triage

# /supergraph:triage Classify issues with a formal state machine. `ready-for-agent` is the handoff trigger to the supergraph pipeline. Announce: "🗂️ /supergraph:triage — classifying issues..." ## State Machine ``` needs-triage ├── enough info → [assign category] → ready-for-agent | ready-for-human └── missing info → needs-info → [info provided] → ready-for-agent | ready-for-human ready-for-agent → supergraph:plan pipeline ready-for-human → manual dev / architectural decision needed wontfix → closed with reason ``` ## Category Roles | Category | When | |---|---| | `bug` | Observed behavior differs from specified behavior | | `enhancement` | New capability or improvement to existing behavior | | `question` | Needs clarification before any action | | `spike` | Research / proof-of-concept, no production code | ## State Roles | State | Meaning | |---|---| | `needs-triage` | Unreviewed — default for new issues | | `needs-info` | Blocked on missing information from reporter | | `ready-for-agent` | Fully specified — safe for `/supergraph:plan` to consume | | `ready-for-human` | Needs human judgment (architecture, business decision, security) | | `wontfix` | Will not be addressed — reason required | ## Triage Workflow ### For each issue: **1. Read the issue completely.** **2. Assign category** — bug / enhancement / question / spike. **3. Check readiness for agent:** A `bug` is `ready-for-agent` when: - [ ] Steps to reproduce are clear - [ ] Expected ...