feat: wire Loop 1 + Loop 2 into all phase execution paths

.planning/STATE.md

@@ -12,7 +12,7 @@ See: .planning/PROJECT.md (updated 2026-03-25)
 Phase: 53 of 53 (Skill Deprecation) — COMPLETED
 Plan: 53-01 of 1 — COMPLETED
 Status: All phases complete — /nf:model-driven-fix deprecated, all consumers rewired to /nf:debug
-Last activity: 2026-03-26 - Completed quick task 361: Add automation-first bias to verify-work and execute-phase workflows
+Last activity: 2026-03-27 - Completed quick task 363: Push Loop 2 + debug_context into execute-plan.md Pattern A
 
 Progress: [██████████] 100% (Phase 50 done; Phase 51 done; Phase 52 done; Phase 53 done)
 
@@ -79,6 +79,8 @@ None yet.
 | 359 | Close gap: allow formal_artifacts create when scope-scan empty | 2026-03-26 | afdea71c | Verified | [359-close-the-gap-when-formal-scope-scan-fin](./quick/359-close-the-gap-when-formal-scope-scan-fin/) |
 | 360 | Add risk-based adaptive quorum fan-out: risk classifier, adaptive dispatch, audit logging | 2026-03-26 | 8e27fe35 | Verified | [360-add-risk-based-adaptive-quorum-fan-out-r](./quick/360-add-risk-based-adaptive-quorum-fan-out-r/) |
 | 361 | Add automation-first bias to verify-work and execute-phase workflows | 2026-03-26 | afbeac9e | Verified | [361-add-automation-first-bias-to-verify-work](./quick/361-add-automation-first-bias-to-verify-work/) |
+| 362 | Wire debug routing (Loop 1 + task classification + debug_context injection) into execute-phase.md | 2026-03-27 | 813c1d77 | Verified | [362-wire-debug-routing-into-execute-phase-md](./quick/362-wire-debug-routing-into-execute-phase-md/) |
+| 363 | Push Loop 2 + debug_context into execute-plan.md Pattern A spawn prompt | 2026-03-27 | 72bbe22d | Verified | [363-push-loop-2-and-debug-context-into-execu](./quick/363-push-loop-2-and-debug-context-into-execu/) |
 
 ### Blockers/Concerns
 

.planning/quick/362-wire-debug-routing-into-execute-phase-md/362-PLAN.md

@@ -0,0 +1,58 @@
+---
+task_id: 362
+description: "Wire debug routing (Loop 1 + task classification + autoresearch-refine + debug_context injection) into execute-phase.md"
+formal_artifacts: none
+---
+
+# Plan: Wire Debug Routing into execute-phase.md
+
+## Objective
+
+Add per-plan task classification and debug routing to `execute-phase.md` so that bug-fix plans get routed through `/nf:debug` (Loop 1 autoresearch-refine) before execution, with constraints injected into executor prompts — matching the `quick.md` Step 5.8 pattern.
+
+## Must-Haves
+
+1. Per-plan Haiku task classification (bug_fix/feature/refactor) in the execute_waves step, before spawning each executor
+2. Debug routing: bug_fix plans (confidence >= 0.7) dispatched through `/nf:debug` before executor spawn
+3. Debug context injection: `<debug_context>` block conditionally injected into executor prompt with constraints, verdict, and reproducing model
+4. Fail-open: all new logic skips silently on Haiku unavailability, debug errors, or missing modules
+5. Sync repo source → installed copy after edit
+
+## Tasks
+
+### Task 1: Add per-plan task classification to execute_waves step
+
+In `core/workflows/execute-phase.md`, inside `<step name="execute_waves">`, add a classification sub-step BEFORE spawning executor agents (before item 2 "Spawn executor agents"). For each plan in the wave:
+
+1. Read the plan's `<objective>` text
+2. Spawn Haiku subagent to classify the plan objective as bug_fix/feature/refactor (same prompt as quick.md Step 2.7 sub-step 1.5)
+3. Store `$PLAN_CLASSIFICATION` per plan
+4. Fail-open: default to `{ type: "feature", confidence: 0.0 }` if Haiku unavailable
+
+### Task 2: Add debug routing step between classification and executor spawn
+
+Add a new sub-step after classification, before executor spawn:
+
+1. **Skip if:** `$PLAN_CLASSIFICATION.type` is NOT `bug_fix`, OR confidence < 0.7
+2. **If routing:** Spawn `/nf:debug` as Task subagent with the plan objective as failure context (same pattern as quick.md Step 5.8 item 2)
+3. Parse debug output → extract `$DEBUG_CONSTRAINTS`, `$DEBUG_FORMAL_VERDICT`, `$DEBUG_REPRODUCING_MODEL`
+4. Fail-open: on error, set all debug vars to null and continue
+
+### Task 3: Inject debug_context block into executor prompt
+
+Modify the executor Task spawn (item 2 in execute_waves) to conditionally include a `<debug_context>` block after the `</formal_coverage_auto_detection>` section:
+
+```
+${DEBUG_CONSTRAINTS || DEBUG_FORMAL_VERDICT || DEBUG_REPRODUCING_MODEL ?
+`<debug_context>
+This plan was routed through /nf:debug before execution...
+</debug_context>` : ''}
+```
+
+Same template as quick.md lines 877-886.
+
+### Task 4: Sync to installed copy
+
+```bash
+cp core/workflows/execute-phase.md ~/.claude/nf/workflows/execute-phase.md
+```

