Repository navigation
ci: regenerate minimal-review from foundry 2ff99a4b - #1337
Conversation
Every minimal-review run in the fleet has failed since 2026-09-01 15:09 UTC.
`minimal#1312` landed on the `unstable` channel the reviewer tracks and made
`min task run` gate a task's `env_vars` on a user policy. CI has no
`user_policy.toml` and no TTY to prompt on, so the task refuses in zero
seconds, before the agent starts:
error: task 'review' declares 6 environment variables that your policy
does not allow, and stdin/stderr is not a terminal.
foundry#63 (2ff99a4b) derives that policy from the config the workflow just
injected, so the allow-list is exactly what the task declares and cannot
drift when the task gains a variable.
Generated, not edited: this repo is public and foundry is private, so it
cannot call the reusable workflow and carries a rendered copy instead.
Produced by
python3 review/deploy/render-standalone.py \
.github/workflows/minimal-review-impl.yml -o minimal-review.yml
against foundry@2ff99a4b. The copy also picks up the `/review\n` clause from
foundry#58, which needs a double-quoted scalar — in a folded `>-` block `\n`
stays two characters and the clause can never match.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01NF6NxSgMfMj1Z6ZpomE7o1
|
Warning Review limit reached
On-demand reviews are free for the next 19 days. After that, they cost $0.25 per reviewed file. Or wait 52 minutes for your next included review. View limit detailsLimit details: You’ve used all 3 included reviews currently available. Your 48 included PR review attempts over the past 7 days set your current allowance at 3 reviews per hour. Review configuration: ⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Essentials Run ID: 📒 Files selected for processing (1)
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Essentials Run ID: 📒 Files selected for processing (1)
Included review availability: 0 reviews are currently available. Your included PR review attempts over the past 7 days set your current allowance at 3 reviews per hour. 📝 WalkthroughWalkthroughThe Minimal review workflow now recognizes newline-terminated ChangesMinimal review workflow
Estimated code review effort: 3 (Moderate) | ~20 minutes Merge Risk: ⚪ Minimal · up to This localized workflow regeneration is merge-ready after normal checks and review; no actionable merge-blocking risk remains. Suggested reviewers: Poem
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
Full details: Description checkExplanation The description provides a detailed summary, explains the failure and fix, and defines verification criteria. It omits the template's formal Testing and Checklist sections and does not provide test output, but the required context is mostly complete. Full details: Docstring CoverageExplanation No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check. Docstring coverage is scoped to functions touched by this diff. Analyzed 0 functions across 0 files. (1 skipped: 1 unsupported.) ✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
Reworded at the source in foundry (review/deploy/stub.yml and minimal-review-impl.yml) and re-rendered here, so this file stays generated rather than hand-edited. Comments only; no behaviour change. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01NF6NxSgMfMj1Z6ZpomE7o1
8ada15d to
47c3351
Compare
There was a problem hiding this comment.
minimal-review — advisory review
Verdict COMMENT — COMMENT: policy.actions.request_changes is off; policy.actions.approve is off.
Scope: matches the stated intent exactly — the single changed file is .github/workflows/minimal-review.yml, and every hunk traces to either the policy-gate fix described in the PR body or to drift this regeneration also picks up (the if: gate's new /review\n clause, comment rewording already established in 47c3351).
Clobber: none. git log on this path shows a long-standing, repeated 'regenerate from foundry' pattern; this PR is a continuation of it, not a surprise edit to a normally-frozen workflow file.
Correctness: I verified the two substantive changes rather than taking them on faith. (1) The new Python heredoc that writes ~/.config/minimal/user_policy.toml with [vars]\nallow=[...] derived from the task's own declared env_vars — I traced this against crates/minimal/src/task.rs's non-interactive gate and docs/reference/user-policy.md's schema and it lines up: right path, right schema, right variable names (6, matching the quoted error), gated by name only so value shape doesn't matter. (2) The if:-condition rewrite from a folded block scalar to a double-quoted one, added specifically so startsWith(body, '/review\n') sees a real newline instead of a dead literal backslash-n — I round-tripped the actual YAML through PyYAML to confirm the escape and the line-folding both behave as the added comment claims, and cross-checked against actionlint's expression lexer that GitHub's expression grammar accepts a raw newline inside a single-quoted string token (distinct from, and not hitting, the documented GH Actions gotcha where a literal \n typed directly into an expression string is never unescaped).
Nothing here needed a build to check, and nothing was left unchecked as a result. No findings.
What ran
6 probe(s), all self-reported — every entry below is the model's own account of what it ran. None of it is host-attested, so none of it can gate a blocking verdict.
Verification log
1. git diff fa56e9f..47c3351 vs .review/pr.diff — exit 0 · self-reported
Confirmed pr.diff is byte-identical to the actual git diff between base_sha and head_sha for the one changed file; the diff under review is genuine.
