docs: plan chat-sessions fixes from real production usage data

Inspected the live agent_sessions/agent_messages tables on mac-mini and
found silent empty responses, a canned non-English refusal after 22 tool
calls, 70-call fan-out for simple fleet questions, 100KB+ persisted
messages, and no session delete/title hygiene.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

.claude/launch.json

@@ -0,0 +1,11 @@
+{
+  "version": "0.0.1",
+  "configurations": [
+    {
+      "name": "web",
+      "runtimeExecutable": "npm",
+      "runtimeArgs": ["--prefix", "web", "run", "dev"],
+      "port": 5173
+    }
+  ]
+}

api/openapi.yaml

@@ -312,6 +312,17 @@ paths:
             type: string
         style: form
         explode: true
+      - name: include
+        in: query
+        schema:
+          type: array
+          items:
+            type: string
+            enum:
+            - status
+        style: form
+        explode: true
+        description: include=status joins entity_status and populates GraphView.health
       responses:
         '200':
           description: Graph view
@@ -1696,6 +1707,22 @@ paths:
                 $ref: '#/components/schemas/HealthSummary'
         default:
           $ref: '#/components/responses/Problem'
+  /dashboard/summary:
+    get:
+      tags:
+      - observability
+      operationId: getDashboardSummary
+      summary: One-round-trip overview for the control room home page
+      x-required-scope: viewer
+      responses:
+        '200':
+          description: Dashboard summary
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/DashboardSummary'
+        default:
+          $ref: '#/components/responses/Problem'
   /export:
     get:
       tags:
@@ -1887,6 +1914,21 @@ components:
         updated_at:
           type: string
           format: date-time
+        health:
+          type: string
+          description: last observed health, when the entity is monitored
+          nullable: true
+          enum:
+          - healthy
+          - degraded
+          - down
+          - unknown
+          - stale
+        last_check_at:
+          type: string
+          format: date-time
+          nullable: true
+          description: when health was last observed
     EntityCreate:
       type: object
       required:
@@ -1983,6 +2025,17 @@ components:
         truncated:
           type: boolean
           description: True if node cap was hit
+        health:
+          type: object
+          description: entity id -> health, present when include=status was requested
+          additionalProperties:
+            type: string
+            enum:
+            - healthy
+            - degraded
+            - down
+            - unknown
+            - stale
     EntityType:
       type: object
       required:
@@ -2207,6 +2260,7 @@ components:
           - disk
           - cert-expiry
           - drift
+          - ping
           - ssh-script
         target:
           type: string
@@ -2246,6 +2300,7 @@ components:
           - disk
           - cert-expiry
           - drift
+          - ping
           - ssh-script
         target:
           type: string
@@ -2992,6 +3047,9 @@ components:
               type: integer
             unknown:
               type: integer
+            stale:
+              type: integer
+              description: last observation older than the check's expected cadence
         entities:
           type: array
           items:
@@ -3012,6 +3070,7 @@ components:
                 - degraded
                 - down
                 - unknown
+                - stale
               trend:
                 type: string
                 enum:
@@ -3024,6 +3083,72 @@ components:
                 type: string
                 format: date-time
                 nullable: true
+    DashboardSummary:
+      type: object
+      required:
+      - entities_by_type
+      - entities_by_state
+      - health
+      - signals_by_severity
+      - approvals_pending
+      - executions_by_state
+      - event_rate
+      properties:
+        entities_by_type:
+          type: object
+          description: entity counts keyed by type
+          additionalProperties:
+            type: integer
+        entities_by_state:
+          type: object
+          description: entity counts keyed by state
+          additionalProperties:
+            type: integer
+        health:
+          type: object
+          required:
+          - healthy
+          - degraded
+          - down
+          - unknown
+          properties:
+            healthy:
+              type: integer
+            degraded:
+              type: integer
+            down:
+              type: integer
+            unknown:
+              type: integer
+            stale:
+              type: integer
+              description: last observation older than the check's expected cadence
+        signals_by_severity:
+          type: object
+          description: open (non-resolved) signal counts keyed by severity
+          additionalProperties:
+            type: integer
+        approvals_pending:
+          type: integer
+        executions_by_state:
+          type: object
+          description: execution counts keyed by state, last 24h
+          additionalProperties:
+            type: integer
+        event_rate:
+          type: array
+          description: event counts bucketed by 5-minute interval, most recent last
+          items:
+            type: object
+            required:
+            - bucket
+            - count
+            properties:
+              bucket:
+                type: string
+                format: date-time
+              count:
+                type: integer
     EnrollRequest:
       type: object
       required:

checks/backup_freshness.sh

@@ -0,0 +1,23 @@
+#!/usr/bin/env bash
+# backup_freshness.sh — check that backups exist and are recent.
+set -euo pipefail
+
+BACKUP_DIRS="${OIKOS_BACKUP_DIRS:-/var/backups /opt/backups /mnt/backups}"
+GRACE_HOURS="${OIKOS_BACKUP_GRACE:-48}"
+STALE=""
+
+for dir in $BACKUP_DIRS; do
+  [ -d "$dir" ] || continue
+  NEWEST=$(find "$dir" -type f -mmin -$((GRACE_HOURS * 60)) 2>/dev/null | head -1 || true)
+  if [ -z "$NEWEST" ]; then
+    LATEST_TS=$(find "$dir" -type f -printf '%T@ %p\n' 2>/dev/null | sort -rn | head -1 | awk '{print $1}' || echo "0")
+    LATEST_HOURS=$(awk "BEGIN {printf \"%.0f\", ($(date +%s) - ${LATEST_TS:-0})/3600}")
+    STALE="$STALE $dir(${LATEST_HOURS}h)"
+  fi
+done
+
+if [ -n "$STALE" ]; then
+  echo "{\"health\":\"degraded\",\"signalKind\":\"backup-stale\",\"evidence\":\"stale backups:$(echo "$STALE" | sed 's/ /, /g')\"}"
+else
+  echo '{"health":"healthy"}'
+fi

checks/caddy_error_rate.sh

@@ -0,0 +1,46 @@
+#!/usr/bin/env bash
+# caddy_error_rate.sh — 5xx error rate from Caddy JSON access logs.
+set -euo pipefail
+
+LOG_DIR=""
+if [ -d /var/log/caddy ]; then
+  LOG_DIR="/var/log/caddy"
+elif [ -d /var/lib/caddy/logs ]; then
+  LOG_DIR="/var/lib/caddy/logs"
+elif [ -d /opt/caddy/logs ]; then
+  LOG_DIR="/opt/caddy/logs"
+fi
+
+if [ -z "$LOG_DIR" ]; then
+  echo '{"health":"healthy"}'
+  exit 0
+fi
+
+CUTOFF=$(date -u -d "5 minutes ago" +%Y-%m-%dT%H:%M 2>/dev/null || date -u -v-5M +%Y-%m-%dT%H:%M 2>/dev/null || echo "")
+
+TOTAL=0
+ERR_5XX=0
+
+for LOG in "$LOG_DIR"/access*.log "$LOG_DIR"/access*.json "$LOG_DIR"/*.log 2>/dev/null; do
+  [ -f "$LOG" ] || continue
+  [ -r "$LOG" ] || continue
+
+  if [ -n "$CUTOFF" ]; then
+    NEW=$(awk -v cutoff="$CUTOFF" '$0 >= cutoff {print}' "$LOG" 2>/dev/null | wc -l | tr -d ' ' || echo 0)
+    if [ "$NEW" -gt 0 ]; then
+      TOTAL=$((TOTAL + NEW))
+      ERR_5XX=$((ERR_5XX + $(awk -v cutoff="$CUTOFF" '$0 >= cutoff && /"status":5[0-9][0-9]/ {print}' "$LOG" 2>/dev/null | wc -l | tr -d ' ' || echo 0)))
+    fi
+  fi
+done
+
+if [ "$TOTAL" -gt 100 ]; then
+  RATE=$(awk "BEGIN {printf \"%.1f\", $ERR_5XX*100/$TOTAL}")
+  if [ "$(echo "$RATE > 5" | bc 2>/dev/null || echo 0)" = "1" ]; then
+    echo "{\"health\":\"degraded\",\"signalKind\":\"caddy-errors\",\"evidence\":\"${RATE}% 5xx rate ($ERR_5XX/$TOTAL)\",\"metrics\":{\"caddy_5xx_rate\":$RATE,\"caddy_requests\":$TOTAL,\"caddy_5xx\":$ERR_5XX}}"
+    exit 0
+  fi
+  echo "{\"health\":\"healthy\",\"metrics\":{\"caddy_5xx_rate\":$RATE,\"caddy_requests\":$TOTAL,\"caddy_5xx\":$ERR_5XX}}"
+else
+  echo '{"health":"healthy"}'
+fi

checks/cpu_check.sh

@@ -0,0 +1,20 @@
+#!/usr/bin/env bash
+# cpu_check.sh — CPU usage % and thermal temperature.
+set -euo pipefail
+
+USAGE=$(top -bn1 2>/dev/null | awk '/^%Cpu/ {print 100 - $8}' || true)
+if [ -z "$USAGE" ]; then
+  CORES=$(nproc 2>/dev/null || sysctl -n hw.ncpu 2>/dev/null || echo 1)
+  USAGE=$(awk -v cores="$CORES" '{print ($1+$2+$3)*100/cores}' /proc/loadavg 2>/dev/null || echo "0")
+fi
+
+TEMP=""
+if [ -f /sys/class/thermal/thermal_zone0/temp ]; then
+  TEMP=$(awk '{printf "%.1f", $1/1000}' /sys/class/thermal/thermal_zone0/temp 2>/dev/null || true)
+fi
+
+if [ -n "$TEMP" ]; then
+  echo "{\"health\":\"healthy\",\"metrics\":{\"cpu_pct\":$USAGE,\"cpu_temp\":$TEMP}}"
+else
+  echo "{\"health\":\"healthy\",\"metrics\":{\"cpu_pct\":$USAGE}}"
+fi

checks/disk_smart_check.sh

@@ -0,0 +1,29 @@
+#!/usr/bin/env bash
+# disk_smart_check.sh — SMART pre-failure indicators for physical disks.
+set -euo pipefail
+
+if ! command -v smartctl >/dev/null 2>&1; then
+  echo '{"health":"healthy"}'
+  exit 0
+fi
+
+DISKS=$(lsblk -ndo NAME,TYPE 2>/dev/null | awk '$2=="disk"{print "/dev/"$1}' || true)
+if [ -z "$DISKS" ]; then
+  echo '{"health":"healthy"}'
+  exit 0
+fi
+
+FAILED=""
+for dev in $DISKS; do
+  INFO=$(smartctl -H "$dev" 2>/dev/null || true)
+  if ! echo "$INFO" | grep -q "PASSED\|OK"; then
+    MODEL=$(smartctl -i "$dev" 2>/dev/null | awk -F': ' '/Device Model|Product/{print $2; exit}' || echo "$dev")
+    FAILED="$FAILED $MODEL"
+  fi
+done
+
+if [ -n "$FAILED" ]; then
+  echo "{\"health\":\"degraded\",\"signalKind\":\"disk-smart-fail\",\"evidence\":\"SMART check failed for:$(echo "$FAILED" | sed 's/ /, /g')\"}"
+else
+  echo '{"health":"healthy"}'
+fi

checks/disk_usage_check.sh

@@ -0,0 +1,26 @@
+#!/usr/bin/env bash
+# disk_usage_check.sh — disk usage and inode usage per mountpoint.
+set -euo pipefail
+
+MOUNTS=$(df -k 2>/dev/null | awk 'NR>1 && $1 ~ /^\// && $NF !~ /^\/(snap|dev|proc|sys|run|private)/ {print $NF}' || true)
+FIRST=1
+
+echo -n '{"health":"healthy","metrics":{'
+for m in $MOUNTS; do
+  LINE=$(df -k "$m" 2>/dev/null | awk 'NR==2 {print $3, $4, $5, $7}' | tr -d '%' || true)
+  if [ -z "$LINE" ]; then continue; fi
+  USED=$(echo "$LINE" | awk '{print $1}')
+  FREE=$(echo "$LINE" | awk '{print $2}')
+  PCT=$(echo "$LINE" | awk '{print $3}')
+
+  INODE_LINE=$(df -i "$m" 2>/dev/null | awk 'NR==2 {print $5}' | tr -d '%' || echo "0")
+  INODE_PCT=$(echo "${INODE_LINE:-0}" | sed 's/-/0/')
+
+  KEY=$(echo "$m" | sed 's|/|_|g' | sed 's|^_||')
+  [ -z "$KEY" ] && KEY="root"
+
+  if [ $FIRST -eq 0 ]; then echo -n ','; fi
+  FIRST=0
+  echo -n "\"disk_${KEY}_pct\":$PCT,\"inode_${KEY}_pct\":$INODE_PCT"
+done
+echo '}}'

checks/docker_health_check.sh

@@ -0,0 +1,19 @@
+#!/usr/bin/env bash
+# docker_health_check.sh — detect unhealthy Docker containers.
+set -euo pipefail
+
+if ! command -v docker >/dev/null 2>&1; then
+  echo '{"health":"healthy"}'
+  exit 0
+fi
+
+UNHEALTHY=$(docker ps --filter "health=unhealthy" --format "{{.Names}}" 2>/dev/null || true)
+
+if [ -n "$UNHEALTHY" ]; then
+  COUNT=$(echo "$UNHEALTHY" | wc -l | tr -d ' ')
+  NAMES=$(echo "$UNHEALTHY" | tr '\n' ',' | sed 's/,$//')
+  echo "{\"health\":\"degraded\",\"signalKind\":\"docker-unhealthy\",\"evidence\":\"$COUNT unhealthy container(s): $NAMES\",\"metrics\":{\"docker_unhealthy\":$COUNT}}"
+else
+  TOTAL=$(docker ps -q 2>/dev/null | wc -l | tr -d ' ' || echo 0)
+  echo "{\"health\":\"healthy\",\"metrics\":{\"docker_unhealthy\":0,\"docker_total\":$TOTAL}}"
+fi

checks/fd_check.sh

@@ -0,0 +1,13 @@
+#!/usr/bin/env bash
+# fd_check.sh — open file descriptor usage ratio.
+set -euo pipefail
+
+FD_PCT=0
+if [ -r /proc/sys/fs/file-nr ]; then
+  read -r ALLOC _ LIMIT < /proc/sys/fs/file-nr
+  if [ "$LIMIT" -gt 0 ]; then
+    FD_PCT=$(awk "BEGIN {printf \"%.1f\", $ALLOC*100/$LIMIT}")
+  fi
+fi
+
+echo "{\"health\":\"healthy\",\"metrics\":{\"fd_pct\":$FD_PCT}}"

checks/install.sh

@@ -0,0 +1,29 @@
+#!/usr/bin/env bash
+# install all check scripts into the canonical directory.
+# Auto-setup hook called by tools/post-pull.sh.
+set -euo pipefail
+
+CLONE_DIR="${HOMELAB_CONTEXT_DIR:-/opt/homelab}"
+CHECK_SRC="$CLONE_DIR/checks"
+CHECK_DST="${OIKOS_CHECK_DIR:-/opt/oikos/checks}"
+
+if [ ! -d "$CHECK_SRC" ]; then
+  exit 0
+fi
+
+mkdir -p "$CHECK_DST"
+
+for script in "$CHECK_SRC"/*.sh; do
+  name=$(basename "$script")
+  if [ "$name" = "install.sh" ]; then continue; fi
+  if [ -f "$CHECK_DST/$name" ]; then
+    if cmp -s "$script" "$CHECK_DST/$name"; then
+      continue
+    fi
+  fi
+  cp "$script" "$CHECK_DST/$name"
+  chmod 755 "$CHECK_DST/$name"
+  echo "[setup-checks] installed $name"
+done
+
+echo "[setup-checks] done"

checks/journal_check.sh

@@ -0,0 +1,15 @@
+#!/usr/bin/env bash
+# journal_check.sh — count journal errors in the last check interval.
+set -euo pipefail
+
+ERRORS=0
+
+if command -v journalctl >/dev/null 2>&1; then
+  ERRORS=$(journalctl -p err --since "-5min" --no-pager 2>/dev/null | wc -l | tr -d ' ' || echo 0)
+fi
+
+if [ "$ERRORS" -gt 0 ]; then
+  echo "{\"health\":\"degraded\",\"signalKind\":\"journal-errors\",\"evidence\":\"$ERRORS error entries in last 5min\",\"metrics\":{\"journal_errors\":$ERRORS}}"
+else
+  echo '{"health":"healthy","metrics":{"journal_errors":0}}'
+fi

checks/load_check.sh

@@ -0,0 +1,8 @@
+#!/usr/bin/env bash
+# load_check.sh — system load average scaled by CPU count.
+set -euo pipefail
+
+LOAD=$(awk '{print $1}' /proc/loadavg 2>/dev/null || sysctl -n vm.loadavg 2>/dev/null | awk '{print $2}' || echo "0")
+CORES=$(nproc 2>/dev/null || sysctl -n hw.ncpu 2>/dev/null || echo 1)
+
+echo "{\"health\":\"healthy\",\"metrics\":{\"load1\":$LOAD,\"cores\":$CORES}}"

checks/memory_check.sh

@@ -0,0 +1,27 @@
+#!/usr/bin/env bash
+# memory_check.sh — RAM usage percentage.
+set -euo pipefail
+
+TOTAL=1
+AVAIL=1
+
+if [ -r /proc/meminfo ]; then
+  TOTAL=$(awk '/^MemTotal:/ {printf "%d", $2}' /proc/meminfo)
+  AVAIL=$(awk '/^MemAvailable:/ {printf "%d", $2}' /proc/meminfo)
+elif [ "$(uname)" = "Darwin" ]; then
+  MEM=$(vm_stat 2>/dev/null | awk '
+    /page size/ {ps=$8}
+    /Pages free/   {free+=$NF}
+    /Pages active/ {active+=$NF}
+    /Pages wired/  {wired+=$NF}
+    END {printf "%.2f %.2f", ps*(free+active+wired)/1048576, ps*wired/1048576}')
+  TOTAL=$(echo "$MEM" | awk '{printf "%.0f", $1}')
+  AVAIL=$(echo "$MEM" | awk '{printf "%.0f", $1 - $2}')
+fi
+
+if [ "$TOTAL" -eq 0 ]; then TOTAL=1; fi
+if [ "$AVAIL" -lt 0 ]; then AVAIL=0; fi
+
+USED_PCT=$(awk "BEGIN {printf \"%.1f\", (1 - $AVAIL/$TOTAL)*100}")
+
+echo "{\"health\":\"healthy\",\"metrics\":{\"mem_pct\":$USED_PCT}}"

checks/oom_check.sh

@@ -0,0 +1,17 @@
+#!/usr/bin/env bash
+# oom_check.sh — detect OOM kills since last boot.
+set -euo pipefail
+
+OOM_COUNT=0
+
+if command -v dmesg >/dev/null 2>&1; then
+  OOM_COUNT=$(dmesg 2>/dev/null | grep -ci 'out of memory\|oom-killer\|Killed process' || echo 0)
+elif command -v journalctl >/dev/null 2>&1; then
+  OOM_COUNT=$(journalctl -k --no-pager 2>/dev/null | grep -ci 'out of memory\|oom-killer\|Killed process' || echo 0)
+fi
+
+if [ "$OOM_COUNT" -gt 0 ]; then
+  echo "{\"health\":\"degraded\",\"signalKind\":\"oom-kills\",\"evidence\":\"$OOM_COUNT OOM events detected since boot\",\"metrics\":{\"oom_count\":$OOM_COUNT}}"
+else
+  echo '{"health":"healthy","metrics":{"oom_count":0}}'
+fi

checks/process_check.sh

@@ -0,0 +1,22 @@
+#!/usr/bin/env bash
+# process_check.sh — systemd service liveness.
+set -euo pipefail
+
+SERVICE="${1:-}"
+if [ -z "$SERVICE" ]; then
+  echo '{"health":"unknown","signalKind":"process-check","evidence":"no service name provided"}'
+  exit 0
+fi
+
+if ! command -v systemctl >/dev/null 2>&1; then
+  echo '{"health":"unknown","signalKind":"process-check","evidence":"systemctl not found"}'
+  exit 0
+fi
+
+STATE=$(systemctl is-active "$SERVICE" 2>/dev/null || echo "unknown")
+
+if [ "$STATE" = "active" ]; then
+  echo "{\"health\":\"healthy\"}"
+else
+  echo "{\"health\":\"degraded\",\"signalKind\":\"$SERVICE\",\"evidence\":\"$SERVICE is $STATE\"}"
+fi

checks/swap_check.sh

@@ -0,0 +1,22 @@
+#!/usr/bin/env bash
+# swap_check.sh — swap usage percentage.
+set -euo pipefail
+
+if [ -r /proc/meminfo ]; then
+  SWAP_TOTAL=$(awk '/^SwapTotal:/ {printf "%d", $2}' /proc/meminfo)
+  SWAP_FREE=$(awk '/^SwapFree:/ {printf "%d", $2}' /proc/meminfo)
+elif [ "$(uname)" = "Darwin" ]; then
+  SP=$(sysctl vm.swapusage 2>/dev/null | awk '{print $4, $9}' | tr -d 'M' || echo "0 0")
+  SWAP_TOTAL=$(echo "$SP" | awk '{printf "%.0f", $1*1024}')
+  SWAP_FREE=$(echo "$SP" | awk '{printf "%.0f", ($1-$2)*1024}')
+else
+  SWAP_TOTAL=0
+  SWAP_FREE=0
+fi
+
+if [ "$SWAP_TOTAL" -eq 0 ]; then
+  echo "{\"health\":\"healthy\",\"metrics\":{\"swap_pct\":0}}"
+else
+  USED_PCT=$(awk "BEGIN {printf \"%.1f\", (1 - $SWAP_FREE/$SWAP_TOTAL)*100}")
+  echo "{\"health\":\"healthy\",\"metrics\":{\"swap_pct\":$USED_PCT}}"
+fi

checks/time_check.sh

@@ -0,0 +1,26 @@
+#!/usr/bin/env bash
+# time_check.sh — NTP synchronization status and clock drift.
+set -euo pipefail
+
+DRIFT_S=0
+SYNCED=true
+
+if command -v chronyc >/dev/null 2>&1; then
+  TRACKING=$(chronyc tracking 2>/dev/null || true)
+  DRIFT_NS=$(echo "$TRACKING" | awk '/System time/ {print $4}' | sed 's/-//' || echo "0")
+  DRIFT_S=$(awk "BEGIN {printf \"%.6f\", $DRIFT_NS/1e9}")
+  # chronyc returns a very small value when synced (nanoseconds)
+elif command -v timedatectl >/dev/null 2>&1; then
+  STATUS=$(timedatectl show 2>/dev/null || true)
+  if echo "$STATUS" | grep -q "NTPSynchronized=no"; then
+    SYNCED=false
+  fi
+fi
+
+if ! $SYNCED; then
+  echo '{"health":"degraded","signalKind":"time-drift","evidence":"NTP not synchronized"}'
+elif [ "$(echo "$DRIFT_S > 1" | bc 2>/dev/null || echo 0)" = "1" ]; then
+  echo "{\"health\":\"degraded\",\"signalKind\":\"time-drift\",\"evidence\":\"clock drift ${DRIFT_S}s exceeds 1s threshold\",\"metrics\":{\"clock_drift_s\":$DRIFT_S}}"
+else
+  echo "{\"health\":\"healthy\",\"metrics\":{\"clock_drift_s\":$DRIFT_S}}"
+fi

checks/updates_check.sh

@@ -0,0 +1,17 @@
+#!/usr/bin/env bash
+# updates_check.sh — pending apt security updates and reboot-required flag.
+set -euo pipefail
+
+SECURITY=0
+REBOOT=0
+
+if command -v apt >/dev/null 2>&1; then
+  apt update -qq >/dev/null 2>&1 || true
+  SECURITY=$(apt list --upgradable 2>/dev/null | grep -c '\-security' || true)
+fi
+
+if [ -f /var/run/reboot-required ]; then
+  REBOOT=1
+fi
+
+echo "{\"health\":\"healthy\",\"metrics\":{\"security_updates\":$SECURITY,\"reboot_required\":$REBOOT}}"

checks/uptime_check.sh

@@ -0,0 +1,7 @@
+#!/usr/bin/env bash
+# uptime_check.sh — detect unexpected reboots by monitoring uptime.
+set -euo pipefail
+
+UPTIME=$(awk '{printf "%.0f", $1}' /proc/uptime 2>/dev/null || sysctl -n kern.boottime 2>/dev/null | awk '{print $4}' | tr -d ',' || echo "0")
+
+echo "{\"health\":\"healthy\",\"metrics\":{\"uptime_seconds\":$UPTIME}}"

checks/zfs_check.sh

@@ -0,0 +1,29 @@
+#!/usr/bin/env bash
+# zfs_check.sh — ZFS pool health.
+set -euo pipefail
+
+if ! command -v zpool >/dev/null 2>&1; then
+  echo '{"health":"healthy"}'
+  exit 0
+fi
+
+STATUS=$(zpool status -x 2>&1 || true)
+SCRUB_OVERDUE=""
+
+if echo "$STATUS" | grep -q "all pools are healthy"; then
+  for pool in $(zpool list -Ho name 2>/dev/null || true); do
+    LAST=$(zpool status "$pool" 2>/dev/null | awk '/scan:/{print $0}' || true)
+    if [ -z "$LAST" ] || echo "$LAST" | grep -q "scrub repaired"; then
+      SCRUB_OVERDUE="$pool"
+      break
+    fi
+  done
+  if [ -n "$SCRUB_OVERDUE" ]; then
+    echo "{\"health\":\"degraded\",\"signalKind\":\"zfs-scrub-overdue\",\"evidence\":\"pool $SCRUB_OVERDUE scrub has errors or is overdue\"}"
+  else
+    echo '{"health":"healthy"}'
+  fi
+else
+  HEALTH=$(echo "$STATUS" | grep "state:" | awk '{print $2}' | head -1)
+  echo "{\"health\":\"degraded\",\"signalKind\":\"zfs-degraded\",\"evidence\":\"pool state: $HEALTH\"}"
+fi

cmd/nomos/agent.go

@@ -108,11 +108,16 @@ func (a *agent) chat(ctx context.Context, sessionID, message string, emit func(a
 	// Rebuild conversation context from persisted history so sessions are
 	// multi-turn. The current user turn is saved by the HTTP handler before
 	// this runs, so it is already included in the history for real sessions.
-	// Intermediate tool_use/tool_result pairs are not replayed (their ids
-	// must match exactly or the API rejects them); prior final answers carry
-	// the salient context. Ephemeral sessions (no store) fall back to the
-	// single incoming message.
-	messages := []openai.ChatCompletionMessageParamUnion{openai.SystemMessage(a.system)}
+	// Prior tool_use/tool_result pairs are replayed as a tool-calling
+	// assistant message followed by matching tool-role results, so the agent
+	// starts each turn already knowing what it already checked instead of
+	// re-querying the same tools from scratch. Ephemeral sessions (no store)
+	// fall back to the single incoming message.
+	system := a.system
+	if snapshot := a.fleetSnapshot(); snapshot != "" {
+		system += "\n\n" + snapshot
+	}
+	messages := []openai.ChatCompletionMessageParamUnion{openai.SystemMessage(system)}
 	history, _ := a.store.getMessages(ctx, sessionID)
 	for _, m := range history {
 		text := extractText(m.Content)
@@ -120,6 +125,12 @@ func (a *agent) chat(ctx context.Context, sessionID, message string, emit func(a
 		case "user":
 			messages = append(messages, openai.UserMessage(text))
 		case "assistant":
+			if calls := extractToolCalls(m.Content); len(calls) > 0 {
+				messages = append(messages, assistantToolCallMessage(calls))
+				for _, c := range calls {
+					messages = append(messages, openai.ToolMessage(c.resultText(), c.id))
+				}
+			}
 			if text != "" {
 				messages = append(messages, openai.AssistantMessage(text))
 			}
@@ -243,6 +254,140 @@ func extractText(content json.RawMessage) string {
 	return m.Text
 }
 
