fix(fleet): make framework shell assertions SIGPIPE-safe (#1100)

packages/mosaic/framework/tools/fleet/test-start-agent-session.sh

@@ -14,6 +14,82 @@ fail() {
   exit 1
 }
 
+pane_command_clears_environment() {
+  local calls_file="$1"
+  local -a argv=()
+  local index
+  mapfile -d '' -t argv < "$calls_file"
+  for ((index = 0; index + 1 < ${#argv[@]}; index++)); do
+    if [ "${argv[$index]}" = /usr/bin/env ] && [ "${argv[$((index + 1))]}" = -i ]; then
+      return 0
+    fi
+  done
+  return 1
+}
+
+print_pane_argv() {
+  local calls_file="$1"
+  local -a argv=()
+  local bytes index
+  mapfile -d '' -t argv < "$calls_file"
+  bytes=$(wc -c < "$calls_file")
+  printf 'observed pane argv: records=%s bytes=%s\n' "${#argv[@]}" "$bytes" >&2
+  for ((index = 0; index < ${#argv[@]}; index++)); do
+    printf '  [%03d] %q\n' "$index" "${argv[$index]}" >&2
+  done
+}
+
+check_pane_environment_boundary() {
+  local calls_file="$1"
+  if pane_command_clears_environment "$calls_file"; then
+    return 0
+  fi
+  print_pane_argv "$calls_file"
+  return 1
+}
+
+contains_literal() {
+  grep -F -- "$2" <<< "$1" >/dev/null
+}
+
+contains_line() {
+  grep -xF -- "$2" <<< "$1" >/dev/null
+}
+
+# Portability regression: inspect the authoritative NUL-delimited argv instead
+# of piping a newline reconstruction through `grep -q` under pipefail. The old
+# pipeline could report failure after a successful match when an upstream
+# producer received SIGPIPE. A large trailing argument keeps that failure class
+# covered without making stream size part of the semantic contract.
+PORTABILITY_CALLS="$ROOT/portability-calls"
+printf -v PORTABILITY_PADDING '%*s' 32768 ''
+PORTABILITY_PADDING=${PORTABILITY_PADDING// /x}
+printf '%s\0' /usr/bin/env -i "$PORTABILITY_PADDING" > "$PORTABILITY_CALLS"
+pane_command_clears_environment "$PORTABILITY_CALLS" || \
+  fail "valid large pane argv was rejected by the environment-boundary assertion"
+
+assert_pane_boundary_rejected() {
+  local case_name="$1"
+  local expected_records="$2"
+  local diagnostic
+  if diagnostic=$(check_pane_environment_boundary "$PORTABILITY_CALLS" 2>&1); then
+    fail "pane boundary accepted invalid $case_name fixture"
+  fi
+  contains_literal "$diagnostic" "records=$expected_records bytes=" || \
+    fail "pane argv diagnostic omitted counts for $case_name fixture"
+  contains_literal "$diagnostic" '[000]' || \
+    fail "pane argv diagnostic omitted indexed arguments for $case_name fixture"
+}
+
+printf '%s\0' tmux -i > "$PORTABILITY_CALLS"
+assert_pane_boundary_rejected missing-env 2
+printf '%s\0' /usr/bin/env HOME=/untrusted > "$PORTABILITY_CALLS"
+assert_pane_boundary_rejected missing-i 2
+printf '%s\0' /usr/bin/env HOME=/untrusted -i > "$PORTABILITY_CALLS"
+assert_pane_boundary_rejected non-adjacent-i 3
+printf '%s\0' -i /usr/bin/env > "$PORTABILITY_CALLS"
+assert_pane_boundary_rejected reversed-boundary 2
+
 cat > "$FAKE_BIN/tmux" <<'SHIM'
 #!/usr/bin/env bash
 set -euo pipefail
@@ -115,19 +191,19 @@ AGENT_VALID="coder0"
 write_generated "$HOME_VALID" "$AGENT_VALID"
 run_start "$HOME_VALID" "$AGENT_VALID"
 valid_args=$(tr '\0' '\n' < "$TMUX_CALLS")
-echo "$valid_args" | grep -qF new-session || fail "valid generated projection did not reach tmux"
-echo "$valid_args" | grep -qF 'mosaic' || fail "fixed mosaic launcher command missing"
-echo "$valid_args" | grep -qF 'yolo' || fail "fixed yolo launcher command missing"
-echo "$valid_args" | grep -qF 'pi' || fail "roster runtime missing"
-if echo "$valid_args" | grep -qF 'bash -c'; then
+contains_literal "$valid_args" new-session || fail "valid generated projection did not reach tmux"
+contains_literal "$valid_args" mosaic || fail "fixed mosaic launcher command missing"
+contains_literal "$valid_args" yolo || fail "fixed yolo launcher command missing"
+contains_literal "$valid_args" pi || fail "roster runtime missing"
+if contains_literal "$valid_args" 'bash -c'; then
   fail "launcher constructed a shell command payload"
 fi
 
