fix: resolve critical complexity routing issues from multi-agent review

Fixes 6 critical issues discovered in multi-agent code review:

1. **Parameter propagation** - CRITICAL FIX
   - Added complexity_level parameter to super-dev-pipeline invocations
   - Fixed both sequential and parallel execution paths
   - Without this, complexity routing was completely non-functional

2. **Keyword matching rules** - CRITICAL FIX
   - Defined explicit matching algorithm in workflow.yaml
   - Case insensitive, word boundary matching, exact strategy
   - Added keyword variants (auth -> authentication, authorize, etc.)
   - Scan locations: story_title, task_descriptions, subtask_descriptions

3. **Threshold decision tree** - CRITICAL FIX
   - Rewrote overlapping logic to be mutually exclusive
   - Priority order: COMPLEX → MICRO → STANDARD
   - Prevents stories from matching multiple categories

4. **Task counting method** - CRITICAL FIX
   - Defined method: "top_level_only" (ignore subtasks)
   - Added documentation with examples
   - Eliminates ambiguity in complexity scoring

5. **max_files implementation** - FIX
   - Added file_count ≤ 5 check to MICRO classification
   - Previously extracted but never used (dead code)

6. **Version synchronization** - FIX
   - Updated super-dev-pipeline to v1.3.0 (was 1.2.0)
   - Matches batch-super-dev version for consistency

Impact: These fixes make complexity routing actually functional. The original
implementation computed complexity but never passed it to the pipeline,
rendering the entire feature non-operational.

