Files
stack/packages/mosaic/framework/tools/git/test-gitea-login-resolution.sh
Hermes Agent 3012b5c5e5 fix(git): fail closed on unquoted non-string YAML token scalars (#865)
Round-7 blocker-1 residual: the PyYAML-absent line-parser fallback in
detect-platform.sh (_strip_scalar) returned a stringified scalar for
UNQUOTED YAML values that PyYAML's implicit resolver types as a
non-string (int/null/bool/float/timestamp). That bypassed _accept's
isinstance(str) guard and could surface a garbage credential (e.g.
"12345", "null", "true") where the PyYAML path resolves NO token and
fails closed -- violating the module invariant that the fallback is only
ever MORE conservative than PyYAML, never less.

Root cause fix: mirror PyYAML 6.0.3's SafeLoader implicit resolver. An
unquoted plain scalar matching the null/bool/int/float/timestamp forms
now returns None (fail closed); a quoted scalar is always a string and is
accepted verbatim (quote-stripped) as before. Quoted-string handling,
scope-aware attribution, indentation, and inline-comment stripping are
unchanged. The predicate was fuzzed against real PyYAML over ~800k random
tokens with zero fail-open divergences.

Extends the forced-PyYAML-absence parser-equivalence harness with
token: 12345/null/~/yes/true/3.14 (each fails closed identically to
PyYAML) and token: "12345"/'abc' (quoted literals still accepted).

Blockers 2/3/4 (port-bound host, origin+full-path URL pin, review-body
binding) are untouched.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-21 22:17:09 -05:00

481 lines
18 KiB
Bash
Executable File

#!/usr/bin/env bash
# Regression harness for host-specific Gitea tea login resolution.
set -euo pipefail
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
WORK_DIR="${MOSAIC_TEST_WORK_DIR:-$PWD/.mosaic-test-work/gitea-login-resolution}"
REPO_DIR="$WORK_DIR/repo"
BIN_DIR="$WORK_DIR/bin"
LOG_FILE="$WORK_DIR/calls.log"
CREDENTIALS_FILE="$WORK_DIR/credentials.json"
rm -rf "$WORK_DIR"
mkdir -p "$REPO_DIR" "$BIN_DIR"
git -C "$REPO_DIR" init -q
git -C "$REPO_DIR" remote add origin https://git.uscllc.com/USC/uconnect.git
cat > "$CREDENTIALS_FILE" <<'JSON'
{
"gitea": {
"mosaicstack": {
"url": "https://git.mosaicstack.dev",
"token": "mosaic-token"
},
"usc": {
"url": "https://git.uscllc.com",
"token": "usc-token"
}
}
}
JSON
cat > "$BIN_DIR/tea" <<'SH'
#!/usr/bin/env bash
set -euo pipefail
if [[ "$*" == "login list --output json" ]]; then
cat <<'JSON'
[
{"name":"evil-usc","url":"https://evilgit.uscllc.com","user":"bad.actor"},
{"name":"usc","url":"https://git.uscllc.com","user":"ci-bot"}
]
JSON
exit 0
fi
if [[ "${1:-}" == "api" ]]; then
printf '%s\n' '{"login":"ci-bot"}'
exit 0
fi
printf 'tea %s\n' "$*" >> "$MOSAIC_TEST_LOG"
if [[ "${MOSAIC_TEA_FAIL_PR_CREATE:-}" == "1" && "$*" == pr\ create* ]]; then
echo 'GetUserByName: simulated stale login failure' >&2
exit 1
fi
exit 0
SH
cat > "$BIN_DIR/curl" <<'SH'
#!/usr/bin/env bash
set -euo pipefail
