stack/packages/mosaic/framework/tools/git/test-issue-comment-readback.sh

#!/usr/bin/env bash
# Regression harness for issue-comment.sh's Gitea comment write + verification
# (#865).
#
# The #865 defect class: tea 0.11.1's `tea issue comment ...` (a nonexistent
# subcommand) silently no-ops yet exits 0, and tea cannot emit the id of a
# record it created — so an exit code is worthless as proof of a durable write.
# The wrapper therefore does NOT write via tea at all. It POSTs the comment to
# the Gitea REST API (which returns the created comment object, including its
# id), then GETs THAT EXACT id back and requires it to match on id, author
# (acting identity), body, and issue. Because verification is keyed to the id
# the create returned, no concurrent comment can masquerade as this write, and a
# suppressed/no-op create yields no id and fails closed.
#
# This harness models a REAL server: the curl stub keeps persistent comment
# state on disk, the POST actually CREATES and PERSISTS a record and returns its
# id, and the read-back GET reads that same state. There is no independently
# fabricated record for the wrapper to "find" — the only way verification
# passes is if the POST genuinely created the record the read-back retrieves.
# It proves the wrapper:
#   1. never shells out to tea to write (no `tea comment` / `tea issue comment`);
#   2. creates the comment via REST POST and learns the provider-returned id;
#   3. verifies THAT EXACT id by direct GET, attributed to the acting identity;
#   4. fails closed when the write is a no-op even though a concurrent
#      SAME-IDENTITY comment with the same body already exists (the closed
#      concurrency window — no fallback list scan can rescue a no-op);
#   5. fails closed when the created record is not authored by the acting
#      identity;
#   6. treats the exact-id GET as the SOLE authority — it performs NO follow-up
#      list enumeration (the stub exposes no comment-list endpoint, so any
#      residual enumeration attempt would fail the run);
#   7. with a RESOLVABLE --login override, performs the write, the /user identity
#      lookup, and the read-back ALL under THAT login's token/identity — never
#      the host default;
#   8. with an UNRESOLVABLE --login override, FAILS CLOSED (nonzero, no write, no
#      success line) instead of silently downgrading to the host default
#      identity — the token seam maps each bearer token to the identity it
#      authenticates as, so a misattributed write is caught;
#   9. with a --login override whose tea config URL is a DIFFERENT host than the
#      repo remote, FAILS CLOSED (host-bound token selection) rather than sending
#      that other host's credential cross-host;
#  10. leaves NO temp files behind (POST/GET bodies + metadata) on either the
#      success or the failure path — nested function-scoped RETURN traps do not
#      clobber each other and every scratch file is removed on all exit paths.

set -euo pipefail

SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
WORK_DIR="${MOSAIC_TEST_WORK_DIR:-$PWD/.mosaic-test-work/issue-comment-readback}"
REPO_DIR="$WORK_DIR/repo"
BIN_DIR="$WORK_DIR/bin"
XDG_DIR="$WORK_DIR/xdg"
TEA_LOG="$WORK_DIR/tea.log"
CURL_LOG="$WORK_DIR/curl.log"
AUTH_LOG="$WORK_DIR/auth.log"
OUTPUT_FILE="$WORK_DIR/output.log"
CREDENTIALS_FILE="$WORK_DIR/credentials.json"
STATE_FILE="$WORK_DIR/comments.json"
# A dedicated scratch dir the wrapper is pointed at via TMPDIR, so the leak
# check can assert every POST/GET body + metadata temp file is cleaned up.
TMP_SCRATCH="$WORK_DIR/scratch"

cleanup() {
    rm -rf "$WORK_DIR"
}
trap cleanup EXIT

mkdir -p "$REPO_DIR" "$BIN_DIR" "$XDG_DIR" "$TMP_SCRATCH"
git -C "$REPO_DIR" init -q
git -C "$REPO_DIR" remote add origin https://git.mosaicstack.dev/mosaicstack/stack.git

