jpmschweitzerandClaude Opus 4.5
f4e8552298
Implements the first Claude-like agent for codebase exploration: Core Features: - Explore agent with glob, grep, read, and bash tools - Native PydanticAI tool calling with Ollama/Mistral Nemo - Sanitized Ollama provider (fixes content:null issue) - REST API endpoints for agent execution Tool Infrastructure: - BaseTool abstract class with ToolResult dataclass - ReadFileTool, GlobFilesTool, GrepContentTool, BashReadOnlyTool - Path validation and sandboxing support CLI Client (separate package for future extraction): - webber-cli command with chat, explore, status commands - Communicates with Webber API backend - Rich console output with theming Configuration: - Dev server on port 8095 (production uses 8086) - Mistral Nemo optimizations (temp 0.3, tool_choice required) Tests: 24 tests covering tools and API endpoints Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
708 B
708 B
Background
Research with Gemini identified key issues with mistral-nemo and tool calling:
- "Pre-computation Hallucination" - model answers before using tools
- High default temperature (0.7-0.8) causes wandering
- Model is "chatty and confident" - needs explicit constraints
Key Recommendations from Gemini Research
- Temperature 0.0 for tool-calling agents (deterministic, follows schema)
- Chain of Thought (CoT) - force step-by-step reasoning
- Negative constraints - tell model what NOT to do (Nemo responds better)
- Explicit tool descriptions - verbose docstrings with "never estimate yourself"
- "Strictly tool-based assistant" pattern - NO internal knowledge claim