CalvinBackup/gstack
1
0
Fork 0
mirror of https://github.com/garrytan/gstack.git synced 2026-09-11 07:29:00 +02:00
Code Issues Packages Projects Releases Wiki Activity

docs: sync docs for v1.66.0.0 (test/evals/CI speedup)

Browse Source 
CONTRIBUTING.md, AGENTS.md, and ARCHITECTURE.md still taught bare
`bun test` for the suite; the shipped runner deprecates it (walks the
whole repo, loads paid eval files, misses the strict classifier). All
suite-level references now say `bun run test`, the Tier 1 section
describes the strict shard runner (~90-100s, --verbose, --wall-timeout),
the sharded paid-runner paragraph documents diff-based shard skipping
and the EVALS_JOBS / EVALS_CONCURRENCY split, the Tier 3 row points at
the actual judge-only invocation, and GSTACK_EVAL_MODEL_JUDGE is
documented at the judge it overrides.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Garry Tan
2026-08-15 17:23:00 -07:00
co-authored by Claude Fable 5
parent f627c676fc
commit 9b9bc84bdc
3 changed files with 25 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ARCHITECTURE.md
+2 -2
View File
@@ -321,7 +321,7 @@ Three reasons:
| 2 — E2E via `claude -p` | Spawn real Claude session, run each skill, check for errors | ~$3.85 | ~20min |
| 3 — LLM-as-judge | Sonnet scores docs on clarity/completeness/actionability | ~$0.15 | ~30s |
Tier 1 runs on every `bun test`. Tiers 2+3 are gated behind `EVALS=1`. The idea is: catch 95% of issues for free, use LLMs only for judgment calls.
Tier 1 runs on every `bun run test`. Tiers 2+3 are gated behind `EVALS=1`. The idea is: catch 95% of issues for free, use LLMs only for judgment calls.
## Command dispatch
@@ -435,7 +435,7 @@ The `EvalCollector` accumulates test results and writes them in two ways:
| 2 — E2E via `claude -p` | Spawn real Claude session, run each skill, scan for errors | ~$3.85 | ~20min |
| 3 — LLM-as-judge | Sonnet scores docs on clarity/completeness/actionability | ~$0.15 | ~30s |
Tier 1 runs on every `bun test`. Tiers 2+3 are gated behind `EVALS=1`. The idea: catch 95% of issues for free, use LLMs only for judgment calls and integration testing.
Tier 1 runs on every `bun run test`. Tiers 2+3 are gated behind `EVALS=1`. The idea: catch 95% of issues for free, use LLMs only for judgment calls and integration testing.
## What's intentionally not here