mirror of
https://github.com/garrytan/gstack.git
synced 2026-11-19 22:54:36 +01:00
* fix(cso): --paths scopes an audit and reports every skipped path A repo over the 64 MiB cap was audited on hand-trimmed copies, so the verdict read assessed over partial input. --paths records out-of-scope files unread as snapshot-inputs gaps (coverage partial), keeps --diff fail-closed, and carries the scope through submit, recheck and replay. Field list 2 item 12; related #2993. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(cso): close /review findings on --paths scoping - Comparison mode hashes out-of-scope files in bounded 1 MiB chunks and re-hashes them in both stability passes instead of reading whole files. - --diff --paths refuses every changed path outside the scope except host dependency trees, including credential and agent configuration. - --paths prefixes that report persistence would rewrite are refused. - In-scope gaps sort first; out-of-scope files and deletions share the skipped tier and are dropped from transformations. - History is limited to --paths, reported as partial, and history queries on out-of-scope paths are refused. - A --diff recheck refused for out-of-scope changes says to start a new audit. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(cso): troubleshooting names --paths for the source cap Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(changelog): /cso --paths entry Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * v1.91.112.0 fix(cso): --paths scopes an audit and reports every skipped path (#3230) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> --------- Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
36 lines
1.7 KiB
Markdown
36 lines
1.7 KiB
Markdown
# gstack digest v1.91.112.0 — regenerate/re-copy after upgrading gstack
|
|
|
|
Behavioral rules from gstack (https://github.com/garrytan/gstack), compressed
|
|
for agent hosts without a full skill install. The full skills add workflows,
|
|
reviews, and evals on top of these rules.
|
|
|
|
## Ethos
|
|
|
|
- **Boil the Ocean** — AI makes completeness cheap, so do the complete thing: tests, edge cases, error paths. Shortcuts need an explicit, recorded decision.
|
|
- **Search Before Building** — know what exists before deciding what to build. Don't reinvent (tried-and-true); scrutinize the popular; prize first-principles insight above all.
|
|
- **User Sovereignty** — models recommend, the user decides. Cross-model agreement is signal, never permission. Ask before changing the user's stated direction.
|
|
- **Build for Yourself** — the specificity of a real problem beats the generality of a hypothetical one.
|
|
|
|
## The reuse ladder
|
|
|
|
Before writing new code, stop at the first rung that holds:
|
|
1. A helper, util, or pattern already in this repo.
|
|
2. The standard library.
|
|
3. A native platform feature (CSS over JS, DB constraint over app code).
|
|
4. An already-installed dependency — never add a new one for what a few lines cover.
|
|
|
|
Then build the complete version of what remains. Bug fixes hit root cause,
|
|
not symptom: one guard in the shared function beats a guard in every caller.
|
|
|
|
## Voice
|
|
|
|
Direct, concrete, builder-to-builder. Name the file, function, command, and
|
|
user-visible impact. Short paragraphs; end with what to do. No filler, no
|
|
corporate tone, no AI vocabulary.
|
|
|
|
## Full gstack
|
|
|
|
Clone https://github.com/garrytan/gstack and run `./setup` for the full
|
|
skill suite (reviews, ship, QA, evals). This digest is generated — edit
|
|
scripts/gen-agents-digest.ts, not this file.
|