@sienklogic/plan-build-run 2.11.0 → 2.12.1

package/plan-build-run/workflows/execute-phase.md

@@ -0,0 +1,439 @@
+<purpose>
+Execute all plans in a phase using wave-based parallel execution. Orchestrator stays lean — delegates plan execution to subagents.
+</purpose>
+
+<core_principle>
+Orchestrator coordinates, not executes. Each subagent loads the full execute-plan context. Orchestrator: discover plans → analyze deps → group waves → spawn agents → handle checkpoints → collect results.
+</core_principle>
+
+<required_reading>
+Read STATE.md before any operation to load project context.
+</required_reading>
+
+<process>
+
+<step name="initialize" priority="first">
+Load all context in one call:
+
+```bash
+INIT=$(node ~/.claude/plan-build-run/scripts/pbr-tools.cjs init execute-phase "${PHASE_ARG}")
+```
+
+Parse JSON for: `executor_model`, `verifier_model`, `commit_docs`, `parallelization`, `branching_strategy`, `branch_name`, `phase_found`, `phase_dir`, `phase_number`, `phase_name`, `phase_slug`, `plans`, `incomplete_plans`, `plan_count`, `incomplete_count`, `state_exists`, `roadmap_exists`.
+
+**If `phase_found` is false:** Error — phase directory not found.
+**If `plan_count` is 0:** Error — no plans found in phase.
+**If `state_exists` is false but `.planning/` exists:** Offer reconstruct or continue.
+
+When `parallelization` is false, plans within a wave execute sequentially.
+</step>
+
+<step name="handle_branching">
+Check `branching_strategy` from init:
+
+**"none":** Skip, continue on current branch.
+
+**"phase" or "milestone":** Use pre-computed `branch_name` from init:
+```bash
+git checkout -b "$BRANCH_NAME" 2>/dev/null || git checkout "$BRANCH_NAME"
+```
+
+All subsequent commits go to this branch. User handles merging.
+</step>
+
+<step name="validate_phase">
+From init JSON: `phase_dir`, `plan_count`, `incomplete_count`.
+
+Report: "Found {plan_count} plans in {phase_dir} ({incomplete_count} incomplete)"
+</step>
+
+<step name="discover_and_group_plans">
+Load plan inventory with wave grouping in one call:
+
+```bash
+PLAN_INDEX=$(node ~/.claude/plan-build-run/scripts/pbr-tools.cjs phase-plan-index "${PHASE_NUMBER}")
+```
+
+Parse JSON for: `phase`, `plans[]` (each with `id`, `wave`, `autonomous`, `objective`, `files_modified`, `task_count`, `has_summary`), `waves` (map of wave number → plan IDs), `incomplete`, `has_checkpoints`.
+
+**Filtering:** Skip plans where `has_summary: true`. If `--gaps-only`: also skip non-gap_closure plans. If all filtered: "No matching incomplete plans" → exit.
+
+Report:
+```
+## Execution Plan
+
+**Phase {X}: {Name}** — {total_plans} plans across {wave_count} waves
+
+| Wave | Plans | What it builds |
+|------|-------|----------------|
+| 1 | 01-01, 01-02 | {from plan objectives, 3-8 words} |
+| 2 | 01-03 | ... |
+```
+</step>
+
+<step name="execute_waves">
+Execute each wave in sequence. Within a wave: parallel if `PARALLELIZATION=true`, sequential if `false`.
+
+**For each wave:**
+
+1. **Describe what's being built (BEFORE spawning):**
+
+   Read each plan's `<objective>`. Extract what's being built and why.
+
+   ```
+   ---
+   ## Wave {N}
+
+   **{Plan ID}: {Plan Name}**
+   {2-3 sentences: what this builds, technical approach, why it matters}
+
+   Spawning {count} agent(s)...
+   ---
+   ```
+
+   - Bad: "Executing terrain generation plan"
+   - Good: "Procedural terrain generator using Perlin noise — creates height maps, biome zones, and collision meshes. Required before vehicle physics can interact with ground."
+
+2. **Spawn executor agents:**
+
+   Pass paths only — executors read files themselves with their fresh 200k context.