.planning/quick/362-wire-debug-routing-into-execute-phase-md/362-VERIFICATION.md

@@ -0,0 +1,22 @@
+# Verification: Quick Task 362
+
+## Must-Haves
+
+| # | Requirement | Status | Evidence |
+|---|---|---|---|
+| 1 | Per-plan Haiku task classification before executor spawn | PASS | Step 1.5a at line 108 — Haiku classifies plan objective as bug_fix/feature/refactor |
+| 2 | Debug routing for bug_fix plans (confidence >= 0.7) | PASS | Step 1.5b at line 145 — spawns /nf:debug before executor |
+| 3 | debug_context block injected into executor prompt | PASS | Lines 253-262 — conditional block with constraints, verdict, reproducing model |
+| 4 | Fail-open on all new logic | PASS | Line 139 (classification fallback), line 148 (debug vars null on skip), line 185 (debug error → null + continue) |
+| 5 | Sync repo source → installed copy | PASS | `cp core/workflows/execute-phase.md ~/.claude/nf/workflows/execute-phase.md` — verified via diff |
+
+## Pattern Match with quick.md
+
+| Element | quick.md | execute-phase.md | Match |
+|---|---|---|---|
+| Classification | Step 2.7 sub-step 1.5 | Step 1.5a | Yes — same Haiku prompt, same JSON schema |
+| Debug routing | Step 5.8 | Step 1.5b | Yes — same skip condition, same /nf:debug prompt |
+| Debug context injection | Lines 877-886 | Lines 253-262 | Yes — same template |
+| Fail-open | Fallback to feature/0.0 | Fallback to feature/0.0 | Yes |
+
+## Status: Verified

