- 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.
- 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.
Introduce the foundation for the Multi-Client Provider (MCP) architecture.
This phase includes:
- A new `McpClient` trait to abstract tool execution.
- A `LocalMcpClient` that executes tools in-process for backward compatibility ("legacy mode").
- A placeholder `RemoteMcpClient` for future development.
- An `McpMode` enum in the configuration (`mcp.mode`) to toggle between `legacy` and `enabled` modes, defaulting to `legacy`.
- Refactoring of `SessionController` to use the `McpClient` abstraction, decoupling it from the tool registry.
This lays the groundwork for routing tool calls to a remote MCP server in subsequent phases.
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>
Introduces a tool registry architecture with sandboxed code execution, web search capabilities, and consent-based permission management. Enables safe, pluggable LLM tool integration with schema validation.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Implements AES-256-GCM encrypted storage and keyring-based credential management for securely handling API keys and sensitive data. Supports secure local storage and OS-native keychain integration.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Introduces SQL schema for persistent conversation storage and encrypted secure items, supporting the new storage architecture for managing chat history and sensitive credentials.
🤖 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.
- Add `.pre-commit-config.yaml` with hooks for formatting, linting, and general file checks.
- Update `CONTRIBUTING.md` to include pre-commit setup instructions and emphasize automated checks during commits.
- Provide detailed steps for installing and running pre-commit hooks.
- 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.
- Introduce `.cargo/config.toml` with platform-specific linker and flags.
- Update Woodpecker CI to include Windows target, adjust build and packaging steps.
- Modify `Cargo.toml` to use `reqwest` with `rustls-tls` for TLS support.
