Adds log_format parameter supporting json_array (default), ndjson, and single formats. NDJSON format enables webhook integrations like Sumo Logic to parse individual log records at ingest time. Defaults to json_array for backward compatibility.
* feat(generic_api_callback.py): make generic api OSS + support multiple generic API's
Enables https://github.com/BerriAI/litellm/pull/17094#discussion_r2562832967
* feat(callback_utils.py): support custom generic api callbacks
* feat(generic_api_callback.py): support specifying which event types to run the generic api for
* fix(litellm_logging.py): log system prompt for anthropic messages
* feat(generic_api_callback.py): support generic api compatible api's - e.g. rubrik agent cloud
* docs(sidebars.js): document new OSS generic api
* docs(generic_api.md): document new OSS Generic API
* docs(custom_webhook_api.md): document custom webhook api integration tutorial
* docs(custom_webhook_api.md): cleanup
* docs(custom_webhook_api.md): document what get's logged to custom webhook api
* Refactor: Pass callback config to GenericAPILogger
Co-authored-by: krrishdholakia <krrishdholakia@gmail.com>
* Fix: Handle empty messages list in logging payload
Co-authored-by: krrishdholakia <krrishdholakia@gmail.com>
* Checkpoint before follow-up message
Co-authored-by: krrishdholakia <krrishdholakia@gmail.com>
* feat: Cache GenericAPILogger instances to improve performance
Co-authored-by: krrishdholakia <krrishdholakia@gmail.com>
---------
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
* Litellm dev 11 22 2025 p1 (#16975)
* fix(model_armor.py): return response after applying changes
* fix: initial commit adding guardrail span logging to otel on post-call runs
sends it as a separate span right now, need to include in the same llm request/response span
* fix(opentelemetry.py): include guardrail in received request log + set input/ouput fields on parent otel span instead of nesting it
allows request/response to be seen easily on observability tools
* fix(model_armor.py): working model armor logging on post call events
* fix: fix exception message
* fix(opentelemetry.py): add backwards compatibility for litellm_request
allow users building on the spec change to use previous spec
* feat(anthropic/chat/transformations): for claude-4-5-sonnet and opus-4-1 support passing structured output to anthropic api
* docs: document new feature
* fix: fix output format
* fix: cleanup
* fix(transformation.py): conditionally pass in json tool call
* fix: support ARIZE_SPACE_ID instead of ARIZE_SPACE_KEY
* docs(arize_integration.md): cleanup arize docs
* feat(callback_info_helpers.tsx): allow setting arize space id via ui
* fix: fix linting error
* fix(opentelemetry.py): working arize phoenix root span tracing
* [Feat] Add SENTRY_ENVIRONMENT configuration for Sentry integration and corresponding tests
* [Refactor] Enhance test_sentry_environment by mocking sentry_sdk and improving environment handling
* [Fix] Update default SENTRY_ENVIRONMENT to 'production' and enhance test for Sentry integration
* [Fix] Update test_sentry_environment to verify correct handling of SENTRY_ENVIRONMENT values
* [Fix] Update test_sentry_environment to assert correct handling of production environment
* docs: Corrected documentation updates from Sept 2025
This PR contains the actual intended documentation changes, properly synced with main:
✅ Real changes applied:
- Added AWS authentication link to bedrock guardrails documentation
- Updated Vertex AI with Gemini API alternative configuration
- Added async_post_call_success_hook code snippet to custom callback docs
- Added SSO free for up to 5 users information to enterprise and custom_sso docs
- Added SSO free information block to security.md
- Added cancel response API usage and curl example to response_api.md
- Added image for modifying default user budget via admin UI
- Re-ordered sidebars in documentation
❌ Sync issues resolved:
- Kept all upstream changes that were added to main after branch diverged
- Preserved Provider-Specific Metadata Parameters section that was added upstream
- Maintained proper curl parameter formatting (-d instead of -D)
This corrects the sync issues from the original PR #14769.
* docs: Restore missing files from original PR
Added back ~16 missing documentation files that were part of the original PR:
✅ Restored files:
- docs/my-website/docs/completion/usage.md
- docs/my-website/docs/fine_tuning.md
- docs/my-website/docs/getting_started.md
- docs/my-website/docs/image_edits.md
- docs/my-website/docs/image_generation.md
- docs/my-website/docs/index.md
- docs/my-website/docs/moderation.md
- docs/my-website/docs/observability/callbacks.md
- docs/my-website/docs/providers/bedrock.md
- docs/my-website/docs/proxy/caching.md
- docs/my-website/docs/proxy/config_settings.md
- docs/my-website/docs/proxy/db_deadlocks.md
- docs/my-website/docs/proxy/load_balancing.md
- docs/my-website/docs/proxy_api.md
- docs/my-website/docs/rerank.md
✅ Fixed context-caching issue:
- Restored provider_specific_params.md to main version (preserving Provider-Specific Metadata Parameters section)
- Your original PR didn't intend to modify this file - it was just a sync issue
Now includes all ~26 documentation files from the original PR #14769.