ISSUE_NUMBER=7
REPO_SLUG="mosaicstack/stack"
API_BASE="https://git.mosaicstack.dev/api/v1/repos/mosaicstack/stack"
API_ROOT="https://git.mosaicstack.dev/api/v1"
BODY='durable "note" -- marker'
ACTING_LOGIN="primary-reviewer"
FOREIGN_LOGIN="other-writer"
# A dedicated per-role --login override identity, with its own token stored in
# tea's config (exactly the author-not-equal-reviewer hardening path).
OVERRIDE_LOGIN="delegated-reviewer"
DEFAULT_TOKEN="test-only-placeholder"
OVERRIDE_TOKEN="override-token-placeholder"
# A --login override whose tea config URL points at a DIFFERENT Gitea host than
# the repo remote (git.mosaicstack.dev). Its token must NEVER be sent to the
# repo host: host-bound selection must fail closed on the host mismatch.
CROSS_HOST_LOGIN="foreign-host-reviewer"
CROSS_HOST_TOKEN="cross-host-token-placeholder"

# tea config: the override login has its own token here (as tea itself stores
# per-login tokens). The default login name ("mosaicstack") is deliberately NOT
# present, so the no-override default path resolves via the host credential
# fallback while an explicit --login must resolve from this file or fail closed.
# A second login is configured for a DIFFERENT host to exercise host-bound
# rejection.
mkdir -p "$XDG_DIR/tea"
OVERRIDE_LOGIN="$OVERRIDE_LOGIN" OVERRIDE_TOKEN="$OVERRIDE_TOKEN" \
    CROSS_HOST_LOGIN="$CROSS_HOST_LOGIN" CROSS_HOST_TOKEN="$CROSS_HOST_TOKEN" \
    python3 - "$XDG_DIR/tea/config.yml" <<'PY'
import os
import sys

with open(sys.argv[1], "w", encoding="utf-8") as handle:
    handle.write("logins:\n")
    handle.write(f"  - name: {os.environ['OVERRIDE_LOGIN']}\n")
    handle.write("    url: https://git.mosaicstack.dev\n")
    handle.write(f"    token: {os.environ['OVERRIDE_TOKEN']}\n")
    handle.write(f"  - name: {os.environ['CROSS_HOST_LOGIN']}\n")
    handle.write("    url: https://git.uscllc.com\n")
    handle.write(f"    token: {os.environ['CROSS_HOST_TOKEN']}\n")
PY

CONFIGURED_GITEA_URL="https://git.mosaicstack.dev" python3 - "$CREDENTIALS_FILE" <<'PY'
import json
import os
import sys

with open(sys.argv[1], "w", encoding="utf-8") as credentials:
    json.dump({
        "gitea": {
            "mosaicstack": {
                "url": os.environ["CONFIGURED_GITEA_URL"],
                "token": "test-only-placeholder",
            }
        }
    }, credentials)
PY

# tea stub: only ever answers the login list (used to resolve the default login
# name). It must NEVER be asked to write a comment — the wrapper writes via REST.
cat > "$BIN_DIR/tea" <<'SH'
#!/usr/bin/env bash
set -euo pipefail

printf '%s\n' "$*" >> "$ISSUE_COMMENT_TEA_LOG"

if [[ "$*" == "login list --output json" ]]; then
    printf '%s\n' '[{"name":"mosaicstack","url":"https://git.mosaicstack.dev"}]'
    exit 0
fi

echo "Unexpected tea command (wrapper must not write via tea): $*" >&2
exit 92
SH
chmod +x "$BIN_DIR/tea"

# curl stub: a small REST server backed by persistent on-disk comment state.
#   GET  /user                 -> acting identity
#   POST /issues/7/comments    -> CREATE + PERSIST, return created object
#   GET  /issues/comments/{id} -> read the persisted record by exact id
# There is deliberately NO comment-LIST endpoint: exact-id read-back is the sole
# authority, so any residual list enumeration attempt hits the unexpected-request
# guard and fails the test.
cat > "$BIN_DIR/curl" <<'SH'
#!/usr/bin/env bash
set -euo pipefail

