ceremony/test/labels-dispatch.test.sh

189 lines
8.4 KiB
Bash
Raw Permalink Normal View History

fix(labels): wake the sweep over REST, so board events reconcile in seconds `.github/workflows/labels.yml` dispatched the sweep with `gh workflow run`, the eighth runtime gh call site the 0.6.0 merge reintroduced and the only one !204 did not port. On this forge the runner carries neither gh nor a GitHub API, so the step refused and the entire event-driven reconcile path ended there — every transition waiting up to an hour for the scheduled sweep. The workflow-dispatch endpoint has the SAME shape on both forges: POST {api}/repos/{owner}/{repo}/actions/workflows/{file}/dispatches {"ref": "<branch>", "inputs": {...}} -> 204, empty body so the step no longer decides a forge at all. The CEREMONY_FORGE_CLIENT=gh declaration and both inline refusals are removed rather than ported, and test/no-runtime-gh.test.sh now asserts their ABSENCE — an opt-out with no gh behind it is a standing permission slip. The ref is supplied explicitly and taken from the repository, never from GITHUB_REF_NAME: on a pull_request_target run that is `<n>/merge`, which is not a branch. A non-204 still fails the job, keeping the misconfiguration alarm the trigger exists to be, and the diagnostic explains Forgejo's empty 500 rather than passing a bare status to a reader who will go looking for an outage that is not there. test/labels-dispatch.test.sh extracts the shipped step and executes it against a recording stub, asserting the method, endpoint, ref and inputs actually sent. Dropping the inputs or ignoring a non-204 both red the suite. Refs #205
2026-08-05 16:58:05 +00:00
#!/usr/bin/env bash
# The sweep dispatch in .github/workflows/labels.yml (#205).
#
# This EXTRACTS the shipped step's `run:` script and EXECUTES it against a
# recording stub, rather than grepping the YAML for strings. A grep here would
# pass on a step that assembles a perfect request and never sends it — the
# shape of defect this repo keeps finding in its own tests. So every case
# asserts on what the step actually sent, or on what it actually did when the
# forge refused.
set -uo pipefail
ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
# shellcheck source=test/harness.sh
. "$ROOT/test/harness.sh"
WORKFLOW="$ROOT/.github/workflows/labels.yml"
TMP="$(mktemp -d)"
trap 'rm -rf "${TMP:?}"' EXIT
# --- the step under test, taken from the shipped workflow --------------------
STEP="$TMP/step.sh"
{
printf '%s\n' '#!/usr/bin/env bash' 'set -e'
yq -r '.jobs.trigger.steps[] | select(.name == "dispatch the sweep") | .run' "$WORKFLOW"
} >"$STEP"
chmod +x "$STEP"
step_extracted() { [ "$(wc -l <"$STEP")" -ge 10 ]; }
check "the step's script was extracted from the shipped workflow" 0 "" step_extracted
# --- stubs -------------------------------------------------------------------
# `curl` records every invocation and answers with the code the case wants. It
# parses only what the step actually passes, so a step that stopped sending
# `-d`, or changed the method, fails here rather than recording nothing.
make_curl() { # make_curl <http-code> <body>
cat >"$TMP/bin/curl" <<STUB
#!/usr/bin/env bash
method=GET; data=; url=; out=; write=
while [ \$# -gt 0 ]; do
case "\$1" in
-X) method="\$2"; shift 2 ;;
-d) data="\$2"; shift 2 ;;
-o) out="\$2"; shift 2 ;;
-w) write="\$2"; shift 2 ;;
-H) printf '%s\n' "HEADER \$2" >>"$TMP/calls"; shift 2 ;;
-fsS|-sS|-s) shift ;;
*) url="\$1"; shift ;;
esac
done
printf '%s\n' "METHOD \$method" "URL \$url" "DATA \$data" >>"$TMP/calls"
# the default-branch read is a plain GET whose stdout the step pipes to jq
if [ "\$method" = GET ]; then printf '{"default_branch":"trunk"}'; exit 0; fi
[ -n "\$out" ] && printf '%s' '$2' >"\$out"
[ -n "\$write" ] && printf '%s' '$1'
exit 0
STUB
chmod +x "$TMP/bin/curl"
}
run_step() { # run_step <http-code> <body> [env assignments...]