+// persistedCall is one merged tool_use+tool_result pair from a persisted
+// assistant message's tool_calls array. The store keeps them as two entries
+// sharing the same id (mirroring the SSE event pair); replay needs one
+// entry per id to build a valid tool-calling assistant message.
+type persistedCall struct {
+	id     string
+	name   string
+	args   json.RawMessage
+	result json.RawMessage
+	errMsg string
+}
+
+func (c persistedCall) resultText() string {
+	if c.errMsg != "" {
+		return c.errMsg
+	}
+	if len(c.result) > 0 {
+		return string(c.result)
+	}
+	return "null"
+}
+
+// extractToolCalls parses and merges a persisted message's tool_calls array,
+// preserving first-seen order across ids.
+func extractToolCalls(content json.RawMessage) []persistedCall {
+	var m struct {
+		ToolCalls []struct {
+			ID     string          `json:"id"`
+			Type   string          `json:"type"`
+			Name   string          `json:"name"`
+			Args   json.RawMessage `json:"args"`
+			Result json.RawMessage `json:"result"`
+			Error  string          `json:"error"`
+		} `json:"tool_calls"`
+	}
+	if err := json.Unmarshal(content, &m); err != nil || len(m.ToolCalls) == 0 {
+		return nil
+	}
+
+	byID := make(map[string]*persistedCall, len(m.ToolCalls))
+	var order []string
+	for _, tc := range m.ToolCalls {
+		if tc.ID == "" {
+			continue
+		}
+		pc, ok := byID[tc.ID]
+		if !ok {
+			pc = &persistedCall{id: tc.ID}
+			byID[tc.ID] = pc
+			order = append(order, tc.ID)
+		}
+		if tc.Name != "" {
+			pc.name = tc.Name
+		}
+		if len(tc.Args) > 0 && string(tc.Args) != "null" {
+			pc.args = tc.Args
+		}
+		if tc.Type == "tool_result" {
+			pc.errMsg = tc.Error
+			pc.result = tc.Result
+		}
+	}
+
+	calls := make([]persistedCall, 0, len(order))
+	for _, id := range order {
+		calls = append(calls, *byID[id])
+	}
+	return calls
+}
+
+// assistantToolCallMessage builds the tool-calling assistant message that
+// must precede the tool-role results being replayed.
+func assistantToolCallMessage(calls []persistedCall) openai.ChatCompletionMessageParamUnion {
+	toolCalls := make([]openai.ChatCompletionMessageToolCallParam, 0, len(calls))
+	for _, c := range calls {
+		args := string(c.args)
+		if args == "" {
+			args = "{}"
+		}
+		toolCalls = append(toolCalls, openai.ChatCompletionMessageToolCallParam{
+			ID: c.id,
+			Function: openai.ChatCompletionMessageToolCallFunctionParam{
+				Name:      c.name,
+				Arguments: args,
+			},
+		})
+	}
+	return openai.ChatCompletionMessageParamUnion{
+		OfAssistant: &openai.ChatCompletionAssistantMessageParam{ToolCalls: toolCalls},
+	}
+}
+
+// fleetSnapshot returns a compact, current-as-of-now fleet health line for
+// the system prompt so the agent starts each turn already oriented instead
+// of spending its first iteration rediscovering topology it already has
+// tools to query. Best-effort: an empty string on any failure just means no
+// snapshot, not an error for the turn.
+func (a *agent) fleetSnapshot() string {
+	result, err := a.client.callTool("get_health_summary", map[string]any{})
+	if err != nil {
+		return ""
+	}
+	rows, ok := result.([]any)
+	if !ok {
+		return ""
+	}
+
+	counts := map[string]int{}
+	var attention []string
+	for _, r := range rows {
+		row, ok := r.(map[string]any)
+		if !ok {
+			continue
+		}
+		health, _ := row["health"].(string)
+		counts[health]++
+		if health != "healthy" && health != "" {
+			if slug, ok := row["slug"].(string); ok && len(attention) < 10 {
+				attention = append(attention, fmt.Sprintf("%s(%s)", slug, health))
+			}
+		}
+	}
+	if len(counts) == 0 {
+		return ""
+	}
+
+	summary := fmt.Sprintf("Current fleet snapshot (as of now): healthy=%d degraded=%d down=%d stale=%d unknown=%d.",
+		counts["healthy"], counts["degraded"], counts["down"], counts["stale"], counts["unknown"])
+	if len(attention) > 0 {
+		summary += " Needs attention: " + fmt.Sprintf("%v", attention) + "."
+	}
+	return summary
+}
+
 func (a *agent) buildTools() ([]openai.ChatCompletionToolParam, error) {
 	defs, err := a.client.listToolsFull()
 	if err != nil {

cmd/nomos/main.go

@@ -5,6 +5,7 @@ import (
 	"bytes"
 	"context"
 	"encoding/json"
+	"errors"
 	"fmt"
 	"log/slog"
 	"net/http"
@@ -351,9 +352,51 @@ type mcpJSONRPCResponse struct {
 	Error     json.RawMessage `json:"error"`
 }
 
+// errStaleSession signals that the MCP server rejected our session id (e.g.
+// after an api/MCP restart), so the client should re-initialize and retry.
+var errStaleSession = fmt.Errorf("mcp session stale")
+
+// doRequest serializes MCP calls and transparently re-initializes the session
+// if the server has forgotten it (common after an api redeploy), retrying the
+// original call once. Without this, an api restart permanently breaks nomos
+// until it is itself restarted.
 func (c *mcpClient) doRequest(method string, params map[string]any) (*mcpJSONRPCResponse, error) {
 	c.mu.Lock()
 	defer c.mu.Unlock()
+
+	resp, err := c.send(method, params)
+	if err != nil && method != "initialize" && errors.Is(err, errStaleSession) {
+		slog.Warn("nomos: mcp session stale, reconnecting")
+		if rerr := c.reconnectLocked(); rerr != nil {
+			return nil, fmt.Errorf("mcp reconnect: %w (original: %v)", rerr, err)
+		}
+		return c.send(method, params)
+	}
+	return resp, err
+}
+
+// reconnectLocked re-initializes the MCP session. The caller must hold c.mu.
+func (c *mcpClient) reconnectLocked() error {
+	c.sessionID = ""
+	resp, err := c.send("initialize", map[string]any{
+		"protocolVersion": "2024-11-05",
+		"capabilities":    map[string]any{},
+		"clientInfo":      map[string]any{"name": "nomos", "version": "2.0"},
+	})
+	if err != nil {
+		return err
+	}
+	if resp.sessionID == "" {
+		return fmt.Errorf("no session ID on re-initialize")
+	}
+	c.sessionID = resp.sessionID
+	_, _ = c.send("notifications/initialized", map[string]any{})
+	slog.Info("nomos: mcp reconnected", "session", c.sessionID[:16]+"...")
+	return nil
+}
+
+// send performs one MCP round-trip. It does not lock; callers hold c.mu.
+func (c *mcpClient) send(method string, params map[string]any) (*mcpJSONRPCResponse, error) {
 	c.nextID++
 	body, _ := json.Marshal(map[string]any{
 		"jsonrpc": "2.0",
@@ -378,13 +421,21 @@ func (c *mcpClient) doRequest(method string, params map[string]any) (*mcpJSONRPC
 	}
 	defer resp.Body.Close()
 
+	// A rejected/unknown session comes back as 4xx (commonly 400/404).
+	if resp.StatusCode == http.StatusNotFound || resp.StatusCode == http.StatusBadRequest {
+		return nil, errStaleSession
+	}
+
 	result := &mcpJSONRPCResponse{}
 	result.sessionID = resp.Header.Get("Mcp-Session-Id")
 
 	scanner := bufio.NewScanner(resp.Body)
+	scanner.Buffer(make([]byte, 0, 64*1024), 4*1024*1024)
+	gotData := false
 	for scanner.Scan() {
 		line := scanner.Text()
 		if strings.HasPrefix(line, "data: ") {
+			gotData = true
 			data := line[6:]
 			if err := json.Unmarshal([]byte(data), result); err != nil {
 				return nil, fmt.Errorf("parse response: %w", err)
@@ -396,6 +447,12 @@ func (c *mcpClient) doRequest(method string, params map[string]any) (*mcpJSONRPC
 		return nil, fmt.Errorf("rpc error: %s", string(result.Error))
 	}
 
+	// Empty body with no result and a session set: the server likely dropped
+	// our session. Notifications legitimately return no data, so exempt them.
+	if !gotData && result.Result == nil && method != "notifications/initialized" {
+		return nil, errStaleSession
+	}
+
 	if result.sessionID != "" {
 		c.sessionID = result.sessionID
 	}

cmd/oikos/main.go

@@ -1,14 +1,17 @@
 package main
 
 import (
+	"bytes"
 	"context"
 	"fmt"
+	"io"
 	"log/slog"
 	"net/http"
 	"os"
 	"os/signal"
 	"strings"
 	"syscall"
+	"time"
 
 	"github.com/dtoro/oikos/internal/config"
 	"github.com/dtoro/oikos/internal/db"
@@ -24,30 +27,38 @@ import (
 
 // uiHandler serves the control-room SPA from assets embedded at build time
 // (web/embed.go), with SPA fallback to index.html. Requests arrive as /ui/*;
-// the /ui prefix is stripped to index into the embedded dist/ tree.
+// the /ui prefix is stripped to index into the embedded dist/ tree. Files are
+// written via http.ServeContent (not http.FileServer) to avoid its
+// index.html -> "./" canonical redirect, which loops for /ui/.
 func uiHandler() http.Handler {
 	dist, err := web.DistFS()
 	if err != nil {
 		slog.Warn("ui: embedded assets unavailable", "error", err)
 		return http.NotFoundHandler()
 	}
-	fileServer := http.FileServer(http.FS(dist))
-	return http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-		path := strings.TrimPrefix(strings.TrimPrefix(r.URL.Path, "/ui"), "/")
-		if path == "" {
-			path = "index.html"
+	serve := func(w http.ResponseWriter, r *http.Request, name string) bool {
+		f, err := dist.Open(name)
+		if err != nil {
+			return false
 		}
-		if f, err := dist.Open(path); err == nil {
-			f.Close()
-			r.URL.Path = "/" + path
-			fileServer.ServeHTTP(w, r)
+		defer f.Close()
+		data, err := io.ReadAll(f)
+		if err != nil {
+			return false
+		}
+		http.ServeContent(w, r, name, time.Time{}, bytes.NewReader(data))
+		return true
+	}
+	return http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		name := strings.TrimPrefix(strings.TrimPrefix(r.URL.Path, "/ui"), "/")
+		if name == "" {
+			name = "index.html"
+		}
+		if serve(w, r, name) {
 			return
 		}
 		// SPA fallback: serve index.html for unknown client-side routes.
-		if f, err := dist.Open("index.html"); err == nil {
-			f.Close()
-			r.URL.Path = "/index.html"
-			fileServer.ServeHTTP(w, r)
+		if serve(w, r, "index.html") {
 			return
 		}
 		http.NotFound(w, r)

compose/oikos/Dockerfile

@@ -23,8 +23,10 @@ COPY --from=ui-builder /web/dist ./web/dist
 
 RUN CGO_ENABLED=0 go build -o /oikos -tags timetzdata -ldflags="-s -w" ./cmd/oikos
 
-# --- Runtime: distroless static ---
-FROM gcr.io/distroless/static:nonroot
+# --- Runtime: alpine with SSH + ping for scheduler checks ---
+FROM alpine:3.21
+
+RUN apk add --no-cache ca-certificates openssh-client-default
 
 COPY --from=builder /oikos /oikos
 COPY --from=builder /build/seeds /seeds

docker-compose.yml

@@ -83,6 +83,12 @@ services:
       OIKOS_DATABASE_URL: postgres://oikos:${OIKOS_DB_PASSWORD:-oikos_dev}@postgres:5432/oikos?sslmode=disable
       OIKOS_DEBUG: "true"
       OIKOS_SCHEDULER_INTERVAL: "30s"
+      OIKOS_SSH_KEY_PATH: /etc/oikos/ssh_key
+      OIKOS_SSH_USER: root
+    volumes:
+      - ${OIKOS_SSH_KEY_PATH:-~/.ssh/id_ed25519}:/etc/oikos/ssh_key:ro
+    cap_add:
+      - NET_RAW
     command: ["scheduler"]
     stop_signal: SIGTERM
     stop_grace_period: 30s

docs/adr/0013-signal-triggers.md

@@ -0,0 +1,197 @@
+# Signal Trigger Architecture
+
+## Overview
+
+When Nomos is asked "what are the thermals of hubris?", here is exactly what happens:
+
+```mermaid
+sequenceDiagram
+    participant N as Nomos (Agent)
+    participant A as Oikos API
+    participant S as Scheduler (Docker)
+    participant H as Hubris (Proxmox)
+    participant T as TimescaleDB
+
+    Note over S,H: Every 60s (autonomous loop)
+    S->>H: SSH exec /opt/oikos/checks/cpu_check.sh
+    H-->>S: {"health":"ok","metrics":{"cpu_pct":2.5,"cpu_temp":48}}
+    S->>T: INSERT metric_samples (cpu_pct, cpu_temp)
+    S->>T: UPSERT entity_status (health)
+    alt unhealthy
+        S->>T: UPSERT signal (dedup by target+kind)
+    end
+
+    Note over N,T: User asks "what are the thermals of hubris?"
+    N->>A: MCP query_metrics(metric=["cpu_pct","cpu_temp"])
+    A->>T: SELECT time_bucket(…) FROM metric_samples
+    T-->>A: cpu_pct=15%, cpu_temp=48°C
+    A-->>N: {avg, min, max} per bucket
+```
+
+## Two Paths
+
+### Path A — Autonomous Collection (Scheduler)
+
+1. Operator creates a check via REST API: `POST /api/v1/checks`
+2. Scheduler loads enabled checks every 30s from `check_defs` table
+3. For `ssh-script` checks, scheduler SSHs to target host and runs `/opt/oikos/checks/<script>.sh`
+4. Script returns JSON with `health`, `signalKind`, `evidence`, and `metrics`
+5. Metrics written to TimescaleDB `metric_samples` table **every cycle** (healthy or not)
+6. If unhealthy: a signal is raised (deduplicated by target_entity_id + kind)
+7. If healthy again: the signal is auto-resolved, entity_status health updated
+8. All state changes emit SSE events for real-time UI updates
+
+### Path B — Query (Nomos via MCP)
+
+1. Nomos calls `query_metrics(metric=["cpu_pct","cpu_temp"])` MCP tool
+2. API runs time-bucketed aggregation over `metric_samples`
+3. Returns latest readings with avg/min/max per bucket
+4. Nomos formats them and presents to the user
+
+## Check Kinds
+
+| Kind | Where it runs | Protocol | Example |
+|------|--------------|----------|---------|
+| `ping` | Scheduler container | ICMP (`ping` binary) | Reachability + latency |
+| `http` | Scheduler container | HTTP GET | Service endpoint health |
+| `tcp` | Scheduler container | TCP dial | Port open check |
+| `disk` | Scheduler container | `unix.Statfs` | Local disk usage + inodes |
+| `cert-expiry` | Scheduler container | TLS dial | Certificate days remaining |
+| `ssh-script` | Remote target via SSH | SSH exec + JSON | Any script in `/opt/oikos/checks/` |
+
+## Available Check Scripts
+
+All scripts live in `/opt/oikos/checks/` on target hosts. They output JSON:
+
+```json
+{"health":"healthy","metrics":{"cpu_pct":2.5,"cpu_temp":48.0}}
+```
+or on failure:
+```json
+{"health":"degraded","signalKind":"disk-smart-fail","evidence":"SMART failed for Samsung 990"}
+```
+
+| Script | Metrics | Signal (on failure) |
+|--------|---------|---------------------|
+| `cpu_check.sh` | `cpu_pct`, `cpu_temp` | threshold-based |
+| `memory_check.sh` | `mem_pct` | threshold-based |
+| `load_check.sh` | `load1`, `cores` | threshold-based |
+| `swap_check.sh` | `swap_pct` | threshold-based |
+| `disk_usage_check.sh` | `disk_*_pct`, `inode_*_pct` | threshold-based |
+| `disk_smart_check.sh` | — | `disk-smart-fail` |
+| `updates_check.sh` | `security_updates`, `reboot_required` | threshold-based |
+| `zfs_check.sh` | — | `zfs-degraded`, `zfs-scrub-overdue` |
+| `process_check.sh` | — | `<service-name>` |
+| `uptime_check.sh` | `uptime_seconds` | threshold-based |
+| `oom_check.sh` | `oom_count` | `oom-kills` |
+| `journal_check.sh` | `journal_errors` | `journal-errors` |
+| `time_check.sh` | `clock_drift_s` | `time-drift` |
+| `fd_check.sh` | `fd_pct` | threshold-based |
+| `docker_health_check.sh` | `docker_unhealthy`, `docker_total` | `docker-unhealthy` |
+| `caddy_error_rate.sh` | `caddy_5xx_rate`, `caddy_requests`, `caddy_5xx` | `caddy-errors` |
+| `backup_freshness.sh` | — | `backup-stale` |
+
+## Script Deployment
+
+```mermaid
+sequenceDiagram
+    participant R as Git Repo
+    participant T as Sync Timer (5min)
+    participant H as Target Host
+
+    Note over R,T: Operator pushes scripts
+    R->>T: git pull (homelab-context)
+    T->>T: tools/post-pull.sh
+    T->>T: → tools/setup-checks.sh
+    T->>T: → checks/install.sh
+    T->>H: cp *.sh → /opt/oikos/checks/
+```
+
+## Defining a Check
+
+```bash
+curl -X POST http://oikos:8090/api/v1/checks \
+  -H 'Content-Type: application/json' \
+  -d '{
+    "kind": "ssh-script",
+    "target": "host:hubris",
+    "config": {
+      "host": "192.168.8.77",
+      "script": "cpu_check.sh",
+      "thresholds": {
+        "cpu_pct": {"warn": 90, "crit": 95},
+        "cpu_temp": {"crit": 85}
+      }
+    },
+    "interval_s": 60
+  }'
+```
+
+## Signal Lifecycle
+
+```mermaid
+stateDiagram-v2
+    [*] --> raised
+    raised --> acknowledged
+    raised --> muted: mute_until set
+    raised --> resolved: condition cleared
+
+    acknowledged --> acting: classification exists
+    acknowledged --> muted
+    acknowledged --> resolved
+
+    acting --> resolved: verification passed
+    acting --> raised: retry budget remaining
+    acting --> failed
+
+    failed --> acknowledged: operator retry
+
+    muted --> raised: mute_until expired
+
+    resolved --> [*]
+```
+
+Signals deduplicate: **one open signal per (target_entity_id, kind)**.
+Repeated failures increment `occurrence_count` instead of creating duplicates.
+
+## Threshold Evaluation
+
+Each check config can define per-metric thresholds in the `config` JSONB:
+
+```json
+{
+  "thresholds": {
+    "cpu_temp": {"crit": 85},
+    "cpu_pct": {"warn": 90, "crit": 95}
+  }
+}
+```
+
+Severity mapping:
+- metric >= `crit` → severity = `critical`
+- metric >= `warn` → severity = `warning`
+- `health == "down"` with no thresholds → severity = `critical`
+- Otherwise → severity = `warning`
+
+## Data Flow (DB Tables)
+
+```mermaid
+flowchart TD
+    CD[check_defs] -->|scheduler reads| EC[executeCheck]
+    EC -->|healthy?| RS[resolve signal + upsert entity_status]
+    EC -->|unhealthy?| US[UpsertSignal dedup by target+kind]
+    EC -->|every cycle| IM[INSERT metric_samples]
+    US --> S[signals]
+    RS --> ES[entity_status]
+    IM --> MS[(metric_samples)]
+    MS --> R1H[metric_rollups_1h continuous aggregate]
+    MS --> R1D[metric_rollups_1d continuous aggregate]
+```
+
+## Prerequisites for SSH Checks
+
+1. **Key**: SSH private key mounted at `/etc/oikos/ssh_key` in the scheduler container
+2. **User**: `OIKOS_SSH_USER=root` (or set `"user"` in check config)
+3. **Scripts**: Deployed on target host at `/opt/oikos/checks/`
+4. **Network**: Scheduler container must reach target host (bridge → LAN works)
+5. **Container**: Scheduler needs `openssh-client` (alpine base) + `CAP_NET_RAW` (for ping)