printf 'curl %s\n' "$*" >> "$MOSAIC_TEST_LOG"
url="${*: -1}"
case "$url" in
*/pulls/*.diff)
printf 'diff --git a/file b/file\n'
;;
*/pulls/*)
printf '{"head":{"sha":"abc123"}}'
;;
*/commits/*/status)
printf '{"state":"success","statuses":[{"context":"ci/mock","status":"success"}]}'
;;
*)
printf '{}'
;;
esac
SH
chmod +x "$BIN_DIR/tea" "$BIN_DIR/curl"
run_in_repo() {
(
cd "$REPO_DIR"
PATH="$BIN_DIR:$PATH" \
MOSAIC_CREDENTIALS_FILE="$CREDENTIALS_FILE" \
MOSAIC_TEST_LOG="$LOG_FILE" \
"$@"
)
}
usc_login=$(run_in_repo bash -c '
export GITEA_LOGIN=mosaicstack
export GITEA_URL=https://git.mosaicstack.dev
source "'"$SCRIPT_DIR"'/detect-platform.sh"
get_gitea_login
')
if [[ "$usc_login" != "usc" ]]; then
echo "Expected USC host to resolve tea login 'usc' despite stale mosaicstack env; got '$usc_login'" >&2
exit 1
fi
usc_login_with_usc_url=$(run_in_repo bash -c '
export GITEA_LOGIN=mosaicstack
export GITEA_URL=https://git.uscllc.com
source "'"$SCRIPT_DIR"'/detect-platform.sh"
get_gitea_login
')
if [[ "$usc_login_with_usc_url" != "usc" ]]; then
echo "Expected USC host to reject stale GITEA_LOGIN even when GITEA_URL matches USC; got '$usc_login_with_usc_url'" >&2
exit 1
fi
usc_login_without_url=$(run_in_repo bash -c '
export GITEA_LOGIN=mosaicstack
unset GITEA_URL
source "'"$SCRIPT_DIR"'/detect-platform.sh"
get_gitea_login
')
if [[ "$usc_login_without_url" != "usc" ]]; then
echo "Expected USC host to ignore unmatched GITEA_LOGIN without URL; got '$usc_login_without_url'" >&2
exit 1
fi
git -C "$REPO_DIR" remote set-url origin https://hermes:token@git.uscllc.com/USC/uconnect.git
embedded_host=$(run_in_repo bash -c '
source "'"$SCRIPT_DIR"'/detect-platform.sh"
get_remote_host
')
if [[ "$embedded_host" != "git.uscllc.com" ]]; then
echo "Expected credential-bearing remote host to strip userinfo; got '$embedded_host'" >&2
exit 1
fi
git -C "$REPO_DIR" remote set-url origin https://git.uscllc.com/USC/uconnect.git
override_login=$(run_in_repo bash -c '
export GITEA_LOGIN=usc
source "'"$SCRIPT_DIR"'/detect-platform.sh"
get_gitea_login_for_repo_override
')
if [[ "$override_login" != "usc" ]]; then
echo "Expected --repo override path to honor explicit GITEA_LOGIN; got '$override_login'" >&2
exit 1
fi
git -C "$REPO_DIR" remote set-url origin https://git.mosaicstack.dev/mosaicstack/stack.git
: > "$LOG_FILE"
run_in_repo env GITEA_LOGIN=usc "$SCRIPT_DIR/issue-list.sh" --repo USC/uconnect -n 1
grep -q -- 'tea issues list --repo USC/uconnect --login usc' "$LOG_FILE"
git -C "$REPO_DIR" remote set-url origin https://git.uscllc.com/USC/uconnect.git
: > "$LOG_FILE"
run_in_repo "$SCRIPT_DIR/issue-close.sh" -i 42
grep -q -- 'tea issue close 42 --repo USC/uconnect --login usc' "$LOG_FILE"
if grep -q -- '--login mosaicstack' "$LOG_FILE"; then
echo "issue-close.sh used hardcoded mosaicstack login on USC host" >&2
exit 1
fi
: > "$LOG_FILE"
run_in_repo "$SCRIPT_DIR/milestone-list.sh"
grep -q -- 'tea milestone list --repo USC/uconnect --login usc' "$LOG_FILE"
