The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
fix(continuous-learning-v2): observer background process crashes immediately (#312)
zzzhizhiadc0f6700813
diff --git a/skills/continuous-learning-v2/agents/start-observer.sh b/skills/continuous-learning-v2/agents/start-observer.shindex 99b250992..3197b8bc4 100755--- a/skills/continuous-learning-v2/agents/start-observer.sh+++ b/skills/continuous-learning-v2/agents/start-observer.sh@@ -14,6 +14,9 @@set -e+# NOTE: set -e is disabled inside the background subshell below+# to prevent claude CLI failures from killing the observer loop.+# ─────────────────────────────────────────────# Project detection# ─────────────────────────────────────────────@@ -132,12 +135,37 @@ case "${1:-start}" inecho "Starting observer agent for ${PROJECT_NAME}..."- # The observer loop- (- trap 'rm -f "$PID_FILE"; exit 0' TERM INT+ # The observer loop — fully detached with nohup, IO redirected to log.+ # Variables passed safely via env to avoid shell injection from special chars in paths.+ nohup env \+ CONFIG_DIR="$CONFIG_DIR" \+ PID_FILE="$PID_FILE" \+ LOG_FILE="$LOG_FILE" \+ OBSERVATIONS_FILE="$OBSERVATIONS_FILE" \+ INSTINCTS_DIR="$INSTINCTS_DIR" \+ PROJECT_DIR="$PROJECT_DIR" \+ PROJECT_NAME="$PROJECT_NAME" \+ PROJECT_ID="$PROJECT_ID" \+ MIN_OBSERVATIONS="$MIN_OBSERVATIONS" \+ OBSERVER_INTERVAL_SECONDS="$OBSERVER_INTERVAL_SECONDS" \+ /bin/bash -c '+ set +e+ unset CLAUDECODE++ SLEEP_PID=""+ USR1_FIRED=0++ cleanup() {+ [ -n "$SLEEP_PID" ] && kill "$SLEEP_PID" 2>/dev/null+ # Only remove PID file if it still belongs to this process+ if [ -f "$PID_FILE" ] && [ "$(cat "$PID_FILE" 2>/dev/null)" = "$$" ]; then+ rm -f "$PID_FILE"+ fi+ exit 0+ }+ trap cleanup TERM INTanalyze_observations() {- # Only analyze if observations file exists and has enough entriesif [ ! -f "$OBSERVATIONS_FILE" ]; thenreturnfi@@ -149,36 +177,45 @@ case "${1:-start}" inecho "[$(date)] Analyzing $obs_count observations for project ${PROJECT_NAME}..." >> "$LOG_FILE"# Use Claude Code with Haiku to analyze observations- # The prompt now specifies project-scoped instinct creation+ # The prompt specifies project-scoped instinct creationif command -v claude &> /dev/null; thenexit_code=0- claude --model haiku --print \- "Read $OBSERVATIONS_FILE and identify patterns for the project '${PROJECT_NAME}'.-If you find 3+ occurrences of the same pattern, create an instinct file in $INSTINCTS_DIR/ following this format:+ claude --model haiku --max-turns 3 --print \+ "Read $OBSERVATIONS_FILE and identify patterns for the project '${PROJECT_NAME}' (user corrections, error resolutions, repeated workflows, tool preferences).+If you find 3+ occurrences of the same pattern, create an instinct file in $INSTINCTS_DIR/<id>.md.++CRITICAL: Every instinct file MUST use this exact format:----id: <kebab-case-id>-trigger: \"<when this happens>\"-confidence: <0.3-0.9>-domain: <code-style|testing|git|debugging|workflow|etc>+id: kebab-case-name+trigger: \"when <specific condition>\"+confidence: <0.3-0.85 based on frequency: 3-5 times=0.5, 6-10=0.7, 11+=0.85>+domain: <one of: code-style, testing, git, debugging, workflow, file-patterns>source: session-observationscope: projectproject_id: ${PROJECT_ID}project_name: ${PROJECT_NAME}----# <Title>+# Title## Action-<What to do>+<what to do, one clear sentence>## Evidence-<What observations led to this>+- Observed N times in session <id>+- Pattern: <description>+- Last observed: <date>-Be conservative - only create instincts for clear patterns.-If a pattern seems universal (not project-specific), set scope to 'global' instead of 'project'.-Examples of global patterns: 'always validate user input', 'prefer explicit error handling'.-Examples of project patterns: 'use React functional components', 'follow Django REST framework conventions'." \+Rules:+- Be conservative, only clear patterns with 3+ observations+- Use narrow, specific triggers+- Never include actual code snippets, only describe patterns+- If a similar instinct already exists in $INSTINCTS_DIR/, update it instead of creating a duplicate+- The YAML frontmatter (between --- markers) with id field is MANDATORY+- If a pattern seems universal (not project-specific), set scope to 'global' instead of 'project'+- Examples of global patterns: 'always validate user input', 'prefer explicit error handling'+- Examples of project patterns: 'use React functional components', 'follow Django REST framework conventions'" \>> "$LOG_FILE" 2>&1 || exit_code=$?if [ "$exit_code" -ne 0 ]; thenecho "[$(date)] Claude analysis failed (exit $exit_code)" >> "$LOG_FILE"@@ -187,7 +224,6 @@ Examples of project patterns: 'use React functional components', 'follow Djangoecho "[$(date)] claude CLI not found, skipping analysis" >> "$LOG_FILE"fi- # Archive processed observationsif [ -f "$OBSERVATIONS_FILE" ]; thenarchive_dir="${PROJECT_DIR}/observations.archive"mkdir -p "$archive_dir"@@ -195,28 +231,46 @@ Examples of project patterns: 'use React functional components', 'follow Djangofi}- # Handle SIGUSR1 for on-demand analysis- trap 'analyze_observations' USR1+ on_usr1() {+ # Kill pending sleep to avoid leak, then analyze+ [ -n "$SLEEP_PID" ] && kill "$SLEEP_PID" 2>/dev/null+ SLEEP_PID=""+ USR1_FIRED=1+ analyze_observations+ }+ trap on_usr1 USR1echo "$$" > "$PID_FILE"echo "[$(date)] Observer started for ${PROJECT_NAME} (PID: $$)" >> "$LOG_FILE"while true; do- # Check at configured interval (default: 5 minutes)- sleep "$OBSERVER_INTERVAL_SECONDS"+ # Interruptible sleep — allows USR1 trap to fire immediately+ sleep "$OBSERVER_INTERVAL_SECONDS" &+ SLEEP_PID=$!+ wait $SLEEP_PID 2>/dev/null+ SLEEP_PID=""- analyze_observations+ # Skip scheduled analysis if USR1 already ran it+ if [ "$USR1_FIRED" -eq 1 ]; then+ USR1_FIRED=0+ else+ analyze_observations+ fidone- ) &-- disown+ ' >> "$LOG_FILE" 2>&1 &- # Wait a moment for PID file- sleep 1+ # Wait for PID file+ sleep 2if [ -f "$PID_FILE" ]; then- echo "Observer started (PID: $(cat "$PID_FILE"))"- echo "Log: $LOG_FILE"+ pid=$(cat "$PID_FILE")+ if kill -0 "$pid" 2>/dev/null; then+ echo "Observer started (PID: $pid)"+ echo "Log: $LOG_FILE"+ else+ echo "Failed to start observer (process died immediately, check $LOG_FILE)"+ exit 1+ fielseecho "Failed to start observer"exit 1