.planning/quick/362-wire-debug-routing-into-execute-phase-md/scope-contract.json

@@ -0,0 +1,23 @@
+{
+  "nf/quick-362-wire-debug-routing-into-execute-phase-md": {
+    "task_id": 362,
+    "task_description": "Wire debug routing (Loop 1 + task classification + autoresearch-refine + debug_context injection) into execute-phase.md — matching the quick.md Step 5.8 pattern",
+    "approach": "Add phase-level task classification and debug routing to execute-phase.md's plan execution loop, dispatching bug-fix phases through /nf:debug before execution and injecting formal constraints into executor prompts, matching the quick.md Step 5.8 pattern.",
+    "out_of_scope": [
+      "Rewriting the /nf:debug skill itself — only phase-level routing and constraint injection are in scope",
+      "Cross-phase bug-fix dependencies — phase classification is per-plan, not per-milestone",
+      "Modifying quick.md — only execute-phase.md is in scope"
+    ],
+    "classification": {
+      "type": "feature",
+      "confidence": 0.85,
+      "routed_through_debug": false
+    },
+    "risk_level": "high",
+    "risk_reason": "Workflow file modification (execute-phase.md) — guardrail-protected",
+    "branches_affected": ["nf/quick-362-wire-debug-routing-into-execute-phase-md"],
+    "created_at": "2026-03-27T12:46:04.416Z",
+    "planner_model": "inherit",
+    "created_by": "quick-orchestrator"
+  }
+}

.planning/quick/363-push-loop-2-and-debug-context-into-execu/363-PLAN.md

@@ -0,0 +1,43 @@
+---
+task_id: 363
+description: "Push Loop 2 and debug_context into execute-plan.md Pattern A spawn prompt"
+formal_artifacts: none
+---
+
+# Plan: Push Loop 2 + debug_context into Pattern A
+
+## Objective
+
+Expand the Pattern A spawn prompt in `execute-plan.md` to include `<formal_coverage_auto_detection>` (Loop 2) and `<debug_context>` blocks, so the nested child nf-executor inherits both verification loops when committing.
+
+## Must-Haves
+
+1. Pattern A spawn prompt includes `<formal_coverage_auto_detection>` block with Loop 2 (solution-simulation-loop)
+2. Pattern A spawn prompt includes conditional `<debug_context>` passthrough from parent context
+3. Pattern B confirmed safe (orchestrator commits, not subagent) — no changes needed
+4. Fail-open preserved on all new blocks
+5. Sync repo source → installed copy
+
+## Analysis
+
+- **Pattern A** (line 121): Currently a one-liner prose description. Expand to include formal blocks in the prompt specification.
+- **Pattern B** (line 123): Segment subagents do NOT commit — orchestrator (main context) commits. Orchestrator has Loop 2. **No change needed.**
+- **Pattern C** (line 125): Executes in main context. Has Loop 2. **No change needed.**
+- **Pattern D** (lines 130+): Worktree executors with minimal prompts. Opt-in only (--parallel flag). **Defer to separate task.**
+
+## Tasks
+
+### Task 1: Expand Pattern A spawn description to include formal blocks
+
+Replace the Pattern A one-liner at line 121 with an expanded prompt specification that includes:
+1. The existing instructions (execute plan, autonomous, all tasks, SUMMARY, commit, deviation/auth rules)
+2. `<formal_coverage_auto_detection>` block (same as execute-phase.md lines 217-251)
+3. `<debug_context>` passthrough: `${PARENT_DEBUG_CONTEXT || ''}` — the parent executor passes any debug_context it received from the orchestrator
+
+Note: The parent nf-executor (spawned by execute-phase.md) receives `$DEBUG_CONSTRAINTS`, `$DEBUG_FORMAL_VERDICT`, `$DEBUG_REPRODUCING_MODEL` from the orchestrator's debug routing. When spawning the Pattern A child, the parent must forward these as a `<debug_context>` block in the child's prompt.
+
+### Task 2: Sync to installed copy
+
+```bash
+cp core/workflows/execute-plan.md ~/.claude/nf/workflows/execute-plan.md
+```