docs/adr/0014-entity-model.md

@@ -0,0 +1,613 @@
+# Oikos Entity Model — Types, Relationships & Interactions
+
+**Status:** Adopted
+**Date:** 2026-07-08
+**Scope:** Full inventory of every entity type, relationship, state machine, and
+cognition pipeline — with clear markers for what is **code-real** vs **schema-only**.
+
+---
+
+## 1. Entity Type Hierarchy (56 types)
+
+```mermaid
+graph TD
+    subgraph meta["layer: meta"]
+        entity["★ entity"]
+    end
+
+    subgraph infrastructure["layer: infrastructure"]
+        subgraph physical["domain: physical"]
+            site
+            ups
+            sensor
+            peripheral
+        end
+
+        subgraph compute["domain: compute"]
+            ce["★ compute-entity"]
+            machine["★ machine"]
+            proxmox-host
+            standalone-server
+            workstation
+            appliance
+            vm
+            container["★ container"]
+            lxc
+            docker-container
+            hypervisor
+        end
+
+        subgraph network["domain: network"]
+            net["★ network"]
+            lan
+            mesh
+            vlan
+            network-interface
+            dns-zone
+            dns-record
+            ingress-route
+            certificate
+            firewall-rule
+        end
+
+        subgraph storage["domain: storage"]
+            storage-pool
+            volume
+            backup-target
+            dataset
+        end
+
+        subgraph software["domain: software"]
+            service
+            application
+            config-repo
+            deploy-pipeline
+            package-set
+            cluster
+            compose-stack
+        end
+
+        subgraph external["domain: external"]
+            domain-registration
+            cloud-service
+            isp-link
+            vendor-dependency
+        end
+    end
+
+    subgraph governance["layer: governance"]
+        subgraph identity["domain: identity"]
+            person
+            agent
+            identity-provider
+            account
+            secret
+            key
+            access-grant
+        end
+    end
+
+    subgraph cognition["layer: cognition"]
+        check
+        signal
+        classification
+        execution
+        feedback
+        pattern
+        skill
+        approval
+        document
+        runbook
+        investigation
+    end
+
+    entity --> ce
+    entity --> machine
+    entity --> net
+    entity --> container
+    entity --> site
+    entity --> ups
+    entity --> sensor
+    entity --> peripheral
+    entity --> vm
+    entity --> hypervisor
+    entity --> network-interface
+    entity --> dns-zone
+    entity --> dns-record
+    entity --> ingress-route
+    entity --> certificate
+    entity --> firewall-rule
+    entity --> storage-pool
+    entity --> volume
+    entity --> backup-target
+    entity --> dataset
+    entity --> service
+    entity --> application
+    entity --> config-repo
+    entity --> deploy-pipeline
+    entity --> package-set
+    entity --> cluster
+    entity --> compose-stack
+    entity --> domain-registration
+    entity --> cloud-service
+    entity --> isp-link
+    entity --> vendor-dependency
+    entity --> person
+    entity --> agent
+    entity --> identity-provider
+    entity --> account
+    entity --> secret
+    entity --> key
+    entity --> access-grant
+    entity --> check
+    entity --> signal
+    entity --> classification
+    entity --> execution
+    entity --> feedback
+    entity --> pattern
+    entity --> skill
+    entity --> approval
+    entity --> document
+    entity --> runbook
+    entity --> investigation
+
+    ce --> machine
+    ce --> container
+    machine --> proxmox-host
+    machine --> standalone-server
+    machine --> workstation
+    machine --> appliance
+    container --> lxc
+    container --> docker-container
+    net --> lan
+    net --> mesh
+    net --> vlan
+```
+
+★ = abstract (cannot be instantiated; polymorphic target for relationships)
+
+### Concrete instances (88 active entities)
+
+| Type | Count | Examples |
+|------|-------|---------|
+| `lxc` | 19 | jellyfin, caddy, dns, gitea, nextcloud, matrix, arriman… |
+| `service` | 25 | caddy, authentik, dns, jellyfin, paperless, matrix… |
+| `ingress-route` | 21 | *.hubris.network |
+| `config-repo` | 6 | caddy-conf, gitea-customizations, mule-image… |
+| `proxmox-host` | 2 | hubris, strong |
+| `workstation` | 2 | mac-mini, republic-laptop |
+| `standalone-server` | 1 | netbird-vps |
+| `vm` | 2 | zimaos, haos |
+| `storage-pool` | 3 | local-lvm-hubris, library-hubris, ludo-lvm |
+| `volume` | 2 | library, media-local |
+| + sites, networks, agents, documents, destroyed… | | |
+
+---
+
+## 2. Core Sequence: Machine Onboarding
+
+```mermaid
+sequenceDiagram
+    participant O as Operator
+    participant A as Oikos API
+    participant D as DB
+    participant S as Scheduler
+    participant T as Target Machine
+
+    O->>A: POST /api/v1/entities {type:proxmox-host, slug:host:new, …}
+    A->>D: INSERT INTO entities
+    A->>A: ensureDefaultChecks().resolveHost() → lan_ip
+    A->>D: INSERT check_defs × 6 (target_id set)
+    A-->>O: 201 Created
+
+    Note over S,T: 30s scheduler tick
+    S->>D: ListEnabledCheckDefs
+    S->>T: SSH exec /opt/oikos/checks/cpu_check.sh
+    T-->>S: {"health":"ok","metrics":{"cpu_pct":2.5,"cpu_temp":48}}
+    S->>D: INSERT metric_samples
+    S->>D: UPSERT entity_status (health)
+```
+
+**What's code-real here:**
+- `CreateEntity()` at `internal/httpapi/impl.go:811` — handles POST, validates type, calls `ensureDefaultChecks()`
+- `ensureDefaultChecks()` → `internal/checkdefaults/defaults.go:144` — resolves host IP, SSH user, creates 6 check_defs rows with target_id
+- Scheduler at `internal/scheduler/scheduler.go:26` — loads `ListEnabledCheckDefs`, dispatches by kind, writes metrics + signals
+
+---
+
+## 3. Core Sequence: The OODA Loop (observe → orient → decide → act → learn)
+
+```mermaid
+flowchart TB
+    subgraph OBSERVE["🔍 OBSERVE (Scheduler every 30s)"]
+        direction TB
+        S1["ListEnabledCheckDefs"]
+        S2["ping → exec.Command(ping, host)"]
+        S3["http → http.Get(url)"]
+        S4["tcp → net.DialTimeout(tcp, addr)"]
+        S5["disk → unix.Statfs(path)"]
+        S6["cert-expiry → tls.Dial + cert.NotAfter"]
+        S7["ssh-script → exec.Command(ssh, host, script)"]
+        S8["checkResult{health, signalKind, evidence, metrics}"]
+        S1 --> S2 & S3 & S4 & S5 & S6 & S7
+        S2 & S3 & S4 & S5 & S6 & S7 --> S8
+        S8 -->|INSERT| MS[("metric_samples")]
+        S8 -->|UPSERT| SG["signals (dedup by target+kind)"]
+        S8 -->|UPSERT| ES["entity_status (health)"]
+    end
+
+    subgraph ORIENT["🧭 ORIENT (Classification)"]
+        direction TB
+        C1["policy.ClassifySignal(signal, entity, blast_radius)"]
+        C2["read_only → route: auto_act"]
+        C3["reversible_low → route: auto_act"]
+        C4["config_mutation → route: escalate"]
+        C5["destructive → route: hold"]
+        C1 --> C2 & C3 & C4 & C5
+    end
+
+    subgraph DECIDE["⚖️ DECIDE (Approval Gate)"]
+        direction TB
+        D1["auto_act → execute immediately"]
+        D2["escalate → INSERT approval (pending)"]
+        D3["notifier → Matrix alert + HMAC token"]
+        D4["operator replies ✅ or ❌"]
+        D5["hold → queued, never auto-executed"]
+        D2 --> D3 --> D4
+    end
+
+    subgraph ACT["⚡ ACT (Execution)"]
+        direction TB
+        A1["Nomos → MCP request_execution"]
+        A2["actuator.Execute() → SSH exec"]
+        A3["systemctl restart / apt upgrade / pct exec"]
+        A1 --> A2 --> A3
+    end
+
+    subgraph LEARN["🧠 LEARN (Patterns + Skills)"]
+        direction TB
+        L1["execution → produces → feedback"]
+        L2["feedback → contributes-to → pattern"]
+        L3["pattern → informs → skill"]
+        L1 --> L2 --> L3
+    end
+
+    SG --> ORIENT
+    ORIENT --> DECIDE
+    DECIDE --> ACT
+    ACT --> LEARN
+
+    style OBSERVE fill:#e3f2fd
+    style ORIENT fill:#fff3e0
+    style DECIDE fill:#fce4ec
+    style ACT fill:#e8f5e9
+    style LEARN fill:#f3e5f5
+```
+
+### What's code-real in the OODA loop
+
+| Phase | Table | Code | Status |
+|-------|-------|------|--------|
+| Observe | `check_defs`, `metric_samples` | `scheduler.go:26-215` | ✅ fully wired, 6 probe kinds |
+| Observe → Orient | `signals` | `scheduler.go:130-141` (UpsertSignal) | ✅ dedup, severity, events |
+| Orient | `classifications` | `policy/classify.go` (function exists) | ⚠ function defined but scheduler never calls it |
+| Decide | `approvals` | `server.go:311-367` (request_execution) | ✅ escalation gate works |
+| Act | `executions` | `actuator/exec.go` (SSH exec) | ✅ systemctl, apt, pct |
+| Learn | `feedback`, `patterns`, `skills` | tables + list endpoints only | ⚠ schema only, no write path |
+
+---
+
+## 4. Relationship Types — The Edge Catalog (34 edges)
+
+### Infrastructure Topology
+
+```mermaid
+graph LR
+    HH["host:hubris"] -->|hosts| LX1["lxc:jellyfin"]
+    HH -->|hosts| LX2["lxc:caddy"]
+    HH -->|hosts| LX3["lxc:dns"]
+    HH -->|hosts| LX4["lxc:gitea"]
+    HH -->|hosts| LX5["lxc:…"]
+    HS["host:strong"] -->|hosts| LX6["lxc:jellyfin"]
+    HS -->|hosts| LX7["lxc:arriman"]
+    HH -->|member-of| CL["cluster:homelab"]
+    HS -->|member-of| CL
+    LX2 -->|provides| SV1["service:caddy"]
+    LX4 -->|provides| SV2["service:gitea"]
+    LX3 -->|provides| SV3["service:dns"]
+    HH -->|mounts| VL["volume:library"]
+    HH -->|stores-on| PL["pool:library-hubris"]
+```
+
+### Network
+
+```mermaid
+graph LR
+    IG["ingress:paperless.hubris.network"] -->|routes-to| SP["service:paperless"]
+    IG -->|secured-by| IDP["idp:authentik"]
+    IG -->|uses-certificate| CRT["cert:*.hubris.network"]
+    SJ["service:jellyfin"] -->|authenticates-via| IDP
+    DNS["dns:paperless"] -->|in-zone| ZN["zone:hubris.network"]
+    DNS -->|resolves-to| LX["lxc:caddy"]
+    HH["host:hubris"] -->|connects-via| LL["lan:lab"]
+    HS["host:strong"] -->|connects-via| LH["lan:household"]
+```
+
+### Service Dependencies (feeds blast_radius CTE)
+
+```mermaid
+graph LR
+    JF["service:jellyfin"] -->|depends-on| AK["service:authentik"]
+    PP["service:paperless"] -->|depends-on| AK
+    AR["service:arr-stack"] -->|depends-on| JF
+    AK -->|depends-on| CD["service:caddy"]
+    AK -->|depends-on| DNS["service:dns"]
+```
+
+### Cognition (OODA edges)
+
+```mermaid
+graph LR
+    CK["check:ssh-script:d419257d"] -->|checks| HH["host:hubris"]
+    CK -->|raises| SG["signal:cpu-pressure"]
+    SG -->|about| HH
+    CL["classification:xyz"] -->|classifies| SG
+    CL -->|precedes| EX["execution:restart-xyz"]
+    EX -->|targets| HH
+    EX -->|performs| AG["agent:nomos"]
+```
+
+### Governance
+
+```mermaid
+graph LR
+    DT["person:dtoro"] -->|owns| NO["agent:nomos"]
+    DT -->|decides| AP["approval:xyz"]
+    AK["idp:authentik"] -->|authenticates| DT
+```
+
+---
+
+## 5. Lifecycle State Machines
+
+### Infrastructure (15 concrete types use this)
+
+```mermaid
+stateDiagram-v2
+    [*] --> planned
+    planned --> provisioning
+    planned --> destroyed: cancelled
+
+    provisioning --> active
+    provisioning --> failed
+
+    active --> migrating
+    active --> failed
+    active --> deprecated
+
+    migrating --> active: post-verify
+    migrating --> failed
+
+    failed --> active: recovery verified
+    failed --> deprecated: write-off
+
+    deprecated --> active: un-deprecate
+    deprecated --> destroyed
+
+    destroyed --> [*]
+```
+
+**Real precondition checks** (code in `impl.go:1494-1579`):
+| Transition | Precondition | How it's checked |
+|------------|-------------|-----------------|
+| provisioning→active | `health-check-answering` | `SELECT health FROM entity_status WHERE entity_id=$1` — must be healthy |
+| provisioning→active | `age-key-enrolled-if-needed` | Checks `attributes->>'age_pubkey'` (workstation only) |
+| provisioning→active | `mesh-joined-if-needed` | Checks `attributes->>'mesh_ip'` (workstation only) |
+| provisioning→active | `doc-page-complete` | `SELECT count(*) FROM relationships WHERE target_id=$1 AND type='documents'` |
+| deprecated→destroyed | `no-inbound-edges` | `SELECT count(*) FROM relationships WHERE target_id=$1 AND valid_to IS NULL` |
+| any → terminated | `backups-verified` | Checks flag in entity attributes |
+| any → terminated | `secrets-revoked` | Checks flag in entity attributes |
+
+**Soft preconditions** (always pass — operator-confirmed): `inventory-entry`, `ip-reserved`, `preflight-passed`, `backup-verified`, `replacement-live`, `caddy-backends-checked`, `un-deprecate-note`, etc.
+
+### Signal
+
+```mermaid
+stateDiagram-v2
+    [*] --> raised
+    raised --> acknowledged
+    raised --> muted: mute_until set
+    raised --> resolved: condition cleared
+
+    acknowledged --> acting: classification exists
+    acknowledged --> muted
+    acknowledged --> resolved
+
+    acting --> resolved: verification passed
+    acting --> raised: retry budget
+    acting --> failed
+
+    failed --> acknowledged: operator retry
+
+    muted --> raised: mute_until expired
+
+    resolved --> [*]
+```
+
+**Implemented preconditions:**
+- `raised → muted`: requires `mute_until` set (MuteSignal handler, `impl.go:615-689`)
+- `acting → resolved`: requires `verification-passed` (soft — operator confirms)
+
+**Dedup mechanism:** `UNIQUE INDEX uq_signals_open ON signals(target_entity_id, kind) WHERE state NOT IN ('resolved','failed')` — at most one open signal per (entity, kind). Repeated failures call `UpsertSignal` which increments `occurrence_count` on the existing row.
+
+### Execution
+
+```mermaid
+stateDiagram-v2
+    [*] --> proposed
+    proposed --> approved
+    proposed --> auto_approved
+    proposed --> denied
+    proposed --> expired
+
+    approved --> executing
+    auto_approved --> executing
+    expired --> [*]
+    denied --> [*]
+
+    executing --> verified
+    executing --> failed
+    executing --> timed_out
+
+    failed --> rolled_back
+    rolled_back --> verified
+    rolled_back --> rollback_failed
+
+    verified --> [*]
+    rollback_failed --> [*]
+    timed_out --> [*]
+```
+
+### Approval
+
+```mermaid
+stateDiagram-v2
+    [*] --> pending
+    pending --> approved
+    pending --> denied
+    approved --> revoked
+    approved --> expired
+
+    denied --> [*]
+    revoked --> [*]
+    expired --> [*]
+```
+
+---
+
+## 6. What's Code-Real vs Schema-Only
+
+### ✅ Fully Implemented (code exists, running in production)
+
+| Component | File(s) | What it does |
+|-----------|---------|-------------|
+| Entity CRUD | `impl.go:811-966` | Create, read, patch, list entities |
+| Lifecycle transitions | `impl.go:1494-1579` | Precondition checks + state transitions |
+| Relationship management | `seed.go` (ingest) | Create edges with `valid_from/valid_to` |
+| Client enrollment | `impl.go:1134-1236` | `POST /clients/enroll` — age keypair, Infisical, state: provisioning |
+| Check definitions | `phase3.go:265-376` | CreateCheck, ListChecks, PatchCheck |
+| Scheduler observe | `scheduler.go:26-215` | 6 probe kinds, metric_samples, signals, entity_status |
+| Signals | `scheduler.go:81-161` | UpsertSignal (dedup), ResolveSignal, severity evaluation |
+| Executions | `server.go:286-411` | request_execution MCP tool — reversible_low/config_mutation/destructive |
+| Approvals | `server.go:970-1052` | createApproval, DecideApproval → executeApprovedAction |
+| Notifier | `notifier/notifier.go` | Matrix alerts for pending approvals |
+| Patterns | `phase3.go:1100+` | ListPatterns, PatchPattern (status/quarantine) |
+| Skills | `phase3.go:1300+` | ListSkills, PatchSkill, ListSkillVersions |
+| Default checks | `checkdefaults/defaults.go` | Auto-create checks on entity creation/enrollment/seed |
+| TimescaleDB metrics | `metric_samples` table | Hypertable with 1h/1d continuous aggregates, 90-day retention |
+| Events + SSE | `events` table + pg_notify | Real-time UI updates via SSE endpoint |
+| Audit log | `audit_log` hypertable | Every mutation with actor + action |
+| Knowledge entities | `knowledge_entities` | Documents, runbooks, investigations with FTS |
+| MCP tools | `server.go` | 24 tools for observe/orient/decide/act |
+| Blast radius | `blast_radius()` fn | Recursive CTE — depends-on + hosts + routes-to edges |
+
+### ⚠ Schema Defined, Not Yet Wired (table exists, no active code path creates rows)
+
+| Component | What's Missing |
+|-----------|---------------|
+| `classifications` auto-creation | `policy.ClassifySignal()` exists but scheduler never calls it. Signals are raised but never automatically classified. |
+| `feedback` records | No code writes to the `feedback` table. Execution results are not analyzed for patterns. |
+| Pattern auto-learning | No code transitions patterns from `hypothesized → validated`. Requires `evidence-count≥5 + confidence≥0.7` but no aggregation runs. |
+| Skill execution | Skill entities carry a JSON `procedure` field but no execution engine reads or runs it. |
+| `drift` check kind | Defined in OpenAPI and `check_defs.kind` enum, but no scheduler implementation exists. |
+
+### 📋 Defined in Seeds Only (ontology.yaml references, no DB schema)
+
+| Item | Notes |
+|------|-------|
+| Relationship type `cluster` | Mentioned in inventory but not in ontology relationship_types |
+| `certificate` entity type | Referenced in `uses-certificate` edges but no concrete certificates in inventory |
+| Relationship type `powers` / `monitors` | Not defined in relationship_types |
+
+---
+
+## 7. Database Physical Schema
+
+```mermaid
+erDiagram
+    lifecycle_defs ||--o{ entity_types : "lifecycle_id FK"
+    entity_types ||--o{ entities : "type FK"
+    entity_types ||--o| entity_types : "parent_type FK (self-ref)"
+
+    entities ||--o| entity_status : "dual entity (shared PK)"
+    entities ||--o| check_defs : "dual entity (shared PK)"
+    entities ||--o| signals : "dual entity (shared PK)"
+    entities ||--o| classifications : "dual entity (shared PK)"
+    entities ||--o| executions : "dual entity (shared PK)"
+    entities ||--o| feedback : "dual entity (shared PK)"
+    entities ||--o| patterns : "dual entity (shared PK)"
+    entities ||--o| skills : "dual entity (shared PK)"
+    entities ||--o| approvals : "dual entity (shared PK)"
+    entities ||--o| knowledge_entities : "dual entity (shared PK)"
+
+    entities ||--o{ relationships : "source_id FK"
+    entities ||--o{ relationships : "target_id FK"
+
+    check_defs }o--|| entities : "target_id FK"
+    signals }o--|| entities : "target_entity_id FK"
+    executions }o--|| entities : "target_entity_id FK"
+    approvals }o--|| entities : "subject_entity_id FK"
+
+    entity_types ||--o{ relationship_types : "source_type FK"
+    entity_types ||--o{ relationship_types : "target_type FK"
+    relationship_types ||--o{ relationships : "type FK"
+
+    entity_types ||--o{ approval_rules : "entity_type FK"
+
+    signals ||--o| check_defs : "check_id FK"
+```
+
+**Key architectural patterns:**
+- **Dual entities:** `check_defs`, `signals`, `classifications`, `executions`, `feedback`, `patterns`, `skills`, `approvals`, `knowledge_entities` — all have `entity_id UUID PK REFERENCES entities(id)`. Every row is also an entity.
+- **Partial unique indexes:** `relationships` (current edges), `signals` (open signals), `patterns` (per-type action) — all use `WHERE` clauses for snapshot semantics.
+- **TimescaleDB hypertables:** `metric_samples`, `events`, `audit_log`, `agent_activity` — with continuous aggregates and retention policies.
+- **SSE fan-out:** `pg_notify('oikos_events', ...)` trigger on `events` INSERT → Go listener fan-out → SSE connections.
+
+---
+
+## 8. How Nomos Queries Thermals — End-to-End Trace
+
+```mermaid
+sequenceDiagram
+    participant U as User
+    participant N as Nomos (Agent)
+    participant A as Oikos API
+    participant T as TimescaleDB
+    participant S as Scheduler
+    participant H as Hubris
+
+    Note over S,H: Autonomous collection (every 60s)
+    S->>H: SSH exec cpu_check.sh
+    H-->>S: {"metrics":{"cpu_pct":15,"cpu_temp":48}}
+    S->>T: INSERT metric_samples (cpu_pct, cpu_temp)
+
+    Note over U,N: User asks question
+    U->>N: "what are the thermals of hubris?"
+    N->>A: MCP query_metrics(metric=["cpu_pct","cpu_temp"])
+    A->>T: SELECT time_bucket('1h', ts) … FROM metric_samples
+    T-->>A: {avg:15, min:2, max:40} (cpu_pct)
+    T-->>A: {avg:48, min:42, max:85} (cpu_temp)
+    A-->>N: time-bucketed metrics
+    N-->>U: "CPU at 15%, temp 48°C — normal range"
+```
+
+**What made this possible (chronologically):**
+1. `scheduler.go` refactored to return metrics map → `checkResult{metrics}`
+2. `ssh-script` check kind implemented → SSH exec to remote host
+3. `cpu_check.sh` deployed to hubris → returns `{"metrics":{"cpu_pct":2.5,"cpu_temp":48}}`
+4. Check created: `POST /checks {"kind":"ssh-script","target":"host:hubris","config":{"host":"192.168.8.77","script":"cpu_check.sh"}}`
+5. Fixed: `InsertMetricSample` missing `ts` column → `now()` literal
+6. Fixed: SSH port/user parsing bugs
+7. Fixed: SSH warnings polluting JSON output
+8. Scheduler loop → metrics written to TimescaleDB every 60s
+9. MCP `query_metrics` reads from TimescaleDB → Nomos gets live data

docs/adr/README.md

@@ -5,7 +5,7 @@ after acceptance — superseding decisions get a new ADR that links back.
 Statuses: proposed | accepted | superseded-by-NNNN.
 
 | ADR | Title |
-|---|---|
+|---|---|---|
 | [0001](0001-go-single-binary.md) | Go with single-binary role packaging |
 | [0002](0002-postgres-timescale-only-datastore.md) | PostgreSQL + TimescaleDB as the only datastore |
 | [0003](0003-db-native-ontology-yaml-seeds.md) | DB-native ontology with YAML seed manifests |
@@ -16,3 +16,7 @@ Statuses: proposed | accepted | superseded-by-NNNN.
 | [0008](0008-forward-only-migrations.md) | Forward-only migrations |
 | [0009](0009-sse-over-websocket.md) | SSE over WebSocket for the event stream |
 | [0010](0010-infisical-with-sops-fallback.md) | Infisical secrets with SOPS DR fallback |
+| [0011](0011-client-lifecycle-flows.md) | Client lifecycle flows — enrollment, bootstrap, sync |
+| [0012](0012-hermes-oikos-interactions.md) | Hermes–Oikos interactions — agent/OS contract |
+| [0013](0013-signal-triggers.md) | Signal triggers — host health checks via scheduler |
+| [0014](0014-entity-model.md) | Entity model — types, relationships, state machines, OODA loop |

internal/checkdefaults/defaults.go

@@ -0,0 +1,204 @@
+package checkdefaults
+
+import (
+	"context"
+	"encoding/json"
+	"fmt"
+
+	"github.com/google/uuid"
+	"github.com/jackc/pgx/v5"
+)
+
+type CheckDef struct {
+	Kind       string
+	Script     string
+	Host       string
+	User       string
+	Port       int
+	Thresholds map[string]any
+	Extra      map[string]any
+}
+
+func ResolveHost(attrs map[string]any) string {
+	if ip, ok := attrs["lan_ip"].(string); ok && ip != "" {
+		return ip
+	}
+	if mesh, ok := attrs["mesh"].(map[string]any); ok {
+		if nb, ok := mesh["netbird"].(map[string]any); ok {
+			if ip, ok := nb["ip"].(string); ok && ip != "" {
+				return ip
+			}
+		}
+	}
+	if ip, ok := attrs["mesh_ip"].(string); ok && ip != "" {
+		return ip
+	}
+	return ""
+}
+
+func resolveSSHUser(attrs map[string]any) string {
+	if ssh, ok := attrs["ssh"].(map[string]any); ok {
+		if u, ok := ssh["user"].(string); ok && u != "" {
+			return u
+		}
+	}
+	return "root"
+}
+
+func resolveSSHPort(attrs map[string]any) int {
+	if ssh, ok := attrs["ssh"].(map[string]any); ok {
+		switch p := ssh["port"].(type) {
+		case float64:
+			return int(p)
+		case int:
+			return p
+		}
+	}
+	return 22
+}
+
+func ForEntityType(entityType string, attrs map[string]any) []CheckDef {
+	host := ResolveHost(attrs)
+	user := resolveSSHUser(attrs)
+	port := resolveSSHPort(attrs)
+
+	ssh := func(script string) CheckDef {
+		return CheckDef{Kind: "ssh-script", Script: script, Host: host, User: user, Port: port}
+	}
+
+	switch entityType {
+	case "proxmox-host", "standalone-server":
+		if host == "" {
+			return nil
+		}
+		return []CheckDef{
+			{Kind: "ping", Host: host},
+			ssh("cpu_check.sh"),
+			ssh("memory_check.sh"),
+			ssh("load_check.sh"),
+			ssh("disk_usage_check.sh"),
+			ssh("updates_check.sh"),
+		}
+	case "workstation":
+		if host == "" {
+			return nil
+		}
+		return []CheckDef{
+			{Kind: "ping", Host: host},
+			ssh("cpu_check.sh"),
+			ssh("memory_check.sh"),
+			ssh("load_check.sh"),
+		}
+	case "lxc":
+		if host == "" {
+			return nil
+		}
+		return []CheckDef{
+			ssh("cpu_check.sh"),
+			ssh("memory_check.sh"),
+			ssh("load_check.sh"),
+			ssh("disk_usage_check.sh"),
+		}
+	case "vm":
+		if host == "" {
+			return nil
+		}
+		return []CheckDef{
+			{Kind: "ping", Host: host},
+		}
+	case "service":
+		if host == "" {
+			return nil
+		}
+		n, _ := attrs["name"].(string)
+		if n == "" {
+			return nil
+		}
+		return []CheckDef{
+			{Kind: "ssh-script", Script: "process_check.sh", Host: host, User: user, Port: port,
+				Extra: map[string]any{"args": n}},
+		}
+	}
+	return nil
+}
+
+func ShortSlug(slug string) string {
+	const n = 8
+	if len(slug) > n {
+		return slug[len(slug)-n:]
+	}
+	return slug
+}
+
+func DefaultInterval(kind string) int32 {
+	switch kind {
+	case "ping":
+		return 30
+	case "ssh-script":
+		return 60
+	default:
+		return 300
+	}
+}
+
+func Ensure(ctx context.Context, tx pgx.Tx, entityID uuid.UUID, slug, entityType string, attrsJSON []byte) {
+	_, _ = tx.Exec(ctx,
+		`INSERT INTO entity_status (entity_id, health, updated_at)
+		 VALUES ($1, 'unknown', now())
+		 ON CONFLICT (entity_id) DO NOTHING`,
+		entityID)
+
+	var attrs map[string]any
+	if len(attrsJSON) > 0 {
+		json.Unmarshal(attrsJSON, &attrs)
+	}
+	if attrs == nil {
+		attrs = map[string]any{}
+	}
+
+	defs := ForEntityType(entityType, attrs)
+	if len(defs) == 0 {
+		return
+	}
+
+	for i, def := range defs {
+		checkID, err := uuid.NewV7()
+		if err != nil {
+			checkID = uuid.New()
+		}
+		checkSlug := fmt.Sprintf("check:%s:%s:%d", def.Kind, ShortSlug(slug), i)
+
+		_, _ = tx.Exec(ctx,
+			`INSERT INTO entities (id, slug, type, name, state, attributes, version, created_at, updated_at)
+			 VALUES ($1, $2, 'check', $2, 'active', '{}', 1, now(), now())
+			 ON CONFLICT (slug) DO NOTHING`,
+			checkID, checkSlug)
+
+		configMap := map[string]any{}
+		if def.Script != "" {
+			configMap["script"] = def.Script
+		}
+		if def.Host != "" {
+			configMap["host"] = def.Host
+		}
+		if def.User != "" && def.User != "root" {
+			configMap["user"] = def.User
+		}
+		if def.Port != 0 && def.Port != 22 {
+			configMap["port"] = def.Port
+		}
+		if def.Thresholds != nil {
+			configMap["thresholds"] = def.Thresholds
+		}
+		for k, v := range def.Extra {
+			configMap[k] = v
+		}
+		configJSON, _ := json.Marshal(configMap)
+
+		_, _ = tx.Exec(ctx,
+			`INSERT INTO check_defs (entity_id, target_id, kind, config, interval_s, timeout_s, enabled)
+			 VALUES ($1, $2, $3, $4, $5, 30, true)
+			 ON CONFLICT (entity_id) DO NOTHING`,
+			checkID, entityID, def.Kind, configJSON, DefaultInterval(def.Kind))
+	}
+}

internal/db/queries/operations.sql

@@ -240,8 +240,8 @@ SELECT * FROM risk_classes ORDER BY name;
 SELECT * FROM approval_rules ORDER BY entity_type, action;
 
