@pareto4/pp-core 1.5.0

package/pp-core/workflows/new-milestone.md

@@ -0,0 +1,643 @@
+<purpose>
+
+Start a new milestone cycle for an existing project. Loads project context, gathers milestone goals (from MILESTONE-CONTEXT.md or conversation), updates PROJECT.md and STATE.md, optionally runs parallel research, defines scoped requirements with REQ-IDs, spawns the roadmapper to create phased execution plan, and commits all artifacts. Brownfield equivalent of new-project.
+
+</purpose>
+
+<required_reading>
+
+Read all files referenced by the invoking prompt's execution_context before starting.
+
+</required_reading>
+
+<available_agent_types>
+Valid GSD subagent types (use exact names — do not fall back to 'general-purpose'):
+- pp-project-researcher — Researches project-level technical decisions
+- pp-research-synthesizer — Synthesizes findings from parallel research agents
+- pp-roadmapper — Creates phased execution roadmaps
+</available_agent_types>
+
+<process>
+
+## 1. Load Context
+
+Parse `$ARGUMENTS` before doing anything else:
+- `--reset-phase-numbers` flag → opt into restarting roadmap phase numbering at `1`
+- remaining text → use as milestone name if present
+
+If the flag is absent, keep the current behavior of continuing phase numbering from the previous milestone.
+
+- Read PROJECT.md (existing project, validated requirements, decisions)
+- Read MILESTONES.md (what shipped previously)
+- Read STATE.md (pending todos, blockers)
+- Check for MILESTONE-CONTEXT.md (from /pp-discuss-milestone)
+
+## 2. Gather Milestone Goals
+
+**If MILESTONE-CONTEXT.md exists:**
+- Use features and scope from discuss-milestone
+- Present summary for confirmation
+
+**If no context file:**
+- Present what shipped in last milestone
+
+**Text mode (`workflow.text_mode: true` in config or `--text` flag):** Set `TEXT_MODE=true` if `--text` is present in `$ARGUMENTS` OR `text_mode` from init JSON is `true`. When TEXT_MODE is active, replace every `AskUserQuestion` call with a plain-text numbered list and ask the user to type their choice number. This is required for non-Claude runtimes (OpenAI Codex, Gemini CLI, etc.) where `AskUserQuestion` is not available.
+- Ask inline (freeform, NOT AskUserQuestion): "What do you want to build next?"
+- Wait for their response, then use AskUserQuestion to probe specifics
+- If user selects "Other" at any point to provide freeform input, ask follow-up as plain text — not another AskUserQuestion
+
+## 2.5. Scan Planted Seeds
+
+Check `.planning/seeds/` for seed files that match the milestone goals gathered in step 2.
+
+```bash
+ls .planning/seeds/SEED-*.md 2>/dev/null
+```
+
+**If no seed files exist:** Skip this step silently — do not print any message or prompt.
+
+**If seed files exist:** Read each `SEED-*.md` file and extract from its frontmatter and body:
+- **Idea** — the seed title (heading after frontmatter, e.g. `# SEED-001: <idea>`)
+- **Trigger conditions** — the `trigger_when` frontmatter field and the "When to Surface" section's bullet list
+- **Planted during** — the `planted_during` frontmatter field (for context)
+
+Compare each seed's trigger conditions against the milestone goals from step 2. A seed matches when its trigger conditions are relevant to any of the milestone's target features or goals.
+
+**If no seeds match:** Skip silently — do not prompt the user.
+
+**If matching seeds found:**
+
+**`--auto` mode:** Auto-select ALL matching seeds. Log: `[auto] Selected N matching seed(s): [list seed names]`
+
+**Text mode (`TEXT_MODE=true`):** Present matching seeds as a plain-text numbered list:
+```
+Seeds that match your milestone goals:
+1. SEED-001: <idea> (trigger: <trigger_when>)
+2. SEED-003: <idea> (trigger: <trigger_when>)
+
+Enter numbers to include (comma-separated), or "none" to skip:
+```
+
+**Normal mode:** Present via AskUserQuestion:
+```
+AskUserQuestion(
+  header: "Seeds",
+  question: "These planted seeds match your milestone goals. Include any in this milestone's scope?",
+  multiSelect: true,
+  options: [
+    { label: "SEED-001: <idea>", description: "Trigger: <trigger_when> | Planted during: <planted_during>" },
+    ...
+  ]
+)
+```
+
+**After selection:**
+- Selected seeds become additional context for requirement definition in step 9. Store them in an accumulator (e.g. `$SELECTED_SEEDS`) so step 9 can reference the ideas and their "Why This Matters" sections when defining requirements.
