CalvinBackup/gstack
1
0
Fork 0
mirror of https://github.com/garrytan/gstack.git synced 2026-09-15 09:25:28 +02:00
Code Issues Packages Projects Releases Wiki Activity

docs: close cross-model doc-review gaps for v1.72.0.0

Browse Source 
setup's manual bun-verify instruction gets the same sha256sum-first
fallback the automated snippet got (coreutils-only Linux); BROWSER.md's
BROWSE_STATE_FILE row now lists the under-root world-writable refusal;
test-cost ceilings in CLAUDE.md/CONTRIBUTING.md updated for the five
new gate E2E cases (~$4.20 E2E / ~$4.35 evals).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Garry Tan
2026-08-28 17:26:57 +00:00
co-authored by Claude Fable 5
parent eb8742635c
commit 917a74e033
4 changed files with 8 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files
CONTRIBUTING.md
+3 -3
View File
@@ -149,14 +149,14 @@ Bun auto-loads `.env` — no extra config. Conductor workspaces inherit `.env` f
| Tier | Command | Cost | What it tests |
|------|---------|------|---------------|
| 1 — Static | `bun run test` | Free | Command validation, snapshot flags, SKILL.md correctness, TODOS-format.md refs, observability unit tests |
| 2 — E2E | `bun run test:e2e` | ~$3.85 | Full skill execution via `claude -p` subprocess |
| 2 — E2E | `bun run test:e2e` | ~$4.20 | Full skill execution via `claude -p` subprocess |
| 3 — LLM eval | `EVALS=1 bun test test/skill-llm-eval.test.ts` | ~$0.15 standalone | LLM-as-judge scoring of generated SKILL.md docs |
| 2+3 | `bun run test:evals` | ~$4 combined | E2E + LLM-as-judge (runs both) |
```bash
bun run test # Tier 1 only (run before every commit, ~90-100s for the full ~7,000-test suite)
bun run test:e2e # Tier 2: E2E only (needs EVALS=1, can't run inside Claude Code)
bun run test:evals # Tier 2 + 3 combined (~$4/run)
bun run test:evals # Tier 2 + 3 combined (~$4.35/run)
```
### Tier 1: Static validation (free)
@@ -176,7 +176,7 @@ eval files, and misses the strict classifier. No API keys needed.
- **Catalog budget** (`test/catalog-budget.test.ts`) — Caps the aggregate discovery surface: the sum of every skill's frontmatter `name` + `description` (what every host loads at discovery, every session) must stay under 1,150 token-equivalents, with a 260-byte per-skill cap. Counting goes through the shared census in `test/helpers/skill-census.ts` (physical files vs authored skills vs registry entries — three deliberately different counts). Adding a skill? The failure message carries the re-measure + ratchet protocol.
- **Context-budget ratchet** (`test/context-budget-ratchet.test.ts`) — CI ceilings on the two token ledgers the catalog budget doesn't cover: the always-on full-frontmatter aggregate and each skill's per-invocation eager tokens (SKILL.md + forced-read references), graded against `test/fixtures/context-budget.json` via `lib/context-bill.ts`. New skills fail until they have a ceiling; ceilings for removed skills must be pruned. Legitimate growth or a landed reduction: re-run `bun test/helpers/capture-context-budget.ts` and commit the refreshed fixture in the same commit, so the change is a visible decision in the diff.
### Tier 2: E2E via `claude -p` (~$3.85/run)
### Tier 2: E2E via `claude -p` (~$4.20/run)
Spawns `claude -p` as a subprocess with `--output-format stream-json --verbose`, streams NDJSON for real-time progress, and scans for browse errors. This is the closest thing to "does this skill actually work end-to-end?"