 -- name: InsertMetricSample :exec
-INSERT INTO metric_samples (entity_id, metric, value, tags)
-VALUES ($1, $2, $3, $4);
+INSERT INTO metric_samples (entity_id, metric, value, tags, ts)
+VALUES ($1, $2, $3, $4, now());
 
 -- name: QueryMetrics :many
 SELECT time_bucket(sqlc.arg('bucket_interval')::interval, ts) AS bucket,

internal/db/seed.go

@@ -6,6 +6,7 @@ import (
 	"errors"
 	"fmt"
 
+	"github.com/dtoro/oikos/internal/checkdefaults"
 	"github.com/google/uuid"
 	"github.com/jackc/pgx/v5"
 )
@@ -143,6 +144,8 @@ func IngestInventorySeed(ctx context.Context, tx pgx.Tx, data map[string]any) (*
 			return nil, fmt.Errorf("entity_status %s: %w", slug, err)
 		}
 
+		checkdefaults.Ensure(ctx, tx, entityID, slug, typeName, attrsBytes)
+
 		r.Entities++
 	}
 

internal/db/sqlcgen/models.go

@@ -26,6 +26,22 @@ type AgentActivity struct {
 	CorrelationID *string
 }
 
+type AgentMessage struct {
+	ID        uuid.UUID
+	SessionID uuid.UUID
+	Role      string
+	Content   []byte
+	CreatedAt time.Time
+}
+
+type AgentSession struct {
+	ID           uuid.UUID
+	Title        string
+	Actor        string
+	CreatedAt    time.Time
+	LastActiveAt time.Time
+}
+
 type Approval struct {
 	EntityID        uuid.UUID
 	SubjectEntityID *uuid.UUID

internal/db/sqlcgen/operations.sql.go

@@ -560,8 +560,8 @@ func (q *Queries) InsertFeedback(ctx context.Context, arg InsertFeedbackParams)
 }
 
 const insertMetricSample = `-- name: InsertMetricSample :exec
-INSERT INTO metric_samples (entity_id, metric, value, tags)
-VALUES ($1, $2, $3, $4)
+INSERT INTO metric_samples (entity_id, metric, value, tags, ts)
+VALUES ($1, $2, $3, $4, now())
 `
 
 type InsertMetricSampleParams struct {

internal/httpapi/dashboard.go

@@ -0,0 +1,172 @@
+package httpapi
+
+import (
+	"context"
+	"time"
+
+	"github.com/dtoro/oikos/internal/httpapi/gen"
+)
+
+// GetDashboardSummary returns one round-trip overview for the control room
+// home page: entity counts, health rollup, open signals, pending approvals,
+// executions in the last 24h, and an event-rate sparkline.
+func (s *Server) GetDashboardSummary(ctx context.Context, req gen.GetDashboardSummaryRequestObject) (gen.GetDashboardSummaryResponseObject, error) {
+	resp := gen.DashboardSummary{
+		EntitiesByType:    map[string]int{},
+		EntitiesByState:   map[string]int{},
+		SignalsBySeverity: map[string]int{},
+		ExecutionsByState: map[string]int{},
+	}
+
+	rows, err := s.pool.Query(ctx, `SELECT type, count(*) FROM entities GROUP BY type`)
+	if err != nil {
+		return nil, err
+	}
+	for rows.Next() {
+		var typ string
+		var n int
+		if err := rows.Scan(&typ, &n); err != nil {
+			rows.Close()
+			return nil, err
+		}
+		resp.EntitiesByType[typ] = n
+	}
+	rows.Close()
+	if err := rows.Err(); err != nil {
+		return nil, err
+	}
+
+	rows, err = s.pool.Query(ctx, `SELECT coalesce(state, 'unknown'), count(*) FROM entities GROUP BY state`)
+	if err != nil {
+		return nil, err
+	}
+	for rows.Next() {
+		var state string
+		var n int
+		if err := rows.Scan(&state, &n); err != nil {
+			rows.Close()
+			return nil, err
+		}
+		resp.EntitiesByState[state] = n
+	}
+	rows.Close()
+	if err := rows.Err(); err != nil {
+		return nil, err
+	}
+
+	// Exclude 'check' entities (internal probes) — only entities actually
+	// being monitored should count toward the fleet health rollup.
+	rows, err = s.pool.Query(ctx, `
+		SELECT st.health, count(*)
+		FROM entity_status st JOIN entities e ON e.id = st.entity_id
+		WHERE e.type <> 'check'
+		GROUP BY st.health`)
+	if err != nil {
+		return nil, err
+	}
+	stale := 0
+	for rows.Next() {
+		var health string
+		var n int
+		if err := rows.Scan(&health, &n); err != nil {
+			rows.Close()
+			return nil, err
+		}
+		switch health {
+		case "healthy":
+			resp.Health.Healthy = n
+		case "degraded":
+			resp.Health.Degraded = n
+		case "down":
+			resp.Health.Down = n
+		case "stale":
+			stale = n
+		default:
+			resp.Health.Unknown = n
+		}
+	}
+	rows.Close()
+	if err := rows.Err(); err != nil {
+		return nil, err
+	}
+	if stale > 0 {
+		resp.Health.Stale = &stale
+	}
+
+	rows, err = s.pool.Query(ctx, `
+		SELECT severity, count(*) FROM signals
+		WHERE state NOT IN ('resolved', 'failed')
+		GROUP BY severity`)
+	if err != nil {
+		return nil, err
+	}
+	for rows.Next() {
+		var severity string
+		var n int
+		if err := rows.Scan(&severity, &n); err != nil {
+			rows.Close()
+			return nil, err
+		}
+		resp.SignalsBySeverity[severity] = n
+	}
+	rows.Close()
+	if err := rows.Err(); err != nil {
+		return nil, err
+	}
+
+	if err := s.pool.QueryRow(ctx,
+		`SELECT count(*) FROM approvals WHERE status = 'pending'`,
+	).Scan(&resp.ApprovalsPending); err != nil {
+		return nil, err
+	}
+
+	rows, err = s.pool.Query(ctx, `
+		SELECT status, count(*) FROM executions
+		WHERE created_at > now() - interval '24 hours'
+		GROUP BY status`)
+	if err != nil {
+		return nil, err
+	}
+	for rows.Next() {
+		var status string
+		var n int
+		if err := rows.Scan(&status, &n); err != nil {
+			rows.Close()
+			return nil, err
+		}
+		resp.ExecutionsByState[status] = n
+	}
+	rows.Close()
+	if err := rows.Err(); err != nil {
+		return nil, err
+	}
+
+	rows, err = s.pool.Query(ctx, `
+		SELECT date_trunc('hour', ts) + (extract(minute FROM ts)::int / 5) * interval '5 minutes' AS bucket,
+		       count(*)
+		FROM events
+		WHERE ts > now() - interval '6 hours'
+		GROUP BY bucket
+		ORDER BY bucket`)
+	if err != nil {
+		return nil, err
+	}
+	for rows.Next() {
+		var bucket time.Time
+		var n int
+		if err := rows.Scan(&bucket, &n); err != nil {
+			rows.Close()
+			return nil, err
+		}
+		resp.EventRate = append(resp.EventRate, struct {
+			Bucket time.Time `json:"bucket"`
+			Count  int       `json:"count"`
+		}{Bucket: bucket, Count: n})
+	}
+	rows.Close()
+	if err := rows.Err(); err != nil {
+		return nil, err
+	}
+
+	return gen.GetDashboardSummary200JSONResponse(resp), nil
+}

internal/httpapi/default_checks.go

@@ -0,0 +1,13 @@
+package httpapi
+
+import (
+	"context"
+
+	"github.com/dtoro/oikos/internal/checkdefaults"
+	"github.com/google/uuid"
+	"github.com/jackc/pgx/v5"
+)
+
+func ensureDefaultChecks(ctx context.Context, tx pgx.Tx, entityID uuid.UUID, slug, entityType string, attrsJSON []byte) {
+	checkdefaults.Ensure(ctx, tx, entityID, slug, entityType, attrsJSON)
+}

internal/httpapi/gen/api.gen.go

@@ -81,6 +81,7 @@ const (
 	CheckKindDisk       CheckKind = "disk"
 	CheckKindDrift      CheckKind = "drift"
 	CheckKindHttp       CheckKind = "http"
+	CheckKindPing       CheckKind = "ping"
 	CheckKindSshScript  CheckKind = "ssh-script"
 	CheckKindTcp        CheckKind = "tcp"
 )
@@ -91,6 +92,7 @@ const (
 	CheckCreateKindDisk       CheckCreateKind = "disk"
 	CheckCreateKindDrift      CheckCreateKind = "drift"
 	CheckCreateKindHttp       CheckCreateKind = "http"
+	CheckCreateKindPing       CheckCreateKind = "ping"
 	CheckCreateKindSshScript  CheckCreateKind = "ssh-script"
 	CheckCreateKindTcp        CheckCreateKind = "tcp"
 )
@@ -102,6 +104,15 @@ const (
 	ClassificationRouteHold     ClassificationRoute = "hold"
 )
 
+// Defines values for EntityHealth.
+const (
+	EntityHealthDegraded EntityHealth = "degraded"
+	EntityHealthDown     EntityHealth = "down"
+	EntityHealthHealthy  EntityHealth = "healthy"
+	EntityHealthStale    EntityHealth = "stale"
+	EntityHealthUnknown  EntityHealth = "unknown"
+)
+
 // Defines values for EntityTypeLayer.
 const (
 	EntityTypeLayerCognition      EntityTypeLayer = "cognition"
@@ -153,11 +164,21 @@ const (
 	ExecutionStatusVerifying      ExecutionStatus = "verifying"
 )
 
+// Defines values for GraphViewHealth.
+const (
+	GraphViewHealthDegraded GraphViewHealth = "degraded"
+	GraphViewHealthDown     GraphViewHealth = "down"
+	GraphViewHealthHealthy  GraphViewHealth = "healthy"
+	GraphViewHealthStale    GraphViewHealth = "stale"
+	GraphViewHealthUnknown  GraphViewHealth = "unknown"
+)
+
 // Defines values for HealthSummaryEntitiesHealth.
 const (
 	HealthSummaryEntitiesHealthDegraded HealthSummaryEntitiesHealth = "degraded"
 	HealthSummaryEntitiesHealthDown     HealthSummaryEntitiesHealth = "down"
 	HealthSummaryEntitiesHealthHealthy  HealthSummaryEntitiesHealth = "healthy"
+	HealthSummaryEntitiesHealthStale    HealthSummaryEntitiesHealth = "stale"
 	HealthSummaryEntitiesHealthUnknown  HealthSummaryEntitiesHealth = "unknown"
 )
 
@@ -295,6 +316,11 @@ const (
 	Out  GetEntityRelationsParamsDirection = "out"
 )
 
+// Defines values for GetGraphParamsInclude.
+const (
+	Status GetGraphParamsInclude = "status"
+)
+
 // Defines values for QueryMetricsParamsRollup.
 const (
 	QueryMetricsParamsRollupAuto QueryMetricsParamsRollup = "auto"
@@ -520,6 +546,38 @@ type ClientSecrets struct {
 	Keys []string `json:"keys"`
 }
 
+// DashboardSummary defines model for DashboardSummary.
+type DashboardSummary struct {
+	ApprovalsPending int `json:"approvals_pending"`
+
+	// EntitiesByState entity counts keyed by state
+	EntitiesByState map[string]int `json:"entities_by_state"`
+
+	// EntitiesByType entity counts keyed by type
+	EntitiesByType map[string]int `json:"entities_by_type"`
+
+	// EventRate event counts bucketed by 5-minute interval, most recent last
+	EventRate []struct {
+		Bucket time.Time `json:"bucket"`
+		Count  int       `json:"count"`
+	} `json:"event_rate"`
+
+	// ExecutionsByState execution counts keyed by state, last 24h
+	ExecutionsByState map[string]int `json:"executions_by_state"`
+	Health            struct {
+		Degraded int `json:"degraded"`
+		Down     int `json:"down"`
+		Healthy  int `json:"healthy"`
+
+		// Stale last observation older than the check's expected cadence
+		Stale   *int `json:"stale,omitempty"`
+		Unknown int  `json:"unknown"`
+	} `json:"health"`
+
+	// SignalsBySeverity open (non-resolved) signal counts keyed by severity
+	SignalsBySeverity map[string]int `json:"signals_by_severity"`
+}
+
 // EnrollRequest defines model for EnrollRequest.
 type EnrollRequest struct {
 	// Hostname Actual hostname of the enrolling machine
@@ -552,18 +610,27 @@ type EnrollResponse struct {
 
 // Entity defines model for Entity.
 type Entity struct {
-	Attributes       *map[string]interface{} `json:"attributes,omitempty"`
-	CreatedAt        time.Time               `json:"created_at"`
-	Id               openapi_types.UUID      `json:"id"`
-	MaintenanceUntil *time.Time              `json:"maintenance_until"`
-	Name             string                  `json:"name"`
-	Slug             string                  `json:"slug"`
-	State            *string                 `json:"state"`
-	Type             string                  `json:"type"`
-	UpdatedAt        time.Time               `json:"updated_at"`
-	Version          int                     `json:"version"`
+	Attributes *map[string]interface{} `json:"attributes,omitempty"`
+	CreatedAt  time.Time               `json:"created_at"`
+
+	// Health last observed health, when the entity is monitored
+	Health *EntityHealth      `json:"health"`
+	Id     openapi_types.UUID `json:"id"`
+
+	// LastCheckAt when health was last observed
+	LastCheckAt      *time.Time `json:"last_check_at"`
+	MaintenanceUntil *time.Time `json:"maintenance_until"`
+	Name             string     `json:"name"`
+	Slug             string     `json:"slug"`
+	State            *string    `json:"state"`
+	Type             string     `json:"type"`
+	UpdatedAt        time.Time  `json:"updated_at"`
+	Version          int        `json:"version"`
 }
 
+// EntityHealth last observed health, when the entity is monitored
+type EntityHealth string
+
 // EntityCreate defines model for EntityCreate.
 type EntityCreate struct {
 	// Attributes Validated against the type's attribute_schema
@@ -696,12 +763,18 @@ type ExecutionRequest struct {
 // GraphView defines model for GraphView.
 type GraphView struct {
 	Edges []Relationship `json:"edges"`
-	Nodes []Entity       `json:"nodes"`
+
+	// Health entity id -> health, present when include=status was requested
+	Health *map[string]GraphViewHealth `json:"health,omitempty"`
+	Nodes  []Entity                    `json:"nodes"`
 
 	// Truncated True if node cap was hit
 	Truncated *bool `json:"truncated,omitempty"`
 }
 
+// GraphViewHealth defines model for GraphView.Health.
+type GraphViewHealth string
+
 // HealthSummary defines model for HealthSummary.
 type HealthSummary struct {
 	Entities []struct {
@@ -715,7 +788,10 @@ type HealthSummary struct {
 		Degraded int `json:"degraded"`
 		Down     int `json:"down"`
 		Healthy  int `json:"healthy"`
-		Unknown  int `json:"unknown"`
+
+		// Stale last observation older than the check's expected cadence
+		Stale   *int `json:"stale,omitempty"`
+		Unknown int  `json:"unknown"`
 	} `json:"summary"`
 }
 
@@ -1234,8 +1310,14 @@ type GetGraphParams struct {
 	Root    *string   `form:"root,omitempty" json:"root,omitempty"`
 	Depth   *int      `form:"depth,omitempty" json:"depth,omitempty"`
 	RelType *[]string `form:"rel_type,omitempty" json:"rel_type,omitempty"`
+
+	// Include include=status joins entity_status and populates GraphView.health
+	Include *[]GetGraphParamsInclude `form:"include,omitempty" json:"include,omitempty"`
 }
 
+// GetGraphParamsInclude defines parameters for GetGraph.
+type GetGraphParamsInclude string
+
 // SearchKnowledgeParams defines parameters for SearchKnowledge.
 type SearchKnowledgeParams struct {
 	Q     string `form:"q" json:"q"`
@@ -1469,6 +1551,9 @@ type ServerInterface interface {
 	// List secrets accessible to this client
 	// (GET /clients/{slug}/secrets)
 	GetClientSecrets(w http.ResponseWriter, r *http.Request, slug EntitySlug)
+	// One-round-trip overview for the control room home page
+	// (GET /dashboard/summary)
+	GetDashboardSummary(w http.ResponseWriter, r *http.Request)
 	// List entities
 	// (GET /entities)
 	ListEntities(w http.ResponseWriter, r *http.Request, params ListEntitiesParams)
@@ -1664,6 +1749,12 @@ func (_ Unimplemented) GetClientSecrets(w http.ResponseWriter, r *http.Request,
 	w.WriteHeader(http.StatusNotImplemented)
 }
 
+// One-round-trip overview for the control room home page
+// (GET /dashboard/summary)
+func (_ Unimplemented) GetDashboardSummary(w http.ResponseWriter, r *http.Request) {
+	w.WriteHeader(http.StatusNotImplemented)
+}
+
 // List entities
 // (GET /entities)
 func (_ Unimplemented) ListEntities(w http.ResponseWriter, r *http.Request, params ListEntitiesParams) {
@@ -2537,6 +2628,26 @@ func (siw *ServerInterfaceWrapper) GetClientSecrets(w http.ResponseWriter, r *ht
 	handler.ServeHTTP(w, r)
 }
 
+// GetDashboardSummary operation middleware
+func (siw *ServerInterfaceWrapper) GetDashboardSummary(w http.ResponseWriter, r *http.Request) {
+
+	ctx := r.Context()
+
+	ctx = context.WithValue(ctx, BearerAuthScopes, []string{})
+
+	r = r.WithContext(ctx)
+
+	handler := http.Handler(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		siw.Handler.GetDashboardSummary(w, r)
+	}))
+
+	for _, middleware := range siw.HandlerMiddlewares {
+		handler = middleware(handler)
+	}
+
+	handler.ServeHTTP(w, r)
+}
+
 // ListEntities operation middleware
 func (siw *ServerInterfaceWrapper) ListEntities(w http.ResponseWriter, r *http.Request) {
 
@@ -3305,6 +3416,14 @@ func (siw *ServerInterfaceWrapper) GetGraph(w http.ResponseWriter, r *http.Reque
 		return
 	}
 
+	// ------------- Optional query parameter "include" -------------
+
+	err = runtime.BindQueryParameter("form", true, false, "include", r.URL.Query(), &params.Include)
+	if err != nil {
+		siw.ErrorHandlerFunc(w, r, &InvalidParamFormatError{ParamName: "include", Err: err})
+		return
+	}
+
 	handler := http.Handler(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
 		siw.Handler.GetGraph(w, r, params)
 	}))
@@ -4547,6 +4666,9 @@ func HandlerWithOptions(si ServerInterface, options ChiServerOptions) http.Handl
 	r.Group(func(r chi.Router) {
 		r.Get(options.BaseURL+"/clients/{slug}/secrets", wrapper.GetClientSecrets)
 	})
+	r.Group(func(r chi.Router) {
+		r.Get(options.BaseURL+"/dashboard/summary", wrapper.GetDashboardSummary)
+	})
 	r.Group(func(r chi.Router) {
 		r.Get(options.BaseURL+"/entities", wrapper.ListEntities)
 	})
@@ -5020,6 +5142,34 @@ func (response GetClientSecretsdefaultApplicationProblemPlusJSONResponse) VisitG
 	return json.NewEncoder(w).Encode(response.Body)
 }
 
+type GetDashboardSummaryRequestObject struct {
+}
+
+type GetDashboardSummaryResponseObject interface {
+	VisitGetDashboardSummaryResponse(w http.ResponseWriter) error
+}
+
+type GetDashboardSummary200JSONResponse DashboardSummary
+
+func (response GetDashboardSummary200JSONResponse) VisitGetDashboardSummaryResponse(w http.ResponseWriter) error {
+	w.Header().Set("Content-Type", "application/json")
+	w.WriteHeader(200)
+
+	return json.NewEncoder(w).Encode(response)
+}
+
+type GetDashboardSummarydefaultApplicationProblemPlusJSONResponse struct {
+	Body       Problem
+	StatusCode int
+}
+
+func (response GetDashboardSummarydefaultApplicationProblemPlusJSONResponse) VisitGetDashboardSummaryResponse(w http.ResponseWriter) error {
+	w.Header().Set("Content-Type", "application/problem+json")
+	w.WriteHeader(response.StatusCode)
+
+	return json.NewEncoder(w).Encode(response.Body)
+}
+
 type ListEntitiesRequestObject struct {
 	Params ListEntitiesParams
 }
@@ -6401,6 +6551,9 @@ type StrictServerInterface interface {
 	// List secrets accessible to this client
 	// (GET /clients/{slug}/secrets)
 	GetClientSecrets(ctx context.Context, request GetClientSecretsRequestObject) (GetClientSecretsResponseObject, error)
+	// One-round-trip overview for the control room home page
+	// (GET /dashboard/summary)
+	GetDashboardSummary(ctx context.Context, request GetDashboardSummaryRequestObject) (GetDashboardSummaryResponseObject, error)
 	// List entities
 	// (GET /entities)
 	ListEntities(ctx context.Context, request ListEntitiesRequestObject) (ListEntitiesResponseObject, error)
@@ -6870,6 +7023,30 @@ func (sh *strictHandler) GetClientSecrets(w http.ResponseWriter, r *http.Request
 	}
 }
 
+// GetDashboardSummary operation middleware
+func (sh *strictHandler) GetDashboardSummary(w http.ResponseWriter, r *http.Request) {
+	var request GetDashboardSummaryRequestObject
+
+	handler := func(ctx context.Context, w http.ResponseWriter, r *http.Request, request interface{}) (interface{}, error) {
+		return sh.ssi.GetDashboardSummary(ctx, request.(GetDashboardSummaryRequestObject))
+	}
+	for _, middleware := range sh.middlewares {
+		handler = middleware(handler, "GetDashboardSummary")
+	}
+
+	response, err := handler(r.Context(), w, r, request)
+
+	if err != nil {
+		sh.options.ResponseErrorHandlerFunc(w, r, err)
+	} else if validResponse, ok := response.(GetDashboardSummaryResponseObject); ok {
+		if err := validResponse.VisitGetDashboardSummaryResponse(w); err != nil {
+			sh.options.ResponseErrorHandlerFunc(w, r, err)
+		}
+	} else if response != nil {
+		sh.options.ResponseErrorHandlerFunc(w, r, fmt.Errorf("unexpected response type: %T", response))
+	}
+}
+
 // ListEntities operation middleware
 func (sh *strictHandler) ListEntities(w http.ResponseWriter, r *http.Request, params ListEntitiesParams) {
 	var request ListEntitiesRequestObject
@@ -8031,166 +8208,175 @@ func (sh *strictHandler) GetTrends(w http.ResponseWriter, r *http.Request, entit
 // Base64 encoded, gzipped, json marshaled Swagger object
 var swaggerSpec = []string{
 