+- Unselected seeds remain untouched in `.planning/seeds/` — never delete or modify seed files during this workflow.
+
+## 3. Determine Milestone Version
+
+- Parse last version from MILESTONES.md
+- Suggest next version (v1.0 → v1.1, or v2.0 for major)
+- Confirm with user
+
+## 3.5. Verify Milestone Understanding
+
+Before writing any files, present a summary of what was gathered and ask for confirmation.
+
+```
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+ GSD ► MILESTONE SUMMARY
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+**Milestone v[X.Y]: [Name]**
+
+**Goal:** [One sentence]
+
+**Target features:**
+- [Feature 1]
+- [Feature 2]
+- [Feature 3]
+
+**Key context:** [Any important constraints, decisions, or notes from questioning]
+```
+
+AskUserQuestion:
+- header: "Confirm?"
+- question: "Does this capture what you want to build in this milestone?"
+- options:
+  - "Looks good" — Proceed to write PROJECT.md
+  - "Adjust" — Let me correct or add details
+
+**If "Adjust":** Ask what needs changing (plain text, NOT AskUserQuestion). Incorporate changes, re-present the summary. Loop until "Looks good" is selected.
+
+**If "Looks good":** Proceed to Step 4.
+
+## 4. Update PROJECT.md
+
+Add/update:
+
+```markdown
+## Current Milestone: v[X.Y] [Name]
+
+**Goal:** [One sentence describing milestone focus]
+
+**Target features:**
+- [Feature 1]
+- [Feature 2]
+- [Feature 3]
+```
+
+Update Active requirements section and "Last updated" footer.
+
+Ensure the `## Evolution` section exists in PROJECT.md. If missing (projects created before this feature), add it before the footer:
+
+```markdown
+## Evolution
+
+This document evolves at phase transitions and milestone boundaries.
+
+**After each phase transition** (via `/pp-transition`):
+1. Requirements invalidated? → Move to Out of Scope with reason
+2. Requirements validated? → Move to Validated with phase reference
+3. New requirements emerged? → Add to Active
+4. Decisions to log? → Add to Key Decisions
+5. "What This Is" still accurate? → Update if drifted
+
+**After each milestone** (via `/pp:complete-milestone`):
+1. Full review of all sections
+2. Core Value check — still the right priority?
+3. Audit Out of Scope — reasons still valid?
+4. Update Context with current state
+```
+
+## 5. Update STATE.md
+
+Reset STATE.md frontmatter AND body atomically via the SDK. This writes the new
+milestone version/name into the YAML frontmatter, resets `status` to
+`planning`, zeroes `progress.*` counters, and rewrites the `## Current Position`
+section to the new-milestone template. Accumulated Context (decisions,
+blockers, todos) is preserved across the switch — symmetric with
+`milestone.complete`.
+
+```bash