local code="$1" body="$2"
shift 2
rm -rf "${TMP:?}/bin"
mkdir -p "$TMP/bin"
: >"$TMP/calls"
make_curl "$code" "$body"
env PATH="$TMP/bin:$PATH" \
GITHUB_TOKEN=tok \
GITHUB_API_URL=https://forge.example/api/v1 \
GITHUB_REPOSITORY=owner/repo \
SWEEP_WORKFLOW=self-labels-sweep.yml \
"$@" \
"$STEP"
}
sent() { grep -h "^$1 " "$TMP/calls" | tail -1 | cut -d' ' -f2-; }
sent_field() { jq -r "$1" <<<"$(sent DATA)"; }
# --- the success path --------------------------------------------------------
check "a 204 dispatch succeeds, naming what it woke and where" 0 \
"sweep dispatched — self-labels-sweep.yml on main" \
run_step 204 "" DEFAULT_BRANCH=main
posted() { [ "$(sent METHOD)" = POST ]; }
check "...by POST, not GET" 0 "" posted
right_endpoint() {
[ "$(sent URL)" = \
"https://forge.example/api/v1/repos/owner/repo/actions/workflows/self-labels-sweep.yml/dispatches" ]
}
check "...to the dispatches endpoint of the workflow it was told to wake" 0 "" right_endpoint
ref_is_main() { [ "$(sent_field .ref)" = main ]; }
check "...carrying a ref, because REST has no default and refuses without one" 0 "" ref_is_main
bootstrap_is_string_no() { [ "$(sent_field '.inputs.bootstrap')" = no ]; }
check "...and bootstrap=no as a STRING input, not a bare flag" 0 "" bootstrap_is_string_no
bearer_sent() { grep -qF 'HEADER Authorization: Bearer tok' "$TMP/calls"; }
check "...under the bearer header both forges accept" 0 "" bearer_sent
# --- the ref it must NOT inherit ---------------------------------------------
# On pull_request_target GITHUB_REF_NAME is `<n>/merge`. A step that reaches
# for it dispatches at something that is not a branch — and the forge answers
# that with the opaque 500, so it would look like an outage.
check "a pull_request_target run still dispatches at the branch" 0 "" \
run_step 204 "" DEFAULT_BRANCH=main GITHUB_REF_NAME=203/merge
ref_is_not_a_merge_ref() { case "$(sent_field .ref)" in *merge*) return 1 ;; *) return 0 ;; esac; }
check "...never at its merge ref" 0 "" ref_is_not_a_merge_ref
# --- the fallback ------------------------------------------------------------
check "an absent default branch is read from the forge, not guessed" 0 "" \
run_step 204 "" DEFAULT_BRANCH=
ref_is_trunk() { [ "$(sent_field .ref)" = trunk ]; }
check "...and the dispatch uses what the read returned" 0 "" ref_is_trunk
# --- failure is loud, and the diagnostic is owned ----------------------------
# `gh workflow run` failing WAS the misconfiguration alarm. The port keeps that
# contract: a consumer missing the caller, its input, or `actions: write` must
# fail here rather than sweep silently never again.
check "an empty 500 fails the step — the alarm still rings" 1 \
"/self-labels-sweep.yml/dispatches (ref=main)" \
run_step 500 "" DEFAULT_BRANCH=main
check "...explaining Forgejo's EMPTY 500 rather than passing it through" 1 \
"empty 500 body from Forgejo means the workflow name or the ref did not resolve" \
run_step 500 "" DEFAULT_BRANCH=main
check "...and naming the consumer causes the alarm exists for" 1 "actions: write" \
run_step 500 "" DEFAULT_BRANCH=main
check "any non-204 fails, not only the statuses the API documents" 1 "forbidden" \
run_step 403 '{"message":"forbidden"}' DEFAULT_BRANCH=main
# --- the API root is not guessed ---------------------------------------------
# Defaulting an unset GITHUB_API_URL to api.github.com sent this forge's
# dispatch to GitHub and reported success (@codex-reviewer-andresmgsl). The
# teeth are the call count: refusing AFTER a request is not refusing.
run_step_no_api() {
rm -rf "${TMP:?}/bin"; mkdir -p "$TMP/bin"; : >"$TMP/calls"
make_curl 204 ""
