Files
msd-core/gsd-core/workflows/diagnose-issues.md
Tom Boucher 7c07fce70f fix(#381): make gsd_run launcher reachable in fresh-shell-per-block runtimes (#1084)
* fix(#381): make gsd_run launcher reachable in fresh-shell-per-block runtimes

On runtimes that execute each fenced bash block in a separate shell process
(e.g. Claude Code — documented behavior: each Bash command is a separate
process; inline shell functions and exported vars do not persist between
calls), the once-per-file gsd_run() function was undefined in every block
after the preamble block, and the call was swallowed by
`2>/dev/null || echo "{}"` into silent empty state.

Fix (budget-neutral session-level resolution):
- Ship gsd-core/bin/gsd_run, a POSIX sh wrapper that symlink-resolves its own
  location and execs the co-located gsd-tools.cjs. Exposed on PATH via the npm
  `bin` field (global installs) and shipped to local installs via the recursive
  gsd-core/ copy.
- The per-file launcher preamble now appends `export PATH='<bindir>':"$PATH"`
  to the file named by $CLAUDE_ENV_FILE (Claude Code's documented
  env-persistence mechanism) so later fresh-shell blocks resolve gsd_run from
  PATH. Guarded as a strict no-op when CLAUDE_ENV_FILE is unset; the inline
  gsd_run() definition remains the fallback for all other runtimes. The
  single-quoted dir neutralizes shell metacharacters at source time.
- Propagated via scripts/sync-runtime-launcher.cjs to all launcher-using files.
- XL workflow byte budget 93000 -> 93200 (the ~130B clause pushes plan-phase.md
  to 93135; legitimate content growth, ratchet-up per #717).

Regression tests (I)/(J) in runtime-launcher-parity.test.cjs cover wrapper
delegation and end-to-end PATH persistence (sourcing the env file with a
space-bearing install path).

Known limitation: an install path containing a literal single-quote yields a
malformed env-file line and falls back to the status quo (no regression);
rare on sanitized home directories.

Closes #381

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

* docs(#381): add changeset for gsd_run fresh-shell reachability fix

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

* test(#381): scope test (J) bare-PATH execution to POSIX (Windows Git Bash exec bit)

Windows Git Bash (msys2) does not honor Node's chmod exec bit for
PATH-executing extension-less scripts, so the bare `gsd_run` command lookup
failed there even though the env-file PATH persistence was correct. The
env-file content assertions (the fix's actual cross-platform logic) still run
on every platform; only the final source-and-execute sub-step is gated to
non-win32. Global installs on Windows are covered by npm's generated bin shim.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

---------

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-11 21:42:52 -04:00

12 KiB
Raw Blame History

Orchestrate parallel debug agents to investigate UAT gaps and find root causes.

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.

<available_agent_types> Valid GSD subagent types (use exact names — do not fall back to 'general-purpose'):

  • gsd-debugger — Diagnoses and fixes issues </available_agent_types>
DEBUG_DIR=.planning/debug

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

<core_principle> Diagnose before planning fixes.

