feat: add Explore agent with PydanticAI tool calling

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>

AGENTS.md

@@ -105,6 +105,18 @@ curl http://localhost:8086/docs   # Swagger UI
 
 ---
 
+## 1.5 Known Issues & Future Improvements
+
+### Explore Agent
+
+- **Gitignore Support**: The filesystem tools (`glob_files`, `grep_content`) currently do NOT honor `.gitignore`. They return results from ignored directories like `.venv/`, `node_modules/`, etc. This should be fixed to filter out gitignored files by default.
+
+- **Model Hallucination**: Mistral Nemo sometimes hallucinates file contents instead of using actual tool results. Consider using a more capable model (codestral, qwen2.5-coder) or adding response validation.
+
+- **Ollama Provider**: We use a custom `WebberOllamaProvider` (ported from tatlock) that sanitizes `content: null` to `content: ""` for assistant messages with tool calls. This works around an Ollama API limitation.
+
+---
+
 ## 2. FastAPI Architecture & Best Practices
 *Reference: [FastAPI Best Practices](https://github.com/zhanymkanov/fastapi-best-practices)*