docs: create milestone v1.2 Architect & Multi-Question (4 phases)

Phases:
- 10. multi-question-schema: Extend agent output schema to return multiple questions
- 11. architect-agent: Agent modes for concept refinement and phase breakdown
- 12. phase-task-decomposition: Agents break phases into tasks with questions
- 13. real-claude-e2e-tests: Verify flows with actual Claude CLI

.planning/ROADMAP.md

@@ -12,6 +12,7 @@ None
 
 - ✅ **v1.0 Core System** - Phases 1-6 (shipped 2026-01-30)
 - ✅ **v1.1 Test Infrastructure** - Phases 7-9 (shipped 2026-01-31)
+- 🚧 **v1.2 Architect & Multi-Question** - Phases 10-13 (in progress)
 
 ## Phases
 
@@ -140,6 +141,47 @@ Plans:
 
 </details>
 
+### 🚧 v1.2 Architect & Multi-Question (In Progress)
+
+**Milestone Goal:** Enable structured planning workflow with Architect agent and efficient multi-question Q&A
+
+#### Phase 10: Multi-Question Schema
+**Goal**: Extend agent output schema to return multiple questions; resume agent with all answers batched
+**Depends on**: Phase 9 (v1.1 complete)
+**Research**: Unlikely (extends existing schema patterns)
+**Plans**: TBD
+
+Plans:
+- [ ] 10-01: TBD (run /gsd:plan-phase 10 to break down)
+
+#### Phase 11: Architect Agent
+**Goal**: Agent modes for concept refinement (questioning) and phase breakdown (persisting to ROADMAP.md)
+**Depends on**: Phase 10
+**Research**: Unlikely (internal workflow patterns)
+**Plans**: TBD
+
+Plans:
+- [ ] 11-01: TBD
+
+#### Phase 12: Phase-Task Decomposition
+**Goal**: Agents break phases into individual tasks with ability to ask questions during breakdown
+**Depends on**: Phase 11
+**Research**: Unlikely (internal coordination patterns)
+**Plans**: TBD
+
+Plans:
+- [ ] 12-01: TBD
+
+#### Phase 13: Real Claude E2E Tests
+**Goal**: Verify multi-question and architect flows with actual Claude CLI; replace with mocks after verification
+**Depends on**: Phase 12
+**Research**: Likely (validating Claude CLI --json-schema with multi-question arrays)
+**Research topics**: Claude CLI behavior with array-typed questions, response parsing, error handling for real agent failures
+**Plans**: TBD
+
+Plans:
+- [ ] 13-01: TBD
+
 ## Progress
 
 **Execution Order:**
@@ -158,6 +200,10 @@ Phases execute in numeric order: 1 → 1.1 → 2 → 3 → 4 → 5 → 6 → 7
 | 8. E2E Scenario Tests | v1.1 | 2/2 | Complete | 2026-01-31 |
 | 8.1. Agent Output Schema | v1.1 | 2/2 | Complete | 2026-01-31 |
 | 9. Extended Scenarios | v1.1 | 2/2 | Complete | 2026-01-31 |
+| 10. Multi-Question Schema | v1.2 | 0/? | Not started | - |
+| 11. Architect Agent | v1.2 | 0/? | Not started | - |
+| 12. Phase-Task Decomposition | v1.2 | 0/? | Not started | - |
+| 13. Real Claude E2E Tests | v1.2 | 0/? | Not started | - |
 
 ---
 *Roadmap created: 2026-01-30*

.planning/STATE.md

@@ -5,15 +5,16 @@
 See: .planning/PROJECT.md (updated 2026-01-31)
 
 **Core value:** Coordinate multiple Claude Code agents without losing track or stepping on each other.
-**Current focus:** Planning next milestone
+**Current focus:** v1.2 Architect & Multi-Question
 
 ## Current Position
 
-Milestone: v1.1 complete
+Phase: 10 of 13 (Multi-Question Schema)
-Status: Ready to plan next milestone
+Plan: Not started
-Last activity: 2026-01-31 — v1.1 Test Infrastructure shipped
+Status: Ready to plan
+Last activity: 2026-01-31 — Milestone v1.2 created
 
-Progress: ██████████ 100% (v1.0 + v1.1 complete)
+Progress: ░░░░░░░░░░ 0%
 
 ## Performance Metrics
 
@@ -129,13 +130,14 @@ None yet.
   - Retrofits Phase 1 code before continuing to Phase 2
   - Establishes architectural foundation for rest of project
 - Milestone v1.1 created: Test infrastructure, 3 phases (Phase 7-9)
+- Milestone v1.2 created: Architect & Multi-Question, 4 phases (Phase 10-13)
 
 ### Blockers/Concerns
 
-None yet.
+None.
 
 ## Session Continuity
 
 Last session: 2026-01-31
-Stopped at: Completed 09-02-PLAN.md (Phase 9 complete, v1.1 milestone complete)
+Stopped at: Milestone v1.2 initialization
 Resume file: None