v1.11.1 — installer 'A' option and bot evaluation notes

- install.js: split into 'I' (prompts + loop) and new 'A' (everything
  including bot + metrics); update prompt to (I, A, U, C, Q).
- CHANGELOG: document complexity check (1.11.1) and expand 1.11.0
  notes for the LLM-as-judge evaluation system.
- version.json: 1.10.0 -> 1.11.1.

CHANGELOG.md

@@ -2,6 +2,16 @@
 
 All notable changes to Plan2Code will be documented in this file.
 
+## v1.11.1
+
+### 🔧 Changed
+
+- **Task complexity check in Document workflow** — Enhanced task writing guidance with lightweight cognitive complexity heuristics (inspired by PR #26)
+  - "Time-boxed" criterion now includes explicit split triggers: 5+ logic branches, 2+ integration points, or shared interface mutation
+  - New "Complexity check" prompt: before finalizing each task, LLM considers logic branches, distinct behaviors, integration points, shared interface impact, and error/edge cases
+  - Tasks complex on 3+ signals must be split; adjacent trivial tasks forming a cohesive unit should be combined
+  - Process step 7 updated to reinforce the complexity check during phase file authoring
+
 ## v1.11.0
 
 ### ✨ Added
@@ -13,7 +23,15 @@ All notable changes to Plan2Code will be documented in this file.
   - State file (`.plan2code-bot-state.json`) saved after each step; automatically deleted on full success, preserved on failure for later resume
   - Resume auto-detects state files in current directory (enhancement mode) or immediate subdirectories (new-project mode)
   - Artifact validation after each step (aborts on missing expected outputs)
-  - Auto-responder handles `AskUserQuestion` prompts autonomously (approvals, testing gates, name questions)
+  - **LLM-as-judge evaluation system** — Always-on quality assessment that transforms bot from "yes-man" to authentic QA agent
+    - **Intelligent decision making**: Uses LLM to answer `AskUserQuestion` prompts based on current observations (tools used, files created, errors) instead of hardcoded keyword matching
+    - **Post-step evaluation**: Comprehensive quality assessment after each step using step-specific criteria (score 0-100, strengths, weaknesses, suggestions, critical issues)
+    - **Observation tracking**: Full execution history captured (tools, files, messages, errors, questions with LLM reasoning)
+    - **Quality gate**: Blocks finalization if average score < 60, ensuring minimum quality standards
+    - **Evaluation artifacts**: Creates `BOT-EVALUATION.md` (quality assessments) and `BOT-NOTES.md` (execution observations) for metrics analysis
+    - **Color-coded output**: Green (≥85), yellow (70-84), red (<70) score display in console
+    - **Honest scoring**: Evaluation criteria emphasize realistic assessment (most work scores 70-85, not inflated)
+    - **Metrics-ready data**: Structured `EvaluationResult` and `ExecutionObservation` in state file for `plan2code-metrics` analysis
   - Bot-friendly skill installation (copies plan2code skills with `disable-model-invocation` stripped)
   - Implement step loops up to 10 passes until all phases are complete
   - Installer integration: `C > B` menu option to install bot CLI only

install.js

@@ -1387,32 +1387,43 @@ function runInteractive() {
     console.log(padEndVisible(`${COLORS.CYAN}║${COLORS.RESET} ${COLORS.BRIGHT}INSTALL PLAN2CODE${COLORS.RESET}`, 58) + `${COLORS.CYAN}║${COLORS.RESET}`);
     console.log(`${COLORS.CYAN}╠═════════════════════════════════════════════════════════╣${COLORS.RESET}`);
     console.log(padEndVisible(`${COLORS.CYAN}║${COLORS.RESET}  ${COLORS.BRIGHT}I.${COLORS.RESET}  ${COLORS.GREEN}INSTALL${COLORS.RESET}    Install Plan2Code for all platforms`, 58) + `${COLORS.CYAN}║${COLORS.RESET}`);
+    console.log(padEndVisible(`${COLORS.CYAN}║${COLORS.RESET}  ${COLORS.BRIGHT}A.${COLORS.RESET}  ${COLORS.MAGENTA}ALL${COLORS.RESET}        Install Plan2Code + dev tools`, 58) + `${COLORS.CYAN}║${COLORS.RESET}`);
     console.log(padEndVisible(`${COLORS.CYAN}║${COLORS.RESET}  ${COLORS.BRIGHT}U.${COLORS.RESET}  ${COLORS.RED}UNINSTALL${COLORS.RESET}  Remove Plan2Code files`, 58) + `${COLORS.CYAN}║${COLORS.RESET}`);
     console.log(padEndVisible(`${COLORS.CYAN}║${COLORS.RESET}  ${COLORS.BRIGHT}C.${COLORS.RESET}  ${COLORS.BLUE}CUSTOM${COLORS.RESET}     Advanced options`, 58) + `${COLORS.CYAN}║${COLORS.RESET}`);
     console.log(padEndVisible(`${COLORS.CYAN}║${COLORS.RESET}  ${COLORS.BRIGHT}Q.${COLORS.RESET}  ${COLORS.DIM}QUIT${COLORS.RESET}       Exit`, 58) + `${COLORS.CYAN}║${COLORS.RESET}`);
     console.log(`${COLORS.CYAN}╚═════════════════════════════════════════════════════════╝${COLORS.RESET}`);
     console.log('');
 
