* feat(reasoning): support 'minimal' effort type for OpenAI
* fix(reasoning): correctly map 'minimal' effort to Reasoning object
* chore(dependencies): update OpenAI package version to 1.99.5 in pyproject.toml and requirements.txt
* chore(dependencies): update poetry.lock for OpenAI package version 1.99.5 and Poetry version 2.1.3
* fix sso logout
- add a new login page with sso button
* lint fix
* lint fix
* lint fix
* fix tests
* fix test
* Revert "fix test"
This reverts commit 74eb7345710892d5a9d02baec0ef389b98d0dde3.
* Reapply "fix test"
This reverts commit 72d0b2d4c62f6bb9351a7656ff88efc2ba91aef7.
* add host to add modal
* close modal after save is clicked. and auto-refresh
* show old values in edit modal
* send the whole payload on edit
* Update settings.tsx
* resolve conflict
* fix conflict
* merge main
* first draft of notifications added to settings
* add error compatibility by taking errors from the backend
- db errors
- auth errors
* add support for different types of errors
* minor
* name change
* email alerts page notifications modified
* remove unused code
* fix(access group): allow access group on mcp tool retrieval
* fix(test): fix broken tests and add test case for access group
* fix(mypy): fix typing issues
* feat(usage): add aggregated user daily activity endpoint and UI integration; fallback to paginated flow if unavailable
* refactor(usage): deduplicate daily activity logic; add wrapper to user paginated endpoint; share date formatting in UI
* chore(lint): remove unused imports from internal_user_endpoints
Co-authored-by: Cole McIntosh <82463175+colesmcintosh@users.noreply.github.com>
* fix proxy config
* fix(responses api): fix streaming ID consistency and tool format handling (#12640)
* fix(responses): ensure streaming chunk IDs use consistent encoding format
Fixes streaming ID inconsistency where streaming responses used raw provider IDs
while non-streaming responses used properly encoded IDs with provider context.
Changes:
- Updated LiteLLMCompletionStreamingIterator to accept provider context
- Added _encode_chunk_id() method using same logic as non-streaming responses
- Modified chunk transformation to encode all streaming item_ids with resp_ prefix
- Updated handlers to pass custom_llm_provider and litellm_metadata to streaming iterator
Impact:
- Streaming chunk IDs now format: resp_<base64_encoded_provider_context>
- Enables session continuity when using streaming response IDs as previous_response_id
- Allows provider detection and load balancing with streaming responses
- Maintains backward compatibility with existing streaming functionality
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* fix(types): add explicit Optional[str] type annotation for model_id
This resolves MyPy type checking error where model_id could be None
but wasn't explicitly typed as Optional[str].
* fix(types): handle None case for litellm_metadata access
Prevents 'Item None has no attribute get' error by checking for None
before accessing litellm_metadata dictionary.
* test: add comprehensive tests for streaming ID consistency
Adds unit and E2E tests to verify streaming chunk IDs are properly encoded
with consistent format across streaming responses.
## Tests Added
### Unit Test (test_reasoning_content_transformation.py)
- `test_streaming_chunk_id_encoding()`: Validates the `_encode_chunk_id()` method
correctly encodes chunk IDs with `resp_` prefix and provider context
### E2E Tests (test_e2e_openai_responses_api.py)
- `test_streaming_id_consistency_across_chunks()`: Tests that all streaming chunk IDs
are properly encoded across multiple chunks in a real streaming response
- `test_streaming_response_id_as_previous_response_id()`: Tests the core use case -
using streaming response IDs for session continuity with `previous_response_id`
## Key Testing Approach
- Uses **Gemini** (non-OpenAI model) to test the transformation logic rather than
OpenAI passthrough, since the streaming ID consistency issue occurs when LiteLLM
transforms responses rather than just passing through to native OpenAI responses API
- Tests validate that streaming chunk IDs now use same encoding as non-streaming responses
- Verifies session continuity works with streaming responses
Addresses @ishaan-jaff's request for unit tests covering the streaming ID consistency fix.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* fix(lint): remove unused imports in transformation.py
Removes unused imports to fix CI linting errors:
- GenericResponseOutputItem
- OutputFunctionToolCall
* test: remove E2E tests from openai_endpoints_tests
Remove streaming ID consistency E2E tests as requested by @ishaan-jaff.
Keep only the mock/unit test in test_reasoning_content_transformation.py
* revert: remove streaming chunk ID encoding to original behavior
This reverts the streaming chunk ID encoding changes to understand the original issue better.
Original behavior was:
- Streaming chunks: raw provider IDs
- Streaming final response: raw IDs (PROBLEM!)
- Non-streaming final response: encoded IDs (correct)
The real issue: streaming final response IDs were not encoded, breaking session continuity.
* fix(responses): encode streaming final response IDs to match OpenAI behavior
Fixes streaming ID inconsistency to match OpenAI's Responses API behavior:
- Streaming chunks: raw message IDs (like OpenAI's msg_xxx)
- Final response: encoded IDs (like OpenAI's resp_xxx)
This enables session continuity by ensuring streaming final response IDs
have the same encoded format as non-streaming responses, allowing them
to be used as previous_response_id in follow-up requests.
Changes:
- Add custom_llm_provider and litellm_metadata to LiteLLMCompletionStreamingIterator
- Update handlers to pass provider context to streaming iterator
- Apply _update_responses_api_response_id_with_model_id to final streaming response
- Keep streaming chunks as raw IDs to match OpenAI format
Impact:
- Session continuity works with streaming responses
- Load balancing can detect provider from streaming final response IDs
- Format matches OpenAI's Responses API exactly
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* test: update unit test to match correct OpenAI-compatible behavior
Updates the unit test to verify streaming chunk IDs are raw (not encoded)
to match OpenAI's responses API format:
- Streaming chunks: raw message IDs (like msg_xxx)
- Final response: encoded IDs (like resp_xxx)
This reflects the correct behavior implemented in the fix.
---------
Co-authored-by: Claude <noreply@anthropic.com>
* cleanup
* TestBaseResponsesAPIStreamingIterator
---------
Co-authored-by: Javier de la Torre <jatorre@carto.com>
Co-authored-by: Claude <noreply@anthropic.com>
* feat: Add GPT-5 model family with official OpenAI specifications (#13378)
* Add GPT-5 model family support
Added four new GPT-5 models:
- gpt-5: Flagship model for logic and multi-step tasks
- gpt-5-mini: Cost-sensitive version for budget use cases
- gpt-5-nano: Speed-optimized version for low latency
- gpt-5-chat: Enterprise-focused version for advanced conversations
* Update GPT-5 models with official OpenAI specifications
- Add gpt-5-chat-latest with 400k context, 128k output tokens
- Add gpt-5-2025-08-07 with enhanced reasoning capabilities
- Add gpt-5-mini-2025-08-07 with cost-optimized pricing
- Add gpt-5-nano-2025-08-07 with ultra-fast performance
- Update existing gpt-5, gpt-5-mini, gpt-5-nano to match dated versions
- All models now support reasoning tokens and 400k context window
- Pricing updated per official OpenAI documentation
* fix conflicts
---------
Co-authored-by: Cole McIntosh <82463175+colesmcintosh@users.noreply.github.com>
Ishaan Jaff