* fix: support Anthropic tool_use and tool_result in token counter
* refactor(token_counter): add dynamic field inference for Anthropic content blocks
* test: Add additional tests
* make format
* Fix lint error
* Fix mypy narrow type lint errors
- Removed litellm/model_prices_and_context_window_backup.json
- Updated get_model_cost_map() to read from single source
- Refactored _load_local_model_cost_map() to support:
* Package resources (production/pip install)
* Project root (development)
- Updated CI/CD workflows:
* .circleci/config.yml: Copy to litellm/ before publishing
* .github/workflows/simple_pypi_publish.yml: Same approach
* ci_cd/check_files_match.py: Updated file paths
- Updated test_get_model_file.py to use project root
- Renamed test_get_backup_model_cost_map → test_get_local_model_cost_map
Benefits:
- Eliminates file duplication
- Single source of truth for model pricing
- No need for PRs like #16460 to sync backup files
- Simpler maintenance
The backup was unnecessary because CI copies the file to the package before publishing.
Implements support for reasoning_effort="none" parameter for Gemini models,
providing significant cost savings (up to 96% cheaper) by disabling thinking
budget while maintaining response quality.
Changes:
- Added "supports_reasoning": true to gemini-2.0-flash-thinking-exp-01-21 in model config
- Implemented mapping for reasoning_effort="none" to thinkingConfig {thinkingBudget: 0, includeThoughts: false}
- Added unit test to verify the mapping works correctly
Performance impact:
- Without reasoning_effort: ~313 tokens
- With reasoning_effort="none": ~12 tokens (96% cheaper)
Closes#16420
Co-authored-by: Krish Dholakia <krrishdholakia@gmail.com>
Related to PR #16210 which fixed automatic summary field addition
Changes:
- Document reasoning_effort string vs dict formats
- Add summary field options (auto, detailed, concise)
- Add table of supported reasoning_effort values by GPT-5 model
- Clarify model-specific support and limitations
- Note that summary field requires org verification
The previous implementation automatically added summary field causing
400 errors for unverified orgs. Now users can opt-in by passing
reasoning_effort as dict with explicit summary field.
Fixes#16533
Before this fix, non-ASCII characters (Japanese, Spanish, Chinese, etc.)
in function call arguments were being escaped as Unicode sequences.
Example:
- Before: "やあ" → "\u3084\u3042"
- After: "やあ" → "やあ" (preserved)
Changes:
- Add ensure_ascii=False to json.dumps() in _transform_parts()
- Add test for Japanese and Spanish Unicode character preservation
This is not a breaking change as both formats are equivalent in JSON.
The fix improves readability and aligns with OpenAI's behavior.
* fix: Improve Azure auth parameter handling for None values
Previously, litellm_params.get() with default fallbacks could ignore
environment variables when the param existed but was None. Now explicitly
checks for None values before falling back to environment variables.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* fix lint
---------
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Krish Dholakia <krrishdholakia@gmail.com>
