|
|
10c8e2baae
|
feat(v2): complete multi-LLM providers, TUI redesign, and advanced agent features
Multi-LLM Provider Support:
- Add llm-core crate with LlmProvider trait abstraction
- Implement Anthropic Claude API client with streaming
- Implement OpenAI API client with streaming
- Add token counting with SimpleTokenCounter and ClaudeTokenCounter
- Add retry logic with exponential backoff and jitter
Borderless TUI Redesign:
- Rewrite theme system with terminal capability detection (Full/Unicode256/Basic)
- Add provider tabs component with keybind switching [1]/[2]/[3]
- Implement vim-modal input (Normal/Insert/Visual/Command modes)
- Redesign chat panel with timestamps and streaming indicators
- Add multi-provider status bar with cost tracking
- Add Nerd Font icons with graceful ASCII fallbacks
- Add syntax highlighting (syntect) and markdown rendering (pulldown-cmark)
Advanced Agent Features:
- Add system prompt builder with configurable components
- Enhance subagent orchestration with parallel execution
- Add git integration module for safe command detection
- Add streaming tool results via channels
- Expand tool set: AskUserQuestion, TodoWrite, LS, MultiEdit, BashOutput, KillShell
- Add WebSearch with provider abstraction
Plugin System Enhancement:
- Add full agent definition parsing from YAML frontmatter
- Add skill system with progressive disclosure
- Wire plugin hooks into HookManager
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
|
2025-12-02 17:24:14 +01:00 |
|
|
|
f87e5d2796
|
feat(tools): implement M11 subagent system with task routing
Add tools-task crate with subagent registry and tool whitelist system:
Core Features:
- Subagent struct with name, description, keywords, and allowed tools
- SubagentRegistry for managing and selecting subagents
- Tool whitelist validation per subagent
- Keyword-based task matching and agent selection
Built-in Subagents:
- code-reviewer: Read-only code analysis (Read, Grep, Glob)
- test-writer: Test file creation (Read, Write, Edit, Grep, Glob)
- doc-writer: Documentation management (Read, Write, Edit, Grep, Glob)
- refactorer: Code restructuring (Read, Write, Edit, Grep, Glob)
Test Coverage:
- Subagent tool whitelist enforcement
- Keyword matching for task descriptions
- Registry selection based on task description
- Tool validation for specific agents
- Error handling for nonexistent agents
Implements M11 from AGENTS.md for specialized agents with limited tool access.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
|
2025-11-01 20:37:37 +01:00 |
|
