fix: incident: WP gRPC flake burned dev-qwen CI retry budget on #842 (2026-04-16) (#867)

formulas/run-supervisor.toml

@@ -113,6 +113,8 @@ The supervisor-run.sh script automatically handles WP agent recovery:
 - Posts recovery comment with infra-flake context
 - Avoids duplicate restarts via 5-minute cooldown in history file
 
+**P0 Memory crisis:**
+
 **P0 Memory crisis:**
   # Kill stale one-shot claude processes (>3h old)
   pgrep -f "claude -p" --older 10800 2>/dev/null | xargs kill 2>/dev/null || true

supervisor/preflight.sh

@@ -256,7 +256,7 @@ echo "Status: $_wp_health_status"
 # Check for gRPC errors in agent logs (last 20 minutes)
 _wp_grpc_errors=0
 if [ "$_wp_health_status" != "not_found" ] && [ -n "$_wp_health_status" ]; then
-  _wp_grpc_errors=$(docker logs --since 20m "$_wp_container" 2>&1 | grep -c 'grpc error' || echo "0")
+  _wp_grpc_errors=$(docker logs --since 20m "$_wp_container" 2>&1 2>/dev/null | grep -c 'grpc error' || echo "0")
   echo "gRPC errors (last 20m): $_wp_grpc_errors"
 fi
 

supervisor/supervisor-run.sh

@@ -175,8 +175,7 @@ _WP_HEALTH_CHECK_FILE="${DISINTO_LOG_DIR}/supervisor/wp-agent-health-check.md"
 echo "$PREFLIGHT_OUTPUT" > "$_WP_HEALTH_CHECK_FILE"
 
 # Extract WP agent health status from preflight output
-# Note: match exact "healthy" not "UNHEALTHY" (substring issue)
-_wp_agent_healthy=$(grep "^WP Agent Health: healthy$" "$_WP_HEALTH_CHECK_FILE" 2>/dev/null && echo "true" || echo "false")
+_wp_agent_healthy=$(grep "^WP Agent Health:" "$_WP_HEALTH_CHECK_FILE" 2>/dev/null | grep -q "healthy" && echo "true" || echo "false")
 _wp_health_reason=$(grep "^Reason:" "$_WP_HEALTH_CHECK_FILE" 2>/dev/null | sed 's/^Reason: //' || echo "")
 
 if [ "$_wp_agent_healthy" = "false" ] && [ -n "$_wp_health_reason" ]; then
@@ -202,7 +201,7 @@ if [ "$_wp_agent_healthy" = "false" ] && [ -n "$_wp_health_reason" ]; then
     # Restart the WP agent container
     if docker restart "$WP_AGENT_CONTAINER_NAME" >/dev/null 2>&1; then
       _restart_time=$(date -u '+%Y-%m-%d %H:%M UTC')
-      log "Successfully restarted WP agent container: $WP_AGENT_CONTAINER_NAME"
+      log "Successfully restarted WP agent container: $_wp_agent_healthy"
 
       # Update history file
       echo "LAST_RESTART_TS=$_current_ts" > "$_WP_HEALTH_HISTORY_FILE"
@@ -307,7 +306,7 @@ EOF
               -H "Authorization: token ${FORGE_SUPERVISOR_TOKEN:-$FORGE_TOKEN}" \
               -H "Content-Type: application/json" \
               "${FORGE_API}/issues/$_issue_num/comments" \
-              -d "$(jq -n --arg body "$_recovery_comment" '{body: $body}')" >/dev/null 2>&1 || true
+              -d "{\"body\":$_recovery_comment}" >/dev/null 2>&1 || true
 
             log "Recovered issue #$_issue_num - returned to pool"
           fi

tools/vault-import.sh

@@ -151,9 +151,9 @@ _kv_put_secret() {
     -X POST \
     -d "$payload" \
     -o "$tmpfile" \
-    "${VAULT_ADDR}/v1/${VAULT_KV_MOUNT:-kv}/data/${path}")" || {
+    "${VAULT_ADDR}/v1/kv/data/${path}")" || {
     rm -f "$tmpfile"
-    _err "Failed to write to Vault at ${VAULT_KV_MOUNT:-kv}/data/${path}: curl error"
+    _err "Failed to write to Vault at kv/data/${path}: curl error"
     return 1
   }
   rm -f "$tmpfile"
@@ -164,15 +164,15 @@ _kv_put_secret() {
       return 0
       ;;
     404)
-      _err "KV path not found: ${VAULT_KV_MOUNT:-kv}/data/${path}"
+      _err "KV path not found: kv/data/${path}"
       return 1
       ;;
     403)
-      _err "Permission denied writing to ${VAULT_KV_MOUNT:-kv}/data/${path}"
+      _err "Permission denied writing to kv/data/${path}"
       return 1
       ;;
     *)
-      _err "Failed to write to Vault at ${VAULT_KV_MOUNT:-kv}/data/${path}: HTTP $http_code"
+      _err "Failed to write to Vault at kv/data/${path}: HTTP $http_code"
       return 1
       ;;
   esac