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 2026-09-26 00:22:43 +00:00
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__":