merge: absorb main into next — 23-commit divergence (08-05..13 base=main window)
ci/woodpecker/pr/ci Pipeline failed

17 content commits + 3 merge bubbles were genuinely missing from next (~8,000 lines:
goal controller #1152, framework enforcement #1174/#1195, pr-edit wrapper #1173/#1200,
pipefail series #1100/#1105/#1106/#1107, git-tools fixes #1073/#1085/#1086/#1089,
#991, #1007, enrollment tolerance #1094). 3 commits were already in next by content
(#1060 identical, #1066/#1062 evolved twins — conflicts resolved to next's side).

Per-commit classification and evidence: mosaic-brain fleet/lanes/stack-remediation/main-next-divergence.md.
Conflict resolutions (6 files) itemized in the PR body.
This commit is contained in:
2026-08-19 16:27:17 -05:00
105 changed files with 7967 additions and 208 deletions
@@ -5,7 +5,10 @@
detect_platform() {
local remote_url
remote_url=$(git remote get-url origin 2>/dev/null)
# `|| true` is load-bearing under `set -e`: outside a git repo this returns 128 and
# kills the CALLER before the -z check below can run, so the error message that is
# already written here was unreachable. Same idiom as get_gitea_repo_args() below.
remote_url=$(git remote get-url origin 2>/dev/null) || true
if [[ -z "$remote_url" ]]; then
echo "error: not a git repository or no origin remote" >&2
@@ -39,7 +42,10 @@ detect_platform() {
get_repo_info() {
local remote_url
remote_url=$(git remote get-url origin 2>/dev/null)
# `|| true` is load-bearing under `set -e`: outside a git repo this returns 128 and
# kills the CALLER before the -z check below can run, so the error message that is
# already written here was unreachable. Same idiom as get_gitea_repo_args() below.
remote_url=$(git remote get-url origin 2>/dev/null) || true
if [[ -z "$remote_url" ]]; then
echo "error: not a git repository or no origin remote" >&2
@@ -240,6 +246,21 @@ PY
} >&2
}
# Explain tea's most misleading failure. `user does not exist [uid: 0, name: ]` reads
# as a missing account; it almost always means a REVOKED OR STALE TOKEN. `tea login`
# keeps its OWN COPY of the token, so rotating the credential store does not update it.
# Diagnostic only -- stderr, no control flow, no exit.
explain_tea_user_does_not_exist() {
cat >&2 <<'MSG'
NOTE: `user does not exist [uid: 0, name: ]` from tea usually means a REVOKED OR STALE TOKEN,
not a missing account. A `tea login` stores its OWN COPY of the token; rotating the
credential store does NOT update it.
CHECK: the login's cached copy (`tea login list` -- read the FULL table, never `| head`),
then re-register that login against the current token.
DO NOT probe capability with a mutating request; a POST is the action, not a check.
MSG
}
get_gitea_login_for_host() {
local host="${1:-}"
local login
@@ -91,13 +91,32 @@ elif [[ "$PLATFORM" == "gitea" ]]; then
GITEA_LOGIN_NAME=$(get_gitea_login || true)
if [[ -n "$GITEA_LOGIN_NAME" ]]; then
if [[ -n "$COMMENT" ]]; then
tea issue comment "$ISSUE_NUMBER" "$COMMENT" --repo "$OWNER/$REPO" --login "$GITEA_LOGIN_NAME"
# `tea issue comment` is NOT a subcommand -- tea 0.11.x lists only
# list/create/edit/reopen/close under `tea issue`. Comments are the
# TOP-LEVEL `tea comment`, which takes the same --repo/--login flags.
# The old call therefore always failed, was unchecked, and the script
# closed the issue anyway, losing the record of WHY.
#
# Use `tea comment` rather than the API helper so the comment and the
# close are made by the SAME principal ($GITEA_LOGIN_NAME). Routing the
# comment through the token-authenticated helper here would attribute the
# comment to the token holder and the close to the tea login -- two
# principals for one operation.
tea comment "$ISSUE_NUMBER" "$COMMENT" --repo "$OWNER/$REPO" --login "$GITEA_LOGIN_NAME" || {
echo "Error: failed to post comment on #$ISSUE_NUMBER -- NOT closing (fail closed)." >&2
exit 1
}
fi
tea issue close "$ISSUE_NUMBER" --repo "$OWNER/$REPO" --login "$GITEA_LOGIN_NAME"
else
echo "No tea login configured for $(get_remote_host); using authenticated Gitea API fallback." >&2
if [[ -n "$COMMENT" ]]; then
gitea_issue_comment_api
# Fail closed here too: an unchecked comment lets the issue close without its
# audit trail, which is the same defect as the tea path above.
gitea_issue_comment_api || {
echo "Error: failed to post comment on #$ISSUE_NUMBER -- NOT closing (fail closed)." >&2
exit 1
}
fi
gitea_issue_close_api
fi
@@ -254,15 +254,32 @@ from urllib.parse import urlparse
def _origin_and_path(url):
# Normalize a URL to (scheme, host, effective-port) + comment path. The port
# defaults to the scheme's default (80 http / 443 otherwise) so an implicit
# port and its explicit default form compare equal.
# Normalize a URL to (scheme-class, host, distinguishing-port) + comment path.
#
# #991: http and https collapse into ONE scheme class ("web"). A Gitea whose
# ROOT_URL is configured http:// returns http:// object URLs even when every
# client reaches it over https://, so a scheme-strict comparison rejects the
# provider's own correct answer about a write that landed — a deterministic
# false negative on every comment posted against such a deployment. The
# scheme is also not what this check defends: the forgeries it exists to
# catch (look-alike host, decoy path prefix, wrong owner/repo/number) all
# vary the HOST or the PATH, both of which stay strict below. Any OTHER
# scheme (file:, ftp:, javascript:) remains distinguishing and is rejected.
#
# Port: an implicit port and its own scheme's default compare equal, so
# http://h == https://h. An EXPLICIT non-default port still distinguishes,
# because a different port is a different service on the same host.
parsed = urlparse(url or "")
scheme = (parsed.scheme or "").lower()
host = (parsed.hostname or "").lower()
default_port = 80 if scheme == "http" else 443
port = parsed.port if parsed.port is not None else default_port
return (scheme, host, port), parsed.path.rstrip("/")
if scheme in ("http", "https"):
scheme_class = "web"
default_port = 80 if scheme == "http" else 443
port = None if parsed.port in (None, default_port) else parsed.port
else:
scheme_class = scheme
port = parsed.port
return (scheme_class, host, port), parsed.path.rstrip("/")
try:
@@ -156,6 +156,7 @@ case "$PLATFORM" in
exit 0
fi
echo "Warning: tea issue create failed, trying Gitea API fallback..." >&2
{ declare -F explain_tea_user_does_not_exist >/dev/null && explain_tea_user_does_not_exist; } || true
fi
gitea_issue_create_api
;;
@@ -71,6 +71,7 @@ elif [[ "$PLATFORM" == "gitea" ]]; then
exit 0
fi
echo "Warning: tea issue view failed, trying Gitea API fallback..." >&2
{ declare -F explain_tea_user_does_not_exist >/dev/null && explain_tea_user_does_not_exist; } || true
fi
gitea_issue_view_api
else
+306
View File
@@ -0,0 +1,306 @@
#!/usr/bin/env bash
# mosaic-worktree.sh — the only supported way to create and dispose of a git
# worktree on a fleet host.
#
# Why this exists as a helper and not as a rule: the rule already existed, in
# the framework's own words ("Big work → /var/tmp"), and 255 GB accumulated in
# $HOME across 842 directories anyway. Five placement conventions were live on
# one fleet host simultaneously. Every one was a decision an agent had to make,
# and a decision an agent has to make is a decision that drifts.
#
# So this script makes NO placement decision available. The caller supplies a
# branch name. Every path is DERIVED:
#
# main worktree <- git worktree list --porcelain (never cwd, which may
# itself already be a worktree)
# REPO_NAME <- basename of the main worktree
# REPO_PARENT <- dirname of the main worktree
# WT_ROOT <- $REPO_PARENT/$REPO_NAME-worktrees
# SLUG <- branch with '/' replaced by '-'
# WT_PATH <- $WT_ROOT/$SLUG
#
# The derivation puts the worktree on the same filesystem as the object store
# it shares, as a sibling of the repo, under one root per repo. Those are the
# properties that make the checkout cheap and — via `git worktree list` —
# enumerable, which is the only reason automated cleanup can ever be safe.
#
# Usage:
# mosaic-worktree.sh new <branch> [--from <base>] create (branch may exist)
# mosaic-worktree.sh path <branch> print derived path, no side effect
# mosaic-worktree.sh list this repo's worktrees + state
# mosaic-worktree.sh rm <branch> [--force] remove; refuses to lose work
# mosaic-worktree.sh gc [--apply] report/remove clean+pushed worktrees
#
# `rm` and `gc` refuse to delete a worktree with uncommitted changes, with
# commits absent from every remote, or holding ignored files that are not of the
# well-known regenerable kind (a `.env` is ignored so it is never committed,
# which is also why nothing else holds a copy). That check is by EVIDENCE, never
# by size or age. --force overrides it and is yours to type deliberately.
#
# Run from anywhere inside the repo, or pass --repo <path>.
set -euo pipefail
die() { printf 'mosaic-worktree: %s\n' "$*" >&2; exit 1; }
REPO_HINT=""
ARGS=()
while [ $# -gt 0 ]; do
case "$1" in
--repo) REPO_HINT="${2:-}"; shift 2 ;;
*) ARGS+=("$1"); shift ;;
esac
done
set -- "${ARGS[@]+"${ARGS[@]}"}"
CMD="${1:-}"
[ -n "$CMD" ] || die "no command. Try: new | path | list | rm | gc"
shift || true
# ---- mechanical derivation -------------------------------------------------
# The FIRST entry of `git worktree list --porcelain` is always the main
# worktree, regardless of which worktree we are standing in. Deriving from cwd
# would nest worktrees inside worktrees.
resolve_repo() {
local start="${REPO_HINT:-$PWD}"
git -C "$start" rev-parse --git-dir >/dev/null 2>&1 \
|| die "not inside a git repository: $start"
# Take the first entry WITHOUT closing the pipe early. `awk ... exit` on the
# first match closes the read end while git is still writing, git takes SIGPIPE,
# and under `set -euo pipefail` the command substitution returns 141 and this
# function aborts SILENTLY — no message, no worktree, and `new` exits 141 while
# printing nothing at all.
#
# Whether it happens depends on how much git still had to write when awk left,
# so the failure is a function of REPO SIZE: fine on a repo with three
# worktrees, reliably broken on one with seventy. That is backwards — the repos
# this helper exists to serve are exactly the ones that accumulated worktrees,
# and it silently did nothing on those while working everywhere it was tried.
# Measured on a repo with 73 worktrees (10 KB of porcelain): rc=141, no output.
#
# The file's own comment block below already names this class for `head -200`
# and removed that cap for the same reason. The `exit` here is the same defect
# in the same file, so the rule is now uniform: nothing in this script closes a
# git pipe early. Dropping `exit` costs one pass over a few KB.
MAIN_WT="$(git -C "$start" worktree list --porcelain | awk '/^worktree /&&!seen{print substr($0,10); seen=1}')"
[ -n "$MAIN_WT" ] || die "could not resolve the main worktree"
REPO_NAME="$(basename -- "$MAIN_WT")"
REPO_PARENT="$(dirname -- "$MAIN_WT")"
WT_ROOT="$REPO_PARENT/$REPO_NAME-worktrees"
}
slugify() { printf '%s' "$1" | tr '/' '-'; }
derive_path() {
local branch="$1"
[ -n "$branch" ] || die "branch name required"
printf '%s/%s' "$WT_ROOT" "$(slugify "$branch")"
}
# A worktree root under $HOME defeats the entire point: wrong filesystem, and
# $HOME is for configuration and state, not work products. Refuse rather than
# silently produce the layout we are trying to eliminate.
assert_not_home() {
local p="$1" home_real repo_real
home_real="$(cd "$HOME" && pwd -P)"
repo_real="$(cd "$(dirname -- "$p")" 2>/dev/null && pwd -P || dirname -- "$p")"
case "$repo_real/" in
"$home_real"/*)
die "refusing: derived path is under \$HOME ($p).
The repo itself lives under \$HOME, so its worktrees would too. Move the repo
to a work filesystem (e.g. /src/$REPO_NAME) and re-run. \$HOME holds
configuration, credentials, state and caches — not checkouts." ;;
esac
}
# ---- work-loss evidence ----------------------------------------------------
# Two independent questions, both answered from git, neither from size or age:
# dirty — anything uncommitted in the tree
# unpushed — commits reachable from HEAD that no remote ref contains
# precious — IGNORED files git will not mention and will not miss
#
# The third question is not obvious and was missed on the first pass. An
# independent reviewer demonstrated it in four commands: a pushed, clean
# worktree whose .gitignore covers `*.secret`, holding one `local.secret`.
# `git status --porcelain` is empty, `rev-list --count HEAD --not --remotes` is
# 0 — the evidence reads SAFE — and `git worktree remove` deletes the file. The
# same shape covers `.env`, credentials, scratch notes, downloaded fixtures:
# precisely the files that are ignored BECAUSE they must not be committed, which
# is also why nothing else is holding a copy.
#
# So ignored files count as work unless they are the well-known regenerable
# kind. Getting that set wrong is asymmetric: an over-broad list preserves a
# worktree that could have been reclaimed (cheap, visible, fixable by --force),
# an over-narrow one deletes the only copy of a secret (silent, permanent).
# The list stays short and conservative for that reason.
DISPOSABLE_RE='(^|/)(node_modules|\.venv|venv|__pycache__|\.mypy_cache|\.pytest_cache|\.ruff_cache|\.turbo|\.cache|\.parcel-cache|\.gradle|dist|build|out|target|coverage|\.next|\.nuxt|\.svelte-kit)(/|$)|\.(pyc|pyo|o|class)$'
# These three run under `set -euo pipefail` inside command substitution, which
# makes any nonzero exit ANYWHERE in the pipeline abort the calling function
# silently. Two ways that bites, one of which shipped:
#
# * `grep -v` exits 1 when it filters everything out. A worktree whose only
# ignored entry is `node_modules/` is exactly the SAFE case, and it made
# `rm` exit 1 with no message and no removal — found by review.
# * `head -200` closes the pipe, SIGPIPEs the producer, and turns a worktree
# with 201 dirty files into the same silent abort. Not reported; it is the
# same defect one step upstream, so the cap is gone. Counting is cheap;
# the cap only ever protected output that is now never printed.
#
# Every one of them therefore ends in a total, and every stage that can
# legitimately exit nonzero says so explicitly.
wt_dirty() {
local out
out="$(git -C "$1" status --porcelain 2>/dev/null || true)"
if [ -n "$out" ]; then printf '%s\n' "$out" | wc -l; else printf '0'; fi
}
wt_unpushed() { git -C "$1" rev-list --count HEAD --not --remotes 2>/dev/null || printf '?'; }
# Default --ignored (not =matching) so a 40k-file node_modules collapses to one
# directory entry instead of being enumerated and then discarded.
wt_precious() {
local ignored
ignored="$(git -C "$1" status --porcelain --ignored 2>/dev/null \
| awk '/^!! /{print substr($0,4)}' || true)"
[ -n "$ignored" ] || { printf '0'; return 0; }
printf '%s\n' "$ignored" | grep -Ecv "$DISPOSABLE_RE" || true
}
wt_state() {
local wt="$1" d u p
d="$(wt_dirty "$wt")"; u="$(wt_unpushed "$wt")"; p="$(wt_precious "$wt")"
if [ "$d" -eq 0 ] && [ "$u" = "0" ] && [ "$p" -eq 0 ]; then
printf 'SAFE\tclean; 0 unpushed; no ignored files worth keeping'
else
printf 'PRESERVE\t%s uncommitted; %s unpushed; %s ignored-but-not-disposable' "$d" "$u" "$p"
fi
}
# ---- commands --------------------------------------------------------------
cmd_path() { resolve_repo; derive_path "${1:-}"; echo; }
cmd_new() {
local branch="${1:-}" base=""
shift || true
while [ $# -gt 0 ]; do
case "$1" in --from) base="${2:-}"; shift 2 ;; *) die "unknown flag: $1" ;; esac
done
[ -n "$branch" ] || die "usage: mosaic-worktree.sh new <branch> [--from <base>]"
resolve_repo
local path; path="$(derive_path "$branch")"
assert_not_home "$path"
if [ -e "$path" ]; then
echo "exists: $path"
echo "(already checked out — reuse it, or 'rm' it first)"
return 0
fi
mkdir -p "$WT_ROOT"
# Existing branch -> check it out. New branch -> create from base (default:
# the remote's default branch if resolvable, else current HEAD).
if git -C "$MAIN_WT" show-ref --verify --quiet "refs/heads/$branch" \
|| git -C "$MAIN_WT" show-ref --verify --quiet "refs/remotes/origin/$branch"; then
git -C "$MAIN_WT" worktree add "$path" "$branch"
else
if [ -z "$base" ]; then
base="$(git -C "$MAIN_WT" symbolic-ref --quiet --short refs/remotes/origin/HEAD 2>/dev/null || true)"
[ -n "$base" ] || base="HEAD"
fi
git -C "$MAIN_WT" worktree add -b "$branch" "$path" "$base"
fi
cat <<EOF
worktree: $path
branch: $branch
Removal is part of this task, not a later chore. When the work is pushed:
mosaic-worktree.sh rm $branch
EOF
}
cmd_list() {
resolve_repo
printf 'repo: %s\nroot: %s\n\n' "$MAIN_WT" "$WT_ROOT"
git -C "$MAIN_WT" worktree list --porcelain \
| awk '/^worktree /{print substr($0,10)}' \
| while read -r wt; do
[ "$wt" = "$MAIN_WT" ] && { printf '%-10s %s (main)\n' "-" "$wt"; continue; }
printf '%-10s %s\t%s\n' "$(wt_state "$wt" | cut -f1)" "$wt" "$(wt_state "$wt" | cut -f2)"
done
}
cmd_rm() {
local branch="${1:-}" force=0
shift || true
while [ $# -gt 0 ]; do
case "$1" in --force) force=1; shift ;; *) die "unknown flag: $1" ;; esac
done
[ -n "$branch" ] || die "usage: mosaic-worktree.sh rm <branch> [--force]"
resolve_repo
local path; path="$(derive_path "$branch")"
[ -d "$path" ] || die "no worktree at $path"
local d u p
d="$(wt_dirty "$path")"; u="$(wt_unpushed "$path")"; p="$(wt_precious "$path")"
if [ "$force" -eq 0 ] && { [ "$d" -ne 0 ] || [ "$u" != "0" ] || [ "$p" -ne 0 ]; }; then
die "refusing to remove $path
uncommitted files: $d
unpushed commits: $u
ignored, not disposable: $p
Commit and push first — that is the contract. Ignored files are counted because
git will neither report them nor miss them: a .env or a *.secret is ignored
precisely so it is never committed, which is also why nothing else holds a copy.
List them with: git -C $path status --porcelain --ignored | grep '^!!'
