Replace iter_lines()/aiter_lines() with iter_text()/aiter_text() using explicit
UTF-8 encoding to handle non-ASCII characters like µ in streaming responses.
- Added utf8_iter_lines() and utf8_aiter_lines() helper functions
- Ensures proper UTF-8 decoding of streaming response content
- Added comprehensive tests for Unicode character handling
Fixes#12660
* show team member tpm/rpm limits
* ui - allow setting team settings
* fix better debugging
* fix types: TeamMemberUpdateRequest
* add _upsert_budget_and_membership
* allow updating team member RPM/TPM in teamMemberUpdateCall
* editing team member rpm/tpm
* UI - fixes for team member component
* fix info
* test_upsert_rpm_only_creates_new_budget
* alert_to_webhook_url: avoid secret false positive
Trivy detects the example as a potential secret; tweak the hostname
a bit to make it obviously not hooks.slack.com to avoid this.
* Remove log file
Drop log file checked into the git tree; this contains strings that
trivy detects as potential secrets.
* Reduced max_input_tokens from 400000 to 272000 for both azure/gpt-5-chat and azure/gpt-5-chat-latest to optimize resource usage and align with updated model specifications.
- test_assistant_message_cache_control: Tests assistant messages with string content and cache_control
- test_assistant_message_list_content_cache_control: Tests assistant messages with list content and cache_control
- test_tool_message_cache_control: Tests tool messages with list content and cache_control
- test_tool_message_string_content_cache_control: Tests tool messages with string content and cache_control
- test_assistant_tool_calls_cache_control: Tests assistant tool_calls with cache_control
- test_multiple_tool_calls_with_mixed_cache_control: Tests multiple tool calls with mixed cache_control
- test_no_cache_control_no_cache_point: Tests that messages without cache_control don't generate cachePoint blocks
These tests ensure that cachePoint blocks are correctly generated for all message types when cache_control is present.
- Add cachePoint support for assistant messages (both string and list content)
- Add cachePoint support for tool messages (both message-level and content-level cache_control)
- Add cachePoint support for assistant tool_calls
- Move CachePointBlock import to file header for better code organization
- Ensure cachePoint blocks are created as separate content blocks alongside main content
This enables comprehensive cache control across all message types in Bedrock conversations.
* Improve LiteLLM model name display with better styling and overflow handling
Co-authored-by: ishaan <ishaan@berri.ai>
* Add Tooltip to LiteLLM model name for improved text display
Co-authored-by: ishaan <ishaan@berri.ai>
---------
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: ishaan <ishaan@berri.ai>
* Fix - add safe divide by 0 for most places to prevent crash
* Enhance MCPRequestHandler to support permission inheritance and intersection logic for access groups. Added integration tests to verify behavior when keys have no permissions and when both keys and teams have overlapping permissions.
* Remove redundant assertions for permission checks in test_user_api_key_auth_mcp.py to streamline test logic.
* Refactor integration tests for MCPRequestHandler to simplify mocking. Replace complex database mocks with direct function mocks for permission inheritance and intersection scenarios, improving test clarity and maintainability.
* Revert "Fix - add safe divide by 0 for most places to prevent crash"
This reverts commit 265d40e39051e148996b9fb7f354730c57ff23ac.
* fix intent params
* Add responses
* fix unrelated test
* test fix - fireworks API endpoint is down
* test fix fireworks ai is having an active outage
* test_completion_cost_databricks
* dbrx fix test API currently not responding
* Update OpenAI Realtime handler to use the correct endpoint and include all query parameters. Adjusted error messages for missing API base and key. Updated health check URL construction to pass model as a query parameter.
* Enhance OpenAI Realtime handler tests to ensure model parameter inclusion in WebSocket URL. Added new tests to verify correct URL construction with model and additional parameters, preventing 'missing_model' errors. Updated existing tests for consistency.
* Remove debug print statements for API base and key in OpenAIRealtime handler to clean up the code.
---------
Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com>
* Fix - add safe divide by 0 for most places to prevent crash
* feat(prometheus): add new metrics for monitoring pod lock manager and spend update queues
* fix(prometheus): specify type for buffer monitoring metrics in PrometheusMetricLabels
* Revert "Fix - add safe divide by 0 for most places to prevent crash"
This reverts commit 265d40e39051e148996b9fb7f354730c57ff23ac.