output_file=""
method="GET"
url=""
data=""
auth_token=""
while [[ $# -gt 0 ]]; do
    case "$1" in
        -o) output_file="$2"; shift 2 ;;
        -H)
            [[ "$2" == Authorization:* ]] && auth_token="${2##* }"
            shift 2 ;;
        -w) shift 2 ;;
        -X) method="$2"; shift 2 ;;
        -d|--data) data="$2"; shift 2 ;;
        -s|-S|-sS) shift ;;
        http://*|https://*) url="$1"; shift ;;
        *) shift ;;
    esac
done

path="${url%%\?*}"
query="${url#*\?}"
[[ "$query" == "$url" ]] && query=""
printf '%s %s\n' "$method" "$url" >> "$ISSUE_COMMENT_CURL_LOG"

# Map the presented bearer token to the identity it authenticates as — the same
# derivation Gitea's own /user does. The wrapper's write, /user lookup, and
# read-back must all carry the SAME token, so the acting identity recorded here
# reveals which credential actually performed the request.
acting_identity=""
case "$auth_token" in
    "$ISSUE_COMMENT_DEFAULT_TOKEN") acting_identity="$ISSUE_COMMENT_ACTING_LOGIN" ;;
    "$ISSUE_COMMENT_OVERRIDE_TOKEN") acting_identity="$ISSUE_COMMENT_OVERRIDE_LOGIN" ;;
    "$ISSUE_COMMENT_CROSS_HOST_TOKEN") acting_identity="$ISSUE_COMMENT_CROSS_HOST_LOGIN" ;;
esac
printf '%s %s %s\n' "$method" "$path" "${acting_identity:-<unauthenticated>}" >> "$ISSUE_COMMENT_AUTH_LOG"

write_response() {
    local status="$1" body="$2"
    [[ -n "$output_file" ]] || exit 96
    printf '%s' "$body" > "$output_file"
    printf '%s' "$status"
}

if [[ "$method" == "GET" && "$path" == "$ISSUE_COMMENT_API_ROOT/user" ]]; then
    [[ -n "$acting_identity" ]] || { write_response 401 '{"message":"unauthenticated"}'; exit 0; }
    write_response 200 "$(ISSUE_COMMENT_LOGIN="$acting_identity" python3 - <<'PY'
import json
import os
print(json.dumps({"login": os.environ["ISSUE_COMMENT_LOGIN"]}))
PY
)"
elif [[ "$method" == "POST" && "$path" == "$ISSUE_COMMENT_API_BASE/issues/7/comments" ]]; then
    result=$(ISSUE_COMMENT_ACTING_LOGIN="${acting_identity:-$ISSUE_COMMENT_ACTING_LOGIN}" ISSUE_COMMENT_DATA="$data" python3 - <<'PY'
import json
import os

state_path = os.environ["ISSUE_COMMENT_STATE"]
mode = os.environ["ISSUE_COMMENT_TEST_MODE"]
acting = os.environ["ISSUE_COMMENT_ACTING_LOGIN"]
foreign = os.environ["ISSUE_COMMENT_FOREIGN_LOGIN"]
repo = os.environ["ISSUE_COMMENT_REPO_SLUG"]
body = json.loads(os.environ["ISSUE_COMMENT_DATA"]).get("body")

with open(state_path, encoding="utf-8") as handle:
    comments = json.load(handle)

# no-op-concurrent: the wrapper's own write is SUPPRESSED (returns 200 with no
# created object) even though a concurrent same-identity comment already exists
# in state. Nothing is persisted; there is no created id to verify.
if mode == "no-op-concurrent":
    print("200")
    print(json.dumps({}))
    raise SystemExit(0)

author = foreign if mode == "author-mismatch" else acting
new_id = (max((c["id"] for c in comments), default=0)) + 1
record = {
    "id": new_id,
    "body": body,
    "user": {"login": author},
    # REAL Gitea comment shape: issue_url is the WEB (html) path, not an API
    # path, and a plain issue comment leaves pull_request_url empty.
    "issue_url": f"https://git.mosaicstack.dev/{repo}/issues/7",
    "pull_request_url": "",
}
comments.append(record)
with open(state_path, "w", encoding="utf-8") as handle:
    json.dump(comments, handle)
print("201")
print(json.dumps(record))
PY
)
    write_response "$(printf '%s' "$result" | head -n1)" "$(printf '%s' "$result" | tail -n +2)"
elif [[ "$method" == "GET" && "$path" == "$ISSUE_COMMENT_API_BASE"/issues/comments/* ]]; then
    result=$(ISSUE_COMMENT_GET_ID="${path##*/}" python3 - <<'PY'
import json
import os