If this work is genuinely disposable, re-run with --force."
fi
# NB: ${force:+--force} would expand for force=0 too ("0" is non-empty).
if [ "$force" -eq 1 ]; then
git -C "$MAIN_WT" worktree remove --force "$path"
else
git -C "$MAIN_WT" worktree remove "$path"
fi
git -C "$MAIN_WT" worktree prune
echo "removed: $path"
rmdir "$WT_ROOT" 2>/dev/null || true
}
cmd_gc() {
local apply=0
[ "${1:-}" = "--apply" ] && apply=1
resolve_repo
git -C "$MAIN_WT" worktree prune
git -C "$MAIN_WT" worktree list --porcelain \
| awk '/^worktree /{print substr($0,10)}' \
| while read -r wt; do
[ "$wt" = "$MAIN_WT" ] && continue
local_state="$(wt_state "$wt")"
case "$local_state" in
SAFE*)
if [ "$apply" -eq 1 ]; then
git -C "$MAIN_WT" worktree remove "$wt" && echo "removed: $wt"
else
echo "reclaimable (clean + fully pushed): $wt"
fi ;;
*) echo "preserved: $wt [$(printf '%s' "$local_state" | cut -f2)]" ;;
esac
done
git -C "$MAIN_WT" worktree prune
[ "$apply" -eq 1 ] || echo $'\n(report only — re-run with --apply to remove the reclaimable ones)'
}
case "$CMD" in
new) cmd_new "$@" ;;
path) cmd_path "$@" ;;
list) cmd_list "$@" ;;
rm) cmd_rm "$@" ;;
gc) cmd_gc "$@" ;;
-h|--help|help) sed -n '2,40p' "$0" | sed 's/^# \{0,1\}//' ;;
*) die "unknown command: $CMD (new | path | list | rm | gc)" ;;
esac
@@ -84,7 +84,7 @@ cp "$TARGET" "$BAK"
export MOSAIC_TEST_WORK_DIR="$WORK/.work"
# --- where the prose lives: usage() { ... EOF ---------------------------------
PROSE_LO="$(grep -n '^usage() {' "$BAK" | head -1 | cut -d: -f1)"
PROSE_LO="$(grep -n -m1 '^usage() {' "$BAK" | cut -d: -f1)"
PROSE_HI="$(awk -v lo="$PROSE_LO" 'NR > lo && /^EOF$/ { print NR; exit }' "$BAK")"
if [[ -z "$PROSE_LO" || -z "$PROSE_HI" ]]; then
echo "!! cannot locate the usage() heredoc -- the prose guard would be inert; refusing" >&2
@@ -219,6 +219,7 @@ case "$PLATFORM" in
exit 0
fi
echo "Warning: tea pr create failed, trying Gitea API fallback..." >&2
{ declare -F explain_tea_user_does_not_exist >/dev/null && explain_tea_user_does_not_exist; } || true
gitea_pr_create_api
;;
*)
+185
View File
@@ -0,0 +1,185 @@
#!/usr/bin/env bash
# pr-edit.sh - Edit a pull request on GitHub or Gitea
# Usage: pr-edit.sh -n <pr_number> [-t <title>] [-b <body>] [-B <base>] [--draft|--ready] [--login <name>] [-r owner/repo] [-H host]
set -euo pipefail
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
# shellcheck source=detect-platform.sh
source "$SCRIPT_DIR/detect-platform.sh"
PR_NUMBER=""
TITLE=""
BODY=""
BASE_BRANCH=""
DRAFT_MODE=""
LOGIN_OVERRIDE=""
REPO_OVERRIDE=""
HOST_OVERRIDE=""
AUTH_CONFIG=""
cleanup() {
[[ -z "$AUTH_CONFIG" ]] || rm -f -- "$AUTH_CONFIG"
}
terminate() {
local signal="$1"
trap - "$signal"
cleanup
kill -s "$signal" "$$"
}
trap cleanup EXIT
trap 'terminate HUP' HUP
trap 'terminate INT' INT
trap 'terminate TERM' TERM
usage() {
cat <<EOF
Usage: $(basename "$0") [OPTIONS]
Edit a pull request on the current repository (Gitea or GitHub).
Options:
-n, --number NUMBER Pull request number (required)
-t, --title TITLE New title
-b, --body BODY New body/description
-B, --base BRANCH New base branch
--draft Mark the pull request as draft
--ready Mark the pull request ready for review
-l, --login NAME Gitea login (must authenticate as MOSAIC_GIT_IDENTITY)
-r, --repo OWNER/REPO Explicit target repository
-H, --host HOST Explicit Gitea host (required with --repo off-host)
-h, --help Show this help message
EOF
exit "${1:-1}"
}
while [[ $# -gt 0 ]]; do
case "$1" in
-n|--number) PR_NUMBER="${2:-}"; shift 2 ;;
-t|--title) TITLE="${2:-}"; shift 2 ;;
-b|--body) BODY="${2:-}"; shift 2 ;;
-B|--base) BASE_BRANCH="${2:-}"; shift 2 ;;
--draft)
[[ "$DRAFT_MODE" != "ready" ]] || { echo "Error: --draft and --ready are mutually exclusive" >&2; exit 1; }
DRAFT_MODE="draft"; shift ;;
--ready)
[[ "$DRAFT_MODE" != "draft" ]] || { echo "Error: --draft and --ready are mutually exclusive" >&2; exit 1; }
DRAFT_MODE="ready"; shift ;;
-l|--login) LOGIN_OVERRIDE="${2:-}"; shift 2 ;;
-r|--repo) REPO_OVERRIDE="${2:-}"; shift 2 ;;
-H|--host) HOST_OVERRIDE="${2:-}"; shift 2 ;;
-h|--help) usage 0 ;;
*) echo "Unknown option: $1" >&2; usage ;;
esac
done
[[ -n "$PR_NUMBER" ]] || { echo "Error: Pull request number is required (-n)" >&2; exit 1; }
[[ "$PR_NUMBER" =~ ^[1-9][0-9]*$ ]] || { echo "Error: Pull request number must be a positive integer" >&2; exit 1; }
if [[ -z "$TITLE" && -z "$BODY" && -z "$BASE_BRANCH" && -z "$DRAFT_MODE" ]]; then
echo "Error: At least one edit option is required" >&2
exit 1
fi
[[ -z "$REPO_OVERRIDE" || "$REPO_OVERRIDE" =~ ^[^/[:space:]]+/[^/[:space:]]+$ ]] || {
echo "Error: --repo must be OWNER/REPO" >&2
exit 1
}
if [[ -n "$HOST_OVERRIDE" || -n "$REPO_OVERRIDE" ]]; then
PLATFORM="gitea"
else
PLATFORM=$(detect_platform)
fi
case "$PLATFORM" in
github)
[[ -z "$LOGIN_OVERRIDE" ]] || { echo "Error: --login is only valid for Gitea" >&2; exit 1; }
if [[ -n "$TITLE" || -n "$BODY" || -n "$BASE_BRANCH" ]]; then
CMD=(gh pr edit "$PR_NUMBER")
[[ -n "$TITLE" ]] && CMD+=(--title "$TITLE")
[[ -n "$BODY" ]] && CMD+=(--body "$BODY")
[[ -n "$BASE_BRANCH" ]] && CMD+=(--base "$BASE_BRANCH")
"${CMD[@]}"
fi
if [[ "$DRAFT_MODE" == "draft" ]]; then
gh pr ready "$PR_NUMBER" --undo
elif [[ "$DRAFT_MODE" == "ready" ]]; then
gh pr ready "$PR_NUMBER"
fi
;;
gitea)
IDENTITY="${MOSAIC_GIT_IDENTITY:-}"
[[ -n "$IDENTITY" ]] || {
echo "Error: MOSAIC_GIT_IDENTITY is required for a mutating Gitea operation" >&2
exit 1
}
HOST="${HOST_OVERRIDE:-}"
if [[ -z "$HOST" ]]; then
HOST=$(get_remote_host) || {
echo "Error: Could not resolve Gitea host; pass --host with --repo" >&2
exit 1
}
fi
HOST="${HOST#http://}"; HOST="${HOST#https://}"; HOST="${HOST%%/*}"
REPO_SLUG="${REPO_OVERRIDE:-}"
if [[ -z "$REPO_SLUG" ]]; then
REPO_SLUG=$(get_repo_slug) || { echo "Error: Could not resolve Gitea repo slug from remote" >&2; exit 1; }
fi
if [[ -n "$LOGIN_OVERRIDE" ]]; then
GITEA_LOGIN_NAME="$LOGIN_OVERRIDE"
elif [[ -n "${GITEA_LOGIN:-}" ]]; then
GITEA_LOGIN_NAME="$GITEA_LOGIN"
else
echo "Error: --login (or GITEA_LOGIN) is required; refusing host-first login selection" >&2
exit 1
fi
TOKEN=$(get_gitea_token_for_login "$GITEA_LOGIN_NAME" "$HOST") || {
echo "Error: login '$GITEA_LOGIN_NAME' is not configured for target host '$HOST'" >&2
exit 1
}
AUTH_CONFIG=$(gitea_write_auth_config "$TOKEN") || {
echo "Error: could not stage private Gitea authentication" >&2
exit 1
}
unset TOKEN
API_BASE="https://${HOST}/api/v1"
# Resolve identity through the SAME private curl config used for the
# mutation. Tea login names are globally scoped and can be duplicated
# across hosts; a separate `tea api --login NAME` could validate another
# credential than this host-bound token.
AUTHENTICATED_USER=$(curl -fsS --config "$AUTH_CONFIG" -H "User-Agent: mosaic-pr-edit" "$API_BASE/user" \
| python3 -c 'import json,sys; value=json.load(sys.stdin).get("login"); print(value) if isinstance(value,str) and value else sys.exit(1)') || {
echo "Error: could not authenticate the host-bound credential for '$GITEA_LOGIN_NAME'" >&2
exit 1
}
[[ "$AUTHENTICATED_USER" == "$IDENTITY" ]] || {
echo "Error: host-bound credential authenticates as '$AUTHENTICATED_USER', not MOSAIC_GIT_IDENTITY '$IDENTITY'" >&2
exit 1
}
REPO_API="$API_BASE/repos/${REPO_SLUG}"
curl -fsS --config "$AUTH_CONFIG" -H "User-Agent: mosaic-pr-edit" "$REPO_API" >/dev/null || {
echo "Error: target repository preflight failed for https://${HOST}/${REPO_SLUG}" >&2
exit 1
}
PAYLOAD=$(TITLE="$TITLE" BODY="$BODY" BASE_BRANCH="$BASE_BRANCH" DRAFT_MODE="$DRAFT_MODE" python3 - <<'PY'
import json
import os
payload = {}
if os.environ["TITLE"]: payload["title"] = os.environ["TITLE"]
if os.environ["BODY"]: payload["body"] = os.environ["BODY"]
if os.environ["BASE_BRANCH"]: payload["base"] = os.environ["BASE_BRANCH"]
if os.environ["DRAFT_MODE"]: payload["draft"] = os.environ["DRAFT_MODE"] == "draft"
print(json.dumps(payload))
PY
)
curl -fsS --config "$AUTH_CONFIG" -X PATCH \
-H "User-Agent: mosaic-pr-edit" -H "Content-Type: application/json" \
-d "$PAYLOAD" "$REPO_API/pulls/${PR_NUMBER}"
echo "Updated Gitea pull request #$PR_NUMBER as '$AUTHENTICATED_USER'" >&2
;;
*) echo "Error: Could not detect git platform" >&2; exit 1 ;;
esac
@@ -243,15 +243,35 @@ from urllib.parse import urlparse
def _origin_and_path(url):
# Normalize a URL to (scheme, host, effective-port) + comment path. The port
# defaults to the scheme's default (80 http / 443 otherwise) so an implicit
# port and its explicit default form compare equal.
# Normalize a URL to (scheme-class, host, distinguishing-port) + comment path.
#
# #991: http and https collapse into ONE scheme class ("web"). A Gitea whose
# ROOT_URL is configured http:// returns http:// object URLs even when every
# client reaches it over https://, so a scheme-strict comparison rejects the
# provider's own correct answer about a comment that landed — a deterministic
# false negative on EVERY review comment posted against such a deployment.
# That matters more here than anywhere else: on a host where no seat can
# create a review OBJECT, the comment-form review record this path produces
# is the only gate-16 evidence available, and this check refuses all of it.
# The scheme is also not what the check defends: the forgeries it exists to
# catch (look-alike host, decoy path prefix, wrong owner/repo/kind/number)
# all vary the HOST or the PATH, both of which stay strict below. Any OTHER
# scheme (file:, ftp:, javascript:) remains distinguishing and is rejected.
#
# Port: an implicit port and its own scheme's default compare equal, so
# http://h == https://h. An EXPLICIT non-default port still distinguishes,
# because a different port is a different service on the same host.
parsed = urlparse(url or "")
scheme = (parsed.scheme or "").lower()
host = (parsed.hostname or "").lower()
default_port = 80 if scheme == "http" else 443
port = parsed.port if parsed.port is not None else default_port
return (scheme, host, port), parsed.path.rstrip("/")
if scheme in ("http", "https"):
scheme_class = "web"
default_port = 80 if scheme == "http" else 443
port = None if parsed.port in (None, default_port) else parsed.port
else:
scheme_class = scheme
port = parsed.port
return (scheme_class, host, port), parsed.path.rstrip("/")
try:
@@ -0,0 +1,58 @@
#!/bin/bash
# Regression: detect_platform / get_repo_info must FAIL LOUDLY outside a git repo,
# not kill the caller silently.
#
# Both functions already contained the right error path:
# if [[ -z "$remote_url" ]]; then echo "error: not a git repository..." >&2; return 1; fi
# but under `set -e` -- which every wrapper in this directory uses -- the preceding
# assignment `remote_url=$(git remote get-url origin 2>/dev/null)` returns git's 128
# outside a repo and terminates the CALLER first. The message was unreachable.
#
# Observed cost: pr-review.sh invoked from a non-repo cwd exits 128 with NO stdout and
# NO stderr, even when -r/--repo and -H/--host are supplied -- the flags documented as
# "skips git-remote inference". Two reviewer seats hit this and correctly reported
# `blocked` with no diagnostic to report.
#
# The control that matters is the LOUD one: asserting "rc != 0" passes on the broken
# build too, because 128 is also non-zero. The test must assert the MESSAGE.
set -uo pipefail
fail=0
HERE="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
TMP="$(mktemp -d)"; trap 'rm -rf "$TMP"' EXIT
run_outside() { # $1=function name -> "rc:sawmessage"
local fn="$1" out rc
out=$( cd "$TMP" && bash -c "set -e; source '$HERE/detect-platform.sh'; $fn" 2>&1 ); rc=$?
printf '%s:%s' "$rc" "$(grep -qi 'not a git repository' <<<"$out" && echo yes || echo no)"
}
check() { if [ "$2" = "$3" ]; then echo " PASS $1 ($2)"; else echo " FAIL $1: got $2, want $3"; fail=1; fi; }
# $TMP must not be inside a git repo. Do not SKIP on failure: be-coder-07 showed the
# original SKIP exited 0, so pointing TMPDIR beneath a git worktree made this test PASS
# against unchanged main. A skip that exits 0 is indistinguishable from a pass.
# GIT_CEILING_DIRECTORIES stops git walking above $TMP, making the condition hold
# regardless of where TMPDIR lives, rather than merely detecting when it does not.
# GIT_CEILING_DIRECTORIES is matched against the PHYSICAL path -- a symlinked TMPDIR
# (/tmp is commonly one) makes the logical path never match, and the ceiling silently
# does nothing. Resolve it before exporting.
TMP="$(cd "$TMP" && pwd -P)"
export GIT_CEILING_DIRECTORIES="$TMP"
if ( cd "$TMP" && git rev-parse --git-dir >/dev/null 2>&1 ); then
echo " FAIL scratch dir is inside a git repo even with GIT_CEILING_DIRECTORIES set;"
echo " the outside-a-repo precondition cannot be established -- refusing to report a result"
exit 1
fi
echo "== outside a git repo: rc=1 AND the diagnostic is emitted =="
check "detect_platform" "$(run_outside detect_platform)" "1:yes"
check "get_repo_info" "$(run_outside get_repo_info)" "1:yes"
echo "== inside a git repo the functions still work =="
git init -q "$TMP/repo" 2>/dev/null
git -C "$TMP/repo" remote add origin https://git.mosaicstack.dev/mosaicstack/stack.git 2>/dev/null
out=$( cd "$TMP/repo" && bash -c "set -e; source '$HERE/detect-platform.sh'; detect_platform" 2>&1 ); rc=$?
if [ "$rc" -eq 0 ] && grep -qi 'gitea' <<<"$out"; then echo " PASS detect_platform in-repo (rc=0, $out)"
else echo " FAIL detect_platform in-repo: rc=$rc out=$out"; fail=1; fi
[ "$fail" -eq 0 ] && echo "OK detect-platform fails loudly outside a repo" || echo "FAILED"
exit "$fail"
@@ -0,0 +1,64 @@
#!/bin/bash
# Regression: the tea-failure diagnostic must be STATUS-NEUTRAL.
#
# Found by be-coder-08 reviewing PR #1086. At all three call sites the diagnostic is emitted
# immediately BEFORE the Gitea API fallback. Written as the last command of an && list:
# declare -F explain_... >/dev/null && explain_...
# under `set -e` a FAILING diagnostic exits and the fallback never runs -- a diagnostic that
# suppresses the recovery path it exists to explain. It misbehaves ONLY when the helper is
# PRESENT, so the helper-absent path (pre-#1086 behaviour) keeps working and reads as a
# passing control.
#
# TWO DEFECTS IN THE FIRST VERSION OF THIS TEST, both found by be-coder-08:
# 1. `out=$( ... ) 2>"$errto"` applies the redirection to the ASSIGNMENT, not to the
# command substitution, so the probe's stderr was never actually pointed at /dev/full
# and the /dev/full rows proved nothing. Verified: `out=$(echo x >&2) 2>/dev/full`
# leaks to the terminal and returns 0; the redirect must be INSIDE the substitution.
# 2. `eval "$CONSTRUCT"` changes `set -e` semantics for a bare && list, so the probe did
# not exercise the construct as the shipped file executes it. It now writes the line
# into a real script and runs it -- same parse, same set -e rules, no eval.
# The construct is still LIFTED FROM THE SHIPPED FILE: retyping the fixed form makes the
# probe pass on a build whose real call sites still carry the bare && form.
set -uo pipefail
fail=0
GIT_DIR_UNDER_TEST="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
TMP="$(mktemp -d)"; trap 'rm -rf "$TMP"' EXIT
probe() { # $1=present|absent $2=stderr target $3=source file -> "rc:fallback"
local helper="$1" errto="$2" src="$3" construct script out rc
construct=$(grep -m1 'explain_tea_user_does_not_exist' "$GIT_DIR_UNDER_TEST/$src" | sed 's/^[[:space:]]*//')
[ -n "$construct" ] || { printf 'no-construct:no'; return; }
script="$TMP/probe.sh"
{
echo '#!/bin/bash'
echo 'set -e'
echo 'explain_tea_user_does_not_exist() { echo "diagnostic" >&2; }'
[ "$helper" = absent ] && echo 'unset -f explain_tea_user_does_not_exist'
echo "$construct" # the shipped line, parsed by a real shell
echo 'echo FALLBACK_REACHED'
} > "$script"
# redirect INSIDE the substitution so the subshell's stderr really is $errto
out=$( bash "$script" 2>"$errto" ); rc=$?
