forked from heavy-duty/rig
fix(drill): read every task, and fail a configured leg that cannot mint
Addresses grok's and kimi's REQUEST_CHANGES on !130. 1. forgejo_run_verdict read only the FIRST entry of actions/tasks. That payload accumulates, so the moment a repo is drilled twice our run shares it with older ones — and nothing documents the sort order. A green job then reports as a timeout: a false FAILURE on the gate this leg exists to provide. It now inspects every entry and lets the newest id above pre_id decide. Newlines are stripped first, so a pretty-printed payload parses like a compact one. 2. A mint that yielded nothing degraded to SKIPPED "no registration token source" — violating #129's own acceptance ("token source present but the instance is unreachable -> the leg FAILS; it must not skip and must not pass") and sending the operator to check an env var they had already set. forgejo_token_verdict separates absent inputs from a configured leg that could not mint; only the former skips. 3. The pre---yes confirm block still announced a GitHub runner alone. Refs #129 Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
parent
1179d3142f
commit
9c0e508b76
2 changed files with 98 additions and 19 deletions
|
|
@ -143,29 +143,61 @@ leg() { LEG_NAMES+=("$1"); LEG_RESULTS+=("$2"); }
|
|||
# non-terminal status is pending, not failed; grading a running job as a
|
||||
# failure would make the leg flaky inside its own watch window.
|
||||
#
|
||||
# EVERY entry is inspected, and the NEWEST id above pre_id decides — never
|
||||
# entry[0]. actions/tasks accumulates, so the moment a repo is drilled twice
|
||||
# our run shares the payload with older ones, and nothing documents the sort
|
||||
# order. Reading the first entry made a green job report as a timeout, a false
|
||||
# FAILURE on the gate this leg exists to provide (grok/kimi on !130).
|
||||
#
|
||||
# grep-and-sed, not jq: a throwaway drill machine has neither jq nor an
|
||||
# authenticated forge CLI, the same constraint json_field() carries in
|
||||
# commands/lib/runner-config.sh. `id` is a bare number, which json_field's
|
||||
# quoted-value shape cannot read, so this reads both forms itself.
|
||||
# quoted-value shape cannot read, so this reads both forms itself. Newlines are
|
||||
# stripped first so a pretty-printed payload parses identically to a compact
|
||||
# one — the instance documents neither.
|
||||
forgejo_run_verdict() {
|
||||
# `run_status`, not `status`: the latter is read-only in zsh, and while this
|
||||
# file is bash, the function is awk-extracted and sourced by other shells in
|
||||
# test harnesses — where the assignment fails silently and grades every run
|
||||
# as pending.
|
||||
local pre="$1" file="$2" id run_status
|
||||
id="$(grep -o '"id"[[:space:]]*:[[:space:]]*[0-9][0-9]*' "$file" 2>/dev/null \
|
||||
| head -n1 | sed 's/.*:[[:space:]]*//')"
|
||||
[ -n "$id" ] || { echo pending; return 0; }
|
||||
[ "$id" != "$pre" ] || { echo pending; return 0; }
|
||||
run_status="$(grep -o '"status"[[:space:]]*:[[:space:]]*"[^"]*"' "$file" 2>/dev/null \
|
||||
| head -n1 | sed 's/.*:[[:space:]]*"//; s/"$//')"
|
||||
case "$run_status" in
|
||||
success) echo success ;;
|
||||
local pre="$1" file="$2" obj id best_id="" best_st=""
|
||||
[ -r "$file" ] || { echo pending; return 0; }
|
||||
while IFS= read -r obj; do
|
||||
[ -n "$obj" ] || continue
|
||||
id="$(printf '%s' "$obj" | grep -o '"id"[[:space:]]*:[[:space:]]*[0-9][0-9]*' \
|
||||
| head -n1 | sed 's/.*:[[:space:]]*//')"
|
||||
[ -n "$id" ] || continue
|
||||
# Strictly newer than the pre-dispatch id. Equal is the run that was
|
||||
# already there; lower is older still.
|
||||
if [ -n "$pre" ]; then
|
||||
[ "$id" -gt "$pre" ] 2>/dev/null || continue
|
||||
fi
|
||||
if [ -z "$best_id" ] || [ "$id" -gt "$best_id" ] 2>/dev/null; then
|
||||
best_id="$id"
|
||||
best_st="$(printf '%s' "$obj" | grep -o '"status"[[:space:]]*:[[:space:]]*"[^"]*"' \
|
||||
| head -n1 | sed 's/.*:[[:space:]]*"//; s/"$//')"
|
||||
fi
|
||||
done <<EOF
|
||||
$(tr -d '\n' < "$file" 2>/dev/null | grep -o '{[^{}]*}')
|
||||
EOF
|
||||
[ -n "$best_id" ] || { echo pending; return 0; }
|
||||
case "$best_st" in
|
||||
success) echo success ;;
|
||||
failure | cancelled | skipped | timedout) echo failed ;;
|
||||
*) echo pending ;;
|
||||
*) echo pending ;;
