fix(issue-33): subscriber exit codes are named on both sides; wait keeps a spent budget at rc 2; G-8 is deterministic
- job_subscriber.py returns only named codes (RC_COMPLETED 0, RC_ERROR 1, RC_NO_EVENT 2, RC_BROKER_UNAVAILABLE 3, RC_WALL_CLOCK 4). The wrapper mirrors them as SUB_RC_* and compares subscriber codes only by name; a test keeps the mirror equal to the Python constants and forbids numeric comparisons of $sub_rc/$sub_exit and numeric `return` in the subscriber. - `delegate-job wait` passed the subscriber's code straight through, so a spent budget would have reached its callers as 4; it is 2 again (B7 fails without the mapping). - tier1 G-8 gave both clocks 0.5 s and raced; the wall clock now runs out first by construction (idle 30 s) and the test asserts RC_WALL_CLOCK. Other subscriber rc asserts use the names. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
GodopuandClaude Opus 5.5 committed
1 parent
9ec0569401
commit
1673818bb5
6 files changed
+77
-37
No files matched your search
@@ -49,11 +49,15 @@ logger = logging.getLogger("delegate_job.job_subscriber")
|
||||
TERMINAL_EVENTS = ("completed", "error")
|
||||
TERMINAL_STATUSES = ("completed", "error", "cancelled")
|
||||
STATE_EVENT = "state"
|
||||
# Exit codes. The wrapper mirrors them as SUB_RC_* (a test keeps the two equal).
|
||||
RC_COMPLETED = 0
|
||||
RC_ERROR = 1
|
||||
# Issue #33: which clock ended the wait. The wrapper maps both to a timeout
|
||||
# (caller rc 2) and labels the close from them: rc 2 -> deadline_timeout
|
||||
# (no event for the idle window, K x N), rc 4 -> wall_clock_timeout (the job
|
||||
# budget, --timeout, ran out while events may still have been arriving).
|
||||
RC_NO_EVENT = 2
|
||||
RC_BROKER_UNAVAILABLE = 3
|
||||
RC_WALL_CLOCK = 4
|
||||
|
||||
|
||||
@@ -350,9 +354,9 @@ def _run_subscriber(args) -> int:
|
||||
jobs = _collect_jobs(args)
|
||||
except FileNotFoundError as exc:
|
||||
logger.error("%s", exc)
|
||||
return 2
|
||||
return RC_NO_EVENT # nothing to watch: reported like silence, as before #33
|
||||
if not jobs:
|
||||
return 2
|
||||
return RC_NO_EVENT
|
||||
|
||||
expected_ids: Set[str] = {j["job_id"] for j in jobs}
|
||||
tokens = {j["job_id"]: j.get("auth_token") for j in jobs}
|
||||
@@ -451,8 +455,8 @@ def _run_subscriber(args) -> int:
|
||||
_check_disk_fallback(pending, args.registry_dir, terminal, dispatch_tokens, attempts)
|
||||
if not pending:
|
||||
if any(state == "error" for state in terminal.values()):
|
||||
return 1
|
||||
return 0
|
||||
return RC_ERROR
|
||||
return RC_COMPLETED
|
||||
|
||||
try:
|
||||
mqtt_common.with_retry(
|
||||
@@ -467,10 +471,10 @@ def _run_subscriber(args) -> int:
|
||||
_check_disk_fallback(pending, args.registry_dir, terminal, dispatch_tokens, attempts)
|
||||
if not pending:
|
||||
if any(state == "error" for state in terminal.values()):
|
||||
return 1
|
||||
return 0
|
||||
return RC_ERROR
|
||||
return RC_COMPLETED
|
||||
logger.error("broker connection failed: %s", exc)
|
||||
return 3
|
||||
return RC_BROKER_UNAVAILABLE
|
||||
|
||||
try:
|
||||
while pending:
|
||||
@@ -552,8 +556,8 @@ def _run_subscriber(args) -> int:
|
||||
|
||||
# All jobs reached a terminal state. error wins over completed.
|
||||
if any(state == "error" for state in terminal.values()):
|
||||
return 1
|
||||
return 0
|
||||
return RC_ERROR
|
||||
return RC_COMPLETED
|
||||
|
||||
|
||||
def main(argv=None) -> int:
|
||||
@@ -590,7 +594,7 @@ def main(argv=None) -> int:
|
||||
return _run_subscriber(args)
|
||||
except Exception as exc:
|
||||
logger.error("subscriber fatal error: %s", exc)
|
||||
return 3
|
||||
return RC_BROKER_UNAVAILABLE
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -140,6 +140,8 @@ EOF
|
||||
# ---- arg parsing helpers --------------------------------------------------
|
||||
AGENT="claude-code"; PROMPT=""; PROMPT_FILE=""; WORKDIR="$(pwd)"; AGENT_SESSION="herdr:claude"