printf '%s:%s' "$rc" "$(grep -q FALLBACK_REACHED <<<"$out" && echo yes || echo no)"
}
check() { if [ "$2" = "$3" ]; then echo " PASS $1 ($2)"; else echo " FAIL $1: got $2, want $3"; fail=1; fi; }
echo "== diagnostic must not alter exit status or skip the fallback =="
# /dev/full makes every stderr write fail -- the real-world shape is a closed or full fd.
for src in pr-create.sh issue-view.sh issue-create.sh; do
check "$src stderr OK / helper present" "$(probe present /dev/null "$src")" "0:yes"
check "$src stderr OK / helper absent " "$(probe absent /dev/null "$src")" "0:yes"
check "$src stderr FAILING / helper present" "$(probe present /dev/full "$src")" "0:yes"
check "$src stderr FAILING / helper absent " "$(probe absent /dev/full "$src")" "0:yes"
done
echo "== all three call sites use the status-neutral form =="
for f in pr-create.sh issue-view.sh issue-create.sh; do
p="$GIT_DIR_UNDER_TEST/$f"
grep -q '{ declare -F explain_tea_user_does_not_exist >/dev/null && explain_tea_user_does_not_exist; } || true' "$p" \
&& echo " PASS $f guarded" || { echo " FAIL $f: diagnostic is not status-neutral"; fail=1; }
done
[ "$fail" -eq 0 ] && echo "OK diagnostic is status-neutral" || echo "FAILED"
exit "$fail"
@@ -7,14 +7,40 @@ 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"
HOME_DIR="$WORK_DIR/home"
LOG_FILE="$WORK_DIR/calls.log"
CREDENTIALS_FILE="$WORK_DIR/credentials.json"
rm -rf "$WORK_DIR"
mkdir -p "$REPO_DIR" "$BIN_DIR"
mkdir -p "$REPO_DIR" "$BIN_DIR" "$HOME_DIR"
git -C "$REPO_DIR" init -q
git -C "$REPO_DIR" remote add origin https://git.uscllc.com/USC/uconnect.git
# HERMETICITY (#1007) — TWO mechanisms with DIFFERENT jobs; do not conflate them.
#
# OPERATIVE: the empty repo-local `mosaic.gitIdentity` below. get_gitea_token()
# step 0 resolves a per-agent identity from `git config --get mosaic.gitIdentity`,
# which on a provisioned agent seat is set GLOBALLY and so leaks into this fresh
# repo. It then reads a REAL per-slot token from $HOME and returns it WITHOUT ever
# consulting MOSAIC_CREDENTIALS_FILE, so the fixture credentials below are silently
# ignored. This suite is the one where the consequence is not subtle: it FAILS
# outright on a provisioned seat (rc=1 bare, rc=0 with $HOME sandboxed, one
# variable changed) and passes everywhere else, including CI, which has no
# per-agent token to leak.
#
# CONTAINMENT: the sandboxed HOME in the four run helpers below. It only has to
# bound a failure that the pin should already have prevented.
#
# NOTE FOR ANYONE AUDITING THIS SUITE: the sandboxed HOME is containment, NOT an
# assay. Running a suite under a decoy HOME to test for this defect REMOVES the
# trigger — ~/.gitconfig is where the global identity lives, so step 0 is skipped
# by construction and every suite reads clean however vulnerable it is. To measure,
# REPLICATE a seat (a decoy HOME whose .gitconfig sets mosaic.gitIdentity, with no
# per-slot token) so step 0 reaches its fail-loud branch.
#
# Note the env-var route does NOT work: detect-platform.sh reads
# "${MOSAIC_GIT_IDENTITY:-}", and `:-` treats set-but-empty identically to unset.
git -C "$REPO_DIR" config mosaic.gitIdentity ""
cat > "$CREDENTIALS_FILE" <<'JSON'
{
@@ -86,6 +112,7 @@ run_in_repo() {
(
cd "$REPO_DIR"
PATH="$BIN_DIR:$PATH" \
HOME="$HOME_DIR" \
MOSAIC_CREDENTIALS_FILE="$CREDENTIALS_FILE" \
MOSAIC_TEST_LOG="$LOG_FILE" \
"$@"
@@ -283,6 +310,7 @@ run_in_repo2() {
(
cd "$REPO_DIR"
PATH="$BIN_DIR2:$PATH" \
HOME="$HOME_DIR" \
MOSAIC_CREDENTIALS_FILE="$CREDENTIALS_FILE" \
MOSAIC_TEST_LOG="$LOG_FILE" \
"$@"
@@ -343,7 +371,7 @@ write_fixture() { printf '%s' "$1" > "$FIXTURE_XDG/tea/config.yml"; }
token_fallback() {
(
cd "$REPO_DIR"
XDG_CONFIG_HOME="$FIXTURE_XDG" PYTHONPATH="$NOYAML_DIR" bash -c '
HOME="$HOME_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"
@@ -354,7 +382,7 @@ token_fallback() {
token_pyyaml() {
(
cd "$REPO_DIR"
XDG_CONFIG_HOME="$FIXTURE_XDG" bash -c '
HOME="$HOME_DIR" XDG_CONFIG_HOME="$FIXTURE_XDG" bash -c '
source "'"$SCRIPT_DIR"'/detect-platform.sh"
get_gitea_token_for_login "$1" "$2"
' _ "$1" "$2"
@@ -1,7 +1,7 @@
#!/usr/bin/env bash
# Regression harness for #701: -h/--help must exit 0, bad args must still exit nonzero.
#
# Covers the 7 wrappers whose usage() previously hard-coded `exit 1`, so every
# Covers wrappers whose usage() previously hard-coded `exit 1`, so every
# --help invocation exited nonzero and logged a phantom isError across fleet lanes.
# Asserts, per wrapper:
# 1. `--help` exits 0 and prints usage.
@@ -18,6 +18,7 @@ WRAPPERS=(
issue-list.sh
milestone-create.sh
pr-create.sh
pr-edit.sh
pr-list.sh
pr-merge.sh
)
@@ -47,7 +48,7 @@ for wrapper in "${WRAPPERS[@]}"; do
done
if [[ "$fail" -eq 0 ]]; then
echo "help-exit-code regression passed (7/7 wrappers)"
echo "help-exit-code regression passed (8/8 wrappers)"
fi
exit "$fail"
@@ -0,0 +1,150 @@
#!/usr/bin/env bash
# Regression: issue-close.sh must NOT close an issue when the closing comment could not
# be posted, and comment+close must be made by ONE principal.
#
# Guards two defects fixed together (see #1081):
# 1. `tea issue comment` is not a subcommand -- tea exposes comments as the TOP-LEVEL
# `tea comment`. The old call always failed, was unchecked, and the issue closed
# anyway, losing the record of WHY it was closed.
# 2. Routing the comment through the token-authenticated API helper while the close
# used --login would attribute one operation to two principals.
#
# SAFETY (rev-974, #1085 review 130): this test previously ran under `set -uo pipefail`
# with unchecked mkdir/redirect/cd, then prepended a possibly-nonexistent $MOCK_BIN to
# PATH -- while `git remote add origin` names the REAL repository. Forcing setup failure
# with an unwritable AGENT_WORK_ROOT made it `git init` in its CALLER's directory and
# invoke the real, provider-mutating issue-close.sh. Setup now fails closed, and both
# `tea` and `curl` are asserted to resolve INSIDE $MOCK_BIN before any target run.
set -euo pipefail
# NOTE: with `set -e`, `grep -q X && fail "..."` is a trap -- the ABSENT case (grep rc=1,
# which is the PASSING case for a must-not-appear assertion) is the last command of an &&
# list and silently terminates the script with no message. Every must-not-appear check
# below is therefore an if-block. This is the same set -e + &&-list defect be-coder-08
# found in #1086, reintroduced here by adding `set -e` for the sandbox-safety fix.
WORK_ROOT="${AGENT_WORK_ROOT:-${TMPDIR:-/tmp}}"
SANDBOX="$WORK_ROOT/issue-close-fail-closed-test-$$"
MOCK_BIN="$SANDBOX/bin"; REPO_DIR="$SANDBOX/repo"; CALLS="$SANDBOX/calls.log"
cleanup() { rm -rf "$SANDBOX"; }
trap cleanup EXIT
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
TARGET="$SCRIPT_DIR/issue-close.sh"
[ -f "$TARGET" ] || { echo "FAIL: issue-close.sh not found beside this test"; exit 1; }
fail() { echo "FAIL: $*"; exit 1; }
# Every setup step is checked. Under `set -e` these abort; the explicit || fail keeps the
# reason legible instead of a bare non-zero exit.
mkdir -p "$MOCK_BIN" "$REPO_DIR" || fail "setup: cannot create sandbox under $WORK_ROOT"
: > "$CALLS" || fail "setup: cannot write calls log at $CALLS"
cd "$REPO_DIR" || fail "setup: cannot cd into $REPO_DIR"
git init -q || fail "setup: git init failed"
git remote add origin https://git.mosaicstack.dev/mosaicstack/stack.git || fail "setup: git remote add failed"
export PATH="$MOCK_BIN:$PATH" CALLS
export GITEA_URL="https://git.mosaicstack.dev"
export GITEA_TOKEN="redacted-test-token"
cat > "$MOCK_BIN/curl" <<'EOF'
#!/bin/bash
method=GET; url=""
while [ $# -gt 0 ]; do
case "$1" in
-X) method="$2"; shift 2 ;;
http*|https*) url="$1"; shift ;;
*) shift ;;
esac
done
printf 'curl %s %s\n' "$method" "$url" >> "$CALLS"
[ "${MOCK_CURL_FAIL:-}" = "1" ] && [ "$method" = "POST" ] && exit 22
exit 0
EOF
chmod +x "$MOCK_BIN/curl"
mk_tea() { # $1 = exit code for a comment attempt; $2 = login list (empty => no login)
local rc="$1" login="${2-}"
cat > "$MOCK_BIN/tea" <<EOF
#!/bin/bash
printf 'tea %s\n' "\$*" >> "$CALLS"
if [[ "\$*" == *"login list"* ]]; then
printf '%s\n' '${login}'; exit 0
fi
# Fail ANY comment attempt -- both the correct top-level \`tea comment\` and the broken
# \`tea issue comment\` -- so an unfixed script exercises the DEFECT rather than tripping
# a setup assertion.
if [[ "\$1" == "comment" || ( "\$1" == "issue" && "\$2" == "comment" ) ]]; then exit $rc; fi
exit 0
EOF
chmod +x "$MOCK_BIN/tea"
}
LOGIN_JSON='[{"name":"git.mosaicstack.dev","url":"https://git.mosaicstack.dev"}]'
# The mocks must be the ones that run. Without this, a failed setup silently falls through
# to the real tea/curl and the "test" mutates the real provider.
assert_mocked() {
local w
for w in tea curl; do
p=$(command -v "$w" || true)
[ -n "$p" ] || fail "SAFETY: $w does not resolve at all"
case "$p" in
"$MOCK_BIN"/*) : ;;
*) fail "SAFETY: $w resolves to $p, OUTSIDE the sandbox -- refusing to invoke the target" ;;
esac
done
}
run_target() { # never let a target failure abort the test; we assert on rc
# Call sites MUST use `rc=0; run_target ... || rc=$?` -- a bare `run_target ...; rc=$?`
# lets the non-zero RETURN trip set -e in the CALLER before rc is ever read.
set +e; bash "$TARGET" "$@" >/dev/null 2>&1; local rc=$?; set -e; return $rc
}
# ── tea path ────────────────────────────────────────────────────────────────────────
# 1. NEGATIVE (the regression): comment fails => must NOT close, must exit non-zero
mk_tea 1 "$LOGIN_JSON"; : > "$CALLS"; assert_mocked
rc=0; run_target -i 42 -c "closing note" || rc=$?
grep -qE 'tea (issue )?comment' "$CALLS" || fail "no comment attempt -- setup did not reach the tea branch"
if grep -q 'tea issue close' "$CALLS"; then fail "ISSUE CLOSED AFTER THE COMMENT FAILED -- the regression"; fi
[ "$rc" -ne 0 ] || fail "comment failed but issue-close exited 0 -- FAIL-OPEN"
# 2. POSITIVE: comment succeeds => close proceeds, exit 0
mk_tea 0 "$LOGIN_JSON"; : > "$CALLS"; assert_mocked
rc=0; run_target -i 42 -c "closing note" || rc=$?
[ "$rc" -eq 0 ] || fail "comment succeeded but issue-close exited $rc"
grep -q 'tea issue close' "$CALLS" || fail "issue not closed even though the comment succeeded"
# 3. must use top-level `tea comment`, never `tea issue comment`
if grep -q 'tea issue comment' "$CALLS"; then fail "used 'tea issue comment' -- not a valid subcommand"; fi
# 4. ONE PRINCIPAL: comment and close must carry the SAME --login
c=$(grep -m1 '^tea comment' "$CALLS" | grep -o -- '--login [^ ]*' | awk '{print $2}')
k=$(grep -m1 '^tea issue close' "$CALLS" | grep -o -- '--login [^ ]*' | awk '{print $2}')
[ -n "$c" ] || fail "comment carried no --login"
[ "$c" = "$k" ] || fail "MIXED PRINCIPALS: comment=$c close=$k"
# ── no-login / API fallback path ────────────────────────────────────────────────────
# rev-974: the delta also adds fail-closed behaviour to this branch, and the suite never
# reached it -- replacing the whole fallback contract with an unconditional close still
# passed. These assert the POSTCONDITION (which HTTP calls happened, in what order),
# not merely that a command ran.
# 5. no login + comment FAILS => POST attempted, NO PATCH, non-zero
mk_tea 0 ""; : > "$CALLS"; assert_mocked
rc=0; MOCK_CURL_FAIL=1 run_target -i 42 -c "closing note" || rc=$?
grep -q 'curl POST' "$CALLS" || fail "API path: no comment POST attempted"
if grep -q 'curl PATCH' "$CALLS"; then fail "API path: ISSUE CLOSED (PATCH) AFTER THE COMMENT POST FAILED"; fi
[ "$rc" -ne 0 ] || fail "API path: comment failed but exited 0 -- FAIL-OPEN"
# 6. no login + comment SUCCEEDS => POST strictly BEFORE PATCH, exit 0
mk_tea 0 ""; : > "$CALLS"; assert_mocked
rc=0; run_target -i 42 -c "closing note" || rc=$?
[ "$rc" -eq 0 ] || fail "API path: comment succeeded but exited $rc"
order=$(grep -oE 'curl (POST|PATCH)' "$CALLS" | awk '{print $2}' | paste -sd, -)
[ "$order" = "POST,PATCH" ] || fail "API path: expected POST,PATCH -- got '${order:-<none>}'"
# 7. no login + NO comment => PATCH only, never a POST
mk_tea 0 ""; : > "$CALLS"; assert_mocked
rc=0; run_target -i 42 || rc=$?
[ "$rc" -eq 0 ] || fail "API path: no-comment close exited $rc"
if grep -q 'curl POST' "$CALLS"; then fail "API path: posted a comment when none was requested"; fi
grep -q 'curl PATCH' "$CALLS" || fail "API path: issue not closed when no comment was requested"
echo "issue-close.sh fail-closed + single-principal regression passed"
@@ -61,15 +61,54 @@ STATE_FILE="$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="$WORK_DIR/scratch"
HOME_DIR="$WORK_DIR/home"
cleanup() {
rm -rf "$WORK_DIR"
}
trap cleanup EXIT
mkdir -p "$REPO_DIR" "$BIN_DIR" "$XDG_DIR" "$TMP_SCRATCH"
mkdir -p "$REPO_DIR" "$BIN_DIR" "$XDG_DIR" "$TMP_SCRATCH" "$HOME_DIR"
git -C "$REPO_DIR" init -q
git -C "$REPO_DIR" remote add origin https://git.mosaicstack.dev/mosaicstack/stack.git
# HERMETICITY (#1007) — TWO mechanisms with DIFFERENT jobs; do not conflate them.
#
# OPERATIVE: the empty repo-local `mosaic.gitIdentity` below. get_gitea_token()
# step 0 resolves a per-agent identity from `git config --get mosaic.gitIdentity`,
# which on a provisioned agent seat is set GLOBALLY and so leaks into this fresh
# repo. It then reads a REAL per-slot token from $HOME and returns it WITHOUT ever
# consulting MOSAIC_CREDENTIALS_FILE, so the fixture credential below is silently
# ignored. The stub curl then rejects the unrecognised bearer, and this suite
# fails at its FIRST case with `Gitea authenticated-identity read failed with
# HTTP 401`. An empty repo-local value shadows the global one and reads back
# empty at rc=0. Measured: without this pin the suite is RED on every seat.
#
# CONTAINMENT: the sandboxed HOME in run_comment(). It only has to bound a
# failure that the pin should already have prevented.
#
# THIS SUITE WAS THE HARDEST OF THE FIVE TO SEE, and the reason is worth stating
# because it generalises: run_comment() sends the wrapper's stdout AND stderr to
# $OUTPUT_FILE, and the EXIT trap above deletes $WORK_DIR. So the 401 — the only
# thing that says what went wrong — exists only inside a directory that is gone
# by the time anyone looks. The suite exits 1 with ZERO bytes on stdout and
# stderr. A suite that discards or deletes its own evidence turns any post-hoc
# assay into a non-measurement: "nothing found" there means "no surviving
# trace", never "clean". It was found by intercepting the identity read at its
# SOURCE (a PATH shim over `git` logging every `mosaic.gitIdentity` read to a
# file outside $WORK_DIR), which is deletion-proof by construction, rather than
# by grepping for the symptom.
#
# NOTE FOR ANYONE AUDITING THIS SUITE: the sandboxed HOME is containment, NOT an
# assay. Running a suite under a decoy HOME to test for this defect REMOVES the
# trigger — ~/.gitconfig is where the global identity lives, so step 0 is skipped
# by construction and every suite reads clean however vulnerable it is. To
# measure, REPLICATE a seat (a decoy HOME whose .gitconfig sets
# mosaic.gitIdentity, with no per-slot token) so step 0 reaches its fail-loud
# branch — or intercept the read as described above.
#
# Note the env-var route does NOT work: detect-platform.sh reads
# "${MOSAIC_GIT_IDENTITY:-}", and `:-` treats set-but-empty identically to unset.
git -C "$REPO_DIR" config mosaic.gitIdentity ""
ISSUE_NUMBER=7
REPO_SLUG="mosaicstack/stack"
@@ -280,7 +319,10 @@ print("201")
print(json.dumps(record))
PY
)
write_response "$(printf '%s' "$result" | head -n1)" "$(printf '%s' "$result" | tail -n +2)"
response_status="${result%%$'\n'*}"
response_body=""
[[ "$result" == *$'\n'* ]] && response_body="${result#*$'\n'}"
write_response "$response_status" "$response_body"
elif [[ "$method" == "GET" && "$path" == "$ISSUE_COMMENT_API_BASE"/issues/comments/* ]]; then
result=$(ISSUE_COMMENT_GET_ID="${path##*/}" python3 - <<'PY'
import json
@@ -299,7 +341,10 @@ else:
print(json.dumps(match))
PY
)
write_response "$(printf '%s' "$result" | head -n1)" "$(printf '%s' "$result" | tail -n +2)"
response_status="${result%%$'\n'*}"
response_body=""
[[ "$result" == *$'\n'* ]] && response_body="${result#*$'\n'}"
write_response "$response_status" "$response_body"
else
echo "Unexpected curl request: $method $url" >&2
exit 97
@@ -366,6 +411,7 @@ run_comment() {
cd "$REPO_DIR"
PATH="$BIN_DIR:$PATH" \
TMPDIR="$TMP_SCRATCH" \
HOME="$HOME_DIR" \
XDG_CONFIG_HOME="$XDG_DIR" \
MOSAIC_CREDENTIALS_FILE="$CREDENTIALS_FILE" \
ISSUE_COMMENT_TEA_LOG="$TEA_LOG" \
@@ -7,13 +7,38 @@ SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
WORK_DIR="${MOSAIC_TEST_WORK_DIR:-$PWD/.mosaic-test-work/issue-create-interactive-auth}"
REPO_DIR="$WORK_DIR/repo"
BIN_DIR="$WORK_DIR/bin"
HOME_DIR="$WORK_DIR/home"
LOG_FILE="$WORK_DIR/calls.log"
CREDENTIALS_FILE="$WORK_DIR/credentials.json"
rm -rf "$WORK_DIR"
mkdir -p "$REPO_DIR" "$BIN_DIR"
mkdir -p "$REPO_DIR" "$BIN_DIR" "$HOME_DIR"
git -C "$REPO_DIR" init -q
git -C "$REPO_DIR" remote add origin https://git.mosaicstack.dev/mosaicstack/stack.git
