Owlibou/owlen
2
0
Fork 0
Code Issues 20 Pull Requests Actions Packages Projects Releases 5 Activity
125 Commits 3 Branches 10 Tags
96e0436d43dec8b2549d777c3454abfb56ee83d7
Commit Graph

3 Commits

Author SHA1 Message Date
vikingowl
9545a4b3ad feat(phase10): complete MCP-only architecture migration 
This commit completes Phase 10 of the MCP migration by removing all
direct provider usage from CLI/TUI and enforcing MCP-first architecture.

## Changes

### Core Architecture
- **main.rs**: Replaced OllamaProvider with RemoteMcpClient
  - Uses MCP server configuration from config.toml if available
  - Falls back to auto-discovery of MCP LLM server binary
- **agent_main.rs**: Unified provider and MCP client to single RemoteMcpClient
  - Simplifies initialization with Arc::clone pattern
  - All LLM communication now goes through MCP protocol

### Dependencies
- **Cargo.toml**: Removed owlen-ollama dependency from owlen-cli
  - CLI no longer knows about Ollama implementation details
  - Clean separation: only MCP servers use provider crates internally

### Tests
- **agent_tests.rs**: Updated all tests to use RemoteMcpClient
  - Replaced OllamaProvider::new() with RemoteMcpClient::new()
  - Updated test documentation to reflect MCP requirements
  - All tests compile and run successfully

### Examples
- **Removed**: custom_provider.rs, basic_chat.rs (deprecated)
- **Added**: mcp_chat.rs - demonstrates recommended MCP-based usage
  - Shows how to use RemoteMcpClient for LLM interactions
  - Includes model listing and chat request examples

### Cleanup
- Removed outdated TODO about MCP integration (now complete)
- Updated comments to reflect current MCP architecture

## Architecture

```
CLI/TUI → RemoteMcpClient (impl Provider)
          ↓ MCP Protocol (STDIO/HTTP/WS)
          MCP LLM Server → OllamaProvider → Ollama
```

## Benefits
- ✅ Clean separation of concerns
- ✅ CLI is protocol-agnostic (only knows MCP)
- ✅ Easier to add new LLM backends (just implement MCP server)
- ✅ All tests passing
- ✅ Full workspace builds successfully

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-10-10 22:29:20 +02:00
vikingowl
e94df2c48a feat(phases4,7,8): implement Agent/ReAct, Code Execution, and Prompt Server 
Completes Phase 4 (Agentic Loop with ReAct), Phase 7 (Code Execution),
and Phase 8 (Prompt Server) as specified in the implementation plan.

**Phase 4: Agentic Loop with ReAct Pattern (agent.rs - 398 lines)**
- Complete AgentExecutor with reasoning loop
- LlmResponse enum: ToolCall, FinalAnswer, Reasoning
- ReAct parser supporting THOUGHT/ACTION/ACTION_INPUT/FINAL_ANSWER
- Tool discovery and execution integration
- AgentResult with iteration tracking and message history
- Integration with owlen-agent CLI binary and TUI

**Phase 7: Code Execution with Docker Sandboxing**

*Sandbox Module (sandbox.rs - 255 lines):*
- Docker-based execution using bollard
- Resource limits: 512MB memory, 50% CPU
- Network isolation (no network access)
- Timeout handling (30s default)
- Container auto-cleanup
- Support for Rust, Node.js, Python environments

*Tool Suite (tools.rs - 410 lines):*
- CompileProjectTool: Build projects with auto-detection
- RunTestsTool: Execute test suites with optional filters
- FormatCodeTool: Run formatters (rustfmt/prettier/black)
- LintCodeTool: Run linters (clippy/eslint/pylint)
- All tools support check-only and auto-fix modes

*MCP Server (lib.rs - 183 lines):*
- Full JSON-RPC protocol implementation
- Tool registry with dynamic dispatch
- Initialize/tools/list/tools/call support

**Phase 8: Prompt Server with YAML & Handlebars**

*Prompt Server (lib.rs - 405 lines):*
- YAML-based template storage in ~/.config/owlen/prompts/
- Handlebars 6.0 template engine integration
- PromptTemplate with metadata (name, version, mode, description)
- Four MCP tools:
  - get_prompt: Retrieve template by name
  - render_prompt: Render with Handlebars variables
  - list_prompts: List all available templates
  - reload_prompts: Hot-reload from disk

*Default Templates:*
- chat_mode_system.yaml: ReAct prompt for chat mode
- code_mode_system.yaml: ReAct prompt with code tools

**Configuration & Integration:**
- Added Agent module to owlen-core
- Updated owlen-agent binary to use new AgentExecutor API
- Updated TUI to integrate with agent result structure
- Added error handling for Agent variant

**Dependencies Added:**
- bollard 0.17 (Docker API)
- handlebars 6.0 (templating)
- serde_yaml 0.9 (YAML parsing)
- tempfile 3.0 (temporary directories)
- uuid 1.0 with v4 feature

**Tests:**
- mode_tool_filter.rs: Tool filtering by mode
- prompt_server.rs: Prompt management tests
- Sandbox tests (Docker-dependent, marked #[ignore])

All code compiles successfully and follows project conventions.

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-10-10 20:50:40 +02:00
vikingowl
33d11ae223 fix(agent): improve ReAct parser and tool schemas for better LLM compatibility 
- Fix ACTION_INPUT regex to properly capture multiline JSON responses
  - Changed from stopping at first newline to capturing all remaining text
  - Resolves parsing errors when LLM generates formatted JSON with line breaks

- Enhance tool schemas with detailed descriptions and parameter specifications
  - Add comprehensive Message schema for generate_text tool
  - Clarify distinction between resources/get (file read) and resources/list (directory listing)
  - Include clear usage guidance in tool descriptions

- Set default model to llama3.2:latest instead of invalid "ollama"

- Add parse error debugging to help troubleshoot LLM response issues

The agent infrastructure now correctly handles multiline tool arguments and
provides better guidance to LLMs through improved tool schemas. Remaining
errors are due to LLM quality (model making poor tool choices or generating
malformed responses), not infrastructure bugs.

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-10-09 19:43:07 +02:00