ea35ab6d4e
day 0 blog post
2026-02-05 11:47:36 -08:00
dbd4bb5cf4
Add Claude Opus 4.6 ( #20508 )
...
Add Claude Opus 4.6 entries for Anthropic, Bedrock Converse, and Vertex AI.
Align pricing and capability metadata with Anthropic docs, including
long-context rates, above-200k prompt-caching rates, prefill removal,
and tool-use system prompt token counts.
Register the Bedrock Converse model ID in constants and add targeted
tests to validate model map values and converse registration.
2026-02-05 11:33:44 -08:00
eae5fa195e
[Feat] add claude-opus-4-6 to model cost map ( #20506 )
...
* add claude-opus-4-6 to model cost map
* fix azure_ai
* new model
2026-02-05 10:59:56 -08:00
d2bd029fa4
[Fix] 404 Not Found on /api/event_logging/batch endpoint ( #20504 )
...
* fix typing
* add event_logging_batch
* TestEventLoggingBatchEndpoint
2026-02-05 10:58:08 -08:00
f65eec8fa8
docs: Update CLI arguments documentation with all available options ( #20437 )
...
- Reorganized documentation into logical sections (Server Configuration,
Server Backend Options, SSL/TLS Configuration, Model Configuration,
Model Parameters, Database Configuration, Debugging, Testing & Health Checks)
- Added missing CLI arguments:
- --iam_token_db_auth: RDS IAM token authentication for database connections
- --run_gunicorn: Start proxy with gunicorn backend
- --run_hypercorn: Start proxy with hypercorn backend (HTTP/2 support)
- --ssl_keyfile_path, --ssl_certfile_path, --ciphers: SSL/TLS configuration
- --keepalive_timeout: Uvicorn keepalive timeout setting
- --max_requests_before_restart: Worker recycling for memory management
- --use_prisma_db_push: Alternative database schema update method
- --test_async, --num_requests: Async endpoint testing
- --version/-v: Print version
- --max_budget: Set budget limits for API calls
- --headers, --add_key, --save: Model configuration options
- --use_queue: Celery workers for async endpoints
- --local: Local debugging flag
- Updated default value for --num_workers to reflect actual behavior
- Added environment variable documentation for applicable options
Co-authored-by: Cursor Agent <cursoragent@cursor.com >
2026-02-05 08:46:37 -08:00
b74afec2be
Merge pull request #20398 from BerriAI/litellm_oss_staging_02_04_2026
...
Litellm oss staging 02 04 2026
2026-02-05 19:42:36 +05:30
df590be7af
Fix test_global_redaction_off_with_dynamic_params
2026-02-05 18:26:03 +05:30
34e5bb29a5
Merge pull request #20338 from Lucky-Lodhi2004/ttl-prompt-caching-bedrock
...
fix #20326 - [Feature]: Support TTL(1h) field in prompt caching for Bedrock Claude 4.5 models
2026-02-05 16:52:12 +05:30
fa733c252e
Merge branch 'litellm_oss_staging_02_04_2026' into ttl-prompt-caching-bedrock
2026-02-05 16:52:02 +05:30
7e8be5f542
Merge branch 'main' into ttl-prompt-caching-bedrock
2026-02-05 16:50:54 +05:30
a21b625a59
Merge pull request #20105 from qiniu/fix/vertex-gemini-streaming-content-filter
...
Fix Vertex AI Gemini streaming content_filter handling
2026-02-05 16:48:48 +05:30
453d1bd5e1
Merge branch 'main' into litellm_oss_staging_02_04_2026
2026-02-05 12:19:03 +05:30
075b1b7921
Merge pull request #20341 from natimofeev/bugfix/remove-user-messages-merging
...
bugfix: Disable merging of consecutive user messages for GigaChat provider
2026-02-05 12:18:09 +05:30
1017c3a0e4
Merge pull request #20464 from BerriAI/litellm_cicd_5_feb_2026
...
Litellm cicd 5 feb 2026
2026-02-05 11:03:35 +05:30
0ce1bfe26a
bump: version 1.81.7 → 1.81.8
2026-02-05 10:44:48 +05:30
5422a5962e
Fix test_route_a2a_model_bypasses_router
2026-02-05 09:47:05 +05:30
5e8c7f0de1
Fix mypy issues
2026-02-05 09:44:05 +05:30
0f177a3b01
Fix: test_team_update_sc_2
2026-02-05 09:40:21 +05:30
02ed25c886
Merge pull request #20461 from BerriAI/ui_build_fix_4
...