# HERMETICITY (#1007) — TWO mechanisms with DIFFERENT jobs; do not conflate them.
#
# OPERATIVE: the empty repo-local `mosaic.gitIdentity` below. get_gitea_token()
# step 0 resolves a per-agent identity from `git config --get mosaic.gitIdentity`,
# which on a provisioned agent seat is set GLOBALLY and so leaks into this fresh
# repo. It then reads a REAL per-slot token from $HOME and returns it WITHOUT ever
# consulting MOSAIC_CREDENTIALS_FILE, so the fixture credential below is silently
# ignored and the suite runs against a production credential. An empty repo-local
# value shadows the global one and reads back empty at rc=0. Measured: this suite
# resolves a per-slot token without it.
#
# CONTAINMENT: the sandboxed HOME in run_wrapper(). It only has to bound a failure
# that the pin should already have prevented.
#
# NOTE FOR ANYONE AUDITING THIS SUITE: the sandboxed HOME is containment, NOT an
# assay. Running a suite under a decoy HOME to test for this defect REMOVES the
# trigger — ~/.gitconfig is where the global identity lives, so step 0 is skipped
# by construction and every suite reads clean however vulnerable it is. To measure,
# REPLICATE a seat (a decoy HOME whose .gitconfig sets mosaic.gitIdentity, with no
# per-slot token) so step 0 reaches its fail-loud branch.
#
# Note the env-var route does NOT work: detect-platform.sh reads
# "${MOSAIC_GIT_IDENTITY:-}", and `:-` treats set-but-empty identically to unset.
git -C "$REPO_DIR" config mosaic.gitIdentity ""
cat > "$CREDENTIALS_FILE" <<'JSON'
{"gitea":{"mosaicstack":{"url":"https://git.mosaicstack.dev","token":"test-token"}}}
@@ -50,6 +75,7 @@ run_wrapper() {
(
cd "$REPO_DIR"
PATH="$BIN_DIR:$PATH" \
HOME="$HOME_DIR" \
MOSAIC_CREDENTIALS_FILE="$CREDENTIALS_FILE" \
MOSAIC_TEST_LOG="$LOG_FILE" \
"$@"
@@ -69,7 +69,7 @@ section_nums() { # $1 = output $2 = header-prefix
}
fail() { echo "FAIL: $1" >&2; exit 1; }
contains() { printf '%s\n' "$1" | grep -qx "$2"; }
contains() { grep -qx "$2" <<<"$1"; }
# ---------------------------------------------------------------------------
# Fixed (current) script behavior
@@ -0,0 +1,95 @@
#!/usr/bin/env bash
# test-mosaic-worktree-large-repo.sh — the helper must work on the repos it exists for.
#
# resolve_repo() took the first line of `git worktree list --porcelain` with
# `awk '/^worktree /{print substr($0,10); exit}'`. The `exit` closes the read end
# of the pipe while git is still writing, git takes SIGPIPE, and under
# `set -euo pipefail` the command substitution returns 141 — so the assignment
# fails, `set -e` aborts the function, and the script dies printing NOTHING. No
# message, no path, no worktree, exit 141.
#
# What makes it worth a dedicated test rather than a fixture line is WHEN it
# fires. If git finishes writing before awk leaves, there is no SIGPIPE and
# everything works. So the failure is a function of how much porcelain the repo
# produces: invisible on a three-worktree repo, reliable on a seventy-worktree
# one. It was measured on a repo with 73 worktrees (10 KB of porcelain) — rc=141,
# no output — and it had passed every hand-check before that, on small repos.
#
# A test that ran `git worktree list` against whatever repo it happens to sit in
# would inherit that same size dependence and would have PASSED on the tree that
# was broken. So git is stubbed on PATH and made to emit a large porcelain
# stream, which turns "depends on the repo you are standing in" into "always".
#
# Exit: 0 = the helper resolved the repo · 1 = it did not
set -uo pipefail
HERE="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)"
TOOL="${1:-$HERE/mosaic-worktree.sh}"
[ -x "$TOOL" ] || { printf 'test-mosaic-worktree-large-repo: not executable: %s\n' "$TOOL" >&2; exit 2; }
TMP="$(mktemp -d)"; trap 'rm -rf "$TMP"' EXIT
mkdir -p "$TMP/bin"
# The stub answers exactly the two calls resolve_repo makes, and answers the
# porcelain one with ~450 KB — comfortably past a 64 KB pipe buffer, so the
# writer is still writing when a reader that quits early goes away. Anything
# else exits non-zero rather than pretending to be git.
cat > "$TMP/bin/git" <<'STUB'
#!/bin/sh
while [ $# -gt 0 ]; do
case "$1" in -C) shift 2 ;; *) break ;; esac
done
case "$*" in
"rev-parse --git-dir")
echo .git; exit 0 ;;
"worktree list --porcelain")
# The first entry is the main worktree. That single line is all the helper
# needs, and it is exactly what it stopped receiving.
printf 'worktree /src/fakerepo\nHEAD %040d\nbranch refs/heads/main\n\n' 0
awk 'BEGIN{ for (i = 0; i < 4000; i++)
printf "worktree /src/fakerepo-worktrees/w%d\nHEAD %040d\nbranch refs/heads/topic-%d\n\n", i, 0, i }'
# NOT `exit 0`. Real git dies of SIGPIPE here and reports 141, and pipefail
# in the caller is what turns that into the silent abort. A stub that exits 0
# regardless hands the caller a clean status and the probe passes on the
# broken tree — which is how this test failed to be a test on its first run.
exit $? ;;
esac
exit 1
STUB
chmod +x "$TMP/bin/git"
fail=0
check() {
local why="$1" want="$2" got="$3"
if [ "$want" = "$got" ]; then
printf 'ok %s\n' "$why"
else
printf 'FAIL %s\n want: %s\n got: %s\n' "$why" "$want" "$got"
fail=1
fi
}
out="$(PATH="$TMP/bin:$PATH" "$TOOL" path feat/workspace-hygiene 2>&1)"
rc=$?
# Both halves are asserted. rc alone would pass if the helper started printing a
# usage error, and output alone would miss a non-zero exit — and the defect's
# signature is precisely a non-zero exit with no output, which only the pair
# distinguishes from every other way this could go wrong.
check 'resolving a repo with a large worktree list exits 0' 0 "$rc"
check 'and derives the path from the main worktree' /src/fakerepo-worktrees/feat-workspace-hygiene "$out"
printf '\n'
if [ "$fail" -eq 0 ]; then
printf 'mosaic-worktree: resolves against a large porcelain stream.\n'
else
cat <<'EOF'
mosaic-worktree could not resolve the repository.
An empty output with a non-zero exit is the SIGPIPE signature: a reader that
quits early (`awk ... exit`, `head -n`) kills the producer, and pipefail turns
that into a silent abort. Nothing in this script may close a git pipe early.
EOF
fi
exit "$fail"
+160
View File
@@ -0,0 +1,160 @@
#!/usr/bin/env bash
# Regression harness for secret-safe, identity-bound PR editing and explicit targets.
set -euo pipefail
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
WORK_DIR="${MOSAIC_TEST_WORK_DIR:-$PWD/.mosaic-test-work/pr-edit}"
REPO_DIR="$WORK_DIR/repo"; BIN_DIR="$WORK_DIR/bin"; HOME_DIR="$WORK_DIR/home"
XDG_DIR="$WORK_DIR/xdg"; LOG_FILE="$WORK_DIR/calls.log"
rm -rf "$WORK_DIR"; mkdir -p "$REPO_DIR" "$BIN_DIR" "$HOME_DIR" "$XDG_DIR/tea"
git -C "$REPO_DIR" init -q
git -C "$REPO_DIR" remote add origin https://git.uscllc.com/other/wrong-checkout.git
git -C "$REPO_DIR" config mosaic.gitIdentity ""
cat > "$XDG_DIR/tea/config.yml" <<'YAML'
logins:
- name: usc-coder3
url: https://git.uscllc.com
token: fixture-usc-token
- name: same-host-other
url: https://git.uscllc.com
token: fixture-other-token
- name: mosaic-coder3
url: https://git.mosaicstack.dev
token: fixture-mosaic-token
YAML
cat > "$BIN_DIR/tea" <<'SH'
#!/usr/bin/env bash
set -euo pipefail
# Deliberately misleading duplicate-name response: the wrapper must never use
# tea for identity validation because its name lookup is not host-bound.
[[ "$*" == "api --login duplicate /user" ]] && { printf '{"login":"coder3"}\n'; exit 0; }
exit 1
SH
cat > "$BIN_DIR/curl" <<'SH'
#!/usr/bin/env bash
set -euo pipefail
printf 'curl' >> "$MOSAIC_TEST_LOG"; printf ' <%s>' "$@" >> "$MOSAIC_TEST_LOG"; printf '\n' >> "$MOSAIC_TEST_LOG"
if [[ "${*: -1}" == */user ]]; then
printf '{"login":"%s"}\n' "${MOSAIC_STUB_AUTH_USER:-coder3}"
elif [[ "${*: -1}" == */repos/* && " $* " != *" -X PATCH "* ]]; then
[[ "${MOSAIC_STUB_SIGNAL:-}" == "TERM" ]] && { kill -TERM "$PPID"; sleep 1; }
[[ "${MOSAIC_STUB_SIGNAL:-}" == "INT" ]] && { kill -INT "$PPID"; sleep 1; }
printf '{"name":"repo"}\n'
else
printf '{"number":42,"draft":false}\n'
fi
SH
cat > "$BIN_DIR/gh" <<'SH'
#!/usr/bin/env bash
set -euo pipefail
printf 'gh' >> "$MOSAIC_TEST_LOG"; printf ' <%s>' "$@" >> "$MOSAIC_TEST_LOG"; printf '\n' >> "$MOSAIC_TEST_LOG"
SH
chmod +x "$BIN_DIR/tea" "$BIN_DIR/curl" "$BIN_DIR/gh" "$SCRIPT_DIR/pr-edit.sh"
run_wrapper() {
(cd "$REPO_DIR"; PATH="$BIN_DIR:$PATH" HOME="$HOME_DIR" XDG_CONFIG_HOME="$XDG_DIR" \
MOSAIC_TEST_LOG="$LOG_FILE" "$SCRIPT_DIR/pr-edit.sh" "$@")
}
assert_no_secret() {
! grep -q 'fixture-.*-token' "$LOG_FILE" || { echo "Credential leaked into curl argv/log" >&2; exit 1; }
}
# The explicit target differs from CWD origin and must govern BOTH host and slug.
: > "$LOG_FILE"
# shellcheck disable=SC2016 # literal backticks prove argument-array body safety.
MOSAIC_GIT_IDENTITY=coder3 run_wrapper -n 42 --login mosaic-coder3 -r mosaicstack/stack \
-H git.mosaicstack.dev --title 'New title' --body 'Body with `literal` bytes' --base develop --draft >/dev/null
python3 - "$LOG_FILE" <<'PY'
import json, pathlib, sys
lines = pathlib.Path(sys.argv[1]).read_text().splitlines()
assert len(lines) == 3, lines
assert "https://git.mosaicstack.dev/api/v1/user" in lines[0], lines
assert "https://git.mosaicstack.dev/api/v1/repos/mosaicstack/stack" in lines[1], lines
assert "https://git.mosaicstack.dev/api/v1/repos/mosaicstack/stack/pulls/42" in lines[2], lines
assert all("--config" in line for line in lines), lines
assert "Authorization:" not in "\n".join(lines), lines
payload = lines[2].split(" <-d> <", 1)[1].split("> <https://", 1)[0]
assert json.loads(payload) == {"title":"New title","body":"Body with `literal` bytes","base":"develop","draft":True}
PY
assert_no_secret
# Ready maps to false and still preflights before the write.
: > "$LOG_FILE"
MOSAIC_GIT_IDENTITY=coder3 run_wrapper -n 42 --login usc-coder3 -r USC/uconnect -H git.uscllc.com --ready >/dev/null
grep -q '"draft": false' "$LOG_FILE"; assert_no_secret
# Identity is mandatory; no ambient/first-host login can write.
: > "$LOG_FILE"
if run_wrapper -n 42 --login usc-coder3 --draft >/dev/null 2>&1; then echo "Unset identity wrote" >&2; exit 1; fi
[[ ! -s "$LOG_FILE" ]] || { echo "Unset identity reached curl" >&2; exit 1; }
# Explicit and ambient same-host wrong principals both refuse after identity
# lookup but before repo preflight/PATCH. The /user read is expected curl #1.
for mode in explicit ambient; do
: > "$LOG_FILE"
if [[ "$mode" == explicit ]]; then
cmd=(--login same-host-other)
else
cmd=(); export GITEA_LOGIN=same-host-other
fi
if MOSAIC_STUB_AUTH_USER=other MOSAIC_GIT_IDENTITY=coder3 run_wrapper -n 42 "${cmd[@]}" -r USC/uconnect -H git.uscllc.com --draft >/dev/null 2>&1; then
echo "$mode wrong identity wrote" >&2; exit 1
fi
unset GITEA_LOGIN
[[ "$(wc -l < "$LOG_FILE")" -eq 1 ]] || { echo "$mode wrong identity passed identity lookup" >&2; exit 1; }
! grep -q '/repos/' "$LOG_FILE" || { echo "$mode wrong identity reached repo preflight/PATCH" >&2; exit 1; }
done
# Set identity with no explicit/ambient login refuses rather than selecting first host login.
: > "$LOG_FILE"
if MOSAIC_GIT_IDENTITY=coder3 run_wrapper -n 42 -r USC/uconnect -H git.uscllc.com --draft >/dev/null 2>&1; then
echo "Missing login selected a principal" >&2; exit 1
fi
[[ ! -s "$LOG_FILE" ]] || { echo "Missing login reached curl" >&2; exit 1; }
# Split-credential probe for the duplicate-name cross-host seam: tea's
# name-only /user would report coder3, while the selected host-bound curl token
# reports other. The wrapper must trust only the latter handle used by PATCH.
: > "$LOG_FILE"
if MOSAIC_STUB_AUTH_USER=other MOSAIC_GIT_IDENTITY=coder3 run_wrapper -n 42 --login mosaic-coder3 \
-r mosaicstack/stack -H git.mosaicstack.dev --draft >/dev/null 2>&1; then
echo "Duplicate-name split credential reached PATCH" >&2; exit 1
fi
[[ "$(wc -l < "$LOG_FILE")" -eq 1 ]] || { echo "Duplicate-name identity mismatch passed /user" >&2; cat "$LOG_FILE" >&2; exit 1; }
! grep -q -- '-X> <PATCH' "$LOG_FILE" || { echo "Duplicate-name mismatch mutated" >&2; exit 1; }
# TERM and INT during repo preflight clean up, do not mutate, and return the
# signal status rather than swallowing termination into success.
for sig in TERM INT; do
: > "$LOG_FILE"
set +e
MOSAIC_STUB_SIGNAL="$sig" MOSAIC_GIT_IDENTITY=coder3 run_wrapper -n 42 --login usc-coder3 \
-r USC/uconnect -H git.uscllc.com --draft >/dev/null 2>&1
rc=$?
set -e
[[ "$rc" -ne 0 ]] || { echo "$sig was swallowed into success" >&2; exit 1; }
[[ "$rc" -eq 143 || "$rc" -eq 130 ]] || { echo "$sig returned unexpected status $rc" >&2; exit 1; }
! grep -q -- '-X> <PATCH' "$LOG_FILE" || { echo "$sig continued into PATCH" >&2; exit 1; }
assert_no_secret
done
# Cross-host credential fails before curl; explicit target preflight failure blocks PATCH.
: > "$LOG_FILE"
if MOSAIC_GIT_IDENTITY=coder3 run_wrapper -n 42 --login mosaic-coder3 -r USC/uconnect -H git.uscllc.com --draft >/dev/null 2>&1; then
echo "Cross-host login wrote" >&2; exit 1
fi
[[ ! -s "$LOG_FILE" ]] || { echo "Cross-host login reached curl" >&2; exit 1; }
if run_wrapper -n 42 --draft --ready >/dev/null 2>&1; then echo "Accepted conflicting modes" >&2; exit 1; fi
if run_wrapper -n 42 >/dev/null 2>&1; then echo "Accepted no-op edit" >&2; exit 1; fi
run_wrapper --help 2>&1 | grep -q '^Usage:'
# GitHub retains provider-native edit/readiness behavior.
git -C "$REPO_DIR" remote set-url origin https://github.com/acme/widgets.git
: > "$LOG_FILE"; run_wrapper -n 7 --title 'GitHub title' --draft >/dev/null
grep -q 'gh <pr> <edit> <7> <--title> <GitHub title>' "$LOG_FILE"
grep -q 'gh <pr> <ready> <7> <--undo>' "$LOG_FILE"
echo "PR edit regression harness passed"
@@ -8,6 +8,7 @@ WORK_ROOT="${AGENT_WORK_ROOT:-${HOME:-/tmp}/mosaic/agent-work}"
SANDBOX="$WORK_ROOT/pr-merge-empty-uid-test-$$"
MOCK_BIN="$SANDBOX/bin"
REPO_DIR="$SANDBOX/repo"
HOME_DIR="$SANDBOX/home"
LOG_FILE="$SANDBOX/mock.log"
cleanup() {
@@ -15,7 +16,7 @@ cleanup() {
}
trap cleanup EXIT
mkdir -p "$MOCK_BIN" "$REPO_DIR"
mkdir -p "$MOCK_BIN" "$REPO_DIR" "$HOME_DIR"
: > "$LOG_FILE"
cat > "$MOCK_BIN/tea" <<'EOF'
@@ -109,7 +110,48 @@ chmod +x "$MOCK_BIN/curl"
cd "$REPO_DIR"
git init -q
git remote add origin https://git.mosaicstack.dev/mosaicstack/stack.git
# HERMETICITY (#1007) — TWO mechanisms with DIFFERENT jobs; do not conflate them.
#
# OPERATIVE: the empty repo-local `mosaic.gitIdentity` below. get_gitea_token()
# step 0 resolves a per-agent identity from `git config --get mosaic.gitIdentity`,
# which on a provisioned agent seat is set GLOBALLY and so leaks into this fresh
# repo. Step 0 runs BEFORE the credential loader AND before the GITEA_TOKEN env
# check, so the `GITEA_TOKEN=redacted-test-token` exported below is silently
# overridden and a REAL per-slot token from $HOME is what flows through the
# wrapper. Measured on a provisioned seat before this pin: all 5 mock-curl calls
# carried the real per-slot token in argv and the fixture token was never used at
# ALL. Three consequences specific to this suite:
# 1. pr-merge.sh passes the token as `-H "Authorization: token $token"` and the
# mock curl logs full argv, so the real credential is written to $LOG_FILE
# on disk — transiently: the suite truncates that file between phases and
# the EXIT trap removes $SANDBOX, so it leaves NO post-hoc trace. That is
# why this suite was the hardest of the three to detect; observing it needs
# an instrument that captures argv while the run is live.
# 2. Every failure path dumps $OUTPUT/$LOG_FILE to stderr through
# `sed 's/redacted-test-token/***REDACTED***/g'` — a redaction pattern that
# is the literal fixture string and therefore CANNOT match the token
# actually in use.
# 3. The leak assertion at "Token leaked to pr-merge.sh output" greps for that
# same fixture string, so on a provisioned seat it passes vacuously: it is
# searching for a value the run never used.
# An empty repo-local value shadows the global one and reads back empty at rc=0.
#
# CONTAINMENT: the sandboxed HOME exported below. It only has to bound a failure
# that the pin should already have prevented.
#
# NOTE FOR ANYONE AUDITING THIS SUITE: the sandboxed HOME is containment, NOT an
# assay. Running a suite under a decoy HOME to test for this defect REMOVES the
# trigger — ~/.gitconfig is where the global identity lives, so step 0 is skipped
# by construction and every suite reads clean however vulnerable it is. To measure,
# REPLICATE a seat (a decoy HOME whose .gitconfig sets mosaic.gitIdentity, with no
# per-slot token) so step 0 reaches its fail-loud branch.
#
# Note the env-var route does NOT work: detect-platform.sh reads
# "${MOSAIC_GIT_IDENTITY:-}", and `:-` treats set-but-empty identically to unset.
git -C "$REPO_DIR" config mosaic.gitIdentity ""
# $SANDBOX/$HOME_DIR were derived from the real $HOME above, before this export.
export HOME="$HOME_DIR"
export PATH="$MOCK_BIN:$PATH"
export PR_MERGE_TEST_LOG="$LOG_FILE"
export GITEA_LOGIN="git.mosaicstack.dev"
@@ -8,12 +8,68 @@ WORK_DIR="${MOSAIC_TEST_WORK_DIR:-$PWD/.mosaic-test-work/pr-metadata-gitea}"
REPO_DIR="$WORK_DIR/repo"
FIXTURE_DIR="$WORK_DIR/fixtures"
STUB_DIR="$WORK_DIR/stubs"
HOME_DIR="$WORK_DIR/home"
CREDENTIALS_FILE="$WORK_DIR/credentials.json"
rm -rf "$WORK_DIR"
mkdir -p "$REPO_DIR" "$FIXTURE_DIR" "$STUB_DIR"
mkdir -p "$REPO_DIR" "$FIXTURE_DIR" "$STUB_DIR" "$HOME_DIR"
