@yemi33/minions 0.1.1035 → 0.1.1036

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
@@ -1,5 +1,46 @@
1
1
  # Changelog
2
2
 
3
+ ## 0.1.1036 (2026-04-16)
4
+
5
+ ### Features
6
+ - Doc-chat performance — debounced persistence, session TTL, smart disk reads (#1164)
7
+ - split getStatus() into fast/slow state tiers with separate TTLs (#1170)
8
+ - Cache _countWorktrees() with 30s TTL (#1166)
9
+ - Pre-cache gzipped status buffer alongside JSON cache (#1171)
10
+ - parallelize ADO and GitHub PR polling with Promise.allSettled (#1172)
11
+ - route implement items to dedicated implement playbook (#1115)
12
+
13
+ ### Fixes
14
+ - allow test tasks to create PRs when files are modified
15
+ - sidecar oversized dispatch prompts to prevent dashboard OOM (closes #1167) (#1183)
16
+ - use locked write for failed-with-PR reconciliation in cleanup.js (#1169)
17
+ - prevent test from corrupting live meeting state
18
+ - scheduler enabled field falsy check treats undefined as disabled (#1160)
19
+ - update branch-dedup tests to use canonical PR IDs after merge with master (#1146)
20
+ - auto-review not firing for manually-linked PRs with autoObserve=true
21
+ - mark PR abandoned on 404 instead of silently retrying each tick
22
+ - replace undefined PROJECTS with config.projects in checkWatches (#1108)
23
+ - write permission for publish workflow
24
+ - run tests inline and post check runs for publish PRs
25
+ - add maxBuffer to all GitHub CLI spawns + paginate PR list (#1130)
26
+ - add required CI checks for PRs + update publish for auto-merge
27
+ - revert to PR merge now that stale status check is removed
28
+ - guard live review check against undefined vote/state values (#1132)
29
+ - push version bump directly to master instead of via PR
30
+ - add push-triggered CI for chore/publish branches
31
+ - publish workflow chore PRs failing to merge
32
+ - harden KB ordering
33
+ - harden audited state transitions
34
+
35
+ ### Other
36
+ - [E2E] Dashboard & engine perf: gzip cache, tiered status, lock backoff, polling parallelization (#1174)
37
+ - Fix doc chat session isolation
38
+ - test(pipeline): add unit tests for CRUD, stage execution, run lifecycle (#1162)
39
+ - chore: test publish after removing stale status check
40
+ - chore: trigger publish test
41
+ - chore: test publish workflow fix
42
+ - chore: trigger publish workflow test
43
+
3
44
  ## 0.1.1035 (2026-04-16)
4
45
 
5
46
  ### Features
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@yemi33/minions",
3
- "version": "0.1.1035",
3
+ "version": "0.1.1036",
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/test.md CHANGED
@@ -17,14 +17,15 @@ Team root: {{team_root}}
17
17
 
18
18
  ## Instructions
19
19
 
20
- This is a **test/build/run task**. Your goal is to build, run, test, or verify something — NOT to create new features or PRs.
20
+ This is a **test/build/run task**. Your goal is to build, run, test, or verify something.
21
21
 
22
22
  1. **Navigate** to the correct project directory
23
23
  2. You are already in the correct working directory. If you need a specific branch, use `git checkout` — do NOT create additional worktrees.
24
24
  3. **Build** the project — follow the repo's build instructions (check CLAUDE.md, package.json, README)
25
25
  4. **Run** if the task asks for it (e.g., `yarn start`, `yarn dev`, docker-compose, etc.)
26
26
  5. **Test** if the task asks for it (e.g., `yarn test`, `pytest`, etc.)
27
- 6. **Report results** what worked, what failed, build output, test results, localhost URL if running
27
+ 6. **Write tests** if the task asks you to add or improve test coverage commit and open a PR when done
28
+ 7. **Report results** — what worked, what failed, build output, test results, localhost URL if running
28
29
 
29
30
  ## Working Style
30
31
 
@@ -32,9 +33,9 @@ Use subagents only for genuinely parallel, independent tasks. For building, test
32
33
 
33
34
  ## Rules
34
35
 
35
- - **Do NOT create pull requests** this is a test/verification task only
36
- - **Do NOT push commits** unless the task explicitly asks you to fix something
37
- - **Do NOT modify code** unless the task explicitly asks for a fix
36
+ - **Do NOT modify production code** unless the task explicitly asks for a fix
37
+ - **Create a PR** if the task involves writing or modifying files (new tests, test fixes, etc.) — follow the same PR conventions as implement tasks
38
+ - **Do NOT push or create a PR** for pure build/run/verify tasks that make no file changes
38
39
  - Use PowerShell for build commands on Windows if applicable
39
40
  - If a build or test fails, report the error clearly — don't try to fix it unless asked
40
41
  - If running a local server, report the URL (e.g., http://localhost:3000)
@@ -66,6 +67,6 @@ Include:
66
67
 
67
68
  ## When to Stop
68
69
 
69
- Your task is complete once you have run the tests, written findings to the inbox file, and (if applicable) created a PR with new tests. Stop after writing findings.
70
+ Your task is complete once you have run the tests, written findings to the inbox file, and (if the task involved file changes) created and submitted a PR. Stop after writing findings.
70
71
 
71
72
  Do NOT remove worktrees — the engine handles cleanup automatically.