- Switch to `ollama-rs` crate for chat, model listing, and streaming.
- Remove custom request building, authentication handling, and debug logging.
- Drop unsupported tool conversion; now ignore tool descriptors with a warning.
- Refactor model fetching to use local model info and optional cloud details.
- Consolidate error mapping via `map_ollama_error`.
- Update health check to use the new HTTP client.
- Delete obsolete `provider_interface.rs` test as the provider interface has changed.
Deletes the `owlen-ollama` Cargo.toml and source files, fully removing the Ollama provider from the workspace. This aligns the project with the MCP‑only architecture and eliminates direct provider dependencies.
- Introduce `show_onboarding` UI setting (default true) and persist its state after first launch.
- Show onboarding status line and system status on initial run; fallback to normal status thereafter.
- Implement `show_tutorial` method displaying keybinding tips and system status.
- Register `:tutorial` command in command palette.
- Add migration documentation explaining `schema_version` update and deprecation of `agent.max_tool_calls`.
- Update README with description of the new tutorial command.
- Detect terminal color support and automatically switch to the new `ansi_basic` theme when only 16‑color support is available.
- Introduce `OfflineProvider` that supplies a placeholder model and friendly messages when no providers are reachable, keeping the TUI usable.
- Add `CONFIG_SCHEMA_VERSION` (`1.1.0`) with schema migration logic and default handling in `Config`.
- Update configuration saving to persist the schema version and ensure defaults.
- Register the `ansi_basic` theme in `theme.rs`.
- Extend `ChatApp` with `set_status_message` to display custom status lines.
- Update documentation (architecture, Vim mode state machine) to reflect new behavior.
- Add async‑trait and futures dependencies required for the offline provider implementation.
Phase 10 "Cleanup & Production Polish" is now complete. All LLM
interactions now go through the Model Context Protocol (MCP), removing
direct provider dependencies from CLI/TUI.
## Major Changes
### MCP Architecture
- All providers (local and cloud Ollama) now use RemoteMcpClient
- Removed owlen-ollama dependency from owlen-tui
- MCP LLM server accepts OLLAMA_URL environment variable for cloud providers
- Proper notification handling for streaming responses
- Fixed response deserialization (McpToolResponse unwrapping)
### Code Cleanup
- Removed direct OllamaProvider instantiation from TUI
- Updated collect_models_from_all_providers() to use MCP for all providers
- Updated switch_provider() to use MCP with environment configuration
- Removed unused general config variable
### Documentation
- Added comprehensive MCP Architecture section to docs/architecture.md
- Documented MCP communication flow and cloud provider support
- Updated crate breakdown to reflect MCP servers
### Security & Performance
- Path traversal protection verified for all resource operations
- Process isolation via separate MCP server processes
- Tool permissions controlled via consent manager
- Clean release build of entire workspace verified
## Benefits of MCP Architecture
1. **Separation of Concerns**: TUI/CLI never directly instantiates providers
2. **Process Isolation**: LLM interactions run in separate processes
3. **Extensibility**: New providers can be added as MCP servers
4. **Multi-Transport**: Supports STDIO, HTTP, and WebSocket
5. **Tool Integration**: MCP servers expose tools to LLMs
This completes Phase 10 and establishes a clean, production-ready architecture
for future development.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
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>
- 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>
- Introduce `owlen-mcp-llm-server` crate with RPC handling, `generate_text` tool, model listing, and streaming notifications.
- Add `RpcNotification` struct and `MODELS_LIST` method to the MCP protocol.
- Update `owlen-core` to depend on `tokio-stream`.
- Adjust Ollama provider to omit empty `tools` field for compatibility.
- Enhance `RemoteMcpClient` to locate the renamed server binary, handle resource tools locally, and implement the `Provider` trait (model listing, chat, streaming, health check).
- Add new crate to workspace `Cargo.toml`.
- Added a `tool_output` color to the `Theme` struct.
- Updated all built-in themes to include the new color.
- Modified the TUI to use the `tool_output` color for rendering tool output.
- Added a `tool_output` color to the `Theme` struct.
- Updated all built-in themes to include the new color.
- Modified the TUI to use the `tool_output` color for rendering tool output.
Adds consent management for tool execution, input validation, sandboxed process execution, and MCP server integration. Updates session management to support tool use, conversation persistence, and streaming responses.
Major additions:
- Database migrations for conversations and secure storage
- Encryption and credential management infrastructure
- Extensible tool system with code execution and web search
- Consent management and validation systems
- Sandboxed process execution
- MCP server integration
Infrastructure changes:
- Module registration and workspace dependencies
- ToolCall type and tool-related Message methods
- Privacy, security, and tool configuration structures
- Database-backed conversation persistence
- Tool call tracking in conversations
Provider and UI updates:
- Ollama provider updates for tool support and new Role types
- TUI chat and code app updates for async initialization
- CLI updates for new SessionController API
- Configuration documentation updates
- CHANGELOG updates
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Standardize array and vector formatting for clarity.
- Adjust spacing and indentation in examples and TUI code.
- Ensure proper newline usage across files (e.g., LICENSE, TOML files, etc.).
- Simplify `.to_string()` and `.ok()` calls for brevity.
- Include detailed architecture overview in `docs/architecture.md`.
- Add `docs/configuration.md`, detailing configuration file structure and settings.
- Provide a step-by-step provider implementation guide in `docs/provider-implementation.md`.
- Add frequently asked questions (FAQ) document in `docs/faq.md`.
- Create `docs/migration-guide.md` for future breaking changes and version upgrades.
- Introduce new examples in `examples/` showcasing basic chat, custom providers, and theming.
- Add a changelog (`CHANGELOG.md`) for tracking significant changes.
- Provide contribution guidelines (`CONTRIBUTING.md`) and a Code of Conduct (`CODE_OF_CONDUCT.md`).
- Introduce multiple built-in themes (`default_dark`, `default_light`, `gruvbox`, `dracula`, `solarized`, `midnight-ocean`, `rose-pine`, `monokai`, `material-dark`, `material-light`).
- Implement theming system with customizable color schemes for all UI components in the TUI.
- Include documentation for themes in `themes/README.md`.
- Add fallback mechanisms for default themes in case of parsing errors.
- Support custom themes with overrides via configuration.
- Introduce `command_suggestions` feature for autocompletion in Command mode.
- Implement `render_command_suggestions` to display filtered suggestions in a popup.
- Enable navigation through suggestions using Up/Down keys and Tab for completion.
- Add dynamic filtering of suggestions based on input buffer.
- Improve input handling, ensuring suggestion state resets appropriately when exiting Command mode.
- Refactor `render_help` to display tabbed UI for help topics.
- Introduce `help_tab_index` to manage selected tab state.
- Allow navigation between help tabs using Tab, h/l, and number keys (1-5).
- Enhance visual design of help sections using styled tabs and categorized content.
- Update input handling to reset tab state upon exit from help mode.
- Implement `StorageManager` for saving, loading, and managing sessions.
- Introduce platform-specific session directories for persistence.
- Add session browser UI for listing, loading, and deleting saved sessions.
- Enable AI-generated descriptions for session summaries.
- Update configurations to support storage settings and description generation.
- Extend README and tests to document and validate new functionality.