+_PP_SHIM_NAME="pp-tools.cjs"; _PP_RUNTIME_ROOT="${RUNTIME_DIR:-$(git rev-parse --show-toplevel 2>/dev/null || pwd)}"; PP_TOOLS="${_PP_RUNTIME_ROOT}/pp-core/bin/${_PP_SHIM_NAME}"; if [ -f "$PP_TOOLS" ]; then pp_run() { node "$PP_TOOLS" "$@"; }; elif [ -f "${_PP_RUNTIME_ROOT}/.claude/pp-core/bin/${_PP_SHIM_NAME}" ]; then PP_TOOLS="${_PP_RUNTIME_ROOT}/.claude/pp-core/bin/${_PP_SHIM_NAME}"; pp_run() { node "$PP_TOOLS" "$@"; }; elif [ -f "${_PP_RUNTIME_ROOT}/.codex/pp-core/bin/${_PP_SHIM_NAME}" ]; then PP_TOOLS="${_PP_RUNTIME_ROOT}/.codex/pp-core/bin/${_PP_SHIM_NAME}"; pp_run() { node "$PP_TOOLS" "$@"; }; elif command -v pp-tools >/dev/null 2>&1; then PP_TOOLS="$(command -v pp-tools)"; pp_run() { "$PP_TOOLS" "$@"; }; elif [ -f "$HOME/.claude/pp-core/bin/${_PP_SHIM_NAME}" ]; then PP_TOOLS="$HOME/.claude/pp-core/bin/${_PP_SHIM_NAME}"; pp_run() { node "$PP_TOOLS" "$@"; }; elif [ -f "${HERMES_HOME:-$HOME/.hermes}/pp-core/bin/${_PP_SHIM_NAME}" ]; then PP_TOOLS="${HERMES_HOME:-$HOME/.hermes}/pp-core/bin/${_PP_SHIM_NAME}"; pp_run() { node "$PP_TOOLS" "$@"; }; elif [ -f "${CURSOR_CONFIG_DIR:-$HOME/.cursor}/pp-core/bin/${_PP_SHIM_NAME}" ]; then PP_TOOLS="${CURSOR_CONFIG_DIR:-$HOME/.cursor}/pp-core/bin/${_PP_SHIM_NAME}"; pp_run() { node "$PP_TOOLS" "$@"; }; elif [ -f "${CODEX_HOME:-$HOME/.codex}/pp-core/bin/${_PP_SHIM_NAME}" ]; then PP_TOOLS="${CODEX_HOME:-$HOME/.codex}/pp-core/bin/${_PP_SHIM_NAME}"; pp_run() { node "$PP_TOOLS" "$@"; }; elif [ -f "${GEMINI_CONFIG_DIR:-$HOME/.gemini}/pp-core/bin/${_PP_SHIM_NAME}" ]; then PP_TOOLS="${GEMINI_CONFIG_DIR:-$HOME/.gemini}/pp-core/bin/${_PP_SHIM_NAME}"; pp_run() { node "$PP_TOOLS" "$@"; }; elif [ -f "${COPILOT_CONFIG_DIR:-$HOME/.copilot}/pp-core/bin/${_PP_SHIM_NAME}" ]; then PP_TOOLS="${COPILOT_CONFIG_DIR:-$HOME/.copilot}/pp-core/bin/${_PP_SHIM_NAME}"; pp_run() { node "$PP_TOOLS" "$@"; }; elif [ -f "${WINDSURF_CONFIG_DIR:-$HOME/.codeium/windsurf}/pp-core/bin/${_PP_SHIM_NAME}" ]; then PP_TOOLS="${WINDSURF_CONFIG_DIR:-$HOME/.codeium/windsurf}/pp-core/bin/${_PP_SHIM_NAME}"; pp_run() { node "$PP_TOOLS" "$@"; }; elif [ -f "${AUGMENT_CONFIG_DIR:-$HOME/.augment}/pp-core/bin/${_PP_SHIM_NAME}" ]; then PP_TOOLS="${AUGMENT_CONFIG_DIR:-$HOME/.augment}/pp-core/bin/${_PP_SHIM_NAME}"; pp_run() { node "$PP_TOOLS" "$@"; }; elif [ -f "${TRAE_CONFIG_DIR:-$HOME/.trae}/pp-core/bin/${_PP_SHIM_NAME}" ]; then PP_TOOLS="${TRAE_CONFIG_DIR:-$HOME/.trae}/pp-core/bin/${_PP_SHIM_NAME}"; pp_run() { node "$PP_TOOLS" "$@"; }; elif [ -f "${QWEN_CONFIG_DIR:-$HOME/.qwen}/pp-core/bin/${_PP_SHIM_NAME}" ]; then PP_TOOLS="${QWEN_CONFIG_DIR:-$HOME/.qwen}/pp-core/bin/${_PP_SHIM_NAME}"; pp_run() { node "$PP_TOOLS" "$@"; }; elif [ -f "${CODEBUDDY_CONFIG_DIR:-$HOME/.codebuddy}/pp-core/bin/${_PP_SHIM_NAME}" ]; then PP_TOOLS="${CODEBUDDY_CONFIG_DIR:-$HOME/.codebuddy}/pp-core/bin/${_PP_SHIM_NAME}"; pp_run() { node "$PP_TOOLS" "$@"; }; elif [ -f "${CLINE_CONFIG_DIR:-$HOME/.cline}/pp-core/bin/${_PP_SHIM_NAME}" ]; then PP_TOOLS="${CLINE_CONFIG_DIR:-$HOME/.cline}/pp-core/bin/${_PP_SHIM_NAME}"; pp_run() { node "$PP_TOOLS" "$@"; }; elif [ -f "${GROK_AGENTS_HOME:-$HOME/.agents}/pp-core/bin/${_PP_SHIM_NAME}" ]; then PP_TOOLS="${GROK_AGENTS_HOME:-$HOME/.agents}/pp-core/bin/${_PP_SHIM_NAME}"; pp_run() { node "$PP_TOOLS" "$@"; }; elif [ -f "${ANTIGRAVITY_CONFIG_DIR:-$HOME/.gemini/antigravity}/pp-core/bin/${_PP_SHIM_NAME}" ]; then PP_TOOLS="${ANTIGRAVITY_CONFIG_DIR:-$HOME/.gemini/antigravity}/pp-core/bin/${_PP_SHIM_NAME}"; pp_run() { node "$PP_TOOLS" "$@"; }; elif [ -f "${OPENCODE_CONFIG_DIR:-${XDG_CONFIG_HOME:-$HOME/.config}/opencode}/pp-core/bin/${_PP_SHIM_NAME}" ]; then