|
||||
esac
|
||||
}
|
||||
|
||||
# forgejo_token_verdict <resolved_token> <api_token> — ok | mint-failed | no-source.
|
||||
# #129's acceptance: "Token source present but the instance is unreachable ->
|
||||
# the leg FAILS; it must not skip and must not pass". A mint that yields
|
||||
# nothing — unreachable instance, under-scoped token, wrong repo — is a
|
||||
# CONFIGURED leg failing, and reporting it as "no token source" both writes
|
||||
# SKIPPED where the record owes a FAIL and sends the operator to check an env
|
||||
# var they already set. Absent inputs are the only honest skip.
|
||||
forgejo_token_verdict() {
|
||||
if [ -n "$1" ]; then echo ok
|
||||
elif [ -n "$2" ]; then echo mint-failed
|
||||
else echo no-source
|
||||
fi
|
||||
}
|
||||
|
||||
|
||||
# run_logged <log> <cmd...> — run a long command with its narration in a file
|
||||
# and a dot every 5s on the terminal: a silent multi-minute apt/install run is
|
||||
|
|
@ -411,7 +443,7 @@ This will, ON THIS HOST ($(hostname)):
|
|||
· run 'rig bootstrap $ROLE --users $USERS_FILE' — sshd hardening, hostname
|
||||
change, tailnet join, box ($BOXREPO@$BOXREF) + its Incus stack — TWICE
|
||||
(the second run is the idempotence assertion)
|
||||
· install Coolify${COOLIFY_VERSION:+ $COOLIFY_VERSION} and a GitHub runner${RUNNER_REPO:+ against $RUNNER_REPO}
|
||||
· install Coolify${COOLIFY_VERSION:+ $COOLIFY_VERSION}, a GitHub runner${RUNNER_REPO:+ against $RUNNER_REPO} and a Forgejo runner${FJ_INSTANCE:+ against $FJ_INSTANCE}${FJ_RUNNER_REPO:+ ($FJ_RUNNER_REPO)}
|
||||
Only do this on a THROWAWAY machine you can format.
|
||||
EOF
|
||||
[ -t 0 ] || { echo "drill: no TTY to confirm on — pass --yes if you mean it." >&2; exit 2; }
|
||||
|
|
@ -787,7 +819,12 @@ else
|
|||
| grep -o '"token"[[:space:]]*:[[:space:]]*"[^"]*"' | head -n1 \
|
||||
| sed 's/.*:[[:space:]]*"//; s/"$//')"
|
||||
fi
|
||||
if [ -z "$fj_reg" ]; then
|
||||
fj_tok_verdict="$(forgejo_token_verdict "$fj_reg" "${FORGEJO_API_TOKEN:-}")"
|
||||
if [ "$fj_tok_verdict" = mint-failed ]; then
|
||||
# Configured, and it did not work. Never a skip: see forgejo_token_verdict.
|
||||
no "registration-token mint FAILED against ${FJ_INSTANCE} — is it reachable, and does FORGEJO_API_TOKEN own ${FJ_RUNNER_REPO}? (the token is never printed)"
|
||||
leg "forgejo runner lifecycle ($FJ_RUNNER_REPO)" "FAIL — registration-token mint failed"
|
||||
elif [ "$fj_tok_verdict" = no-source ]; then
|
||||
skip "forgejo runner lifecycle: no FORGEJO_RUNNER_TOKEN and no FORGEJO_API_TOKEN to mint one — the leg did not run"
|
||||
leg "forgejo runner lifecycle ($FJ_RUNNER_REPO)" "SKIPPED — no registration token source"
|
||||
else
|
||||
|
|
|
|||
|
|
@ -50,10 +50,10 @@ trap 'rm -rf "$WORK"' EXIT
|
|||
|
||||
# --- the functions under test, extracted -------------------------------------
|
||||
FNS="$WORK/drill-fns.sh"
|
||||
for fn in tree_of assert_installed_from classify_leg capture_state emit_record forgejo_run_verdict; do
|
||||
for fn in tree_of assert_installed_from classify_leg capture_state emit_record forgejo_run_verdict forgejo_token_verdict; do
|
||||
awk "/^${fn}\(\) \{/,/^\}/" "$ROOT/drill/drill.sh" >> "$FNS"
|
||||
done
|
||||
for fn in tree_of assert_installed_from classify_leg capture_state emit_record forgejo_run_verdict; do
|
||||
for fn in tree_of assert_installed_from classify_leg capture_state emit_record forgejo_run_verdict forgejo_token_verdict; do
|
||||
check "extraction guards the awk: ${fn}() landed" 0 "${fn}() {" grep -F "${fn}() {" "$FNS"
|
||||
done
|
||||
# shellcheck source=/dev/null
|
||||
|
|
@ -243,6 +243,48 @@ printf '%s' '{"workflow_runs":[{"id":25,"status":"running","run_number":1}],"tot
|
|||
check "verdict: an assigned-but-running task is PENDING, not FAILED" 0 "pending" \
|
||||
forgejo_run_verdict "24" "$FJ/new-running.json"
