@yemi33/minions 0.1.249 → 0.1.251

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/CHANGELOG.md CHANGED
@@ -1,10 +1,14 @@
1
1
  # Changelog
2
2
 
3
- ## 0.1.249 (2026-04-03)
3
+ ## 0.1.251 (2026-04-03)
4
4
 
5
5
  ### Features
6
+ - add 'pin' action to CC — pin critical context to all agents
6
7
  - mandatory test validation before PR creation in implement and fix playbooks
7
8
 
9
+ ### Fixes
10
+ - don't hardcode npm test — agents must read project conventions
11
+
8
12
  ## 0.1.248 (2026-04-03)
9
13
 
10
14
  ### Fixes
@@ -279,6 +279,16 @@ async function ccExecuteAction(action) {
279
279
  status.style.color = 'var(--green)';
280
280
  break;
281
281
  }
282
+ case 'pin': {
283
+ await fetch('/api/pinned', {
284
+ method: 'POST', headers: { 'Content-Type': 'application/json' },
285
+ body: JSON.stringify({ title: action.title, content: action.content || action.description, level: action.level || '' })
286
+ });
287
+ status.innerHTML = '&#x1F4CC; Pinned: <strong>' + escHtml(action.title) + '</strong> — visible to all agents';
288
+ status.style.color = 'var(--green)';
289
+ refresh();
290
+ break;
291
+ }
282
292
  case 'plan': {
283
293
  await fetch('/api/plan', {
284
294
  method: 'POST', headers: { 'Content-Type': 'application/json' },
package/dashboard.js CHANGED
@@ -378,7 +378,8 @@ If no actions are needed (just answering a question, or you handled it directly)
378
378
 
379
379
  Available action types:
380
380
  - **dispatch**: Create a work item for an agent. Fields: title, workType (ask/explore/fix/review/test/implement/verify), priority (low/medium/high), agents (array of IDs, optional), project, description. Use \`verify\` when the user wants to build PRs locally, merge branches together, start a dev server, and get a localhost URL to test.
381
- - **note**: Save a note/decision. Fields: title, content
381
+ - **note**: Save a note/decision to the inbox. Fields: title, content
382
+ - **pin**: Pin critical context visible to ALL agents on every task. Use when the user says "remember", "pin", "always", "from now on". Fields: title, content, level (optional: "critical" or "warning")
382
383
  - **plan**: Create a multi-step plan. Fields: title, description, project, branchStrategy (parallel/shared-branch)
383
384
  - **cancel**: Cancel a running agent. Fields: agent (agent ID), reason
384
385
  - **retry**: Retry failed work items. Fields: ids (array of work item IDs)
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@yemi33/minions",
3
- "version": "0.1.249",
3
+ "version": "0.1.251",
4
4
  "description": "Multi-agent AI dev team that runs from ~/.minions/ — five autonomous agents share a single engine, dashboard, and knowledge base",
5
5
  "bin": {
6
6
  "minions": "bin/minions.js"
package/playbooks/fix.md CHANGED
@@ -47,8 +47,8 @@ If you encounter merge conflicts (e.g., during `git pull` or when the PR shows c
47
47
 
48
48
  Before pushing your fix, run the project's test suite:
49
49
 
50
- 1. Find the test command (check `package.json` scripts, CLAUDE.md, or README usually `npm test`)
51
- 2. Run the full test suite
50
+ 1. Find the test command by reading the project's own documentation — check CLAUDE.md, agent.md, README, or package.json scripts in the project root. Every project defines its own conventions.
51
+ 2. Run the full test suite using whatever command the project specifies
52
52
  3. If any tests fail due to your changes, fix them before pushing
53
53
  4. Do NOT push code that breaks existing tests
54
54
 
@@ -73,8 +73,8 @@ After building, verify the build succeeded. If the build fails:
73
73
 
74
74
  Before creating a PR, you MUST run the project's test suite and ensure all existing tests pass:
75
75
 
76
- 1. Find the test command (check `package.json` scripts, CLAUDE.md, or README usually `npm test`)
77
- 2. Run the full test suite
76
+ 1. Find the test command by reading the project's own documentation — check CLAUDE.md, agent.md, README, or package.json scripts in the project root. Every project defines its own conventions.
77
+ 2. Run the full test suite using whatever command the project specifies
78
78
  3. If any tests fail:
79
79
  - Determine if YOUR changes caused the failure (compare with the failing test's assertions)
80
80
  - Fix any regressions you introduced