Conversation
Ensure final finish_reason chunks retain non-OpenAI attributes from original provider chunks, including the holding_chunk flush path where delta is non-empty. Add regression tests for both final-chunk branches. Made-with: Cursor
Made-with: Cursor
Previously, stream_chunk_builder only took annotations from the first chunk that contained them, losing any annotations from later chunks. This is a problem because providers like Gemini/Vertex AI send grounding metadata (converted to annotations) in the final streaming chunk, while other providers may spread annotations across multiple chunks. Changes: - Collect and merge annotations from ALL annotation-bearing chunks instead of only using the first one
) * added the header mapping feature * added tests * final cleanup * final cleanup * added missing test and logic * fixed header sending bug * Update litellm/proxy/auth/auth_utils.py Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com> * added back init file in responses + fixed test_auth_utils.py int local_testing --------- Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
Support missing base64 padding in managed character/video IDs so copied encoded IDs still decode to the original upstream character ID. Made-with: Cursor
Use typed character response models and video multipart helpers so /videos/characters forwards uploaded MP4 files with video/* content type. Made-with: Cursor
Avoid the temporary Any alias and use a concrete FileTypes import compatible with type checks. Made-with: Cursor
…atch Fix: Vertex ai Batch Output File Download Fails with 500
docs(blog): add WebRTC blog post link
…header_order Refactor: Filtering beta header after transformation
…al-streaming-attributes fix(streaming): preserve custom attributes on final stream chunk
… issues - Remove duplicate DecodedCharacterId TypedDict from litellm/types/videos/main.py - Remove dead LITELLM_MANAGED_VIDEO_CHARACTER_COMPLETE_STR constant from litellm/types/utils.py - Add FastAPI Form validation for name field in video_create_character endpoint Made-with: Cursor
…n video handlers Add response.raise_for_status() before transform_*_response() calls in all eight video character/edit/extension handler methods (sync and async): - video_create_character_handler / async_video_create_character_handler - video_get_character_handler / async_video_get_character_handler - video_edit_handler / async_video_edit_handler - video_extension_handler / async_video_extension_handler Without these checks, httpx does not raise on 4xx/5xx responses, so provider errors (e.g., 401 Unauthorized) pass directly to Pydantic model constructors, causing ValidationError instead of meaningful HTTP errors. The raise_for_status() ensures the exception handler receives proper HTTPStatusError for translation into actionable messages. Made-with: Cursor
…r in router-first routing Add avideo_create_character and avideo_get_character to the list of video endpoints that use router-first routing when a model is provided (either from decoded IDs or target_model_names). Previously only avideo_edit and avideo_extension were in the router-first block. This ensures both character endpoints benefit from multi-deployment load balancing and model resolution, making them consistent with the other video operations. This allows: - avideo_create_character: Router picks among multiple deployments when target_model_names is set - avideo_get_character: Router assists with multi-model environments for consistency Made-with: Cursor
- Clear examples for SDK and proxy usage - Feature highlights: router support, encoding, error handling - Best practices for character uploads and prompting - Available from LiteLLM v1.83.0+ - Troubleshooting guide for common issues Made-with: Cursor
- Add curl examples for avideo_edit and avideo_extension APIs - Explain how LiteLLM encodes/decodes managed character IDs - Show metadata included in character IDs (provider, model_id) - Detail transparent router-first routing benefits Made-with: Cursor
…tion test Add avideo_create_character, avideo_get_character, avideo_edit, and avideo_extension to the skip condition since Azure video calls don't use initialize_azure_sdk_client. Tests now properly skip with expected behavior instead of failing: - test_ensure_initialize_azure_sdk_client_always_used[avideo_create_character] ✓ - test_ensure_initialize_azure_sdk_client_always_used[avideo_get_character] ✓ - test_ensure_initialize_azure_sdk_client_always_used[avideo_edit] ✓ - test_ensure_initialize_azure_sdk_client_always_used[avideo_extension] ✓ Made-with: Cursor
…sion methods Convert all 8 new video methods from @AbstractMethod to concrete implementations that raise NotImplementedError. This prevents breaking external third-party BaseVideoConfig subclasses at import time. Methods affected: - transform_video_create_character_request/response - transform_video_get_character_request/response - transform_video_edit_request/response - transform_video_extension_request/response External integrators can now upgrade without instantiation errors; NotImplementedError is only raised when operations are actually called on unsupported providers. This restores backward compatibility with the project's policy. Made-with: Cursor
…r-endpoint-fixes [Feat] Add create character endpoints and other new videos Endpoints
…14_2026 Litellm oss staging 03 14 2026
Closed
towry
pushed a commit
that referenced
this pull request
Mar 20, 2026
docs: Learn page updates, card links, integrations, sidebar changes
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Relevant issues
Pre-Submission checklist
Please complete all items before asking a LiteLLM maintainer to review your PR
tests/test_litellm/directory, Adding at least 1 test is a hard requirement - see detailsmake test-unit@greptileaiand received a Confidence Score of at least 4/5 before requesting a maintainer reviewDelays in PR merge?
If you're seeing a delay in your PR being merged, ping the LiteLLM Team on Slack (#pr-review).
CI (LiteLLM team)
Branch creation CI run
Link:
CI run for the last commit
Link:
Merge / cherry-pick CI run
Links:
Type
🆕 New Feature
🐛 Bug Fix
🧹 Refactoring
📖 Documentation
🚄 Infrastructure
✅ Test
Changes