Skip to content

biff, bottom, jnv, ninja, yazi, ut, jaq, prek, uv: type /usr/bin executables as OutputBin - #1410

Merged
bryan-minimal merged 4 commits into
mainfrom
bin-output-types
Nov 11, 2026
Merged

bryan-minimal merged 4 commits into
mainfrom
bin-output-types

Conversation

@bryan-minimal

Copy link
Copy Markdown
Member

Nine packages shipped their /usr/bin executable under an OutputLib-typed output. They are now OutputBin, and each package has a minimal smoke test.

package output smoke test test_deps
biff biff (usr/bin/biff) existing smoketest (biff --version) [bash-bootstrap] (unchanged)
bottom btm (usr/bin/btm) existing smoketest (btm --version) [bash-bootstrap] (unchanged)
jnv jnv (usr/bin/jnv) existing smoketest (jnv --version) [bash-bootstrap] (unchanged)
ninja ninja (usr/bin/ninja) new standaloneTest "/usr/bin/ninja --version" none
ut ut (usr/bin/ut) new standaloneTest "/usr/bin/ut --help" (--version is not a flag: exit 2) none
yazi yazi (usr/bin/yazi) new standaloneTest "/usr/bin/yazi --version" none
jaq jaq (usr/bin/jaq) existing smoketest + filtering filtering: [base] → [bash-bootstrap, grep]
prek prek (usr/bin/prek) existing store_from_runtime_deps + system_ca_default [base] → [bash-bootstrap]; [base, git] → [bash-bootstrap, git, coreutils, grep]
uv minimal (usr/bin/uv) existing system_certs [base, ca-certificates] → [bash-bootstrap, ca-certificates, coreutils, grep]

jaq, prek and uv are the same mis-typing, found by grepping for usr/bin/* globs typed OutputLib. Their base test deps were moved here, not into the minimal-test_deps batches (#1404–#1409), so the two sets of PRs don't touch the same files.

The new tests use standaloneTest, which execs the binary directly with no shell and no test_deps. That is a smaller closure than [bash-bootstrap]. The text is identical to what #1378 adds for ninja, ut and yazi, so the two PRs' test hunks match. Line 1 (the minimal.ncl destructure) still conflicts with #1378, and whichever merges second needs a trivial rebase.

prek's comment on store_from_runtime_deps said "[base] plus prek's runtime closure has no needs.internet package". It now says [bash-bootstrap]. The argument is unchanged, because bash-bootstrap's only runtime_dep is glibc.

Spec hash: these packages REBUILD

The output type is part of outputs, which is in the spec hash. Unlike a test-only change, this PR rebuilds every package it touches:

  • biff, bottom, jnv, jaq, prek, ut, yazi: leaf packages with no importers. Each rebuilds once.
  • uv: rebuilds, along with its 2 importers (diffoscope, httpie).
  • ninja: a large cascade. ninja is a build dep of 57 packages (mesa, libpsl, meson-python, xorgproto, rizin, zig, …), so all of them and their dependents rebuild. ninja is in its own commit (the second one) so it can be dropped or split out if that cascade should wait.

Not changed, but the same pattern: coreutils, binutils, xz and diffutils type usr/bin/**/* as OutputLib, and zstd types its usr/bin/zstd* entries that way. All of them are toolchain-level, so changing them would rebuild the world. Left for a deliberate base-soup bundle.

Smoke tests are expected to pass. A failure (exit 127, or a missing library) would mean an undeclared runtime_dep, which gets fixed in a follow-up commit.

🤖 Generated with Claude Code

bryan-minimal and others added 2 commits November 8, 2026 13:29
… as OutputBin

Each shipped its executable under an OutputLib output. ut and yazi gain a
smoke test (standaloneTest, no test_deps); jaq, prek and uv tests drop `base`
for bash-bootstrap plus the tools their scripts call. The output type is part
of the spec hash, so these packages rebuild.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Kept as its own commit: ninja is a build dep of 57 packages, so changing its
output type (part of the spec hash) rebuilds all of them and their dependents.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
@bryan-minimal
bryan-minimal requested a review from a team as a code owner November 8, 2026 21:29
@coderabbitai

coderabbitai Bot commented Nov 8, 2026 •

Copy link
Copy Markdown
Contributor

Warning

Review limit reached

  • Run on-demand review

This review includes 11 billable files and costs up to $2.75.