git -C "$REPO_DIR" init -q
git -C "$REPO_DIR" remote add origin https://git.uscllc.com/USC/uconnect.git
# HERMETICITY (#1007) — TWO mechanisms with DIFFERENT jobs; do not conflate them.
#
# OPERATIVE: the empty repo-local `mosaic.gitIdentity` below. get_gitea_token()
# step 0 resolves a per-agent identity from `git config --get mosaic.gitIdentity`,
# which on a provisioned agent seat is set GLOBALLY and so leaks into this fresh
# repo. Step 0 runs BEFORE the credential loader AND before the GITEA_TOKEN env
# check, so the `GITEA_TOKEN="stub-token"` set in the run helpers below is
# silently overridden and a REAL per-slot token from $HOME is what reaches curl.
# Measured on a provisioned seat before this pin: both stub-curl calls carried
# the real token in argv. An empty repo-local value shadows the global one and
# reads back empty at rc=0.
#
# CONTAINMENT: the sandboxed HOME in the three run helpers below. It only has to
# bound a failure that the pin should already have prevented.
#
# NOTE FOR ANYONE AUDITING THIS SUITE: the sandboxed HOME is containment, NOT an
# assay. Running a suite under a decoy HOME to test for this defect REMOVES the
# trigger — ~/.gitconfig is where the global identity lives, so step 0 is skipped
# by construction and every suite reads clean however vulnerable it is. To measure,
# REPLICATE a seat (a decoy HOME whose .gitconfig sets mosaic.gitIdentity, with no
# per-slot token) so step 0 reaches its fail-loud branch. See
# test-gitea-token-identity.sh for the stronger `env -i HOME=…` form used where a
# suite's whole subject IS identity resolution.
#
# Note the env-var route does NOT work: detect-platform.sh reads
# "${MOSAIC_GIT_IDENTITY:-}", and `:-` treats set-but-empty identically to unset.
git -C "$REPO_DIR" config mosaic.gitIdentity ""
# The pin above removes step 0, but this suite has a SECOND, independent
# dependency on operator state, and closing only the first would leave the suite
# red on any hermetic environment. The `GITEA_TOKEN="stub-token"` /
# `GITEA_URL="https://git.example.test"` pair the run helpers set is INERT: step 2
# of get_gitea_token accepts GITEA_TOKEN only when GITEA_URL matches the remote
# host, and this repo's origin is git.uscllc.com, so that pair can never satisfy
# it. Before this fixture the only credential that could reach the authenticated
# curl branch was a REAL one — from step 0 on an agent seat, or from step 1
# reading the operator's own ~/.config/mosaic/credentials.json. That is why the
# "curl success path" case passed: not because the stub credential worked, but
# because a production credential was available.
#
# A fixture is used rather than relying on the sandboxed HOME making step 1 find
# nothing: a test that passes because production configuration is ABSENT fails
# the moment it is present. Step 1 now resolves deterministically to a value that
# is a fixture on every machine.
cat > "$CREDENTIALS_FILE" <<'JSON'
{
"gitea": {
"usc": {
"url": "https://git.uscllc.com",
"token": "stub-token"
}
}
}
JSON
cat > "$FIXTURE_DIR/gitea-standard.json" <<'JSON'
{
@@ -131,6 +187,8 @@ run_curl_success_case() {
set +e
output=$(cd "$REPO_DIR" && \
PATH="$STUB_DIR:$PATH" \
HOME="$HOME_DIR" \
MOSAIC_CREDENTIALS_FILE="$CREDENTIALS_FILE" \
TMPDIR="$tmpdir" \
GITEA_TOKEN="stub-token" \
GITEA_URL="https://git.example.test" \
@@ -170,6 +228,8 @@ run_curl_early_exit_cleanup_case() {
set +e
output=$(cd "$REPO_DIR" && \
PATH="$STUB_DIR:$PATH" \
HOME="$HOME_DIR" \
MOSAIC_CREDENTIALS_FILE="$CREDENTIALS_FILE" \
TMPDIR="$tmpdir" \
GITEA_TOKEN="stub-token" \
GITEA_URL="https://git.example.test" \
@@ -204,7 +264,8 @@ run_curl_early_exit_cleanup_case() {
run_case() {
local fixture="$1" expected_number="$2" expected_head="$3"
local output
output=$(cd "$REPO_DIR" && MOSAIC_GITEA_PR_METADATA_RAW_FILE="$fixture" "$SCRIPT_DIR/pr-metadata.sh" -n "$expected_number")
output=$(cd "$REPO_DIR" && HOME="$HOME_DIR" MOSAIC_CREDENTIALS_FILE="$CREDENTIALS_FILE" \
MOSAIC_GITEA_PR_METADATA_RAW_FILE="$fixture" "$SCRIPT_DIR/pr-metadata.sh" -n "$expected_number")
PR_METADATA_OUTPUT="$output" python3 - "$expected_number" "$expected_head" <<'PY'
import json
import os
@@ -225,7 +225,10 @@ write_response() {
emit() {
# Split a two-line "status\n<json body>" python result into the response.
local result="$1"
write_response "$(printf '%s' "$result" | head -n1)" "$(printf '%s' "$result" | tail -n +2)"
response_status="${result%%$'\n'*}"
response_body=""
[[ "$result" == *$'\n'* ]] && response_body="${result#*$'\n'}"
write_response "$response_status" "$response_body"
}
mode="${PR_REVIEW_TEST_MODE:-}"
@@ -436,6 +439,19 @@ elif mode == "comment-url-wrong-repo":
elif mode == "comment-url-suffix-injection":
# Prefix-injected: a bare endswith("/<slug>/pulls/123") test would ACCEPT it.
pr_url = f"{_origin}/deceptive{_slug}/pulls/123"
elif mode == "comment-url-wrong-port":
# #991 bound: an EXPLICIT non-default port is a different service on the same
# host. Relaxing http-vs-https must NOT relax this.
pr_url = f"{_p.scheme}://{_p.hostname}:8443{_slug}/pulls/123"
elif mode == "comment-url-non-web-scheme":
# #991 bound: ONLY http/https collapse; any other scheme stays distinguishing.
pr_url = f"ftp://{_p.netloc}{_slug}/pulls/123"
elif mode == "comment-url-scheme-downgrade":
# #991, and the only URL mode here that must be ACCEPTED. A Gitea whose
# ROOT_URL is http:// returns http:// object URLs for a repo reached over
# https://. Same host, same path, correct record — a truthful provider
# answer about a comment that landed, not a forgery.
pr_url = f"http://{_p.netloc}{_slug}/pulls/123"
elif mode == "comment-mixed-case-slug":
# #875: EXPECTED_REPO_SLUG is taken verbatim from GITEA_API_BASE and can be
# mixed-case (e.g. "USC/uconnect"), but Gitea canonicalizes the returned
@@ -890,11 +906,16 @@ fi
assert_no_temp_leak "review-body-reuse"
# Cases 12-15 (#865 Blocker 3): a PR comment whose id/author/body are all correct
# but whose provider-returned pull_request_url is forged must FAIL CLOSED.
# Verification pins the URL's ORIGIN (scheme+host+effective-port) and FULL path
# (deployment prefix + exact owner/repo + kind + number); a bare endswith/suffix
# test would wrongly accept the look-alike-host and prefix-injection variants.
for bad_mode in comment-url-wrong-host comment-url-wrong-owner comment-url-wrong-repo comment-url-suffix-injection; do
# but whose provider-returned pull_request_url does not belong to this PR must
# FAIL CLOSED. Verification pins the URL's ORIGIN (scheme-class + host + explicit
# non-default port) and FULL path (deployment prefix + exact owner/repo + kind +
# number); a bare endswith/suffix test would wrongly accept the look-alike-host
# and prefix-injection variants. comment-url-wrong-port and
# comment-url-non-web-scheme (#991) bound the scheme relaxation from the other
# side: collapsing http/https must not also collapse a different port or a
# different scheme family.
for bad_mode in comment-url-wrong-host comment-url-wrong-owner comment-url-wrong-repo \
comment-url-suffix-injection comment-url-wrong-port comment-url-non-web-scheme; do
if run_review "$bad_mode" comment durable-body; then
echo "FAIL: forged comment URL ($bad_mode) was accepted" >&2
cat "$OUTPUT_FILE" >&2
@@ -920,6 +941,19 @@ run_review comment-mixed-case-slug comment durable-body https://git.mosaicstack.
grep -q 'Added and verified comment on Gitea PR #123' "$OUTPUT_FILE"
assert_no_temp_leak "comment-mixed-case-slug"
# Case 15c (#991): the deployment's Gitea ROOT_URL is http:// while every client
# reaches it over https://, so the provider returns an http:// pull_request_url
# for a comment that is otherwise entirely correct. Same class as 15b — a
# legitimate provider response, not a spoof — and a scheme-strict compare
# rejects it on EVERY comment, deterministically. That is not a cosmetic false
# negative here: on a host where no seat can create a review OBJECT, this
# comment-form record is the only gate-16 evidence obtainable, and the wrapper
# refuses all of it while the comment sits durably on the PR. Host, path, owner,
# repo, kind and number stay strict; only http-vs-https is relaxed.
run_review comment-url-scheme-downgrade comment durable-body
grep -q 'Added and verified comment on Gitea PR #123' "$OUTPUT_FILE"
assert_no_temp_leak "comment-url-scheme-downgrade"
# Case 16 (#865 ITEM 1, current-head TOCTOU): the PR head advances between the
# pre-submit head read (which pins the review) and the post-verify re-read. The
# review is genuinely created and verified as pinned to the OLD head, but the
@@ -222,8 +222,8 @@ grep -q 'Unknown action: bogus-action' "$OUTPUT_FILE"
# --- Case 2: -h/--help documents both overrides.
HELP_TEXT="$("$SCRIPT_DIR/pr-review.sh" -h)"
echo "$HELP_TEXT" | grep -q -- '-r, --repo'
echo "$HELP_TEXT" | grep -q -- '-H, --host'
grep -q -- '-r, --repo' <<<"$HELP_TEXT"
grep -q -- '-H, --host' <<<"$HELP_TEXT"
# --- Case 3 (comment): a TRUE no-git-origin dir + -r/-H must not silently die
# and must not fail with "not a git repository or no origin remote" either.
+703
View File
@@ -0,0 +1,703 @@
#!/usr/bin/env bash
# test-wrapper-guard.sh — hermetic behavioural regression for wrapper-guard.sh.
#
# Resolves no credentials, touches no network, and creates no repository: the
# guard reads a hook payload on stdin and answers with an exit code, so the whole
# contract is testable from fixtures.
#
# The fixtures are written to a temp file rather than passed inline, and this is
# not stylistic. The guard inspects the literal text of the Bash command it is
# handed. A test that embeds `git clone ... $HOME` inside its own command line
# trips the guard on the harness instead of on the fixture — which is exactly
# what happened the first time this was checked by hand. Substring matching over
# whole command text is the guard's deliberate fail-closed posture; a test that
# does not account for it silently measures the wrong thing.
#
# Exit: 0 = every fixture behaved as specified · 1 = at least one did not
set -uo pipefail
HERE="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)"
GUARD="${1:-$HERE/wrapper-guard.sh}"
[ -x "$GUARD" ] || { printf 'test-wrapper-guard: not executable: %s\n' "$GUARD" >&2; exit 2; }
TMP="$(mktemp -d)"; trap 'rm -rf "$TMP"' EXIT
FIXTURES="$TMP/fixtures.tsv"
# Each line: <expected-exit> TAB <hook payload> TAB <what it proves>
# [ TAB <substring the block message must contain> ]
# 0 = allowed, 2 = blocked. The optional fourth field is how the remediation
# itself gets checked; without it a block is only asserted to have happened,
# not to have been useful.
{
printf '2\t{"tool_input":{"command":"git clone https://example.invalid/x ~/wt"}}\tcheckout into $HOME is refused\n'
printf '2\t{"tool_input":{"command":"git worktree add ~/wt topic"}}\tworktree into $HOME is refused\n'
printf '2\t{"tool_input":{"command":"g\\"it\\" clone https://example.invalid/x $HOME/wt"}}\ta double quote inside git does not hide a checkout\n'
printf '2\t{"tool_input":{"command":"g'"'"'it'"'"' clone https://example.invalid/x $HOME/wt"}}\ta single quote inside git does not hide a checkout\n'
printf '2\t{"tool_input":{"command":"g\\\\it clone https://example.invalid/x $HOME/wt"}}\tan unquoted escape inside git does not hide a checkout\n'
# Path words use the same quote/escape state machine as names, but preserve
# substitutions so HOME remains visible. Quotes do not split the path word.
printf '2\t{"tool_input":{"command":"git clone x \\"$HOME\\"/wt"}}\ta closing quote between HOME and slash does not hide the path\n'
printf '2\t{"tool_input":{"command":"git clone x ${HOME}/wt"}}\tthe braced HOME spelling is the same home path\n'
printf '2\t{"tool_input":{"command":"git clone x \\"${HOME}\\"/wt"}}\tbraced HOME may also end a quoted span before the slash\n'
# Lexically equivalent absolute paths must be compared after shell-known HOME
# expansion and dot-segment normalization, without resolving filesystem links.
printf '2\t{"tool_input":{"command":"git clone x /var/../$HOME/wt"}}\tHOME expansion after parent traversal is normalized before comparison\n'
printf '2\t{"tool_input":{"command":"git worktree add /var/../${HOME}/wt"}}\tworktree placement also normalizes embedded HOME expansion\n'
printf '2\t{"tool_input":{"command":"git clone --separate-git-dir=/var/../$HOME/gd x /src/wt"}}\tseparate Git state cannot hide behind parent traversal\n'
printf '0\t{"tool_input":{"command":"git clone x $HOME/../outside-home/wt"}}\ta parent segment that leaves HOME is not over-blocked\n'
# The target may be HOME itself. End-of-command and whitespace terminate the
# token just as a slash does; punctuation that can extend a path does not.
printf '2\t{"tool_input":{"command":"git clone x $HOME"}}\tthe unbraced variable may name HOME exactly\n'
printf '2\t{"tool_input":{"command":"git clone x \\"$HOME\\""}}\tquotes do not change the exact HOME target\n'
printf '2\t{"tool_input":{"command":"git clone x ${HOME}"}}\tthe braced variable may name HOME exactly\n'
printf '2\t{"tool_input":{"command":"git clone x ~"}}\ttilde may name HOME exactly\n'
printf '2\t{"tool_input":{"command":"git worktree add $HOME topic"}}\twhitespace terminates an exact HOME target before another argument\n'
# Unquoted POSIX metacharacters terminate the target word even without spaces.
printf '2\t{"tool_input":{"command":"git clone x $HOME;echo x"}}\tsemicolon terminates an exact HOME target\n'
printf '2\t{"tool_input":{"command":"git clone x \\"$HOME\\"&& echo x"}}\tand-if terminates a quoted exact HOME target\n'
printf '2\t{"tool_input":{"command":"git clone x ${HOME}| cat"}}\ta pipe terminates a braced exact HOME target\n'
printf '2\t{"tool_input":{"command":"git clone x ~&"}}\tbackground operator terminates a tilde HOME target\n'
printf '2\t{"tool_input":{"command":"git clone x $HOME</dev/null"}}\tinput redirection terminates the target word\n'
printf '2\t{"tool_input":{"command":"git clone x $HOME>out"}}\toutput redirection terminates the target word\n'
printf '2\t{"tool_input":{"command":"( git clone x $HOME)"}}\ta subshell close terminates the exact HOME target\n'
printf '2\t{"tool_input":{"command":"git clone x $HOME\\necho x"}}\ta literal newline terminates the target word\n'
printf '0\t{"tool_input":{"command":"git clone x $HOME_BACKUP/wt"}}\ta longer HOME-prefixed variable is a different path\n'
printf '0\t{"tool_input":{"command":"git clone x $HOMEBREW/wt"}}\tHOMEBREW is not HOME either\n'
printf '0\t{"tool_input":{"command":"git clone x $HOME.bak/wt"}}\ta dot continues the path token into a sibling name\n'
printf '0\t{"tool_input":{"command":"git clone x $HOME+bak/wt"}}\tplus is ordinary sibling filename content\n'
printf '0\t{"tool_input":{"command":"git clone x $HOME@bak/wt"}}\tat-sign is ordinary sibling filename content\n'
printf '0\t{"tool_input":{"command":"git clone x $HOME,bak/wt"}}\tcomma is ordinary sibling filename content\n'
printf '0\t{"tool_input":{"command":"git clone x $HOME:bak/wt"}}\tcolon is ordinary sibling filename content\n'
printf '0\t{"tool_input":{"command":"git clone x $HOME=bak/wt"}}\tequals is ordinary sibling filename content\n'
printf '0\t{"tool_input":{"command":"git clone x ${HOME}+bak/wt"}}\tbraced HOME plus suffix is still a sibling\n'
printf '0\t{"tool_input":{"command":"git clone x /home/tester+bak/wt"}}\ta literal plus-suffixed home path is a sibling\n'
printf '0\t{"tool_input":{"command":"git clone x /home/tester@bak/wt"}}\ta literal at-suffixed home path is a sibling\n'
printf '0\t{"tool_input":{"command":"git clone x $HOME+bak/wt;echo x"}}\ta later terminator does not turn a sibling into HOME\n'
printf '0\t{"tool_input":{"command":"git clone x $HOME@bak/wt&& echo x"}}\tand-if after a sibling preserves the allow\n'
printf '0\t{"tool_input":{"command":"git clone x \\"$HOME;bak/wt\\""}}\ta quoted semicolon is filename content, not a boundary\n'
printf '0\t{"tool_input":{"command":"git clone x $HOME\\\\;bak/wt"}}\tan escaped semicolon is filename content, not a boundary\n'
printf '0\t{"tool_input":{"command":"git clone x $HOME\\u001b/wt"}}\ta raw internal-marker byte is encoded as filename content\n'
printf '0\t{"tool_input":{"command":"git clone x /home/tester.bak/wt"}}\ta literal sibling path is not beneath HOME\n'
printf '0\t{"tool_input":{"command":"git clone x /home/testerx/wt"}}\ta longer literal basename is not HOME\n'
printf '0\t{"tool_input":{"command":"git clone x ~root/wt"}}\tanother account tilde is not this account HOME\n'
printf '0\t{"tool_input":{"command":"git clone x $HOME}/wt"}}\ta closing brace without an opening brace is a literal suffix\n'
printf '0\t{"tool_input":{"command":"git clone x ${HOME/wt"}}\tan opening brace without a close is not a HOME expansion\n'
# Quote removal must not create an expansion the shell never performs.
printf '0\t{"tool_input":{"command":"git clone x '"'"'$HOME'"'"'/wt"}}\tsingle-quoted HOME is a literal directory name\n'
printf '0\t{"tool_input":{"command":"git clone x \\\\$HOME/wt"}}\tan escaped dollar makes HOME literal outside quotes\n'
printf '0\t{"tool_input":{"command":"git clone x \\"\\\\$HOME\\"/wt"}}\tan escaped dollar makes HOME literal inside double quotes\n'
printf '0\t{"tool_input":{"command":"git clone x \\"~/wt\\""}}\ttilde does not expand inside double quotes\n'
printf '0\t{"tool_input":{"command":"git clone x '"'"'~/wt'"'"'"}}\ttilde does not expand inside single quotes\n'
printf '0\t{"tool_input":{"command":"git clone x \\\\~/wt"}}\tan escaped tilde is literal too\n'
printf '0\t{"tool_input":{"command":"git clone https://example.invalid/x /src/wt"}}\tcheckout onto a work filesystem is fine\n'