PP_TOOLS="${OPENCODE_CONFIG_DIR:-${XDG_CONFIG_HOME:-$HOME/.config}/opencode}/pp-core/bin/${_PP_SHIM_NAME}"; pp_run() { node "$PP_TOOLS" "$@"; }; elif [ -f "${KILO_CONFIG_DIR:-${XDG_CONFIG_HOME:-$HOME/.config}/kilo}/pp-core/bin/${_PP_SHIM_NAME}" ]; then PP_TOOLS="${KILO_CONFIG_DIR:-${XDG_CONFIG_HOME:-$HOME/.config}/kilo}/pp-core/bin/${_PP_SHIM_NAME}"; pp_run() { node "$PP_TOOLS" "$@"; }; else echo "ERROR: pp-tools.cjs not found at $PP_TOOLS and pp-tools is not on PATH. Run: npx -y @pareto4/pp-core@latest --claude --local" >&2; exit 1; fi; if [ -n "${CLAUDE_ENV_FILE:-}" ] && [ -n "${PP_TOOLS:-}" ]; then printf "export PATH='%s':\"\$PATH\"\n" "${PP_TOOLS%/*}" >> "$CLAUDE_ENV_FILE" 2>/dev/null || true; fi
+pp_run query state.milestone-switch --milestone "v[X.Y]" --name "[Name]"
+```
+
+The resulting Current Position section looks like:
+
+```markdown
+## Current Position
+
+Phase: Not started (defining requirements)
+Plan: —
+Status: Defining requirements
+Last activity: [today] — Milestone v[X.Y] started
+```
+
+Bug #2630: a prior version of this workflow rewrote the Current Position body
+manually but left the frontmatter pointing at the previous milestone, so every
+downstream reader (`state.json`, `getMilestoneInfo`, progress bars) reported the
+stale milestone until the first phase advance forced a resync. Always use the
+SDK handler above — do not hand-edit STATE.md here.
+
+## 6. Cleanup and Commit
+
+Delete MILESTONE-CONTEXT.md if exists (consumed).
+
+Clear leftover phase directories from the previous milestone:
+
+```bash
+pp_run query phases.clear --confirm
+```
+
+```bash
+pp_run query commit "docs: start milestone v[X.Y] [Name]" --files .planning/PROJECT.md .planning/STATE.md
+```
+
+## 7. Load Context and Resolve Models
+
+```bash
+INIT=$(pp_run query init.new-milestone)
+if [[ "$INIT" == @file:* ]]; then INIT=$(cat "${INIT#@file:}"); fi
+AGENT_SKILLS_RESEARCHER=$(pp_run query agent-skills pp-project-researcher)
+AGENT_SKILLS_SYNTHESIZER=$(pp_run query agent-skills pp-research-synthesizer)
+AGENT_SKILLS_ROADMAPPER=$(pp_run query agent-skills pp-roadmapper)
+```
+
+Extract from init JSON: `researcher_model`, `synthesizer_model`, `roadmapper_model`, `commit_docs`, `research_enabled`, `current_milestone`, `project_exists`, `roadmap_exists`, `latest_completed_milestone`, `phase_dir_count`, `phase_archive_path`, `agents_installed`, `missing_agents`.
+
+**If `agents_installed` is false:** Display a warning before proceeding:
+```
+⚠ GSD agents not installed. The following agents are missing from your agents directory:
+  {missing_agents joined with newline}
+
+Subagent spawns (pp-project-researcher, pp-research-synthesizer, pp-roadmapper) will fail
+with "agent type not found". Run the installer with --global to make agents available:
+
+  npx @opengsd/pp-core@latest --global
+
+Proceeding without research subagents — roadmap will be generated inline.
+```
+Skip the parallel research spawn step and generate the roadmap inline.
+
+## 7.5 Reset-phase safety (only when `--reset-phase-numbers`)
+
+If `--reset-phase-numbers` is active:
+
+1. Set starting phase number to `1` for the upcoming roadmap.
