agileflow 2.85.0 → 2.86.0

package/src/core/commands/batch.md

@@ -6,12 +6,14 @@ compact_context:
   preserve_rules:
     - "map: Execute action on each item sequentially"
     - "pmap: Execute action on each item in parallel (spawn Task agents)"
+    - "pmap MODE=loop: Iterate on each item until tests pass"
     - "filter: Return items matching criteria"
     - "reduce: Aggregate items into single output"
   state_fields:
     - batch_operation
     - items_processed
     - items_total
+    - batch_loop
 ---
 
 # /agileflow:batch
@@ -44,15 +46,22 @@ node .agileflow/scripts/obtain-context.js batch
 ```
 /agileflow:batch map "docs/06-stories/*.md" validate
 /agileflow:batch pmap "src/**/*.tsx" add-tests
+/agileflow:batch pmap "src/**/*.tsx" add-tests MODE=loop  # Iterate until tests pass
 /agileflow:batch filter stories status=ready
 /agileflow:batch reduce "docs/06-stories/*.md" summary
 ```
 
+**Loop Mode** (pmap only):
+- `MODE=loop` - Iterate on each file until tests pass
+- Sequential processing with quality gates
+- Tracks progress in `batch_loop` session state
+
 **Workflow**:
 1. Parse operation and pattern
 2. Resolve pattern to item list
 3. For each item: execute action based on operation type
-4. Collect and report results
+4. (Loop mode) Run tests, iterate if failing
+5. Collect and report results
 
 <!-- COMPACT_SUMMARY_END -->
 
@@ -355,8 +364,114 @@ Batch operations update session-state.json:
 
 ---
 
+## Loop Mode (pmap with quality gates)
+
+Process items iteratively until quality gates pass. Useful for test-driven batch operations.
+
+### Usage
+
+```
+/agileflow:batch pmap "pattern" action MODE=loop [GATE=tests] [MAX=50]
+```
+
+### Parameters
+
+| Parameter | Description | Default |
+|-----------|-------------|---------|
+| MODE=loop | Enable loop mode | off |
+| GATE=tests | Quality gate type (v1: tests only) | tests |
+| MAX=N | Max total iterations | 50 |
+
+### How It Works
+
+1. **Initialize**: Resolve glob pattern to file list
+2. **Process**: Work on first file, implement the action
+3. **Validate**: On stop, run tests for that file
+4. **Iterate**: If tests pass → next file; if fail → continue fixing
+5. **Complete**: When all files pass or max iterations reached
+
+### Example
+
+```
+/agileflow:batch pmap "src/components/*.tsx" add-tests MODE=loop
+```
+
+**Output:**
+```
+======================================================
+  BATCH LOOP - Iteration 1/50
+======================================================
+
+🔄 Iteration 1/50
+📍 Working on: src/components/Button.tsx
+
+Running tests for: src/components/Button.tsx
+──────────────────────────────────────────────────────
+✓ Tests passed (2.3s)
+
+✅ Item complete: src/components/Button.tsx
+
+━━━ Next Item ━━━
+src/components/Input.tsx
+
+Progress: 1/8 items complete
+
+▶ Implement "add-tests" for this file
+  Run tests when ready. Loop will validate and continue.
+```
+
+### Manual Control
+
+```bash
+# Check loop status
+node scripts/batch-pmap-loop.js --status
+
+# Stop the loop
+node scripts/batch-pmap-loop.js --stop
+
+# Reset loop state
+node scripts/batch-pmap-loop.js --reset
+
+# Initialize directly (alternative to slash command)
+node scripts/batch-pmap-loop.js --init --pattern="src/**/*.tsx" --action="add-tests" --max=30
+```
+
+### Session State
+
+Loop mode tracks progress in `session-state.json`:
+
+```json
+{
+  "batch_loop": {
+    "enabled": true,
+    "pattern": "src/**/*.tsx",
+    "action": "add-tests",
+    "quality_gate": "tests",
+    "current_item": "src/components/Button.tsx",
+    "items": {
+      "src/components/Button.tsx": { "status": "completed", "iterations": 1 },
+      "src/components/Input.tsx": { "status": "in_progress", "iterations": 0 }
+    },
+    "summary": { "total": 8, "completed": 1, "pending": 7 },
+    "iteration": 2,
+    "max_iterations": 50
+  }
+}
+```
+
+### Quality Gate (V1)
+
+V1 supports **tests gate only**:
+- Runs: `npm test -- --testPathPattern="filename"`
+- Passes if tests for this file pass (or no matching tests)
+- Fails if tests for this file fail
+
+Future versions may add: coverage, lint, types gates.
+
+---
+
 ## Integration
 
