fix(issue-26): integer knobs that reach bash arithmetic are read as decimal
bash read MAM_JOB_TIMEOUT_S=0700 as octal 448 (and failed on 0900) while the loop runner read 700. One rule now, with a per-knob minimum: lib.sh mam_int / mam_int_knob and runner._positive_int (blanks allowed, digits only, decimal, min <= n <= 999999999). - minimum 1: MAM_JOB_TIMEOUT_S, MAM_HEARTBEAT_SEC, MAM_HEARTBEAT_MISSES, MAM_ACK_TIMEOUT_S (invalid env: warning + default) and the wrapper's --timeout/--idle-timeout/--heartbeat/--heartbeat-misses/--ack-timeout (invalid: rc 1); the runner's job_budget, --job-timeout, contract_args. - minimum 0 (0 = check once): MAM_INJECT_ACK_GRACE_S, delegate_wait_started's ack_s, SKS_DIALOG_TIMEOUT, SKS_BUSY_TIMEOUT, SKS_DELIVERY_GRACE_S. - tests/test_issue26_ints.py: INT_KNOBS is the one table of minimums; a static guard keeps env defaults out of arithmetic and checks each normalised knob against it. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
1 parent
f1331d36ce
commit
80dc2eb45e
4 files changed
+367
-24
No files matched your search
@@ -115,7 +115,7 @@ usage() {
|
||||
multi-agent-mux-delegate-job <command> [options]
|
||||
|
||||
submit --agent <name> (--prompt <text> | --prompt-file <path>) [--workdir <dir>] [--agent-session <label>]
|
||||
[--timeout <sec> (default: $MAM_JOB_TIMEOUT_S or 3600)] [--idle-timeout <sec>] [--validate <script>]
|
||||
[--timeout <sec> (positive decimal integer; default: $MAM_JOB_TIMEOUT_S or 3600)] [--idle-timeout <sec>] [--validate <script>]
|
||||
[--heartbeat <sec>] [--heartbeat-misses <count>] [--ack-timeout <sec>]
|
||||
[--registry-dir <dir>] [--dry-run] [--role <role_name>]
|
||||
[--type <direct|loop|discuss>] [--reviewer <reviewer_agent>]
|
||||
@@ -147,15 +147,10 @@ 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 [[ "$MAM_JOB_TIMEOUT_S" =~ ^[0-9]+$ && "$MAM_JOB_TIMEOUT_S" -gt 0 ]]; then
|
||||
TIMEOUT="$MAM_JOB_TIMEOUT_S"
|
||||
else
|
||||
echo "WARNING: MAM_JOB_TIMEOUT_S=$MAM_JOB_TIMEOUT_S ignored (not a positive integer); using 3600" >&2
|
||||
fi
|
||||
fi
|
||||
# Issue #26: integer knobs are read as decimal by mam_int (lib.sh).
|
||||
TIMEOUT=$(mam_int_knob MAM_JOB_TIMEOUT_S 3600 1)
|
||||
# Issue #18 liveness contract (N / K / T). An unset --idle-timeout derives K x N.
|
||||
HEARTBEAT_SEC="${MAM_HEARTBEAT_SEC:-30}"; HEARTBEAT_MISSES="${MAM_HEARTBEAT_MISSES:-4}"; ACK_TIMEOUT="${MAM_ACK_TIMEOUT_S:-180}"
|
||||
HEARTBEAT_SEC=$(mam_int_knob MAM_HEARTBEAT_SEC 30 1); HEARTBEAT_MISSES=$(mam_int_knob MAM_HEARTBEAT_MISSES 4 1); ACK_TIMEOUT=$(mam_int_knob MAM_ACK_TIMEOUT_S 180 1)
|
||||
JOB_ID=""; REGISTRY_DIR="$REGISTRY_DIR_DEFAULT"; DELEGATE_ROLE="Worker"
|
||||
TYPE="direct"; REVIEWER="hermes"; REVIEWER_SESSION="herdr:hermes"; MAX_ITERATIONS=5
|
||||
DEFAULT_COUNTERPART_ROLE="Reviewer"
|
||||
@@ -193,6 +188,13 @@ parse_opts() {
|
||||
*) echo "unknown option: $1" >&2; usage; exit 1;;