-	"H4sIAAAAAAAC/+x923LcuNngq6C4W5VWwlb7MPNnR75SZI3txI61lib/pkauFpr8uhsRCHAAsKWOS1W5",
-	"2gfYyhPmSbZwIEh2g2z2QZYzlRtbEkEQ+E74zvgSJTzLOQOmZHTyJZoDTkGYH8+v8Ez/n4JMBMkV4Sw6",
-	"iT6B5IVIAC1ASMIZmnKB3k2HH7BK5lEcyWQOGdbvqWUO0UkklSBsFj08PMRRjgXOQLkPnBVCcrH+iY85",
-	"/qUAlJjHaCp4hjDKBSwILyQSIHPOJPxGIgb3amyHRXFE9Lu/FCCWURwxnOmP+4fty4qjc6aIWr5L11fy",
-	"00/vXiMukKTFDA3geHaMbuZcqpN5MRFE3hyVn82xmldfJWkURwJ+KYiANDpRooA+K7ikRQDg9lljCXfy",
-	"JMPJMCOM3MToht4nJwlO02XbevS7W67oR8GzK6Lf/hIErMZKA6xTLjKsopMoxQqGSr8aB+Z9l0KWcwUs",
-	"Wf4Jluu7PaMEmBrOgIHAClJ0C8tXSEBO8VKiO6LmhKEX382RAFUIhtQcEBdkRhimnjRKKFhirhZd+/hQ",
-	"f72+/gzfvwc2U/Po5PmL/xVc+tTS+DqGrvCsIlPCBXpzfvUKfff8BeLM80lGZOZ4JLy4ioe2QdR7khHV",
-	"hiVqHtYnSGGKC6qik++fxXrPJCuy6OTFM/0bYfa35373hCmYgTAfuuJd9KD49tTwoHdqMWbkwQWwlLDZ",
-	"aZ4LvsBU/ynhTAEz+8N5TkmCNcxHf5Ma8F9qH/yfAqbRSfQ/RpU4G9mncuQnNJ9cobc5ZjNAUuEZpK8Q",
-	"RhkoPMTuDXSHJUoEGEocpAWmQ70iwelR9BBHF4JPKGQdC83tiN9tt+By3sB6z4XgAg0+/XiGfvju+9+b",
-	"ZVySGcP0p1zDOj0Y1OysoTW4LyFZjigxb7B4OgOmThNFFkQZBs8Fz0EoYpGM3ZOxpYYvETBNcz9HinM6",
-	"TjClhgGw5ExTif52QjQDRXGUJfm4pDuQCaZmX9HnNdKKI6xXMSZpgGniKOFCgH3ZDWEFpXhCoeS4tVfS",
-	"QtjxmewY7/kljsCI7b7TNxZam4WwvFBjWWQZFsteM/FCbfuKBCm3AIUskgRkFxgmnFPATA9W/BbYOOGF",
-	"JcfNcDNkYIVKj7VYpaXn2VOJ1Z/tEa1kVKOUeIU2K7Lik79BovT36rJpna4te62TmxUgY6z6LtZSfdr9",
-	"zmaadXNM+pEB3OdEgNxqmZZk/NiisHBdHXZLWFrndbiHpFCWqXNOSbIcJkYQ69+xUiDY0CCjncFzvKQc",
-	"B3Q2oyJp3HAJKbKzo5RMp+0gq/AriLwdJxRb8l4nfaehrT9QWBWyvsXcHmaaqgzNQGpkGSPmBwtrqyYu",
-	"+C2kwT3Kwi6sUyfUGpA/rxLOEhBMbiaPED84PdGRcgMaDod+pw1yaZB4F9t8KihsxTq4UJzxbDmmsABa",
-	"h69+Uh0Dhh9gASIIRyeLyxOnCcsPeIkmgPBEKoEThQaEzUEQJVHK79hRH0bryQWbiCvhOYztWrtRrk2u",
-	"HMTQjkV8AUKQFGSftTp1NHTchEgiTAsraKlm3YT8M0MnT08C++Kmm5l6AS0IqiIl6pwpsdwORIniou/x",
-	"bQeval/mFIziSH8RK2syL6WC0shLC9oC2V2UKVCY0NpWKggcRm3KQM15vymMpdxL7TFujzHJ+402YnKc",
-	"8BR66j0H0GQqzHrGDVOZJcRLUErPuEZqt9Yyh3uc5XrN0YzyCabHmoLHOFEh4VZYo2Ar7WGBaRFmx/5S",
-	"6tbY8Xambjl0Nofkdn2zCWdTEvC7/AVTYu0cLWrd6RegV43WOhnWlN+e54LemlhgOpZhal7VnuZK5Xqe",
-	"RP+bEnmrD2AQamiOZA2OVJCpsfvlfGj3FNYv2tQZhcUMNugdA8KkwiyBoRGOaa+T0k7cchK72fVDNND/",
-	"bjUzyYBrwycMww6CiqO/c9bH3OhQmRx51DBZX1FFJj0otO2IrOi0iwi9f6fNIGsSmx/+X8+exd8Y6W0i",
-	"nm4S8Dt7HtxYifJuFNex24qwi9IruAu+NiEocFB0EfpDaJFa/yBT5wXaTfdKStm5NmRCsVRjgVNi7R+i",
-	"IAvrUO4PWAi8DCsOB7GcewpdZ2aODZpSYEmXBGBFNrHQrzxTIcQKSHiWATOWuwfrvlan4IWCVcV3aM/h",
-	"mvI757TFjDR+ut7unVtCew+uuHUH2RlWk+1umz7AFVLZaG/aKMIZZwruVYDijctnSijIsfU7BPwIF1jN",
-	"JeJTZEYjfdqJwqwYmTeRmmOFytfjLQhfEkdtzQ9ekQykwllu7Dtt1jO4VyjnlCINO5Aa4f2YQPJcWtKe",
-	"te/wShSAyBQd69HHS5zp7yQk17CTtZ2FvHqc9gGdGTf67bEEVeTHcr47zGrn94r5zhlXnJEEJRbdPuDi",
-	"mDbepEF2nsiGkC4hEWAV9DVFWa4v6R2bEkkSTJE0LyI9DGHjNSUTCkhxpOZEosTMvgUc1nVfGVz2OROc",
-	"0k+OaNaWPedSlS7W5tJPE1VgisoBBodzQGDmI2yGMpzMCQvSXAZy7syj5qSXNmCsn6N3F4a6tcQ1yt7C",
-	"atlWDrRqCZsionfyhMHdkOJc8fxoo8lkpu2CmwsjhgTHOBdkgRWMb0Phy9M358PL87NP51fDP53/dXh8",
-	"fGy2S7mmhhQSsczb9mrmLiaUJOGp8Qye6/nsGE1TZurLjxeXNbYN2xeOHseW4JxwbyPanxjRLIHpaaHm",
-	"jkbRu9e9ZrYEv/Xs7rUQUVl6G5cEMzYBha4PuDcqErOMh+yLm0hjBQvxGsrD4GwHRZjMVDg2ppQgk0KB",
-	"DGoXj6gNZVhLR6bNuXHBlHXO7BZ1KAVLKzNXboVaKkXU4kPpGQZqMwl28kps5yF1NoJzu5jdV3M0kNZY",
-	"TjtdtPpIG9TR5qzAM6xVFSO29Qd+I5F/cewiv4FPb8RaO3aaK3lt7S5pDzlAlEwhWSZUL8TZZGP7agce",
-	"V474QirjokeMs6F31EPlLugn8ZtIakfARTjN41QhClgqxJk/GKcEaCpR5laYC5DA1HEUb4G7DyBM7sFi",
-	"DYd9EPdVODeM6iuj/FcYRmYcGiiBmSRGU/Z7Ch/KLQi4cmTQAsNxPZ2lvqA/Xn78M7osQbXR7Gq8HNh2",
-	"yjVwg4+IHJd0GLbiKV6CqNtsGShsjwmBrSVRCI2VGV+AMOgzds6MkdaQpwd0X+usFaE5FvqIKtlts01o",
-	"YDrudKKth0BNBBdM2DMXkJjslM97CVwnXR1iSig30eFX8rmTvjZK2fFa1tVjUI53U00xlUGH3RolHZKE",
-	"diaZbnEbxlM3QlrcaAfBx660GRRRC5dateru2z4MhhV+xCCYhAUIp2fWaIdHcXSHRelZEURprTXsODKG",
-	"W9gulf0VKh9r9Iqf9UgdC0wkpFtEuNz57XfmlxgkLZ9kspXLs5Y4tjmW6kLbfccnDVds77e4BpvaMxvo",
-	"kdytWyfG9fbPCpwFtKXLW0Ipsk/RYF1nsk+csDgKaUwCpJG4+ztmH9GxagfXTsbNgO3S1MW+1BNIcHIp",
-	"Vs0MJxsi7sx4cslfRvxoPp4uaz/bwVNMbLRMLy8d88LkGOkTjtq/C65/GE9wcut+0z+O3Xuf9/FU1xYS",
-	"0Oy2Tpvy+VLb+rC9+Gp141VSrJKsAgy2uzkqwBJYth2ddRpfYUXzyPp0M26y9SC1ns0BN4MwPYrircPL",
-	"9aqLjYeDm6sz4eGNwPn8LwTu1mEI6QyacauunOhPDoFyTvKQl5rxdIvZnBsoMI8SBUvKbO6w015/CiU4",
-	"Nynqc6ICfvpVpYzbFDG75RCc3gKman5ZpQ6vwEqvl6xscMWzbGZoRIzNX0xkGGYCp1Yq8DvNKAW7Zfqn",
-	"oKaKpbJhx/3kVmucWUAztE0yLbTKnHO9VPuzVOYDjdXu6pDq9Eo42IUQsxZBakORh3FQIzRgDz4psRR8",
-	"WG58s322HbLL/a1CxW0urgguBJM/MX5HNS2/JQHZ2FPLoITdQjoOUvbGmJTA7LZX0Lj9ZGYkz0OS8C2Z",
-	"zSmZzbVANVVDZXSrF83bTLXemW2KKAodO654JOVJkdmQlSjYhPNb49JYgFRk1parvdlpahcQQvL70l59",
-	"rcXoOrXX/YlBazttd2htiW0FIiP6KNzpZe8SC6i0X6aCZyfoi+In6IsDlTxBP2srOh0aGRij4+Pjzw8P",
-	"D9Em7iFlkraR9Wse19o6QvD+AEqQ5BKEg3DgAFi2WQ+Zebclg4HSIq9TksB3URw9n+t/WrIWjErTddjg",
-	"xawX+21RfZLh+15TZoT1GreNmeyzIVcKbvEdsrBAZZbjhs+uakiy15niD8QuleXKDFr9QkUXngo8zitE",
-	"hhZxYbNwtrPQ85wSkO15YM2UniY0/5tQyRmi/A4EmvCCpbHWonJI0WSJYGHfswVLo++jAEqbY8InprZD",
-	"CtE5pO8BpdUgb+XupQrlFazXnv1SYIGZIqwtK22Lypf5MudqDpL83SY8losvC6xWvG7mAPFjPrcXnHVB",
-	"c7eYXYOSagZcCakGKa1hvmbbdaWQ1IpEV0+vlSz4WrWCEFwEToofCdB0aOoHapkTyA5Hg+9evDiqZ5M0",
-	"v2diVWHx3Gb+rcDOzuDH95EqZZLwBtoJpTluUkq86zzCE16okwnV+lgtQ6oQZLP5aD7TGTO40GaB7DTE",
-	"uyKzH969jlHCBcgYCZyNs0mMUiJvx7NJjEgeIwVZTrGCGGWarmSMJIgFSUCGvFdzLgP64iUtZmVM8kLw",
-	"+4zfmyQelx9TC7QHDfJwMtDbIsNsKACnWq4g59TvmaRjvkvvk5O/AaXLKWHbx3vpfRKjRRYjLlDKk1sQ",
-	"pvoaE1ZP6+of8XXA24Djttyfqvinn03vaxyDvhPv3UHvXptQucDJLcrLZRA207/MBBgn0oZjIngcRytL",
-	"6Nz2pefElU1ryRLo0LEAgSm1ggeRaXPh3nu3u3XeEnE+K4QA5kP/rXkEUkHepTmadY8zkBLP+kVAp4QR",
-	"Od/fifoYjlhfaSoK5sI6xjDzeJC32sxsOVwV5D08FXpUp5TsTFR0zFjiy6InNEvDwbZBzm703lfhq7Cw",
-	"dI1sPLv09lN6aWsTIDomaFNRzeE9Nk1UtrEPSDpWfFfaWcWJhU5ceVCdrKytbROK+qUq9UZMt+O3HR8b",
-	"3+vnjQsDZBMMwskqCRYpYZiuxF85g6HiQ24yaN0vGWaaePR/1bPyN/Pwc7CGsjvkTZhWSmG/PBHnSepV",
-	"OB1tW+618f1wUkF9Tc0vxA2oB/FG5O1ZGc5bIdkylFt9skIbcwirimPLH22SvchapKsvoMFUm5wtxtUm",
-	"XLbgJwyf9Y0ElhECjmv4sk7KxgnfM25Z2kg9D1Uh1VgCsK1CzlOK8y5jcM5pOk75Hds3IW7b7hZVfoNV",
-	"4IfO9R226rfeNyW3QJfjBBc9+Tor1N5JgTxJjNLV7fA4QK7JRlWwch26rBGc3JYxgNK5YL6jt23NVMnp",
-	"oh5Q/rzLIT8Hn2pqijYO0WKjbKZRS2RxutEavFfZZIV6gpx8Syjdy6e2OZvE1PCMK89Bzzd6d6PZxj9W",
-	"yD2V6o6sN1slSNItHf654AmkhQipn2XqXoqMIjyySRCjMothVCa35BQz9Onl8IejtXxiuM8h0aaET79p",
-	"qx1nWg6W/shsLT69eSP1fJpw8oBbd++4tyHPS21RhEKba6bbzlNZuB5iroA1JH32SpAFt/CXpgJPrcBS",
-	"IFf8pAKmxidbM+Y2JNOWzlLRXTtR+bN3c52u1Tl456l3ilYs0CqjLp3xuZpKmWWYBZwmb7h3lpmmNy7Z",
-	"Kwo3s3Kdk1YZhyjflSOUxJzyQg8wbiYZVrr6F08ICLdyUXobqoVlU6B42b+8Wxv9zQRhKedRXJbqm3Jy",
-	"1nLotp19WwA6XHT/X882ll26dcce3SEquSqDUisAZDzDdNmiTRMBVWbUDtkd6won1xwX9LsSE5ijhAEW",
-	"KBf8b/bTMfp9imza2uZYYnvcVFIespze289NiUI5CJTi5dZBQR+mq6AVTMyQkBRaQzFVFRb4E8ACxGmh",
-	"5qHWvdYsGi0I3IE4QXqY1p5u0cd3r8/QH//7qp60Sdjw9OId+tc//onOcJour9mUizss0iEu1BwRUzIE",
-	"TMKQsGEKuZrHiHFb3OS8N1pDE4WaHx1fM9N68sS4BUmC7Dpt3Z9tz1oVCQ5MZxF0Y7J9b/S7ZftSQ0zm",
-	"zYraDSuZRphGp3UdNl0Gv2uAmioueLTeX9S2Cx3qsxyQ3mxZ3P2R3HKJ5jwDiifo4+UxutLq5ZRQ0BvX",
-	"Q377W7/Ja2Z2+dvfooHpQIoTNTR64dEJesNNxAAEkqqYSIQFoKqB7h1Rc8RxToZa7M2AxdfMlihKNCg/",
-	"f/b+XYymhdZK0E/v5JGFlwEzzgDJHJLja3bNzjhbaHRyVtNPXh6dXLMhOrdRKP31sj0pumlrhnpzrF95",
-	"T6SSqJCAbr6YMzqu93R+uLGLd42gczwjzAa8Bk7QINPgFn3/LEYZvkcvnj07MvP+xCSeArr4eHllC69z",
-	"hW5Wuv/eoIHtI5xTvER3hKX8zr79oTBCAQnX6lqiBAuxRDfutLt5hd6cX7kOxBLdnF/h2U2MLk6vzt6i",
-	"Mn8D3ZQNfW/QwLUCLlsA28/4ev8KZi9fvvwB/XR1Zp6fu6Qk8xSnqQApzbomzRRJNGj2pDaIupoD+nB2",
-	"gYz4n+IE0EAqATgzM7y9urqIEZ9OSUIw1QR0+fpPR5rsTAgKUoQVuhllSX5zzTirCGFCGBZLhFmqB/NC",
-	"GT+q4SVL15plXZLQK0RMGSCnEt0JnF+zip6sfYxMXQjChtqlNrPSnBOmpOVHShJwoRjHZBe2EFeLa0Ed",
-	"Y8qT0chZ3scukjxyBbu1OGJk2e304l1NazmJnh8/O35mzNwcGM5JdBK9PH52/NIGgedG3o2MkBjiWktb",
-	"d2haJxDh7F0anUT/uwCxbHa/bXY8/zncOrnWgLSj0XPLu42OpTtMUE/d6Hw5pDlXmxv5fuE9xrpO0j1G",
-	"ug7xPUbaNtgPn1daSr949myrhsgrSYSl2dDLfmiiPpQdXGtXv33HFLOEwBm9duSUS0DAlMnjeogrxSy8",
-	"BQ+zWuvpWpap7emMJjDHC2LaGRg3O55J49OeaHbGE1K6Xe+H5cJtA6/oJLLqgJl1VDooZSsn6WPh1I/q",
-	"xUTe6qhwebhOrG3MU3px1j65d3/bXx1v+BbsT8cWnqD25wdNoAjXKLTkBY94uQ0jjL6Q9GHkG51rWDcp",
-	"fgOC/QUWGse5SxBpstRr0wvaoyHe8gsr1zZYWjLZMH/g6XIPMqpv2tdmWja1XLr0nBk0zRhvyfxt6RPy",
-	"9sPpWdUu2doGA0nYjMKwkBCjsvjHqdRDSVLY3FHGbyNMic0LHR72ZMRd7zp47RaJBCRcpJAe4mSwuDIp",
-	"OsCWdVg66LYCtC/L+KibZZoitfn+HTqYGdJP96q3TN1F+7J9dx9T8WpT+zjb5c21KrT/KH37HWxVx+Yn",
-	"PNr0Ikp1Dw2URK/PL8+ODsHeZubt9b0mz5oIcre6d2aH9GLaNbWrJ+37vI4dmLVs37r2aq3a7tdF2bZd",
-	"8tMRtaOIAylrhgRRClPCXPlLRdC2xHWTxtamWdkcKAutJ1SrNqLS5Wr10keeH/bTQfTa6ucD4NfOhLDD",
-	"8cBKmyGWwxQrHKPSTfn7o944D4kvo6Tvq5uXPU6aJGRan+xIQe5SskclHdua5Strsq2UU150tT/l2JmM",
-	"7kqsa9UR0a6E0mjvseHAWxnbz8vhi/G/tsZZduVd93Vs1Yz4V3dINntrP+FpuUJOBxCrbkbQlp01HLVu",
-	"OQfksgl5IYflE2TMMqQEJvRoV3+Ii0qNbLdZg5pgsUvZ7FCWLWVjH+6SCDOEZ4BuYZljImJ3e5/5e3uP",
-	"0NhENGrFsY2sL94obzhGZ5hSELbpH6YCcLpEc7wA/Q33DmHm2GGQaunSqI4wiV42wNGUCrb57FnZE/gx",
-	"pHmzL/BXFugrzXVDlxuaERkw5a/ytBFA20CZpR5hB6Bv+zGEEYO7sg/tv/7xT0SkLKCkoZJ+arTjl1BR",
-	"uSPcFhK3V+s0KPyLpMXsYZRUDcqDaRifXITxbk6SuetDbnqPxzasZsnWdAC2vb7L1trItBg3RDwjC2BI",
-	"lbFGE2VmqAwAm+biJmpHmFSAU8SnaEYUygtKQ0T6BlSzufrauRXaAuKMLt3ipF8ckdW67JWWL1++/OGo",
-	"5Spf2zV960tGPz+mitKAREgqu5bkKVCFD0Czb0A5MkjqMzuI4gqc2xJnvJNWay4sfvgcoGxZdUyfdfaD",
-	"HpoEE+MdNG/YYHJado+10/5GrknsdsIsm7U/Ot7LDwXwftmr7/uBTNsScl0N5r8uMdTbqbQqwGV6wyYJ",
-	"8iOhCoSpzq/fD0RYQosUJNKjgaWYKdkmOnb17/p6tW1f9I0vt36z7Gja+eIKsRUT+9B1iuHMpIWMXIpm",
-	"6Cu/7On4/bfS0dvbbH0l3dy1NaNEHoznoWIer2rXmiXt7MY6L4XrN+nHavRH/8qOrJKK2j1ZsbvS3Xz6",
-	"/ArP2qZ0w0ZmjJvwIB4whtZU0w1U0fRflINH3mBpN8LOnF1VM5RqRo+RnLFv/22qZqS2Dk3Woe2JoO22",
-	"BOc4MQZYmW98FKPSjeJmt8GuqsGnyacIWGxNM02LwXJ3PuAb0mh9Dfy3TftrXSi+Mv2vd0hol3Sus2Xc",
-	"RMgvBRRPyiZ+Cwgj/VqhPOkO3v+fsxj95UOMfIeJI2QGmpYR+/JT6ToOKkNvQHnSe0Tju018OZy5bjRP",
-	"h503vpJ+NcF1p0PuAE761aT78pqDutTBAgIXN9Qu36g6rqcwfXXNCKUww7Qxic0kRt89+0HrtWa6YfX8",
-	"6Bhd2Byymf7INbMCUdtEy+rVl2hQSjkPl6OgvNPb21XWPXK0oX7/xlf3TrUxiIs3VGfrU3GIC1dUzRU0",
-	"g9Qu21i5iOMgUmtk7nccVvc7tomwP+hxn+ywXrEMU87RsEM8eF6aRnwkK7Lo5PtAIdFjWxOrKWq5LXVZ",
-	"L9XaridQW5se+4Gtm6pskR8ynZpqUW82WK/qTOB8jlLiOnQdwqVaViyUHyRT64hwgn2KCZVfVZyvE3SZ",
-	"/iQ3H8i+zUc/ihZAd04lq8qwghwRTbhhFt9HxJSWGReDefL58I7PfUzu7j7ZO9NxfdpDhLheG6AjUZ/W",
-	"3Pjp4zgDDV3kkSOPnpB4rWfVq9SjqpK4jYpX23s94vG5+qkA9i6aUTDInRhy+ziAfs8pDbdQM8VJq0r/",
-	"10Jl3TG6MN7XzuzV84W7x7GHxHn0qp+gV7TWtOI/6adP7NtcOI/9U7k2F7aO9IApp2+JVFyYUCuUrLBr",
-	"qZGdYGQrH1uDUZc2Mf0SmEJ2Q8foHCdz+/3fSHRD0puyJtf8DQl+h0iKBgJkkcE1M4Ls5r1Wlc0Mw3ev",
-	"b45idGNGr7yrgRqjmxQr7J/88fLjn6+ZeRVZaB+jt4CFmgBWyF4qrqSeQCzR8+/lMfoDSDWE6ZQLEwQk",
-	"5sm//vHPa2a6GkOKchBDWUz0Ticg0KSYTkHEKBU8H3KaglSuhPfiv45emSLcN+dXyMHsmimOJji5nZJw",
-	"IPjSwLRNWLWGcDwEUC5gSu73jdhYI6t6sYGCzhk2s62Ce2XBMawoqH3C9Sjg5TlyLx7C7b8oCcjOiQaX",
-	"l+dH+zBHlZvTGaerhu1aiffo+dnfSD3Ev9fR4WsUn/D4qGjrUIGxOrVunYUWtwQ7ruaA5pilFMRqdGLg",
-	"M8gMDR7FNoNUujjFqGy9F18zzFIERM1BIGDGG+6OBd8LeGCTKV2Z6hHiopa/ds183ZrzvZkYSNmGoDkT",
-	"YeimvKHrxuecnVLJEdybv5YpFjafRHAKJv3JJgPZ6T7++f1f0R1e2jFSbzF0FLiIxHm96PWbDB+u3qj1",
-	"tUOIFcd1sEIZPUGDzDbIdPXLPoh1CCXrkyegOvU50l6if/3f/1cVSdq0ev0nR7VbJXjWst+qsZsDIjVa",
-	"ejyXby98HMIv5kFsD0f0O+QuIdxNRu3lT2giYWRv1XuUmuMzM/XTo/LMXxx4gFC7mQthVArXkb/OENWr",
-	"/nesbtWyWbSXt56bx5cA6d7OnBXVwbT14bZZWRN6fz398B7VLn5a7xDKFKd8tsur9ozc+sUVfcMvIK7t",
-	"w0/eRw/REEWTQh/wBxGuZTo6knpivRtpOyolroH96z+Ul6W//oRGyDWkMcFnwRsZ9HIpFWS9iMf487uk",
-	"qrkHcZOxdqmw8JHYQT0Oe/QK8Ywo40y7m2uFwUYQBvYCnbbsO8H5Tkp9R4DoxYYAUWw6ZFLT5s9qrL39",
-	"9f07Y0q1NJ2Fplxk0aPmGVf3VwZo1zxEC/N0b9K9LCYWpxrHCyILTMnfXc8tc38k+h0y90fu4AjXJFrd",
-	"D9lGoz9SAGUvonzMA6N51WUArHYAKkGzP2jNxtC8Ma11gJubtxBhqd4KF/s4vHxD5JEELJJ2SF+ax/4O",
-	"xX6m/S/Rqrq8n738DVjBjVskDxepekvUIUzaHwtKhybP36LTNuP0SK7iuYPysJQxcjczNljUv7IVDX3x",
-	"cYIe2Ut1Wvq1ofO9uSa0AvwhOitQ6jUcOSpxhuyFpNo2D2Vz9kVjmJvNhaDBGFB/pjY2hG0euiGO9cEN",
-	"6iVZegekehzrvrXp/od6azFsebVhIFKPC8VrkfrmRZf2KobdCmN3CXc9pWht3CV6OF600yIJB+ptZ4jV",
-	"VE4N7Zwo85S76zFcN4napObHymo5IIocI2koblshYS6yCbCETyvrP2Hj2t7Qzcm1jIst17p29c4mympA",
-	"JPjpxhb7kKBH3WFOeFSSi3HA1qqc9GFeW275t9pqayRarqk/ddrckuXQIyDs/K4nnyIsXanpOCuUMwy8",
-	"i1pzDh56x+HdHBiqclHX/Mb1kpMra4d9w2UneoVPWXpiib2zkcqLZy960KF1J9c7Mu7t3lTagFFzqCjZ",
-	"GDa2trpG0P3ptenZCFLs6Is+jkMtWQLajiuG20LRaU0Ef4tFilKgoEyjbsYVkkWec2G6bc9N/25366lE",
-	"cE+krSv39zb4UmsbfX/9MsAatSTt3TjjqyRq66U9YbJ2G0fUGsQ8EUfUGst4rFdJhftwguse2x2yvygH",
-	"baN779EEccfYe79MgV9TzL287vzpIu6eNA4Ub88rUivpmYK78WuzJlK+fdDeWuEbKZDEU1BLtMB0AU70",
-	"Xr75/dExOvWNmLU4z+vazpqqc/ldm7C+8HeGf31J3STJ1pa4my95X7ubaN/L2x+euB2uZ7hv8ZS4qkp3",
-	"cMlIaOD6ggMaoQq2aFSdJEf9eW3l7HAZKb5MrKDQrwn7p4KCjL6B/uF6IYcsKDD7OnA/cCSKpmlWBSJ3",
-	"SD0688ZVo5G8/9oro3frTyJ3iZ9ttoOnCsR6BXQp+V622mMNUH+jFll9jdvYZE/C5hc2U8BZQw0qQYO0",
-	"wHQYCPt20kwPtn7sbpX7UckjWyf/puRhKMKx9yEJw2UgdjkjT92YS1CKsNnTyvrmWg4o7v3uDtEY2y4S",
-	"STcnGtwSSofyjqhkHiMGCxDDsjem6f1ytMORENZpP2EiTUZguQgiUZ1eKKRo8OLZC/S7KmnwGL3nd2Da",
-	"BBFlCwXc0tHNjPIJpsd6ujFO1Am6jvh0eh3daAsWpzb70G5pXA5Ct+DqDcpjh2QZpAQroEv99WdHJ+Zo",
-	"qoHFtkw086A77DJJMOtuz2GkTYg8d5Mbejv6EaYXDRptiww9nt76bfLIqcGmLW1Rgtik5idUkr14LGm9",
-	"7CLYkJCvGmT28ccfNUt4gtxPfgoib4cmNXaDtuxvl39aXbm65P6AijKRt6iEwYH0ZVGfc0vRqNHTKNu1",
-	"QpKCNX1XG6umjYLkfmUs5uq/bRNeOsta9p6plrC2lSN7hRS/C3UarYWZgB3mbphzlmqtpj71QIKStmHK",
-	"WHFru5hMFiLRLeT2RJibCsDl0S4NLNrMqHN3taCNoQVatqzHBdFgTkBgkcyXQ3yHBRy9QgkWKWGY2uvV",
-	"plwkkLYZUt00920YUvU1Pk1wq9kq4KvcE9CgSJextFOnlLI3fNehcOnG9K6dg4PVZPu7j9mUR3F051xF",
-	"cZQIokgSvBP6USrG+1zY8mty81ucP6GXvyS6Q3WY9TS83ZUpNR6xxSY4uX2USpPT5NbBPIz17p3bVw93",
-	"rcRpUmVoYge8HW+UaEAvK6x2c3DwfSgU1OB3iCCEXuu4YIrQvp26W+/yW725vJp5j8v2vi5FaAB7UnDN",
-	"SK6u3h+CKARIThePQxef7NwHJo12NK8h85tAnoNChb8MswJTutwVfdpU3aA02CH9rjC07pexyTr9T/T+",
-	"MY91jZWnPNUtVRzqUDezoQHFCqTyJWg5CPvoaLeQvp32scMPFhXfcKw9J4xBOvY3zYe6B66H2zUmWmPt",
-	"31503THENx9bNzRpLuIh+tcSKTuG0WsUPnJT9ZDmfylHfnsCbGeB5Pe0P77cVKXvx3Ths3jbXgztWSFv",
-	"yvFk3+KnKzN6a1H071bMYbZ5QNJxYDsEowNLEWaYLiVxjf4oLWs4TA/vQCHVNgUdj1lMpbcCSWFcN3rq",
-	"CWAB4rRQ8+jk588a4/bWbPvhQtDoJBrhnIwWzw09uP2sX6/jyuBdhbavKzDNWU3TmLrvvLkNW1azlodi",
-	"b8gCf0VXXN1BRKTtSEw4i8vraGotltydM+tznm9X6uDm41X1xZew38Ns0bXhGVhUmxhQ4xbF4IJ8t4bq",
-	"FgJ3o15c3fePBqm5TX+EE1WbFurNjL605F2apXnVS8uz2gxevq2/Xw/AxCupRrEPjlVTuSjK+kS+QtKR",
-	"hqsTrnx1tRrHL8HSKxnbimXz3ZSo2PXpi11xcw1TDS4LgTvnQq2/53oePHx++P8BAAD//5TywEKf5AAA",
+	"H4sIAAAAAAAC/+x963IbudXgq6C4WzXUpCn6MpPsyLU/FFljO7FjraXJt6mRiwK7D0mM0EAPgKbEuFyV",
+	"X/sAW3nCPMlXuHY3iSabF1nOVP7YkhqNBs4FOPfzqZfyvOAMmJK9k0+9GeAMhPnx/ApP9f8ZyFSQQhHO",
+	"eie9DyB5KVJAcxCScIYmXKA3k8E7rNJZL+nJdAY51u+pRQG9k55UgrBp7/Pnz0mvwALnoNwHzkohuVj9",
+	"xPsC/1oCSs1jNBE8RxgVAuaElxIJkAVnEr6RiMG9GtlhvaRH9Lu/liAWvaTHcK4/Hh62LyvpnTNF1OJN",
