aboutsummaryrefslogtreecommitdiff
path: root/modules/ext/skill-pack-core.js
Commit message (Collapse)AuthorAgeFilesLines
* docs(newos4): merge the two shell-composition skills into one seeded skill ↵Agando2026-10-231-0/+52
| | | | | | | | | | | | | | | | | | | | | (v4.6.65) Packet 9. `terminal-commands-silently-failing` and `command-composition-rules` described the same bug family from two angles, and since v4.6.58 both were describing behaviour that is now refused outright. - new seeded skill `command-composition-rules` in skill-pack-core's _buildSkills(): the rule, why the refusal exists (with the 42-42 / 34k-a measurement), what works (one command per call, wc multi-path, interactive-only pipes, quoted operators), how to verify a plausible-looking result, and the pitfalls - its History section names both retired skills so a reader arriving from either search finds the surviving one - mirrored onto disk as skills/command-composition-rules.md + .json and added to skills/index.json (18 entries) so the repo copy matches what sessions receive Verified live on v4.6.65: seeding reported 15 skills (was 14), the file and index entry exist in the fresh VFS, and the natural-language query "does the terminal have a shell and what is refused" returns command-composition-rules first (13.78, 3/4).
* fix(newos4): unmeasured skills are untracked, world-model writes verified, ↵Agando2026-10-231-0/+5
| | | | | | | | | | | | | | | | | | | | | | | skill audit External review packet (os4-external-review-v4.6.51.html) triaged against the code: 2 findings confirmed and fixed, 4 could not be reproduced and were recorded as such. - module-memory-graph.js: getStaleSkills() treated a missing lastUsed as 999 days unused, so skill-audit recommended archiving every skill (22 of 22). Skills with no usage telemetry are now collected by getUntrackedSkills() and never counted stale. Live: "Stale: 0" + "Untracked: 22 (no usage telemetry — NOT stale)". - module-world-model.js: _saveToVFS() ignored fsWriteJSON()'s return value and promoted whatever a truthy read returned. Now write -> read-back -> byte compare -> promote, with every return checked. Regression test modules/test/test-world-model-save.js (red on the old code: promoted=true with errs=[]; green now). - scripts/newos4-skill-audit.py: 5 mechanical probes (version x3, read_file paging + context budget, selection symbols, required scripts, extKeys) + skill presence; exits non-zero on drift. 7/7 pass today. Weekly job cb6bc2a16216 runs it Mondays. Not reproduced (recorded in admin/docs/newos4-external-review-verification-2026-10-23.md): world_model_query empty-payload throw (live call returns JSON), pipes-as-command-names, ls skills empty (23 entries via fs.readDir), ~66 agent dirs (4 live).
* auto: 2026-07-09_06:00 changesAgando2026-07-091-0/+298
|
* auto: 2026-06-23_06:00 changesAgando2026-06-231-3/+6
|
* auto: 2026-06-10_18:00 changesAgando2026-06-101-11/+39
|
* auto: 2026-06-09_06:00 changesAgando2026-06-091-0/+6
|
* auto: 2026-06-08_18:00 changesAgando2026-06-081-1/+35
|
* auto: 2026-06-06_18:01 changesAgando2026-06-061-0/+42
|
* auto: 2026-06-06_06:00 changesAgando2026-06-061-1/+254
|
* auto: 2026-06-02_18:00 changesAgando2026-06-021-43/+241
|
* auto: 2026-05-28_18:00 changesAgando2026-05-281-0/+3
|
* auto: 2026-05-27_06:00 changesAgando2026-05-271-1/+1
|
* auto: 2026-05-25_18:02 changesAgando2026-05-251-0/+285