state_path = os.environ["ISSUE_COMMENT_STATE"]
wanted = int(os.environ["ISSUE_COMMENT_GET_ID"])
with open(state_path, encoding="utf-8") as handle:
    comments = json.load(handle)
match = next((c for c in comments if c["id"] == wanted), None)
if match is None:
    print("404")
    print(json.dumps({"message": "not found"}))
else:
    print("200")
    print(json.dumps(match))
PY
)
    write_response "$(printf '%s' "$result" | head -n1)" "$(printf '%s' "$result" | tail -n +2)"
else
    echo "Unexpected curl request: $method $url" >&2
    exit 97
fi
SH
chmod +x "$BIN_DIR/curl"

# Seed persistent server state for a mode, then run the wrapper against it.
seed_state() {
    local mode="$1"
    ISSUE_COMMENT_SEED_MODE="$mode" ISSUE_COMMENT_SEED_BODY="$BODY" \
        ISSUE_COMMENT_SEED_ACTING="$ACTING_LOGIN" ISSUE_COMMENT_SEED_REPO="$REPO_SLUG" \
        python3 - "$STATE_FILE" <<'PY'
import json
import os
import sys

mode = os.environ["ISSUE_COMMENT_SEED_MODE"]
body = os.environ["ISSUE_COMMENT_SEED_BODY"]
acting = os.environ["ISSUE_COMMENT_SEED_ACTING"]
repo = os.environ["ISSUE_COMMENT_SEED_REPO"]
# REAL Gitea comment shape: issue_url is the WEB path, pull_request_url empty.
issue_url = f"https://git.mosaicstack.dev/{repo}/issues/7"


def comment(cid, text, author):
    return {
        "id": cid,
        "body": text,
        "user": {"login": author},
        "issue_url": issue_url,
        "pull_request_url": "",
    }


if mode == "fresh-success":
    # 50 pre-existing comments already exist; the comment this run creates
    # becomes id 51, proving exact-id read-back works regardless of how many
    # comments precede it (no list enumeration is involved).
    comments = [comment(i, f"prior {i}", acting) for i in range(1, 51)]
elif mode == "no-op-concurrent":
    # A concurrent SAME-IDENTITY comment with the IDENTICAL body already exists.
    # The wrapper's own write will be a no-op; it must still fail closed because
    # no created id is returned — it must not scan and accept this record.
    comments = [comment(55, body, acting)]
else:  # author-mismatch
    comments = []

with open(sys.argv[1], "w", encoding="utf-8") as handle:
    json.dump(comments, handle)
PY
}

run_comment() {
    local mode="$1"
    shift
    : > "$TEA_LOG"
    : > "$CURL_LOG"
    : > "$AUTH_LOG"
    : > "$OUTPUT_FILE"
    seed_state "$mode"
    (
        cd "$REPO_DIR"
        PATH="$BIN_DIR:$PATH" \
        TMPDIR="$TMP_SCRATCH" \
        XDG_CONFIG_HOME="$XDG_DIR" \
        MOSAIC_CREDENTIALS_FILE="$CREDENTIALS_FILE" \
        ISSUE_COMMENT_TEA_LOG="$TEA_LOG" \
        ISSUE_COMMENT_CURL_LOG="$CURL_LOG" \
        ISSUE_COMMENT_AUTH_LOG="$AUTH_LOG" \
        ISSUE_COMMENT_STATE="$STATE_FILE" \
        ISSUE_COMMENT_TEST_MODE="$mode" \
        ISSUE_COMMENT_ACTING_LOGIN="$ACTING_LOGIN" \
        ISSUE_COMMENT_FOREIGN_LOGIN="$FOREIGN_LOGIN" \
        ISSUE_COMMENT_OVERRIDE_LOGIN="$OVERRIDE_LOGIN" \
        ISSUE_COMMENT_CROSS_HOST_LOGIN="$CROSS_HOST_LOGIN" \
        ISSUE_COMMENT_DEFAULT_TOKEN="$DEFAULT_TOKEN" \
        ISSUE_COMMENT_OVERRIDE_TOKEN="$OVERRIDE_TOKEN" \
        ISSUE_COMMENT_CROSS_HOST_TOKEN="$CROSS_HOST_TOKEN" \
        ISSUE_COMMENT_REPO_SLUG="$REPO_SLUG" \
        ISSUE_COMMENT_API_BASE="$API_BASE" \
        ISSUE_COMMENT_API_ROOT="$API_ROOT" \
        "$SCRIPT_DIR/issue-comment.sh" -i "$ISSUE_NUMBER" -c "$BODY" "$@"
    ) > "$OUTPUT_FILE" 2>&1
}

