@yemi33/minions 0.1.167 → 0.1.169

package/CHANGELOG.md

@@ -1,5 +1,27 @@
 # Changelog
 
+## 0.1.169 (2026-04-02)
+
+### Engine
+- engine/lifecycle.js
+
+## 0.1.168 (2026-04-02)
+
+### Engine
+- engine.js
+- engine/lifecycle.js
+- engine/playbook.js
+- engine/shared.js
+
+### Dashboard
+- dashboard.js
+- dashboard/js/render-work-items.js
+- dashboard/js/settings.js
+
+### Other
+- routing.md
+- test/unit.test.js
+
 ## 0.1.167 (2026-04-02)
 
 ### Engine

package/dashboard/js/render-work-items.js

@@ -116,7 +116,7 @@ function renderWorkItems(items) {
 function editWorkItem(id, source) {
   const item = allWorkItems.find(i => i.id === id);
   if (!item) return;
-  const types = ['implement', 'fix', 'review', 'plan', 'verify', 'evaluate', 'decompose', 'meeting', 'investigate', 'refactor', 'test', 'explore', 'ask', 'docs'];
+  const types = ['implement', 'fix', 'review', 'plan', 'verify', 'decompose', 'meeting', 'investigate', 'refactor', 'test', 'explore', 'ask', 'docs'];
   const priorities = ['critical', 'high', 'medium', 'low'];
   const agentOpts = (cmdAgents || []).map(a => '<option value="' + escHtml(a.id) + '"' + (item.agent === a.id ? ' selected' : '') + '>' + escHtml(a.name) + '</option>').join('');
   const typeOpts = types.map(t => '<option value="' + t + '"' + ((item.type || 'implement') === t ? ' selected' : '') + '>' + t + '</option>').join('');
@@ -316,7 +316,7 @@ async function submitFeedback(id, source) {
 }
 
 function openCreateWorkItemModal() {
-  const typeOpts = ['implement', 'fix', 'explore', 'test', 'review', 'ask', 'plan', 'verify', 'evaluate', 'decompose', 'meeting'].map(t =>
+  const typeOpts = ['implement', 'fix', 'explore', 'test', 'review', 'ask', 'plan', 'verify', 'decompose', 'meeting'].map(t =>
     '<option value="' + t + '"' + (t === 'implement' ? ' selected' : '') + '>' + t + '</option>'
   ).join('');
   const priOpts = ['high', 'medium', 'low'].map(p =>

package/dashboard/js/settings.js

@@ -39,7 +39,7 @@ async function openSettings() {
     '</div>' +
     '<div style="display:flex;flex-direction:column;gap:6px;margin-bottom:16px">' +
       settingsToggle('Auto-approve Plans', 'set-autoApprovePlans', !!e.autoApprovePlans, 'PRDs are approved automatically without human review') +
-      settingsToggle('Auto-review PRs', 'set-autoReview', e.autoReview !== false, 'Automatically dispatch review agents for new PRs') +
+      settingsToggle('Eval Loop', 'set-evalLoop', e.evalLoop !== false, 'Auto-review implementations and iterate fix cycles until pass') +
       settingsToggle('Auto-decompose', 'set-autoDecompose', e.autoDecompose !== false, 'Large implement items are auto-split into sub-tasks') +
       settingsToggle('Allow Temp Agents', 'set-allowTempAgents', !!e.allowTempAgents, 'Spawn ephemeral agents when all permanent agents are busy') +
     '</div>' +
@@ -122,7 +122,7 @@ async function saveSettings() {
       restartGracePeriod: document.getElementById('set-restartGracePeriod').value,
       meetingRoundTimeout: document.getElementById('set-meetingRoundTimeout').value,
       autoApprovePlans: document.getElementById('set-autoApprovePlans').checked,
-      autoReview: document.getElementById('set-autoReview').checked,
+      evalLoop: document.getElementById('set-evalLoop').checked,
       autoDecompose: document.getElementById('set-autoDecompose').checked,
       allowTempAgents: document.getElementById('set-allowTempAgents').checked,
     };

package/dashboard.js

@@ -2956,7 +2956,7 @@ What would you like to discuss or change? When you're happy, say "approve" and I
           }
         }
         if (e.worktreeRoot !== undefined) config.engine.worktreeRoot = String(e.worktreeRoot || D.worktreeRoot);
-        for (const key of ['autoApprovePlans', 'autoReview', 'autoDecompose', 'allowTempAgents']) {
+        for (const key of ['autoApprovePlans', 'evalLoop', 'autoDecompose', 'allowTempAgents']) {
           if (e[key] !== undefined) config.engine[key] = !!e[key];
         }
       }

package/engine/lifecycle.js

@@ -478,6 +478,7 @@ function updateWorkItemStatus(meta, status, reason) {
       if (status === 'done') {
         delete target.failReason;
         delete target.failedAt;
+        delete target._retryCount;
         target.completedAt = ts();
       } else if (status === 'failed') {
         if (reason) target.failReason = reason;
@@ -1068,7 +1069,7 @@ function resolveWiPath(meta) {
 }
 