[Infra] Fixing UI Build
2026-02-04 20:05:50 -08:00
b982542c6c
fixing build
2026-02-04 20:05:10 -08:00
137413f8c1
Merge pull request #20460 from BerriAI/litellm_proxy_extras_bump_version_5_feb
...
chore: update poetry.lock for litellm-proxy-extras 0.4.30
2026-02-05 09:28:10 +05:30
64aeb18a10
chore: update poetry.lock for litellm-proxy-extras 0.4.30
...
Co-authored-by: Cursor <cursoragent@cursor.com >
2026-02-05 09:25:52 +05:30
cda4b72e2d
Merge pull request #20458 from BerriAI/litellm_proxy_extras_bump_version_5_feb
...
bump: litellm-proxy-extras 0.4.29 → 0.4.30
2026-02-05 09:22:29 +05:30
3c12dda856
bump: litellm-proxy-extras 0.4.29 → 0.4.30
...
- Add allow_team_guardrail_config field to TeamTable and DeletedTeamTable
- Add migration 20260205091235_allow_team_guardrail_config
2026-02-05 09:21:20 +05:30
e0802783f3
feat(openrouter): add Qwen3-235B models ( #20455 )
...
Add OpenRouter Qwen3-235B-A22B models to the pricing configuration:
- openrouter/qwen/qwen3-235b-a22b-2507
- openrouter/qwen/qwen3-235b-a22b-thinking-2507
Closes request from PR #13019 comments.
2026-02-04 19:35:22 -08:00
47b546f69a
fix(lint): remove unused Any/cast imports in github_copilot transformation ( #20431 )
...
The cast(Any, message) pattern was used to suppress typed-dict mutation
warnings, but the parameter has no type annotation so it's unnecessary.
Direct assignment works and eliminates the F401 unused-import lint error.
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com >
2026-02-04 18:41:01 -08:00
8e1201ca3d
docs: improve Okta SSO setup guide with step-by-step instructions ( #20353 )
...
* docs: improve Okta SSO setup guide with step-by-step instructions
- Add clear steps for creating OIDC app in Okta Admin Console
- Document critical Authorization Server Access Policy configuration
- Add troubleshooting table for common errors
- Link to official Okta documentation for detailed UI instructions
- Fix incorrect OAuth endpoint examples (was using Auth0 URLs)
* docs: add Okta console screenshots for SSO setup guide
- Add screenshot showing Sign-in redirect URI configuration
- Add screenshot showing Client Credentials location
- Add screenshot showing Authorization Server Access Policy setup
* docs: replace Okta screenshots with annotated Scribe versions
- Replace screenshots with Scribe-annotated versions highlighting key areas
- Add step-by-step screenshots for Authorization Server Access Policy setup
- Remove old unannotated screenshots
2026-02-04 18:39:51 -08:00
15b717c300
[Feat] UI - Add support for MCP Semantic Filtering on UI ( #20454 )
...
* feat: remove_callbacks_by_type
* feat: _init_semantic_filter_settings_in_db
* add MCP semantic filtering settings endpoints
* v0 - semantic filter UI
* fix endpint _init_semantic_filter_settings_in_db
* refactor ui
* add LITELLM_UI_ALLOW_HEADERS
* ui fix
* ui fix
2026-02-04 18:38:53 -08:00
2a3843aa57
[Fix] inconsistent response format in anthropic.messages.acreate() when using non anthropic providers ( #20442 )
...
* _translate_openai_content_to_anthropic
* test_response_format_consistency
* test fixes unit tests
* test fix
* fix: use dict access for anthropic content blocks in tests (#20447 )
The translate_openai_response_to_anthropic method returns dicts, not objects.
Changed .type/.text/.thinking attribute access to dict ['key'] access.
---------
Co-authored-by: shin-bot-litellm <shin-bot-litellm@berri.ai >
2026-02-04 16:37:40 -08:00
6a73e5bd37
Revert "fix(a2a): use text/event-stream SSE format for message/stream endpoin…" ( #20446 )
...
This reverts commit 0209b214ac
2026-02-04 16:08:22 -08:00
0209b214ac
fix(a2a): use text/event-stream SSE format for message/stream endpoint ( #20365 )
...
* fix(a2a): use text/event-stream SSE format for message/stream endpoint
The A2A gateway's streaming response was using application/x-ndjson
Content-Type and raw NDJSON body format. The A2A protocol spec requires
text/event-stream with SSE framing (data: ...\n\n).
