diff options
Diffstat (limited to '.github/workflows/ai-validation.yml')
| -rw-r--r-- | .github/workflows/ai-validation.yml | 76 |
1 files changed, 42 insertions, 34 deletions
diff --git a/.github/workflows/ai-validation.yml b/.github/workflows/ai-validation.yml index d7d93c37..3d77ec08 100644 --- a/.github/workflows/ai-validation.yml +++ b/.github/workflows/ai-validation.yml @@ -49,6 +49,14 @@ jobs: runs-on: ubuntu-latest permissions: contents: read + outputs: + # Surface whether the PR touched any docs/**/*.md so validate's review + # steps can skip on infrastructure-only PRs (workflow/config/README + # changes). actions/upload-artifact silently omits empty directories + # — when no .md files change, _changed_md/ isn't uploaded, and + # validate's working-directory: _changed_md would otherwise fail + # before any in-step short-circuit can run. + has_md_changes: ${{ steps.changes.outputs.has_md_changes }} steps: - name: Checkout PR merge ref (NO credentials) uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 @@ -58,10 +66,13 @@ jobs: fetch-depth: 2 - name: Compute changed files and bundle .md content + id: changes run: | set -euo pipefail - git fetch --depth=1 origin "${{ github.event.pull_request.base.ref }}" - BASE="origin/${{ github.event.pull_request.base.ref }}" + # Fetch the base branch explicitly by refname to avoid ambiguity with + # same-named tags (e.g., a `rolling` tag), then diff against FETCH_HEAD. + git fetch --no-tags --depth=1 origin "refs/heads/${{ github.event.pull_request.base.ref }}" + BASE="FETCH_HEAD" # --diff-filter=ACMRT excludes Deleted entries so the bundling # loop below (`git show HEAD:<path>`) doesn't try to extract # blobs for files that no longer exist in the merge ref. @@ -69,30 +80,6 @@ jobs: # in changed-md.txt (which drives the bundling step). git diff "$BASE...HEAD" --name-only --diff-filter=ACMRT -z -- 'docs/**/*.md' > changed-md.z git diff "$BASE...HEAD" --name-only --diff-filter=ACMRT -z -- 'docs/**/*.rst' > changed-rst.z - # Reject paths containing line-disrupting control bytes (LF, CR, - # other 0x01-0x1F + 0x7F) before generating the newline-delimited - # *.txt manifests. NUL itself can't appear in a git pathname - # (it's the on-disk tree-entry terminator), so it stays out of - # the rejection class and remains the legitimate record delimiter - # for `git diff -z` — `grep -z` honors that contract. - # - # POSIX filesystems generally allow LF/CR in filenames and git - # stores them fine; the hazard is purely in our line-delimited - # downstream tooling. Without this guard, `tr '\0' '\n'` on a - # path like `docs/foo\nbar.md` would split it into two logical - # lines — downstream consumers reading line-by-line would miss - # validation coverage on the real file (or worse, act on a - # synthetic path). Fail fast at this seam. - # - # An earlier `tr -d '\0\n\r' | grep [\x00-\x1F\x7F]` form - # stripped the very bytes it was meant to reject before the - # grep ran — defeating the guard. - for z in changed-md.z changed-rst.z; do - if LC_ALL=C grep -zPq '[\x01-\x1F\x7F]' "$z"; then - echo "::error::Refusing to bundle: path in $z contains a control character. Reject the offending file name in the PR." - exit 1 - fi - done tr '\0' '\n' < changed-md.z > changed-md.txt tr '\0' '\n' < changed-rst.z > changed-rst.txt git diff "$BASE...HEAD" -- 'docs/**/*.md' > diff-md.patch @@ -146,6 +133,17 @@ jobs: git show "HEAD:$path" > "_changed_md/$path" done < changed-md.z + # Use diff-md.patch (unfiltered git diff) rather than changed-md.txt + # (--diff-filter=ACMRT) so deletion-only PRs still trigger validate. + # Pass 1 reviews the diff, not just the post-image files in + # _changed_md/, so deletes are legitimate review targets even though + # they produce no entries in _changed_md/. + if [ -s diff-md.patch ]; then + echo "has_md_changes=true" >> "$GITHUB_OUTPUT" + else + echo "has_md_changes=false" >> "$GITHUB_OUTPUT" + fi + - name: Upload PR input artifact uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2 with: @@ -158,6 +156,11 @@ jobs: validate: needs: [prepare] + # Skip the entire job on infrastructure-only PRs. Otherwise the + # expensive setup chain (artifact download, GitHub App token, reviewer + # checkout/install, reference-DB download/extract, uv setup) runs even + # though Pass 1 + Pass 2 are guaranteed to no-op. + if: needs.prepare.outputs.has_md_changes == 'true' runs-on: ubuntu-latest permissions: contents: read @@ -209,6 +212,16 @@ jobs: with: name: pr-input + - name: Ensure _changed_md exists (handles deletion-only PRs) + if: steps.secrets-check.outputs.skip != 'true' + # actions/upload-artifact silently omits empty directories. On a + # deletion-only PR, prepare's _changed_md/ holds no files and never + # makes it across the artifact boundary — Pass 1's + # working-directory: _changed_md would then fail. Recreate the + # directory unconditionally; Pass 1 still operates on the diff + # via --pr-diff ../diff-md.patch, which is the source of truth. + run: mkdir -p _changed_md + - name: Generate GitHub App token if: steps.secrets-check.outputs.skip != 'true' id: app @@ -218,11 +231,6 @@ jobs: private-key: ${{ secrets.VYOS_APP_PRIVATE_KEY }} owner: VyOS-Networks repositories: vyos-1x,vyos-docs-opus-reviewer - # Token is used only for read-only operations: sparse-checkout - # of branches.json from the reviewer repo, full checkout of - # vyos-1x, and download of the reference-DB release asset. No - # write back to either repo. Scope the App token accordingly. - permission-contents: read - name: Sparse-checkout branches.json from reviewer if: steps.secrets-check.outputs.skip != 'true' @@ -277,9 +285,9 @@ jobs: with: repository: VyOS-Networks/vyos-docs-opus-reviewer # Pin the DB to the same release tag as REVIEWER_REF so a future - # reviewer-v1.x.x release with a schema change can't be silently - # picked up while the pinned reviewer code still expects the - # old schema. Reproducibility > recency for this artifact. + # reviewer-v1.x.x release with a schema change cannot be silently + # picked up while the pinned reviewer code still expects the old + # schema. Reproducibility > recency for this artifact. tag: ${{ env.REVIEWER_REF }} fileName: reference-db-${{ steps.branch.outputs.vyos1x }}.tar.gz out-file-path: .reference-db |