+	"trqSn3568xJxgSQtp6gPx9NjdDPjUp3MyrEg8ubIf7bAalZ9lWS9pCfg15IIyHonSpTQZQWXtIwA3D5r",
+	"LOFOnuQ4HeSEkZsE3dD79CTFWbZoW49+d8sV/Sh4fkX025+igNVYaYB1wkWOVe+kl2EFA6VfTSLzvskg",
+	"L7gCli7+DIvV3Z5RAkwNpsBAYAUZuoXFCySgoHgh0R1RM8LQs+9mSIAqBUNqBogLMiUM00AaHgqWmKtF",
+	"1z4+0F+vrz/H92+BTdWsd/L02f+KLn1iaXwVQ1d4WpEp4QK9Or96gb57+gxxFvgkJzJ3PBJfXMVD2yDq",
+	"LcmJasMSNQ/rE2QwwSVVvZPvnyR6zyQv897Jsyf6N8Lsb0/D7glTMAVhPnTF19GD4ttTw2e9U4sxcx5c",
+	"AMsIm54WheBzTPWfUs4UMLM/XBSUpFjDfPiL1ID/VPvg/xQw6Z30/sewOs6G9qkchgnNJ5fobYbZFJBU",
+	"eArZC4RRDgoPsHsD3WGJUgGGEvtZielAr0hwetT7nPQuBB9TyNcstLAjfrfdgv28kfWeC8EF6n/48Qz9",
+	"8N33fzDLuCRThulPhYZ1djCo2Vlja3BfQtKP8Jg3WDydAlOnqSJzogyDF4IXIBSxSMbuychSw6ceME1z",
+	"P/cU53SUYkoNA2DJmaYS/e2UaAbqJb08LUae7kCmmJp99T6ukFbSw3oVI5JFmCbppVwIsC+7IaykFI8p",
+	"eI5beSUrhR2fyzXjA78kPTDHdtfpGwutzUJYUaqRLPMci0WnmXiptn1FgpRbgEKWaQpyHRjGnFPATA9W",
+	"/BbYKOWlJcfNcDNkYA+VDmuxQkvHu6c6Vn+2V7SSvRqlJEu0WZEVH/8CqdLfq59Nq3Rt2WuV3OwBMsKq",
+	"62It1Wfr39lMs26OcTcygPuCCJBbLdOSTBhblhauy8NuCcvqvA73kJbKMnXBKUkXg9QcxPp3rBQINjDI",
+	"aGfwAi8oxxGZzYhIGjdcQobs7Cgjk0k7yCr8CiJvRynFlrxXSd9JaKsPFFalrG+xsJeZpipDM5CZs4wR",
+	"84OFtRUT5/wWsugeZWkXtlYm1BJQuK9SzlIQTG4mjxg/ODnRkXIDGg6HYacNcmmQ+Dq2+VBS2Ip1cKk4",
+	"4/liRGEOtA5f/aS6Bgw/wBxEFI7uLPY3ThOW7/ACjQHhsVQCpwr1CZuBIEqijN+xoy6M1pELNhFXygsY",
+	"2bWuR7lWuQoQAzsW8TkIQTKQXdbqxNHYdRMjiTgtLKGlmnUT8s8MnTw+CeyLm/XM1AloUVCVGVHnTInF",
+	"diBKFRddr287eFn6MrdgL+npL2JlVeaFVOCVvKykLZDdRZgChQmtbaWCwGHEphzUjHebwmjKncQeY/YY",
+	"kaLbaHNMjlKeQUe55wCSTIXZwLhxKrOEeAlK6RlXSO3WauZwj/NCr7k3pXyM6bGm4BFOVexwK61SsJX0",
+	"MMe0jLNj91Pq1ujxdqb159DZDNLb1c2mnE1IxO7yV0yJ1XP0Uetuvwi9arTWybAm/Ha8F/TWxBzTkYxT",
+	"87L0NFOq0POk+t+MyFt9AYNQA3Mla3Bkgkw0lgorgUg5G9itxcWMNqlGYTGFDeJHnzCpMEthYM7IrNOF",
+	"aSduuZDd7Poh6ut/t5qZ5MC1/hMH5Rq6Snp/56yL1rFGcnJUUkNofUUVtXQg1LabsiLXdbQYzDxtelmT",
+	"5sLw3z95knydFLiJhtZTQtjg0+j+PObXY7qO5Fa8XXgb4S5o24SnyLWxjt4/xxappREycTah3SSx1J+k",
+	"K0PGFEs1EjgjVhsiCvK4ROX+gIXAi7gYcRA9uuMR7JTOkUFTBixddxCwMh9b6Fd2qhhiBaQ8z4EZPT6A",
+	"dV8dVPBSwbIYPLC3ck0UnnHaolQaq11nY88toZ0HV9y6wxEaF5rtbpsWwSVS2ah9Wp/CGWcK7lWE4o0B",
+	"aEIoyJG1QkSsChdYzSTiE2RGI33pidKsGJk3kZphhfzryRaEL4mjtuYHr0gOUuG8MNqeVvIZ3CtUcEqR",
+	"hh1IjfBuTCB5IS1pT9t3eCVKQGSCjvXo4wXO9XdSUmjYydrOYjY+TruAzowbfnssQZXFsZztDrPaNb6k",
+	"zHPGFWckRalFd3C/OKZNNsmTay9mQ0iXkAqw4vqK2CxXl/SGTYgkKaZImheRHoawsaGSMQWkOFIzIlFq",
+	"Zt8CDquSsIwu+yWWszHHIrusjMJLLOBUdDnyZqvoZWOUMwJyNF6MtIJjyBZnGdFbxfSiMefq60t2Oivm",
+	"GdOw1ECBDI0XyM6btGiG7uP+0j/wt53qtPrpuT4hhNvw0lT6mZ9pXKa3oOxk3w9ywkoFyF/hCcq5VJqp",
+	"9Bv6oqzjuokQO1H3ay4Y2DdQt5vXvxCjlmVeC7baA6HdTxfHfGIAg559N4shYgaYqoh0lcFU4AxarAEZ",
+	"v2uR+O18i/hDqTCNINysj4+lxqnZB6cZ6BMaW2+0EY6+kQjuC0g1LaTYChQxwbNkt6xldUuY80tNqs26",
+	"nVWzxNBpr3uLO5iDcAasXdHHC2CozzgbCJCcziE7cn7AVXz6z62samlrK5wdO2kC8uNbSiJnWJx2G+wc",
+	"g9g5E5zSD+6OXaG1GZfK+6easDlNVYkp8gPMlTcDBGY+wqYox+mMsCgD5yBnzrbUnPTSRtvo5+jNhREG",
+	"tIBqzq+5NVFYsalVqdoUTnInTxjcDSguFC+ONtqbzLTr4OZiMGJy1qgQZI4VjG5jsR+nr84Hl+dnH86v",
+	"Bn8+/9vg+PjYbJdyfXlmkIpF0bZXM3c5piSNT42n8FTPZ8doGjVTX76/uKxJOXHjjLu+R/Z+drJw2x3/",
+	"EyNagsD0tFQzd6WjNy87zWzlg61nd6/FiMrS28gTzMh4Y9d9wL1RkZiVU5B9cRNpLGEhWUF5HJztoIiT",
+	"mYoHFiglyLhUjXOsem0X5bG6blqvAMiQHZWguxkwx/AGdESinDOiuHX0BdtJh4PcXz4fD+d8Moq5uZsc",
+	"CJpbMou3SzNBL40ttikaG9eWY32RMMxSGJVMWZv/blP5I7f1mKus1bUIvV6Lab5jdEGbbWknY/d2jjdn",
+	"bHL3odl9NUeDnBvLaeeYVtdbg2/abOB4irXOa+hbf+AbicKLIxdQFPn0Rqy1Y6e5kpfWgCettgSIkgmk",
+	"i5TqhTjj3mhJdVjF45KuWEplPL9IizPB/wuV+bnbXdhEUjsCLuLRg6cKUTDcxoLIMCFAM4lyt8JCgASm",
+	"jnvJFrh7B8KEtM1XcNgFcV+Ec+OovjJWpArDVjFAfSUwk0ZorfYUF1daEHDlyKAFhqN6lGR9QX+6fP8X",
+	"dOlBtdF+13g5su2Ma+BGHxE58nQYNwdTvABRN/7loLC9QAW2JqlSaKxM+RyEQZ9R9qaMtEbSBEB3NfO1",
+	"IrTAQl/ent02GxcNTEdrnTKrkTUmMAjM/VkISE3Q48e9Dlx3ujrEeCg30RFW8nEtfW08ZUcrwbwPQTnB",
+	"3zHBVEYdQCuUdEgS2plk1h+3cTytR0iLP+Yg+NiVNqNH1NxF7C77jbaPrsAKP2BsRd2KUKMd3kt6d1h4",
+	"E70gSsvzcQ+EUWnjBk7ZXaAKISxB8LOGgWOBiYRsi8AJd3/XjAluiVHSCrGLW/nOavHIm0N0nCmj6/i0",
+	"4dPr/BbXYFN7Bpk+kN9u63jrzo4+gfOItHR5SyhF9inqr8pM9ok7LI5iEpMAaU7c/T18D+ihs4NrN+Nm",
+	"wK6T1MW+1BOJm3WRu83AWRt5tDaQ1tn6zPGj+XiyqP1sB08wsdEXennZiJfGEq5vOGr/Lrj+YTTG6a37",
+	"Tf84cu993MflWVtIRLLbOho3hOFu6wwNx1ergbM6xaqTVYDB9nqOirAElm1XZ53Gl1jRmpONczDnJggc",
+	"Musi6/PCGq2PesnW4Ur1ZL6Nl4Oba20c3SuBi9lfCdytwhCyKTQDINal2nxwCJQzUsRcMJUdqs1sv6Nx",
+	"KRKZGXGTkQwNrssnT55DsHU5jdTavAhLaZnB/7Y0acxHzkMN0Zg5xrMtgOPsfRGwKFGy1Oc8xZ3Z+lMo",
+	"xYVZ1IyoiP96WcbkNpDaYjCG9tcGBq2+VO+6aGxwyYUQ8HkovK1Y93Y8jlvjsAQ0I8BIrs9in6Gll+wC",
+	"vZT5QMMntaudba2xxcGwiwdTtqHqP27DFrfhMuQdACu/XBTuf2b8jmq+eU0i10pXOzVht5CNoly0MS5E",
+	"YHbbKXCrXahhpChil8hrMp1RMp1p1Jg8Xh9h0omvbOx451hzRRSFNTuu+DDjaZnbsBFRsjHnt8YaNAep",
+	"yLQte2qzvdkuIIbkt17Vf6mP7FWOqptio4aKrN0WuCW2FYicaClip5eDNTGiDXyaCJ6foE+Kn6BPDlTy",
+	"BP3McA7ZwLBqgo6Pjz9+/vx5o3ub+LQpc6+sGKtr64jB+x0oQdJLEA7Ckctm0aZ45ebdlihCSsuiTkkC",
+	"3/WS3tOZ/qclctBIg+suNjyfdmK/LfJBc3zfacqcsE7jtrEwhPyEpRIY+A5ZWCCfd7Dhs8vCpex0b4VL",
+	"d514dGUGRUMqFlYhcFQQcF4hMraICxsJu51xoygoAdkei90Mq21C878IlZwhyu9AoDEvWZZoia2wQSQw",
+	"t+/ZFOLh970ISptj4reyVuFKsXbINo7UYCDYS9wqKlivPPu1xAIzRVhbZPgWuaizRcHVDCT5u8098Iv3",
+	"Kc9LBktzgYQxH9tTwNdBczd3Z4OSarqvh1SDlFYwX1OL14Vx1so2LN9eS3lptfxBIbiI3BQ/EqDZwGT0",
+	"1cJxkB2O+t89e3bUHuVn3Hzx47lNc16CnZ0hjO9yqvh8nQ20E0s12CSUBK9DD495qU7GVMtjteCBUpDN",
+	"mrf5zFp3y4VWPeRaG8Y6p/a7Ny8TlHIBMkEC56N8nKCMyNvRdJwgUiRIQV5QE4yYm5i2BGmxnaQgo0GJ",
+	"XEbkxUtaTr0790Lw+5zfm8gwF3RVi1GI2jLiEWavyxyzgQCc6XMFOX9Ix8gv8116n578ApQuJoRt7yqn",
+	"92mC5nmCuEAZT29BmHoomLB6aHV3Z7kD3gYctwWUVem43ewHIRowanYKhjH05qWJMhA4vUWFXwZhU/3L",
+	"VICxv224JqLXcW9pCWu3fRk4cWnT+mSJ1Myag8CU2oMHkUlz4cHwubsFoMVZf1YKASxETbSGYEgFxTrJ",
+	"0ax7lIOUeNrNeTwhjMjZ/vbnh7BhhwBUUTLnETOKWcCDvNVqZsvlqqDoYA3Ro9aekmuTBRwzenxZ9MRm",
+	"adgmN5yzGx0flecvfli60nKBXTqbeMNpa2NH1kzQJqKay3tkypptox+QbKT4rrSzjBMLnaQyPruzsra2",
+	"TSjqFuXVGTHrbebt+Nj4XjeLXxwgm2AQj/NJscgIw3TJdc0ZDBQfcBOW7X7JMdPEo/+rnvnfzMONtvOY",
+	"5YNpoRT2C7FxlqROpUx622Zeb3w/Ho9RX1PzC0kD6lG8EXl75j2h8aSkUfXJCm3MIawqV+F/tIluIm85",
+	"XUMSK6Za5WxRrjbhsgU/cfisbiSyjBhwXAm2VVI2hv6OLl+vI3W8VIVUIwnAtvLWTygu1imDM06zUcbv",
+	"2L6xhNvWm6pCQ6wAP3Cm77hWv/W+KbkFuhiluOzI13mp9o6n5GlqhK71Bo8DhOlsFAUr06ELuMHprfcB",
+	"eOOC+Y7etlVTbc5QJQp93OWSr2LsbeLkIYpe+fJWtRggJxutwHuZTZaoJ8rJt4TSvWxqmwNxTB7tqLIc",
+	"dHyjc324bexjpdxTqF4TMGgz9Um2pcG/EDyFrBQx8dNHPWbICMJDGz8y9AEgQx8XVFDM0Ifngx+OVkKx",
+	"vd9uFCKX2qq5MH0OentkvuIL37yReihSPO7Crbuzj92Q56XWKGLu0xXVbeepLFwPMVdEG5Ih8CeeCNnd",
+	"XpoJPHGxCz6IIdhJBUyMTbamzG2IQ/bGUrE+7aSyZ+9mOl1JEQnG02AUrVig9Yy6dMrnchRqnmMWMZq8",
+	"4sFYZsrQuTi5Xry8pKtluMw4RIU6WTF3esZLPcCYmWRc6OqedyIgXlxN6W2o1hRYihfdS6xopb8ZWy3l",
+	"rJf4qjkmH5y1XLptd98WgI4Xvvn9k42lD9y6k4DuGJVceafUEgAZzzFdtEjTREAVVLZDBMmqwMk1x0Xt",
+	"rsQ45ihhgAUqBP/FfjpBf8iQjfjb7Ets95tKymOa01v7uQlRqACBMrzY2ikY3HQVtKKBGRLSUksoJiHF",
+	"VQsALECclrFcxfdOLRrOCdyBOEF6mJaebtH7Ny/P0J/+66oe70rY4PTiDfrXP/6JznCWLa7ZhIs7LLIB",
+	"LtUMEZNtBUzCgLBBBoWaJYhxmxfmrDdaQhOlmh0dXzNTDPrEmAVJiuw6bTKpLZheZZ72TZEvdGMCpW/0",
+	"u76guCEm82ZF7YaVTGlqI9O6mtcu+cGVJM8UF3w1qO3MFvAe6LsckN6sL7DyntxyiWY8B4rH6P3lMbrS",
+	"4uWEUNAb10O+/TZs8pqZXX77LeqbmuA4VQMjFx6doFfceAxAIKnKsURYAKpK2t8RNUMcF2Sgj70psOSa",
+	"2bxXifr+82dv3yRoUmqpBP30Rh5ZeBkw4xyQLCA9vmbX7IyzuUYnZzX55PnRyTUboHPrhdJf9wXD0U1b",
+	"efKbY/3KWyKVRKUEdPPJ3NFJvcvC5xu7eNeaocBTwqzDq+8OGmRKzqPvnyQox/fo2ZMnR2ben5jEE0AX",
+	"7y+vbPGTQqGbpXr8N6hvK/sXFC/QHWEZv7NvvyvNoYCEaz4hUYqFWKAbd9vdvECvzq9cTwCJbs6v8PQm",
+	"QRenV2evkY/fQDe+xP4N6rvi/L4ov/1MqLlTwez58+c/oJ+uzszzcxeUZJ7iLBMgpVnXuBldivrNLhEG",
+	"UVczQO/OLmw5kAlOAfWlEoBzM8Prq6uLBPHJhKQEU01Aly//fGRziEtmItEVuhnmaXFzzTirCGFMGBYL",
+	"hFmmB/NSGTuq4SVL15plXZDQC0RMBiWnEt0JXFyzip6sfoxMSg3ChtqlVrOyghOmpOVHSlJwrhjHZBc2",
+	"u1sf14I6xpQnw6HTvI+dJ3nossBrfsSeZbfTizc1qeWk9/T4yfETo+YWwHBBeie958dPjp9bJ/DMnHdD",
+	"c0gMcK3IvLs0rRGIcPYm6530/k8JYtGsR9/sQfJzvJlBrST4mtYLLe82aojvMEE9dGPtyzHJudrcMHTw",
+	"6DDW9XboMNL1bOkw0jam+PxxqcnDsydPtmpRsBRE6NWGTvpDE/URfaTeQGb7qmVmCZE7euXK8UtAwJSJ",
+	"4/qcVIJZfAsBZrVmELVIVttlAY1hhufE1MgwZnY8lcambcNMx8SbXe8HfuG2lmbvpGfFATPrMJROaeUk",
+	"fS2chlGdmChoHRUuD1cbvY15vBVn5ZN7V5z/zfFGaIryeGwRCGp/ftAEinCNQj0vVCWAtmGE4SeSfR6G",
+	"1iMa1k2K34Dg0FJK47hwASJNlnppujMENCRbfmGpkZKlJRMN80eeLfYgo/qmQ1qrZVPLpYvAmVHVjPGW",
+	"yN+W4jOv352eVQ0MrG7Ql4RNKQxKCQnyeVNOpB5IksHmMkVhG3FKbLZY+rwnI+7afeilWyQSkHKRQXaI",
+	"m8HiyoToAFvUYemg2wrQriwTvG6WacrMxvuvkcHMkG6yV72I+S7Sl62E/5CCV5vYx9kub64k8P1H6Nvv",
+	"Yqt6KDzi1aYX4cU91FcSvTy/PDs6BHubmbeX95o8azzI68W9MzukE9OuiF0daT/EdezArL6S+sqrtcy+",
+	"3xZl2wYGj0fUjiIOJKwZEkQZTAhz6S8VQbsKjxsktjbJysZAWWg9oli1EZUuVquTPPL0sJ+Ootcmjh8A",
+	"v3YmhB2O+/a0GWA5yLDCCfJmyj8cdcZ57PgyQvq+srkvD9MkIVM1ZkcKcm1CH5R0bFWbLyzJtlKObz25",
+	"P+XYmYzsSqxp1RHRroTSqIyy4cJbGtvNyhHqGHxpidNXxl+1dWzVEOA3d0k2+1s84m25RE4HOFbdjKA1",
+	"O6s4atlyBshFE/JSDvwTZNQypAQm9GhXe4jzSg1tCWODmmiyi68TKX2d4iS4uyTCDOEpoFtYFJiIxPXT",
+	"NX9vLzybGI9GLTm2EfXFG+kNx+gMUwrC1kvEVADOFmiG56C/4YtYMHPtMMj06dLIjjCBXtbB0TwVbEXj",
+	"M1+X/yFO82ax6S98oC9VbI61GzYjcmAqNNe2HkDbxIBlAWEHoG/7MYQRgztf3Phf//gnIlKW4GnI00+N",
+	"dsISKip3hNtC4rbZXYPCP0laTj8P06pJSDQM44PzMN7NSDpzvUBM/4/EutUs2Zqy0rbfhm9vgUybD0PE",
+	"UzIHhpT3NRovM0PeAWwafBivHWFSAc4Qn6ApUagoKY0R6StQzQYnK/dWbAuIM7pwi5NhcURW67JNpp8/",
+	"f/7DUUtzfdu5ZOu23x8fUkRpQCJ2Kru2IBlQhQ9As69AOTJI6zM7iOIKnNsSZ7KTVHtJy2nv88cIZcuq",
+	"a8l0bZHxgQkwMdZB84Z1Jme+8K6d9hu5cmK3E6ZvmPLgePcfiuD9slPvlQOpth5y65q8fFliyHwLmGGt",
+	"GE5UEn4FaqVfzAMibuVbMSu5H4P84vfH03sGA8FLlg2UIIUJqdOCT4gFcm3+keA8NyFBqMBT2MPHWi9o",
+	"06qC+ACTTWf4j4QqEKY+Qr1ZoivEJZEeDSzDTMm2w3tXC3vIGNz2xVC1des3fTnetS8usXs5tg9drR7O",
+	"TGDO0AXJxr7y656m938rLam9qNoX0o5cTT5K5MFOXaiYJyg7tXJVOxsSz/319lVaEhvF/b+wKdFTUbst",
+	"0dRKy8BWzji/wtO2Kd2woRnjJjyIDZKhFeVgA1U0LUh+8DCojO1q8JnTbOtNQCq10/W3mgddOeVMav3c",
+	"xH3aqhRac05xgVOjAvuI76MEeUOWm926G6vqtCaiJaIzNxVlfQz63QWXe0ynCFUIvm7aX6kD8oXpf7VG",
+	"RftJ58qyJk2E/FpC+ahsEraAMNKvlSqQbv/t/z1L0F/fJSjU+DhCZqAp2rEvP3njfZsUGkjvAc0fbceX",
+	"w5mrB/R42HkVahkshxjvdMkdwE2ynPbge3TUTx0sINJ1pNY5pmoXkMHkxTUjlMIU08YkNpYbfffkBy3X",
+	"mukG1fOjY3Rho/im+iPXzB6IWitdVK8+R31/ygW4HEXPO729Xc+6B/b31JvHfHH7YBuDOI9Pdbc+Foc4",
+	"h1FV3kIzSK1TzFIXmYOcWkPT5XpQdbluO8L+qMd9sMM6eZNMQk1DDwngeW5KIZK8zHsn30dSuR5am1gO",
+	"EixsslFLk9jOVZnaCiXZD2xd1maLCJ3JxNbZ9ai1du2pwMUMZcTVSDuEUdvnjPgPkok1BbmDfYIJlV/0",
+	"OF8laB+AJjdfyKHQSjeKFkB3DuarEuGiHNEbc8MsoZKLSe4zJgbz5OPhTc/7qNzri7zvTMf1aQ/hZHxp",
+	"gI5EfVrT9zx40voauiggRx49IvFa23YQqYdVLncbFS8XWHvA63P5UxHsXTT9kFC4Y8jt4wDyPac0XsTO",
+	"mDqXhf4vhcqaadp045Xr44fP5649a4cT58HzrqJW0VrZkP8EAD+ybXPufCaPZdqc20zeAwb9viZScWGc",
+	"3eBZYWdHxNxCy+SetroDL21qwCUwheyGjtE5Tmf2+99IdEOyG58VbXvgC36HSIb6AmSZwzUzB9nNWy0q",
+	"mxkGb17eHCXoxoxeelcDNUE3GVY4PPnT5fu/XDPzKrLQPkavAQs1Bqz0uZUbOGvOW6Cn38tj9EeQagCT",
+	"CRfGDUvMk3/945/XzNSVhgwVIAayHOudjkGgcTmZgEhQJngx4DQDqVwS9cXvj16YNOhX51fIweyaKY7G",
+	"OL2dkLgr/tLAtO2wanXhBAigQsCE3O/rsbFKVvViAwVrZ9jMtgrulQXHoKKg9glX/bCX58i9eAiz/9wT",
+	"kJ0T9S8vz4/2YY4qOmqtn64atmsu5INHyH8lGSn/XldHyBJ9xOujoq1DOcbq1Lp1HGDS4uy4mgGaYZZR",
+	"EMveiX6I4TM0eJTYGF7p/BRDX/wwuWaYZQiImoFAwIw13F0LoRpz34azukThI8RFLYLwmoXMQWd7Mz4Q",
+	"XwiiORNh6Ma3l7sJUX+nVHIE9+avPsjFRvQITsEEoNlwLDvd+7+8/Ru6wws7Ruotxq4C55E4r6cdf5Xu",
+	"w+V2cF/ahVhx3BpW8N4T1M9tiVKXQR6cWIcQsj4EAqpTnyPtBfrX//v/VZqqTWzQf3JUu1WIbS3+sBq7",
+	"2SFSo6WHM/l2wsch7GIBxK5t3O+Q66C52xm1lz2hiYShbQn5IFnfZ2bqx0flWeh6eQBXu5kLYeQP12Ho",
+	"xYnqdRd2zC/WZ7NoTzA+N48vAbK9jTlLooMprMRtrFwTen87ffcW1VpvrdZoZYpTPt3lVXtHbv3ikrwR",
+	"FpDU9hEm7yKHaIiicakv+IMcrj4hAEk9sd6NtDWtUtdC4OUffaf/lx/QELmSQD4Sr5EqtpAK8k7EY+z5",
+	"605V08Rzk7J2qbAInth+3Q979ALxnChjTLubaYHBehD6toVRW/Sd4HwnoX6Ng+jZBgdRYmqUUlNo0Uqs",
+	"ne313WuTSrUwtZ0mXOS91bC8pU6hv3DCvB9k5P6mxbeCFyU1El5osXrs+j0mXTbhPhPfQ6jJuNw5oeuu",
+	"HjJ+vWopG+FI8xDNzdO9GfKyHFtK1ZQ7J7LElPzd1XIzPVDR75DpgbqDeV8zXtXjtI3zfqQA6rVH64OB",
+	"tNmuNQJWO+CAscVmY65Vrp/WmvVNRzdEWKa3wsU+ZrxQaHsoAYu0HdKX5nHozdnNYPFrb1kJ2M8K8BXo",
+	"9o3upIfzv70m6hCK+o8lpQOTP2LRaYu8BiRXXuq+FwFkglzHzwaLhle2oqFPwfvRISarTku/NXS+Ne1n",
+	"K8AfomIHpUFuk0OPM2Qb3SLFozGqXdEY52bTaDbq2erO1EYzskVpN3jn3rlBnU6Wzm62Dvd8KJl7EFEl",
+	"Lqf5lpmR+ANcKl6LP2g2ULUtPnZLuN7FifeYR2ujR+3heNFOiyQcqGaiIVaTkTewc6I8UO6u13Bd0Ws7",
+	"Nd9XutgBUeQYSUNx27wP0yApwhIhWK77hI120LGO3LU4ki3XutLSaRNlNSAS/XRji11IMKDuMDc88uRi",
+	"zMq13C19mdeW6/9WW22NRP2aulOnjZhZDAIC4ib9ekgtwtKlMI/yUjnFIBjeNefgQTCH3s2AoSrCdsUa",
+	"Xk+kubLa5VecTKNX+JgJNZbY1xboefbkWQc6tEbyeqXPvY22SiswagYVJRvFxubs1wi6O7027TVRih1+",
+	"0tdxrNRPRNpxKX5bCDqt4e2vschQBhSUKQDPuEKyLAouTBX3makL77rpSgT3RNp6BaEfSEjhtzEFL59H",
+	"WKMWer4bZ3yR8HO9tEcMQW/jiFrhoUfiiFrBooD1KlRyH05wVYnXByJc+EHbyN57FNfcMaKgW/zDbymS",
+	"wLfRf7w4gkAaB4oiKCpS8/RMwXWS2yyJ+LcPWrMt3ukESTwBtUBzTOfgjt7LV384OkanocC3Ps6LurSz",
+	"Iupcftd2WF+EXvRf/qRukmRrqeVfSywwU6ZRVbQjz2rPq6rhf63ZVa2zlfEjhTExtfZxyywHhvsab4mr",
+	"KiEJe0ZCfVdvHtAQVbBFw+omOerOa0t3h4uzCclvJYVuxf0/lBRk7yuoS68Xcsg0CbOvA9eZR6JsqmaV",
+	"e3WHgKqzoFw1GhSEr70wcrf+JHLNIW0RJzxRIFbzuv3J97xVH2uA+ivVyOpr3EYnexQ2v7DxD04balAJ",
+	"6mclpoOIM3stzXRg64eugroflTywdvJvSh6GIhx7H5IwXFzlOmPkqRtzCUoRNn3cs765lgMe92F3hyi4",
+	"bheJpJsT9W8JpQN5R1Q6SxCDOYiBr7lqKtoc7XAlxGXaD5hIE+foF0EkqtMLhQz1nz15hn5XhUIeo7f8",
+	"DkzxI6Js+oNbOrqZUj7G9FhPN8KpOkHXPT6ZXPdutAaLMxtTabc08oPQLbgsCn/tkDyHjGAFdKG//uTo",
+	"xFxNNbDYUpxmHnSHXXwMZuuLjpjTJkaeu50bejv6EaYXDRpt8ww9nNz6dfLIqcGmTdhRgthQ7UcUksPx",
+	"6GndV6dsnJAvGmT2/scfNUsEgtzv/BRE3g5MwO8GafkDkbdnbtxjphT7ZRxSUCbyFnkYHEheFvU5tzwa",
+	"NXoaycj2kKRgVd/lgr1ZI826W3KOaSm5bcDL2mSdvWeqheFtZcheIsXvYhVsa24mYIfpOXTOMi3V1Kfu",
+	"S1DSloEZKW51FxPJQiS6hcLeCDOT17g42qUsR5sade5aVlofWqQQzapfEPVnBAQW6WwxwHdYwNELlGKR",
+	"EYapbds34SKFrE2RWk9zX4ciVV/j4zi3mgUQvkj/iQZFuoilneq/+J4D6y6FSzemc0YgHCzTPPTUZhPe",
+	"S3p3zlSU9FJBFEmjvcYfJA++SyOg35KZ3+L8Ea38nugOVbk40PB2rXhqPGJTaHB6+yD5M6fprYN5HOvr",
+	"d25fPVy7ktO0itDEDng7dippQC8vrXRzcPC9KxXU4HcIJ4Re66hkitCuFeBbe0Qud8SvZt6jieOXpQgN",
+	"4EAKrsTK1dXbQxCFAMnp/GHo4oOd+8Ck0Y7mFWR+FchzUKjwl2NWYkoXu6JPq6obhAY7pFtrTGt+GZmo",
+	"0/947x/yWtdYecxb3VLFoS51Mxvqm5QqFRLrChD20dFuLn077UO7HywqvmJfe0EYg2zkoBqvibjqbteY",
+	"aPW1f33edccQX71v3dCkafBE9K8eKTu60WsUPnRTdTjN/+pHfn0H2M4HUtjT/vhyU3nbj6ktaPG2/TG0",
+	"Z96/SceTXZOfrszorY+if7dkDrPNA5KOA9shGB1YhjDDdCGJK19Iqc/hMJXJI4lU2yR0PGQyld4KpKUx",
+	"3eipx4AFiNNSzXonP3/UGLfd2O2HS0F7J70hLshw/tTQg9vPatsml9zv8s5DXoEpOWtK4dRt581t2LSa",
+	"lTgU23kNQuu3pOptRaSts0w4S3ybo1rhKNfLaHXO8+1SHdx8vMq++BS3e5gtuuJCfYtq4wNqdOeMLijU",
+	"oKh6K7hOjUnwUkrUzyAlGQxxqmrTQr1E06eWuEuztCB66fOsNkM431bfrztgkqVQoyQ4x6qpnBdldaKQ",
+	"IelIw+UJV7a6Wo7jp2jqlUxsxrL5bkZU4qoPJihk43tMNbgsBu6CC7X6nqvk8Pnj5/8OAAD//2XM3suJ",
+	"7gAA",
 }
 