The official a2a-sdk client validates the Content-Type header and raises
SSEError when it doesn't contain text/event-stream.
Changes:
- Changed media_type from application/x-ndjson to text/event-stream
- Updated response body to use SSE framing (data: prefix + \n\n suffix)
- Added tests validating Content-Type and SSE body format
Fixes #20278
* Potential fix for code scanning alert no. 4045: Information exposure through an exception
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
* test(a2a): add manual SSE format validation script
Adds a manual test script that:
1. Starts a real A2A agent on port 10001
2. Starts LiteLLM proxy with the agent registered
3. Makes a streaming request to the proxy's A2A gateway
4. Validates Content-Type header is text/event-stream
5. Validates body uses SSE framing (data: ...\n\n)
Run: python tests/a2a_manual/test_a2a_sse_manual.py
---------
Co-authored-by: shin-bot-litellm <shin-bot-litellm@users.noreply.github.com >
Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com >
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
2026-02-04 16:07:17 -08:00
795ba8efe3
Merge pull request #20443 from BerriAI/docs_langfuse_multi_project_cred_support
...
langfuse doc update
2026-02-04 15:55:04 -08:00
555e1da9b4
langfuse doc update
2026-02-04 15:53:24 -08:00
d1994a148d
Fix mypy type error in fireworks_ai transformation ( #20391 )
...
Cast message to dict before calling pop() to satisfy mypy's type checker.
The message is typed as a Union of TypedDicts which don't have the
'provider_specific_fields' key, but the runtime check already confirms
it's a dict with this key.
2026-02-04 15:44:45 -08:00
d2e113111f
Merge pull request #20436 from BerriAI/litellm_search_tools_config_ui
...
[Feature] UI - Search Tools: Show Config Defined Search Tools
2026-02-04 13:56:19 -08:00
cd9466a50c
Adding tests
2026-02-04 12:35:58 -08:00
609c423314
migrate to antd table
2026-02-04 12:22:57 -08:00
208cf5e86d
refactor - rename search tools files
2026-02-04 11:53:03 -08:00
a16faa9e0a
Merge pull request #20394 from BerriAI/litellm_spend_fix_2
...
[Fix] Unique Constraint on Daily Tables + Logging When Updates Fail
2026-02-04 09:42:46 -08:00
e4b45dc32e
Merge branch 'main' into ttl-prompt-caching-bedrock
2026-02-04 18:52:28 +05:30
31e2e727e3
fixed linting
2026-02-04 13:20:40 +00:00
bfabb39fc6
fix: Fix Vertex AI Gemini streaming content_filter handling
...
- Add promptFeedback.blockReason check in chunk_parser
- Return content_filter finish_reason when blocked
- Extract content filter logic into _check_prompt_level_content_filter() method
- Update unit tests to reflect simplified implementation
Signed-off-by: Kris Xia <xiajiayi0506@gmail.com >
2026-02-04 21:11:47 +08:00
1e55e61907
made changes suggested by agent
2026-02-04 13:10:37 +00:00
8b563a7641
Merge pull request #20402 from BerriAI/litellm_responses_tools_file_ids
...
Add mapping for responses tools in file ids
2026-02-04 18:09:39 +05:30
8a3b253e62
Merge pull request #20390 from BerriAI/litellm_fix_empty_message
...
Fix: empty assistant message for converse API
2026-02-04 18:05:37 +05:30
18a524a1dc
Merge pull request #20408 from BerriAI/litellm_fix_model+map_streaming
...
Fix supports_native_streaming for gemini and vertex ai and claude models
2026-02-04 17:56:48 +05:30
a86e501632
Merge pull request #20407 from BerriAI/litellm_key_mcp_permissions
...
Add Key info endpoint object permission data
2026-02-04 17:56:05 +05:30
1a5f2a566f
Fix: test_bedrock_no_default_message
2026-02-04 17:52:28 +05:30
b2feedc469
Merge pull request #20318 from BerriAI/litellm_oss_staging_02_03_2026
...
feat(guardrails): implement team-based isolation guardrails mgmnt (#1…
2026-02-04 17:49:30 +05:30
54b5c7d2cd
Fix: litellm/tests/test_litellm/proxy/guardrails/guardrail_hooks/test_grayswan.py
2026-02-04 17:35:26 +05:30
Ishaan Jaffer