CalvinBackup/gstack
1
0
Fork 0
mirror of https://github.com/garrytan/gstack.git synced 2026-07-06 16:17:56 +02:00
Code Issues Packages Projects Releases Wiki Activity

docs: wire detached-eval guidance into /ship + correct CLAUDE.md flags

Browse Source 
- /ship eval step (sections/tests.md): long eval suites launch via gstack-detach
  (own session, machine lock, EXIT sentinel) so a turn boundary can't kill a
  30+ min run mid-ship — the exact failure observed during this branch's ship.
- CLAUDE.md: correct the now-stale /tmp reference; document the --lock (serialize
  worktrees, no API saturation), --timeout watchdog, run-scoped log, and the
  guaranteed EXIT sentinel the poller breaks on.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Garry Tan
2026-06-12 06:24:39 -07:00
parent 6eea549121
commit a38089aac6
3 changed files with 45 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ship/sections/tests.md
+16
View File
@@ -332,6 +332,22 @@ EVAL_JUDGE_TIER=full EVAL_VERBOSE=1 bin/test-lane --eval test/evals/<suite>_eval
If multiple suites need to run, run them sequentially (each needs a test lane). If the first suite fails, stop immediately — don't burn API cost on remaining suites.
**Long eval suites (30+ min): launch detached so a turn boundary can't kill them.**
A plain backgrounded eval lives in the harness's process group and dies to a
SIGTERM ("polite quit") on a turn boundary, a stopped monitor, or an interruption
(observed mid-`/ship`: `script terminated by signal SIGTERM`). Run it through
`~/.claude/skills/gstack/bin/gstack-detach` instead — it survives in its own
session, serializes against other worktrees via a machine lock (no API
saturation), and writes a guaranteed `### gstack-detach EXIT=<code> ###` sentinel:
```bash
~/.claude/skills/gstack/bin/gstack-detach --label ship-evals --lock gstack-evals --timeout 5400 -- <project eval command>
```
Then poll the printed log path; break on the `EXIT=` sentinel (covers both pass
and crash — silence is never success). The detached run survives even if your
poller is reaped.
**4. Check results:**
- **If any eval fails:** Show the failures, the cost dashboard, and **STOP**. Do not proceed.
ship/sections/tests.md.tmpl
+16
View File
@@ -76,6 +76,22 @@ EVAL_JUDGE_TIER=full EVAL_VERBOSE=1 bin/test-lane --eval test/evals/<suite>_eval
If multiple suites need to run, run them sequentially (each needs a test lane). If the first suite fails, stop immediately — don't burn API cost on remaining suites.
**Long eval suites (30+ min): launch detached so a turn boundary can't kill them.**
A plain backgrounded eval lives in the harness's process group and dies to a
SIGTERM ("polite quit") on a turn boundary, a stopped monitor, or an interruption
(observed mid-`/ship`: `script terminated by signal SIGTERM`). Run it through
`~/.claude/skills/gstack/bin/gstack-detach` instead — it survives in its own
session, serializes against other worktrees via a machine lock (no API
saturation), and writes a guaranteed `### gstack-detach EXIT=<code> ###` sentinel:
```bash
~/.claude/skills/gstack/bin/gstack-detach --label ship-evals --lock gstack-evals --timeout 5400 -- <project eval command>
```
Then poll the printed log path; break on the `EXIT=` sentinel (covers both pass
and crash — silence is never success). The detached run survives even if your
poller is reaped.
**4. Check results:**
- **If any eval fails:** Show the failures, the cost dashboard, and **STOP**. Do not proceed.