+   This keeps orchestrator context lean (~10-15%).
+
+   Check if CONTEXT.md exists for this phase:
+
+   ```bash
+   CONTEXT_FILE=$(ls ${phase_dir}/*-CONTEXT.md 2>/dev/null | head -1)
+   ```
+
+   ```
+   Task(
+     subagent_type="pbr-executor",
+     model="{executor_model}",
+     prompt="
+       <objective>
+       Execute plan {plan_number} of phase {phase_number}-{phase_name}.
+       Commit each task atomically. Create SUMMARY.md. Update STATE.md.
+       </objective>
+
+       <execution_context>
+       @~/.claude/plan-build-run/workflows/execute-plan.md
+       @~/.claude/plan-build-run/templates/summary.md
+       @~/.claude/plan-build-run/references/checkpoints.md
+       @~/.claude/plan-build-run/references/tdd.md
+       </execution_context>
+
+       <files_to_read>
+       Read these files at execution start using the Read tool:
+       - Plan: {phase_dir}/{plan_file}
+       - State: .planning/STATE.md
+       - Config: .planning/config.json (if exists)
+       - Context: {CONTEXT_FILE} (if exists — contains user decisions from discuss-phase)
+       </files_to_read>
+
+       <user_decisions>
+       If a CONTEXT.md file exists for this phase, read it FIRST. It contains
+       user decisions from the discuss-phase that MUST be honored during execution.
+       The plan encodes most decisions, but CONTEXT.md is the authoritative source
+       for user intent. When the plan is ambiguous, defer to CONTEXT.md.
+       </user_decisions>
+
+       <success_criteria>
+       - [ ] All tasks executed
+       - [ ] Each task committed individually
+       - [ ] SUMMARY.md created in plan directory
+       - [ ] STATE.md updated with position and decisions
+       </success_criteria>
+     "
+   )
+   ```
+
+3. **Wait for all agents in wave to complete.**
+
+4. **Report completion — spot-check claims first:**
+
+   For each SUMMARY.md:
+   - Verify first 2 files from `key-files.created` exist on disk
+   - Check `git log --oneline --all --grep="{phase}-{plan}"` returns ≥1 commit
+   - Check for `## Self-Check: FAILED` marker
+
+   If ANY spot-check fails: report which plan failed, route to failure handler — ask "Retry plan?" or "Continue with remaining waves?"
+
+   If pass:
+   ```
+   ---
+   ## Wave {N} Complete
+
+   **{Plan ID}: {Plan Name}**
+   {What was built — from SUMMARY.md}
+   {Notable deviations, if any}
+
+   {If more waves: what this enables for next wave}
+   ---
+   ```
+
+   - Bad: "Wave 2 complete. Proceeding to Wave 3."
+   - Good: "Terrain system complete — 3 biome types, height-based texturing, physics collision meshes. Vehicle physics (Wave 3) can now reference ground surfaces."
+
+5. **Handle failures:**
+
+   **Known Claude Code bug (classifyHandoffIfNeeded):** If an agent reports "failed" with error containing `classifyHandoffIfNeeded is not defined`, this is a Claude Code runtime bug — not a PBR or agent issue. The error fires in the completion handler AFTER all tool calls finish. In this case: run the same spot-checks as step 4 (SUMMARY.md exists, git commits present, no Self-Check: FAILED). If spot-checks PASS → treat as **successful**. If spot-checks FAIL → treat as real failure below.
+
+   For real failures: report which plan failed → ask "Continue?" or "Stop?" → if continue, dependent plans may also fail. If stop, partial completion report.
+
+6. **Execute checkpoint plans between waves** — see `<checkpoint_handling>`.
+
+7. **Proceed to next wave.**
+</step>
+
+<step name="checkpoint_handling">
+Plans with `autonomous: false` require user interaction.
