- Introduced TokenCallbackHandler to track input and output token usage during LLM operations.
- Updated RunResult model to include token usage data.
- Enhanced RunsStore to support token usage persistence in the database.
- Modified RunService to yield token usage information during event streaming.
- Implemented UI components to display token statistics in the run detail view.
- Added tests for token handling and reporting functionality.
Made-with: Cursor
- Added api-client module with functions for creating and listing runs, and fetching settings.
- Introduced SSE connection handling for real-time updates with event listeners for agent and run events.
- Created types for agents and runs to support the new API structure.
- Updated .gitignore to ensure proper exclusion of Next.js library directories.
Made-with: Cursor
- Introduced lightningcss as a dependency for enhanced styling capabilities.
- Updated global CSS variables to reflect a new design theme, including background, border, and text colors.
- Modified layout components to incorporate new fonts and improved spacing.
- Enhanced sidebar and dashboard layouts with subtle background textures and improved responsiveness.
- Refined button styles and added new animations for a more dynamic user experience.
- Improved the Run History Table with a new grid layout and status indicators.
- Added FastAPI-based API structure with routers for runs and settings management.
- Implemented endpoints for creating, listing, and retrieving run configurations.
- Introduced settings management with load and update functionality.
- Created models for run configurations and settings using Pydantic.
- Established a store for managing run states and results.
- Enhanced .gitignore to exclude node_modules and results directories.
- Added package.json and package-lock.json for frontend dependencies.
- Included initial tests for API endpoints and model validations.
- Introduced a new API structure with FastAPI, including routers for runs and settings.
- Implemented endpoints for creating, listing, and retrieving run configurations.
- Added settings management with load and update functionality.
- Integrated SQLite checkpointing for durable state management during analysis.
- Updated dependencies in `pyproject.toml` and `requirements.txt` to include FastAPI and related packages.
- Enhanced `.gitignore` to exclude SQLite checkpoints and results directories.
Add effort parameter (high/medium/low) for Claude 4.5+ and 4.6 models,
consistent with OpenAI reasoning_effort and Google thinking_level.
Also add content normalization for Anthropic responses.
- Point requirements.txt to pyproject.toml as single source of truth
- Resolve welcome.txt path relative to module for CLI portability
- Include cli/static files in package build
- Extract shared normalize_content for OpenAI Responses API and
Gemini 3 list-format responses into base_client.py
- Update README install and CLI usage instructions
Enable use_responses_api for native OpenAI provider, which supports
reasoning_effort with function tools across all model families.
Removes the UnifiedChatOpenAI subclass workaround.
Closes#403
- Add http_client and http_async_client parameters to all LLM clients
- OpenAIClient, GoogleClient, AnthropicClient now support custom httpx clients
- Fixes SSL certificate verification errors on Windows Conda environments
- Users can now pass custom httpx.Client with verify=False or custom certs
Fixes#369
- OpenAI: add GPT-5.4, GPT-5.4 Pro; remove o-series and legacy GPT-4o
- Anthropic: add Claude Opus 4.6, Sonnet 4.6; remove legacy 4.1/4.0/3.x
- Google: add Gemini 3.1 Pro, 3.1 Flash Lite; remove deprecated
gemini-3-pro-preview and Gemini 2.0 series
- xAI: clean up model list to match current API
- Simplify UnifiedChatOpenAI GPT-5 temperature handling
- Add missing tradingagents/__init__.py (fixes pip install building)
Add _clean_dataframe() to normalize stock DataFrames before stockstats:
coerce invalid dates/prices, drop rows missing Close, fill price gaps.
Also add on_bad_lines="skip" to all cached CSV reads.
LLMs (especially smaller models) sometimes pass multiple indicator
names as a single comma-separated string instead of making separate
tool calls. Split and process each individually at the tool boundary.
InvestDebateState was missing bull_history, bear_history, judge_decision.
RiskDebateState was missing aggressive_history, conservative_history,
neutral_history, latest_speaker, judge_decision. This caused KeyError
in _log_state() and reflection, especially with edge-case config values.
Prevents UnicodeEncodeError on Windows where the default encoding
(cp1252/gbk) cannot handle Unicode characters in LLM output.
Closes#77, closes#114, closes#126, closes#215, closes#332
- Add save prompt after analysis with organized subfolder structure
- Fix report truncation by using sequential panels instead of Columns
- Add optional full report display prompt
- Add update_analyst_statuses() for unified status logic (pending/in_progress/completed)
- Normalize analyst selection to predefined ANALYST_ORDER for consistent execution
- Add message deduplication to prevent duplicates from stream_mode=values
- Restructure streaming loop so state handlers run on every chunk
- Add StatsCallbackHandler for tracking LLM calls, tool calls, and tokens
- Integrate callbacks into TradingAgentsGraph and all LLM clients
- Dynamic agent/report counts based on selected analysts
- Fix report completion counting (tied to agent completion)
Ali AL OGAILI
Yijia-Xiao
Yijia Xiao
CadeYu
阳虎
makk9
Ljx-007
RinZ27