Milestone M6 implementation adds a comprehensive hook system that allows
users to run custom scripts at various lifecycle events.
New crate: crates/platform/hooks
- HookEvent enum with multiple event types:
* PreToolUse: fires before tool execution, can deny operations (exit code 2)
* PostToolUse: fires after tool execution
* SessionStart: fires at session start, can persist env vars
* SessionEnd, UserPromptSubmit, PreCompact (defined for future use)
- HookManager for executing hooks with timeout support
- JSON I/O: hooks receive event data via stdin, can output to stdout
- Hooks located in .owlen/hooks/{EventName}
CLI integration:
- All tool commands (Read, Write, Edit, Glob, Grep, Bash, SlashCommand)
now fire PreToolUse hooks before execution
- Hooks can deny operations by exiting with code 2
- Hooks timeout after 5 seconds by default
Tests added:
- pretooluse_can_deny_call: verifies hooks can block tool execution
- posttooluse_runs_parallel: verifies PostToolUse hooks execute
- sessionstart_persists_env: verifies SessionStart can create env files
- hook_timeout_works: verifies timeout mechanism
- hook_not_found_is_ok: verifies missing hooks don't cause errors
All 63 tests passing.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Changes slash command directory from `.claude/commands/` to
`.owlen/commands/` to reflect that owlen is its own tool while
maintaining compatibility with claude-code slash command syntax.
Updated locations:
- CLI main: command file path lookup
- Tests: slash_command_works and slash_command_file_refs
All 56 tests passing.
This commit implements the complete M1 milestone (Config & Permissions) including:
- New permissions crate with Tool, Action, Mode, and PermissionManager
- Three permission modes: Plan (read-only default), AcceptEdits, Code
- Pattern matching for permission rules (exact match and prefix with *)
- Integration with config-agent for mode-based permission management
- CLI integration with --mode flag to override configured mode
- Permission checks for Read, Glob, and Grep operations
- Comprehensive test suite (10 tests in permissions, 4 in config, 4 in CLI)
Also fixes:
- Fixed failing test in tools-fs (glob pattern issue)
- Improved glob_list() root extraction to handle patterns like "/*.txt"
All 21 workspace tests passing.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Update workspace members and dependency paths to reflect new directory structure:
- crates/cli → crates/app/cli
- crates/config → crates/platform/config
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add new tools-fs crate with read, glob, and grep utilities
- Fix glob command to support actual glob patterns (**, *) instead of just directory walking
- Rename binary from "code" to "owlen" to match package name
- Fix test to reference correct binary name "owlen"
- Add API key support to OllamaClient for authentication
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Add support for Ollama Cloud by detecting model names with "-cloud" suffix
and checking for API key presence. Update config to read OLLAMA_API_KEY
environment variable. When both conditions are met, automatically use
https://ollama.com endpoint; otherwise use local/configured URL.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Fix configuration loading order to ensure environment variables have
highest precedence over config files. Also update env prefix from
CODE_ to OWLEN_ for consistency with project naming.
Changes:
- Move env variable merge to end of chain for proper precedence
- Update environment prefix from CODE_ to OWLEN_
- Add precedence tests to verify correct override behavior
- Clean up unused dependencies (serde_json, toml)
- Add tempfile dev dependency for testing
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Set up Cargo workspace with initial crates:
- cli: main application entry point with chat streaming tests
- config: configuration management
- llm/ollama: Ollama client integration with NDJSON support
Includes .gitignore for Rust and JetBrains IDEs.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
This commit completes all remaining Sprint 1 tasks from the project analysis:
**MCP RPC Timeout Protection**
- Add configurable `rpc_timeout_secs` field to McpServerConfig
- Implement operation-specific timeouts (10s-120s based on method type)
- Wrap all MCP RPC calls with tokio::time::timeout to prevent indefinite hangs
- Add comprehensive test suite (mcp_timeout.rs) with 5 test cases
- Modified files: config.rs, remote_client.rs, presets.rs, failover.rs, factory.rs, chat_app.rs, mcp.rs
**Async Migration Completion**
- Remove all remaining tokio::task::block_in_place calls
- Replace with try_lock() spin loop pattern for uncontended config access
- Maintains sync API for UI rendering while completing async migration
- Modified files: session.rs (config/config_mut), chat_app.rs (controller_lock)
**Dependency Updates**
- Update tokio 1.47.1 → 1.48.0 for latest performance improvements
- Update reqwest 0.12.23 → 0.12.24 for security patches
- Update 60+ transitive dependencies via cargo update
- Run cargo audit: identified 3 CVEs for Sprint 2 (sqlx, ring, rsa)
**Code Quality**
- Fix clippy deprecation warnings (generic-array 0.x usage in encryption/storage)
- Add temporary #![allow(deprecated)] with TODO comments for future generic-array 1.x upgrade
- All tests passing (except 1 pre-existing failure unrelated to these changes)
Sprint 1 is now complete. Next up: Sprint 2 security fixes and test coverage improvements.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Acceptance Criteria:\n- Declarative keymap sequences replace pending_key/pending_focus_chord logic.\n- :keymap show streams the active binding table and bindings export reflects new schema.\n- Vim/Emacs default keymaps resolve multi-step chords via the registry.
