* v1.91.68.0 fix(cso-eval): failed receipts with usage for post-run integrity failures; Claude producers stop mutating the sealed source
Claude Code adds <dir>/.mcp.json as a sandbox deny path for every --add-dir.
The producer passed the sealed source as one, so bubblewrap left an empty
0444 .mcp.json mount point there that Claude Code cannot unlink from the 0555
directory, and the post-run source check failed with no receipt.
- claudeExecArgs no longer adds the source directory
- post-run integrity failures write status:failed receipts carrying the
check code/reason plus usage, tokens and estimated cost (no output or
artifacts)
- INVALID_PRODUCER_SOURCE / PRODUCER_CHANGED_SOURCE_MODE name the first
offending relative path and the rule it broke
* fix(cso-eval): run the trusted launcher outside Claude's sandbox; keep every other command sandboxed
Claude Code 2.1.263 forces every Bash command into its bubblewrap sandbox
while CLAUDE_CODE_SUBPROCESS_ENV_SCRUB is set, excludedCommands
notwithstanding. Inside it the launcher's owner check sees root as nobody
and the Docker socket is unreachable, so comprehensive cells degraded to
static-only results.
- drop CLAUDE_CODE_SUBPROCESS_ENV_SCRUB for producers; pass --settings with
sandbox enabled, failIfUnavailable, no unsandboxed fallback, no
auto-allow, and excludedCommands naming only the exact launcher path
- ClaudeAdapter.run refuses to start the agent
(CLAUDE_PRODUCER_SANDBOX_POLICY_MISMATCH) unless args and env carry
exactly that policy
- README containment note and CHANGELOG updated
* test(doctor): split the two multi-run doctor tests so each fits Windows' 30s per-test budget
On windows-latest each bin/gstack-doctor run costs ~4-5s. The cached/live probe test made 7 runs and the artifacts-sync test 5; both hit the 30s per-test timeout, which killed doctor mid-output ("no row codex probe") and then EBUSY on cleanup. Same failure on #3093 and the fix/runtime-root-source-guard PR. Every assertion is kept; each test now makes at most 4 runs.
1.7 KiB
gstack digest v1.91.68.0 — 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:
- A helper, util, or pattern already in this repo.
- The standard library.
- A native platform feature (CSS over JS, DB constraint over app code).
- 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.