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 </core_principle>

**Extract gaps from UAT.md:**

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: "..."},
  ...
]
**Read worktree config:**
_GSD_SHIM_NAME="gsd-tools.cjs"; _GSD_RUNTIME_ROOT="${RUNTIME_DIR:-$(git rev-parse --show-toplevel 2>/dev/null || pwd)}"; GSD_TOOLS="${_GSD_RUNTIME_ROOT}/gsd-core/bin/${_GSD_SHIM_NAME}"; if [ -f "$GSD_TOOLS" ]; then gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${_GSD_RUNTIME_ROOT}/.claude/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${_GSD_RUNTIME_ROOT}/.claude/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${_GSD_RUNTIME_ROOT}/.codex/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${_GSD_RUNTIME_ROOT}/.codex/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif command -v gsd-tools >/dev/null 2>&1; then GSD_TOOLS="$(command -v gsd-tools)"; gsd_run() { "$GSD_TOOLS" "$@"; }; elif [ -f "$HOME/.claude/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="$HOME/.claude/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${HERMES_HOME:-$HOME/.hermes}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${HERMES_HOME:-$HOME/.hermes}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${CURSOR_CONFIG_DIR:-$HOME/.cursor}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${CURSOR_CONFIG_DIR:-$HOME/.cursor}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${CODEX_HOME:-$HOME/.codex}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${CODEX_HOME:-$HOME/.codex}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${GEMINI_CONFIG_DIR:-$HOME/.gemini}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${GEMINI_CONFIG_DIR:-$HOME/.gemini}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${COPILOT_CONFIG_DIR:-$HOME/.copilot}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${COPILOT_CONFIG_DIR:-$HOME/.copilot}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${WINDSURF_CONFIG_DIR:-$HOME/.codeium/windsurf}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${WINDSURF_CONFIG_DIR:-$HOME/.codeium/windsurf}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${AUGMENT_CONFIG_DIR:-$HOME/.augment}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${AUGMENT_CONFIG_DIR:-$HOME/.augment}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${TRAE_CONFIG_DIR:-$HOME/.trae}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${TRAE_CONFIG_DIR:-$HOME/.trae}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${QWEN_CONFIG_DIR:-$HOME/.qwen}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${QWEN_CONFIG_DIR:-$HOME/.qwen}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${CODEBUDDY_CONFIG_DIR:-$HOME/.codebuddy}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${CODEBUDDY_CONFIG_DIR:-$HOME/.codebuddy}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${CLINE_CONFIG_DIR:-$HOME/.cline}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${CLINE_CONFIG_DIR:-$HOME/.cline}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${GROK_AGENTS_HOME:-$HOME/.agents}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${GROK_AGENTS_HOME:-$HOME/.agents}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${ANTIGRAVITY_CONFIG_DIR:-$HOME/.gemini/antigravity}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${ANTIGRAVITY_CONFIG_DIR:-$HOME/.gemini/antigravity}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${OPENCODE_CONFIG_DIR:-${XDG_CONFIG_HOME:-$HOME/.config}/opencode}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${OPENCODE_CONFIG_DIR:-${XDG_CONFIG_HOME:-$HOME/.config}/opencode}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${KILO_CONFIG_DIR:-${XDG_CONFIG_HOME:-$HOME/.config}/kilo}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${KILO_CONFIG_DIR:-${XDG_CONFIG_HOME:-$HOME/.config}/kilo}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; else echo "ERROR: gsd-tools.cjs not found at $GSD_TOOLS and gsd-tools is not on PATH. Run: npx -y @opengsd/gsd-core@latest --claude --local" >&2; exit 1; fi; if [ -n "${CLAUDE_ENV_FILE:-}" ] && [ -n "${GSD_TOOLS:-}" ]; then printf "export PATH='%s':\"\$PATH\"\n" "${GSD_TOOLS%/*}" >> "$CLAUDE_ENV_FILE" 2>/dev/null || true; fi
USE_WORKTREES=$(gsd_run 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.
**Load agent skills:**
AGENT_SKILLS_DEBUGGER=$(gsd_run query agent-skills gsd-debugger)
EXPECTED_BASE=$(git rev-parse HEAD)

Spawn debug agents in parallel:

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

Print: ◆ Spawning diagnostics agent... (each runs in a subagent — no output until they return, ~1–5 min; expected, not a freeze)

Before spawning, materialize the guard into WORKTREE_GUARD: read gsd-core/references/worktree-branch-check.md, substitute {EXPECTED_BASE} with $EXPECTED_BASE, and use the resulting <worktree_branch_check> block (the runnable guard) as WORKTREE_GUARD below.

Agent(
  prompt=filled_debug_subagent_prompt + "\n\n" + WORKTREE_GUARD + "\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}"
)

ORCHESTRATOR RULE — CODEX RUNTIME: After calling Agent() above to spawn debug agent(s), stop working on this task immediately. Do not read more files, edit code, or run tests related to these gaps while the subagent(s) are active. Wait for all subagents to return before proceeding. This prevents duplicate work, conflicting edits, and wasted context.

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
**Collect root causes from agents:**

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
**Update UAT.md gaps with diagnosis:**

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_run query commit "docs({phase_num}): add root causes from diagnosis" --files ".planning/phases/XX-name/{phase_num}-UAT.md"
**Report diagnosis results and hand off:**

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.

<context_efficiency> Agents start with symptoms pre-filled from UAT (no symptom gathering). Agents only diagnose—plan-phase --gaps handles fixes (no fix application). </context_efficiency>

<failure_handling> Agent fails to find root cause:

  • Mark gap as "needs manual review"
  • Continue with other gaps
  • Report incomplete diagnosis

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) </failure_handling>

<success_criteria>

  • Gaps parsed from UAT.md
  • Debug agents spawned in parallel
  • Root causes collected from all agents
  • UAT.md gaps updated with artifacts and missing
  • Debug sessions saved to ${DEBUG_DIR}/
  • Hand off to verify-work for automatic planning </success_criteria>