: > "$LOG_FILE"
run_in_repo "$SCRIPT_DIR/milestone-create.sh" -t "0.2.0" -d "USC milestone"
grep -q -- 'tea milestones create --title 0.2.0 --description USC milestone --repo USC/uconnect --login usc' "$LOG_FILE"
: > "$LOG_FILE"
run_in_repo "$SCRIPT_DIR/milestone-close.sh" -t "0.2.0"
grep -q -- 'tea milestone close 0.2.0 --repo USC/uconnect --login usc' "$LOG_FILE"
if command -v pwsh >/dev/null 2>&1; then
: > "$LOG_FILE"
run_in_repo pwsh -NoProfile -File "$SCRIPT_DIR/issue-list.ps1" -Limit 1
grep -q -- 'tea issues list --state open --limit 1 --repo USC/uconnect --login usc' "$LOG_FILE"
: > "$LOG_FILE"
run_in_repo pwsh -NoProfile -File "$SCRIPT_DIR/issue-create.ps1" -Title "PowerShell issue"
grep -q -- 'tea issue create --title PowerShell issue --repo USC/uconnect --login usc' "$LOG_FILE"
: > "$LOG_FILE"
run_in_repo pwsh -NoProfile -File "$SCRIPT_DIR/pr-list.ps1" -Limit 1
grep -q -- 'tea pr list --state open --limit 1 --repo USC/uconnect --login usc' "$LOG_FILE"
: > "$LOG_FILE"
run_in_repo pwsh -NoProfile -File "$SCRIPT_DIR/pr-create.ps1" -Title "PowerShell PR"
grep -q -- 'tea pr create --title PowerShell PR --head master --repo USC/uconnect --login usc' "$LOG_FILE"
: > "$LOG_FILE"
run_in_repo pwsh -NoProfile -File "$SCRIPT_DIR/pr-merge.ps1" -Number 42 -SkipQueueGuard
grep -q -- 'tea pr merge 42 --style squash --repo USC/uconnect --login usc' "$LOG_FILE"
: > "$LOG_FILE"
run_in_repo pwsh -NoProfile -File "$SCRIPT_DIR/milestone-create.ps1" -List
grep -q -- 'tea milestones list --repo USC/uconnect --login usc' "$LOG_FILE"
fi
: > "$LOG_FILE"
if run_in_repo "$SCRIPT_DIR/pr-diff.sh" --repo USC/uconnect -n 7 >/dev/null 2>&1; then
echo "Expected pr-diff.sh --repo without host to fail loud" >&2
exit 1
fi
if grep -q -- 'git.mosaicstack.dev/api/v1/repos/USC/uconnect' "$LOG_FILE"; then
echo "pr-diff.sh --repo defaulted API host to git.mosaicstack.dev" >&2
exit 1
fi
: > "$LOG_FILE"
run_in_repo env GITEA_URL=https://git.uscllc.com "$SCRIPT_DIR/pr-diff.sh" --repo USC/uconnect -n 7 >/dev/null
grep -q -- 'curl .*https://git.uscllc.com/api/v1/repos/USC/uconnect/pulls/7.diff' "$LOG_FILE"
: > "$LOG_FILE"
run_in_repo "$SCRIPT_DIR/pr-ci-wait.sh" --repo USC/uconnect --host git.uscllc.com -n 9 -t 2 -i 1
grep -q -- 'curl .*https://git.uscllc.com/api/v1/repos/USC/uconnect/pulls/9' "$LOG_FILE"
grep -q -- 'curl .*https://git.uscllc.com/api/v1/repos/USC/uconnect/commits/abc123/status' "$LOG_FILE"
: > "$LOG_FILE"
run_in_repo env MOSAIC_TEA_FAIL_PR_CREATE=1 GITEA_TOKEN=usc-token GITEA_URL=https://git.uscllc.com "$SCRIPT_DIR/pr-create.sh" -t "USC API fallback" -H feature/pr-create
grep -q -- 'tea pr create --repo USC/uconnect --login usc --title USC API fallback --head feature/pr-create' "$LOG_FILE"
grep -q -- 'curl .*Authorization: token usc-token .*https://git.uscllc.com/api/v1/repos/USC/uconnect/pulls' "$LOG_FILE"
if grep -q -- 'git.mosaicstack.dev/api/v1/repos/USC/uconnect/pulls' "$LOG_FILE"; then