# Assert the wrapper left no scratch temp files behind in TMPDIR (POST/GET
# request bodies + metadata). Called after both success and failure paths so a
# clobbered/leaked RETURN trap is caught on every exit route.
assert_no_temp_leak() {
    local context="$1" leaked
    leaked=$(find "$TMP_SCRATCH" -type f -name 'mosaic-issue-comment-*' 2>/dev/null || true)
    if [[ -n "$leaked" ]]; then
        echo "FAIL: issue-comment temp files leaked ($context):" >&2
        printf '%s\n' "$leaked" >&2
        exit 1
    fi
}

# Case 1: a genuine REST create (id 51) is verified end to end via its exact
# provider-returned id — no list enumeration is involved.
run_comment fresh-success
grep -q 'Added and verified comment on Gitea issue #7 (comment ID 51)' "$OUTPUT_FILE"
# The write is a REST POST, never a tea comment.
grep -q "^POST $API_BASE/issues/7/comments$" "$CURL_LOG"
if grep -Eq '^comment |^issue comment ' "$TEA_LOG"; then
    echo "FAIL: wrapper wrote a comment via tea instead of REST" >&2
    exit 1
fi
# Read-back is a DIRECT GET of the exact created id.
grep -q "^GET $API_BASE/issues/comments/51$" "$CURL_LOG"
# Acting identity resolved via GET /user.
grep -q "^GET $API_ROOT/user$" "$CURL_LOG"
# No comment-list enumeration is performed — the exact-id GET is authoritative.
if grep -Eq "^GET $API_BASE/issues/7/comments(\?|$)" "$CURL_LOG"; then
    echo "FAIL: wrapper performed a redundant comment-list enumeration" >&2
    exit 1
fi
# Default path (no --login): the host credential fallback resolves, and the
# write is performed AND self-verified under the host-default acting identity.
grep -q "^POST $API_BASE/issues/7/comments $ACTING_LOGIN$" "$AUTH_LOG"
grep -q "^GET $API_BASE/issues/comments/51 $ACTING_LOGIN$" "$AUTH_LOG"
# Success path leaves no scratch temp files behind.
assert_no_temp_leak "fresh-success"

# Case 2: a no-op write with a concurrent SAME-IDENTITY, same-body comment
# already present must FAIL CLOSED — the closed concurrency window.
if run_comment no-op-concurrent; then
    echo "FAIL: wrapper reported success when its write no-opped but a concurrent same-identity comment existed" >&2
    cat "$OUTPUT_FILE" >&2
    exit 1
fi
if grep -q 'Added and verified comment' "$OUTPUT_FILE"; then
    echo "FAIL: wrapper accepted a concurrent record for a no-op write (window not closed)" >&2
    exit 1
fi
# It must NOT have fallen back to a list scan that could find the concurrent id.
if grep -q "^GET $API_BASE/issues/comments/55$" "$CURL_LOG"; then
    echo "FAIL: wrapper read back the concurrent comment id 55 (illegitimate fallback)" >&2
    exit 1
fi

