diff --git a/.gitea/workflows/release.yml b/.gitea/workflows/release.yml index 821ed8f..f59fbac 100644 --- a/.gitea/workflows/release.yml +++ b/.gitea/workflows/release.yml @@ -176,6 +176,39 @@ jobs: fi fi + # ── Orphan sweep ──────────────────────────────────────────────── + # + # The check above is VERSION-SCOPED: it only ever asks about the one + # version this run computed. That is enough to recover an orphan on + # the very next run, and useless afterwards — once any releasable + # commit lands, the next run computes a NEW version, never looks at + # the old tag again, and the orphan becomes permanent and silent. + # + # servuo-plugins v0.1.0 is the proof, and the proof is pointed: the + # commit that ADDED the recovery above was itself typed + # `fix(release): ... recover the orphaned v0.1.0 tag`, so it bumped to + # v0.1.1 — and the run that introduced the recovery stepped straight + # past the tag it was written to rescue. That tag is still orphaned. + # + # So every v* tag is checked, and anything missing a release is + # WARNED about. Deliberately not recovered: publishing an old version + # would mean building today's tree and shipping it under a tag whose + # tree it is not, which is worse than the inconsistency it fixes. + # A human decides whether to recover or drop it. + # + # Never fails the run. A sweep that can break a good release is a + # sweep someone will delete. + ORPHANS="" + for T in $(git tag -l 'v*' --sort=-v:refname); do + T_HTTP="$(curl -s -o /dev/null -w '%{http_code}' \ + -H "Authorization: token $(printf '%s' "${REGISTRY_TOKEN:-}" | tr -d '\r\n')" \ + "https://${GITEA_HOST}/api/v1/repos/${REPO}/releases/tags/${T}" || echo 000)" + [ "$T_HTTP" = "404" ] && ORPHANS="${ORPHANS} ${T}" + done + if [ -n "${ORPHANS}" ]; then + echo "::warning::Tags with no release:${ORPHANS} — a run failed after tagging. Publish or delete them; this job will not do either." + fi + # Changelog range. A recovery run has nothing after the tag, so # summarize what the tag itself contains rather than emitting an empty # list: the range that produced it, i.e. previous-tag..this-tag. @@ -477,18 +510,73 @@ jobs: # corrupt the Authorization header. CI_TOKEN="$(printf '%s' "${REGISTRY_TOKEN}" | tr -d '\r\n')" - REL_ID="$(curl -sSf -X POST "${API}/releases" \ - -H "Authorization: token ${CI_TOKEN}" \ - -H "Content-Type: application/json" \ - -d "$(jq -n --arg tag "$TAG" --arg body "$BODY" \ - '{tag_name:$tag, name:$tag, body:$body, draft:false, prerelease:false}')" \ - | jq -r '.id')" + PAYLOAD="$(jq -n --arg tag "$TAG" --arg body "$BODY" \ + '{tag_name:$tag, name:$tag, body:$body, draft:false, prerelease:false}')" + + # installer#22's release run failed exactly here: it landed one second + # after the tag push and Gitea answered 500, having not finished + # processing the pushed tag. Re-running published the same artifacts + # untouched, so it was a race, not a bad request — but the tag sat + # orphaned until a human noticed. + # + # Two things made that worse than it needed to be. + # + # 1. `curl -sSf` prints NO response body on an error status, so all the + # log carried was "curl: (22) ... error: 500" and the cause had to be + # inferred from timestamps. Capture the body and print it. + # 2. Nothing retried, so a transient 5xx became a permanent orphan. + # + # 4xx is deliberately NOT retried: a bad token or a malformed body does + # not improve by being sent again, and retrying only turns a clear + # failure into a slow one. + REL_ID="" + for attempt in 1 2 3 4 5; do + HTTP="$(curl -s -o /tmp/rel.json -w '%{http_code}' -X POST "${API}/releases" \ + -H "Authorization: token ${CI_TOKEN}" \ + -H "Content-Type: application/json" \ + -d "${PAYLOAD}" || echo 000)" + + if [ "$HTTP" = "201" ] || [ "$HTTP" = "200" ]; then + REL_ID="$(jq -r '.id' /tmp/rel.json)" + break + fi + + echo "::warning::POST /releases attempt ${attempt} returned HTTP ${HTTP}" + echo "--- response body ---" + cat /tmp/rel.json || true + echo + echo "---------------------" + + case "$HTTP" in + 4*) echo "::error::HTTP ${HTTP} is a client error - not retrying."; exit 1 ;; + esac + + if [ "$attempt" = 5 ]; then + echo "::error::POST /releases still failing after 5 attempts. Tag ${TAG} is pushed but has no release." + echo "::error::Re-run this workflow - the plan step detects the orphan tag and republishes it." + exit 1 + fi + sleep $(( attempt * 5 )) + done + + if [ -z "$REL_ID" ] || [ "$REL_ID" = "null" ]; then + echo "::error::Release created but no id came back; refusing to upload assets blind." + exit 1 + fi echo "Created release ${TAG} (id=${REL_ID})" for f in "${TARBALL}" SHA256SUMS; do - curl -sSf -X POST "${API}/releases/${REL_ID}/assets?name=${f}" \ + # Same treatment. An upload that fails quietly leaves a release whose + # SHA256SUMS does not cover every artifact it advertises, which is + # worse than no release at all -- that file is the trust anchor. + HTTP="$(curl -s -o /tmp/asset.json -w '%{http_code}' -X POST "${API}/releases/${REL_ID}/assets?name=${f}" \ -H "Authorization: token ${CI_TOKEN}" \ - -F "attachment=@dist/${f}" >/dev/null + -F "attachment=@dist/${f}" || echo 000)" + if [ "$HTTP" != "201" ] && [ "$HTTP" != "200" ]; then + echo "::error::uploading ${f} returned HTTP ${HTTP}" + cat /tmp/asset.json || true + exit 1 + fi echo " uploaded ${f}" done