Test Notes:\n- cargo test -p owlen-tui
Acceptance Criteria:\n- Users can toggle high-contrast and reduced-chrome modes via :accessibility commands.\n- Accessibility flags persist in config and update UI header legends without restart.\n- Reduced chrome removes glass shadows while preserving layout readability.
Test Notes:\n- cargo test -p owlen-tui
Acceptance-Criteria:\n- snapshot coverage for idle chat and tool-call streaming states protects header, toast, and transcript rendering.\n- Tests use deterministic settings so reruns pass without manual snapshot acceptance.
Test-Notes:\n- INSTA_UPDATE=always cargo test -p owlen-tui --test chat_snapshots\n- cargo test
Acceptance-Criteria:\n- spec-compliant names are shared via WEB_SEARCH_TOOL_NAME and ModeConfig checks canonical identifiers.\n- workspace depends on once_cell so regex helpers build without local target hacks.
Test-Notes:\n- cargo test
Acceptance-Criteria:\n- cloud WireMock tests pass when providers.ollama_cloud.base_url targets a local endpoint.\n- 429 responses surface ProviderErrorKind::RateLimited and 401 payloads report API key guidance.
Test-Notes:\n- cargo test -p owlen-core --test ollama_wiremock cloud_rate_limit_returns_error_without_usage\n- cargo test -p owlen-core --test ollama_wiremock cloud_tool_call_flows_through_web_search\n- cargo test
- Introduce reference MCP presets with installation/audit helpers and remove legacy connector lists.
- Add CLI `owlen tools` commands to install presets or audit configuration, with optional pruning.
- Extend the TUI :tools command to support listing presets, installing them, and auditing current configuration.
- Document the preset workflow and provide regression tests for preset application.
- Reject dotted tool identifiers during registration and remove alias-backed lookups.
- Drop web.search compatibility, normalize all code/tests around the canonical web_search name, and update consent/session logic.
- Harden CLI toggles to manage the spec-compliant identifier and ensure MCP configs shed non-compliant entries automatically.
Acceptance Criteria:
- Tool registry denies invalid identifiers by default and no alias codepaths remain.
Test Notes:
- cargo check -p owlen-core (tests unavailable in sandbox).
Acceptance Criteria:
- Workspace builds against ratatui 0.29, crossterm 0.28.1, and tui-textarea 0.7 with palette support enabled
- Chat header context and usage gauges render with refreshed tailwind gradients
- Header layout uses the Flex API to balance top-row metadata across window widths
Test Notes:
- cargo test -p owlen-tui
Acceptance Criteria:\n- Local provider chat succeeds and records usage\n- Cloud tool-call scenario exercises web.search and usage tracking\n- Unauthorized and rate-limited cloud responses surface errors without recording usage\n\nTest Notes:\n- CARGO_NET_OFFLINE=true cargo test -p owlen-core --tests ollama_wiremock
AC:\n- Providers emit ProviderFailure with structured kind/detail for auth, rate-limit, timeout, and unavailable cases.\n- TUI maps ProviderFailure kinds to consistent toasts and fallbacks (no 429 string matching).\n- Cloud health checks detect unauthorized failures without relying on string parsing.\n\nTests:\n- cargo test -p owlen-core (fails: httpmock cannot bind 127.0.0.1 inside sandbox).\n- cargo test -p owlen-providers\n- cargo test -p owlen-tui