+2. If `phase_dir_count > 0`, archive the old phase directories before roadmapping so new `01-*` / `02-*` directories cannot collide with stale milestone directories.
+
+If `phase_dir_count > 0` and `phase_archive_path` is available:
+
+```bash
+mkdir -p "${phase_archive_path}"
+find .planning/phases -mindepth 1 -maxdepth 1 -type d -exec mv {} "${phase_archive_path}/" \;
+```
+
+Then verify `.planning/phases/` no longer contains old milestone directories before continuing.
+
+If `phase_dir_count > 0` but `phase_archive_path` is missing:
+- Stop and explain that reset numbering is unsafe without a completed milestone archive target.
+- Tell the user to complete/archive the previous milestone first, then rerun `/pp:new-milestone --reset-phase-numbers ${GSD_WS}`.
+
+## 8. Research Decision
+
+Check `research_enabled` from init JSON (loaded from config).
+
+**If `research_enabled` is `true`:**
+
+AskUserQuestion: "Research the domain ecosystem for new features before defining requirements?"
+- "Research first (Recommended)" — Discover patterns, features, architecture for NEW capabilities
+- "Skip research for this milestone" — Go straight to requirements (does not change your default)
+
+**If `research_enabled` is `false`:**
+
+AskUserQuestion: "Research the domain ecosystem for new features before defining requirements?"
+- "Skip research (current default)" — Go straight to requirements
+- "Research first" — Discover patterns, features, architecture for NEW capabilities
+
+**IMPORTANT:** Do NOT persist this choice to config.json. The `workflow.research` setting is a persistent user preference that controls plan-phase behavior across the project. Changing it here would silently alter future `/pp:plan-phase` behavior. To change the default, use `/pp:settings`.
+
+**If user chose "Research first":**
+
+```
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+ GSD ► RESEARCHING
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+◆ Spawning 4 researchers in parallel... (each runs in a subagent — no output until they return, ~1–5 min; expected, not a freeze)
+  → Stack, Features, Architecture, Pitfalls
+```
+
+```bash
+mkdir -p .planning/research
+```
+
+Spawn 4 parallel pp-project-researcher agents. Each uses this template with dimension-specific fields:
+
+**Common structure for all 4 researchers:**
+```text
+Agent(prompt="
+<research_type>Project Research — {DIMENSION} for [new features].</research_type>
+
+<milestone_context>
+SUBSEQUENT MILESTONE — Adding [target features] to existing app.
+{EXISTING_CONTEXT}
+Focus ONLY on what's needed for the NEW features.
+</milestone_context>
+
+<question>{QUESTION}</question>
+
+<files_to_read>
+- .planning/PROJECT.md (Project context)
+</files_to_read>
+
+${AGENT_SKILLS_RESEARCHER}
+
+<downstream_consumer>{CONSUMER}</downstream_consumer>
+
+<quality_gate>{GATES}</quality_gate>
+
+<output>
+Write to: .planning/research/{FILE}
+Use template: ~/.claude/pp-core/templates/research-project/{FILE}
+</output>
+", subagent_type="pp-project-researcher", model="{researcher_model}", description="{DIMENSION} research")
+```
+
+**Dimension-specific fields:**
+
+| Field | Stack | Features | Architecture | Pitfalls |
+|-------|-------|----------|-------------|----------|
+| EXISTING_CONTEXT | Existing validated capabilities (DO NOT re-research): [from PROJECT.md] | Existing features (already built): [from PROJECT.md] | Existing architecture: [from PROJECT.md or codebase map] | Focus on common mistakes when ADDING these features to existing system |
+| QUESTION | What stack additions/changes are needed for [new features]? | How do [target features] typically work? Expected behavior? | How do [target features] integrate with existing architecture? | Common mistakes when adding [target features] to [domain]? |
+| CONSUMER | Specific libraries with versions for NEW capabilities, integration points, what NOT to add | Table stakes vs differentiators vs anti-features, complexity noted, dependencies on existing | Integration points, new components, data flow changes, suggested build order | Warning signs, prevention strategy, which phase should address it |
+| GATES | Versions current (verify with Context7), rationale explains WHY, integration considered | Categories clear, complexity noted, dependencies identified | Integration points identified, new vs modified explicit, build order considers deps | Pitfalls specific to adding these features, integration pitfalls covered, prevention actionable |
+| FILE | STACK.md | FEATURES.md | ARCHITECTURE.md | PITFALLS.md |
+
+> **ORCHESTRATOR RULE — CODEX RUNTIME**: After calling all 4 researcher Agent() calls above, do NOT read research files or synthesize content independently while the subagents are active. Wait for all 4 researchers to complete before spawning the synthesizer. This prevents duplicate work and wasted context.