 # The pane must start through an absolute clean-environment boundary. Its
 # runtime command remains an argv vector, but no holder/session environment
 # control variable can pass through the pane command.
-echo "$valid_args" | grep -qxF '/usr/bin/env' || fail "pane does not use absolute env"
-echo "$valid_args" | grep -qxF -- '-i' || fail "pane environment is not cleared"
+check_pane_environment_boundary "$TMUX_CALLS" || \
+  fail "pane command did not use an adjacent /usr/bin/env -i boundary"
 
 # Git identity is generated authority, not an optional or independently mutable
 # local value. Each invalid form must fail before fake tmux receives a call.
@@ -156,7 +232,7 @@ assert_git_identity_rejected() {
     fail "Git identity case $case_name was accepted"
   fi
   [ ! -s "$TMUX_CALLS" ] || fail "tmux ran before Git identity $case_name rejection"
-  echo "$output" | grep -qF "code=$expected_code" || \
+  contains_literal "$output" "code=$expected_code" || \
     fail "Git identity $case_name diagnostic omitted code $expected_code"
 }
 
@@ -176,7 +252,7 @@ if output=$(run_start "$HOME_UNSAFE_PARENT" coder-parent 2>&1); then
   fail "generated file under a world-writable parent was accepted"
 fi
 [ ! -s "$TMUX_CALLS" ] || fail "tmux ran before unsafe parent rejection"
-echo "$output" | grep -qF 'code=unsafe-permissions' || fail "unsafe parent diagnostic missing"
+contains_literal "$output" 'code=unsafe-permissions' || fail "unsafe parent diagnostic missing"
 
 : > "$TMUX_CALLS"
 HOME_SYMLINK_PARENT="$ROOT/symlink-parent"
@@ -187,7 +263,7 @@ if output=$(run_start "$HOME_SYMLINK_PARENT" coder-symlink-parent 2>&1); then
   fail "generated file under a symlinked parent was accepted"
 fi
 [ ! -s "$TMUX_CALLS" ] || fail "tmux ran before symlinked parent rejection"
-echo "$output" | grep -qF 'code=unsafe-directory' || fail "symlinked parent diagnostic missing"
+contains_literal "$output" 'code=unsafe-directory' || fail "symlinked parent diagnostic missing"
 
 # Every managed ancestor is a boundary: MOSAIC_HOME, fleet, and agents. A
 # symlink or group/world-writable ancestor must fail before environment parsing,
@@ -225,8 +301,8 @@ assert_managed_ancestor_rejected() {
   fi
   [ ! -s "$TMUX_CALLS" ] || fail "tmux ran before $hazard $ancestor rejection"
   [ ! -e "$home/work" ] || fail "workdir was created before $hazard $ancestor rejection"
-  echo "$output" | grep -qF "code=unsafe-" || fail "managed ancestor diagnostic missing"
-  if echo "$output" | grep -qF 'key=MOSAIC_AGENT_COMMAND'; then
+  contains_literal "$output" 'code=unsafe-' || fail "managed ancestor diagnostic missing"
+  if contains_literal "$output" 'key=MOSAIC_AGENT_COMMAND'; then
     fail "environment parsing ran before $hazard $ancestor rejection"
   fi
 }
@@ -247,9 +323,9 @@ if output=$(run_start "$HOME_SHADOW" coder1 2>&1); then
   fail "generated-key shadow was accepted"
 fi
 [ ! -s "$TMUX_CALLS" ] || fail "tmux ran before generated-key shadow rejection"
-echo "$output" | grep -qF 'key=MOSAIC_AGENT_RUNTIME' || fail "shadow diagnostic omitted key"
-echo "$output" | grep -qF 'sha256=' || fail "shadow diagnostic omitted hash"
-if echo "$output" | grep -qF 'codex'; then
+contains_literal "$output" 'key=MOSAIC_AGENT_RUNTIME' || fail "shadow diagnostic omitted key"
+contains_literal "$output" 'sha256=' || fail "shadow diagnostic omitted hash"
+if contains_literal "$output" codex; then
   fail "shadow diagnostic leaked value"
 fi
 
