84fa08ab45
feat(plan): Add plan execution system with external tool support
...
Plan Execution System:
- Add PlanStep, AccumulatedPlan types for multi-turn tool call accumulation
- Implement AccumulatedPlanStatus for tracking plan lifecycle
- Support selective approval of proposed tool calls before execution
External Tools Integration:
- Add ExternalToolDefinition and ExternalToolTransport to plugins crate
- Extend ToolContext with external_tools registry
- Add external_tool_to_llm_tool conversion for LLM compatibility
JSON-RPC Communication:
- Add jsonrpc crate for JSON-RPC 2.0 protocol support
- Enable stdio-based communication with external tool servers
UI & Engine Updates:
- Add plan_panel.rs component for displaying accumulated plans
- Wire plan mode into engine loop
- Add plan mode integration tests
🤖 Generated with [Claude Code](https://claude.com/claude-code )
Co-Authored-By: Claude <noreply@anthropic.com >
2025-12-26 22:47:54 +01:00
997007439e
docs(platform): Add README.md for all platform crates
2025-12-26 18:30:56 +01:00
5b0774958a
feat(auth): add multi-provider authentication with secure credential storage
...
Authentication System:
- Add credentials crate with keyring (OS keychain) and file fallback storage
- Add auth-manager crate for unified auth across providers
- Implement API key login flow for Anthropic, OpenAI, and Ollama Cloud
- Add CLI commands: login, logout, auth (status)
- Store credentials securely in macOS Keychain / GNOME Keyring / Windows Credential Manager
API Key Helpers:
- Support for password manager integration (1Password, Bitwarden, pass, AWS Secrets, Vault)
- Command-based helpers with TTL caching
- Priority chain: env vars → helpers → cache → stored credentials
Background Token Refresh:
- Automatic OAuth token refresh before expiration
- Configurable check interval and refresh threshold
MCP OAuth Support:
- Add OAuth config to MCP server definitions
- Support for SSE/HTTP transport with OAuth
- Token storage with mcp: prefix
Bug Fixes:
- Fix keyring crate requiring explicit backend features (was using mock store)
- Fix provider index not updated on credential store
- Add User-Agent headers to avoid Cloudflare blocks
🤖 Generated with [Claude Code](https://claude.ai/claude-code )
Co-Authored-By: Claude <noreply@anthropic.com >
2025-12-03 00:27:37 +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
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