+
+After all 4 complete, spawn synthesizer:
+
+```text
+Agent(prompt="
+Synthesize research outputs into SUMMARY.md.
+
+<files_to_read>
+- .planning/research/STACK.md
+- .planning/research/FEATURES.md
+- .planning/research/ARCHITECTURE.md
+- .planning/research/PITFALLS.md
+</files_to_read>
+
+${AGENT_SKILLS_SYNTHESIZER}
+
+Write to: .planning/research/SUMMARY.md
+Use template: ~/.claude/pp-core/templates/research-project/SUMMARY.md
+Commit after writing.
+", subagent_type="pp-research-synthesizer", model="{synthesizer_model}", description="Synthesize research")
+```
+
+> **ORCHESTRATOR RULE — CODEX RUNTIME**: After calling Agent() above, stop working on this task immediately. Do not read more files, edit code, or run tests related to this task while the subagent is active. Wait for the subagent to return its result. This prevents duplicate work, conflicting edits, and wasted context. Only resume when the subagent result is available.
+
+**Synthesizer output self-heal (#222) — verify SUMMARY.md materialized:** The synthesizer's canonical output is `.planning/research/SUMMARY.md` on disk; its brief structured return (`## SYNTHESIS COMPLETE` plus a few `###` confirmation lines) is NOT the file content. A known LLM false-refusal (issue #222) sometimes makes the agent return the full SUMMARY.md document inline — fabricating a write restriction (e.g. "the runtime is blocking file writes") — instead of writing the file. Prompt hardening alone does not fully eliminate it, so the orchestrator MUST absorb the failure deterministically before spawning `pp-roadmapper`:
+
+1. Verify `.planning/research/SUMMARY.md` exists AND is substantive — non-empty, and free of any leftover `<!-- gsd:write-continue -->` continuation sentinel (which marks a truncated/incomplete write). You may validate with `pp-tools verify-summary .planning/research/SUMMARY.md` — it exits 0 regardless, so check its JSON `passed` field (`"passed": false` means missing or invalid), not the process exit code. If it passes, continue normally.
+2. If it is MISSING or invalid AND the synthesizer's return message contains the FULL SUMMARY.md document — recognizable by the template's top-level markers `# Project Research Summary`, `## Key Findings`, `## Implications for Roadmap`, and `## Sources`, not merely the brief `## SYNTHESIS COMPLETE` confirmation — the false-refusal fired: write that returned document to `.planning/research/SUMMARY.md` with the Write tool, then commit ALL research artifacts the synthesizer owns (it commits on behalf of the four researchers) with `pp-tools query commit "docs: complete project research" --files .planning/research/` unless they are already committed. Log `⚠ #222 self-heal: synthesizer returned SUMMARY.md inline without writing it; orchestrator persisted the file.`
+3. If it is MISSING or invalid AND the return is only a brief confirmation (no full SUMMARY document to recover), the synthesizer genuinely failed — surface the error and stop; do NOT spawn `pp-roadmapper` against a missing or incomplete SUMMARY.md.
+
+This guarantees `pp-roadmapper` (which lists SUMMARY.md as required reading) never runs against a missing or truncated SUMMARY.md.
+
+Display key findings from SUMMARY.md:
+```
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+ GSD ► RESEARCH COMPLETE ✓
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+**Stack additions:** [from SUMMARY.md]
+**Feature table stakes:** [from SUMMARY.md]
+**Watch Out For:** [from SUMMARY.md]
+```
+
+**If "Skip research":** Continue to Step 9.
+
+## 9. Define Requirements
+
+```
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+ GSD ► DEFINING REQUIREMENTS
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+```
+
+Read PROJECT.md: core value, current milestone goals, validated requirements (what exists).
+
+**If `$SELECTED_SEEDS` is non-empty (from step 2.5):** Include selected seed ideas and their "Why This Matters" sections as additional input when defining requirements. Seeds provide user-validated feature ideas that should be incorporated into the requirement categories alongside research findings or conversation-gathered features.
+
+**If research exists:** Read FEATURES.md, extract feature categories.
+
+Present features by category:
+```
+## [Category 1]
+**Table stakes:** Feature A, Feature B
+**Differentiators:** Feature C, Feature D
+**Research notes:** [any relevant notes]
+```
+
+**If no research:** Gather requirements through conversation. Ask: "What are the main things users need to do with [new features]?" Clarify, probe for related capabilities, group into categories.