.planning/quick/363-push-loop-2-and-debug-context-into-execu/363-VERIFICATION.md

@@ -0,0 +1,26 @@
+# Verification: Quick Task 363
+
+## Must-Haves
+
+| # | Requirement | Status | Evidence |
+|---|---|---|---|
+| 1 | Pattern A includes formal_coverage_auto_detection (Loop 2) | PASS | Lines 132-154 — full block with simulateSolutionLoop, gates, fail-open |
+| 2 | Pattern A includes debug_context passthrough | PASS | Line 156 — `${PARENT_DEBUG_CONTEXT || ''}` + line 161 passthrough docs |
+| 3 | Pattern B confirmed safe (orchestrator commits) | PASS | Line 123 — "Autonomous segments: NO SUMMARY/commit", orchestrator does final commit |
+| 4 | Fail-open preserved | PASS | Lines 140, 152, 153 — skip silently on errors/missing modules |
+| 5 | Sync repo → installed copy | PASS | `cp` verified via diff |
+
+## End-to-End Trace
+
+```
+User runs /nf:execute-phase
+  → execute-phase.md Step 1.5: Classify plan → route bug_fix through /nf:debug (Loop 1)
+  → execute-phase.md Step 2: Spawn nf-executor with <formal_coverage_auto_detection> + <debug_context>
+    → nf-executor reads execute-plan.md
+    → Pattern C: executes in main context → has Loop 2 + debug_context ✓
+    → Pattern A: spawns child nf-executor with Loop 2 + debug_context passthrough ✓ (NEW)
+    → Pattern B: segment subagents don't commit, orchestrator commits with Loop 2 ✓
+    → Pattern D: worktree executors — no loops (opt-in only, deferred)
+```
+
+## Status: Verified

.planning/quick/363-push-loop-2-and-debug-context-into-execu/scope-contract.json

@@ -0,0 +1,23 @@
+{
+  "nf/quick-362-wire-debug-routing-into-execute-phase-md": {
+    "task_id": 363,
+    "task_description": "Push Loop 2 (formal_coverage_auto_detection + solution-simulation-loop) and debug_context into execute-plan.md Pattern A spawn prompt",
+    "approach": "Inject formal_coverage_auto_detection, solution-simulation-loop, and debug_context constraint blocks into the Pattern A nf-executor spawn prompt in execute-plan.md so nested child executors inherit both verification loops.",
+    "out_of_scope": [
+      "Implementation of Loop modules (already exist)",
+      "Changes to Pattern B, C, or D routing",
+      "Loop 1 debug routing integration (already handled at orchestrator level)"
+    ],
+    "classification": {
+      "type": "feature",
+      "confidence": 0.85,
+      "routed_through_debug": false
+    },
+    "risk_level": "high",
+    "risk_reason": "Workflow file modification (execute-plan.md) — guardrail-protected",
+    "branches_affected": ["nf/quick-362-wire-debug-routing-into-execute-phase-md"],
+    "created_at": "2026-03-27T13:46:18.360Z",
+    "planner_model": "inherit",
+    "created_by": "quick-orchestrator"
+  }
+}

core/workflows/execute-phase.md

@@ -101,6 +101,89 @@ node ~/.claude/nf/bin/gsd-tools.cjs activity-set \
    - 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."
 