 /**
- * Parse structured eval verdict from evaluate agent output.
+ * Parse structured eval verdict from review agent output.
  * Looks for a JSON block with { pass, build, tests, criteria_met, criteria_failed, feedback }.
  * Returns parsed object or null if not found.
  */
@@ -1247,8 +1248,8 @@ function runPostCompletionHooks(dispatchItem, agentId, code, stdout, config) {
   // For 'fix' items, only trigger when they were created by the eval loop (_evalParentId set)
   const isEvalEligible = type === 'implement' || (type === 'fix' && meta?.item?._evalParentId);
   if (isSuccess && !skipDoneStatus && isEvalEligible && meta?.item?.id) {
-    const autoReview = config.engine?.autoReview ?? shared.ENGINE_DEFAULTS.autoReview;
-    if (autoReview) {
+    const evalLoop = config.engine?.evalLoop !== false;
+    if (evalLoop) {
       try {
         const wiPath = resolveWiPath(meta);
         if (wiPath) {
@@ -1297,10 +1298,10 @@ function runPostCompletionHooks(dispatchItem, agentId, code, stdout, config) {
   if (isSuccess && type === 'review' && meta?.item?._evalParentId) {
     try {
       const verdict = parseEvalVerdict(resultSummary || stdout);
-      const autoReview = config.engine?.autoReview ?? shared.ENGINE_DEFAULTS.autoReview;
+      const evalLoop = config.engine?.evalLoop !== false;
       const maxIter = config.engine?.evalMaxIterations ?? shared.ENGINE_DEFAULTS.evalMaxIterations;
 
-      if (verdict && !verdict.pass && autoReview) {
+      if (verdict && !verdict.pass && evalLoop) {
         const wiPath = resolveWiPath(meta);
         if (wiPath) {
           const items = safeJson(wiPath) || [];

package/engine/playbook.js

@@ -478,7 +478,7 @@ function selectPlaybook(workType, item) {
   if (workType === 'review' && !item?._pr && !item?.pr_id) {
     return 'work-item';
   }
-  const typeSpecificPlaybooks = ['explore', 'review', 'test', 'plan-to-prd', 'plan', 'ask', 'verify', 'evaluate', 'decompose', 'meeting-investigate', 'meeting-debate', 'meeting-conclude'];
+  const typeSpecificPlaybooks = ['explore', 'review', 'test', 'plan-to-prd', 'plan', 'ask', 'verify', 'decompose', 'meeting-investigate', 'meeting-debate', 'meeting-conclude'];
   return typeSpecificPlaybooks.includes(workType) ? workType : 'work-item';
 }
 

package/engine/shared.js

@@ -355,10 +355,9 @@ const ENGINE_DEFAULTS = {
   allowTempAgents: false, // opt-in: spawn ephemeral agents when all permanent agents are busy
   autoDecompose: true, // auto-decompose implement:large items into sub-tasks
   autoApprovePlans: false, // auto-approve PRDs without waiting for human approval
-  autoReview: true, // auto-dispatch review agents for new PRs (disable for manual review workflow)
   meetingRoundTimeout: 600000, // 10min per meeting round before auto-advance
-  evalLoop: true, // enable evaluate→fix loop after implementation completes
-  evalMaxIterations: 3, // max evaluate→fix cycles before escalating to human
+  evalLoop: true, // enable review→fix loop after implementation completes
+  evalMaxIterations: 3, // max review→fix cycles before escalating to human
   evalMaxCost: null, // USD ceiling per work item across all eval iterations; null = no limit (gather baseline data first)
 };
 

package/engine.js

@@ -1257,9 +1257,9 @@ function discoverFromPrs(config, project) {
     // minionsReview tracks metadata (reviewer, note) but not the authoritative status
     const reviewStatus = pr.reviewStatus || 'pending';
 
-    // PRs needing review: pending or waiting (review dispatched but no verdict yet)
-    const autoReview = config.engine?.autoReview !== false;
-    const needsReview = autoReview && reviewStatus === 'pending';
+    // PRs needing review: only dispatch if evalLoop is enabled
+    const evalLoop = config.engine?.evalLoop !== false;
+    const needsReview = evalLoop && reviewStatus === 'pending';
     if (needsReview) {
       const key = `review-${project?.name || 'default'}-${pr.id}`;
       if (isAlreadyDispatched(key) || isOnCooldown(key, cooldownMs)) continue;