echo "pr-create.sh API fallback defaulted USC repo to git.mosaicstack.dev" >&2
exit 1
fi
git -C "$REPO_DIR" remote set-url origin https://git.mosaicstack.dev/mosaicstack/stack.git
: > "$LOG_FILE"
run_in_repo env GITEA_TOKEN=mosaic-token GITEA_URL=https://git.mosaicstack.dev "$SCRIPT_DIR/issue-close.sh" -i 536
grep -q -- 'curl .*https://git.mosaicstack.dev/api/v1/repos/mosaicstack/stack/issues/536' "$LOG_FILE"
if grep -q -- 'tea issue close 536 .*--login mosaicstack' "$LOG_FILE"; then
echo "issue-close.sh invented a mosaicstack tea login instead of using API fallback" >&2
exit 1
fi
# ---------------------------------------------------------------------------
# #560: loud diagnostic + host-derived login for BOTH instances + override-wins
# ---------------------------------------------------------------------------
# Loud diagnostic: a host with no matching tea login must emit an actionable
# error to stderr (the previous behavior was a SILENT failure). The original
# mock defines only usc/evil-usc logins, so mosaicstack resolution fails here.
git -C "$REPO_DIR" remote set-url origin https://git.mosaicstack.dev/mosaicstack/stack.git
diag_stderr=$(run_in_repo bash -c '
source "'"$SCRIPT_DIR"'/detect-platform.sh"
get_gitea_login_for_host git.mosaicstack.dev
' 2>&1 1>/dev/null || true)
if ! grep -q "no Gitea tea login matches host 'git.mosaicstack.dev'" <<<"$diag_stderr"; then
echo "Expected loud diagnostic naming the unresolved host; got: $diag_stderr" >&2
exit 1
fi
if ! grep -q "Available tea logins:" <<<"$diag_stderr"; then
echo "Expected diagnostic to list available tea logins; got: $diag_stderr" >&2
exit 1
fi
# Both-instance host derivation + override-wins, using a mock that DOES define a
# mosaicstack login. Scoped to this section so the API-fallback assertions above
# (which rely on mosaicstack having NO tea login) remain valid.
BIN_DIR2="$WORK_DIR/bin2"
mkdir -p "$BIN_DIR2"
cp "$BIN_DIR/curl" "$BIN_DIR2/curl"
cat > "$BIN_DIR2/tea" <<'SH'
#!/usr/bin/env bash
set -euo pipefail
if [[ "$*" == "login list --output json" ]]; then
cat <<'JSON'
[
{"name":"mosaicstack","url":"https://git.mosaicstack.dev","user":"ci-bot"},
{"name":"usc","url":"https://git.uscllc.com","user":"ci-bot"}
]
JSON
exit 0
fi
printf 'tea %s\n' "$*" >> "$MOSAIC_TEST_LOG"
exit 0
SH
chmod +x "$BIN_DIR2/tea"
run_in_repo2() {
(
cd "$REPO_DIR"
PATH="$BIN_DIR2:$PATH" \
MOSAIC_CREDENTIALS_FILE="$CREDENTIALS_FILE" \
MOSAIC_TEST_LOG="$LOG_FILE" \
"$@"
)
}
git -C "$REPO_DIR" remote set-url origin https://git.mosaicstack.dev/mosaicstack/stack.git
mosaic_login=$(run_in_repo2 bash -c 'source "'"$SCRIPT_DIR"'/detect-platform.sh"; get_gitea_login')
if [[ "$mosaic_login" != "mosaicstack" ]]; then
echo "Expected mosaicstack origin to derive login 'mosaicstack'; got '$mosaic_login'" >&2
exit 1
fi
git -C "$REPO_DIR" remote set-url origin https://git.uscllc.com/USC/uconnect.git
usc_login_derived=$(run_in_repo2 bash -c 'source "'"$SCRIPT_DIR"'/detect-platform.sh"; get_gitea_login')