* docs: Remove files that were deleted in original PR
- Removed docs/my-website/docs/providers/azure_ai_img_edit.md (was deleted in original PR)
- sdk/headers.md was already not present
Now matches the complete intended changes from original PR #14769.
* docs: Restore azure_ai_img_edit.md from main
- Restored docs/my-website/docs/providers/azure_ai_img_edit.md from main branch
- This file should not have been deleted as it was a newer commit
- SDK headers file doesn't exist in main (was reverted) and wasn't part of your original changes
Fixes the file restoration issues.
* docs: Fix vertex.md - preserve context caching from newer commit
- Restored vertex.md to main version to preserve context caching content (lines 817-887)
- Added back only your intended change: alternative gemini config example
- Context caching content from newer commit is now preserved
Fixes the vertex.md sync issue where newer content was incorrectly deleted.
* docs: Fix providers/bedrock.md - restore deleted content from newer commit
- Restored providers/bedrock.md to main version
- Preserves 'Usage - Request Metadata' section that was added in newer commit
- Your actual intended change was to proxy/guardrails/bedrock.md (authentication tip) which is preserved
- Now only has additions, no subtractions as intended
Fixes the bedrock.md sync issue.
* docs: Restore missing IAM policy section in bedrock.md
Added back your intended IAM policy documentation that was lost when restoring main version:
✅ Added IAM AssumeRole Policy section:
- Explains requirement for sts:AssumeRole permission
- Shows error message example when permission missing
- Provides complete IAM policy JSON example
- Links to AWS AssumeRole documentation
- Clarifies trust policy requirements
Now bedrock.md has both:
- All newer content preserved (Request Metadata section)
- Your intended IAM policy addition restored
---------
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
* feat(langfuse-otel): Add comprehensive metadata support to Langfuse OpenTelemetry integration
This commit brings the langfuse_otel integration to feature parity with the vanilla Langfuse integration by adding support for all metadata fields.
Changes:
- Extended LangfuseSpanAttributes enum with all supported metadata fields:
- Generation-level: generation_name, generation_id, parent_observation_id, version, mask_input/output
- Trace-level: trace_user_id, session_id, tags, trace_name, trace_id, trace_metadata, trace_version, trace_release, existing_trace_id, update_trace_keys
- Debug: debug_langfuse
- Implemented metadata extraction and mapping in langfuse_otel.py:
- Added _extract_langfuse_metadata() helper to extract metadata from kwargs
- Support for header-based metadata (langfuse_* headers) via proxy
- Enhanced _set_langfuse_specific_attributes() to map all metadata to OTEL attributes
- JSON serialization for complex types (lists, dicts) for OTEL compatibility
- Updated documentation:
- Added 'Metadata Support' section explaining all fields are now supported
- Provided usage example showing how to pass metadata
- Clarified that traces are viewed in Langfuse UI (not generic OTEL backends)
- Added opentelemetry-exporter-otlp to required dependencies
This allows users to pass metadata like:
metadata={
'generation_name': 'my-generation',
'trace_id': 'trace-123',
'session_id': 'session-456',
'tags': ['prod', 'v1'],
'trace_metadata': {'user_type': 'premium'}
}
All metadata is exported as OpenTelemetry span attributes with 'langfuse.*' prefix for easy filtering and analysis in the Langfuse UI.
* Fix ruff linting error
* test(langfuse-otel): Fix failing test and add comprehensive metadata tests
- Fix test_set_langfuse_environment_attribute to use positional arguments
instead of keyword arguments when asserting safe_set_attribute calls
- Add test_extract_langfuse_metadata_basic to verify metadata extraction
from litellm_params
- Add test_extract_langfuse_metadata_with_header_enrichment to test
integration with header-based metadata using a stubbed LangFuseLogger
- Add test_set_langfuse_specific_attributes_full_mapping to comprehensively
test all metadata field mappings and JSON serialization of complex types
These tests ensure full coverage of the langfuse_otel metadata features
added in commit ab1dbe355 and fix the CI test failure.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