# -u, because plain `env` PRESERVES the parent environment: on the runner
# every step arrives with GITHUB_API_URL set — the premise of the fix under
# test — so without the unset this case inherits it, the refusal path never
# executes, and the case passes only in a dev shell that lacks the variable
# (@kimi-reviewer-andresmgsl, run 468).
env -u GITHUB_API_URL \
PATH="$TMP/bin:$PATH" GITHUB_TOKEN=tok GITHUB_REPOSITORY=owner/repo \
SWEEP_WORKFLOW=self-labels-sweep.yml DEFAULT_BRANCH=main "$STEP"
}
check "an unset GITHUB_API_URL refuses rather than guessing GitHub" 1 \
"GITHUB_API_URL is unset" run_step_no_api
no_calls_made() { [ ! -s "$TMP/calls" ]; }
check "...having made zero requests: refusing after a POST is not refusing" 0 "" no_calls_made
# --- a transport failure is not silence --------------------------------------
# The old `|| true` invariant was asserted by grepping the gh line this port
# removed, so it passed on any REST implementation including one that swallows
# a failed POST (@codex-reviewer-andresmgsl). Driven instead: curl itself exits
# non-zero, which `-w` cannot report because nothing is written.
make_failing_curl() {
printf '%s\n' '#!/usr/bin/env bash' 'echo "curl: (7) failed to connect" >&2' 'exit 7' \
>"$TMP/bin/curl"
chmod +x "$TMP/bin/curl"
}
run_step_curl_dies() {
rm -rf "${TMP:?}/bin"; mkdir -p "$TMP/bin"; : >"$TMP/calls"
make_failing_curl
env PATH="$TMP/bin:$PATH" GITHUB_TOKEN=tok \
GITHUB_API_URL=https://forge.example/api/v1 GITHUB_REPOSITORY=owner/repo \
SWEEP_WORKFLOW=self-labels-sweep.yml DEFAULT_BRANCH=main "$STEP"
}
check "a POST that never reaches the forge fails the step, and says so" 1 \
"never completed" run_step_curl_dies
# A code-aware guard alongside the behavioural one: no swallowing operator on
# the dispatch itself.
never_silenced() { sed 's/#.*//' "$STEP" | grep -qE '\|\|[[:space:]]*true'; }
check "...and the step carries no || true" 1 "" never_silenced
fix(labels): wake the sweep over REST, so board events reconcile in seconds `.github/workflows/labels.yml` dispatched the sweep with `gh workflow run`, the eighth runtime gh call site the 0.6.0 merge reintroduced and the only one !204 did not port. On this forge the runner carries neither gh nor a GitHub API, so the step refused and the entire event-driven reconcile path ended there — every transition waiting up to an hour for the scheduled sweep. The workflow-dispatch endpoint has the SAME shape on both forges: POST {api}/repos/{owner}/{repo}/actions/workflows/{file}/dispatches {"ref": "<branch>", "inputs": {...}} -> 204, empty body so the step no longer decides a forge at all. The CEREMONY_FORGE_CLIENT=gh declaration and both inline refusals are removed rather than ported, and test/no-runtime-gh.test.sh now asserts their ABSENCE — an opt-out with no gh behind it is a standing permission slip. The ref is supplied explicitly and taken from the repository, never from GITHUB_REF_NAME: on a pull_request_target run that is `<n>/merge`, which is not a branch. A non-204 still fails the job, keeping the misconfiguration alarm the trigger exists to be, and the diagnostic explains Forgejo's empty 500 rather than passing a bare status to a reader who will go looking for an outage that is not there. test/labels-dispatch.test.sh extracts the shipped step and executes it against a recording stub, asserting the method, endpoint, ref and inputs actually sent. Dropping the inputs or ignoring a non-204 both red the suite. Refs #205
2026-08-05 16:58:05 +00:00
# --- what the port removed ---------------------------------------------------
# Strip comments first: the step's prose NAMES `gh workflow run` and
# CEREMONY_FORGE_CLIENT to explain what it replaced, so a raw grep asserts on
# the explanation instead of the code.
step_code() { sed 's/#.*//' "$STEP"; }
invokes_gh() { step_code | grep -qE '(^|[^[:alnum:]_])gh[[:space:]]'; }
decides_forge() { step_code | grep -qE 'GITHUB_SERVER_URL|CEREMONY_FORGE_CLIENT'; }
check "the step no longer INVOKES gh, its comments about it aside" 1 "" invokes_gh
check "...and no longer decides a forge, because REST needs no branch" 1 "" decides_forge
summary