+1.5. **Classify plan type and debug routing (ROUTE-02, ROUTE-03):**
+
+   For each plan, classify its objective and optionally route through `/nf:debug` before execution.
+
+   **1.5a. Classify plan type via Haiku subagent:**
+
+   Spawn a Haiku subagent to classify the plan's objective:
+
+   ```
+   Task(
+     subagent_type="general-purpose",
+     model="haiku",
+     description="Classify plan type for debug routing",
+     prompt="
+   You are classifying a development plan into exactly one category.
+
+   ## Plan Objective
+   {plan_objective_text from <objective> tag}
+
+   ## Categories
+   - bug_fix: The plan fixes a bug, error, regression, crash, or broken behavior.
+   - feature: The plan adds new functionality or capability.
+   - refactor: The plan reorganizes, renames, cleans up, or simplifies existing code without changing behavior.
+
+   Respond with ONLY a JSON object:
+   {
+     \"type\": \"bug_fix\" | \"feature\" | \"refactor\",
+     \"confidence\": 0.0-1.0
+   }
+   "
+   )
+   ```
+
+   Parse response as JSON. Store as `$PLAN_CLASSIFICATION`.
+
+   **Fail-open:** If Haiku is unavailable or JSON parse fails, use `{ "type": "feature", "confidence": 0.0 }`.
+
+   Log: `"Plan classification: ${PLAN_CLASSIFICATION.type} (confidence: ${PLAN_CLASSIFICATION.confidence})"`
+
+   **1.5b. Debug routing:**
+
+   **Skip if:** `$PLAN_CLASSIFICATION.type` is NOT `bug_fix`, OR `$PLAN_CLASSIFICATION.confidence` < 0.7.
+
+   If skipped, log: `"Debug routing: skipped (type: ${PLAN_CLASSIFICATION.type}, confidence: ${PLAN_CLASSIFICATION.confidence})"`
+   Set `$DEBUG_CONSTRAINTS = null`, `$DEBUG_FORMAL_VERDICT = null`, `$DEBUG_REPRODUCING_MODEL = null`.
+
+   **If routing:**
+
+   1. Log: `"Debug routing: bug_fix detected (confidence: ${PLAN_CLASSIFICATION.confidence}) — routing through /nf:debug"`
+
+   2. Spawn `/nf:debug` as a Task subagent:
+
+   ```
+   Task(
+     prompt="
+   Run /nf:debug with the following failure context.
+
+   ## Plan Objective (from phase plan)
+   {plan_objective_text}
+
+   ## Instructions
+   - Run the full debug pipeline (Steps A through A.8: collect context, discovery, reproduction, refinement, constraint extraction)
+   - Return the debug output including:
+     - \$CONSTRAINTS (extracted constraints from Loop 1, if any)
+     - \$FORMAL_VERDICT (pass/fail/skip from formal model checking, if any)
+     - \$REPRODUCING_MODEL (path to reproducing formal model, if any)
+   - If any step fails or produces no output, continue with remaining steps (fail-open)
+   - Do NOT fix the bug — only diagnose and extract constraints. The executor will apply the fix.
+   ",
+     subagent_type="general-purpose",
+     description="Debug routing for plan {plan_number}: {plan_objective_summary}"
+   )
+   ```
+
+   3. Parse debug output. Extract and store:
+      - `$DEBUG_CONSTRAINTS` — constraints from Loop 1 refinement (may be empty)
+      - `$DEBUG_FORMAL_VERDICT` — formal model check result (may be "skipped")
+      - `$DEBUG_REPRODUCING_MODEL` — path to reproducing model (may be null)
+
+   4. Log: `"Debug routing complete. Constraints: ${DEBUG_CONSTRAINTS ? 'found' : 'none'}, Verdict: ${DEBUG_FORMAL_VERDICT || 'skipped'}"`
+
+   **Fail-open:** If the debug subagent errors or times out, log a warning and proceed without debug context. Set all debug vars to null.
+
 2. **Spawn executor agents:**
 
    Pass paths only — executors read files themselves with their fresh 200k context.
@@ -167,6 +250,17 @@ node ~/.claude/nf/bin/gsd-tools.cjs activity-set \
        6. If step 2 found NO intersections: skip Loop 2 entirely (GATE-03) — silent, no log
        </formal_coverage_auto_detection>
 
+       ${DEBUG_CONSTRAINTS || DEBUG_FORMAL_VERDICT || DEBUG_REPRODUCING_MODEL ?
+       `<debug_context>
+       This plan was routed through /nf:debug before execution. Use the following debug output as supplementary context for your implementation:
+
+       ${DEBUG_CONSTRAINTS ? '**Constraints from formal model refinement:**\n' + DEBUG_CONSTRAINTS : ''}
+       ${DEBUG_FORMAL_VERDICT ? '**Formal verdict:** ' + DEBUG_FORMAL_VERDICT : ''}
+       ${DEBUG_REPRODUCING_MODEL ? '**Reproducing model:** ' + DEBUG_REPRODUCING_MODEL : ''}
+
+       These constraints inform the fix but do not gate it. If constraints conflict with the plan, follow the plan.
+       </debug_context>` : ''}
+
        <success_criteria>
        - [ ] All tasks executed
        - [ ] Each task committed individually