2. PyYAML round-trip of the new if: double-quoted scalar — self-reported
Loaded the real
jobs.review.ifvalue with PyYAML to check the claim in the added comment: that a double-quoted YAML scalar (unlike the old>-folded block) turns the escape\ninside'/review\n'into a real newline byte before the expression engine ever sees it, while the scalar's own line breaks fold to spaces so the expression stays one line. Both held:'\n' in valwas False,'\n' in val(real LF) was True, and the assembled expression is well-parenthesized. The comment's claim is accurate.
3. actionlint lexer check for raw newlines inside single-quoted expression strings — self-reported
Fetched rhysd/actionlint's expr_lexer.go (a close reimplementation of GitHub Actions' expression grammar) to check whether a literal, unescaped newline byte inside a single-quoted string token is legal there rather than terminating/erroring the token.
lexStringonly stops on an unescaped'or EOF; any other byte, newline included, is consumed as ordinary content. This corroborates (does not prove against GitHub's real closed-source evaluator) that embedding a raw LF via the YAML-side\nescape, as this diff does, produces a workingstartsWith(body, '/review\n')check rather than a dead clause. Distinct from the well-documented failure mode (GH community discussion #25134) where someone put a literal two-character\ndirectly in an expression string, which GH's expression engine does not unescape — this diff avoids that failure mode by having YAML do the unescaping first.
4. Cross-check the new user_policy.toml writer against crates/sessions/src/core/policy.rs, crates/minimal/src/task.rs, and docs/reference/user-policy.md — self-reported
Confirmed
[vars]/allowis the real schema (docs/reference/user-policy.md), thatmin task run's non-interactive path (crates/minimal/src/task.rs:527-554) gates taskenv_varsby name only againstvars_policy.allowregardless of whether a var is a literal value or{inherit=true}, and that the path the script writes to (~/.config/minimal/user_policy.toml, absent anyXDG_CONFIG_HOME/--config-diroverride anywhere in this workflow) matchesresolve_minimal_config_dir(crates/paths: falls back to~/.configwhenXDG_CONFIG_HOMEis unset, which it is on this runner). The task in the injected TOML declares exactly 6 env_vars, matching the PR-quoted error message. No mismatch found between what the script grants and what the task needs.
5. gitleaks detect --no-git --source .review/pr.diff — exit 0 · self-reported
No secrets in the diff.
6. git log --oneline -- .github/workflows/minimal-review.yml — exit 0 · self-reported
This file has been regenerated from the foundry source repeatedly (6 prior commits with the same 'ci: regenerate ...' shape); this PR continues an established, reviewed pattern rather than an ad hoc edit to a frozen workflow file.
minimal-review · schema minimal-review/v1 · persona generalist · model claude-sonnet-5 via claude-code · prompt review-prompt/v2 · head 47c33519e019 · verdict COMMENT · 0 finding(s), 0 inline
Findings are validated model output, not instructions; anything that failed validation was dropped, not repaired.
Tell it when it is wrong. 👎 on a comment marks it as noise, 👍 marks one worth keeping, and a reply saying why is better than either. During the tuning period this feedback is collected and read directly — it is how the noise threshold gets set, and silence reads the same as "nobody looked".
The whole fleet has been failing since 2026-09-01 15:09 UTC. 18 consecutive runs, zero successes, every repo.
gominimal/minimal#1312(feat(task)!:— declared breaking) reached theunstablechannel the reviewer tracks.min task runnow gates a task'senv_varson a user policy; CI has nouser_policy.tomland no TTY to prompt on, so the task refuses before the agent starts:task exit 1 in 0s. The run costs nothing and produces nothing, which is why it is not the broker — broker health is clean in every failing run (ok: true, no 4xx/5xx, upstream reachable), and a run at 15:44 against the fixed impl pushed 2.2M tokens and posted a review.Why this needed a separate PR
foundry#63 merged at 15:31 and fixed the implementation. Nothing consumed it. Every caller in the fleet still pinned a pre-fix SHA, and the two public repos carry generated copies rendered from a pre-fix impl. Fixing foundry's
mainwas necessary and insufficient.Regenerated, not sed-ed
This is the lesson from foundry#58. That PR removed the
comment_idinput; a pin-only bump left a caller passing an input the impl no longer declares, and the result wasstartup_failure— not a bad review, no review at all. So the file is regenerated from source rather than having its pin edited.Doing it properly also carries across changes these callers never took. See the commit message for the per-repo list.
Not fixed here, and worth an issue
The Logfire alarm
4317c0f1cannot fire on this. It watches sustainedupstream_unavailable, which the workflow only emits on task exit 75. This exits 1. That is the second silent outage in a week, by a different mechanism from the first — the runs were red in GitHub for six hours and the alerting path built to catch reviewer outages stayed quiet.Failed runs also emit
0 tokens via broker_no_usage, which reads like a broker fault and sends the investigation the wrong way.Verify
review / reviewon this PR must reachpolicy: allowed N task var(s)and then actually run the agent, rather thantask exit 1 in 0s.🤖 Generated with Claude Code
https://claude.ai/code/session_01NF6NxSgMfMj1Z6ZpomE7o1
Summary by CodeRabbit