The Responses API expects tool results to use input_text/input_image types,
not output_text. This fix ensures consistent list format for all tool results:
- String content → [{"type": "input_text", "text": "..."}]
- Image content → [{"type": "input_image", "image_url": "..."}]
This resolves the conflict between tests that expected different formats
and aligns with OpenAI's Responses API requirements.
Fixes the regression introduced in #18226.
Fixes#18282
This PR fixes two issues with Gemini context window error handling:
1. **Pattern matching for Gemini 2.0 Flash**: The previous pattern
'input token count exceeds the maximum number of tokens allowed'
doesn't match Gemini 2.0 Flash errors which include dynamic token
counts like '(2800010)' in the message. Split into shorter patterns
that work with both formats.
2. **Add context window check to Gemini block**: The
is_error_str_context_window_exceeded() check was only called for
OpenAI-compatible providers, not for Gemini/Vertex AI. Added the
check to the Gemini-specific error handling block.
Test cases added for both Gemini 2.0 Flash and 2.5/3 error formats.
- test_tool_message_output_is_string_not_list: verifies function_call_output.output is a string
- test_multiple_tool_calls_in_single_choice: verifies multiple tool calls are grouped in one choice
Users were getting "does not support parameters: ['tools']" errors when
using lowercase model names (e.g., "qwen/qwen3-next-80b-a3b-thinking")
because the model cost map has mixed-case keys and the lookup was
case-sensitive.
Added _get_model_cost_key() helper that tries exact match first (O(1)),
then falls back to case-insensitive search if not found.
* fix: enforce team member budget check in common_checks
- Add missing team member budget validation in common_checks() function
- Checks team membership budget when team key is used
- Raises BudgetExceededError when team member spend exceeds max_budget_in_team
- Follows same pattern as other budget checks (team, user, end_user)
- Uses cached get_team_membership() for performance
- Fix AttributeError in lowest_tpm_rpm.py
- Add null check for model_info before accessing .get() method
- Prevents 'NoneType' object has no attribute 'get' error
- Add unit tests for team member budget enforcement
- Test budget exceeded scenario
- Test within budget scenario
- Test edge cases (no budget, no membership, personal keys)
- Tests run without requiring proxy server
Fixes failing test: test_users_in_team_budget
* fix: mock get_async_httpx_client in test_langsmith_key_based_logging
- Mock get_async_httpx_client to return a mock AsyncHTTPHandler instance
- Fixes test failure where mock_post was never called
- LangsmithLogger creates its own httpx client instance via get_async_httpx_client,
so we need to mock the factory function rather than the class method
- Use MagicMock for response.raise_for_status (sync method) instead of AsyncMock
* fix: resolve linting errors (PLR0915, F401)
- Remove unused imports (datetime, ServiceLoggerPayload) from arize_phoenix.py
- Extract health ping setup logic from RedisCache.__init__ to reduce statement count
- Extract team member budget check from common_checks to reduce statement count
* fix: resolve type errors in ChatCompletionToolCallChunk construction
- Cast type field to Literal['function'] to satisfy TypedDict requirements
- Ensure arguments field is explicitly str type to match TypedDict signature
- Fixes pyright errors for incompatible types in transformation.py
* Add monitor mode support to Lakera guardrail
- Add on_flagged parameter to LakeraV2GuardrailConfigModel (default: 'block')
- Support 'monitor' mode that logs violations without blocking requests
- Support 'block' mode (default) that raises HTTPException on violations
- Update async_pre_call_hook and async_moderation_hook to check on_flagged
- Update guardrail initializer to pass on_flagged from config
- Add documentation with monitor mode examples
This allows users to tune Lakera security policies by monitoring violations
without blocking legitimate requests, similar to Pillar's on_flagged_action.
* Add tests for Lakera guardrail monitor mode
- Test monitor mode allows flagged content through (pre_call hook)
- Test block mode raises HTTPException for violations (pre_call hook)
- Test monitor mode works with during_call (moderation_hook)
These tests verify the on_flagged parameter functionality for both
monitor and block modes across different guardrail hooks.
---------
Co-authored-by: Steve <steve.giguere@lakera.ai>