# Case 3: a created record NOT authored by the acting identity must FAIL CLOSED.
if run_comment author-mismatch; then
    echo "FAIL: wrapper accepted a created comment authored by a different identity" >&2
    cat "$OUTPUT_FILE" >&2
    exit 1
fi
if grep -q 'Added and verified comment' "$OUTPUT_FILE"; then
    echo "FAIL: read-back did not enforce acting-identity authorship" >&2
    exit 1
fi
# Failure-after-read-back path must ALSO leave no scratch temp files behind
# (proves the RETURN traps clean up on the error-return route, not just success).
assert_no_temp_leak "author-mismatch"

# Case 4: a RESOLVABLE --login override — the write, the /user identity lookup,
# and the read-back must ALL be performed under THAT login's token/identity, not
# the host default. The override login has id 1 (empty seed).
run_comment override-success --login "$OVERRIDE_LOGIN"
grep -q 'Added and verified comment on Gitea issue #7 (comment ID 1)' "$OUTPUT_FILE"
grep -q "^GET $API_ROOT/user $OVERRIDE_LOGIN$" "$AUTH_LOG"
grep -q "^POST $API_BASE/issues/7/comments $OVERRIDE_LOGIN$" "$AUTH_LOG"
grep -q "^GET $API_BASE/issues/comments/1 $OVERRIDE_LOGIN$" "$AUTH_LOG"
# The host-default identity must NOT have performed ANY request in this run.
if grep -q " $ACTING_LOGIN\$" "$AUTH_LOG"; then
    echo "FAIL: an explicit --login override request was performed under the host default identity" >&2
    cat "$AUTH_LOG" >&2
    exit 1
fi

# Case 5: an UNRESOLVABLE --login override (name absent from tea config) must
# FAIL CLOSED — no silent downgrade to the host default identity: nonzero exit,
# no success line, and NO write performed.
if run_comment override-unresolvable --login "nonexistent-typo-login"; then
    echo "FAIL: unresolvable --login override did not fail closed" >&2
    cat "$OUTPUT_FILE" >&2
    exit 1
fi
if grep -q 'Added and verified comment' "$OUTPUT_FILE"; then
    echo "FAIL: unresolvable --login override reported success" >&2
    exit 1
fi
if grep -q "^POST $API_BASE/issues/7/comments" "$CURL_LOG"; then
    echo "FAIL: unresolvable --login override still performed a write" >&2
    exit 1
fi
# And it must not have silently fallen back to the host default identity.
if grep -q " $ACTING_LOGIN\$" "$AUTH_LOG"; then
    echo "FAIL: unresolvable --login override fell back to the host default identity" >&2
    exit 1
fi

# Case 6: a --login override that IS present in tea config but whose URL is a
# DIFFERENT host than the repo remote must FAIL CLOSED (host-bound selection).
# The cross-host token must NEVER be sent to the repo host, and no write occurs.
if run_comment cross-host --login "$CROSS_HOST_LOGIN"; then
    echo "FAIL: cross-host --login override did not fail closed" >&2
    cat "$OUTPUT_FILE" >&2
    exit 1
fi
if grep -q 'Added and verified comment' "$OUTPUT_FILE"; then
    echo "FAIL: cross-host --login override reported success" >&2
    exit 1
fi
# The cross-host credential must not have performed ANY request against the repo
# host — no request may be attributed to the cross-host identity.
if grep -q " $CROSS_HOST_LOGIN\$" "$AUTH_LOG"; then
    echo "FAIL: cross-host credential was sent to the repo host (cross-host leak)" >&2
    cat "$AUTH_LOG" >&2
    exit 1
fi
if grep -q "^POST $API_BASE/issues/7/comments" "$CURL_LOG"; then
    echo "FAIL: cross-host --login override still performed a write" >&2
    exit 1
fi
# It must not have silently downgraded to the host default identity either.
if grep -q " $ACTING_LOGIN\$" "$AUTH_LOG"; then
    echo "FAIL: cross-host --login override fell back to the host default identity" >&2
    exit 1
fi
assert_no_temp_leak "cross-host"

echo "issue-comment.sh REST create + exact-id read-back regression passed"