+
+**Flow:**
+
+1. Spawn agent for checkpoint plan
+2. Agent runs until checkpoint task or auth gate → returns structured state
+3. Agent return includes: completed tasks table, current task + blocker, checkpoint type/details, what's awaited
+4. **Present to user:**
+   ```
+   ## Checkpoint: [Type]
+
+   **Plan:** 03-03 Dashboard Layout
+   **Progress:** 2/3 tasks complete
+
+   [Checkpoint Details from agent return]
+   [Awaiting section from agent return]
+   ```
+5. User responds: "approved"/"done" | issue description | decision selection
+6. **Spawn continuation agent (NOT resume)** using continuation-prompt.md template:
+   - `{completed_tasks_table}`: From checkpoint return
+   - `{resume_task_number}` + `{resume_task_name}`: Current task
+   - `{user_response}`: What user provided
+   - `{resume_instructions}`: Based on checkpoint type
+7. Continuation agent verifies previous commits, continues from resume point
+8. Repeat until plan completes or user stops
+
+**Why fresh agent, not resume:** Resume relies on internal serialization that breaks with parallel tool calls. Fresh agents with explicit state are more reliable.
+
+**Checkpoints in parallel waves:** Agent pauses and returns while other parallel agents may complete. Present checkpoint, spawn continuation, wait for all before next wave.
+</step>
+
+<step name="aggregate_results">
+After all waves:
+
+```markdown
+## Phase {X}: {Name} Execution Complete
+
+**Waves:** {N} | **Plans:** {M}/{total} complete
+
+| Wave | Plans | Status |
+|------|-------|--------|
+| 1 | plan-01, plan-02 | ✓ Complete |
+| CP | plan-03 | ✓ Verified |
+| 2 | plan-04 | ✓ Complete |
+
+### Plan Details
+1. **03-01**: [one-liner from SUMMARY.md]
+2. **03-02**: [one-liner from SUMMARY.md]
+
+### Issues Encountered
+[Aggregate from SUMMARYs, or "None"]
+```
+</step>
+
+<step name="verify_phase_goal">
+Verify phase achieved its GOAL, not just completed tasks.
+
+```
+Task(
+  prompt="Verify phase {phase_number} goal achievement.
+Phase directory: {phase_dir}
+Phase goal: {goal from ROADMAP.md}
+Check must_haves against actual codebase. Create VERIFICATION.md.",
+  subagent_type="pbr-verifier",
+  model="{verifier_model}"
+)
+```
+
+Read status:
+```bash
+grep "^status:" "$PHASE_DIR"/*-VERIFICATION.md | cut -d: -f2 | tr -d ' '
+```
+
+| Status | Action |
+|--------|--------|
+| `passed` | → update_roadmap |
+| `human_needed` | Present items for human testing, get approval or feedback |
+| `gaps_found` | Present gap summary, offer `/pbr:plan-phase {phase} --gaps` |
+
+**If human_needed:**
+```
+## ✓ Phase {X}: {Name} — Human Verification Required
+
+All automated checks passed. {N} items need human testing:
+
+{From VERIFICATION.md human_verification section}
+
+"approved" → continue | Report issues → gap closure
+```
+
+**If gaps_found:**
+```
+## ⚠ Phase {X}: {Name} — Gaps Found
+
+**Score:** {N}/{M} must-haves verified
+**Report:** {phase_dir}/{phase}-VERIFICATION.md
+
+### What's Missing
+{Gap summaries from VERIFICATION.md}
+
+---
+## ▶ Next Up
+
+`/pbr:plan-phase {X} --gaps`
+
+<sub>`/clear` first → fresh context window</sub>
+
+Also: `cat {phase_dir}/{phase}-VERIFICATION.md` — full report
+Also: `/pbr:verify-work {X}` — manual testing first
+```
+
+Gap closure cycle: `/pbr:plan-phase {X} --gaps` reads VERIFICATION.md → creates gap plans with `gap_closure: true` → user runs `/pbr:execute-phase {X} --gaps-only` → verifier re-runs.
+</step>
+
+<step name="update_roadmap">
+Mark phase complete in ROADMAP.md and advance STATE.md using `phase complete`:
+
+```bash
+TRANSITION=$(node ~/.claude/plan-build-run/scripts/pbr-tools.cjs phase complete "${PHASE_NUMBER}")
+```
+
+This CLI command handles:
+- Marking the phase checkbox as `[x]` complete with today's date
+- Updating plan count to final (e.g., "3/3 plans complete")
+- Updating the Progress table (Status → Complete, adding date)
+- Advancing STATE.md to next phase
+- Detecting if this is the last phase in the milestone
+
+Extract from result: `completed_phase`, `plans_executed`, `next_phase`, `next_phase_name`, `is_last_phase`.
