zsp/everything-claude-code
1
0
Fork 0
mirror of https://github.com/affaan-m/everything-claude-code.git synced 2026-04-07 17:53:32 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix: observer memory explosion with throttling, re-entrancy guard, and tail sampling (#536)

Browse Source 
Three fixes for the positive feedback loop causing runaway memory usage:

1. SIGUSR1 throttling in observe.sh: Signal observer only every 20
   observations (configurable via ECC_OBSERVER_SIGNAL_EVERY_N) instead
   of on every tool call. Uses a counter file to track invocations.

2. Re-entrancy guard in observer-loop.sh on_usr1(): ANALYZING flag
   prevents parallel Claude analysis processes from spawning when
   signals arrive while analysis is already running.

3. Cooldown + tail-based sampling in observer-loop.sh:
   - 60s cooldown between analyses (ECC_OBSERVER_ANALYSIS_COOLDOWN)
   - Only last 500 lines sent to LLM (ECC_OBSERVER_MAX_ANALYSIS_LINES)
     instead of the entire observations file

Closes #521
This commit is contained in:
Affaan Mustafa
2026-03-16 13:47:25 -07:00
committed by GitHub
parent bb27dde116
commit f9e8287346
3 changed files with 435 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

57
skills/continuous-learning-v2/hooks/observe.sh
View File

@@ -365,24 +365,45 @@ if [ "$OBSERVER_ENABLED" = "true" ]; then
fi
fi
# Signal observer if running (check both project-scoped and global observer, deduplicate)
signaled_pids=" "
for pid_file in "${PROJECT_DIR}/.observer.pid" "${CONFIG_DIR}/.observer.pid"; do
if [ -f "$pid_file" ]; then
observer_pid=$(cat "$pid_file" 2>/dev/null || true)
# Validate PID is a positive integer (>1)
case "$observer_pid" in
''|*[!0-9]*|0|1) rm -f "$pid_file" 2>/dev/null || true; continue ;;
esac
# Deduplicate: skip if already signaled this pass
case "$signaled_pids" in
*" $observer_pid "*) continue ;;
esac
if kill -0 "$observer_pid" 2>/dev/null; then
kill -USR1 "$observer_pid" 2>/dev/null || true
signaled_pids="${signaled_pids}${observer_pid} "
fi
# Throttle SIGUSR1: only signal observer every N observations (#521)
# This prevents rapid signaling when tool calls fire every second,
# which caused runaway parallel Claude analysis processes.
SIGNAL_EVERY_N="${ECC_OBSERVER_SIGNAL_EVERY_N:-20}"
SIGNAL_COUNTER_FILE="${PROJECT_DIR}/.observer-signal-counter"
should_signal=0
if [ -f "$SIGNAL_COUNTER_FILE" ]; then
counter=$(cat "$SIGNAL_COUNTER_FILE" 2>/dev/null || echo 0)
counter=$((counter + 1))
if [ "$counter" -ge "$SIGNAL_EVERY_N" ]; then
should_signal=1
counter=0
fi
done
echo "$counter" > "$SIGNAL_COUNTER_FILE"
else
echo "1" > "$SIGNAL_COUNTER_FILE"
fi
# Signal observer if running and throttle allows (check both project-scoped and global observer, deduplicate)
if [ "$should_signal" -eq 1 ]; then
signaled_pids=" "
for pid_file in "${PROJECT_DIR}/.observer.pid" "${CONFIG_DIR}/.observer.pid"; do
if [ -f "$pid_file" ]; then
observer_pid=$(cat "$pid_file" 2>/dev/null || true)
# Validate PID is a positive integer (>1)
case "$observer_pid" in
''|*[!0-9]*|0|1) rm -f "$pid_file" 2>/dev/null || true; continue ;;
esac
# Deduplicate: skip if already signaled this pass
case "$signaled_pids" in
*" $observer_pid "*) continue ;;
esac
if kill -0 "$observer_pid" 2>/dev/null; then
kill -USR1 "$observer_pid" 2>/dev/null || true
signaled_pids="${signaled_pids}${observer_pid} "
fi
fi
done
fi
exit 0