 // GetSwagger returns the content of the embedded swagger specification file

internal/httpapi/impl.go

@@ -75,22 +75,31 @@ func (s *Server) resolveEntityID(ctx context.Context, idOrSlug string) (uuid.UUI
 	return id, err
 }
 
-// entityCols requires the entities table to be aliased as `e`.
+// entityCols requires the entities table to be aliased as `e`, with
+// entity_status left-joined and aliased as `st` (see withEntityStatus).
 const entityCols = `e.id, e.slug, e.type, e.name, e.state, e.attributes,
-                    e.maintenance_until, e.version, e.created_at, e.updated_at`
+                    e.maintenance_until, e.version, e.created_at, e.updated_at,
+                    st.health, st.last_check_at`
 
 func scanEntity(row pgx.Row) (gen.Entity, error) {
 	var e gen.Entity
 	var state *string
 	var attrsJSON []byte
 	var maint *time.Time
+	var health *string
+	var lastCheckAt *time.Time
 	err := row.Scan(&e.Id, &e.Slug, &e.Type, &e.Name, &state, &attrsJSON,
-		&maint, &e.Version, &e.CreatedAt, &e.UpdatedAt)
+		&maint, &e.Version, &e.CreatedAt, &e.UpdatedAt, &health, &lastCheckAt)
 	if err != nil {
 		return e, err
 	}
 	e.State = state
 	e.MaintenanceUntil = maint
+	if health != nil {
+		h := gen.EntityHealth(*health)
+		e.Health = &h
+	}
+	e.LastCheckAt = lastCheckAt
 	var attrs map[string]any
 	if len(attrsJSON) > 0 && json.Unmarshal(attrsJSON, &attrs) == nil && len(attrs) > 0 {
 		e.Attributes = &attrs
@@ -113,6 +122,7 @@ func (s *Server) ListEntities(ctx context.Context, req gen.ListEntitiesRequestOb
 		)
 		SELECT ` + entityCols + ` FROM entities e
 		JOIN entity_types et ON et.name = e.type
+		LEFT JOIN entity_status st ON st.entity_id = e.id
 		WHERE e.type IN (SELECT name FROM tt)
 		  AND ($2::text IS NULL OR e.state = $2)
 		  AND ($3::text IS NULL OR et.domain = $3)
@@ -159,7 +169,7 @@ func (s *Server) GetEntity(ctx context.Context, req gen.GetEntityRequestObject)
 		return nil, err
 	}
 	e, err := scanEntity(s.pool.QueryRow(ctx,
-		"SELECT "+entityCols+" FROM entities e WHERE e.id = $1", id))
+		"SELECT "+entityCols+" FROM entities e LEFT JOIN entity_status st ON st.entity_id = e.id WHERE e.id = $1", id))
 	if err != nil {
 		return nil, err
 	}
@@ -231,6 +241,7 @@ func (s *Server) GetBlastRadius(ctx context.Context, req gen.GetBlastRadiusReque
 		SELECT `+entityCols+`, b.depth
 		FROM blast_radius($1, $2) b
 		JOIN entities e ON e.id = b.entity_id
+		LEFT JOIN entity_status st ON st.entity_id = e.id
 		ORDER BY b.depth, e.slug`, id, depth)
 	if err != nil {
 		return nil, err
@@ -246,13 +257,20 @@ func (s *Server) GetBlastRadius(ctx context.Context, req gen.GetBlastRadiusReque
 		var state *string
 		var attrsJSON []byte
 		var maint *time.Time
+		var health *string
+		var lastCheckAt *time.Time
 		var d int
 		if err := rows.Scan(&e.Id, &e.Slug, &e.Type, &e.Name, &state, &attrsJSON,
-			&maint, &e.Version, &e.CreatedAt, &e.UpdatedAt, &d); err != nil {
+			&maint, &e.Version, &e.CreatedAt, &e.UpdatedAt, &health, &lastCheckAt, &d); err != nil {
 			return nil, err
 		}
 		e.State = state
 		e.MaintenanceUntil = maint
+		if health != nil {
+			h := gen.EntityHealth(*health)
+			e.Health = &h
+		}
+		e.LastCheckAt = lastCheckAt
 		var attrs map[string]any
 		if len(attrsJSON) > 0 && json.Unmarshal(attrsJSON, &attrs) == nil && len(attrs) > 0 {
 			e.Attributes = &attrs
@@ -283,10 +301,13 @@ func (s *Server) GetGraph(ctx context.Context, req gen.GetGraphRequestObject) (g
 		nodes, err = s.queryEntities(ctx, `
 			SELECT `+entityCols+`
 			FROM blast_radius($1, $2, $3) b JOIN entities e ON e.id = b.entity_id
+			LEFT JOIN entity_status st ON st.entity_id = e.id
 			ORDER BY e.slug`, rootID, depth, req.Params.RelType)
 	} else {
 		nodes, err = s.queryEntities(ctx, `
-			SELECT `+entityCols+` FROM entities e ORDER BY e.slug LIMIT $1`,
+			SELECT `+entityCols+` FROM entities e
+			LEFT JOIN entity_status st ON st.entity_id = e.id
+			ORDER BY e.slug LIMIT $1`,
 			graphNodeCap+1)
 		if err == nil && len(nodes) > graphNodeCap {
 			nodes = nodes[:graphNodeCap]
@@ -322,9 +343,44 @@ func (s *Server) GetGraph(ctx context.Context, req gen.GetGraphRequestObject) (g
 	if truncated {
 		resp.Truncated = &truncated
 	}
+
+	if req.Params.Include != nil {
+		for _, inc := range *req.Params.Include {
+			if inc == gen.Status {
+				health, herr := s.entityHealthByID(ctx, ids)
+				if herr != nil {
+					return nil, herr
+				}
+				resp.Health = &health
+				break
+			}
+		}
+	}
+
 	return resp, nil
 }
 
+// entityHealthByID returns entity_status.health keyed by entity id, for the
+// given id set (used by GetGraph's include=status).
+func (s *Server) entityHealthByID(ctx context.Context, ids []uuid.UUID) (map[string]gen.GraphViewHealth, error) {
+	health := make(map[string]gen.GraphViewHealth, len(ids))
+	rows, err := s.pool.Query(ctx,
+		`SELECT entity_id, health FROM entity_status WHERE entity_id = ANY($1)`, ids)
+	if err != nil {
+		return nil, err
+	}
+	defer rows.Close()
+	for rows.Next() {
+		var id uuid.UUID
+		var h string
+		if err := rows.Scan(&id, &h); err != nil {
+			return nil, err
+		}
+		health[id.String()] = gen.GraphViewHealth(h)
+	}
+	return health, rows.Err()
+}
+
 func (s *Server) queryEntities(ctx context.Context, query string, args ...any) ([]gen.Entity, error) {
 	rows, err := s.pool.Query(ctx, query, args...)
 	if err != nil {
@@ -488,14 +544,18 @@ func (s *Server) GetFleetHealth(ctx context.Context, req gen.GetFleetHealthReque
 		Type        string                          `json:"type"`
 	}{}
 
+	// Exclude 'check' entities (internal probes) — only entities actually
+	// being monitored should count toward fleet health.
 	rows, err := s.pool.Query(ctx, `
 		SELECT e.slug, e.type, st.health, st.last_check_at
 		FROM entity_status st JOIN entities e ON e.id = st.entity_id
+		WHERE e.type <> 'check'
 		ORDER BY e.slug`)
 	if err != nil {
 		return nil, err
 	}
 	defer rows.Close()
+	stale := 0
 	for rows.Next() {
 		var slug, typ, health string
 		var lastCheck *time.Time
@@ -509,6 +569,8 @@ func (s *Server) GetFleetHealth(ctx context.Context, req gen.GetFleetHealthReque
 			resp.Summary.Degraded++
 		case "down":
 			resp.Summary.Down++
+		case "stale":
+			stale++
 		default:
 			resp.Summary.Unknown++
 		}
@@ -525,6 +587,9 @@ func (s *Server) GetFleetHealth(ctx context.Context, req gen.GetFleetHealthReque
 			Type:        typ,
 		})
 	}
+	if stale > 0 {
+		resp.Summary.Stale = &stale
+	}
 	return resp, rows.Err()
 }
 
@@ -920,6 +985,8 @@ func (s *Server) CreateEntity(ctx context.Context, req gen.CreateEntityRequestOb
 		return nil, eventErr
 	}
 
+	ensureDefaultChecks(ctx, tx, inserted.ID, slug, req.Body.Type, attrsJSON)
+
 	if err := tx.Commit(ctx); err != nil {
 		return nil, err
 	}
@@ -1184,6 +1251,8 @@ func (s *Server) EnrollClient(ctx context.Context, req gen.EnrollClientRequestOb
 		"info", "oikos-api", "",
 		map[string]any{"slug": req.Body.Slug, "type": current.Type})
 
+	ensureDefaultChecks(ctx, tx, id, req.Body.Slug, current.Type, attrsJSON)
+
 	if err := tx.Commit(ctx); err != nil {
 		return nil, err
 	}

internal/httpapi/phase3.go

@@ -317,7 +317,7 @@ func (s *Server) CreateCheck(ctx context.Context, req gen.CreateCheckRequestObje
 	entity, err := q.InsertEntity(ctx, sqlcgen.InsertEntityParams{
 		ID:         id,
 		Slug:       slug,
-		Type:       "check_def",
+		Type:       "check",
 		Name:       slug,
 		Attributes: []byte("{}"),
 	})
@@ -1835,10 +1835,6 @@ func (s *Server) QueryMetrics(ctx context.Context, req gen.QueryMetricsRequestOb
 	if req.Params.EntityId == nil || *req.Params.EntityId == "" {
 		return nil, fmt.Errorf("%w: entity_id is required", domain.ErrInvalidInput)
 	}
-	if req.Params.Metric == nil || len(*req.Params.Metric) == 0 {
-		return nil, fmt.Errorf("%w: metric is required", domain.ErrInvalidInput)
-	}
-
 	entityID, err := s.resolveEntityID(ctx, *req.Params.EntityId)
 	if err != nil {
 		return nil, err
@@ -1853,8 +1849,33 @@ func (s *Server) QueryMetrics(ctx context.Context, req gen.QueryMetricsRequestOb
 		to = *req.Params.To
 	}
 
+	var metricNames []string
+	if req.Params.Metric != nil && len(*req.Params.Metric) > 0 {
+		metricNames = *req.Params.Metric
+	} else {
+		// metric omitted: report every metric recorded for this entity in range.
+		rows, err := s.pool.Query(ctx, `
+			SELECT DISTINCT metric FROM metric_samples
+			WHERE entity_id = $1 AND ts >= $2 AND ts <= $3
+			ORDER BY metric`, entityID, from, to)
+		if err != nil {
+			return nil, err
+		}
+		for rows.Next() {
+			var name string
+			if err := rows.Scan(&name); err != nil {
+				rows.Close()
+				return nil, err
+			}
+			metricNames = append(metricNames, name)
+		}
+		if err := rows.Err(); err != nil {
+			return nil, err
+		}
+	}
+
 	items := []gen.MetricSeries{}
-	for _, metricName := range *req.Params.Metric {
+	for _, metricName := range metricNames {
 		series := gen.MetricSeries{
 			EntityId: entityID.String(),
 			Metric:   metricName,

internal/mcp/server.go

@@ -125,6 +125,7 @@ func newServer(pool *db.Pool, agentID uuid.UUID) *mcp.Server {
 		return queryRows(ctx, pool, `
 			SELECT e.slug, e.type, st.health, st.last_check_at
 			FROM entity_status st JOIN entities e ON e.id = st.entity_id
+			WHERE e.type <> 'check'
 			ORDER BY e.slug`), nil
 	})
 

internal/scheduler/scheduler.go

@@ -7,10 +7,15 @@ import (
 	"context"
 	"crypto/tls"
 	"encoding/json"
+	"errors"
 	"fmt"
 	"log/slog"
 	"net"
 	"net/http"
+	"os/exec"
+	"regexp"
+	"runtime"
+	"strconv"
 	"time"
 
 	"github.com/dtoro/oikos/internal/config"
@@ -22,6 +27,11 @@ import (
 	"golang.org/x/sys/unix"
 )
 
+var (
+	sshKeyPath string
+	sshUser    string
+)
+
 // Run starts the scheduler loop. Blocks until ctx is cancelled.
 func Run(ctx context.Context, pool *db.Pool, cfg config.Config) {
 	slog.Info("scheduler: starting", "interval", cfg.SchedulerInterval)
@@ -30,6 +40,12 @@ func Run(ctx context.Context, pool *db.Pool, cfg config.Config) {
 		interval = 30 * time.Second
 	}
 
+	sshKeyPath = cfg.SSHKeyPath
+	sshUser = cfg.SSHUser
+	if sshUser == "" {
+		sshUser = "root"
+	}
+
 	ticker := time.NewTicker(interval)
 	defer ticker.Stop()
 
@@ -78,85 +94,94 @@ func runCheckPass(ctx context.Context, pool *db.Pool) {
 }
 
 // runCheck executes a single check and processes the result.
+//
+// check_defs.entity_id identifies the *check* (probe) entity itself;
+// check_defs.target_id identifies the entity actually being observed (the
+// host/service/etc). Health, metrics, and events must attach to the target
+// so the observed entity's own record reflects reality — not the internal
+// probe. Signals stay keyed by the check entity (cd.EntityID), matching how
+// they are created below and resolved elsewhere.
 func runCheck(ctx context.Context, pool *db.Pool, cd sqlcgen.ListEnabledCheckDefsRow) {
 	q := sqlcgen.New(pool)
 	start := time.Now()
 
-	health, signalKind, evidence, checkErr := executeCheck(ctx, cd)
+	result := executeCheck(ctx, cd)
 
 	latency := time.Since(start).Milliseconds()
 
-	// Write metric
-	_ = q.InsertMetricSample(ctx, sqlcgen.InsertMetricSampleParams{
-		EntityID: cd.EntityID,
-		Metric:   "probe_latency_ms",
-		Value:    float64(latency),
-		Tags:     []byte(`{}`),
-	})
+	if result.metrics == nil {
+		result.metrics = make(map[string]float64)
+	}
+	result.metrics["probe_latency_ms"] = float64(latency)
 
-	if checkErr != nil {
-		slog.Warn("scheduler: check failed",
-			"entity", cd.EntitySlug, "kind", cd.Kind, "error", checkErr)
+	targetID := cd.EntityID
+	if cd.TargetID != nil {
+		targetID = *cd.TargetID
 	}
 