|
||||
TIMEOUT=3600; IDLE_TIMEOUT=""; VALIDATE=""; DRY_RUN=0
|
||||
# job_subscriber.py exit codes (its RC_* constants; a test keeps the two equal).
|
||||
SUB_RC_COMPLETED=0; SUB_RC_ERROR=1; SUB_RC_NO_EVENT=2; SUB_RC_BROKER_UNAVAILABLE=3; SUB_RC_WALL_CLOCK=4
|
||||
# Issue #33: the job budget falls back to $MAM_JOB_TIMEOUT_S (--timeout > env > 3600).
|
||||
if [[ -n "${MAM_JOB_TIMEOUT_S:-}" ]]; then
|
||||
if [[ "$MAM_JOB_TIMEOUT_S" =~ ^[0-9]+$ && "$MAM_JOB_TIMEOUT_S" -gt 0 ]]; then
|
||||
@@ -289,7 +291,7 @@ EOF
|
||||
|
||||
# 1) Preflight (a remote session has no local pane to check: Issue #18)
|
||||
if ! _is_remote "$AGENT_SESSION" && ! preflight_agent "$JOB_ID" "$AGENT_SESSION" 0; then
|
||||
finalize_unfinished "$JOB_ID" "error" 1 "preflight"
|
||||
finalize_unfinished "$JOB_ID" "error" "$SUB_RC_ERROR" "preflight"
|
||||
local logs_root="${DELEGATE_JOB_LOGS_DIR:-$WORKDIR/delegate_job_logs}"
|
||||
echo "$logs_root/$JOB_ID"
|
||||
exit 5
|
||||
@@ -334,7 +336,7 @@ EOF
|
||||
else
|
||||
local sub_exit=0
|
||||
wait "$sub_pid" 2>/dev/null || sub_exit=$?
|
||||
if [ $sub_exit -eq 0 ] || [ $sub_exit -eq 3 ]; then
|
||||
if [ $sub_exit -eq $SUB_RC_COMPLETED ] || [ $sub_exit -eq $SUB_RC_BROKER_UNAVAILABLE ]; then
|
||||
sub_ready=1
|
||||
break
|
||||
else
|
||||
@@ -360,7 +362,7 @@ EOF
|
||||
# 5) Deliver the prompt (herdr pane or remote dispatch) and wait for `started`
|
||||
if ! deliver_prompt "$JOB_ID" "$instructions" "$AGENT_SESSION" "$logf"; then
|
||||
reap_subscriber "$sub_pid"
|
||||
finalize_unfinished "$JOB_ID" "error" 1 "inject"
|
||||
finalize_unfinished "$JOB_ID" "error" "$SUB_RC_ERROR" "inject"
|
||||
local logs_root="${DELEGATE_JOB_LOGS_DIR:-$WORKDIR/delegate_job_logs}"
|
||||
echo "$logs_root/$JOB_ID"
|
||||
exit 1
|
||||
@@ -456,7 +458,7 @@ EOF
|
||||
|
||||
# Preflight (skipped for a remote session: Issue #18)
|
||||
if ! _is_remote "$current_session" && ! preflight_agent "$JOB_ID" "$current_session" "$force_warn_only"; then
|
||||
finalize_unfinished "$JOB_ID" "error" 1 "preflight"
|
||||
finalize_unfinished "$JOB_ID" "error" "$SUB_RC_ERROR" "preflight"
|
||||
local logs_root="${DELEGATE_JOB_LOGS_DIR:-$WORKDIR/delegate_job_logs}"
|
||||
echo "$logs_root/$JOB_ID"
|
||||
exit 5
|
||||
@@ -512,7 +514,7 @@ EOF
|
||||
else
|
||||
local sub_exit=0
|
||||
wait "$sub_pid" 2>/dev/null || sub_exit=$?