@@ -265,9 +341,9 @@ if output=$(run_start "$HOME_COMMAND" coder2 2>&1); then
   fail "arbitrary command override was accepted"
 fi
 [ ! -s "$TMUX_CALLS" ] || fail "tmux ran before command rejection"
-echo "$output" | grep -qF 'key=MOSAIC_AGENT_COMMAND' || fail "command diagnostic omitted key"
-echo "$output" | grep -qF 'sha256=' || fail "command diagnostic omitted hash"
-if echo "$output" | grep -qF "$COMMAND_VALUE"; then
+contains_literal "$output" 'key=MOSAIC_AGENT_COMMAND' || fail "command diagnostic omitted key"
+contains_literal "$output" 'sha256=' || fail "command diagnostic omitted hash"
+if contains_literal "$output" "$COMMAND_VALUE"; then
   fail "command diagnostic leaked command value"
 fi
 
@@ -281,7 +357,7 @@ if output=$(run_start "$HOME_PERMS" coder3 2>&1); then
   fail "world-readable local input was accepted"
 fi
 [ ! -s "$TMUX_CALLS" ] || fail "tmux ran before permissions rejection"
-echo "$output" | grep -qF 'code=unsafe-permissions' || fail "permission diagnostic missing"
+contains_literal "$output" 'code=unsafe-permissions' || fail "permission diagnostic missing"
 
 # A unit/holder-like clean bootstrap must yield a pane with trusted HOME and
 # computed PATH only. The pane command itself must not carry loader, shell
@@ -311,19 +387,17 @@ PATH="$PANE_STALE_PATH" \
     MOSAIC_TEST_EXECUTE_PANE=1 \
     "$START" coder-pane-boundary
 pane_args=$(tr '\0' '\n' < "$TMUX_CALLS")
-echo "$pane_args" | grep -qxF "HOME=$PANE_TRUSTED_HOME" || \
+contains_line "$pane_args" "HOME=$PANE_TRUSTED_HOME" || \
   fail "pane did not restore trusted HOME"
-echo "$pane_args" | grep -qF "HOME=$PANE_STALE_HOME" && \
+contains_literal "$pane_args" "HOME=$PANE_STALE_HOME" && \
   fail "pane inherited stale HOME"
-echo "$pane_args" | grep -qF "$PANE_STALE_PATH" && fail "pane inherited stale PATH"
+contains_literal "$pane_args" "$PANE_STALE_PATH" && fail "pane inherited stale PATH"
 for blocked in LD_PRELOAD= BASH_ENV= MOSAIC_UNTRUSTED_SENTINEL=; do
-  echo "$pane_args" | grep -qF "$blocked" && fail "pane inherited $blocked"
+  contains_literal "$pane_args" "$blocked" && fail "pane inherited $blocked"
 done
 