-    // Task 2.2: Input prompt
+    // Input prompt
     console.log('');
-    const answer = await question(`${COLORS.CYAN}${SYMBOLS.SELECT} SELECT OPTION${COLORS.RESET} (I, U, C, Q) [I]: `);
+    const answer = await question(`${COLORS.CYAN}${SYMBOLS.SELECT} SELECT OPTION${COLORS.RESET} (I, A, U, C, Q) [I]: `);
     const input = answer.trim().toUpperCase() || 'I';
 
-    // Task 2.3: I path — Install All
+    // I path — Install prompts + loop
     if (input === 'I') {
       rl.close();
       const loopResult = installPlan2CodeLoop();
       console.log('');
-      const metricsResult = installPlan2CodeMetrics();
-      console.log('');
-      const botResult = installPlan2CodeBot();
-      console.log('');
       const installResult = install();
-      const exitCode = loopResult !== 0 ? loopResult : metricsResult !== 0 ? metricsResult : botResult !== 0 ? botResult : installResult;
+      const exitCode = loopResult !== 0 ? loopResult : installResult;
       process.exit(exitCode);
     }
 
-    // Task 2.4: U path — Uninstall All
+    // A path — Install Everything (prompts + loop + bot + metrics)
+    if (input === 'A') {
+      rl.close();
+      const loopResult = installPlan2CodeLoop();
+      console.log('');
+      const botResult = installPlan2CodeBot();
+      console.log('');
+      const metricsResult = installPlan2CodeMetrics();
+      console.log('');
+      const installResult = install();
+      const exitCode = loopResult !== 0 ? loopResult : installResult !== 0 ? installResult : botResult !== 0 ? botResult : metricsResult;
+      process.exit(exitCode);
+    }
+
+    // U path — Uninstall All
     if (input === 'U') {
       console.log('');
       console.log(`${COLORS.RED}   o     o${COLORS.RESET}`);
@@ -1442,7 +1453,7 @@ function runInteractive() {
       }
     }
 
-    // Task 2.5: C path — CUSTOM sub-menu
+    // C path — CUSTOM sub-menu
     if (input === 'C') {
       console.log('');
       console.log(`${COLORS.CYAN}╔════════════════════════════════════════════════════════════════╗${COLORS.RESET}`);
@@ -1458,13 +1469,13 @@ function runInteractive() {
       const customAnswer = await question(`${COLORS.CYAN}${SYMBOLS.SELECT} SELECT OPTION${COLORS.RESET} (L, O, M, B, Q) [Q]: `);
       const customInput = customAnswer.trim().toUpperCase() || 'Q';
 
-      // Task 2.6: C > L — show local install instructions
+      // C > L — show local install instructions
       if (customInput === 'L') {
         rl.close();
         process.exit(displayLocalInstructions());
       }
 
-      // Task 2.7: C > O — install loop CLI only
+      // C > O — install loop CLI only
       if (customInput === 'O') {
         rl.close();
         const result = installPlan2CodeLoop();
@@ -1485,19 +1496,19 @@ function runInteractive() {
         process.exit(result);
       }
 
-      // Task 2.8: C > Q — back to main menu
+      // C > Q — back to main menu
       return main();
     }
 
-    // Task 2.8: Q — exit
+    // Q — exit
     if (input === 'Q') {
       console.log(`\n${COLORS.YELLOW}${SYMBOLS.WARNING} CANCELLED${COLORS.RESET}\n`);
       rl.close();
       process.exit(0);
     }
 
-    // Task 2.8: Invalid input — loop back
-    console.log(`\n${COLORS.RED}${SYMBOLS.ERROR} Invalid option. Please choose I, U, C, or Q.${COLORS.RESET}\n`);
+    // Invalid input — loop back
+    console.log(`\n${COLORS.RED}${SYMBOLS.ERROR} Invalid option. Please choose I, A, U, C, or Q.${COLORS.RESET}\n`);
     return main();
   }
 

version.json

@@ -1,6 +1,6 @@
 {
   "name": "Plan2Code",
-  "version": "1.10.0",
+  "version": "1.11.1",
   "description": "A structured 4-step workflow methodology for AI-assisted software development",
   "keywords": [
     "ai",