Merge pull request #256 from cndgrr/build/247-read-guards

fix(issueflow): a failed read must never reach a decision function
This commit is contained in:
Daniel Marin 2026-08-03 20:19:35 +01:00 committed by GitHub
commit f73facea6e
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 686 additions and 50 deletions

View file

@ -27,9 +27,83 @@ TRIAGE_ACTORS=()
# The needs-ruling invariants (#52) — one implementation for both surfaces.
# shellcheck source=lib/ruling.sh
. "$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)/../../lib/ruling.sh"
# The guarded read and its reason line (#101, #247) — one implementation for
# both surfaces.
# shellcheck source=lib/read.sh
. "$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)/../../lib/read.sh"
log() { printf 'issueflow: %s\n' "$*"; }
run() { if [ -n "${DRY_RUN:-}" ]; then log "DRY_RUN: $*"; else "$@"; fi; }
# The status a per-issue subshell exits with when it walked away from an
# unreadable fact (#247 D4). Distinguished from every other non-zero status so
# a deliberate skip is counted rather than reported as a crash — and so the
# existing crash handler still names a genuine one.
ISSUEFLOW_SKIP=3
# Set by reconcile_issue_pass, read once by main for the D6 tail.
SKIPPED_COUNT=0
SKIPPED_ISSUES=""
# A per-issue pass is ATOMIC: it commits its whole effect or none of it
# (#247 D1). Inside reconcile_issue_pass's subshell, `run` and `log` do not
# act — they append here, and commit_staged_effects replays them in order
# once the pass has completed. Everywhere else (the arrival path, the sweep's
# own lines) they act immediately, as they always did.
#
# This is the ordering invariant itself, not a fix for the two sites that
# happened to violate it: a mutation reached before a later guarded read is
# what let a pass remove `stale`, or mint `needs-triage`, and THEN report the
# issue as skipped — the sweep saying it touched nothing while a write had
# landed, which is the same false-report class #247 exists to close. Stated
# per site it would hold until the next composition; stated here it holds for
# compositions nobody has written yet, because reconcile_issue has no way to
# mutate directly.
#
# Reads are deliberately NOT staged. They may happen anywhere in the pass,
# because nothing lands until the end.
STAGING=false
STAGED_EFFECTS=()
emit() { printf 'issueflow: %s\n' "$*"; }
apply() { if [ -n "${DRY_RUN:-}" ]; then emit "DRY_RUN: $*"; else "$@"; fi; }
stage() { # $1 = LOG|WRITE, rest = the effect's argv, kept exact by the count
STAGED_EFFECTS+=("$#" "$@")
}
log() { if [ "$STAGING" = true ]; then stage LOG "$@"; else emit "$@"; fi; }
run() { if [ "$STAGING" = true ]; then stage WRITE "$@"; else apply "$@"; fi; }
commit_staged_effects() {
# In staging order, so a completed pass's log and writes read exactly as
# they did when each acted at its own call site. The `>/dev/null` is the one
# every `run` call site already applies: a redirection cannot travel with
# the argv, so it is applied here instead — uniformly, because on this
# surface every staged write has it.
local i=0 argc
STAGING=false
while [ "$i" -lt "${#STAGED_EFFECTS[@]}" ]; do
argc="${STAGED_EFFECTS[i]}"
if [ "${STAGED_EFFECTS[i + 1]}" = LOG ]; then
emit "${STAGED_EFFECTS[@]:i + 2:argc - 1}"
else
apply "${STAGED_EFFECTS[@]:i + 2:argc - 1}" >/dev/null
fi
i=$((i + 1 + argc))
done
STAGED_EFFECTS=()
}
skip_issue() { # $1 = issue, $2 = the whole reason clause — ends this issue's pass
# Leaves the issue exactly as it is: nothing is derived from a read that
# did not answer, and nothing this pass staged is ever committed — `exit`
# discards the subshell that holds the buffer. So a skip implies zero
# `gh issue edit`, zero `gh issue comment`, and no log line claiming an
# effect that never landed, wherever in the pass the failed read lives.
# Called from the read itself, so no call site can forget to check — which
# is why it exits rather than returns. The reason rides its own
# `#$n:`-prefixed line (#247 D5), emitted directly: the skip is a fact
# about the pass, not one of the effects the pass staged.
emit "#$1: skipped this pass — $2"
exit "$ISSUEFLOW_SKIP"
}
load_issueflow_config() { # $1 = labels.conf
local conf="$1" line seen=false
@ -287,6 +361,31 @@ offsite_resolved_decision() { # PR states on stdin -> NUDGE | QUIET
fi
}
issue_payload_valid() { # $1 = the requested issue; payload on stdin
# The second of D3's two required guards, and neither subsumes the other.
# The status check catches the 504 whose body is GitHub's JSON error object
# — valid JSON that passes every jq guard and empties the label set. THIS
# one catches an HTTP 200 whose body is `null`, which exits 0 and empties it
# just the same. `.number` is checked against the issue asked for, so a
# payload about some other issue can never be reconciled as this one.
jq -e --arg n "$1" '
type == "object" and (.number | tostring) == $n and (.labels | type) == "array"
' >/dev/null 2>&1
}
skipped_tail() { # $1 = skip count, $2 = the issue numbers → the D6 line, or nothing
# `reconciled.` stays byte-identical when the pass was whole — tests pin that
# exact string, and #101 D1 is the precedent for not folding new text into a
# matched line. A partial pass says so on a line of its own, after it, so a
# consumer reading only the tail of a job log can see it.
[ "$1" -gt 0 ] || return 0
if [ "$1" -eq 1 ]; then
printf '%s issue skipped this pass on an unreadable fact: %s\n' "$1" "$2"
else
printf '%s issues skipped this pass on unreadable facts: %s\n' "$1" "$2"
fi
}
# API edge. Marker comments make warnings and nudges idempotent across sweeps.
ensure_comment() { # $1 issue, $2 marker, $3 message
local n="$1" marker="$2" message="$3"
@ -295,9 +394,15 @@ ensure_comment() { # $1 issue, $2 marker, $3 message
$message" >/dev/null
}
issue_comment_has_marker() { # $1 issue, $2 marker
gh api --paginate "repos/$REPO/issues/$1/comments" --jq '.[].body' \
| grep -qF "<!-- issueflow:$2 -->"
issue_comment_has_marker() { # $1 issue, $2 marker → 0 found, 1 genuinely absent
# A failed read used to answer "no marker", which re-posts the comment the
# marker exists to suppress — absence of evidence read as evidence of
# absence (#247 D1). It cannot be a return value: every caller treats
# non-zero as "absent", so the skip is taken here, at the read.
local bodies
guarded_read bodies gh api --paginate "repos/$REPO/issues/$1/comments" --jq '.[].body' \
|| skip_issue "$1" "could not read its comments: $(read_failure_reason "$READ_FAILURE_STDERR")"
grep -qF "<!-- issueflow:$2 -->" <<<"$bodies"
}
reference_states() {
@ -324,22 +429,27 @@ offsite_timeline() { # unreadable timelines are deliberately silent
gh api --paginate "repos/$REPO/issues/$1/timeline" 2>/dev/null || return 1
}
last_issue_activity() {
local n="$1" created="$2" latest
latest="$({
printf '%s\n' "$created"
gh api --paginate "repos/$REPO/issues/$n/comments" --jq '.[].created_at'
# Assignment is the claim itself. Ignoring it would let an old issue be
# reclaimed in the seconds between assignment and its required draft PR.
gh api --paginate "repos/$REPO/issues/$n/timeline" \
--jq '.[] | select(.event == "assigned") | .created_at'
} \
| sort | tail -n1)"
last_issue_activity() { # $1 issue, $2 created_at → epoch; non-zero if a read failed
# Both reads are checked, and a failure reports rather than answering an age
# (#247 D1). Swallowed, the comments read falls back to `created_at`, and a
# `claimed` issue created months ago but commented on seconds earlier is
# reclaimed — the live builder unassigned, under a comment asserting 48
# hours of silence. `needs-triage` is cheap to remove; that is not.
# gh's stderr is left to flow to this function's own, where the caller's
# guarded_read captures it for the reason line.
local n="$1" created="$2" comments timeline latest
comments="$(gh api --paginate "repos/$REPO/issues/$n/comments" --jq '.[].created_at')" \
|| return 1
# Assignment is the claim itself. Ignoring it would let an old issue be
# reclaimed in the seconds between assignment and its required draft PR.
timeline="$(gh api --paginate "repos/$REPO/issues/$n/timeline" \
--jq '.[] | select(.event == "assigned") | .created_at')" || return 1
latest="$(printf '%s\n%s\n%s\n' "$created" "$comments" "$timeline" | sort | tail -n1)"
date -d "$latest" +%s
}
reconcile_issue() {
local n="$1" decision refs cross_refs states age assignees open_pr=false label owners
local n="$1" decision refs cross_refs states age created assignees open_pr=false label owners
local merged_ref_pr="" transition_marker="" transition_handled=false
local unchecked="" remove_claimed=claimed
decision="$(queue_decision <<<"$ISSUE_LABELS")"
@ -386,7 +496,9 @@ The merge releases the claim; no builder owes a draft. Triage owes completion in
fi
log "#$n: merged Refs PR -> post-merge; claim released"
else
age="$(last_issue_activity "$n" "$(jq -r '.created_at' <<<"$ISSUE_JSON")")"
created="$(jq -r '.created_at' <<<"$ISSUE_JSON")"
guarded_read age last_issue_activity "$n" "$created" \
|| skip_issue "$n" "could not read its activity history: $(read_failure_reason "$READ_FAILURE_STDERR")"
if [ "$(claim_clock_exempt <<<"$ISSUE_LABELS")" = EXEMPT ]; then
# Legitimately quiet work does not run the reclaim clock. Only the
# clock stops: an unassigned claim is still a repair the decision must
@ -474,8 +586,11 @@ The merge releases the claim; no builder owes a draft. Triage owes completion in
run gh issue edit "$n" -R "$REPO" --remove-label stale >/dev/null
log "#$n: unstale (a ruling is pending)"
fi
[ -n "${age:-}" ] \
|| age="$(last_issue_activity "$n" "$(jq -r '.created_at' <<<"$ISSUE_JSON")")"
if [ -z "${age:-}" ]; then
created="$(jq -r '.created_at' <<<"$ISSUE_JSON")"
guarded_read age last_issue_activity "$n" "$created" \
|| skip_issue "$n" "could not read its activity history: $(read_failure_reason "$READ_FAILURE_STDERR")"
fi
reconcile_ruling "$n" "$age" "$NOW"
fi
}
@ -503,6 +618,45 @@ reconcile_opened_issue() {
log "#$n: needs-triage (opened by $author)"
}
reconcile_issue_pass() { # $1 = issue — one issue's whole pass, in its own subshell
# The subshell is #91's resilience: one unreadable or broken issue must not
# take the sweep down. What it is NOT is an errexit boundary — a command
# whose status is tested by `||` runs with errexit suppressed, and the
# suppression extends through the whole subshell body, so the handler below
# is what disables the errexit that would have caught a failed read (#247
# D2). Removing it would revive errexit and lose #91. Explicit per-read
# checks are the mechanism instead, and each one exits with ISSUEFLOW_SKIP.
#
# What the subshell IS, since #247's first round, is the atomicity
# boundary: the staged effects live in it, so ending it — by a skip, or by
# a crash — discards them, and no partial pass can ever reach the board.
local n="$1" status=0
(
# Everything below stages rather than acts, and commits at the bottom —
# so a skip taken at any read, and a crash at any statement, leaves the
# issue exactly as it was (D1). `|| exit $?` keeps a crash's status the
# subshell's own, as it was when reconcile_issue was the last command
# here: the commit must not overwrite it, and must not run under it.
STAGING=true
guarded_read ISSUE_JSON gh api "repos/$REPO/issues/$n" \
|| skip_issue "$n" "could not read the issue: $(read_failure_reason "$READ_FAILURE_STDERR")"
issue_payload_valid "$n" <<<"$ISSUE_JSON" \
|| skip_issue "$n" "the issue read answered a payload that is not issue #$n carrying a label array"
jq -e 'has("pull_request") | not' <<<"$ISSUE_JSON" >/dev/null || exit 0
ISSUE_LABELS="$(jq -r '.labels[].name' <<<"$ISSUE_JSON")"
reconcile_issue "$n" || exit $?
commit_staged_effects
) || status=$?
if [ "$status" -eq "$ISSUEFLOW_SKIP" ]; then
SKIPPED_COUNT=$((SKIPPED_COUNT + 1))
SKIPPED_ISSUES="${SKIPPED_ISSUES:+$SKIPPED_ISSUES }#$n"
elif [ "$status" -ne 0 ]; then
# Byte-identical, and still owed: a skip is deliberate, a crash is not,
# and folding the two together would hide one behind the other (D4).
log "#$n: reconcile failed — continuing with the remaining issues"
fi
}
main() {
local owner name
REPO="${REPO:?set REPO to owner/name}"
@ -554,17 +708,21 @@ main() {
done < <(refs_references <<<"$body")
done)"
local n
local n tail_line
SKIPPED_COUNT=0
SKIPPED_ISSUES=""
for n in $(gh api --paginate "repos/$REPO/issues?state=open&per_page=100" \
--jq '.[] | select(has("pull_request") | not) | .number'); do
(
ISSUE_JSON="$(gh api "repos/$REPO/issues/$n")"
jq -e 'has("pull_request") | not' <<<"$ISSUE_JSON" >/dev/null || exit 0
ISSUE_LABELS="$(jq -r '.labels[].name' <<<"$ISSUE_JSON")"
reconcile_issue "$n"
) || log "#$n: reconcile failed — continuing with the remaining issues"
reconcile_issue_pass "$n"
done
log "reconciled."
# The job stays green (D7): an hourly sweep over a hundred-issue board meets
# transient 504s as a matter of course, and reddening the whole run for one
# skipped issue trains consumers to ignore red — the outcome #95 and #101
# both steered away from on the PR surface. This line is what buys back the
# auditability that costs.
tail_line="$(skipped_tail "$SKIPPED_COUNT" "$SKIPPED_ISSUES")"
[ -z "$tail_line" ] || log "$tail_line"
}
if [ "${BASH_SOURCE[0]}" = "$0" ]; then main "$@"; fi

View file

@ -74,6 +74,12 @@ SELF_WORKFLOW="${SELF_WORKFLOW:-${GITHUB_WORKFLOW:-}}"
# The needs-ruling invariants (#52) — one implementation for both surfaces.
# shellcheck source=lib/ruling.sh
. "$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)/../../lib/ruling.sh"
# The guarded read and its reason line (#101) — one implementation for both
# surfaces. read_failure_reason lived here until the issue surface needed the
# identical rule (#247); a second copy of it is the failure lib/ruling.sh's
# own header was written to record.
# shellcheck source=lib/read.sh
. "$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)/../../lib/read.sh"
log() { printf 'labels: %s\n' "$*"; }
@ -98,25 +104,6 @@ blind_sweep_warning() { # $1 = unreadable PRs, $2 = all open PRs, $3 = sampled r
fi
}
read_failure_reason() { # $1 = captured stderr → one bounded line; pure (#101)
# Verbatim, collapsed, bounded (D3): gh emits multi-line errors and GraphQL
# blobs. Collapsed so the reason is exactly one log line — a raw newline
# inside the captured per-PR output block could collide with a matched
# string — and truncated because an unbounded paste per PR per sweep is
# noise, and annotations are capped anyway.
local reason
reason="$(printf '%s' "${1-}" | tr '\n' ' ')"
if [ -z "$reason" ]; then
# Empty stderr is itself a fact (D4): a read that failed silently is a
# different observation from a denial, and must not read as one.
echo "no error output"
elif [ "${#reason}" -gt 300 ]; then
printf '%s…\n' "${reason:0:300}"
else
printf '%s\n' "$reason"
fi
}
missing_core_labels_warning() { # $1 = declared rows, $2 = repo label names
local rows="$1" repo_labels="$2" row name missing=""
[ -n "$repo_labels" ] || return 0

20
changelog.d/247.md Normal file
View file

@ -0,0 +1,20 @@
### Fixed
- The issue sweep no longer derives label writes from a read that failed. An
HTTP 504 whose body is GitHub's JSON error object passed every guard and
emptied the label set, so a healthy epic was written `needs-triage` and the
pass reported success (#247).
- A failed comments read no longer reclaims a live claim. Swallowed, it dated
the issue by `created_at` and unassigned the builder under a comment
asserting 48 hours of silence about an issue commented on seconds earlier
(#247).
- A failed comments read no longer reads as "no marker", which re-posted the
comment the marker exists to suppress (#247).
- Every read inside the per-issue subshell is checked explicitly, on its
status and on its payload shape; the issue is left exactly as it is and the
sweep continues. A partial pass names its skipped issues after
`reconciled.` (#247).
- A per-issue pass is now atomic: its writes and its log lines commit only
once the pass completes. A skip could previously land after an earlier
mutation, reporting an issue as untouched when a label had already been
written or removed (#247).

62
lib/read.sh Normal file
View file

@ -0,0 +1,62 @@
#!/usr/bin/env bash
# lib/read.sh — the guarded read: an unreadable fact never invents a verdict.
#
# Both reconcilers source this file. The rule is the family's oldest one
# (#101, #95) and it has now been bought twice: the PR surface learned it
# when a permissions denial and a network hiccup left byte-identical
# evidence, and the ISSUE surface learned it when an HTTP 504 whose body is
# GitHub's JSON error object flowed straight into a decision function —
# `gh api` prints that body to stdout *and* exits non-zero, so the payload
# reaching the guards was valid JSON, `.labels[]` came back empty, and the
# sweep wrote `needs-triage` onto a healthy epic and called the pass a
# success (crew#329, #247).
#
# Two helpers:
# - guarded_read — run a read, keep its stderr, report its status
# - read_failure_reason — render that stderr into one bounded log line
#
# `read_failure_reason` is called from both surfaces. `guarded_read` is
# called from the issue surface only, and that is deliberate rather than
# unfinished: labels-reconcile's two capture sites are byte-identical to each
# other and predate this file, and converting them is a cleanup #247 does not
# own. Do not go looking for a labels-side caller — there is none yet.
#
# What the CALLER does with a failed read is the caller's: labels-reconcile
# leaves the PR alone for the pass, issueflow-reconcile skips the issue. The
# one thing neither may do is carry a degraded value into a decision.
guarded_read() { # $1 = variable to fill, rest = the read; sets READ_FAILURE_STDERR
# The status check and the captured stderr are one operation on purpose: a
# read whose failure is noticed but whose reason is thrown away is what
# #95 had to infer a cause from a control case for — wrongly, it turned
# out (#101 D2). Captured into a file rather than merged into stdout, so
# an unlucky error line can never be read back as the read's own payload.
local __var="$1" __err __out __rc=0
shift
__err="$(mktemp)" || return 1
__out="$("$@" 2>"$__err")" || __rc=$?
# shellcheck disable=SC2034 # the out-parameter: every caller reads it beside the status
READ_FAILURE_STDERR="$(cat "$__err")"
rm -f "$__err"
printf -v "$__var" '%s' "$__out"
return "$__rc"
}
read_failure_reason() { # $1 = captured stderr → one bounded line; pure (#101)
# Verbatim, collapsed, bounded (D3): gh emits multi-line errors and GraphQL
# blobs. Collapsed so the reason is exactly one log line — a raw newline
# inside the captured per-item output block could collide with a matched
# string — and truncated because an unbounded paste per item per sweep is
# noise, and annotations are capped anyway.
local reason
reason="$(printf '%s' "${1-}" | tr '\n' ' ')"
if [ -z "$reason" ]; then
# Empty stderr is itself a fact (D4): a read that failed silently is a
# different observation from a denial, and must not read as one.
echo "no error output"
elif [ "${#reason}" -gt 300 ]; then
printf '%s…\n' "${reason:0:300}"
else
printf '%s\n' "$reason"
fi
}

View file

@ -289,6 +289,12 @@ check "claimed plus attention is a healthy issue" 0 "KEEP" \
INOW=2000000000
iso_at() { date -u -d "@$1" +%Y-%m-%dT%H:%M:%SZ; }
# gh's own rendering of a 5xx whose body carries a `message` key — the line
# crew#329's job log carried, verbatim (#247), and the payload beside it.
GH_STUB_STDERR="gh: We couldn't respond to your request in time. (HTTP 504)"
GH_STUB_ERROR_BODY='{"message":"We could not respond to your request in time.","documentation_url":"https://docs.github.com/rest"}'
export GH_STUB_STDERR # the PATH-stubbed gh of the executable runs reads it too
issue_stub_gh() {
if [ "$1" = api ]; then
shift
@ -303,9 +309,36 @@ issue_stub_gh() {
done
file="$TMP/$(printf '%s' "$endpoint" | tr '/' '_').json"
printf '%s\n' "$endpoint" >>"$TMP/api-calls"
[ ! -f "$file.error" ] || return 1
[ -f "$file" ] || { printf '[]\n'; return 0; }
if [ -n "$jqexpr" ]; then jq -r "$jqexpr" "$file"; else cat "$file"; fi
# A `.http-error` sentinel is the real 5xx (#247): `gh api` prints the
# response body — GitHub's JSON error object — to STDOUT, says why on
# stderr, and exits non-zero. The `.error` sentinel models a failure with
# no payload, which is the *safe* path (an empty label set is empty either
# way), and is why this class was never caught. Both now speak on stderr,
# because the real gh always does and the reason line renders it.
if [ -f "$file.http-error" ]; then
# A --jq call gets the filter applied to the error body, as gh does.
# That is what "yields no timestamps" looks like — the shape that let
# last_issue_activity fall back to created_at and reclaim a live claim.
if [ -n "$jqexpr" ]; then
jq -r "$jqexpr" "$file.http-error" 2>/dev/null || true
else
cat "$file.http-error"
fi
printf '%s\n' "$GH_STUB_STDERR" >&2
return 1
fi
[ ! -f "$file.error" ] || { printf '%s\n' "$GH_STUB_STDERR" >&2; return 1; }
# An absent fixture answers an empty list, and a --jq call gets the filter
# applied to it — the arrival stub's shape, and gh's. Returning the raw
# `[]` to a --jq caller made every missing fixture answer a literal `[]`
# where the real API answers nothing, and `[]` outsorts an ISO-8601
# timestamp in the C locale but not in a UTF-8 one, so last_issue_activity
# dated an issue by a stub artifact on the runner and by its created_at
# here. The old code swallowed the resulting date failure; #247's guards
# turn it into a skip, which is what made the lie visible.
local payload='[]'
[ ! -f "$file" ] || payload="$(cat "$file")"
if [ -n "$jqexpr" ]; then jq -r "$jqexpr" <<<"$payload"; else printf '%s\n' "$payload"; fi
elif [ "$1" = issue ] && [ "$2" = comment ]; then
local n="$3" body="" file
shift 3
@ -576,6 +609,16 @@ unreadable="$(issue_probe 32 $'claimed\noffsite')"
check "an unreadable timeline stays silent" 1 "" test -f "$TMP/posted-32"
check "...and leaves the sweep running without an alarming log" 1 "" \
grep -qiE 'error|failed' <<<"$unreadable"
# Both checks above still hold, and #247 D1 changed what reaches them:
# last_issue_activity reads the same timeline endpoint, so the issue is now
# skipped before the offsite verification runs. The skip is why nothing is
# posted, and its reason line is a deliberate report rather than an alarm
# (D4). D8 leaves offsite_timeline's own silence alone, so it is pinned here
# directly rather than through a probe that can no longer reach it.
offsite_timeline_probe() { ( REPO=owner/repo; gh() { issue_stub_gh "$@"; }; offsite_timeline "$1" ); }
check "an unreadable offsite timeline yields nothing and still fails closed" 1 "" \
offsite_timeline_probe 32
check "...while a readable one answers its payload" 0 "[]" offsite_timeline_probe 31
: >"$TMP/api-calls"
printf '[]\n' >"$(tfix 33)"
@ -629,6 +672,119 @@ churned="$(issue_probe 24 $'claimed\nneeds-ruling')"
check "8 real-quiet days nudge through a 2-day-old label churn" 0 "" \
grep -q 'ruling nudge' <<<"$churned"
# ---------------------------------------------------------------------------
# An unreadable fact invents no verdict on the issue surface either (#247).
# `gh api` prints a 5xx body to stdout AND exits non-zero, and GitHub's 5xx
# body is a JSON object — so the payload that reached the guards was valid
# JSON, `.labels[]` came back empty, and queue_decision was handed the wrong
# input. The pure guards first, then the two decisions the fall-through
# reached.
# ---------------------------------------------------------------------------
payload_refused() { ! issue_payload_valid "$@"; } # 0 when the payload is refused
check "a healthy issue payload is accepted" 0 "" \
issue_payload_valid 40 <<<'{"number":40,"labels":[{"name":"ready"}]}'
check "an issue carrying no labels at all is still a valid payload" 0 "" \
issue_payload_valid 40 <<<'{"number":40,"labels":[]}'
# The reported shape: gh renders `gh: <message> (HTTP 504)` from a body with a
# `message` key, which proves the body was valid JSON. The status check is what
# catches this one; the shape check refuses it independently.
check "a JSON error object is not an issue payload" 0 "" \
payload_refused 40 <<<"$GH_STUB_ERROR_BODY"
# The live path a status check alone would leave open (D3): 200, exit 0, and
# `.labels[]` empties exactly as it does on the 504.
check "an HTTP 200 whose body is null is refused" 0 "" payload_refused 40 <<<'null'
check "a payload missing .labels is refused" 0 "" \
payload_refused 40 <<<'{"number":40}'
check "a payload whose .labels is not an array is refused" 0 "" \
payload_refused 40 <<<'{"number":40,"labels":"ready"}'
check "a payload about a different issue is refused" 0 "" \
payload_refused 40 <<<'{"number":41,"labels":[]}'
check "a payload that is not JSON at all is refused" 0 "" \
payload_refused 40 <<<'not json'
check "an empty payload is refused" 0 "" payload_refused 40 </dev/null
# The reason line's shape (#101 D3/D4), reachable from this surface too — it
# is one implementation in lib/read.sh, not a second spelling.
check "empty stderr is reported as its own fact" 0 "no error output" \
read_failure_reason ""
check "the captured 504 renders verbatim on one line" 0 \
"$GH_STUB_STDERR" read_failure_reason "$GH_STUB_STDERR"
long_stderr="$(read_failure_reason "$(printf 'e%.0s' {1..400})")"
check "400 chars of stderr truncate to 300 plus an ellipsis" 0 "" \
test "$long_stderr" = "$(printf 'e%.0s' {1..300})"
# The D6 tail: silent on a whole pass, and naming both count and numbers on a
# partial one.
check "a whole pass adds no tail line" 0 "" test -z "$(skipped_tail 0 "")"
check "one skipped issue is named in the singular" 0 \
"1 issue skipped this pass on an unreadable fact: #12" skipped_tail 1 "#12"
check "several skipped issues are all named" 0 \
"2 issues skipped this pass on unreadable facts: #12 #40" \
skipped_tail 2 "#12 #40"
# -- the destroyed claim: a 504 on the comments read of a live claim ---------
# created_at long ago, a comment seconds old, and the comments read fails. The
# swallowed read dated the issue by created_at and reclaimed it, unassigning
# the builder under a comment asserting 48 hours of silence.
jq -n --arg at "$(iso_at $((INOW - 10)))" \
'[{"user":{"login":"builder"},"created_at":$at,"html_url":"https://x/live","body":"still on it"}]' \
>"$(cfix 50)"
printf '%s\n' "$GH_STUB_ERROR_BODY" >"$(cfix 50).http-error"
jq -n --arg at "$(iso_at $((INOW - 10 * 86400)))" \
'[{"event":"assigned","created_at":$at}]' >"$(tfix 50)"
claim_edits_before="$(wc -l <"$TMP/issue-edits")"
check "a 504 on the comments read skips the issue instead of grading its age" \
3 "#50: skipped this pass — could not read its activity history: $GH_STUB_STDERR" \
issue_probe 50 claimed 1
check "...so the live claim is not reclaimed" 1 "" \
grep -q 'stale claim reclaimed -> ready' <<<"$(issue_probe 50 claimed 1)"
# shellcheck disable=SC2016 # positional parameters belong to bash -c
check "...no unassign, no label swap, and no reclaim comment" 0 "" \
bash -c 'test "$1" -eq "$(wc -l <"$2")" && test ! -f "$3"' _ \
"$claim_edits_before" "$TMP/issue-edits" "$TMP/posted-50"
# -- the suppressed comment: a 504 on the marker read -----------------------
# The marker is on the issue. Read as "no marker", a failed read re-posts the
# comment the marker exists to suppress — every sweep, forever.
jq -n --arg b '<!-- issueflow:blocked-unparseable -->' \
--arg at "$(iso_at $((INOW - 3600)))" \
'[{"user":{"login":"sweep-bot"},"created_at":$at,"html_url":"https://x/m","body":$b}]' \
>"$(cfix 51)"
printf '%s\n' "$GH_STUB_ERROR_BODY" >"$(cfix 51).http-error"
check "a 504 on the marker read skips rather than reading it as no marker" \
3 "#51: skipped this pass — could not read its comments: $GH_STUB_STDERR" \
issue_probe 51 blocked 1 false "" "no parseable declaration here"
check "...so no duplicate comment is posted" 1 "" test -f "$TMP/posted-51"
# -- a deliberate skip is counted; a genuine crash is still named (D4) -------
printf '%s\n' '{"number":60,"labels":[{"name":"ready"}],"assignees":[]}' \
>"$TMP/repos_owner_repo_issues_60.json"
printf '%s\n' '{"number":61,"labels":[{"name":"ready"}],"assignees":[]}' \
>"$TMP/repos_owner_repo_issues_61.json"
printf '%s\n' "$GH_STUB_ERROR_BODY" >"$TMP/repos_owner_repo_issues_61.json.http-error"
pass_probe() { # $1 issue; $2 non-empty makes reconcile_issue crash
(
REPO=owner/repo
gh() { issue_stub_gh "$@"; }
[ -z "${2:-}" ] || reconcile_issue() { return 9; }
SKIPPED_COUNT=0
SKIPPED_ISSUES=""
reconcile_issue_pass "$1"
printf 'rc=%s count=%s issues=%s\n' "$?" "$SKIPPED_COUNT" "$SKIPPED_ISSUES"
)
}
check "a genuine non-read crash still names the failure byte-identically" 0 \
"issueflow: #60: reconcile failed — continuing with the remaining issues" \
pass_probe 60 crash
check "...and the pass still returns 0, so the loop reaches the next issue" 0 \
"rc=0" pass_probe 60 crash
check "...and a crash is not counted as a skip" 0 "count=0" pass_probe 60 crash
check "a skipped issue is counted and named" 0 "count=1 issues=#61" pass_probe 61
check "...and is not also reported as a crash" 1 "" \
grep -q 'reconcile failed' <<<"$(pass_probe 61)"
check "...leaving the loop free to continue" 0 "rc=0" pass_probe 61
# ---------------------------------------------------------------------------
# The arrival path, executed the way the action executes it (#91): four
# triage-authored mints died silently because the stand-down `return`s in
@ -665,7 +821,19 @@ if [ "$1" = api ]; then
*'states: MERGED'*) file="$GH_FIXTURES/graphql-merged.json" ;;
esac
fi
[ ! -f "$file.error" ] || exit 1
# `.http-error` is the real 5xx (#247): the response body — GitHub's JSON
# error object — goes to STDOUT, the reason to stderr, and the status is
# non-zero. `.error` is the payload-free failure, which is the safe path.
if [ -f "$file.http-error" ]; then
if [ -n "$jqexpr" ]; then
jq -r "$jqexpr" "$file.http-error" 2>/dev/null || true
else
cat "$file.http-error"
fi
printf '%s\n' "${GH_STUB_STDERR:-}" >&2
exit 1
fi
[ ! -f "$file.error" ] || { printf '%s\n' "${GH_STUB_STDERR:-}" >&2; exit 1; }
if [ -f "$file" ]; then payload="$(cat "$file")"; else payload='[]'; fi
if [ -n "$jqexpr" ]; then jq -r "$jqexpr" <<<"$payload"; else printf '%s\n' "$payload"; fi
exit 0
@ -833,4 +1001,245 @@ check "a dead API on the arrival path still fails the run (D2)" 0 "" \
check "...and the sweep does not run over a lying arrival" 1 "" \
grep -qF 'issueflow: reconciled.' <<<"$err_out"
# ---------------------------------------------------------------------------
# The whole sweep over an unreadable board (#247), executed. The sourced
# probes above drive one issue's pass; only this path exercises the loop, the
# counting and the tail — and only this path reproduces crew#329's log, which
# ended `issueflow: reconciled.` with rc=0 over a label it should never have
# written. Its own fixture directory: the arrival fixtures above are stateful
# across their cases.
# ---------------------------------------------------------------------------
SWEEP="$TMP/sweep"
mkdir -p "$SWEEP"
printf '%s\n' \
'{"data":{"repository":{"pullRequests":{"nodes":[],"pageInfo":{"hasNextPage":false,"endCursor":null}}}}}' \
>"$SWEEP/graphql-open.json"
cp "$SWEEP/graphql-open.json" "$SWEEP/graphql-merged.json"
# 70: the 504 with a JSON error body on the per-issue read.
printf '%s\n' "$GH_STUB_ERROR_BODY" >"$SWEEP/repos_owner_repo_issues_70.json.http-error"
# 71: healthy, and carrying no queue label — so if the sweep reaches it, it
# writes needs-triage. That write is the evidence the loop continued.
printf '%s\n' \
'{"number":71,"user":{"login":"triage-one"},"labels":[{"name":"enhancement"}],"assignees":[]}' \
>"$SWEEP/repos_owner_repo_issues_71.json"
# 72: HTTP 200 whose body is `null` — exit 0, and the label set empties just
# as it does on the 504. The shape check is the only thing that catches it.
printf 'null\n' >"$SWEEP/repos_owner_repo_issues_72.json"
sweep_board() { printf '%s\n' "$1" >"$SWEEP/repos_owner_repo_issues_state_open_per_page_100.json"; }
sweep_run() {
: >"$SWEEP/edits"
env PATH="$ARRIVAL/stub:$PATH" GH_FIXTURES="$SWEEP" ISSUEFLOW_NOW="$INOW" \
REPO=owner/repo LABELS_CONF="$ARRIVAL/labels.conf" \
bash "$ROOT/actions/issueflow-reconcile/issueflow-reconcile.sh" 2>&1
}
sweep_board '[{"number":70},{"number":71}]'
sweep_out="$(sweep_run)"
sweep_rc=$?
check "an unreadable issue does not red the sweep (D7)" 0 "" test "$sweep_rc" -eq 0
check "the 504's JSON error body is skipped, with the reason named" 0 \
"issueflow: #70: skipped this pass — could not read the issue: $GH_STUB_STDERR" \
printf '%s\n' "$sweep_out"
check "...and crew#329's label is never written" 1 "" \
grep -qF '#70: needs-triage (no queue state)' <<<"$sweep_out"
check "...nor any edit at all on the unreadable issue" 1 "" \
grep -qF 'issue edit 70' "$SWEEP/edits"
check "...while the readable issue beside it is reconciled as before" 0 "" \
grep -qxF 'issue edit 71 -R owner/repo --add-label needs-triage' "$SWEEP/edits"
check "...and the partial pass names its count and its issue" 0 \
'issueflow: 1 issue skipped this pass on an unreadable fact: #70' \
printf '%s\n' "$sweep_out"
check "...after a byte-identical reconciled. line" 0 "" \
grep -qxF 'issueflow: reconciled.' <<<"$sweep_out"
sweep_board '[{"number":72}]'
null_out="$(sweep_run)"
null_rc=$?
check "an HTTP 200 whose body is null exits 0 and writes nothing" 0 "" \
test "$null_rc" -eq 0
check "...because the shape check refuses it, on its own line" 0 \
'issueflow: #72: skipped this pass — the issue read answered a payload that is not issue #72 carrying a label array' \
printf '%s\n' "$null_out"
check "...so no label is derived from an empty label set" 1 "" \
grep -qF 'issue edit 72' "$SWEEP/edits"
check "...and the tail names it too" 0 \
'issueflow: 1 issue skipped this pass on an unreadable fact: #72' \
printf '%s\n' "$null_out"
sweep_board '[{"number":70},{"number":72}]'
both_out="$(sweep_run)"
check "two skipped issues are both named, in the plural" 0 \
'issueflow: 2 issues skipped this pass on unreadable facts: #70 #72' \
printf '%s\n' "$both_out"
sweep_board '[{"number":71}]'
whole_out="$(sweep_run)"
whole_rc=$?
check "a whole pass still exits 0" 0 "" test "$whole_rc" -eq 0
check "...ends on the byte-identical reconciled. line, with no tail after it" 0 \
"issueflow: reconciled." printf '%s\n' "$(tail -n1 <<<"$whole_out")"
check "...and says nothing about skipping" 1 "" \
grep -q 'skipped this pass' <<<"$whole_out"
# ---------------------------------------------------------------------------
# The ordering invariant (#247 D1): a skip implies ZERO writes, wherever in
# the pass the failed read lives. Round 1 measured what the per-read guards
# alone left standing — a pass could remove `stale`, or mint `needs-triage`,
# and only then reach a guarded read, fail it, and report the issue as
# skipped. The sweep said it had touched nothing while a write had landed:
# the same false report #247 exists to close, one layer along.
#
# Every composition is driven TWICE against identical fixtures, differing
# only in whether the late read answers. The healthy run is the control — it
# proves the mutation is genuinely on this path, so the failing run's "no
# edit" is a fact about the guard and not about a branch that never fired.
# Executed through the sweep, because staging is a property of the pass.
# ---------------------------------------------------------------------------
ORDER="$TMP/order"
mkdir -p "$ORDER"
cp "$SWEEP/graphql-open.json" "$SWEEP/graphql-merged.json" "$ORDER/"
order_board() { printf '%s\n' "$1" >"$ORDER/repos_owner_repo_issues_state_open_per_page_100.json"; }
order_fixture() { # $1 issue, $2 labels JSON, $3 body
jq -n --argjson n "$1" --argjson labels "$2" --arg body "${3:-}" \
--arg at "$(iso_at $((INOW - 10 * 86400)))" \
'{number: $n, created_at: $at, user: {login: "triage-one"},
labels: $labels, assignees: [], body: $body}' \
>"$ORDER/repos_owner_repo_issues_$1.json"
}
order_run() {
: >"$ORDER/edits"
env PATH="$ARRIVAL/stub:$PATH" GH_FIXTURES="$ORDER" ISSUEFLOW_NOW="$INOW" \
REPO=owner/repo LABELS_CONF="$ARRIVAL/labels.conf" \
bash "$ROOT/actions/issueflow-reconcile/issueflow-reconcile.sh" 2>&1
}
# The late read fails, or answers. `guarded_read` is what turns either into a
# skip, so which endpoint carries the sentinel is what picks the composition.
order_breaks() { printf '%s\n' "$GH_STUB_ERROR_BODY" >"$ORDER/repos_owner_repo_issues_$1_$2.json.http-error"; }
order_heals() { rm -f "$ORDER/repos_owner_repo_issues_$1_$2.json.http-error"; }
# A skip must leave no trace of the staged effect: not the write, and not the
# log line that would have announced it. Both halves, because a landed write
# under a "skipped" line and a "reconciled" line over no write are the same
# lie told from opposite ends.
order_wrote() { grep -qF "issue $2 $1" "$ORDER/edits"; }
# -- 1. unstale, then a failed activity read (the round's first composition) -
# `needs-ruling` heals an applied `stale` off before the tail reads the
# issue's activity. The read is two statements later; the write is already
# gone.
order_fixture 80 '[{"name":"ready"},{"name":"needs-ruling"},{"name":"stale"}]'
order_board '[{"number":80}]'
order_heals 80 comments
healthy_unstale="$(order_run)"
check "the control: a healthy pass really does unstale a pending ruling" 0 "" \
order_wrote 80 edit
check "...and says so" 0 "issueflow: #80: unstale (a ruling is pending)" \
printf '%s\n' "$healthy_unstale"
order_breaks 80 comments
broken_unstale="$(order_run)"
check "a failed activity read skips the unstale composition" 0 \
"issueflow: #80: skipped this pass — could not read its activity history: $GH_STUB_STDERR" \
printf '%s\n' "$broken_unstale"
check "...and the stale label is still on the issue" 1 "" order_wrote 80 edit
check "...and nothing claims it came off" 1 "" \
grep -qF 'unstale (a ruling is pending)' <<<"$broken_unstale"
# -- 2. ADD_NEEDS_TRIAGE, then a failed activity read (the second) -----------
# The mint falls through — unlike FLAG_CONFLICT, which returns — into the
# same tail. crew#329's own label, written and then disowned by the log.
order_fixture 81 '[{"name":"enhancement"},{"name":"needs-ruling"}]'
order_board '[{"number":81}]'
order_heals 81 comments
healthy_mint="$(order_run)"
check "the control: a healthy pass really does mint needs-triage here" 0 "" \
order_wrote 81 edit
check "...and says so" 0 "issueflow: #81: needs-triage (no queue state)" \
printf '%s\n' "$healthy_mint"
order_breaks 81 comments
broken_mint="$(order_run)"
check "a failed activity read skips the needs-triage composition" 0 \
"issueflow: #81: skipped this pass — could not read its activity history: $GH_STUB_STDERR" \
printf '%s\n' "$broken_mint"
check "...and crew#329's label is not written on the way out" 1 "" \
order_wrote 81 edit
check "...and nothing claims it was" 1 "" \
grep -qF '#81: needs-triage (no queue state)' <<<"$broken_mint"
# -- 3. the blockers->ready flip, then a failed TIMELINE read ----------------
# The wider class: the failing read is the second one inside
# last_issue_activity, so the comments read answers and the marker check and
# the flip both complete first. A comment AND a label edit are staged.
printf '%s\n' '{"number":82,"state":"closed"}' \
>"$ORDER/repos_owner_repo_issues_82.json"
order_fixture 83 '[{"name":"blocked"},{"name":"needs-ruling"}]' 'Blocked by #82.'
order_board '[{"number":83}]'
order_heals 83 timeline
healthy_flip="$(order_run)"
check "the control: a healthy pass really does flip cleared blockers to ready" 0 \
"issueflow: #83: blockers closed -> ready" printf '%s\n' "$healthy_flip"
check "...writing the label edit" 0 "" order_wrote 83 edit
check "...and posting the blockers-cleared comment" 0 "" order_wrote 83 comment
order_breaks 83 timeline
broken_flip="$(order_run)"
check "a failed timeline read skips the blockers->ready composition" 0 \
"issueflow: #83: skipped this pass — could not read its activity history: $GH_STUB_STDERR" \
printf '%s\n' "$broken_flip"
check "...leaving the issue blocked" 1 "" order_wrote 83 edit
check "...with no comment posted about it" 1 "" order_wrote 83 comment
check "...and nothing claiming the flip happened" 1 "" \
grep -qF 'blockers closed -> ready' <<<"$broken_flip"
# -- 4. a posted nudge, then a failed TIMELINE read -------------------------
# The comment-only half of the class: an epic nudge is staged, and the
# ruling tail's activity read fails after it. A comment is as much a
# mutation as a label — it is the thing markers exist to make idempotent.
order_fixture 84 '[{"name":"epic"},{"name":"needs-ruling"}]' \
'## Task list
- [x] #82'
order_board '[{"number":84}]'
order_heals 84 timeline
healthy_nudge="$(order_run)"
check "the control: a healthy pass really does nudge a completed epic" 0 \
"issueflow: #84: completed epic nudged" printf '%s\n' "$healthy_nudge"
check "...by posting a comment" 0 "" order_wrote 84 comment
order_breaks 84 timeline
broken_nudge="$(order_run)"
check "a failed timeline read skips the epic-nudge composition" 0 \
"issueflow: #84: skipped this pass — could not read its activity history: $GH_STUB_STDERR" \
printf '%s\n' "$broken_nudge"
check "...and the nudge comment is never posted" 1 "" order_wrote 84 comment
check "...and nothing claims it was" 1 "" \
grep -qF 'completed epic nudged' <<<"$broken_nudge"
# -- the skip is still just a skip: counted, tailed, and green (D4, D6, D7) --
check "a mutation-bearing composition that skips is still not a crash" 1 "" \
grep -qF 'reconcile failed' <<<"$broken_flip"
check "...is still counted in the D6 tail" 0 \
'issueflow: 1 issue skipped this pass on an unreadable fact: #83' \
printf '%s\n' "$broken_flip"
order_board '[{"number":83}]'
order_run >/dev/null
check "...and still leaves the job green (D7)" 0 "" test $? -eq 0
# -- the invariant is enforced at the source, not remembered ----------------
# Staging only holds while every mutation goes through run(). A future call
# site reaching gh directly would reopen this hole silently, so it is pinned
# here rather than left to review — the shape lib/ruling.sh already uses for
# #50 D9. reconcile_opened_issue is deliberately exempt: it runs outside the
# per-issue subshell, under live errexit, and stages nothing (#247 D8).
mutation_calls() {
grep -nE '(^|[^_[:alnum:]])gh issue (edit|comment)' \
"$ROOT/actions/issueflow-reconcile/issueflow-reconcile.sh" "$ROOT/lib/ruling.sh" \
| grep -vE '^\S+:[0-9]+: *#' || true
}
# shellcheck disable=SC2016 # positional parameters belong to bash -c
check "every issue mutation on this surface goes through run()" 0 "" \
bash -c 'while IFS= read -r line; do
[ -n "$line" ] || continue
case "$line" in *"run gh issue "*) ;; *) printf "unstaged mutation: %s\n" "$line"; exit 1 ;; esac
done <<<"$1"' _ "$(mutation_calls)"
check "...and the pin sees the call sites it is guarding" 0 "" \
test "$(mutation_calls | wc -l)" -ge 8
summary