# Round ten: placement is decided by the destination and the one clone option
# that creates repository state elsewhere, not by every HOME-valued word in
# the command. Sources, templates, references, and environment are not targets.
printf '0\t{"tool_input":{"command":"NOTE=$HOME git clone https://example.invalid/x /src/wt"}}\tan unrelated assignment carrying HOME is not checkout placement\n'
printf '0\t{"tool_input":{"command":"git clone --reference=$HOME https://example.invalid/x /src/wt"}}\ta HOME reference is an object source, not checkout placement\n'
printf '0\t{"tool_input":{"command":"GIT_DIR=$HOME/x git clone https://example.invalid/x /src/wt"}}\tclone does not place its destination from ambient GIT_DIR\n'
printf '0\t{"tool_input":{"command":"git clone --template=$HOME/t https://example.invalid/x /src/wt"}}\ta HOME template source is not checkout placement\n'
printf '2\t{"tool_input":{"command":"git clone --separate-git-dir=$HOME/gd https://example.invalid/x /src/wt"}}\tseparate-git-dir explicitly places repository state under HOME\n'
printf '2\t{"tool_input":{"command":"git clone --separate-git-dir $HOME/gd https://example.invalid/x /src/wt"}}\tthe space-separated placement option is equivalent\n'
printf '0\t{"tool_input":{"command":"git worktree add --reason=$HOME/note /src/wt"}}\ta worktree reason is metadata, not its path\n'
printf '0\t{"tool_input":{"command":"git clone $HOME/source /src/wt"}}\ta HOME source with an explicit safe destination is not placement\n'
printf '0\t{"tool_input":{"command":"git clone --reference $HOME https://example.invalid/x /src/wt"}}\ta space-separated HOME reference remains a source\n'
printf '0\t{"tool_input":{"command":"git clone --template $HOME/t https://example.invalid/x /src/wt"}}\ta space-separated HOME template remains a source\n'
printf '2\t{"tool_input":{"command":"git clone 2>/dev/null https://example.invalid/x $HOME/wt"}}\ta redirection before clone arguments does not become the destination\n'
printf '2\t{"tool_input":{"command":"git clone --reference $HOME https://example.invalid/x $HOME/wt"}}\ta source option does not hide a later HOME destination\n'
# Round eleven: Git accepts boolean options as a rule-generated family,
# including --no-* negations. Each command below was checked with Git itself:
# `git clone <option> /nonexistent-src /nonexistent-dst` reaches the missing
# source instead of reporting an unknown option. The HOME word is the source,
# not the explicit /src destination, so Bash expansion is allowed here.
printf '0\t{"tool_input":{"command":"git clone --bare $HOME/source /src/wt"}}\tbare clone keeps its HOME source distinct from the safe destination\n'
printf '0\t{"tool_input":{"command":"git clone --mirror $HOME/source /src/wt"}}\tmirror is an accepted flag and does not consume the HOME source\n'
printf '0\t{"tool_input":{"command":"git clone --ipv4 $HOME/source /src/wt"}}\tipv4 is an accepted flag and does not consume the HOME source\n'
printf '0\t{"tool_input":{"command":"git clone --ipv6 $HOME/source /src/wt"}}\tipv6 is an accepted flag and does not consume the HOME source\n'
printf '0\t{"tool_input":{"command":"git clone --no-local $HOME/source /src/wt"}}\tgenerated no-local remains a flag rather than a placement option\n'
printf '0\t{"tool_input":{"command":"git clone --no-reject-shallow $HOME/source /src/wt"}}\tgenerated no-reject-shallow remains a flag rather than placement\n'
printf '0\t{"tool_input":{"command":"git clone -4 $HOME/source /src/wt"}}\tthe short IPv4 flag leaves the HOME word in source position\n'
printf '0\t{"tool_input":{"command":"git clone -6 $HOME/source /src/wt"}}\tthe short IPv6 flag leaves the HOME word in source position\n'
printf '0\t{"tool_input":{"command":"git clone --no-bare $HOME/source /src/wt"}}\tan unusual generated negation is accepted without enumeration\n'
printf '0\t{"tool_input":{"command":"git clone --no-sparse $HOME/source /src/wt"}}\tgenerated no-sparse is accepted without enumeration\n'
printf '0\t{"tool_input":{"command":"git clone --no-dissociate $HOME/source /src/wt"}}\tgenerated no-dissociate is accepted without enumeration\n'
printf '0\t{"tool_input":{"command":"git clone --no-shallow-submodules $HOME/source /src/wt"}}\ta long generated negation is accepted without enumeration\n'
printf '0\t{"tool_input":{"command":"git clone --no-quiet $HOME/source /src/wt"}}\tgenerated no-quiet is accepted without enumeration\n'
printf '0\t{"tool_input":{"command":"git clone --no-progress $HOME/source /src/wt"}}\tgenerated no-progress is accepted without enumeration\n'
printf '0\t{"tool_input":{"command":"git clone --no-recurse-submodules $HOME/source /src/wt"}}\tgenerated no-recurse-submodules is accepted without enumeration\n'
# Git also generates accepted long abbreviations and short-option bundles.
# The closed value-taking option grammar must consume their values correctly.
printf '0\t{"tool_input":{"command":"git clone --templ $HOME/t $HOME/source /src/wt"}}\tan accepted template abbreviation consumes metadata rather than the source\n'
printf '0\t{"tool_input":{"command":"git clone -qj 1 $HOME/source /src/wt"}}\ta short flag bundle ending in jobs consumes its separate value\n'
printf '0\t{"tool_input":{"command":"git clone -qb topic $HOME/source /src/wt"}}\ta short flag bundle ending in branch consumes its separate value\n'
printf '2\t{"tool_input":{"command":"git clone --separate-git-d=$HOME/gd https://example.invalid/x /src/wt"}}\tan accepted placement-option abbreviation remains blocked in attached form\n'
printf '2\t{"tool_input":{"command":"git clone --separate-git-d $HOME/gd https://example.invalid/x /src/wt"}}\tan accepted placement-option abbreviation remains blocked in separate form\n'
# Worktree boolean options have the same generated-negation grammar. The next
# positional is its real path, so safe paths allow and HOME paths still block.
printf '0\t{"tool_input":{"command":"git worktree add --no-force /src/wt"}}\tgenerated worktree no-force accepts a safe path\n'
printf '0\t{"tool_input":{"command":"git worktree add --no-detach /src/wt"}}\tgenerated worktree no-detach accepts a safe path\n'
printf '0\t{"tool_input":{"command":"git worktree add --no-lock /src/wt"}}\tgenerated worktree no-lock accepts a safe path\n'
printf '0\t{"tool_input":{"command":"git worktree add --no-guess-remote /src/wt"}}\ta long worktree negation accepts a safe path without enumeration\n'
printf '0\t{"tool_input":{"command":"git worktree add -d /src/wt"}}\tthe documented short detach flag accepts a safe path\n'
printf '0\t{"tool_input":{"command":"git worktree add -q /src/wt"}}\tthe documented short quiet flag accepts a safe path\n'
printf '0\t{"tool_input":{"command":"git worktree add --lock --rea $HOME/note /src/wt"}}\tan accepted reason abbreviation consumes metadata rather than the path\n'
printf '0\t{"tool_input":{"command":"git worktree add -fb $HOME/topic /src/wt"}}\ta short branch bundle consumes its HOME-valued branch before the safe path\n'
printf '2\t{"tool_input":{"command":"git worktree add -fb topic $HOME/wt"}}\ta short branch bundle does not hide the later HOME path\n'
# Upstream Git defines --orphan as a boolean flag; -b still carries the branch.
printf '0\t{"tool_input":{"command":"git worktree add --orphan /src/wt"}}\torphan mode accepts a safe path without consuming it as a value\n'
printf '2\t{"tool_input":{"command":"git worktree add --orphan $HOME/wt"}}\torphan mode does not hide its HOME path\n'
printf '0\t{"tool_input":{"command":"git worktree add --orphan -b $HOME/topic /src/wt"}}\torphan mode leaves HOME branch metadata to the branch option\n'
printf '2\t{"tool_input":{"command":"git worktree add --orphan -b topic $HOME/wt"}}\torphan mode plus a branch option preserves HOME path blocking\n'
# The optional second positional is commit-ish metadata, never placement.
# HOME expands here, but the explicit worktree path remains safely under /src.
printf '0\t{"tool_input":{"command":"git worktree add /src/wt $HOME/topic"}}\ta HOME-shaped commit-ish is not the worktree path\n'
printf '2\t{"tool_input":{"command":"git worktree add --no-force $HOME/wt"}}\ta generated worktree negation does not hide the HOME path\n'
printf '2\t{"tool_input":{"command":"git worktree add --no-guess-remote $HOME/wt"}}\ta long worktree negation preserves HOME placement blocking\n'
# Explicit placement options and later simple commands remain traps.
printf '2\t{"tool_input":{"command":"git clone --bare $HOME/source /src/wt && git clone x $HOME/wt"}}\ta boolean flag in one command does not hide a later HOME destination\n'
printf '2\t{"tool_input":{"command":"git worktree add --no-force /src/wt; git clone x $HOME/wt"}}\ta worktree flag before a boundary does not hide later HOME placement\n'
# Routing this arm through the shared name site also repaired an over-block it
# had carried from the start: the old whole-command regex found `git` INSIDE a
# longer word, so these two were refused at every head before this commit.
# Same class as mycurl and curl-wrapper, and refusing them is how a guard gets
# routed around instead of repaired.
printf '0\t{"tool_input":{"command":"mygit clone https://example.invalid/x $HOME/wt"}}\tmygit is a different program and its checkout is not ours\n'
printf '0\t{"tool_input":{"command":"gitfoo clone https://example.invalid/x $HOME/wt"}}\tthe name has to end where git ends\n'
printf '0\t{"tool_input":{"command":"curl -s -X GET https://git.example.invalid/api/v1/repos/a/b/pulls/1"}}\treads are never blocked\n'
printf '2\t{"tool_input":{"command":"curl -X POST -d @b https://git.example.invalid/api/v1/repos/a/b/pulls/1/reviews"}}\treview write has a wrapper\n'
printf '2\t{"tool_input":{"command":"curl -X POST -d @b https://git.example.invalid/api/v1/repos/a/b/pulls/1/merge"}}\tmerge write has a wrapper\n'
printf '2\t{"tool_input":{"command":"curl -X POST -d @b https://api.github.com/repos/a/b/issues"}}\tGitHub host is covered too\n'
printf '0\t{"tool_input":{"command":"curl -X POST -d @b https://git.example.invalid/api/v1/repos/a/b/releases"}}\tan endpoint with no wrapper passes\n'
printf '2\t{"tool_input":{"command":"curl -X POST -d {\\"event\\":\\"APPROVE\\"} https://example.invalid/x"}}\tthe APPROVE token is caught anywhere\n'
printf '0\t{"tool_input":{"command":"ls -la /src"}}\tordinary commands are untouched\n'
printf '0\t{"tool_input":{"command":"MOSAIC_WRAPPER_OVERRIDE=1 curl -X POST -d @b https://git.example.invalid/api/v1/repos/a/b/pulls"}}\tbreak-glass works\n'
printf '0\t{"tool_input":{}}\tan empty payload does not block the session\n'
# --- bypasses an independent reviewer demonstrated against the first version.
# Each of these returned 0 (allowed) and each is a real write. They are pinned
# as fixtures rather than fixed-and-forgotten because the class is recurring:
# the guard reads text, so every spelling it does not know is a hole.
printf '2\t{"tool_input":{"command":"curl -d@b https://git.example.invalid/api/v1/repos/a/b/pulls/1/reviews"}}\t-d@body with no space is still a body\n'
printf '2\t{"tool_input":{"command":"curl --request=POST -d@b https://git.example.invalid/api/v1/repos/a/b/pulls/1/reviews"}}\t--request=POST equals-form is still a method\n'
printf '2\t{"tool_input":{"command":"p=/api/v1/repo; q=s/a/b/pulls/1/reviews; curl -d@b https://git.example.invalid${p}${q}"}}\ta path split across variables is still that path\n'
printf '2\t{"tool_input":{"command":"curl --data-binary @b https://git.example.invalid/api/v1/repos/a/b/issues/1/comments"}}\t--data-binary is a body\n'
printf '2\t{"tool_input":{"command":"curl -F f=@b https://git.example.invalid/api/v1/repos/a/b/issues"}}\t-F multipart is a body\n'
# Reads must survive every one of those broadenings, or the guard gets disabled.
printf '0\t{"tool_input":{"command":"curl -s https://git.example.invalid/api/v1/repos/a/b/pulls/1/reviews"}}\tno body and no verb is a read\n'
printf '0\t{"tool_input":{"command":"grep -rn /pulls/ src/ | head -20"}}\ta path fragment in a grep is not an API call\n'
printf '0\t{"tool_input":{"command":"curl -X POST -d @b https://registry.example.invalid/v2/x/manifests/latest"}}\tan unwrapped API is not this guard'"'"'s business\n'
# --- round two of the same review. Splitting the ENDPOINT TOKEN defeats any
# amount of fragment matching, because the endpoint does not exist until the
# shell expands it. The guard now refuses to clear a write whose URL it cannot
# read, rather than pretending it read one.
printf '2\t{"tool_input":{"command":"a=/api/v1/repos/a/b/iss; b=ues/1/comments; curl -d@body https://git.example.invalid${a}${b}"}}\tan endpoint token split across variables is unreadable, not absent\n'
printf '2\t{"tool_input":{"command":"a=/api/v1/repos/a/b/pu; b=lls/1/reviews; curl -d@body https://git.example.invalid${a}${b}"}}\tsame split, review endpoint\n'
printf '0\t{"tool_input":{"command":"curl -X POST -d @payload https://hooks.example.invalid/services/${WEBHOOK_ID}"}}\tan opaque URL that is not forge-shaped stays allowed\n'
# --- round six changed the contract in this direction, and these fixtures are
# where it shows. They used to assert that discussing a call is not making one.
# Five rounds proved there is no textual way to tell a quoted example from a
# quoted command, so the guard stopped trying: it judges the payload, and a
# payload inside quotes is still a payload. Quoting one of these on a Bash
# command line is now refused, and the way to write the example is a
# file-writing tool. This is the deliberate cost of the mechanism change.
printf '2\t{"tool_input":{"command":"grep -R \\"curl -d https://git.example.invalid/api/v1/repos/a/b/issues\\" docs/"}}\tquoting a wrapped write is refused even in a grep\n'
printf '2\t{"tool_input":{"command":"echo \\"curl -d https://git.example.invalid/api/v1/repos/a/b/pulls\\" > note.txt"}}\t...and when written into a file\n'
printf '2\t{"tool_input":{"command":"python3 -c '"'"'print(\\"curl -d https://git.example.invalid/api/v1/repos/a/b/issues\\")'"'"'"}}\t...and when printed from another language\n'
# The boundary that keeps this from being "block everything": what is refused
# is a WRITE to a WRAPPED endpoint. Mentioning either alone still passes, and
# these are asserted as hard as the blocks above.
printf '0\t{"tool_input":{"command":"grep -R \\"curl -s https://git.example.invalid/api/v1/repos/a/b/issues/1/comments\\" docs/"}}\tquoting a READ example is untouched\n'
printf '0\t{"tool_input":{"command":"echo \\"the wrapped endpoint is https://git.example.invalid/api/v1/repos/a/b/issues/1/comments\\" >> notes.md"}}\tnaming the endpoint without a body flag is untouched\n'
printf '0\t{"tool_input":{"command":"grep -R \\"curl -d@b https://git.example.invalid/api/v1/repos/a/b/releases\\" docs/"}}\tquoting a write to an UNWRAPPED endpoint is untouched\n'
printf '0\t{"tool_input":{"command":"issue-comment.sh --repo a/b --issue 1 --body @msg.md"}}\tthe wrapper itself carries a body flag and must never trip its own guard\n'
# Command position must still catch the real thing behind operators and env.
printf '2\t{"tool_input":{"command":"cd /tmp && GITEA_TOKEN=$T curl -d@b https://git.example.invalid/api/v1/repos/a/b/pulls/1/merge"}}\ta real call behind && and an assignment is still a call\n'
# --- the case the AUTHOR hit twice while chasing the above: sending a message
# that QUOTED one of these fixtures. Under the old contract that was a defect
# to be parsed away; under this one it is the documented cost, and the message
# gets composed with a file-writing tool instead.
printf '2\t{"tool_input":{"command":"send.sh -m \\"repro was: cd /tmp && curl -d@b https://git.example.invalid/api/v1/repos/a/b/pulls/1/merge\\""}}\tquoting the repro in a message is refused too\n'
printf '2\t{"tool_input":{"command":"cat >> notes.md <<EOF\\nwe ran: curl -d@b https://git.example.invalid/api/v1/repos/a/b/issues\\nEOF"}}\ta heredoc body carrying the payload is refused with it\n'
# ...but quotes stop being data the moment something executes them.
printf '2\t{"tool_input":{"command":"bash -c \\"curl -d@b https://git.example.invalid/api/v1/repos/a/b/pulls/1/merge\\""}}\tbash -c makes the quoted text code again\n'
# --- round three. Each of these four is a real write that a bare-name match
# for the client could not see, because an ordinary word sat in front of it.
# They are kept as fixtures after the mechanism change even though the guard no
# longer looks for a client at all: they are the evidence for WHY it stopped,
# and a future re-narrowing that reintroduced position would fail here first.
printf '2\t{"tool_input":{"command":"env GITEA_TOKEN=$T curl -d@b https://git.example.invalid/api/v1/repos/a/b/issues/1/comments"}}\tenv VAR=... in front of the client is still the client\n'
printf '2\t{"tool_input":{"command":"command curl -d@b https://git.example.invalid/api/v1/repos/a/b/issues/1/comments"}}\tcommand in front of the client is still the client\n'
printf '2\t{"tool_input":{"command":"timeout 10 curl -d@b https://git.example.invalid/api/v1/repos/a/b/issues/1/comments"}}\ttimeout N in front of the client is still the client\n'
printf '2\t{"tool_input":{"command":"/usr/bin/curl -d@b https://git.example.invalid/api/v1/repos/a/b/issues/1/comments"}}\tan absolute path to the client is still the client\n'
printf '2\t{"tool_input":{"command":"echo timeout 10 curl -d@b https://git.example.invalid/api/v1/repos/a/b/issues/1/comments >> notes.md"}}\tnaming the call after echo carries the payload, so it is refused\n'
# A shell standing between quoted data and execution makes that data code,
# and the pipe is the form agents actually use. Filing it as data allowed the
# call to vanish from the skeleton while still running.
printf '2\t{"tool_input":{"command":"printf '"'"'%%s\\\\n'"'"' '"'"'curl -d@b https://git.example.invalid/api/v1/repos/a/b/issues/1/comments'"'"' | sh"}}\tquoted code piped to a shell is code\n'
printf '2\t{"tool_input":{"command":"cat <<EOF | sh\\ncurl -d@b https://git.example.invalid/api/v1/repos/a/b/issues/1/comments\\nEOF"}}\ta heredoc piped to a shell is code\n'
printf '2\t{"tool_input":{"command":"sh -s <<EOF\\ncurl -d@b https://git.example.invalid/api/v1/repos/a/b/issues/1/comments\\nEOF"}}\tsh -s reads its script from the heredoc\n'
# ...and the questions that used to follow — is the pipe target a shell, does a
# shell on one line execute a string on another — no longer have to be answered
# at all. Both of these carry the payload, both are refused, and neither
# outcome depends on parsing what the pipe or the other line does.
printf '2\t{"tool_input":{"command":"grep -R \\"curl -d@b https://git.example.invalid/api/v1/repos/a/b/issues/1/comments\\" docs/ | wc -l"}}\tpiping the payload to wc is refused without asking what wc is\n'
printf '2\t{"tool_input":{"command":"docker run --rm alpine sh -c '"'"'echo hi'"'"'\\necho \\"example: curl -d@b https://git.example.invalid/api/v1/repos/a/b/issues/1/comments\\" >> notes.md"}}\tan unrelated shell on another line no longer changes the answer either way\n'
# --- round four. The guard was still reading the command as typed rather than
# as the shell will run it: a backslash before a newline is removed before
# anything else happens, so the endpoint token can be split across the join.
printf '2\t{"tool_input":{"command":"curl -d@b https://git.example.invalid/api/v1/repos/a/b/iss\\\\\\nues/1/comments"}}\ta line continuation inside the endpoint token is still that endpoint\n'
printf '2\t{"tool_input":{"command":"curl -d@b https://git.example.invalid/api/v1/repos/a/b/pu\\\\\\nlls/1/reviews"}}\tsame join, review endpoint\n'
printf '2\t{"tool_input":{"command":"cat >> notes.md <<EOF\\nwe ran: curl -d@b https://git.example.invalid/api/v1/repos/a/b/iss\\\\\\nues/1/comments\\nEOF"}}\tthe join still runs first, and the joined payload is refused in a document too\n'
# Transparent prefixes take option VALUES, and the value was a word the list
# did not know — so the client went missing again behind an ordinary `sudo -u`.
printf '2\t{"tool_input":{"command":"sudo -u root curl -d@b https://git.example.invalid/api/v1/repos/a/b/issues/1/comments"}}\tan option value after a prefix does not hide the client\n'
printf '2\t{"tool_input":{"command":"timeout --signal TERM 10 curl -d@b https://git.example.invalid/api/v1/repos/a/b/issues/1/comments"}}\tan option pair plus a duration does not hide the client\n'
printf '2\t{"tool_input":{"command":"xargs echo curl -d@b https://git.example.invalid/api/v1/repos/a/b/issues/1/comments"}}\tthe payload behind xargs echo is refused rather than adjudicated\n'
printf '0\t{"tool_input":{"command":"sudo apt-get install curl"}}\tinstalling the client is not calling it\n'
