mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-12 23:01:41 +00:00
9ddf0535b1
* fix(proxy): skip double-wrapping unified batch output file ids on retrieve After ensure_batch_response_managed_file_ids normalizes output_file_id, the managed files post-call hook was re-encoding the unified id and storing the nested id as the provider mapping. Use the decoded llm_output_file_id for retrieve and model_mappings instead. Co-authored-by: Cursor <cursoragent@cursor.com> * fix(proxy): guard managed file id parsing for non-output unified formats Only treat decoded unified ids as already-wrapped output files when they contain llm_output_file_id. Skip other litellm_proxy id shapes instead of IndexError on split. Co-authored-by: Cursor <cursoragent@cursor.com> * fix(proxy): rename loop variable to satisfy mypy unified file id typing Co-authored-by: Cursor <cursoragent@cursor.com> --------- Co-authored-by: Cursor <cursoragent@cursor.com> |
||
|---|---|---|
| .. | ||
| __init__.py | ||
| test_afile_retrieve_returns_unified_id.py | ||
| test_batch_retrieve_input_file_id.py | ||
| test_batch_retrieve_returns_unified_input_file_id.py | ||
| test_batch_update_db_managed_output_file_id.py | ||
| test_deleted_file_returns_403_not_404.py | ||
| test_enterprise_routes.py | ||
| test_file_deletion_blocking.py | ||
| test_managed_files_access_check.py | ||
| test_managed_files_hook.py | ||