ASSESSMENT_SUMMARY.txt

@@ -0,0 +1,184 @@
+================================================================================
+DOCUMENTATION ASSESSMENT SUMMARY - v1.3.0 Complexity Routing
+================================================================================
+
+Assessment Date: 2026-01-07
+Commit: e5ede9ec (feat: add complexity-based routing and pipeline optimizations)
+Files Analyzed: 9 changed files across batch-super-dev, super-dev-pipeline, dev-story
+
+================================================================================
+OVERALL FINDINGS
+================================================================================
+
+✅ STRENGTHS:
+  - Clear version markers (mostly consistent)
+  - Well-structured step-file architecture
+  - Consistent tone and professional style
+  - Good use of emoji for visual hierarchy
+
+⚠️  ISSUES FOUND:
+  - 3 CRITICAL issues (blocking implementation)
+  - 2 HIGH priority issues (quality gates)
+  - 3 MEDIUM issues (consistency)
+  - Zero LOW priority issues requiring action
+
+QUALITY SCORE: 7/10
+
+================================================================================
+CRITICAL ISSUES (Must Fix Before Merge)
+================================================================================
+
+1. TASK COUNTING METHOD UNDEFINED (Line 230)
+   File: batch-super-dev/instructions.md
+   Impact: Complexity scoring inconsistent across stories
+   Fix: Add explicit definition including nested subtasks handling
+
+2. FILE_COUNT COLLECTED BUT UNUSED (Line 231)
+   File: batch-super-dev/instructions.md
+   Impact: Dead code, confusing developers
+   Fix: Either remove collection OR implement in complexity formula
+
+3. OVERLAPPING COMPLEXITY THRESHOLDS (Lines 242-244)
+   File: batch-super-dev/instructions.md
+   Impact: Edge cases route incorrectly
+   Example: 4-task "security" story with HIGH keyword
+   Fix: Replace with explicit decision tree (see SUGGESTED_FIXES.md)
+
+================================================================================
+HIGH PRIORITY ISSUES (Quality & Integration)
+================================================================================
+
+4. MULTI-AGENT MERGE STRATEGY MISSING (Lines 38-74)
+   File: step-05-code-review.md
+   Impact: Different merge results depending on implementer
+   Fix: Document deduplication, precedence, and merge algorithm
+
+5. RISK KEYWORD MATCHING UNDEFINED (Line 232)
+   File: batch-super-dev/instructions.md
+   Impact: ±5 points variance in complexity scoring
+   Issues: Case sensitivity, substring vs whole-word, deduplication
+   Fix: Specify exact matching rules with pseudocode
+
+================================================================================
+VERSION & CONSISTENCY ISSUES
+================================================================================
+
+6. VERSION MARKER MISMATCH (Line 94)
+   File: step-01-init.md
+   Current: "NEW v1.2.0"
+   Should: "NEW v1.3.0" (to match commit and batch-super-dev)
+
+7. BAILOUT vs SKIP TERMINOLOGY (Sections 4.5 + 6)
+   File: step-01-init.md
+   Issue: Both use similar language but mean different things
+   Fix: Document distinction clearly (see SUGGESTED_FIXES.md)
+
+8. CASE INCONSISTENCY (Multiple files)
+   Issue: "MICRO" vs "micro" used inconsistently
+   Fix: Document convention (uppercase display, lowercase storage)
+
+================================================================================
+DECISION TREE EXAMPLE (FIX #3)
+================================================================================
+
+Current (Problematic):
+  MICRO: task_count ≤ 3 AND complexity_score ≤ 5 AND no HIGH risk
+  COMPLEX: task_count ≥ 16 OR complexity_score ≥ 20 OR has HIGH risk
+  STANDARD: everything else
+
+Proposed (Clear & Unambiguous):
+  Step 1: Has HIGH keyword? → COMPLEX (STOP)
+  Step 2: task_count ≥ 16 OR score ≥ 20? → COMPLEX (STOP)
+  Step 3: task_count ≤ 3 AND score ≤ 5? → MICRO (STOP)
+  Step 4: Default → STANDARD
+
+Test Cases:
+  ✓ 2-task UI story: MICRO
+  ✓ 4-task auth story: COMPLEX (HIGH keyword)
+  ✓ 8-task standard story: STANDARD
+  ✓ 15-task database migration: COMPLEX (HIGH keywords)
+
+================================================================================
+DOCUMENTATION DELIVERABLES
+================================================================================
+
+1. DOCUMENTATION_ASSESSMENT.md (This analysis)
+   - Full assessment with detailed findings
+   - Quality ratings and metrics
+   - Test scenarios for complexity scoring
+   - 11 sections covering all aspects
+
+2. CRITICAL_FIXES_REQUIRED.md
+   - Blocking issues only
+   - Business impact explanation
+   - Specific file paths and line numbers
+   - Sign-off checklist before merge
+
+3. SUGGESTED_FIXES.md
+   - Exact replacement text for all 5 critical issues
+   - Code examples and pseudocode
+   - Complete working solutions ready to copy-paste
+   - 9 detailed fixes with implementation examples
+
+================================================================================
+RECOMMENDED ACTION PLAN
+================================================================================
+
+PHASE 1: Address Critical Issues (2-3 hours)
+  ☐ Fix task counting method (FIX #1)
+  ☐ Decide on file_count (FIX #2)
+  ☐ Implement decision tree (FIX #3)
+  ☐ Document merge strategy (FIX #4)
+  ☐ Specify keyword matching (FIX #5)
+
+PHASE 2: Fix Versions & Consistency (30 minutes)
+  ☐ Update version markers (FIX #6)
+  ☐ Document bailout/skip (FIX #7)
+  ☐ Document case convention (FIX #8)
+
+PHASE 3: QA & Testing (1-2 hours)
+  ☐ Test complexity scoring edge cases
+  ☐ Verify template rendering
+  ☐ Review decision tree logic
+  ☐ Check all file paths are absolute
+
+PHASE 4: Review & Sign-Off (1 hour)
+  ☐ PR review with focus on critical fixes
+  ☐ Merge with confidence
+
+Total Estimate: 4-6 hours
+
+================================================================================
+KEY METRICS
+================================================================================
+
+Clarity:        7/10 (Good, but some ambiguous sections)
+Consistency:    7/10 (Mostly consistent, some case/version issues)
+Completeness:   6/10 (Missing integration details)
+Correctness:    6/10 (Critical logic issues in thresholds)
+
+Files Affected: 4 core files
+Lines Modified: ~150 lines across all fixes
+Breaking Changes: None (backward compatible)
+Risk Level: MEDIUM (issues are fixable, non-fundamental)
+
+================================================================================
+CONTACT & REFERENCES
+================================================================================
+
+Commit: e5ede9ec
+Feature: Complexity-Based Routing v1.3.0
+Assessment: 2026-01-07
+
+Files to Review:
+- src/modules/bmm/workflows/4-implementation/batch-super-dev/instructions.md
+- src/modules/bmm/workflows/4-implementation/super-dev-pipeline/steps/step-01-init.md
+- src/modules/bmm/workflows/4-implementation/super-dev-pipeline/steps/step-03-implement.md
+- src/modules/bmm/workflows/4-implementation/super-dev-pipeline/steps/step-04-post-validation.md
+- src/modules/bmm/workflows/4-implementation/super-dev-pipeline/steps/step-05-code-review.md
+- src/modules/bmm/workflows/4-implementation/batch-super-dev/workflow.yaml
+- src/modules/bmm/workflows/4-implementation/super-dev-pipeline/workflow.yaml
+
+================================================================================
+END OF SUMMARY
+================================================================================

src/modules/bmm/workflows/4-implementation/batch-super-dev/instructions.md

@@ -227,21 +227,41 @@ Run `/bmad:bmm:workflows:sprint-status` to see status.
   <substep n="2.6a" title="Analyze story complexity">
     <action>Read story file: {{file_path}}</action>
 
-    <action>Count unchecked tasks ([ ]) in Tasks/Subtasks section → task_count</action>
+    <action>Count unchecked tasks ([ ]) at top level only in Tasks/Subtasks section → task_count
+      (See workflow.yaml complexity.task_counting.method = "top_level_only")
+    </action>
     <action>Extract file paths mentioned in tasks → file_count</action>
-    <action>Scan story title and task descriptions for risk keywords</action>
+    <action>Scan story title and task descriptions for risk keywords using rules from workflow.yaml:
+      - Case insensitive matching (require_word_boundaries: true)
+      - Include keyword variants (e.g., "authentication" matches "auth")
+      - Scan: story_title, task_descriptions, subtask_descriptions
+    </action>
 