  • 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.

Or wait 53 minutes for your next included review.

Check out review usage here.

View limit details

Limit details: You’ve used all 3 included reviews currently available. Your 49 included PR review attempts over the past 7 days set your current allowance at 3 reviews per hour.

Learn how review limits work.

Review configuration:

Run configuration

Commits

Reviewing files that changed from the base of the PR and between 103b8ba and dd00515.

Files selected for processing: 11

  • packages/biff/build.ncl
  • packages/bottom/build.ncl
  • packages/jaq/build.ncl
  • packages/jnv/build.ncl
  • packages/ninja/build.ncl
  • packages/prek/build.ncl
  • packages/ut/build.ncl
  • packages/uv/build.ncl
  • packages/uv/build.sh
  • packages/yazi/build.ncl
  • packages/yazi/build.sh
  • Autofix · Keep fixing CodeRabbit findings and required CI, and resolving merge conflicts

@agent-137 agent-137 left a comment

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

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

Review on Karl's behalf. This is a comment, not an approval. Nothing was built for it. The findings come from reading the declarations and fetching upstream sources, and each one says how it was checked. The CI rollup on this head is now FAILURE.

CI: every check is green except minimal build, which is red. The cause is mariadb on amd64: fmt-12.2.0.zip returned a 504 from github.com while mariadb was building. mariadb is in the rebuild because it depends on ninja. The diff did not cause this failure; a rerun should clear it. All 9 touched packages passed their standalone tests on arm64. The amd64 test column did not render, because the amd64 run aborted.

Should-fix: none.

Nit:

  • packages/yazi/build.sh:36 copies only target/release/yazi, and packages/uv/build.sh:69 copies only uv. Upstream's workspace builds should also produce ya (yazi-cli, a default member) and uvx (a second [[bin]] in crates/uv). If so, both are left in the build dir and never shipped. This is older than the PR, and the retyping is still complete for what the PR ships. Unverified: this comes from my knowledge of the upstream Cargo workspaces. I did not build or list target/release.

Checked:

  • All 9 retyped globs name only the file that build.sh installs (cp/install lines read for each package).
  • No non-executable output was retyped.
  • On the PR head, git grep for usr/bin globs still typed OutputLib finds only binutils, coreutils, diffutils, xz and zstd. The PR body names exactly these as deferred.
  • The import lines keep the lowercase-first order. base is still used in each package's build_deps.
  • The new standaloneTest lines match the house style (acl, age).
  • The reduced test_deps cover every command each test uses: prek uses mktemp and cat from coreutils; uv uses mktemp and mkdir; jaq uses grep.

bryan-minimal and others added 2 commits November 9, 2026 12:43
Both are already produced by the recipes' existing workspace build and were
left in target/release: uvx is crates/uv/src/bin/uvx.rs (auto-discovered;
only uvw is feature-gated) at uv 0.13.7, and ya is yazi-cli, a
default-member of the yazi 26.9.1 workspace. Copy them, type them
OutputBin, and give each a --version standalone test (agent-137 on #1410).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
# Conflicts:
#	packages/ninja/build.ncl
#	packages/ut/build.ncl
#	packages/yazi/build.ncl

@agent-137 agent-137 left a comment

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

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

Approving at dd00515. CI is green and I have no open findings.

@bryan-minimal
bryan-minimal added this pull request to the merge queue Nov 11, 2026
Merged via the queue into main with commit 8b94f6a Nov 11, 2026
15 checks passed
@bryan-minimal
bryan-minimal deleted the bin-output-types branch November 11, 2026 08:34
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants