Diagnose Issues

After UAT finds gaps, spawn one debug agent per gap. Each agent investigates autonomously with symptoms pre-filled from UAT. Collect root causes, update UAT.md gaps with diagnosis, then hand off to plan-phase --gaps with actual diagnoses.

Orchestrator stays lean: parse gaps, spawn agents, collect results, update UAT.

Debug files use the .planning/debug/ path (hidden directory with leading dot).

UAT tells us WHAT is broken (symptoms). Debug agents find WHY (root cause). plan-phase --gaps then creates targeted fixes based on actual causes, not guesses.

Without diagnosis: "Comment doesn't refresh" → guess at fix → maybe wrong With diagnosis: "Comment doesn't refresh" → "useEffect missing dependency" → precise fix

Read the "Gaps" section (YAML format):

- truth: "Comment appears immediately after submission"
  status: failed
  reason: "User reported: works but doesn't show until I refresh the page"
  severity: major
  test: 2
  artifacts: []
  missing: []

For each gap, also read the corresponding test from "Tests" section to get full context.

Build gap list:

gaps = [
  {truth: "Comment appears immediately...", severity: "major", test_num: 2, reason: "..."},
  {truth: "Reply button positioned correctly...", severity: "minor", test_num: 5, reason: "..."},
  ...
]

USE_WORKTREES=$(gsd-sdk query config-get workflow.use_worktrees 2>/dev/null || echo "true")

Report diagnosis plan to user:

## Diagnosing {N} Gaps

Spawning parallel debug agents to investigate root causes:

| Gap (Truth) | Severity |
|-------------|----------|
| Comment appears immediately after submission | major |
| Reply button positioned correctly | minor |
| Delete removes comment | blocker |

Each agent will:
1. Create DEBUG-{slug}.md with symptoms pre-filled
2. Investigate autonomously (read code, form hypotheses, test)
3. Return root cause

This runs in parallel - all gaps investigated simultaneously.

AGENT_SKILLS_DEBUGGER=$(gsd-sdk query agent-skills gsd-debugger 2>/dev/null)
EXPECTED_BASE=$(git rev-parse HEAD)

Spawn debug agents in parallel:

For each gap, fill the debug-subagent-prompt template and spawn:

Task(
  prompt=filled_debug_subagent_prompt + "\n\n<worktree_branch_check>\nFIRST ACTION: run git merge-base HEAD {EXPECTED_BASE} — if result differs from {EXPECTED_BASE}, run git reset --hard {EXPECTED_BASE} to correct the branch base (safe — runs before any agent work). Then verify: if [ \"$(git rev-parse HEAD)\" != \"{EXPECTED_BASE}\" ]; then echo \"ERROR: Could not correct worktree base\"; exit 1; fi. Fixes EnterWorktree creating branches from main on all platforms.\n</worktree_branch_check>\n\n<files_to_read>\n- {phase_dir}/{phase_num}-UAT.md\n- .planning/STATE.md\n</files_to_read>\n${AGENT_SKILLS_DEBUGGER}",
  subagent_type="gsd-debugger",
  ${USE_WORKTREES !== "false" ? 'isolation="worktree",' : ''}
  description="Debug: {truth_short}"
)

All agents spawn in single message (parallel execution).

Template placeholders:

• {truth}: The expected behavior that failed
• {expected}: From UAT test
• {actual}: Verbatim user description from reason field
• {errors}: Any error messages from UAT (or "None reported")
• {reproduction}: "Test {test_num} in UAT"
• {timeline}: "Discovered during UAT"
• {goal}: find_root_cause_only (UAT flow - plan-phase --gaps handles fixes)
• {slug}: Generated from truth

Each agent returns with:

## ROOT CAUSE FOUND

**Debug Session:** ${DEBUG_DIR}/{slug}.md

**Root Cause:** {specific cause with evidence}

**Evidence Summary:**
- {key finding 1}
- {key finding 2}
- {key finding 3}

**Files Involved:**
- {file1}: {what's wrong}
- {file2}: {related issue}

**Suggested Fix Direction:** {brief hint for plan-phase --gaps}

Parse each return to extract:

• root_cause: The diagnosed cause
• files: Files involved
• debug_path: Path to debug session file
• suggested_fix: Hint for gap closure plan

If agent returns ## INVESTIGATION INCONCLUSIVE:

• root_cause: "Investigation inconclusive - manual review needed"
• Note which issue needs manual attention
• Include remaining possibilities from agent return

For each gap in the Gaps section, add artifacts and missing fields:

- truth: "Comment appears immediately after submission"
  status: failed
  reason: "User reported: works but doesn't show until I refresh the page"
  severity: major
  test: 2
  root_cause: "useEffect in CommentList.tsx missing commentCount dependency"
  artifacts:
    - path: "src/components/CommentList.tsx"
      issue: "useEffect missing dependency"
  missing:
    - "Add commentCount to useEffect dependency array"
    - "Trigger re-render when new comment added"
  debug_session: .planning/debug/comment-not-refreshing.md

Update status in frontmatter to "diagnosed".

Commit the updated UAT.md:

gsd-sdk query commit "docs({phase_num}): add root causes from diagnosis" ".planning/phases/XX-name/{phase_num}-UAT.md"

Display:

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 GSD ► DIAGNOSIS COMPLETE
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

| Gap (Truth) | Root Cause | Files |
|-------------|------------|-------|
| Comment appears immediately | useEffect missing dependency | CommentList.tsx |
| Reply button positioned correctly | CSS flex order incorrect | ReplyButton.tsx |
| Delete removes comment | API missing auth header | api/comments.ts |

Debug sessions: ${DEBUG_DIR}/

Proceeding to plan fixes...

Return to verify-work orchestrator for automatic planning. Do NOT offer manual next steps - verify-work handles the rest.

Agent times out:

• Check DEBUG-{slug}.md for partial progress
• Can resume with /gsd-debug

All agents fail:

• Something systemic (permissions, git, etc.)
• Report for manual investigation
• Fall back to plan-phase --gaps without root causes (less precise)