     <action>Calculate complexity score:
       - Base score = task_count
-      - Add 5 for each HIGH risk keyword (auth, security, payment, migration, database, schema)
+      - Add 5 for each HIGH risk keyword match (auth, security, payment, migration, database, schema, encryption)
-      - Add 2 for each MEDIUM risk keyword (api, integration, external, cache)
+      - Add 2 for each MEDIUM risk keyword match (api, integration, external, third-party, cache)
       - Add 0 for LOW risk keywords (ui, style, config, docs, test)
+      - Count each keyword only once (no duplicates)
     </action>
 
-    <action>Assign complexity level:
+    <action>Assign complexity level using mutually exclusive decision tree (priority order):
-      - MICRO: task_count ≤ 3 AND complexity_score ≤ 5 AND no HIGH risk keywords
+
-      - COMPLEX: task_count ≥ 16 OR complexity_score ≥ 20 OR has HIGH risk keywords
+      1. Check COMPLEX first (highest priority):
-      - STANDARD: everything else
+         IF (task_count ≥ 16 OR complexity_score ≥ 20 OR has ANY HIGH risk keyword)
+         THEN level = COMPLEX
+
+      2. Else check MICRO (lowest complexity):
+         ELSE IF (task_count ≤ 3 AND complexity_score ≤ 5 AND file_count ≤ 5)
+         THEN level = MICRO
+
+      3. Else default to STANDARD:
+         ELSE level = STANDARD
+
+      This ensures no overlaps:
+      - Story with HIGH keyword → COMPLEX (never MICRO or STANDARD)
+      - Story with 4-15 tasks or >5 files → STANDARD (not MICRO or COMPLEX)
+      - Story with ≤3 tasks, ≤5 files, no HIGH keywords → MICRO
     </action>
 
     <action>Store complexity_level for story: {{story_key}}.complexity = {level, score, task_count, risk_keywords}</action>
@@ -418,7 +438,7 @@ Only the first {{max_stories}} will be processed.</output>
     </output>
 
     <action>Invoke workflow: /bmad:bmm:workflows:super-dev-pipeline</action>
-    <action>Parameters: mode=batch, story_key={{story_key}}</action>
+    <action>Parameters: mode=batch, story_key={{story_key}}, complexity_level={{story_key}}.complexity.level</action>
 
     <check if="super-dev-pipeline succeeded">
       <output>✅ Implementation complete: {{story_key}}</output>
@@ -507,7 +527,7 @@ Spawning Task agents in parallel...
                  CRITICAL INSTRUCTIONS:
                  1. Load workflow.xml: _bmad/core/tasks/workflow.xml
                  2. Load workflow config: _bmad/bmm/workflows/4-implementation/super-dev-pipeline/workflow.yaml
-                 3. Execute in BATCH mode with story_key={{story_key}}
+                 3. Execute in BATCH mode with story_key={{story_key}} and complexity_level={{story_key}}.complexity.level
                  4. Follow all 7 pipeline steps (init, pre-gap, implement, post-validate, code-review, complete, summary)
                  5. Commit changes when complete
                  6. Report final status (done/failed) with file list

src/modules/bmm/workflows/4-implementation/batch-super-dev/workflow.yaml

@@ -61,6 +61,33 @@ complexity:
     medium: ["api", "integration", "external", "third-party", "cache"]
     low: ["ui", "style", "config", "docs", "test"]
 
+  # Keyword matching configuration (defines how risk keywords are detected)
+  keyword_matching:
+    case_sensitive: false # "AUTH" matches "auth"
+    require_word_boundaries: true # "auth" won't match "author"
+    match_strategy: "exact" # exact word match required (no stemming)
+    scan_locations:
+      - story_title
+      - task_descriptions
+      - subtask_descriptions
+    # Keyword variants (synonyms that map to canonical forms)
+    variants:
+      auth: ["authentication", "authorize", "authorization", "authz", "authn"]
+      database: ["db", "databases", "datastore"]
+      payment: ["payments", "pay", "billing", "checkout"]
+      migration: ["migrations", "migrate"]
+      security: ["secure", "security"]
+      encryption: ["encrypt", "encrypted", "cipher"]
+
+  # Task counting rules
+  task_counting:
+    method: "top_level_only" # Only count [ ] at task level, not subtasks
+    # Options: "top_level_only", "include_subtasks", "weighted"
+    # Example:
+    # - [ ] Parent task       <- counts as 1
+    #   - [ ] Subtask 1       <- ignored
+    #   - [ ] Subtask 2       <- ignored
+
 # Execution settings
 execution:
   continue_on_failure: true # Keep processing remaining stories if one fails

src/modules/bmm/workflows/4-implementation/super-dev-pipeline/workflow.yaml

@@ -1,7 +1,7 @@
 name: super-dev-pipeline
 description: "Step-file architecture with complexity-based routing and smart batching. Micro stories get lightweight path, standard/complex get full quality gates."
 author: "BMad"
-version: "1.2.0" # Added complexity-based routing
+version: "1.3.0" # Synchronized with batch-super-dev for complexity-based routing
 
 # Critical variables from config
 config_source: "{project-root}/_bmad/bmm/config.yaml"