+
+**Scope each category** via AskUserQuestion (multiSelect: true, header max 12 chars):
+- "[Feature 1]" — [brief description]
+- "[Feature 2]" — [brief description]
+- "None for this milestone" — Defer entire category
+
+Track: Selected → this milestone. Unselected table stakes → future. Unselected differentiators → out of scope.
+
+**Identify gaps** via AskUserQuestion:
+- "No, research covered it" — Proceed
+- "Yes, let me add some" — Capture additions
+
+**Generate REQUIREMENTS.md:**
+- v1 Requirements grouped by category (checkboxes, REQ-IDs)
+- Future Requirements (deferred)
+- Out of Scope (explicit exclusions with reasoning)
+- Traceability section (empty, filled by roadmap)
+
+**REQ-ID format:** `[CATEGORY]-[NUMBER]` (AUTH-01, NOTIF-02). Continue numbering from existing.
+
+**Requirement quality criteria:**
+
+Good requirements are:
+- **Specific and testable:** "User can reset password via email link" (not "Handle password reset")
+- **User-centric:** "User can X" (not "System does Y")
+- **Atomic:** One capability per requirement (not "User can login and manage profile")
+- **Independent:** Minimal dependencies on other requirements
+
+Present FULL requirements list for confirmation:
+
+```
+## Milestone v[X.Y] Requirements
+
+### [Category 1]
+- [ ] **CAT1-01**: User can do X
+- [ ] **CAT1-02**: User can do Y
+
+### [Category 2]
+- [ ] **CAT2-01**: User can do Z
+
+Does this capture what you're building? (yes / adjust)
+```
+
+If "adjust": Return to scoping.
+
+**Commit requirements:**
+```bash
+pp_run query commit "docs: define milestone v[X.Y] requirements" --files .planning/REQUIREMENTS.md
+```
+
+## 10. Create Roadmap
+
+```
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+ GSD ► CREATING ROADMAP
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+◆ Spawning roadmapper... (runs in a subagent — no output until it returns, ~1–5 min; expected, not a freeze)
+```
+
+**Starting phase number:**
+- If `--reset-phase-numbers` is active, start at **Phase 1**
+- Otherwise, continue from the previous milestone's last phase number (v1.0 ended at phase 5 → v1.1 starts at phase 6)
+
+```text
+Agent(prompt="
+<planning_context>
+<files_to_read>
+- .planning/PROJECT.md
+- .planning/REQUIREMENTS.md
+- .planning/research/SUMMARY.md (if exists)
+- .planning/config.json
+- .planning/MILESTONES.md
+</files_to_read>
+
+${AGENT_SKILLS_ROADMAPPER}
+
+</planning_context>
+
+<instructions>
+Create roadmap for milestone v[X.Y]:
+1. Respect the selected numbering mode:
+   - `--reset-phase-numbers` → start at Phase 1
+   - default behavior → continue from the previous milestone's last phase number
+2. Derive phases from THIS MILESTONE's requirements only
+3. Map every requirement to exactly one phase
+4. Derive 2-5 success criteria per phase (observable user behaviors)
+5. Validate 100% coverage
+6. Write files immediately (ROADMAP.md, STATE.md, update REQUIREMENTS.md traceability)
+7. Return ROADMAP CREATED with summary
+
+Write files first, then return.
+</instructions>
+", subagent_type="pp-roadmapper", model="{roadmapper_model}", description="Create roadmap")
+```
+
+> **ORCHESTRATOR RULE — CODEX RUNTIME**: After calling Agent() above, stop working on this task immediately. Do not read more files, edit code, or run tests related to this task while the subagent is active. Wait for the subagent to return its result. This prevents duplicate work, conflicting edits, and wasted context. Only resume when the subagent result is available.
+
+**Handle return:**
+
+**If `## ROADMAP BLOCKED`:** Present blocker, work with user, re-spawn.
+
+**If `## ROADMAP CREATED`:** Read ROADMAP.md, present inline:
+
+```
+## Proposed Roadmap
+
+**[N] phases** | **[X] requirements mapped** | All covered ✓
+
+| # | Phase | Goal | Requirements | Success Criteria |
+|---|-------|------|--------------|------------------|
+| [N] | [Name] | [Goal] | [REQ-IDs] | [count] |
+
+### Phase Details
+
+**Phase [N]: [Name]**
+Goal: [goal]
+Requirements: [REQ-IDs]
+Success criteria:
+1. [criterion]
+2. [criterion]
+```
+
+**Ask for approval** via AskUserQuestion:
+- "Approve" — Commit and continue
+- "Adjust phases" — Tell me what to change
+- "Review full file" — Show raw ROADMAP.md
+
+**If "Adjust":** Get notes, re-spawn roadmapper with revision context, loop until approved.