+
+Then commit all phase artifacts:
+
+```bash
+node ~/.claude/plan-build-run/scripts/pbr-tools.cjs commit "docs(phase-{X}): complete phase execution" --files .planning/ROADMAP.md .planning/STATE.md .planning/phases/{phase_dir}/*-VERIFICATION.md .planning/REQUIREMENTS.md
+```
+</step>
+
+<step name="offer_next">
+
+Route to next action based on phase complete result.
+
+**Use `is_last_phase`, `next_phase`, and `next_phase_name` from the `phase complete` result.**
+
+---
+
+**If `is_last_phase` is false (more phases remain):**
+
+Check if `*-CONTEXT.md` exists in the next phase's directory:
+
+```bash
+ls .planning/phases/${next_phase_dir}/*-CONTEXT.md 2>/dev/null
+```
+
+**If CONTEXT.md does NOT exist:**
+
+```
+## ✓ Phase {X}: {Name} — Execution Complete
+
+---
+
+## ▶ Next Up
+
+**Phase {next_phase}: {next_phase_name}** — {Goal from ROADMAP.md}
+
+`/pbr:discuss-phase {next_phase}` — gather context and clarify approach
+
+<sub>`/clear` first → fresh context window</sub>
+
+---
+
+**Also available:**
+- `/pbr:plan-phase {next_phase}` — skip discussion, plan directly
+- `/pbr:verify-work {X}` — user acceptance test before continuing
+- `/pbr:transition` — full transition with PROJECT.md evolution
+
+---
+```
+
+**If CONTEXT.md exists:**
+
+```
+## ✓ Phase {X}: {Name} — Execution Complete
+
+---
+
+## ▶ Next Up
+
+**Phase {next_phase}: {next_phase_name}** — {Goal from ROADMAP.md}
+<sub>✓ Context gathered, ready to plan</sub>
+
+`/pbr:plan-phase {next_phase}`
+
+<sub>`/clear` first → fresh context window</sub>
+
+---
+
+**Also available:**
+- `/pbr:discuss-phase {next_phase}` — update existing context
+- `/pbr:verify-work {X}` — user acceptance test before continuing
+- `/pbr:transition` — full transition with PROJECT.md evolution
+
+---
+```
+
+---
+
+**If `is_last_phase` is true (milestone complete):**
+
+```
+## ✓ Phase {X}: {Name} — Execution Complete
+
+🎉 Milestone {version} is 100% complete — all {N} phases finished!
+
+---
+
+## ▶ Next Up
+
+**Complete Milestone** — archive and prepare for next
+
+`/pbr:complete-milestone`
+
+<sub>`/clear` first → fresh context window</sub>
+
+---
+
+**Also available:**
+- `/pbr:verify-work` — user acceptance test before completing milestone
+
+---
+```
+</step>
+
+</process>
+
+<context_efficiency>
+Orchestrator: ~10-15% context. Subagents: fresh 200k each. No polling (Task blocks). No context bleed.
+</context_efficiency>
+
+<failure_handling>
+- **classifyHandoffIfNeeded false failure:** Agent reports "failed" but error is `classifyHandoffIfNeeded is not defined` → Claude Code bug, not PBR. Spot-check (SUMMARY exists, commits present) → if pass, treat as success
+- **Agent fails mid-plan:** Missing SUMMARY.md → report, ask user how to proceed
+- **Dependency chain breaks:** Wave 1 fails → Wave 2 dependents likely fail → user chooses attempt or skip
+- **All agents in wave fail:** Systemic issue → stop, report for investigation
+- **Checkpoint unresolvable:** "Skip this plan?" or "Abort phase execution?" → record partial progress in STATE.md
+</failure_handling>
+
+<resumption>
+Re-run `/pbr:execute-phase {phase}` → discover_plans finds completed SUMMARYs → skips them → resumes from first incomplete plan → continues wave execution.
+
+STATE.md tracks: last completed plan, current wave, pending checkpoints.
+</resumption>