# Execution through another command needed its own case under the old design.
printf '2\t{"tool_input":{"command":"find . -maxdepth 0 -exec curl -d@b https://git.example.invalid/api/v1/repos/a/b/issues/1/comments ;"}}\tfind -exec runs the client\n'
# --- round five, and the finding that ended the parser. Command substitution
# inside a double-quoted span EXECUTES, while the skeleton was discarding that
# span as inert prose. The unquoted and process-substitution forms already
# blocked, which is what made it a classification defect rather than a spelling
# one: the same call was refused or allowed depending on a quote character.
printf '2\t{"tool_input":{"command":"echo \\"$(curl -d@b https://git.example.invalid/api/v1/repos/a/b/issues/1/comments)\\""}}\tcommand substitution inside double quotes executes\n'
printf '2\t{"tool_input":{"command":"echo \\"`curl -d@b https://git.example.invalid/api/v1/repos/a/b/issues/1/comments`\\""}}\tso does the backtick form\n'
printf '2\t{"tool_input":{"command":"msg=\\"$(curl -d@b https://git.example.invalid/api/v1/repos/a/b/issues/1/comments)\\""}}\tand an assignment RHS is not data either\n'
printf '2\t{"tool_input":{"command":"echo $(curl -d@b https://git.example.invalid/api/v1/repos/a/b/issues/1/comments)"}}\tthe unquoted form, which blocked before and must keep blocking\n'
printf '2\t{"tool_input":{"command":"cat <(curl -d@b https://git.example.invalid/api/v1/repos/a/b/issues/1/comments)"}}\tprocess substitution, same\n'
printf '2\t{"tool_input":{"command":"bash --command \\"curl -d@b https://git.example.invalid/api/v1/repos/a/b/issues/1/comments\\""}}\tthe long-option spelling of bash -c needs no entry in any list now\n'
# A client the guard was never taught is the point of dropping client
# detection: neither of these names curl at all.
printf '2\t{"tool_input":{"command":"python3 -c '"'"'import requests; requests.post(\\"https://git.example.invalid/api/v1/repos/a/b/issues/1/comments\\", json={})'"'"'"}}\ta library call is a write with no flag and no curl\n'
printf '2\t{"tool_input":{"command":"wget --post-data=x https://git.example.invalid/api/v1/repos/a/b/issues/1/comments"}}\twget spells its body differently and is still a write\n'
# Round six scoped the guard on `https?://`, and review found the absence shape
# had simply moved to that new boundary: a raw provider CLI carries no scheme,
# so the guard never reached the write question. These are the reported repros.
printf '2\t{"tool_input":{"command":"gh api -X POST repos/a/b/issues -f title=x -f body=y"}}\tgh api is a raw write with no URL scheme at all\n'
printf '2\t{"tool_input":{"command":"gh api -X POST repos/a/b/pulls/1/reviews -f event=APPROVE"}}\tand it reaches the endpoint the review wrapper owns\n'
printf '2\t{"tool_input":{"command":"tea api -X POST repos/a/b/issues/1/comments -f body=x"}}\ttea api, same shape, different CLI\n'
printf '2\t{"tool_input":{"command":"curl -X POST -d x git.example.invalid/api/v1/repos/a/b/issues"}}\ta scheme-less host path is still an API write\n'
printf '2\t{"tool_input":{"command":"gh api repos/a/b/issues -f title=x"}}\tgh POSTs implicitly when handed a field, exactly as curl does with -d\n'
# ...and the boundary that stops a broader scope gate becoming block-everything.
printf '0\t{"tool_input":{"command":"gh api repos/a/b/pulls/1"}}\treading through a provider CLI stays untouched\n'
printf '0\t{"tool_input":{"command":"gh api -X POST repos/a/b/releases -f tag_name=v1"}}\tno wrapper owns releases, whoever calls it\n'
printf '0\t{"tool_input":{"command":"tea pulls create --title x --repo a/b"}}\tprovider PORCELAIN is out of scope by decision, not by accident\n'
printf '0\t{"tool_input":{"command":"rm -f /var/tmp/api/v1-issues-notes.txt"}}\t-f is only a body when it carries key=value\n'
printf '0\t{"tool_input":{"command":"grep -f patterns.txt /src/api/v1/repos/a/b/issues.log"}}\tsame, on the flag agents actually collide with\n'
# Wrong remediation is its own defect: /issues/1/labels used to block with
# "use issue-create.sh", which is not the wrapper for that call. Round seven
# answered that by letting EVERY path under a numbered issue or PR through,
# and review showed the reasoning ("no wrapper owns these") was false in this
# tree. These are the reported repros, all rc 0 before round eight, and each
# asserts the wrapper the advice must name — not merely that a block happened.
printf '2\t{"tool_input":{"command":"gh api -X PATCH repos/a/b/issues/1 -f title=x"}}\tan issue edit is issue-edit.sh, not a wrapper gap\tissue-edit.sh\n'
printf '2\t{"tool_input":{"command":"curl -X PATCH -d @b https://git.example.invalid/api/v1/repos/a/b/issues/1"}}\tsame call through curl, same wrapper\tissue-edit.sh\n'
printf '2\t{"tool_input":{"command":"gh api -X PATCH repos/a/b/issues/1/labels -f labels[]=bug"}}\tlabels are wrapped, and the advice says by which\tissue-edit.sh\n'
printf '2\t{"tool_input":{"command":"gh api -X POST repos/a/b/issues/1/assignees -f assignees[]=u"}}\tassignees are issue-assign.sh\tissue-assign.sh\n'
printf '2\t{"tool_input":{"command":"gh api repos/a/b/issues/1/assignees -f assignees[]=u"}}\tthe array field spelling is a body with no -X at all\tissue-assign.sh\n'
printf '2\t{"tool_input":{"command":"curl -X PATCH -d @b https://git.example.invalid/api/v1/repos/a/b/pulls/1/labels"}}\ta PR is an issue where labels live, so the issue wrapper owns them\tissue-edit.sh\n'
printf '2\t{"tool_input":{"command":"curl -X PATCH -d @b https://git.example.invalid/api/v1/repos/a/b/pulls/1"}}\tPR state is pr-close.sh, and the gap in that arm is stated\tpr-close.sh\n'
printf '2\t{"tool_input":{"command":"curl -X PATCH -d @b https://git.example.invalid/api/v1/repos/a/b/milestones/4"}}\ta milestone state change is milestone-close.sh, not the create wrapper\tmilestone-close.sh\n'
# SPAN. A wrapper that owns a slice of an endpoint must not be advertised as
# owning the endpoint. milestone-close.sh takes only -t <title> and sends
# state=closed, so a title/description/due-date edit is a gap and the message
# has to say so — round eight named the wrapper and stopped there.
printf '2\t{"tool_input":{"command":"curl -X PATCH -d @b https://git.example.invalid/api/v1/repos/a/b/milestones/1"}}\ta milestone edit blocks, but the advice states the close-only span\towns the CLOSE only\n'
printf '2\t{"tool_input":{"command":"gh api -X PATCH repos/a/b/issues/1 -f assignee=u"}}\tissue-edit.sh cannot set an assignee, so the message names the one that can\tissue-assign.sh owns the assignee\n'
# The residue: still genuinely owned by nothing, and still flowing through.
# Requesting a reviewer is not submitting one; pr-review.sh files verdicts and
# nothing in the tree adds a requested reviewer.
printf '0\t{"tool_input":{"command":"gh api -X POST repos/a/b/pulls/1/requested_reviewers -f reviewers[]=u"}}\tno wrapper requests a reviewer, so it is not refused with pr-review.sh\n'
# SPAN, applied to the guard's OWN fail-closed rule rather than to a wrapper.
# The scope gate admits three shapes; the unreadable-endpoint rule asked only
# for `https?://`, so a split endpoint in the other two was in scope to block,
# produced no readable endpoint, and fell through to allow. Same defect class
# as the milestone arm, one layer up. Each shape gets its own fixture, because
# a single one would have passed on the arm that already worked.
printf '2\t{"tool_input":{"command":"p=repos/a/b/iss; q=ues; gh api -X POST ${p}${q} -f title=x"}}\ta split endpoint in a provider-CLI api call is unreadable, not absent\n'
printf '2\t{"tool_input":{"command":"p=repos/a/b/issues/1/comm; q=ents; gh api -X POST ${p}${q} -f body=x"}}\tsame, comments\n'
printf '2\t{"tool_input":{"command":"p=repos/a/b/pulls/1/rev; q=iews; gh api -X POST ${p}${q} -f event=APPROVED"}}\tsame, and a verdict is the costliest one to lose\n'
printf '2\t{"tool_input":{"command":"p=repos/a/b/iss; q=ues; tea api -X POST ${p}${q} -f title=x"}}\tevery CLI the scope gate admits, not just gh\n'
printf '2\t{"tool_input":{"command":"p=/api/v1/repos/a/b/iss; q=ues; curl -X POST -d x git.example.invalid${p}${q}"}}\ta schemeless forge host with a split path is unreadable too\n'
printf '2\t{"tool_input":{"command":"h=git.example.invalid; q=ues; curl -X POST -d x ${h}/api/v1/repos/a/b/iss${q}"}}\tthe expansion may come first; the token is what matters\n'
# And the reason this is not "any variable blocks a write": a payload in a
# variable is the SAFE way to pass one and leaves the endpoint fully legible.
printf '0\t{"tool_input":{"command":"gh api repos/a/b/git/refs -f sha=$SHA"}}\tan expansion in a body value leaves the endpoint readable\n'
printf '0\t{"tool_input":{"command":"curl -X POST -d \\"$BODY\\" https://git.example.invalid/api/v1/repos/a/b/git/refs"}}\tsame for a quoted body on an unwrapped endpoint\n'
printf '0\t{"tool_input":{"command":"gh api repos/${OWNER}/${REPO}/git/refs"}}\ta read with a split endpoint is still a read\n'
printf '0\t{"tool_input":{"command":"curl -X PATCH -d @b https://git.example.invalid/api/v1/repos/a/b/issues/comments/5"}}\tediting a comment has no wrapper; only creating one does\n'
printf '0\t{"tool_input":{"command":"curl -X POST -d @b https://git.example.invalid/api/v1/repos/a/b/issues/1/stopwatch/start"}}\tno wrapper owns a stopwatch, and none is invented for it\n'
printf '0\t{"tool_input":{"command":"gh api -X POST repos/a/b/issues/1/times -f time=60"}}\tnor time tracking\n'
printf '0\t{"tool_input":{"command":"gh api -X POST repos/a/b/issues/1/reactions -f content=+1"}}\tnor reactions\n'
# ...and the residue must be decided by the SEGMENT, never by a stray slash.
printf '2\t{"tool_input":{"command":"gh api -X PATCH repos/a/b/issues/1 -f body=see-/docs/x"}}\ta slash inside the body is not a subresource\tissue-edit.sh\n'
# The arms above the numbered ones must keep blocking, with their own wrappers.
printf '2\t{"tool_input":{"command":"curl -X POST -d @b https://git.example.invalid/api/v1/repos/a/b/issues/1/comments"}}\tthe wrapped subresource must not fall through\tissue-comment.sh\n'
printf '2\t{"tool_input":{"command":"curl -X POST -d @b https://git.example.invalid/api/v1/repos/a/b/issues"}}\tnor may issue creation\tissue-create.sh\n'
printf '2\t{"tool_input":{"command":"curl -X POST -d @b https://git.example.invalid/api/v1/repos/a/b/pulls"}}\tPR creation is wrapped and must not fall through with them\tpr-create.sh\n'
printf '2\t{"tool_input":{"command":"curl -X POST -d @b https://git.example.invalid/api/v1/repos/a/b/pulls/1/reviews"}}\tand a review still names the review wrapper\tpr-review.sh\n'
# SPAN a third time, now in the scope gate itself: it asked for `/api/v[0-9]`,
# which is Gitea's spelling. GitHub's API carries no version segment at all
# (`api.github.com/repos/...`), so the schemeless Gitea write was in scope and
# the schemeless GitHub one was not — a gate calibrated to one dialect rather
# than to what identifies a provider API. `/repos/` is the marker both share.
# These endpoints are READABLE, so each asserts the wrapper it must name; a
# rc-only fixture here would pass on the unreadable arm and prove nothing.
printf '2\t{"tool_input":{"command":"curl -X POST -d x api.github.com/repos/a/b/issues"}}\ta schemeless GitHub host is a provider API even with no version segment\tissue-create.sh\n'
printf '2\t{"tool_input":{"command":"curl -X POST -d x api.github.com/repos/a/b/issues/1/comments"}}\tsame, and the subresource still names its own wrapper\tissue-comment.sh\n'
printf '2\t{"tool_input":{"command":"host=api.github.com; curl -X POST -d x ${host}/repos/a/b/issues"}}\tthe host may be a variable; the path is what the guard reads\tissue-create.sh\n'
printf '2\t{"tool_input":{"command":"curl -X POST -d x api.github.com/repos/a/b/pulls/1/reviews"}}\ta verdict is the costliest call to lose to a spelling\tpr-review.sh\n'
printf '2\t{"tool_input":{"command":"p=/repos/a/b/iss; q=ues; curl -X POST -d x api.github.com${p}${q}"}}\tand the split form of it is unreadable, not absent\n'
# The end-of-options marker, which is the one option not spelled like one.
printf '2\t{"tool_input":{"command":"p=repos/a/b/iss; q=ues; gh api -X POST -- ${p}${q} -f title=x"}}\ta bare -- must not walk the endpoint past the scanner\n'
# Widening a scope gate may not create a block. Reads and unwrapped endpoints
# in the newly admitted shape have to stay allowed, or this is a regression
# wearing a fix'"'"'s clothes.
printf '0\t{"tool_input":{"command":"curl api.github.com/repos/a/b/issues"}}\tadmitting a shape to the gate does not make a read a write\n'
printf '0\t{"tool_input":{"command":"curl -X POST -d x api.github.com/repos/a/b/git/refs"}}\tno wrapper owns git refs, on GitHub'"'"'s spelling either\n'
printf '0\t{"tool_input":{"command":"gh api -- repos/a/b/issues"}}\tthe marker in a read is still a read\n'
# The APPROVE trap, in the spelling a provider CLI uses, and the value that
# must never trip it.
printf '0\t{"tool_input":{"command":"curl -X POST -d {\\"event\\":\\"APPROVED\\"} https://git.example.invalid/api/v1/repos/a/b/releases"}}\tAPPROVED is the correct value and is never the trap\n'
# Documented over-block, pinned so it is a known boundary and not a surprise.
printf '2\t{"tool_input":{"command":"python3 -c '"'"'print(\\"https://git.example.invalid/api/v1/repos/a/b/issues/1/comments .post(\\")'"'"'"}}\tprose carrying .post( near a wrapped URL is refused, by the same payload rule\n'
# --- round nine, all four from one adversarial pass, and three of them are
# the same shape: a test written over the WHOLE command text deciding an
# ALLOW. That is the fail-open form this file keeps rediscovering, and it had
# reached the break-glass itself.
#
# BREAK-GLASS. `case "$CMD" in *MOSAIC_WRAPPER_OVERRIDE=1*)` cleared the entire
# command if that string appeared anywhere in it — so quoting the override in a
# note, or naming a variable after it, disabled the guard for the call sitting
# beside it. The override is now read POSITIONALLY: leading `NAME=value`
# assignments only, exactly where the shell would honour one.
printf '2\t{"tool_input":{"command":"echo \\"MOSAIC_WRAPPER_OVERRIDE=1 curl -d@b https://git.example.invalid/api/v1/repos/a/b/pulls/1/reviews\\" >> notes.md"}}\tquoting the override in a document does not arm it\n'
printf '2\t{"tool_input":{"command":"NOTES=MOSAIC_WRAPPER_OVERRIDE=1 curl -d@b https://git.example.invalid/api/v1/repos/a/b/pulls/1/reviews"}}\tan assignment whose VALUE is the override is not the override\n'
printf '2\t{"tool_input":{"command":"MOSAIC_WRAPPER_OVERRIDE=10 curl -d@b https://git.example.invalid/api/v1/repos/a/b/pulls/1/reviews"}}\t=10 matched the old substring test and is not the value 1\n'
printf '0\t{"tool_input":{"command":"GITEA_TOKEN=$T MOSAIC_WRAPPER_OVERRIDE=1 curl -d@b https://git.example.invalid/api/v1/repos/a/b/pulls/1/reviews"}}\tthe override still works behind other assignments, as the shell reads it\n'
# The cost, pinned rather than discovered later: positional means positional.
printf '2\t{"tool_input":{"command":"cd /tmp && MOSAIC_WRAPPER_OVERRIDE=1 curl -d@b https://git.example.invalid/api/v1/repos/a/b/pulls/1/merge"}}\tan override after && is not in command position and does not arm\n'
# SUBRESOURCE REFINEMENT, same defect one arm lower. It asked whether a
# subresource appears ANYWHERE in the command, so a numbered-object write was
# cleared on the strength of text in its own BODY. Inverted: clear only when
# EVERY numbered-object occurrence carries a subresource.
printf '2\t{"tool_input":{"command":"gh api -X PATCH repos/a/b/issues/1 -f body=cf-/pulls/2/files"}}\ta subresource in the body does not clear a write to the numbered issue\tissue-edit.sh\n'
printf '2\t{"tool_input":{"command":"gh api -X PATCH repos/a/b/issues/1 -f body=cf-/issues/3/reactions"}}\tsame, quoting a subresource of the same object type\tissue-edit.sh\n'
# ...and its documented cost, in the safe direction.
printf '2\t{"tool_input":{"command":"gh api -X POST repos/a/b/issues/1/reactions -f content=cf-/issues/2"}}\tan unwrapped subresource write that quotes a bare issue is refused\n'
# -K/--config. curl reads the method, the body, the headers AND the URL from
# that file, so none of them are in the command: every write test above read 0
# and the call went through. An unreadable request is not a cleared one.
printf '2\t{"tool_input":{"command":"curl --config /tmp/req https://git.example.invalid/api/v1/repos/a/b/pulls/1/reviews"}}\tthe request in a config file is unreadable, so it is refused\t--config/-K\n'
printf '2\t{"tool_input":{"command":"curl -K /tmp/req https://git.example.invalid/api/v1/repos/a/b/issues"}}\tthe short spelling, same answer\t--config/-K\n'
# Cost, stated: this refuses a --config read against a host that has nothing
# to do with a forge. The alternative is to require a forge marker in a
# command whose URL may itself be in the file, which is the hole again.
printf '2\t{"tool_input":{"command":"curl --config /tmp/req https://example.invalid/anything"}}\tan unrelated https URL with --config is refused too, by decision\t--config/-K\n'
printf '0\t{"tool_input":{"command":"eslint --config .eslintrc.json src/"}}\t--config on a command that is not curl is nobody'"'"'s business\n'
# ROUND TEN. The --config check above was first written INSIDE the API-shape
# gate, so it was guarded by a condition that the capability it guards against
# removes. A config file can carry the URL; delete the URL from the command and
# nothing is API-shaped, the branch is never entered, and the guard reports
# clean on precisely the call it exists to refuse. It is now asked of any curl.
printf '2\t{"tool_input":{"command":"curl --config /tmp/provider-write.cfg"}}\ta config file can own the URL, so there is nothing API-shaped left to gate on\t--config/-K\n'
printf '2\t{"tool_input":{"command":"curl -K/tmp/provider-write.cfg"}}\tcurl accepts the value attached to the short flag\t--config/-K\n'
printf '2\t{"tool_input":{"command":"curl -sK /tmp/provider-write.cfg"}}\tand inside a bundle, which a space-separated test does not see\t--config/-K\n'
printf '0\t{"tool_input":{"command":"tar -K /tmp/archive.tar"}}\t-K on a command that is not curl is not this hook'"'"'s business\n'
