Skip to content

chore(minimal-toml): declare fmt and verify for the agent runtime - #1542

Merged
norrietaylor merged 1 commit into
mainfrom
chore/agent-fmt-verify-tasks
Sep 18, 2026
Merged

norrietaylor merged 1 commit into
mainfrom
chore/agent-fmt-verify-tasks

Conversation

@norrietaylor

Copy link
Copy Markdown
Member

Preflight for dispatching #1437 and #1501 through the agent runtime.

The runtime runs a repository's own [tasks.fmt] on the coder's changed files and amends the result into its last commit (runner/runner/jobs/implement.py, run_fmt), and its own [tasks.verify] in a fresh clone at the pushed sha. This repository declared neither:

  • with no fmt task, an agent pull request lands red on CI's fmt job for whitespace, and that costs a full revise round — a coder pass plus a 20-minute CI cycle — per PR;
  • with no verify task, the runtime falls back to the plan survey's one test line, just test-one, which takes a filter and has none to run.

Two details that are not style choices:

  • bash = , not exec = . The runner reads spec["bash"] and treats a spec without a string there as "no fmt task".
  • verify is rustfmt alone. It runs under the job's probe budget, 600 s, and a cold cargo clippy --all-targets on this workspace does not fit in that. Each task's own test: lines already compile the crate they touch, and the five required lanes are where the real verification happens.

Nothing here changes what a human runs: just fmt and just fmt-check are untouched, and the new tasks sit beside them for min task run.

🤖 Generated with Claude Code

The runtime runs a repository's own `[tasks.fmt]` on the coder's files and
amends the result into its last commit, and its own `[tasks.verify]` in a
fresh clone at the pushed sha. This repository declared neither, so an agent
pull request landed red on CI's `fmt` job for whitespace, and verify fell back
to the plan survey's `just test-one`, which has no filter to run.

`bash = ` rather than `exec = `: the runner reads `spec["bash"]` and treats
anything else as "no fmt task".

Verify is rustfmt alone on purpose. It runs under the job's probe budget of
ten minutes, and a cold `cargo clippy --all-targets` on this workspace does not
fit in that; each task's own test lines already compile the crate they touch,
and CI is where the full lanes run.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
@norrietaylor
norrietaylor requested a review from a team as a code owner September 18, 2026 07:41
@coderabbitai

coderabbitai Bot commented Sep 18, 2026

Copy link
Copy Markdown
Contributor

Warning

Review paused — included plan limit reached

Keep your review moving with free on-demand reviews.

  • Run this review for free

On-demand reviews are free for the next 2 days.

  • Ask an admin to make reviews automatic

Open in CodeRabbit

Reviews can continue after your included limit without a manual trigger. An admin must approve usage-based billing.

Promotion and pricing details

On-demand reviews are free for the next 2 days. After that, they cost $0.25 per reviewed file.

Review limit details

Or wait 48 minutes for your next included review.

Check out review usage here.

Limit details: You’ve used all 2 included reviews currently available.

Learn how review limits work.

Review configuration:

⚙️ Run configuration

Configuration used: Organization UI

Review profile: CHILL

Plan: Essentials

Run ID: 43c5c9b0-06c3-4554-bad0-b581ab2c421f

📥 Commits

Reviewing files that changed from the base of the PR and between cb384e3 and 4b42017.

📒 Files selected for processing (1)
  • .minimal/minimal.toml

Comment @coderabbitai help to get the list of available commands.

@minimal-foundry minimal-foundry Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

minimal-review — approved

Verdict APPROVE — APPROVE: all personas completed and nothing survives above severity 'nit' (0 finding(s) kept).

Scope matches the title: 27 added lines, exactly the two new task blocks ([tasks.fmt], [tasks.verify]), nothing else touched. Clobber none: git log -- .minimal/minimal.toml shows the file's last change is this PR's own commit; nothing reverted.

Correctness no findings. Both new commands are byte-identical to commands already proven in CI: just fmt is cargo fmt --all (justfile:265) and just fmt-check is cargo fmt --all -- --check (justfile:282, the ci.yml fmt gate), so the fmt/verify pair is exactly the repo's canonical fixer/checker. The field choices parse cleanly against the task schema (crates/mfile/src/tasks.rs): bash = maps to TaskAction::Bash(String) and is already used by [tasks.ci]/[tasks.mutants] in this same file; description and inherit_cwd are valid Task fields. The bash-not-exec invariant and the just test-one fallback claim are consistent with what is checkable here (the justfile's test-one does require a positional filter), though the runtime contract itself (runner/runner/jobs/implement.py) lives in a different repo and was not verifiable. The comments are verbose and reference that out-of-repo runtime, but they document a load-bearing invariant and match this file's existing why-comment style, so not worth a finding.

Secrets none in the diff. A gitleaks scan flags two generic-api-key hits in env_vars.ANTHROPIC_AUTH_TOKEN / env_vars.MODEL_TOKEN, but those lines are in the [tasks.runtime-review] block that the review harness injects into the local working tree — absent from both the base and head commits, so not part of this PR. Not checked (would need a build): nothing; both commands are proven in CI. The change is clean.

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 log --oneline -12 -- .minimal/minimal.toml — exit 0 · self-reported

Last change to the file is the PR's own commit 4b42017; prior commits (patch source anchor, profiles removal) are unrelated. No revert of recent work.

2. sed -n '258,290p' justfile; rg -n 'cargo fmt' justfile — exit 0 · self-reported

just fmt = cargo fmt --all and just fmt-check = cargo fmt --all -- --check, byte-identical to the new [tasks.fmt] and [tasks.verify] commands respectively; both are CI-proven.

3. read crates/mfile/src/tasks.rs — exit 0 · self-reported

Task struct accepts bash (TaskAction::Bash(String)), description, and inherit_cwd; same fields already used by [tasks.ci] and [tasks.mutants] in the same file. New blocks parse cleanly.

4. sed -n '365,368p' justfile — exit 0 · self-reported

test-one filter *args requires a positional filter, supporting the PR's claim that the runtime's fallback to just test-one has no filter to run.

5. gitleaks detect --no-git --source . --report-format json — exit 0 · self-reported

2 generic-api-key hits at .minimal/minimal.toml:134/139 (ANTHROPIC_AUTH_TOKEN / MODEL_TOKEN), both in the [tasks.runtime-review] block that exists only in the local working tree, not in base cb384e3 or head 4b42017. Outside the PR diff; not a finding.

6. git status --short; git diff HEAD --stat; git show 4b42017 --stat — exit 0 · self-reported

PR itself is 27 insertions in one file; the extra 51 working-tree lines are the harness-injected [tasks.runtime-review] task, absent from both base and head.


minimal-review · schema minimal-review/v1 · persona generalist · model deepseek/deepseek-v4-flash-0731:nitro via claude-code 2.1.233 · prompt review-prompt/v2 · head 4b42017b276a · verdict APPROVE · 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".

@norrietaylor
norrietaylor merged commit 7b6f6d2 into main Sep 18, 2026
33 checks passed
@norrietaylor
norrietaylor deleted the chore/agent-fmt-verify-tasks branch September 18, 2026 19:37
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

review:approved minimal-review approved the current head

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants