fix(tools): attribute read-back to acting identity and paginate fully (#865)
All checks were successful
ci/woodpecker/pr/ci Pipeline was successful

Round 2 remediation for the read-back verification in issue-comment.sh and
pr-review.sh.

BLOCKER A (invocation attribution): id-above-boundary + content/state match
only proves temporal ordering — a concurrent write from a different identity
could satisfy it while this tea invocation created nothing. Both wrappers now
resolve the acting identity once via curl GET /api/v1/user and additionally
require the accepted record's author login to equal that identity. Residual
same-identity same-body/state concurrency is documented in-code (tea 0.11.1
emits no reliable created-record id to close it further).

BLOCKER B (pagination): the comments and reviews list reads now walk every
page (?limit=&page=1,2,… until a short/empty page) for both the pre-write
boundary and the post-write read-back, so a record beyond page 1 is still
found.

Adds regressions: concurrent different-identity write fails closed (comments
and reviews); a matching review beyond page 1 is still found. README updated.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
Hermes Agent
2026-07-21 19:02:25 -05:00
parent 10fdd49e32
commit 16481ece3d
5 changed files with 461 additions and 146 deletions

View File

@@ -193,8 +193,9 @@ PY
}
# Resolve and cache the Gitea REST endpoint + token for the current remote.
# Populates GITEA_API_BASE and GITEA_API_TOKEN. Returns non-zero (with a
# clear stderr message) on any resolution failure.
# Populates GITEA_API_ROOT (…/api/v1), GITEA_API_BASE (…/api/v1/repos/<slug>),
# and GITEA_API_TOKEN. Returns non-zero (with a clear stderr message) on any
# resolution failure.
gitea_resolve_api() {
local host configured_url repo
@@ -211,31 +212,85 @@ gitea_resolve_api() {
echo "Error: Could not resolve Gitea owner/repository relative to configured URL" >&2
return 1
}
GITEA_API_BASE="${configured_url%/}/api/v1/repos/$repo"
GITEA_API_ROOT="${configured_url%/}/api/v1"
GITEA_API_BASE="$GITEA_API_ROOT/repos/$repo"
return 0
}
# Print the maximum existing review id on a PR (0 if none). This is the
# pre-write BOUNDARY: Gitea pull-review ids are monotonic, so any review
# submitted by a subsequent `tea pr approve`/`reject` has an id strictly
# greater than this value. Bounding the read-back this way is what turns the
# check into a genuine write-verification rather than a match against any
# historical review — the same never-trust-exit-zero discipline #865 requires
# for comments, applied to the review STATE itself.
gitea_max_review_id() {
local pr_number="$1" response_file status
# Fetch every page of a Gitea list endpoint into $2 (merged into one JSON
# array). Gitea paginates list responses, so a single-page read would
# false-negative once a newly created review/comment lands beyond page 1.
# Walks page=1,2,… until a short or empty page is returned so the merged array
# is exhaustive. $1 is the endpoint URL with NO query string. Returns non-zero
# (clear stderr) on any transport / HTTP / parse failure.
gitea_fetch_all() {
local base_url="$1" dest="$2" page=1 limit=50 status page_file count
response_file=$(mktemp "${TMPDIR:-/tmp}/mosaic-pr-review-boundary.XXXXXX")
printf '[]' > "$dest"
while :; do
page_file=$(mktemp "${TMPDIR:-/tmp}/mosaic-pr-review-page.XXXXXX")
if ! status=$(curl -sS -o "$page_file" -w '%{http_code}' \
-H "Authorization: token $GITEA_API_TOKEN" \
"${base_url}?limit=${limit}&page=${page}"); then
rm -f "$page_file"
echo "Error: Gitea list read transport failed" >&2
return 1
fi
if [[ "$status" != "200" ]]; then
rm -f "$page_file"
echo "Error: Gitea list read failed with HTTP $status" >&2
return 1
fi
count=$(DEST="$dest" python3 - "$page_file" <<'PY'
import json
import os
import sys
try:
with open(os.environ["DEST"], encoding="utf-8") as merged_file:
merged = json.load(merged_file)
with open(sys.argv[1], encoding="utf-8") as page_file:
page = json.load(page_file)
if not isinstance(page, list):
raise ValueError("page response is not a list")
merged.extend(item for item in page if isinstance(item, dict))
with open(os.environ["DEST"], "w", encoding="utf-8") as merged_file:
json.dump(merged, merged_file)
except (OSError, json.JSONDecodeError, TypeError, ValueError) as error:
print(f"Error: could not merge Gitea list page: {error}", file=sys.stderr)
raise SystemExit(1)
print(len(page))
PY
) || { rm -f "$page_file"; return 1; }
rm -f "$page_file"
[[ "$count" -lt "$limit" ]] && break
page=$((page + 1))
if [[ "$page" -gt 1000 ]]; then
echo "Error: Gitea list pagination exceeded 1000 pages" >&2
return 1
fi
done
return 0
}
# Resolve the login of the identity the API token authenticates as (GET
# /user). Used to attribute a read-back review to THIS action's reviewer so a
# concurrent review from a DIFFERENT identity cannot satisfy verification.
# Prints the login on success.
gitea_authenticated_login() {
local response_file status
response_file=$(mktemp "${TMPDIR:-/tmp}/mosaic-pr-review-whoami.XXXXXX")
trap 'rm -f "$response_file"' RETURN
if ! status=$(curl -sS -o "$response_file" -w '%{http_code}' \
-H "Authorization: token $GITEA_API_TOKEN" \
"$GITEA_API_BASE/pulls/$pr_number/reviews"); then
echo "Error: Gitea review boundary read transport failed" >&2
"$GITEA_API_ROOT/user"); then
echo "Error: Gitea authenticated-identity read transport failed" >&2
return 1
fi
if [[ "$status" != "200" ]]; then
echo "Error: Gitea review boundary read failed with HTTP $status" >&2
echo "Error: Gitea authenticated-identity read failed with HTTP $status" >&2
return 1
fi
@@ -243,11 +298,39 @@ gitea_max_review_id() {
import json
import sys
try:
with open(sys.argv[1], encoding="utf-8") as response:
user = json.load(response)
login = user.get("login") if isinstance(user, dict) else None
if not isinstance(login, str) or not login:
raise ValueError("missing authenticated login")
except (OSError, json.JSONDecodeError, TypeError, ValueError) as error:
print(f"Error: could not resolve authenticated Gitea identity: {error}", file=sys.stderr)
raise SystemExit(1)
print(login)
PY
}
# Print the maximum existing review id on a PR (0 if none). This is the
# pre-write BOUNDARY: Gitea pull-review ids are monotonic, so any review
# submitted by a subsequent `tea pr approve`/`reject` has an id strictly
# greater than this value. Paginates fully so a boundary review beyond page 1
# is still counted.
gitea_max_review_id() {
local pr_number="$1" merged_file
merged_file=$(mktemp "${TMPDIR:-/tmp}/mosaic-pr-review-boundary.XXXXXX")
trap 'rm -f "$merged_file"' RETURN
gitea_fetch_all "$GITEA_API_BASE/pulls/$pr_number/reviews" "$merged_file" || return 1
python3 - "$merged_file" <<'PY'
import json
import sys
try:
with open(sys.argv[1], encoding="utf-8") as response:
reviews = json.load(response)
if not isinstance(reviews, list):
raise ValueError("response is not a review list")
ids = [r.get("id") for r in reviews if isinstance(r, dict) and isinstance(r.get("id"), int)]
print(max(ids) if ids else 0)
except (OSError, json.JSONDecodeError, TypeError, ValueError) as error:
@@ -258,21 +341,32 @@ PY
# Independently verify that `tea pr approve`/`reject` produced a durable review
# record — never trust tea's exit code alone (#865, same defect class). Require
# a review that was created by THIS action: its id must be strictly greater
# than the pre-write boundary, its state must equal the expected state
# (APPROVED / REQUEST_CHANGES), and it must have been submitted against the
# PR's current head commit. Prints the matched review id on success; fails
# closed (non-zero, clear stderr) if no such review is found.
# a review attributable to THIS action: its id must be strictly greater than
# the pre-write boundary, its author login must equal the acting identity, its
# state must equal the expected state (APPROVED / REQUEST_CHANGES), and it must
# have been submitted against the PR's current head commit. The reviews list is
# paginated fully so a matching review beyond page 1 is still found. Prints the
# matched review id on success; fails closed (non-zero, clear stderr) if no
# such review is found.
#
# id-above-boundary alone is only temporal ordering; the author-login check is
# what excludes a concurrent review submitted by a DIFFERENT identity.
#
# Residual (documented, not eliminable without a tea-emitted created-record id,
# which tea 0.11.1 does not reliably provide for approve/reject): a concurrent
# review by the SAME identity with the same state against the same head inside
# the boundary window could still be accepted. That is strictly narrower than
# temporal-only matching.
#
# Args: $1 = PR number, $2 = expected state (APPROVED|REQUEST_CHANGES),
# $3 = pre-write boundary review id.
# $3 = pre-write boundary review id, $4 = acting reviewer login.
gitea_verify_review_submitted() {
local pr_number="$1" expected_state="$2" boundary="$3"
local pr_response_file reviews_response_file status head_sha review_id
local pr_number="$1" expected_state="$2" boundary="$3" acting_login="$4"
local pr_response_file reviews_merged_file status head_sha review_id
pr_response_file=$(mktemp "${TMPDIR:-/tmp}/mosaic-pr-review-head.XXXXXX")
