Owlibou/owlen
2
0
Fork 0
Code Issues 20 Pull Requests Actions Packages Projects Releases 5 Activity
255 Commits 3 Branches 10 Tags
5caf5020097d311cf2687c370f2956627babc9f7
Commit Graph

3 Commits

Author SHA1 Message Date
vikingowl
5caf502009 feat(M12): complete milestone with plugins, checkpointing, and rewind 
Implements the remaining M12 features from AGENTS.md:

**Plugin System (crates/platform/plugins)**
- Plugin manifest schema with plugin.json support
- Plugin loader for commands, agents, skills, hooks, and MCP servers
- Discovers plugins from ~/.config/owlen/plugins and .owlen/plugins
- Includes comprehensive tests (4 passing)

**Session Checkpointing (crates/core/agent)**
- Checkpoint struct capturing session state and file diffs
- CheckpointManager with snapshot, diff, save, load, and rewind capabilities
- File diff tracking with before/after content
- Checkpoint persistence to .owlen/checkpoints/
- Includes comprehensive tests (6 passing)

**REPL Commands (crates/app/cli)**
- /checkpoint - Save current session with file diffs
- /checkpoints - List all saved checkpoints
- /rewind <id> - Restore session and files from checkpoint
- Updated /help documentation

M12 milestone now fully complete:
✅ /permissions, /status, /cost (previously implemented)
✅ Checkpointing and /rewind
✅ Plugin loader with manifest schema

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-01 21:59:08 +01:00
vikingowl
04a7085007 feat(repl): implement M12 REPL commands and session tracking 
Add comprehensive REPL commands for session management and introspection:

**Session Tracking** (`crates/core/agent/src/session.rs`):
- SessionStats: Track messages, tool calls, tokens, timing
- SessionHistory: Store conversation history and tool call records
- Auto-formatting for durations (seconds, minutes, hours)

**REPL Commands** (in interactive mode):
- `/help`        - List all available commands
- `/status`      - Show session stats (messages, tools, uptime)
- `/permissions` - Display permission mode and tool access
- `/cost`        - Show token usage and timing (free with Ollama!)
- `/history`     - View conversation history
- `/clear`       - Reset session state
- `/exit`        - Exit interactive mode gracefully

**Stats Tracking**:
- Automatic message counting
- Token estimation (chars / 4)
- Duration tracking per message
- Tool call counting (foundation for future)
- Session uptime from start

**Permission Display**:
- Shows current mode (Plan/AcceptEdits/Code)
- Lists tools by category (read-only, write, system)
- Indicates which tools are allowed/ask/deny

**UX Improvements**:
- Welcome message shows model and mode
- Clean command output with emoji indicators
- Helpful error messages for unknown commands
- Session stats persist across messages

**Example Session**:
```
🤖 Owlen Interactive Mode
Model: qwen3:8b
Mode: Plan

> /help
📖 Available Commands: [list]

> Find all Cargo.toml files
🔧 Tool call: glob...
✅ Tool result: 14 files

> /status
📊 Session Status:
  Messages: 1
  Tools: 1 calls
  Uptime: 15s

> /cost
💰 Token Usage: ~234 tokens

> /exit
👋 Goodbye!
```

Implements core M12 requirements for REPL commands and session management.
Future: Checkpointing/rewind functionality can build on this foundation.

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-01 21:05:29 +01:00
vikingowl
e77e33ce2f feat(agent): implement Agent Orchestrator with LLM tool calling 
Add complete agent orchestration system that enables LLM to call tools:

**Core Agent System** (`crates/core/agent`):
- Agent execution loop with tool call/result cycle
- Tool definitions in Ollama-compatible format (6 tools)
- Tool execution with permission checking
- Multi-iteration support with max iteration safety

**Tool Definitions**:
- read: Read file contents
- glob: Find files by pattern
- grep: Search for patterns in files
- write: Write content to files
- edit: Edit files with find/replace
- bash: Execute bash commands

**Ollama Integration Updates**:
- Extended ChatMessage to support tool_calls
- Added Tool, ToolCall, ToolFunction types
- Updated chat_stream to accept tools parameter
- Made tool call fields optional for Ollama compatibility

**CLI Integration**:
- Wired agent loop into all output formats (Text, JSON, StreamJSON)
- Tool calls displayed with 🔧 icon, results with ✅
- Replaced simple chat with agent orchestrator

**Permission Integration**:
- All tool executions check permissions before running
- Respects plan/acceptEdits/code modes
- Returns clear error messages for denied operations

**Example**:
User: "Find all Cargo.toml files in the workspace"
LLM: Calls glob("**/Cargo.toml")
Agent: Executes and returns 14 files
LLM: Formats human-readable response

This transforms owlen from a passive chatbot into an active agent that
can autonomously use tools to accomplish user goals.

Tested with: qwen3:8b successfully calling glob tool

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-01 20:56:56 +01:00