# curl by any ordinary path spelling. The first version of the config check
# matched the bare word only, so these three executed the same wrapped write
# while the guard reported clean. Recognizing only the unqualified name is
# caller-name parsing, and that is the class this file exists to refuse.
printf '2\t{"tool_input":{"command":"/usr/bin/curl --config /tmp/provider-write.cfg"}}\tan absolute path is the same invocation, not a different one\t--config/-K\n'
printf '2\t{"tool_input":{"command":"env /usr/bin/curl -K/tmp/provider-write.cfg"}}\tand it is still curl behind env, with the value attached\t--config/-K\n'
printf '2\t{"tool_input":{"command":"./curl --config /tmp/provider-write.cfg"}}\ta relative path costs two characters and used to be enough\t--config/-K\n'
# The prefix must end at a slash: a basename that merely ENDS in curl is a
# different program, and blocking it would be the over-block that gets a guard
# routed around rather than fixed.
printf '0\t{"tool_input":{"command":"mycurl --config /tmp/provider-write.cfg"}}\tmycurl is not curl, and over-blocking is its own failure\n'
printf '0\t{"tool_input":{"command":"/opt/x/curl-wrapper --config /tmp/provider-write.cfg"}}\tnor is curl-wrapper, whose name only starts the same way\n'
# And the same name once it is punctuated. The basename repair above fixed the
# UNQUOTED path spelling and nothing else, so two quote characters restored the
# bypass it had just closed: the check was still modelling one presentation of
# a shell word instead of the word. Every one of these executes the real curl.
printf '2\t{"tool_input":{"command":"\\"/usr/bin/curl\\" --config /tmp/provider-write.cfg"}}\tquoting a path does not make it a different program\t--config/-K\n'
printf '2\t{"tool_input":{"command":"'"'"'./curl'"'"' --config /tmp/provider-write.cfg"}}\tnor does quoting a relative one\t--config/-K\n'
printf '2\t{"tool_input":{"command":"$(which curl) --config /tmp/provider-write.cfg"}}\tthe name is in the text even when a substitution supplies the path\t--config/-K\n'
printf '2\t{"tool_input":{"command":"`which curl` --config /tmp/provider-write.cfg"}}\tand in the older spelling of the same substitution\t--config/-K\n'
# The provider-CLI SCOPE gate had the identical defect, untouched while the
# curl arm was repaired twice. It decides whether write detection runs at all,
# so failing to admit these is indistinguishable from allowing them — and no
# URL marker rescues them, because provider CLI paths carry no leading slash.
printf '2\t{"tool_input":{"command":"/usr/bin/gh api -X POST repos/a/b/issues -f title=x"}}\tan absolute path to a provider CLI is still a provider CLI\n'
printf '2\t{"tool_input":{"command":"./gh api -X POST repos/a/b/issues -f title=x"}}\tand a relative one still is too\n'
printf '2\t{"tool_input":{"command":"/usr/local/bin/tea api -X POST repos/a/b/issues -f title=x"}}\tthe same is true of every CLI the gate names, not just the first\n'
printf '0\t{"tool_input":{"command":"mygh api -X POST repos/a/b/issues -f title=x"}}\tmygh is not gh, and the scope gate must not over-admit either\n'
printf '0\t{"tool_input":{"command":"/usr/bin/gh api repos/a/b/issues"}}\ta read through an absolute path is still a read\n'
# Quotes and backslashes INSIDE the word. The previous repair replaced quote
# characters with whitespace, which is token separation and not quote removal:
# a shell removes a quote without splitting the word around it, so `cu"rl"` is
# one word naming curl while whitespace made it two words naming neither.
# `"/usr/bin/curl"` passed under that version only because the inserted space
# happened to land after a slash, which established nothing.
printf '2\t{"tool_input":{"command":"cu\\"rl\\" --config /tmp/provider-write.cfg"}}\ta quote inside the word does not make it another program\t--config/-K\n'
printf '2\t{"tool_input":{"command":"cu'"'"'rl'"'"' --config /tmp/provider-write.cfg"}}\tand a single quote inside it is the same word again\t--config/-K\n'
printf '2\t{"tool_input":{"command":"/usr/bin/cu\\\\rl --config /tmp/provider-write.cfg"}}\tescaping is ordinary word formation, not a disguise\t--config/-K\n'
# A backslash is NOT uniformly removed. It is literal inside single quotes,
# and inside double quotes when it precedes anything other than $, `, ",
# backslash, or newline. These spell a different program and must stay allowed.
printf '0\t{"tool_input":{"command":"'"'"'cu\\\\rl'"'"' --config /tmp/provider-write.cfg"}}\ta backslash inside single quotes remains literal\n'
printf '0\t{"tool_input":{"command":"\\"cu\\\\rl\\" --config /tmp/provider-write.cfg"}}\ta backslash before r inside double quotes remains literal\n'
printf '0\t{"tool_input":{"command":"'"'"'g\\\\it'"'"' clone https://example.invalid/x $HOME/wt"}}\ta literal backslash in a single-quoted non-git name is not a checkout\n'
printf '0\t{"tool_input":{"command":"\\"g\\\\it\\" clone https://example.invalid/x $HOME/wt"}}\ta literal backslash in a double-quoted non-git name is not a checkout\n'
# The other branch of the same rule: OUTSIDE quotes a backslash escapes the
# next character, so an escaped quote is a literal quote IN the name and the
# program is not curl. Held separately from the cases above because it is a
# different arm of the state machine, and an arm without a fixture is a rule
# that is not held.
printf '0\t{"tool_input":{"command":"cu\\\\\\"rl\\\\\\" --config /tmp/provider-write.cfg"}}\tan escaped quote is a literal quote in the name\n'
# Three quoted segments concatenate into ONE word. This is the shape that
# distinguishes quote removal from token separation, so it is worth its own line.
printf '2\t{"tool_input":{"command":"\\"cu\\"'"'"'r'"'"'\\"l\\" --config /tmp/provider-write.cfg"}}\tadjacent quoted segments are one word, and that word is curl\t--config/-K\n'
printf '2\t{"tool_input":{"command":"g\\"h\\" api -X POST repos/a/b/issues -f title=x"}}\tthe CLI name is a word on the same terms\n'
printf '2\t{"tool_input":{"command":"/usr/bin/g\\\\h api -X POST repos/a/b/issues -f title=x"}}\tincluding when it is escaped behind a path\n'
# The FLAG is the same recognition problem as the name, and is read the same
# way. No review raised this one; the name was simply the easier half to reach.
printf '2\t{"tool_input":{"command":"curl --con\\"fig\\" /tmp/provider-write.cfg"}}\tone word spelling --config is still --config\t--config/-K\n'
# The unreadable-endpoint arm is the THIRD name consumer. It kept a private
# bare-name copy of the scope gate's regex, so a caller could be admitted by
# the repaired gate and then go unrecognized by the fail-closed refinement —
# a gate and its own refinement disagreeing about who the caller is.
printf '2\t{"tool_input":{"command":"/usr/bin/gh api -X POST repos/a/b/$EP -f title=x"}}\ta path-qualified CLI with an assembled endpoint is still unreadable\n'
printf '2\t{"tool_input":{"command":"g\\"h\\" api -X POST repos/a/b/$EP -f title=x"}}\tand so is a quoted one, which is where the two halves disagreed\n'
printf '0\t{"tool_input":{"command":"mygh api -X POST repos/a/b/$EP -f title=x"}}\tmygh is still not gh, in the refinement as well as the gate\n'
# Shapes nobody raised. Written down because reasoning that they were already
# covered is precisely what produced two of the rounds above; each one below
# was measured, and the three that fail at df83a9ee are here on that evidence.
# `\curl` is the ordinary way to bypass a shell alias and is a thing people
# actually type, which makes it the least hypothetical entry in the file.
printf '2\t{"tool_input":{"command":"\\\\curl --config /tmp/provider-write.cfg"}}\tescaping the leading character to dodge an alias still names curl\t--config/-K\n'
printf '2\t{"tool_input":{"command":"cur\\"l\\" --config /tmp/provider-write.cfg"}}\tthe quote may sit at any offset in the word\t--config/-K\n'
printf '2\t{"tool_input":{"command":"g\\"h\\" api -X POST \\"repos/a/b/$EP\\" -f title=x"}}\tboth halves dressed at once, which is where they last disagreed\n'
# Over-blocking is a real failure and not a safe direction: a guard that
# refuses legitimate work gets routed around instead of repaired. These four
# pass at both heads, which is what a regression guard is for.
printf '0\t{"tool_input":{"command":"gh api \\"repos/a/b/issues\\""}}\ta quoted read is still a read\n'
printf '0\t{"tool_input":{"command":"curl https://example.com/file.txt -o /tmp/f"}}\tan ordinary download is not a provider write\n'
printf '0\t{"tool_input":{"command":"echo \\"$EP\\" && gh --version"}}\tno api subcommand, so nothing to refuse\n'
printf '0\t{"tool_input":{"command":"echo \\"not a curl call\\""}}\tthe word inside a string, with no flag, is prose\n'
# Percent-encoded endpoints. Not hypothetical: /issues/1174 and /iss%%75es/1174
# both returned HTTP 200 with the same object from the live forge, so the
# encoded spelling IS the wrapped endpoint and the literal comparison below it
# sees a segment matching nothing. Refused rather than decoded — a decoder has
# to be exactly right about depth and normalization, which is the parser
# mistake this file declines everywhere else.
printf '2\t{"tool_input":{"command":"gh api -X POST repos/a/b/iss%%75es/1/comments -f body=x"}}\tan encoded path segment reaches the wrapped endpoint\tpercent-escape\n'
printf '2\t{"tool_input":{"command":"curl -X POST -d @b https://git.example.invalid/api/v1/repos/a/b/pulls/1/revi%%65ws"}}\tsame for the review endpoint, which is the one that matters most\tpercent-escape\n'
printf '2\t{"tool_input":{"command":"gh api -X POST repos/a/b/iss%%2575es/1/comments -f body=x"}}\tdouble-encoded too, which is why this refuses instead of decoding\tpercent-escape\n'
# Scoped to writes, deliberately. Reads are never blocked by this guard and a
# query string carrying %%20 is an ordinary URL, not a hazard.
printf '0\t{"tool_input":{"command":"curl -s https://git.example.invalid/api/v1/repos/a/b/issues?q=a%%20b"}}\ta percent-escape in a READ is not this hook'"'"'s business\n'
} > "$FIXTURES"
fail=0 n=0
while IFS=$'\t' read -r want payload why remedy; do
[ -n "${want:-}" ] || continue
n=$((n + 1))
out="$(printf '%s' "$payload" | "$GUARD" 2>&1)"
got=$?
if [ "$got" != "$want" ]; then
printf 'FAIL %s (want exit %s, got %s)\n' "$why" "$want" "$got"
fail=1
continue
fi
# A block that names the wrong wrapper is a defect in its own right, and until
# now it was invisible here: the harness read the exit code and nothing else,
# so /issues/1/labels blocking with "use issue-create.sh" passed every run for
# six rounds. Where a fixture states the remediation it expects, assert it.
if [ -n "${remedy:-}" ] && ! printf '%s' "$out" | grep -Fq -- "$remedy"; then
printf 'FAIL %s (blocked, but the advice does not name %s)\n' "$why" "$remedy"
fail=1
continue
fi
printf 'ok %s\n' "$why"
done < "$FIXTURES"
# ---- $HOME resolution ------------------------------------------------------
# These cannot be fixtures. Every case above varies the COMMAND; this defect
# varies the ENVIRONMENT, and the loop has no way to express that.
#
# The checkout arm built its pattern from "$HOME" without asking whether $HOME
# was a usable value. Three values it is not: unset (which is a crash under
# `set -u`, not a decision), empty (the pattern collapses to `/`, so `~|\$HOME|`
# matches whatever the empty alternative touches), and "/" (every absolute path
# is under it, so the comparison stops discriminating). An agent seat running
# with no HOME — a systemd unit without one, a container, `env -i` — got the
# checkout question answered by accident rather than on the merits.
#
# The fix resolves $HOME once, rejects all three, and BLOCKS the checkout it
# cannot adjudicate. A guard may not clear a question it was unable to ask. The
# blast radius of that fail-closed arm is asserted below to be one command shape
# and not the session: with no HOME at all, ordinary commands still pass and the
# API arms still block.
home_case() {
local why="$1" want="$2" homeval="$3" cmd="$4" needle="${5:-}"
local out got
n=$((n + 1))
local payload
payload="$(jq -nc --arg command "$cmd" '{tool_input:{command:$command}}')"
if [ "$homeval" = "@unset" ]; then
out="$(printf '%s' "$payload" | env -u HOME "$GUARD" 2>&1)"
else
out="$(printf '%s' "$payload" | env HOME="$homeval" "$GUARD" 2>&1)"
fi
got=$?
if [ "$got" != "$want" ]; then
printf 'FAIL %s (want exit %s, got %s)\n' "$why" "$want" "$got"
fail=1
return
fi
if [ -n "$needle" ] && ! printf '%s' "$out" | grep -Fq -- "$needle"; then
printf 'FAIL %s (exit %s, but the message does not say %s)\n' "$why" "$got" "$needle"
fail=1
return
fi
printf 'ok %s\n' "$why"
}
home_case 'HOME unset: a checkout is refused, not adjudicated' \
2 '@unset' 'git clone https://example.invalid/x /src/wt' 'unset or unusable'
home_case 'HOME empty: same, and it is not the same thing as unset' \
2 '' 'git clone https://example.invalid/x /src/wt' 'unset or unusable'
home_case 'HOME=/ : every path is under it, so it discriminates nothing' \
2 '/' 'git clone https://example.invalid/x /src/wt' 'unset or unusable'
home_case 'a usable HOME still allows a checkout onto a work filesystem' \
0 '/home/tester' 'git clone https://example.invalid/x /src/wt'
home_case 'a usable HOME still catches the literal path' \
2 '/home/tester' 'git clone https://example.invalid/x /home/tester/wt' 'checks a repository out under'
home_case 'a usable HOME catches the exact literal path without a trailing slash' \
2 '/home/tester' 'git clone https://example.invalid/x /home/tester' 'checks a repository out under'
home_case 'quotes around the exact literal HOME path do not change the target' \
2 '/home/tester' 'git clone https://example.invalid/x "/home/tester"' 'checks a repository out under'
home_case 'a quoted literal HOME segment remains contiguous with the suffix' \
2 '/home/tester' 'git clone https://example.invalid/x "/home/tester"/wt' 'checks a repository out under'
home_case 'a repeated leading slash is the same absolute HOME path' \
2 '/home/tester' 'git clone https://example.invalid/x //home/tester/wt' 'checks a repository out under'
home_case 'dot segments cannot disguise the literal HOME path' \
2 '/home/tester' 'git worktree add /var/../home/tester/./wt' 'checks a repository out under'
home_case 'parent traversal into HOME is normalized for separate Git state' \
2 '/home/tester' 'git clone --separate-git-dir=/home/other/../tester/gd x /src/wt' 'checks a repository out under'
home_case 'normalization still permits a literal HOME sibling' \
0 '/home/tester' 'git clone x /home/tester/../tester-sibling/wt'
home_case 'and the unexpanded $HOME spelling, which needs no resolution at all' \
2 '/home/tester' 'git worktree add $HOME/wt topic' 'checks a repository out under'
# Resolve the longest existing parent physically before appending a nonexistent
# destination. Lexical normalization alone cannot see a symlink into HOME, and
# it applies `..` in the wrong order when the preceding component is a symlink.
SYMLINK_HOME="$TMP/symlink-home"
SYMLINK_SAFE="$TMP/symlink-safe"
mkdir -p "$SYMLINK_HOME/nested" "$SYMLINK_SAFE"
ln -s "$SYMLINK_HOME" "$TMP/home-link"
ln -s "$SYMLINK_HOME/nested" "$TMP/home-nested-link"
ln -s "$SYMLINK_SAFE" "$TMP/safe-link"
home_case 'a clone path through a symlink into HOME is refused' \
2 "$SYMLINK_HOME" "git clone x $TMP/home-link/wt" 'checks a repository out under'
home_case 'a worktree path through a symlink into HOME is refused' \
2 "$SYMLINK_HOME" "git worktree add $TMP/home-link/wt" 'checks a repository out under'
home_case 'symlink resolution occurs before a following parent segment' \
2 "$SYMLINK_HOME" "git clone x $TMP/home-nested-link/../wt" 'checks a repository out under'
home_case 'a symlink to a physical path outside HOME remains allowed' \
0 "$SYMLINK_HOME" "git clone x $TMP/safe-link/wt"
# The fail-closed arm is scoped to checkouts. If it were not, a seat with no
# HOME would have every command it runs refused, which is how a guard gets
# disabled rather than fixed.
home_case 'HOME unset does not block an ordinary command' \
0 '@unset' 'ls -la /src'
home_case 'HOME unset does not stop the API arms doing their job' \
2 '@unset' 'curl -X POST -d @b https://git.example.invalid/api/v1/repos/a/b/pulls/1/reviews' 'pr-review.sh'
# ---- the guard standing on its own -----------------------------------------
# Every case above runs the guard from the directory holding its siblings, so
# `[ -x "$W/pr-review.sh" ]` succeeds and the $HOME fallback beside it never
# evaluates. That is a property of the HARNESS, not of the guard, and it hid a
# live fail-open: with the guard copied somewhere alone AND no HOME, the
# fallback expanded an unset variable under `set -u` and the script died at
# rc=1 — on EVERY arm, before any adjudication. A PreToolUse hook exiting
# nonzero-but-not-2 is a non-blocking error, so that seat ran with no guard and
# nothing reported it.
#
# The first remediation moved that expansion four lines earlier and called it
# closed. It was not closed, because the test could not reach it. So the guard
# is copied ALONE here — no siblings, no installed mosaic home — which is the
# deployment this file already claims to support ("still works from a repo
# checkout with no installed mosaic home").
LONE="$TMP/lone"; mkdir -p "$LONE"
cp "$GUARD" "$LONE/wrapper-guard.sh"; chmod +x "$LONE/wrapper-guard.sh"
lone_case() {
local why="$1" want="$2" homeval="$3" cmd="$4" needle="${5:-}"
local out got
n=$((n + 1))
if [ "$homeval" = "@unset" ]; then
out="$(printf '%s' "{\"tool_input\":{\"command\":\"$cmd\"}}" | env -u HOME "$LONE/wrapper-guard.sh" 2>&1)"
else
out="$(printf '%s' "{\"tool_input\":{\"command\":\"$cmd\"}}" | env HOME="$homeval" "$LONE/wrapper-guard.sh" 2>&1)"
fi
got=$?
if [ "$got" != "$want" ]; then
printf 'FAIL %s [standalone] (want exit %s, got %s)\n' "$why" "$want" "$got"
fail=1
return
fi
if [ -n "$needle" ] && ! printf '%s' "$out" | grep -Fq -- "$needle"; then
printf 'FAIL %s [standalone] (exit %s, but the message does not say %s)\n' "$why" "$got" "$needle"
fail=1
return
fi
printf 'ok %s [standalone]\n' "$why"
}
lone_case 'no siblings and no HOME: an ordinary command still passes, not rc=1' \
0 '@unset' 'ls -la /src'
lone_case 'no siblings and no HOME: a wrapped write is still refused' \
2 '@unset' 'curl -X POST -d @b https://git.example.invalid/api/v1/repos/a/b/pulls/1/reviews' 'pr-review.sh'
lone_case 'no siblings and no HOME: a checkout is refused, not adjudicated' \
2 '@unset' 'git clone https://example.invalid/x /src/wt' 'unset or unusable'
# Spelled without quotes on purpose. The payload is interpolated into a JSON
# string by the helper, so a fixture carrying bare double quotes produces
# malformed JSON, jq returns empty, and the guard exits 0 on an empty command —
# a PASS that measures nothing. That is what the first version of this case did.
lone_case 'no siblings and no HOME: the APPROVE trap still fires' \
2 '@unset' 'gh api -X POST repos/a/b/pulls/1/reviews -f event=APPROVE'
lone_case 'no siblings, usable HOME: ordinary commands unaffected' \
0 '/home/tester' 'ls -la /src'
printf '\n'
if [ "$fail" -eq 0 ]; then
printf 'wrapper-guard: %d/%d fixtures behaved as specified.\n' "$n" "$n"
else
cat <<'EOF'
wrapper-guard drifted from its contract.
A guard that blocks too much gets routed around, and a guard that blocks too
little is decoration. Both directions are failures here, which is why the
allowed cases are asserted as hard as the blocked ones.
EOF
fi
exit "$fail"
File diff suppressed because it is too large Load Diff