Commit Graph

4 Commits

Author SHA1 Message Date
4a07b97eab feat(ui): add autocomplete, command help, and streaming improvements
TUI Enhancements:
- Add autocomplete dropdown with fuzzy filtering for slash commands
- Fix autocomplete: Tab confirms selection, Enter submits message
- Add command help overlay with scroll support (j/k, arrows, Page Up/Down)
- Brighten Tokyo Night theme colors for better readability
- Add todo panel component for task display
- Add rich command output formatting (tables, trees, lists)

Streaming Fixes:
- Refactor to non-blocking background streaming with channel events
- Add StreamStart/StreamEnd/StreamError events
- Fix LlmChunk to append instead of creating new messages
- Display user message immediately before LLM call

New Components:
- completions.rs: Command completion engine with fuzzy matching
- autocomplete.rs: Inline autocomplete dropdown
- command_help.rs: Modal help overlay with scrolling
- todo_panel.rs: Todo list display panel
- output.rs: Rich formatted output (tables, trees, code blocks)
- commands.rs: Built-in command implementations

Planning Mode Groundwork:
- Add EnterPlanMode/ExitPlanMode tools scaffolding
- Add Skill tool for plugin skill invocation
- Extend permissions with planning mode support
- Add compact.rs stub for context compaction

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-12-02 19:03:33 +01:00
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
688d1fe58a feat(M8): implement MCP (Model Context Protocol) integration with stdio transport
Milestone M8 implementation adds MCP integration for connecting to external
tool servers and resources.

New crate: crates/integration/mcp-client
- JSON-RPC 2.0 protocol implementation
- Stdio transport for spawning MCP server processes
- Capability negotiation (initialize handshake)
- Tool operations:
  * tools/list: List available tools from server
  * tools/call: Invoke tools with arguments
- Resource operations:
  * resources/list: List available resources
  * resources/read: Read resource contents
- Async design using tokio for non-blocking I/O

MCP Client Features:
- McpClient: Main client with subprocess management
- ServerCapabilities: Capability discovery
- McpTool: Tool definitions with JSON schema
- McpResource: Resource definitions with URI/mime-type
- Automatic request ID management
- Error handling with proper JSON-RPC error codes

Permission Integration:
- Added Tool::Mcp to permission system
- Pattern matching support for mcp__server__tool format
  * "filesystem__*" matches all filesystem server tools
  * "filesystem__read_file" matches specific tool
- MCP requires Ask permission in Plan/AcceptEdits modes
- MCP allowed in Code mode (like Bash)

Tests added (3 new tests with mock Python servers):
1. mcp_server_capability_negotiation - Verifies initialize handshake
2. mcp_tool_invocation - Tests tool listing and calling
3. mcp_resource_reads - Tests resource listing and reading

Permission tests added (2 new tests):
1. mcp_server_pattern_matching - Verifies server-level wildcards
2. mcp_exact_tool_matching - Verifies tool-level exact matching

All 75 tests passing (up from 68).

Note: CLI integration deferred - MCP infrastructure is in place and fully
tested. Future work will add MCP server configuration and CLI commands to
invoke MCP tools.

Protocol: Implements MCP 2024-11-05 specification over stdio transport.

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-01 20:15:39 +01:00
a6cf8585ef feat(permissions): implement permission system with plan mode enforcement (M1 complete)
This commit implements the complete M1 milestone (Config & Permissions) including:

- New permissions crate with Tool, Action, Mode, and PermissionManager
- Three permission modes: Plan (read-only default), AcceptEdits, Code
- Pattern matching for permission rules (exact match and prefix with *)
- Integration with config-agent for mode-based permission management
- CLI integration with --mode flag to override configured mode
- Permission checks for Read, Glob, and Grep operations
- Comprehensive test suite (10 tests in permissions, 4 in config, 4 in CLI)

Also fixes:
- Fixed failing test in tools-fs (glob pattern issue)
- Improved glob_list() root extraction to handle patterns like "/*.txt"

All 21 workspace tests passing.

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-01 19:14:54 +01:00