reviews_response_file=$(mktemp "${TMPDIR:-/tmp}/mosaic-pr-review-state.XXXXXX")
trap 'rm -f "$pr_response_file" "$reviews_response_file"' RETURN
reviews_merged_file=$(mktemp "${TMPDIR:-/tmp}/mosaic-pr-review-state.XXXXXX")
trap 'rm -f "$pr_response_file" "$reviews_merged_file"' RETURN
# Resolve the PR's current head commit so the review can be pinned to it.
if ! status=$(curl -sS -o "$pr_response_file" -w '%{http_code}' \
@@ -302,19 +396,10 @@ print(head_sha)
PY
) || return 1
if ! status=$(curl -sS -o "$reviews_response_file" -w '%{http_code}' \
-H "Authorization: token $GITEA_API_TOKEN" \
"$GITEA_API_BASE/pulls/$pr_number/reviews"); then
echo "Error: Gitea review read-back transport failed" >&2
return 1
fi
if [[ "$status" != "200" ]]; then
echo "Error: Gitea review read-back failed with HTTP $status" >&2
return 1
fi
gitea_fetch_all "$GITEA_API_BASE/pulls/$pr_number/reviews" "$reviews_merged_file" || return 1
review_id=$(EXPECTED_STATE="$expected_state" BOUNDARY_REVIEW_ID="$boundary" EXPECTED_HEAD_SHA="$head_sha" \
python3 - "$reviews_response_file" <<'PY'
review_id=$(EXPECTED_STATE="$expected_state" BOUNDARY_REVIEW_ID="$boundary" EXPECTED_HEAD_SHA="$head_sha" ACTING_LOGIN="$acting_login" \
python3 - "$reviews_merged_file" <<'PY'
import json
import os
import sys
@@ -327,22 +412,24 @@ try:
expected_state = os.environ["EXPECTED_STATE"]
boundary = int(os.environ["BOUNDARY_REVIEW_ID"])
expected_head = os.environ["EXPECTED_HEAD_SHA"]
# Require all of: created-after-boundary (this action's write), the
# expected review state, and pinned to the PR's current head commit.
# The monotonic id boundary is what proves "submitted by this action"
# rather than matching some pre-existing historical review.
acting_login = os.environ["ACTING_LOGIN"]
# Attribution to THIS action: created-after-boundary AND submitted by the
# acting reviewer identity AND expected state AND pinned to the PR's
# current head commit. The author check excludes a concurrent
# DIFFERENT-identity review that id+state+head alone would admit.
matches = [
r for r in reviews
if isinstance(r, dict)
and isinstance(r.get("id"), int)
and r.get("id") > boundary
and (r.get("user") or {}).get("login") == acting_login
and r.get("state") == expected_state
and r.get("commit_id") == expected_head
]
if not matches:
raise ValueError(
f"no {expected_state} review created by this action found "
"(id > boundary, expected state, current head); "
f"no {expected_state} review attributable to this action found "
"(id > boundary, acting identity, expected state, current head); "
"tea may have silently failed (#865 defect class)"
)
review_id = max(r["id"] for r in matches)
@@ -395,6 +482,7 @@ elif [[ "$PLATFORM" == "gitea" ]]; then
# strictly-newer review created by THIS action (never trust tea's
# exit code alone — #865 defect class applies to the review state).
gitea_resolve_api || exit 1
ACTING_LOGIN=$(gitea_authenticated_login) || exit 1
review_boundary=$(gitea_max_review_id "$PR_NUMBER") || exit 1
# tea v0.11.1 defines no --comment/-comment flag on `pr approve`;
# route any review body via the durable comment API instead (#835).
@@ -406,7 +494,7 @@ elif [[ "$PLATFORM" == "gitea" ]]; then
TEA_ARGS+=(--login "$LOGIN_OVERRIDE")
fi
tea "${TEA_ARGS[@]}"
review_id=$(gitea_verify_review_submitted "$PR_NUMBER" "APPROVED" "$review_boundary") || {
review_id=$(gitea_verify_review_submitted "$PR_NUMBER" "APPROVED" "$review_boundary" "$ACTING_LOGIN") || {
echo "Error: could not verify an APPROVED review landed on Gitea PR #$PR_NUMBER via bounded read-back; treating tea's exit code as untrustworthy (#865)." >&2
exit 1
}
@@ -427,6 +515,7 @@ elif [[ "$PLATFORM" == "gitea" ]]; then
# Record the pre-write review-id boundary BEFORE the write (see the
# approve path above for the rationale).
gitea_resolve_api || exit 1
ACTING_LOGIN=$(gitea_authenticated_login) || exit 1
review_boundary=$(gitea_max_review_id "$PR_NUMBER") || exit 1
# tea v0.11.1 defines no --comment/-comment flag on `pr reject`;
# route the review body via the durable comment API instead (#835).
@@ -438,7 +527,7 @@ elif [[ "$PLATFORM" == "gitea" ]]; then
TEA_ARGS+=(--login "$LOGIN_OVERRIDE")
fi
tea "${TEA_ARGS[@]}"
review_id=$(gitea_verify_review_submitted "$PR_NUMBER" "REQUEST_CHANGES" "$review_boundary") || {
review_id=$(gitea_verify_review_submitted "$PR_NUMBER" "REQUEST_CHANGES" "$review_boundary" "$ACTING_LOGIN") || {
echo "Error: could not verify a REQUEST_CHANGES review landed on Gitea PR #$PR_NUMBER via bounded read-back; treating tea's exit code as untrustworthy (#865)." >&2
exit 1
}