-after_pane_env=$(printf '%s\n' "$pane_args" | grep -n -m1 -F '/usr/bin/env' | cut -d: -f1)
-[ -n "$after_pane_env" ] || fail "pane command did not use absolute env"
-printf '%s\n' "$pane_args" | tail -n +"$after_pane_env" | grep -qxF -- '-i' || \
-  fail "pane command did not clear its environment"
+check_pane_environment_boundary "$TMUX_CALLS" || \
+  fail "pane command did not use an adjacent /usr/bin/env -i boundary"
 pane_environment=$(tr '\0' '\n' < "$HOME_PANE_BOUNDARY/fleet/pane-environment")
 # Exercise the repository launcher at $START, not the independently installed
 # host copy. Set-compare every declared generated projection entry with the
@@ -337,11 +411,11 @@ if [ -n "$missing_or_changed_generated_environment" ]; then
   missing_or_changed_keys=$(printf '%s\n' "$missing_or_changed_generated_environment" | cut -d= -f1 | paste -sd, -)
   fail "runtime pane omitted or changed generated environment keys: $missing_or_changed_keys"
 fi
-echo "$pane_environment" | grep -qxF "HOME=$PANE_TRUSTED_HOME" || \
+contains_line "$pane_environment" "HOME=$PANE_TRUSTED_HOME" || \
   fail "runtime pane did not receive trusted HOME"
-echo "$pane_environment" | grep -qF "$PANE_STALE_PATH" && fail "runtime pane received stale PATH"
+contains_literal "$pane_environment" "$PANE_STALE_PATH" && fail "runtime pane received stale PATH"
 for blocked in LD_PRELOAD= BASH_ENV= MOSAIC_UNTRUSTED_SENTINEL=; do
-  echo "$pane_environment" | grep -qF "$blocked" && fail "runtime pane received $blocked"
+  contains_literal "$pane_environment" "$blocked" && fail "runtime pane received $blocked"
 done
 
 write_interaction_generated() {
@@ -442,7 +516,7 @@ if output=$(run_interaction "$HOME_INTERACTION_MALFORMED" interaction-malformed
   fail "interaction wrapper accepted malformed generated data"
 fi
 [ ! -s "$TMUX_CALLS" ] || fail "tmux ran before interaction strict-parser rejection"
-echo "$output" | grep -qF 'code=unknown-key' || fail "interaction did not use shared strict parser first"
+contains_literal "$output" 'code=unknown-key' || fail "interaction did not use shared strict parser first"
 
 # A syntactically valid but policy-incompatible projection reaches the pinned
 # interaction policy check only after strict parsing and never starts tmux.
@@ -455,9 +529,9 @@ if output=$(run_interaction "$HOME_INTERACTION_POLICY" interaction-policy 2>&1);
   fail "interaction wrapper accepted a policy-incompatible projection"
 fi
 interaction_policy_args=$(tr '\0' '\n' < "$TMUX_CALLS")
-echo "$interaction_policy_args" | grep -qF 'new-session' && \
+contains_literal "$interaction_policy_args" new-session && \
   fail "interaction pinned-policy rejection created a tmux session"
-echo "$output" | grep -qF 'operator interaction service requires runtime pi' || \
+contains_literal "$output" 'operator interaction service requires runtime pi' || \
   fail "interaction pinned-policy check did not follow strict parsing"
 
 # Exact stop derives the socket exclusively from the validated generated
@@ -470,10 +544,10 @@ HOME="$HOME_STOP" PATH="$FAKE_BIN:$PATH" MOSAIC_TEST_TMUX_CALLS="$TMUX_CALLS" \
   MOSAIC_TEST_FLEET_OWNER=123e4567-e89b-12d3-a456-426614174000 \
   MOSAIC_HOME="$HOME_STOP" MOSAIC_TMUX_SOCKET=ambient-socket "$START" --stop coder-stop
 stop_args=$(tr '\0' '\n' < "$TMUX_CALLS")
-echo "$stop_args" | grep -qxF 'mosaic-test' || fail "exact stop did not use the validated generated socket"
-echo "$stop_args" | grep -qxF 'kill-session' || fail "exact stop did not request session termination"
-echo "$stop_args" | grep -qxF '=coder-stop' || fail "exact stop did not exact-match the generated agent name"
-if echo "$stop_args" | grep -qF 'ambient-socket'; then
+contains_line "$stop_args" mosaic-test || fail "exact stop did not use the validated generated socket"
+contains_line "$stop_args" kill-session || fail "exact stop did not request session termination"
+contains_line "$stop_args" '=coder-stop' || fail "exact stop did not exact-match the generated agent name"
+if contains_literal "$stop_args" ambient-socket; then
   fail "exact stop trusted an ambient socket"
 fi