|
||||
|
||||
# grok/kimi on !130: the reader must not stop at the FIRST run. actions/tasks
|
||||
# accumulates — the moment a repo is drilled twice, our run shares the payload
|
||||
# with older ones, and nothing documents the sort order. Reading entry[0] makes
|
||||
# a green job read as a timeout, which is a FALSE FAILURE on the very gate this
|
||||
# leg exists to provide.
|
||||
printf '%s' '{"workflow_runs":[{"id":24,"status":"success"},{"id":25,"status":"success"}],"total_count":2}' > "$FJ/oldest-first.json"
|
||||
printf '%s' '{"workflow_runs":[{"id":25,"status":"success"},{"id":24,"status":"success"}],"total_count":2}' > "$FJ/newest-first.json"
|
||||
printf '%s' '{"workflow_runs":[{"id":25,"status":"running"},{"id":26,"status":"success"}],"total_count":2}' > "$FJ/ours-not-first.json"
|
||||
printf '%s' '{"workflow_runs":[{"id":23,"status":"success"},{"id":24,"status":"failure"}],"total_count":2}' > "$FJ/all-stale.json"
|
||||
# Pretty-printed: the instance may or may not compact its JSON, and a parser
|
||||
# that silently depends on one-line objects is a latent failure (kimi, !130).
|
||||
cp /tmp/fjfix/pretty.json "$FJ/pretty.json"
|
||||
check "verdict: ours is LAST in the payload — order must not decide" 0 "success" \
|
||||
forgejo_run_verdict "24" "$FJ/oldest-first.json"
|
||||
check "verdict: ours is FIRST in the payload — same answer" 0 "success" \
|
||||
forgejo_run_verdict "24" "$FJ/newest-first.json"
|
||||
check "verdict: a stale RUNNING entry ahead of ours does not mask it" 0 "success" \
|
||||
forgejo_run_verdict "24" "$FJ/ours-not-first.json"
|
||||
check "verdict: every entry at or below pre is stale — PENDING" 0 "pending" \
|
||||
forgejo_run_verdict "24" "$FJ/all-stale.json"
|
||||
check "verdict: a pretty-printed payload parses too" 0 "success" \
|
||||
forgejo_run_verdict "24" "$FJ/pretty.json"
|
||||
|
||||
# =============================================================================
|
||||
# forgejo_token_verdict — a configured leg that cannot mint must FAIL, not SKIP
|
||||
# =============================================================================
|
||||
# #129's own acceptance: "Token source present but the instance is unreachable
|
||||
# -> the leg FAILS; it must not skip and must not pass". A mint that returns
|
||||
# nothing because the instance is unreachable, the token is under-scoped or the
|
||||
# repo name is wrong is a CONFIGURED leg failing — reporting "no token source"
|
||||
# sends the operator to check an env var they already set, and writes SKIPPED
|
||||
# where the record owes a FAIL. That is the UNREADABLE-vs-NONE shape
|
||||
# drills/README.md names.
|
||||
check "token: a resolved registration token is ok" 0 "ok" \
|
||||
forgejo_token_verdict "reg-tok" ""
|
||||
check "token: an explicit token wins even with no API token" 0 "ok" \
|
||||
forgejo_token_verdict "reg-tok" ""
|
||||
check "token: no token at all and no API token is a genuine SKIP" 0 "no-source" \
|
||||
forgejo_token_verdict "" ""
|
||||
check "token: API token offered but mint produced nothing is a FAILURE" 0 "mint-failed" \
|
||||
forgejo_token_verdict "" "api-tok"
|
||||
|
||||
# The anti-false-positive guard, stated as its own case: an OLD completed run
|
||||
# with the SAME id as pre_id must never be read as this dispatch's result.
|
||||
check "verdict: a pre-existing success with the pre-id is NOT our run" 0 "pending" \
|
||||
|
|
|
|||
Loading…
Reference in a new issue