if [[ "$usc_login_derived" != "usc" ]]; then
echo "Expected usc origin to derive login 'usc'; got '$usc_login_derived'" >&2
exit 1
fi
# Explicit GITEA_LOGIN override is honored when it matches the host.
git -C "$REPO_DIR" remote set-url origin https://git.mosaicstack.dev/mosaicstack/stack.git
override_wins=$(run_in_repo2 bash -c 'export GITEA_LOGIN=mosaicstack; source "'"$SCRIPT_DIR"'/detect-platform.sh"; get_gitea_login')
if [[ "$override_wins" != "mosaicstack" ]]; then
echo "Expected valid GITEA_LOGIN override to win on mosaicstack host; got '$override_wins'" >&2
exit 1
fi
git -C "$REPO_DIR" remote set-url origin https://git.uscllc.com/USC/uconnect.git
# ---------------------------------------------------------------------------
# #865 Blocker 1 & 2: get_gitea_token_for_login must resolve the SAME token as
# PyYAML would (or fail closed identically) even when PyYAML is ABSENT, and must
# bind the credential to the repo host's scheme + host + EFFECTIVE PORT — not the
# hostname alone. These fixtures probe the ImportError-dispatched line-parser
# fallback under FORCED PyYAML absence with adversarial YAML shapes, asserting it
# NEVER misattributes a token from a nested sub-map or a mis-indented line, strips
# inline comments like PyYAML, fails closed where PyYAML errors, and rejects a
# port mismatch while accepting an exact / default-port match. When PyYAML is
# available the same fixtures also assert the PyYAML path agrees (equivalence).
# ---------------------------------------------------------------------------
FIXTURE_XDG="$WORK_DIR/tokenfix"
NOYAML_DIR="$WORK_DIR/noyaml"
mkdir -p "$FIXTURE_XDG/tea" "$NOYAML_DIR"
# A shadow `yaml` module that raises ImportError, forcing the fallback path.
printf 'raise ImportError("forced-absent for #865 fallback regression")\n' > "$NOYAML_DIR/yaml.py"
if python3 -c 'import yaml' >/dev/null 2>&1; then HAVE_PYYAML=true; else HAVE_PYYAML=false; fi
# Confirm the shim really does force ImportError, so the fallback is exercised.
if python3 -c 'import yaml' >/dev/null 2>&1; then
if PYTHONPATH="$NOYAML_DIR" python3 -c 'import yaml' >/dev/null 2>&1; then
echo "FAIL: PyYAML-absence shim did not force ImportError (fallback not exercised)" >&2
exit 1
fi
fi
write_fixture() { printf '%s' "$1" > "$FIXTURE_XDG/tea/config.yml"; }
# Resolve a token via the FORCED-fallback path (PyYAML shimmed to ImportError).
token_fallback() {
(
cd "$REPO_DIR"
XDG_CONFIG_HOME="$FIXTURE_XDG" PYTHONPATH="$NOYAML_DIR" bash -c '
source "'"$SCRIPT_DIR"'/detect-platform.sh"
get_gitea_token_for_login "$1" "$2"
' _ "$1" "$2"
) 2>/dev/null || true
}
# Resolve a token via the normal path (uses PyYAML when installed).
token_pyyaml() {
(
cd "$REPO_DIR"
XDG_CONFIG_HOME="$FIXTURE_XDG" bash -c '
source "'"$SCRIPT_DIR"'/detect-platform.sh"
get_gitea_token_for_login "$1" "$2"
' _ "$1" "$2"
) 2>/dev/null || true
}
assert_token() {
local desc="$1" expected="$2" login="$3" host="$4" got
got=$(token_fallback "$login" "$host")
if [[ "$got" != "$expected" ]]; then
echo "FAIL fallback [$desc]: expected [$expected] got [$got]" >&2
exit 1
fi
if [[ "$HAVE_PYYAML" == true ]]; then
got=$(token_pyyaml "$login" "$host")