+**If "Review":** Display raw ROADMAP.md, re-ask.
+
+**Commit roadmap** (after approval):
+```bash
+pp_run query commit "docs: create milestone v[X.Y] roadmap ([N] phases)" --files .planning/ROADMAP.md .planning/STATE.md .planning/REQUIREMENTS.md
+```
+
+## 10.5. Link Pending Todos to Roadmap Phases
+
+After roadmap approval, scan pending todos against the newly approved phases. For each todo whose scope matches a phase, tag it with `resolves_phase: N` in its YAML frontmatter.
+
+**Check for pending todos:**
+```bash
+PENDING_TODOS=$(ls .planning/todos/pending/*.md 2>/dev/null | head -50)
+```
+
+**If no pending todos exist:** Skip this step silently.
+
+**If pending todos exist:**
+
+Read the approved ROADMAP.md and extract the phase list: phase number, phase name, goal, and requirement IDs.
+
+For each pending todo, compare:
+- The todo's `title` and `area` frontmatter fields
+- The todo body (Problem and Solution sections)
+
+Against each phase's:
+- Phase goal
+- Requirement IDs and descriptions
+
+**Match criteria (best-effort — do not over-match):** A todo is considered resolved by a phase if the phase's goal or requirements directly describe implementing the same feature, area, or capability as the todo. Narrow, specific todos with concrete scopes are the best candidates. Vague or cross-cutting todos should be left unlinked.
+
+**For each matched todo**, add `resolves_phase: [N]` to the YAML frontmatter block (after the existing fields):
+```yaml
+---
+created: [existing]
+title: [existing]
+area: [existing]
+resolves_phase: [N]
+files: [existing]
+---
+```
+
+**Only modify todos that have a clear, confident match.** Leave unmatched todos unmodified.
+
+**If any todos were linked:**
+```bash
+pp_run query commit "docs: tag [count] pending todos with resolves_phase after milestone v[X.Y] roadmap" --files .planning/todos/pending/*.md
+```
+
+Print a summary:
+```
+◆ Linked [N] pending todos to roadmap phases:
+  → [todo title] → Phase [N]: [Phase Name]
+  (Leave [M] unmatched todos in pending/)
+```
+
+## 11. Done
+
+```
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+ GSD ► MILESTONE INITIALIZED ✓
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+**Milestone v[X.Y]: [Name]**
+
+| Artifact       | Location                    |
+|----------------|-----------------------------|
+| Project        | `.planning/PROJECT.md`      |
+| Research       | `.planning/research/`       |
+| Requirements   | `.planning/REQUIREMENTS.md` |
+| Roadmap        | `.planning/ROADMAP.md`      |
+
+**[N] phases** | **[X] requirements** | Ready to build ✓
+
+## ▶ Next Up — [${PROJECT_CODE}] ${PROJECT_TITLE}
+
+**Phase [N]: [Phase Name]** — [Goal]
+
+`/clear` then:
+
+`/pp:discuss-phase [N] ${GSD_WS}` — gather context and clarify approach
+
+Also: `/pp:plan-phase [N] ${GSD_WS}` — skip discussion, plan directly
+```
+
+</process>
+
+<success_criteria>
+- [ ] PROJECT.md updated with Current Milestone section
+- [ ] STATE.md reset for new milestone
+- [ ] MILESTONE-CONTEXT.md consumed and deleted (if existed)
+- [ ] Research completed (if selected) — 4 parallel agents, milestone-aware
+- [ ] Requirements gathered and scoped per category
+- [ ] REQUIREMENTS.md created with REQ-IDs
+- [ ] pp-roadmapper spawned with phase numbering context
+- [ ] Roadmap files written immediately (not draft)
+- [ ] User feedback incorporated (if any)
+- [ ] Phase numbering mode respected (continued or reset)
+- [ ] All commits made (if planning docs committed)
+- [ ] Pending todos scanned for phase matches; matched todos tagged with `resolves_phase: N`
+- [ ] User knows next step: `/pp:discuss-phase [N] ${GSD_WS}`
+
+**Atomic commits:** Each phase commits its artifacts immediately.
+</success_criteria>
+</output>