 - Works with `/agileflow:babysit` for batch story processing
-- Can be used in Ralph Loop for batch operations per iteration
+- **Loop mode** enables iterative batch processing with quality gates
 - Integrates with agent system for parallel work

package/src/core/commands/metrics.md

@@ -76,17 +76,18 @@ Every metric should suggest:
 
 ## Key Metrics Calculated
 
-10+ core metrics:
+11 core metrics:
 1. **Cycle Time** - in-progress → done
 2. **Lead Time** - created → done
 3. **Throughput** - stories completed/period
 4. **WIP** - current in-progress + in-review
 5. **Agent Utilization** - work distribution
-6. **Epic Health** - progress % + trend
-7. **Estimation Accuracy** - estimate vs actual
-8. **Blocked Stories** - count + duration
-9. **Flow Efficiency** - active vs total time %
-10. **Cumulative Flow Diagram** - stacked area chart
+6. **Thread Distribution** - session breakdown by thread type
+7. **Epic Health** - progress % + trend
+8. **Estimation Accuracy** - estimate vs actual
+9. **Blocked Stories** - count + duration
+10. **Flow Efficiency** - active vs total time %
+11. **Cumulative Flow Diagram** - stacked area chart
 
 ---
 
@@ -164,10 +165,11 @@ After displaying metrics:
 
 ## REMEMBER AFTER COMPACTION
 
-- Command is read-only (analyzes bus/log.jsonl + status.json)
-- Calculates 10+ metrics (cycle-time, lead-time, throughput, WIP, etc.)
+- Command is read-only (analyzes bus/log.jsonl + status.json + session registry)
+- Calculates 11 metrics (cycle-time, lead-time, throughput, WIP, thread-distribution, etc.)
 - Shows trends (↗ ↘ →) with % change vs previous period
 - Uses health indicators (🟢🟡🔴) for quick assessment
+- Thread Distribution shows session breakdown by thread type (base/parallel/chained/fusion/big/long)
 - Provides actionable recommendations (HIGH/MEDIUM/LOW)
 - Saves reports to docs/08-project/metrics-reports/
 - Always includes timeframe and generation timestamp
@@ -366,7 +368,48 @@ Balance Score: 78/100 (Good distribution)
 Recommendation: Consider assigning more work to AG-DEVOPS
 ```
 
-### 6. Epic Health
+### 6. Thread Distribution
+**Definition**: Distribution of work by thread type (see docs/02-practices/thread-based-engineering.md)
+
+```bash
+# Get thread type from session registry
+for session in sessions; do
+  thread_type=$(node .agileflow/scripts/session-manager.js thread-type $session)
+  stories_completed=$(count_stories_completed_in_session $session)
+  duration=$(calculate_session_duration $session)
+  echo "$thread_type: $stories_completed stories, $duration hours"
+done
+```
+
+**Output**:
+```
+Thread Distribution (30 days)
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+Sessions by Thread Type:
+  base       ████████████████████░░ 65%  (13 sessions)
+  parallel   ████████░░            25%  (5 sessions)
+  chained    ██░░                  5%   (1 session)
+  fusion     ██░░                  5%   (1 session)
+  big        ░░                    0%   (0 sessions)
+  long       ░░                    0%   (0 sessions)
+
+Avg Duration by Type:
+  base:       45 min avg    8 stories/session
+  parallel:   2.5 hours avg  12 stories/session
+  chained:    3 hours avg    15 stories/session
+  fusion:     30 min avg     1 decision/session
+
+Success Rate by Type:
+  base:       85% stories completed
+  parallel:   92% stories completed  ← Highest
+  chained:    78% stories completed
+  fusion:     N/A (advisory only)
+
+Trend (vs last month): ↗ +15% parallel usage
+Recommendation: Consider using parallel sessions for independent tasks
+```
+
+### 7. Epic Health (was 6)
 **Definition**: Progress and health indicators for epics
 
 ```bash
@@ -641,6 +684,16 @@ EXPORT FORMATS
       "limit": 6,
       "pct": 67,
       "blocked": 2
+    },
+    "thread_distribution": {
+      "base": {"count": 13, "pct": 65, "avg_duration_min": 45, "stories_per_session": 8},
+      "parallel": {"count": 5, "pct": 25, "avg_duration_min": 150, "stories_per_session": 12},
+      "chained": {"count": 1, "pct": 5, "avg_duration_min": 180, "stories_per_session": 15},
+      "fusion": {"count": 1, "pct": 5, "avg_duration_min": 30, "decisions_per_session": 1},
+      "big": {"count": 0, "pct": 0},
+      "long": {"count": 0, "pct": 0},
+      "trend": "parallel_increasing",
+      "change_pct": 15
     }
   },
   "epics": [...],