@yemi33/minions 0.1.1863 → 0.1.1864

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 +1,10 @@
1
1
  # Changelog
2
2
 
3
+ ## 0.1.1864 (2026-05-11)
4
+
5
+ ### Fixes
6
+ - apply targeted-only-test rule to fix/implement-shared/docs playbooks
7
+
3
8
  ## 0.1.1863 (2026-05-11)
4
9
 
5
10
  ### Fixes
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@yemi33/minions",
3
- "version": "0.1.1863",
3
+ "version": "0.1.1864",
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/docs.md CHANGED
@@ -63,8 +63,7 @@ If the doc describes vapor, delete the section. If real features are missing, ad
63
63
 
64
64
  - Re-read the changed doc end-to-end after editing — does it still flow?
65
65
  - If the project has doc-validation tests (lint, link-check, snippet-execution), run
66
- them. Otherwise run `npm test` (or the project's documented test command) to make
67
- sure nothing else broke.
66
+ them. **Use direct binary invocations** (`node test/<file>.test.js`, `python -m pytest`, etc.) — do NOT use package-manager wrappers (`npm test`, `yarn test`) and do NOT run the full-project suite. See shared-rules.md's CRITICAL RULE on test invocation.
68
67
  - For docs with embedded code samples, mentally execute each sample against current
69
68
  code — stale samples are worse than missing ones.
70
69
 
package/playbooks/fix.md CHANGED
@@ -57,15 +57,17 @@ Handle this like the PR author responding directly from a CLI:
57
57
  - Handle merge conflicts when needed, preserving the PR's intended changes while keeping the branch reviewable.
58
58
  - Do not add unrelated cleanups or broaden the PR beyond the review feedback unless that is necessary to make the fix correct.
59
59
 
60
- ## Validation
60
+ ## Validation — TARGETED ONLY, before publish
61
61
 
62
- Before pushing, prove the review fix did not break the branch:
62
+ Prove the review fix did not break the branch, BUT keep verification narrow:
63
63
 
64
64
  - Use the project's source of truth for commands: `CLAUDE.md`, README, package scripts, Makefile, or equivalent build config.
65
- - Run checks that are relevant to the addressed findings. Prefer the full suite when practical.
66
- - Capture the exact commands run and meaningful results in the PR comment and completion report.
65
+ - **Run only TARGETED tests covering the code you changed.** A single test file or a single test name is enough. Examples: `node test/unit/<my-file>.test.js`, `python -m pytest tests/test_my_module.py::test_my_case`, `cargo test --test my_test`.
66
+ - **Do NOT run the full project test suite (`node test/unit.test.js`, `npm test`, `yarn test`, etc.) as a verification step.** The full-suite run in a long agent session is the primary trigger for the runtime CLI crash documented in shared-rules.md. The engine and PR CI handle full-suite regression detection — your job is to verify the code you wrote works, not to re-prove the entire suite.
67
+ - Use a quick `node --check <file>` (or equivalent) for syntax validation — cheap and never crashes.
68
+ - Capture the exact targeted commands run and the meaningful result in the PR comment and completion report.
67
69
  - Fix regressions you introduced. If failures are pre-existing or unrelated, capture the evidence and include it in the PR comment.
68
- - Do not push code that breaks existing tests or the build because of your changes.
70
+ - Do not push code that breaks existing tests or the build because of your changes; if your targeted check fails, fix it before pushing.
69
71
 
70
72
  Long builds, dependency installs, and tests may be quiet for several minutes. Let the normal CLI command run naturally; do not add artificial heartbeat output or split commands just to show progress.
71
73
 
@@ -62,7 +62,7 @@ Deliver this as if the user asked you directly in a CLI, with the added constrai
62
62
  Before publishing, prove the shared branch still works with your change included:
63
63
 
64
64
  - Use the project's source of truth for commands: `CLAUDE.md`, README, package scripts, Makefile, or equivalent build config.
65
- - Run checks that are relevant to this item and to the integrated branch state. Prefer the full suite when practical.
65
+ - **Run only TARGETED tests covering the code you changed.** Do NOT run the full project test suite (`node test/unit.test.js`, `npm test`, `yarn test`, etc.) as a verification step — the full-suite run in a long agent session deterministically crashes the runtime CLI (see shared-rules.md). Use single test files or test names instead. The engine and PR CI handle full-suite regression detection.
66
66
  - Fix regressions you introduced. If failures are pre-existing or caused by earlier branch work, capture the evidence and say so clearly.
67
67
  - Do not push code with a broken build or failing tests that you introduced.
68
68