scriptoriumadmin
  • Joined on 2026-03-01
scriptoriumadmin synced commits to refs/pull/47730/head at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:12 +00:00
5da82b56e4 Merge remote-tracking branch 'origin/main' into litellm_health_check_audio_output_probe
a0042f7a32 fix(health): look up a provider-prefixed base_model under its own provider and keep text-only operator modalities
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 363 commits »
scriptoriumadmin synced commits to refs/pull/47729/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:12 +00:00
0d24446c6d test(mcp): cover no-team admins' toolset access on LLM routes and drop a dead admin-check clause
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)
Compare 237 commits »
scriptoriumadmin synced commits to refs/pull/47729/head at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:12 +00:00
0d24446c6d test(mcp): cover no-team admins' toolset access on LLM routes and drop a dead admin-check clause
fb7583b528 test(responses): cover toolset name fallbacks and align MCP admin docstrings
4de4961587 Merge branch 'main' into litellm_mcp_admin_team_key_scope
be649f66a6 feat(azure_ai): reach Foundry agents through the project Responses API (#47717)
b96c1f30a6 feat(ocr)!: support outputContentFormat=markdown for Azure Document Intelligence (#48926)
Compare 417 commits »
scriptoriumadmin synced commits to refs/pull/47728/head at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:12 +00:00
3fab335add Merge remote-tracking branch 'origin/main' into litellm_autorouter_tool_turns_classifier
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)
26e53cb738 fix(cli): let the proxy decide when a classic lite login token has expired (#47712)
Compare 356 commits »
scriptoriumadmin synced commits to refs/pull/47749/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:12 +00:00
db8bcc999a Merge remote-tracking branch 'origin/main' into litellm_health_scope_like_auth
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 188 commits »
scriptoriumadmin synced commits to refs/pull/47716/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:11 +00:00
804d6c91b1 Merge branch 'main' of https://github.com/BerriAI/litellm into litellm_internal_copy_40078
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)
b96c1f30a6 feat(ocr)!: support outputContentFormat=markdown for Azure Document Intelligence (#48926)
Compare 181 commits »
scriptoriumadmin synced commits to refs/pull/47708/head at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:11 +00:00
1d5858862f test(proxy): boot the CLI tests on the real ProxyConfig config readers
a26294b275 Merge branch 'main' into litellm_suppress_startup_output
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 418 commits »
scriptoriumadmin synced commits to refs/pull/47703/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:11 +00:00
92f50b8164 fix(utils): refuse an oidc/google api_key on pass-through calls before any fetch
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 186 commits »
scriptoriumadmin synced commits to refs/pull/47703/head at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:11 +00:00
92f50b8164 fix(utils): refuse an oidc/google api_key on pass-through calls before any fetch
efe52b79b5 fix(secret_managers): keep get_secret's metadata wait, share concurrent google token fetches, refuse oidc/google on pass-through
2087d8bd89 Merge remote-tracking branch 'origin/main' into litellm_hosted_vllm_google_oidc_api_key
e2fd3eb8c5 fix(oidc): answer 503 on token-count routes during a metadata outage and fall back on a bad GCE_METADATA_TIMEOUT
cf7c35a117 fix(anthropic): map model_context_window_exceeded stop reason to length (#48874)
Compare 369 commits »
scriptoriumadmin synced commits to refs/pull/47708/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:11 +00:00
a66dc50efb test(json_fragment_accumulator): assert peak allocation instead of a drain timing ratio (#43370)
1d5858862f test(proxy): boot the CLI tests on the real ProxyConfig config readers
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 428 commits »
scriptoriumadmin synced commits to refs/pull/47717/head at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:11 +00:00
27b36fc904 fix(azure_ai): answer 400 for /responses/compact on a Foundry agent instead of calling the project with the agent name
092b86f2d3 fix(azure_ai): keep a Foundry agent version requested at the top level when extra_body also names the agent
0c9db4ef81 fix(azure_ai): keep instructions on plain Foundry models that return a null agent_reference
4ba77f56d5 Merge remote-tracking branch 'origin/main' into litellm_foundry_agent_responses_api
365d3d3729 feat(decisions): support Ollama decision models (#48871)
Compare 348 commits »
scriptoriumadmin synced commits to refs/pull/47722/head at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:11 +00:00
d150c818ca fix(proxy): keep a legacy model_max_budget row's stored cap when an org admin gives it a budget_duration
441a9297d0 fix(proxy): let an org admin give a legacy model_max_budget row a budget_duration at the same or a lower cap
7a0693e91f fix(proxy): check precedence when a team edit makes an unenforced model_max_budget entry take effect
67f921404b fix(proxy): name the entry holding the cap in the team model budget raise refusal
21b0cf1fcb docs(proxy): name pattern and access group keys in model_max_budget docstrings
Compare 276 commits »
scriptoriumadmin synced commits to refs/pull/47709/head at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:11 +00:00
f155703e59 Merge remote-tracking branch 'origin/main' into litellm_claude_code_marketplace_auth_required
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 400 commits »
scriptoriumadmin synced commits to refs/pull/47716/head at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:11 +00:00
804d6c91b1 Merge branch 'main' of https://github.com/BerriAI/litellm into litellm_internal_copy_40078
a2ef18b257 test(unit): keep unix socket paths in unit tests under the macOS AF_UNIX limit (#45040)
7fa65b3c5a fix(proxy): name a deployment's declared provider without resolving it in the Vertex AI Live scan
56e60d3b7d feat(router): daily_reset_time picks when deployment rpd and tpd daily limits start over (#48957)
f46adf80e4 fix(proxy): let typesafe/* allowlists cover /typesafe Jev calls and list Jev in the model picker (#47697)
Compare 414 commits »
scriptoriumadmin synced commits to refs/pull/47698/head at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:10 +00:00
5e6b326447 merge: main into litellm_responses_mcp_round_history
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 275 commits »
scriptoriumadmin synced commits to refs/pull/47702/head at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:10 +00:00
0c14826f58 Merge branch 'main' into litellm_silent_experiment_spend_row_flag
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 324 commits »
scriptoriumadmin synced commits to refs/pull/47697/head at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:09 +00:00
c93b2aae61 fix(ui): offer only the TypeSafe names the cost-map rule routes, and keep /v1/models listing as on main
c2c0d6fe7f Merge remote-tracking branch 'origin/main' into litellm_typesafe_project_key_allowlist
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)
Compare 318 commits »
scriptoriumadmin synced commits to refs/pull/47694/merge at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:09 +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 157 commits »
scriptoriumadmin synced commits to refs/pull/47692/head at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:08 +00:00
bce6d2893f fix(router): validate strict litellm params through a helper so star imports cannot re-bind a public Final
9be6f4cfc7 chore: merge main into litellm_gemini_tool_call_id_length
aa2195a995 fix(gemini): keep non-chat routes tolerant of a malformed thought_signature_in_tool_call_id, match tool results by exact id first, and keep the deployment's value when drop_params drops a malformed override
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 413 commits »
scriptoriumadmin synced commits to refs/pull/47693/head at scriptoriumadmin/litellm from mirror 2026-10-29 06:36:08 +00:00
fb7576eb8e fix(proxy): keep model updates that keep their route as on main
cdcae4756a fix(proxy): match a team model's called model through JSON provider prefixes too
15f6e551ef fix(proxy): follow the router's order for tied team patterns and annotate quota tests
8f00e1a839 fix(proxy): re-check team projects by every name a team model serves and check renamed names
761d2f7883 Merge origin/main into litellm_project_model_quota_policy
Compare 279 commits »