd0be5e6 fix(anthropic): merge main, keep pdf bytes a document, and match answered tool uses in one lookup
b96c1f30a6 feat(ocr)!: support outputContentFormat=markdown for Azure Document Intelligence (#48926)
a2ef18b257 test(unit): keep unix socket paths in unit tests under the macOS AF_UNIX limit (#45040)
56e60d3b7d feat(router): daily_reset_time picks when deployment rpd and tpd daily limits start over (#48957)
Compare 207 commits »
scriptoriumadmin synced commits to refs/pull/39977/head at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:17 +00:00
6bdd0be5e6 fix(anthropic): merge main, keep pdf bytes a document, and match answered tool uses in one lookup
3f526a5017 fix(websearch): strip Claude Code instructional prefix in short-circuit search (#43458)
8bbce867d0 feat(proxy): accept request priority from the x-litellm-priority header (#47618)
6063187fea test(spend): audit #47506 billed background cost reaching the creator's loggers (#48919)
8e8f6dc66e feat(tencent): add Seedream image generation and editing through TokenHub (#48735)
Compare 379 commits »
scriptoriumadmin synced commits to refs/pull/39864/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:16 +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 409 commits »
scriptoriumadmin synced commits to refs/pull/39868/head at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:16 +00:00
856751698a Merge remote-tracking branch 'origin/main' into litellm_fix_passthrough_failure_model_from_url
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 397 commits »
scriptoriumadmin synced commits to refs/pull/39555/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:16 +00:00
c997ed0eb1 fix(proxy): label shared-handler errors like the chat route, pick the status before the type, redact only gateway failures
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)
Compare 213 commits »
scriptoriumadmin synced commits to refs/pull/39868/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:16 +00:00
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)
d9c9d84298 fix(proxy): stop log lines from leaving terminal colors on (#48966)
Compare 215 commits »
scriptoriumadmin synced commits to refs/pull/39888/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:16 +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/39707/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:16 +00:00
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)
e4832c5d06 fix(cohere): map string stop parameter to list of strings for stop_sequences (#47091)
Compare 66 commits »
scriptoriumadmin synced commits to refs/pull/39734/head at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:16 +00:00
c44cc663fb Merge remote-tracking branch 'origin/main' into litellm_fix_sendgrid_reply_to
6fe0263761 fix(ui): prefill the key edit Organization picker from org_id (#39535)
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)
Compare 668 commits »
scriptoriumadmin synced commits to refs/pull/39734/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:16 +00:00
83ca14b392 fix(pricing): sync databricks model prices (#48884)
1bd9a0780a refactor(ui): use the shadcn Kbd primitive for keyboard hints (#48885)
7c7304c22b feat(providers): add ZeroGPU as an OpenAI-compatible provider (#43874)
ca6c830221 fix(proxy): account for media in combined TPM reservations (#48865)
Compare 86 commits »
scriptoriumadmin synced commits to refs/pull/39852/head at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:16 +00:00
7c4ef7c30d Merge remote-tracking branch 'origin/main' into litellm_lit_7019_hoist_developer_messages
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)
c40bdc475f fix(router)!: resolve trusted JEV connection environment references (#48717)
8c9a76859d fix(baseten): price the two decision models at their published input rates (#48849)
Compare 401 commits »
scriptoriumadmin synced commits to refs/pull/39864/head at scriptoriumadmin/litellm from mirror 2026-10-29 06:35:16 +00:00
ef52e611b3 fix(realtime): refuse unscreenable Gemini audio, send held setup after buffered audio, reject unknown Vertex voices
ebad57065f fix(realtime): keep Vertex activity detection off for null turn_detection and set up deferred sessions before text content
58089dfcb7 fix(realtime): ack unchanged Gemini Live session.update resends and honor null turn_detection
d8994c152a chore: merge main into litellm_lit_6974_gemini_live_lazy_setup
cf7c35a117 fix(anthropic): map model_context_window_exceeded stop reason to length (#48874)
Compare 361 commits »