|
||||
esac
|
||||
done
|
||||
# Issue #26: a flag value that is not a positive decimal integer is refused.
|
||||
local _flag _var _n
|
||||
for _flag in timeout:TIMEOUT idle-timeout:IDLE_TIMEOUT heartbeat:HEARTBEAT_SEC heartbeat-misses:HEARTBEAT_MISSES ack-timeout:ACK_TIMEOUT; do
|
||||
_var="${_flag#*:}"; [ -n "${!_var}" ] || continue
|
||||
_n=$(mam_int "${!_var}" 1) || { echo "ERROR: --${_flag%%:*} ${!_var}: not a positive decimal integer" >&2; exit 1; }
|
||||
printf -v "$_var" '%s' "$_n"
|
||||
done
|
||||
[ -n "$IDLE_TIMEOUT" ] || IDLE_TIMEOUT=$(( HEARTBEAT_SEC * HEARTBEAT_MISSES ))
|
||||
# lib.sh's send_keys_safe reads the job's own `started` from this registry.
|
||||
export SKS_REGISTRY_DIR="$REGISTRY_DIR"
|
||||
@@ -772,7 +774,7 @@ _wait_started() {
|
||||
}
|
||||
|
||||
# Legacy name retained for callers/tests of the ISSUE-14 guard.
|
||||
_inject_acknowledged() { _wait_started "$1" "${MAM_INJECT_ACK_GRACE_S:-$ACK_TIMEOUT}" "${2:-}"; }
|
||||
_inject_acknowledged() { _wait_started "$1" "$(mam_int_knob MAM_INJECT_ACK_GRACE_S "$ACK_TIMEOUT" 0)" "${2:-}"; }
|
||||
|
||||
# ISSUE-14 / ISSUE-18: herdr's agent_status and the pane busy token describe
|
||||
# the screen, not the protocol. They are no longer liveness *evidence* (a
|
||||
@@ -1112,7 +1114,7 @@ inject_agent() {
|
||||
echo "ERROR: 프롬프트 주입 실패 (send_keys_safe rc=$sks_rc) — 세션 '$sess'" >&2
|
||||
return 1 ;;
|
||||
esac
|
||||
local ack_s="${MAM_INJECT_ACK_GRACE_S:-$ACK_TIMEOUT}"
|
||||
local ack_s="$(mam_int_knob MAM_INJECT_ACK_GRACE_S "$ACK_TIMEOUT" 0)"
|
||||
if ! _wait_started "$job_id" "$ack_s" "${4:-}"; then
|
||||
trap - EXIT
|
||||
echo "ERROR: 프롬프트 주입 실패 — 세션 '$sess': no 'started' within ${ACK_WAITED_S:-$ack_s}s (ack timeout ${ack_s}s, bounded by the wall clock); not re-injecting" >&2
|
||||
@@ -1138,7 +1140,7 @@ remote_dispatch() {
|
||||
echo "ERROR: dispatch publish failed for job $job_id (remote:$sess)" >&2
|
||||
return 1
|
||||
fi
|
||||
local ack_s="${MAM_INJECT_ACK_GRACE_S:-$ACK_TIMEOUT}"
|
||||
local ack_s="$(mam_int_knob MAM_INJECT_ACK_GRACE_S "$ACK_TIMEOUT" 0)"
|
||||
if ! _wait_started "$job_id" "$ack_s" "$sub_log"; then
|
||||
echo "ERROR: remote session '$sess' published no 'started' within ${ACK_WAITED_S:-$ack_s}s (ack timeout ${ack_s}s, bounded by the wall clock); not re-dispatching" >&2
|
||||
return 1
|
||||
|
||||
Reference in new issue
Block a user