if [[ "$got" != "$expected" ]]; then
echo "FAIL pyyaml [$desc]: expected [$expected] got [$got]" >&2
exit 1
fi
fi
}
# 1. Plain, well-formed entry resolves its token.
write_fixture 'logins:
- name: primary
url: https://git.example
token: TOK_PLAIN
'
assert_token "plain scalar" "TOK_PLAIN" primary git.example
# 2. A token nested inside a deeper SUB-MAP must NOT attach to the entry — PyYAML
# resolves the entry's own token to None here, so the fallback must too.
write_fixture 'logins:
- name: primary
url: https://git.example
extra:
token: TOK_NESTED_ATTACKER
- name: other
url: https://git.example
token: TOK_OTHER
'
assert_token "nested sub-map token is not attributed" "" primary git.example
assert_token "sibling entry still resolves its own token" "TOK_OTHER" other git.example
# 3. A MIS-INDENTED token line (deeper than the entry's fields) must not attach;
# PyYAML errors on this shape, so both fail closed.
write_fixture 'logins:
- name: primary
url: https://git.example
token: TOK_MISINDENT
'
assert_token "mis-indented token fails closed" "" primary git.example
# 4. A trailing inline comment on a scalar is stripped, exactly as PyYAML does.
write_fixture 'logins:
- name: primary
url: https://git.example
token: TOK_INLINE # trailing note
'
assert_token "inline comment stripped" "TOK_INLINE" primary git.example
# 5. A PyYAML-fail-closed case: tab indentation. PyYAML raises a scanner error;
# the fallback resolves no token. Both fail closed identically.
write_fixture "$(printf 'logins:\n - name: primary\n url: https://git.example\n\ttoken: TOK_TAB\n')"
assert_token "tab-indent fails closed like PyYAML" "" primary git.example
# 6. Host binding is scheme + host + EFFECTIVE PORT, not hostname alone.
write_fixture 'logins:
- name: ported
url: https://git.example:8443
token: TOK_PORTED
'
assert_token "explicit port exact match accepted" "TOK_PORTED" ported git.example:8443
assert_token "portless repo host rejects :8443 login" "" ported git.example
assert_token "wrong explicit port rejected" "" ported git.example:9443
# 7. An implicit (portless) login URL equals the scheme's explicit default port.
write_fixture 'logins:
- name: defported
url: https://git.example
token: TOK_DEFPORT
'
assert_token "implicit https vs explicit :443 match" "TOK_DEFPORT" defported git.example:443
assert_token "implicit https vs :8443 rejected" "" defported git.example:8443
# 8. An UNQUOTED token whose raw text PyYAML's implicit resolver types as a
# NON-string (int / null / bool / float) must fail closed: PyYAML yields a
# non-str value that _accept rejects, so the fallback must NOT surface the
# stringified scalar as a credential. Each raw form fails closed IDENTICALLY
# to PyYAML (a prior residual emitted "12345"/"null"/"true"/etc. here).
assert_nonstring_token_fails_closed() {
local desc="$1" raw="$2"
write_fixture "logins:
- name: primary
url: https://git.example
token: ${raw}
"
assert_token "$desc" "" primary git.example
}
assert_nonstring_token_fails_closed "unquoted int token fails closed" "12345"
assert_nonstring_token_fails_closed "unquoted null token fails closed" "null"
assert_nonstring_token_fails_closed "unquoted tilde-null token fails closed" "~"
assert_nonstring_token_fails_closed "unquoted yes(bool) token fails closed" "yes"
assert_nonstring_token_fails_closed "unquoted true(bool) token fails closed" "true"
assert_nonstring_token_fails_closed "unquoted float token fails closed" "3.14"
# 9. A QUOTED scalar is ALWAYS a string, even when its contents look like a
# non-string implicit form. The quotes force str typing in PyYAML, so the
# fallback must accept the literal (quote-stripped) contents as the token.
write_fixture 'logins:
- name: primary
url: https://git.example
token: "12345"
'
assert_token "double-quoted digit token is a literal string" "12345" primary git.example
write_fixture "logins:
- name: primary
url: https://git.example
token: 'abc'
"
assert_token "single-quoted token is a literal string" "abc" primary git.example
echo "Gitea login resolution regression harness passed"