|
||||
if [ $sub_exit -eq 0 ] || [ $sub_exit -eq 3 ]; then
|
||||
if [ $sub_exit -eq $SUB_RC_COMPLETED ] || [ $sub_exit -eq $SUB_RC_BROKER_UNAVAILABLE ]; then
|
||||
sub_ready=1
|
||||
break
|
||||
else
|
||||
@@ -545,7 +547,7 @@ EOF
|
||||
# Trigger agent
|
||||
if ! deliver_prompt "$JOB_ID" "$instructions" "$current_session" "$logf"; then
|
||||
reap_subscriber "$sub_pid"
|
||||
finalize_unfinished "$JOB_ID" "error" 1 "inject"
|
||||
finalize_unfinished "$JOB_ID" "error" "$SUB_RC_ERROR" "inject"
|
||||
local logs_root="${DELEGATE_JOB_LOGS_DIR:-$WORKDIR/delegate_job_logs}"
|
||||
echo "$logs_root/$JOB_ID"
|
||||
exit 1
|
||||
@@ -827,11 +829,11 @@ PYEOF
|
||||
_map_sub_rc() {
|
||||
local sub_rc="$1" job_id="$2"
|
||||
local job_status="running"
|
||||
if [[ $sub_rc -eq 0 ]]; then
|
||||
if [[ $sub_rc -eq $SUB_RC_COMPLETED ]]; then
|
||||
job_status="completed"
|
||||
elif [[ $sub_rc -eq 1 ]]; then
|
||||
elif [[ $sub_rc -eq $SUB_RC_ERROR ]]; then
|
||||
job_status="error"
|
||||
elif [[ $sub_rc -eq 3 ]]; then
|
||||
elif [[ $sub_rc -eq $SUB_RC_BROKER_UNAVAILABLE ]]; then
|
||||
job_status="broker_unavailable"
|
||||
local disk_st
|
||||
disk_st="$(_disk_status "$job_id")"
|
||||
@@ -839,7 +841,7 @@ _map_sub_rc() {
|
||||
job_status="$disk_st"
|
||||
fi
|
||||
else
|
||||
job_status="timeout"
|
||||
job_status="timeout" # SUB_RC_NO_EVENT, SUB_RC_WALL_CLOCK (and any other code)
|
||||
fi
|
||||
echo "$job_status"
|
||||
}
|
||||
@@ -952,7 +954,7 @@ finalize_unfinished() {
|
||||
# 2 no event); the disk-heartbeat grace above that ends on the deadline is
|
||||
# the wall clock too. bash only carries the label.
|
||||
local clock="${FINALIZE_CLOCK:-idle}"
|
||||
[ "$sub_rc" = "4" ] && clock="wall"
|
||||
[ "$sub_rc" = "$SUB_RC_WALL_CLOCK" ] && clock="wall"
|
||||
local close_req="deadline_timeout"
|
||||
[ "$clock" = "wall" ] && [ "$phase" != "inject" ] && close_req="wall_clock_timeout"
|
||||
local detail=""
|
||||
@@ -992,7 +994,7 @@ finalize_unfinished() {
|
||||
[ -n "${_disp_tok:-}" ] && disp_arg=(--expect-dispatch-token "$_disp_tok")
|
||||
if [ "$close_req" = "cancelled" ]; then
|
||||
"$PY" "$SCRIPT_DIR/scripts/publish_event.py" --registry-dir "$REGISTRY_DIR" --job "$job_id" --event cancelled --detail "$detail" ${disp_arg[@]+"${disp_arg[@]}"} 2>/dev/null || true
|
||||
elif [ "$sub_rc" -ne 1 ] || [ "$phase" = "inject" ]; then
|
||||
elif [ "$sub_rc" -ne "$SUB_RC_ERROR" ] || [ "$phase" = "inject" ]; then
|
||||
local err_detail="$close_req"
|
||||
[ "$phase" = "inject" ] && err_detail="agent_blocked"
|
||||
"$PY" "$SCRIPT_DIR/scripts/publish_event.py" --registry-dir "$REGISTRY_DIR" --job "$job_id" --event error --detail "$err_detail" ${disp_arg[@]+"${disp_arg[@]}"} 2>/dev/null || true
|
||||
@@ -1199,13 +1201,18 @@ cmd_logs() {
|
||||
cmd_wait() {
|
||||
parse_opts "$@"
|
||||
PY="$(pick_python)"
|
||||
local rc=0
|
||||
if [[ -n "$JOB_ID" ]]; then
|
||||
"$PY" "$SCRIPT_DIR/scripts/job_subscriber.py" --registry-dir "$REGISTRY_DIR" \
|
||||
--job "$JOB_ID" --timeout "$TIMEOUT"
|
||||
--job "$JOB_ID" --timeout "$TIMEOUT" || rc=$?
|
||||
else
|
||||
"$PY" "$SCRIPT_DIR/scripts/job_subscriber.py" --registry-dir "$REGISTRY_DIR" \
|
||||
--wait-any --timeout "$TIMEOUT"
|
||||
--wait-any --timeout "$TIMEOUT" || rc=$?
|
||||
fi
|
||||
# Issue #33: either clock is a timeout (rc 2) to callers of `wait`, as before;
|
||||
# the subscriber's own log says which clock it was.
|
||||
[ "$rc" -eq "$SUB_RC_WALL_CLOCK" ] && rc=$SUB_RC_NO_EVENT
|
||||
return "$rc"
|
||||
}
|
||||
|
||||
main() {
|
||||
|
||||
Reference in new issue
Block a user