Adds detailed reference for all 21 subcommands with arguments,
options, and usage examples. Agents can run `miyabi-gate gate guide`
to get both the workflow overview and per-command documentation.
Closes#113
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Prints a complete workflow guide that any AI agent can read to
understand how to use Polaris: rules, step-by-step workflow,
context attachments, emergency commands, exit codes, and
quality checks.
Closes#111
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
F1: Add depth limit (max 5) to find_note_by_name and
collect_obsidian_matches to prevent stack overflow on large vaults
F2: Fix bus_enqueue to use store_path parent instead of cwd
F3: Fix update_skill_md_from_patterns to preserve sections after
the auto-generated marker instead of truncating them
F4: Fix extract_wikilinks to consume chars after | in [[Note|Display]]
so subsequent links parse correctly
Tests added:
- extract_wikilinks: basic, display text, empty/broken
- find_note_by_name: depth limit enforcement
- resolve_wikilink: direct, nested, non-existent
- build_rejection_section: empty, sorted by count desc
- update_skill_md_from_patterns: append, replace preserving following sections
955 tests GREEN, clippy zero.
Closes#109
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Adds a Completion Stats panel to the Polaris web dashboard showing:
- Completion percentage with large display
- Visual progress bar (green)
- Breakdown of done/active/pending/total tasks
Closes#97
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
After successful task registration, automatically append a queued
entry to skill-runs.jsonl. This connects the Polaris gate workflow
to the skill-bus tracking system.
Use --no-bus to skip auto-enqueue when not needed.
Closes#93
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Add openclaw.rs module for cluster communication
- Expand CLI with OpenClaw-related commands (264 lines)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Phase 2: Hooks System
- Event-driven execution with HookEvent/HookAction types
- HookManager for registration and execution
Phase 3: Multi-Agent Workflow
- Workflow orchestration with dependency graphs
- WorkflowStep with conditions and retry support
Phase 4: MCP (Model Context Protocol) Support
- McpServer for external tool servers
- McpManager for multiple server management
Also includes core modules: cache, error_policy, feature_flags,
git, logger, plugin, retry, rules
662 tests passing
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