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@yemi33/minions",
-  "version": "0.1.167",
+  "version": "0.1.169",
   "description": "Multi-agent AI dev team that runs from ~/.minions/ — five autonomous agents share a single engine, dashboard, and knowledge base",
   "bin": {
     "minions": "bin/minions.js"

package/routing.md

@@ -17,7 +17,6 @@ How the engine decides who handles what. Parsed by engine.js — keep the table
 | test | dallas | ralph |
 | ask | ripley | rebecca |
 | verify | dallas | ralph |
-| evaluate | ripley | lambert |
 | decompose | ripley | rebecca |
 | meeting | ripley | rebecca |
 

package/playbooks/evaluate.md

@@ -1,114 +0,0 @@
-# Evaluate: {{item_name}}
-
-> Agent: {{agent_name}} ({{agent_role}}) | Team root: {{team_root}}
-
-## Context
-
-Project: {{project_name}}
-Repo: {{repo_name}} | Org: {{ado_org}} | ADO Project: {{ado_project}}
-PR: {{pr_url}}
-Work Item: {{item_id}}
-
-## Acceptance Criteria
-
-{{acceptance_criteria}}
-
-## Task Description
-
-{{task_description}}
-
-## Your Task
-
-You are the **Evaluator** in the Planner-Generator-Evaluator pattern. Your job is to independently verify whether the implementation in the PR branch meets the acceptance criteria. You are NOT the implementer — you are the skeptic.
-
-**Mindset: Do not pass unless build succeeds AND all acceptance criteria are demonstrably met.** Assume the implementation is incomplete or wrong until proven otherwise. Look for edge cases, missing requirements, and silent failures.
-
-## Step 1: Check Out the PR Branch
-
-```bash
-cd {{project_path}}
-git fetch origin
-git checkout {{branch_name}}
-git pull origin {{branch_name}}
-```
-
-## Step 2: Build
-
-Run the project build. Check `CLAUDE.md`, `package.json`, or `README` for build instructions.
-
-```bash
-# Typical:
-npm install && npm run build
-# Or whatever the project uses
-```
-
-Record: **PASS** or **FAIL** with error output.
-
-If the build fails, **stop here** — the verdict is `pass: false`. Include the build error in feedback.
-
-## Step 3: Run Tests
-
-Run the full test suite:
-
-```bash
-npm test
-```
-
-Record: **X passed / Y failed / Z skipped**.
-
-If any tests fail, note which ones and whether they are related to the changes.
-
-## Step 4: Diff Review Against Acceptance Criteria
-
-Review the actual code changes:
-
-```bash
-git diff {{main_branch}}...{{branch_name}} --stat
-git diff {{main_branch}}...{{branch_name}}
-```
-
-For **each** acceptance criterion, determine:
-- **Met**: The diff demonstrably satisfies this criterion. Cite the specific file/line.
-- **Not met**: The diff does not satisfy this criterion, or satisfies it only partially. Explain what's missing.
-
-Be precise. "Looks good" is not an evaluation — cite file paths and line numbers.
-
-## Step 5: Output Structured Verdict
-
-After completing your evaluation, output the following JSON block as your final output. This MUST be valid JSON wrapped in a `json` fenced code block:
-
-```json
-{
-  "pass": false,
-  "build": true,
-  "tests": "42/42",
-  "criteria_met": [
-    "criterion 1 — met because X (source: path/to/file.js:42)"
-  ],
-  "criteria_failed": [
-    "criterion 2 — not met because Y is missing"
-  ],
-  "feedback": "Summary of what needs to change for this to pass. Be specific — file names, line numbers, what to add/fix."
-}
-```
-
-Field definitions:
-- `pass`: `true` only if build succeeds AND **all** acceptance criteria are met. Otherwise `false`.
-- `build`: `true` if the build completed without errors, `false` otherwise.
-- `tests`: String in format `"passed/total"` (e.g., `"38/40"`). Use `"N/A"` if no test suite exists.
-- `criteria_met`: Array of strings — one per criterion that IS met. Include source references.
-- `criteria_failed`: Array of strings — one per criterion that is NOT met. Explain why.
-- `feedback`: Actionable feedback for the implementer. Be specific about what to fix. If `pass` is `true`, use this for minor suggestions or "LGTM".
-
-## Rules
-
-- **No Playwright / browser testing** — this phase evaluates build, tests, and code review only.
-- **Do NOT fix code** — only evaluate and report. You are the evaluator, not the implementer.
-- **Do NOT rubber-stamp** — if a criterion is ambiguous, evaluate conservatively (fail it and explain).
-- **Build failure is an automatic fail** — do not evaluate criteria if the build doesn't pass.
-- **Every criterion must be addressed** — `criteria_met` + `criteria_failed` should cover all acceptance criteria.
-- **Cite sources** — reference file paths and line numbers for every met/failed criterion.
-
-{{references}}
-
-**Note:** Do NOT write to `agents/*/status.json` — the engine manages your status automatically.