Bill 0641ce554a fix: remove incorrect tool_calls conversion logic ...

Systematic debugging revealed the root cause of Pydantic validation errors:
- DeepSeek correctly returns tool_calls.arguments as JSON strings
- My wrapper was incorrectly converting strings to dicts
- This caused LangChain's parse_tool_call() to fail (json.loads(dict) error)
- Failure created invalid_tool_calls with dict args (should be string)
- Result: Pydantic validation error on invalid_tool_calls

Solution: Remove all conversion logic. DeepSeek format is already correct.

ToolCallArgsParsingWrapper now acts as a simple passthrough proxy.
Trading session completes successfully with no errors.

Fixes the systematic-debugging investigation that identified the
issue was in our fix attempt, not in the original API response.

Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

2025-11-05 21:18:54 -05:00

..

base_agent

fix: resolve DeepSeek tool_calls args parsing validation error

2025-11-05 20:57:17 -05:00

mock_provider

fix: suppress unused parameter warnings in mock LangChain model

2025-11-01 11:16:51 -04:00

chat_model_wrapper.py

fix: remove incorrect tool_calls conversion logic

2025-11-05 21:18:54 -05:00

context_injector.py

fix: enable intra-day position tracking for sell-then-buy trades

2025-11-05 06:56:54 -05:00

pnl_calculator.py

feat: add daily P&L calculator with weekend gap handling

2025-11-03 23:12:49 -05:00

reasoning_summarizer.py

debug: add logging to verify conversation history capture

2025-11-05 00:46:30 -05:00