-	prevHealth := currentHealth(ctx, pool, cd.EntityID)
+	for metric, value := range result.metrics {
+		_ = q.InsertMetricSample(ctx, sqlcgen.InsertMetricSampleParams{
+			EntityID: targetID,
+			Metric:   metric,
+			Value:    value,
+			Tags:     []byte(`{}`),
+		})
+	}
 
-	if signalKind == "" || health == "healthy" {
-		// Recovery: resolve any open signal for this check
-		resolveSignal(ctx, pool, cd.EntityID, cd.EntitySlug)
-		// Update entity_status to healthy
+	if result.err != nil {
+		slog.Warn("scheduler: check failed",
+			"entity", cd.EntitySlug, "kind", cd.Kind, "error", result.err)
+	}
+
+	prevHealth := currentHealth(ctx, pool, targetID)
+
+	if result.signalKind == "" || result.health == "healthy" {
+		resolveSignal(ctx, pool, cd.EntityID, targetID, cd.EntitySlug)
 		_ = q.UpsertEntityStatus(ctx, sqlcgen.UpsertEntityStatusParams{
-			EntityID:    cd.EntityID,
+			EntityID:    targetID,
 			Health:      "healthy",
 			LastCheckAt: &[]time.Time{time.Now()}[0],
 			Details:     []byte(`{}`),
 		})
 		if prevHealth != "" && prevHealth != "healthy" {
-			emitSchedulerEvent(ctx, pool, "health.changed", cd.EntityID, "info",
+			emitSchedulerEvent(ctx, pool, "health.changed", targetID, "info",
 				map[string]any{"slug": cd.EntitySlug, "from": prevHealth, "to": "healthy"})
 		}
 		return
 	}
 
-	// Failure: upsert signal (dedup via partial unique index)
 	slog.Warn("scheduler: raising signal",
-		"entity", cd.EntitySlug, "kind", signalKind, "evidence", evidence)
+		"entity", cd.EntitySlug, "kind", result.signalKind, "evidence", result.evidence)
 
-	severity := "warning"
-	if signalKind == "down" {
-		severity = "critical"
-	}
+	severity := evaluateSeverity(cd.Kind, result.signalKind, cd.Config, result.metrics)
 
 	sig, err := q.UpsertSignal(ctx, sqlcgen.UpsertSignalParams{
 		EntityID:       cd.EntityID,
-		Kind:           signalKind,
+		Kind:           result.signalKind,
 		Severity:       severity,
 		TargetEntityID: cd.TargetID,
-		Evidence:       &evidence,
+		Evidence:       &result.evidence,
 	})
 	if err != nil {
 		slog.Error("scheduler: upsert signal", "error", err)
 		return
 	}
 
-	// Update entity_status
 	_ = q.UpsertEntityStatus(ctx, sqlcgen.UpsertEntityStatusParams{
-		EntityID:    cd.EntityID,
-		Health:      health,
+		EntityID:    targetID,
+		Health:      result.health,
 		LastCheckAt: &[]time.Time{time.Now()}[0],
 		Details:     []byte(`{}`),
 	})
-	_ = sig // used for flap detection below
+	_ = sig
 
-	// Emit only on transition into failure so a persistently-down entity
-	// doesn't flood the stream every tick.
 	if prevHealth == "" || prevHealth == "healthy" {
-		emitSchedulerEvent(ctx, pool, "signal.raised", cd.EntityID, severity,
-			map[string]any{"slug": cd.EntitySlug, "kind": signalKind, "evidence": evidence})
+		emitSchedulerEvent(ctx, pool, "signal.raised", targetID, severity,
+			map[string]any{"slug": cd.EntitySlug, "kind": result.signalKind, "evidence": result.evidence})
 	}
-	if prevHealth != health {
-		emitSchedulerEvent(ctx, pool, "health.changed", cd.EntityID, severity,
-			map[string]any{"slug": cd.EntitySlug, "from": prevHealth, "to": health})
+	if prevHealth != result.health {
+		emitSchedulerEvent(ctx, pool, "health.changed", targetID, severity,
+			map[string]any{"slug": cd.EntitySlug, "from": prevHealth, "to": result.health})
 	}
 }
 
@@ -175,21 +200,23 @@ func emitSchedulerEvent(ctx context.Context, pool *db.Pool, eventType string, en
 	_ = observability.Event(ctx, sqlcgen.New(pool), eventType, &entityID, severity, "scheduler", "", data)
 }
 
-// resolveSignal resolves any open signal for the given check entity.
-func resolveSignal(ctx context.Context, pool *db.Pool, entityID uuid.UUID, slug string) {
+// resolveSignal resolves any open signal raised by the given check entity.
+// checkID matches how signals are keyed (UpsertSignal uses the check's own
+// entity id); targetID is the observed entity whose status this affects.
+func resolveSignal(ctx context.Context, pool *db.Pool, checkID, targetID uuid.UUID, slug string) {
 	q := sqlcgen.New(pool)
 	// Check if there's an open signal on this entity
 	tag, err := pool.Exec(ctx, `UPDATE signals SET state = 'resolved', updated_at = now()
-		WHERE entity_id = $1 AND state = 'raised'`, entityID)
+		WHERE entity_id = $1 AND state = 'raised'`, checkID)
 	if err != nil {
 		return
 	}
 	if tag.RowsAffected() > 0 {
-		emitSchedulerEvent(ctx, pool, "signal.resolved", entityID, "info",
+		emitSchedulerEvent(ctx, pool, "signal.resolved", targetID, "info",
 			map[string]any{"slug": slug})
 	}
 	_ = q.UpsertEntityStatus(ctx, sqlcgen.UpsertEntityStatusParams{
-		EntityID:    entityID,
+		EntityID:    targetID,
 		Health:      "healthy",
 		LastCheckAt: &[]time.Time{time.Now()}[0],
 		Details:     []byte(`{}`),
@@ -197,8 +224,17 @@ func resolveSignal(ctx context.Context, pool *db.Pool, entityID uuid.UUID, slug
 	slog.Info("scheduler: signal resolved", "entity", slug)
 }
 
+// checkResult bundles the outcome of a single check execution.
+type checkResult struct {
+	health     string
+	signalKind string
+	evidence   string
+	metrics    map[string]float64
+	err        error
+}
+
 // executeCheck dispatches to the appropriate checker by kind.
-func executeCheck(ctx context.Context, cd sqlcgen.ListEnabledCheckDefsRow) (health string, signalKind string, evidence string, err error) {
+func executeCheck(ctx context.Context, cd sqlcgen.ListEnabledCheckDefsRow) checkResult {
 	switch cd.Kind {
 	case "http":
 		return checkHTTP(ctx, cd)
@@ -208,8 +244,12 @@ func executeCheck(ctx context.Context, cd sqlcgen.ListEnabledCheckDefsRow) (heal
 		return checkDisk(ctx, cd)
 	case "cert-expiry":
 		return checkCertExpiry(ctx, cd)
+	case "ping":
+		return checkPing(ctx, cd)
+	case "ssh-script":
+		return checkSSHScript(ctx, cd)
 	default:
-		return "unknown", "", "", nil
+		return checkResult{health: "unknown"}
 	}
 }
 
@@ -224,12 +264,76 @@ func housekeeping(ctx context.Context, pool *db.Pool) {
 		slog.Error("scheduler: prune idempotency keys", "error", err)
 	}
 
+	staleSweep(ctx, pool)
+
 	// Log housekeeping completion
 	slog.Debug("scheduler: housekeeping done", "pruned_idempotency_before", cutoff.Format(time.RFC3339))
 }
 
+// staleMultiplier and staleFloor bound how long an entity can go unobserved
+// before its last-known health is no longer trusted. An entity is stale once
+// it has gone longer than staleMultiplier times its fastest enabled check's
+// interval (or staleFloor, whichever is larger) without a fresh observation —
+// covering both a stalled scheduler and a disabled/broken check_def.
+const (
+	staleMultiplier = 3
+	staleFloor      = 5 * time.Minute
+)
+
+// staleSweep marks entities whose last observation has aged past their
+// check's expected cadence as 'stale', so the system never reports an old
+// health value as if it were current. Runs once per housekeeping pass.
+func staleSweep(ctx context.Context, pool *db.Pool) {
+	rows, err := pool.Query(ctx, `
+		SELECT e.id, e.slug, st.health
+		FROM entity_status st
+		JOIN entities e ON e.id = st.entity_id
+		JOIN (
+			SELECT target_id, MIN(interval_s) AS min_interval
+			FROM check_defs
+			WHERE enabled AND target_id IS NOT NULL
+			GROUP BY target_id
+		) iv ON iv.target_id = st.entity_id
+		WHERE st.health <> 'stale'
+		  AND (st.last_check_at IS NULL
+		       OR st.last_check_at < now() - make_interval(secs => GREATEST(iv.min_interval * $1, $2)))`,
+		staleMultiplier, int(staleFloor.Seconds()))
+	if err != nil {
+		slog.Error("scheduler: stale sweep query", "error", err)
+		return
+	}
+	defer rows.Close()
+
+	type staleEntity struct {
+		id     uuid.UUID
+		slug   string
+		health string
+	}
+	var stale []staleEntity
+	for rows.Next() {
+		var se staleEntity
+		if err := rows.Scan(&se.id, &se.slug, &se.health); err != nil {
+			continue
+		}
+		stale = append(stale, se)
+	}
+	rows.Close()
+
+	for _, se := range stale {
+		_, err := pool.Exec(ctx,
+			`UPDATE entity_status SET health = 'stale', updated_at = now() WHERE entity_id = $1`, se.id)
+		if err != nil {
+			slog.Error("scheduler: mark stale", "entity", se.slug, "error", err)
+			continue
+		}
+		slog.Warn("scheduler: entity stale", "entity", se.slug, "prev_health", se.health)
+		emitSchedulerEvent(ctx, pool, "health.stale", se.id, "warning",
+			map[string]any{"slug": se.slug, "from": se.health, "to": "stale"})
+	}
+}
+
 // checkHTTP performs an HTTP health check.
-func checkHTTP(ctx context.Context, cd sqlcgen.ListEnabledCheckDefsRow) (string, string, string, error) {
+func checkHTTP(ctx context.Context, cd sqlcgen.ListEnabledCheckDefsRow) checkResult {
 	cfg := struct {
 		URL            string `json:"url"`
 		ExpectedStatus int    `json:"expected_status"`
@@ -241,7 +345,7 @@ func checkHTTP(ctx context.Context, cd sqlcgen.ListEnabledCheckDefsRow) (string,
 		_ = json.Unmarshal(cd.Config, &cfg)
 	}
 	if cfg.URL == "" {
-		return "healthy", "", "", nil
+		return checkResult{health: "healthy"}
 	}
 
 	timeout := time.Duration(cd.TimeoutS) * time.Second
@@ -258,25 +362,35 @@ func checkHTTP(ctx context.Context, cd sqlcgen.ListEnabledCheckDefsRow) (string,
 
 	req, err := http.NewRequestWithContext(ctx, http.MethodGet, cfg.URL, nil)
 	if err != nil {
-		return "down", "http", fmt.Sprintf("invalid URL %q: %v", cfg.URL, err), err
+		return checkResult{
+			health: "down", signalKind: "http",
+			evidence: fmt.Sprintf("invalid URL %q: %v", cfg.URL, err),
+			err:      err,
+		}
 	}
 
 	resp, err := client.Do(req)
 	if err != nil {
-		return "down", "http", fmt.Sprintf("GET %s: %v", cfg.URL, err), err
+		return checkResult{
+			health: "down", signalKind: "http",
+			evidence: fmt.Sprintf("GET %s: %v", cfg.URL, err),
+			err:      err,
+		}
 	}
 	defer resp.Body.Close()
 
 	if resp.StatusCode != cfg.ExpectedStatus {
-		return "degraded", "http",
-			fmt.Sprintf("GET %s returned %d (expected %d)", cfg.URL, resp.StatusCode, cfg.ExpectedStatus), nil
+		return checkResult{
+			health: "degraded", signalKind: "http",
+			evidence: fmt.Sprintf("GET %s returned %d (expected %d)", cfg.URL, resp.StatusCode, cfg.ExpectedStatus),
+		}
 	}
 
-	return "healthy", "", "", nil
+	return checkResult{health: "healthy"}
 }
 
 // checkTCP performs a TCP dial check.
-func checkTCP(ctx context.Context, cd sqlcgen.ListEnabledCheckDefsRow) (string, string, string, error) {
+func checkTCP(ctx context.Context, cd sqlcgen.ListEnabledCheckDefsRow) checkResult {
 	cfg := struct {
 		Host string `json:"host"`
 		Port int    `json:"port"`
@@ -285,7 +399,7 @@ func checkTCP(ctx context.Context, cd sqlcgen.ListEnabledCheckDefsRow) (string,
 		_ = json.Unmarshal(cd.Config, &cfg)
 	}
 	if cfg.Host == "" || cfg.Port == 0 {
-		return "healthy", "", "", nil
+		return checkResult{health: "healthy"}
 	}
 
 	timeout := time.Duration(cd.TimeoutS) * time.Second
@@ -296,14 +410,18 @@ func checkTCP(ctx context.Context, cd sqlcgen.ListEnabledCheckDefsRow) (string,
 	addr := net.JoinHostPort(cfg.Host, fmt.Sprintf("%d", cfg.Port))
 	conn, err := net.DialTimeout("tcp", addr, timeout)
 	if err != nil {
-		return "down", "tcp", fmt.Sprintf("dial %s: %v", addr, err), err
+		return checkResult{
+			health: "down", signalKind: "tcp",
+			evidence: fmt.Sprintf("dial %s: %v", addr, err),
+			err:      err,
+		}
 	}
 	conn.Close()
-	return "healthy", "", "", nil
+	return checkResult{health: "healthy"}
 }
 
-// checkDisk performs a disk usage check via local or SSH.
-func checkDisk(ctx context.Context, cd sqlcgen.ListEnabledCheckDefsRow) (string, string, string, error) {
+// checkDisk performs a disk usage check.
+func checkDisk(ctx context.Context, cd sqlcgen.ListEnabledCheckDefsRow) checkResult {
 	cfg := struct {
 		Path         string `json:"path"`
 		ThresholdPct int    `json:"threshold_pct"`
@@ -315,29 +433,45 @@ func checkDisk(ctx context.Context, cd sqlcgen.ListEnabledCheckDefsRow) (string,
 		_ = json.Unmarshal(cd.Config, &cfg)
 	}
 
-	// Use unix.Statfs for disk usage.
 	var stat unix.Statfs_t
 	if err := unix.Statfs(cfg.Path, &stat); err != nil {
-		return "down", "disk", fmt.Sprintf("statfs %s: %v", cfg.Path, err), err
+		return checkResult{
+			health: "down", signalKind: "disk",
+			evidence: fmt.Sprintf("statfs %s: %v", cfg.Path, err),
+			err:      err,
+		}
 	}
 
 	total := stat.Blocks * uint64(stat.Bsize)
 	free := stat.Bfree * uint64(stat.Bsize)
 	if total == 0 {
-		return "healthy", "", "", nil
+		return checkResult{health: "healthy"}
 	}
 
 	usedPct := float64(total-free) / float64(total) * 100
-	if usedPct > float64(cfg.ThresholdPct) {
-		return "degraded", "disk",
-			fmt.Sprintf("%s %.1f%% full (threshold %d%%)", cfg.Path, usedPct, cfg.ThresholdPct), nil
+	inodePct := 0.0
+	if stat.Files > 0 {
+		inodePct = float64(stat.Files-stat.Ffree) / float64(stat.Files) * 100
 	}
 
-	return "healthy", "", "", nil
+	metrics := map[string]float64{
+		"disk_used_pct":  usedPct,
+		"disk_inode_pct": inodePct,
+	}
+
+	if usedPct > float64(cfg.ThresholdPct) {
+		return checkResult{
+			health: "degraded", signalKind: "disk",
+			evidence:   fmt.Sprintf("%s %.1f%% full (threshold %d%%)", cfg.Path, usedPct, cfg.ThresholdPct),
+			metrics:    metrics,
+		}
+	}
+
+	return checkResult{health: "healthy", metrics: metrics}
 }
 
 // checkCertExpiry checks TLS certificate expiry.
-func checkCertExpiry(ctx context.Context, cd sqlcgen.ListEnabledCheckDefsRow) (string, string, string, error) {
+func checkCertExpiry(ctx context.Context, cd sqlcgen.ListEnabledCheckDefsRow) checkResult {
 	cfg := struct {
 		Host     string `json:"host"`
 		Port     int    `json:"port"`
@@ -352,7 +486,7 @@ func checkCertExpiry(ctx context.Context, cd sqlcgen.ListEnabledCheckDefsRow) (s
 		_ = json.Unmarshal(cd.Config, &cfg)
 	}
 	if cfg.Host == "" {
-		return "healthy", "", "", nil
+		return checkResult{health: "healthy"}
 	}
 
 	timeout := time.Duration(cd.TimeoutS) * time.Second
@@ -365,31 +499,264 @@ func checkCertExpiry(ctx context.Context, cd sqlcgen.ListEnabledCheckDefsRow) (s
 	d := tls.Dialer{Config: &tls.Config{InsecureSkipVerify: true}}
 	conn, err := d.DialContext(ctx, "tcp", addr)
 	if err != nil {
-		return "down", "cert-expiry", fmt.Sprintf("TLS dial %s: %v", addr, err), err
+		return checkResult{
+			health: "down", signalKind: "cert-expiry",
+			evidence: fmt.Sprintf("TLS dial %s: %v", addr, err),
+			err:      err,
+		}
 	}
 	defer conn.Close()
 
 	tlsConn := conn.(*tls.Conn)
-	// Use crypto/tls ConnectionState to get verified chains
 	cs := tlsConn.ConnectionState()
 	if len(cs.PeerCertificates) == 0 {
-		return "down", "cert-expiry", "no peer certificates", nil
+		return checkResult{
+			health: "down", signalKind: "cert-expiry",
+			evidence: "no peer certificates",
+		}
 	}
 
 	cert := cs.PeerCertificates[0]
 	daysLeft := int(time.Until(cert.NotAfter).Hours() / 24)
 
-	if daysLeft <= cfg.CritDays {
-		return "down", "cert-expiry",
-			fmt.Sprintf("%s expires in %d days (crit=%d)", cfg.Host, daysLeft, cfg.CritDays), nil
-	}
-	if daysLeft <= cfg.WarnDays {
-		return "degraded", "cert-expiry",
-			fmt.Sprintf("%s expires in %d days (warn=%d)", cfg.Host, daysLeft, cfg.WarnDays), nil
+	metrics := map[string]float64{
+		"cert_days_left": float64(daysLeft),
 	}
 
-	return "healthy", "", "", nil
+	if daysLeft <= cfg.CritDays {
+		return checkResult{
+			health: "down", signalKind: "cert-expiry",
+			evidence: fmt.Sprintf("%s expires in %d days (crit=%d)", cfg.Host, daysLeft, cfg.CritDays),
+			metrics:  metrics,
+		}
+	}
+	if daysLeft <= cfg.WarnDays {
+		return checkResult{
+			health: "degraded", signalKind: "cert-expiry",
+			evidence: fmt.Sprintf("%s expires in %d days (warn=%d)", cfg.Host, daysLeft, cfg.WarnDays),
+			metrics:  metrics,
+		}
+	}
+
+	return checkResult{health: "healthy", metrics: metrics}
+}
+
+// checkPing performs an ICMP ping check using the system ping command.
+func checkPing(ctx context.Context, cd sqlcgen.ListEnabledCheckDefsRow) checkResult {
+	cfg := struct {
+		Host  string `json:"host"`
+		Count int    `json:"count"`
+	}{}
+	if len(cd.Config) > 0 {
+		_ = json.Unmarshal(cd.Config, &cfg)
+	}
+	if cfg.Host == "" {
+		return checkResult{health: "healthy"}
+	}
+	if cfg.Count <= 0 {
+		cfg.Count = 1
+	}
+
+	timeout := time.Duration(cd.TimeoutS) * time.Second
+	if timeout <= 0 {
+		timeout = 10 * time.Second
+	}
+
+	deadline := time.Duration(cfg.Count+1) * timeout
+	ctx, cancel := context.WithTimeout(ctx, deadline)
+	defer cancel()
+
+	countStr := strconv.Itoa(cfg.Count)
+	timeoutSec := strconv.Itoa(int(timeout.Seconds()))
+	if timeoutSec == "0" {
+		timeoutSec = "1"
+	}
+
+	cmd := exec.CommandContext(ctx, "ping", "-c", countStr, "-W", timeoutSec, cfg.Host)
+	if runtime.GOOS == "darwin" {
+		cmd = exec.CommandContext(ctx, "ping", "-c", countStr, "-t", timeoutSec, cfg.Host)
+	}
+
+	output, err := cmd.Output()
+	if err != nil {
+		return checkResult{
+			health: "down", signalKind: "ping",
+			evidence: fmt.Sprintf("ping %s: %v", cfg.Host, err),
+			err:      err,
+		}
+	}
+
+	latency := parsePingLatency(output)
+	metrics := map[string]float64{}
+	if latency > 0 {
+		metrics["ping_latency_ms"] = latency
+	}
+
+	return checkResult{health: "healthy", metrics: metrics}
+}
+
+var pingRttRe = regexp.MustCompile(`(?:rtt\s+min\/avg\/max\/mdev|round-trip\s+min\/avg\/max\/stddev)\s*=\s*[\d.]+\/([\d.]+)\/`)
+
+func parsePingLatency(output []byte) float64 {
+	matches := pingRttRe.FindSubmatch(output)
+	if len(matches) < 2 {
+		return 0
+	}
+	val, err := strconv.ParseFloat(string(matches[1]), 64)
+	if err != nil {
+		return 0
+	}
+	return val
+}
+
+// checkSSHScript executes an allowlisted script on a remote host via SSH.
+func checkSSHScript(ctx context.Context, cd sqlcgen.ListEnabledCheckDefsRow) checkResult {
+	cfg := struct {
+		Host   string `json:"host"`
+		Port   int    `json:"port"`
+		User   string `json:"user"`
+		Script string `json:"script"`
+	}{}
+	if len(cd.Config) > 0 {
+		_ = json.Unmarshal(cd.Config, &cfg)
+	}
+	if cfg.Host == "" || cfg.Script == "" {
+		return checkResult{health: "healthy"}
+	}
+	if cfg.Port == 0 {
+		cfg.Port = 22
+	}
+	if cfg.User == "" {
+		cfg.User = sshUser
+	}
+
+	if !allowlistedScript(cfg.Script) {
+		return checkResult{
+			health: "unknown", signalKind: "ssh-script",
+			evidence: fmt.Sprintf("script %q not allowlisted", cfg.Script),
+		}
+	}
+
+	timeout := time.Duration(cd.TimeoutS) * time.Second
+	if timeout <= 0 {
+		timeout = 10 * time.Second
+	}
+
+	ctx, cancel := context.WithTimeout(ctx, timeout)
+	defer cancel()
+
+	scriptPath := "/opt/oikos/checks/" + cfg.Script
+	port := strconv.Itoa(cfg.Port)
+
+	output, err := sshExec(ctx, cfg.Host, port, cfg.User, scriptPath, timeout)
+	if err != nil {
+		return checkResult{
+			health: "down", signalKind: "ssh-script",
+			evidence: fmt.Sprintf("ssh %s:%s %s: %v", cfg.Host, strconv.Itoa(cfg.Port), cfg.Script, err),
+			err:      err,
+		}
+	}
+
+	type scriptOutput struct {
+		Health     string             `json:"health"`
+		SignalKind string             `json:"signalKind"`
+		Evidence   string             `json:"evidence"`
+		Metrics    map[string]float64 `json:"metrics"`
+	}
+	var so scriptOutput
+	if err := json.Unmarshal(output, &so); err != nil {
+		return checkResult{
+			health: "down", signalKind: "ssh-script",
+			evidence: fmt.Sprintf("invalid script output from %s: %v", cfg.Script, err),
+			err:      err,
+		}
+	}
+
+	health := so.Health
+	if health == "" {
+		health = "healthy"
+	}
+
+	metrics := so.Metrics
+	if metrics == nil {
+		metrics = make(map[string]float64)
+	}
+
+	return checkResult{
+		health:     health,
+		signalKind: so.SignalKind,
+		evidence:   so.Evidence,
+		metrics:    metrics,
+	}
+}
+
+var scriptNameRe = regexp.MustCompile(`^[a-z][a-z0-9_-]+\.sh$`)
+
+func allowlistedScript(name string) bool {
+	return scriptNameRe.MatchString(name)
+}
+
+func sshExec(ctx context.Context, host, port, user, cmd string, timeout time.Duration) ([]byte, error) {
+	args := []string{
+		"-o", "ConnectTimeout=" + strconv.Itoa(int(timeout.Seconds())),
+		"-o", "StrictHostKeyChecking=no",
+		"-o", "BatchMode=yes",
+		"-o", "UserKnownHostsFile=/dev/null",
+		"-o", "LogLevel=ERROR",
+	}
+	if sshKeyPath != "" {
+		args = append(args, "-i", sshKeyPath)
+	}
+	if port != "" && port != "22" {
+		args = append(args, "-p", port)
+	}
+	args = append(args, "-l", user, host, cmd)
+	c := exec.CommandContext(ctx, "ssh", args...)
+	out, err := c.Output()
+	if err != nil {
+		var ee *exec.ExitError
+		if errors.As(err, &ee) {
+			return nil, fmt.Errorf("ssh %s: %v (stderr: %s)", host, err, string(ee.Stderr))
+		}
+		return nil, fmt.Errorf("ssh %s: %v", host, err)
+	}
+	return out, nil
 }
 
 
+// metricThreshold defines warn/crit thresholds for a single metric.
+type metricThreshold struct {
+	Warn float64 `json:"warn"`
+	Crit float64 `json:"crit"`
+}
+
+// thresholdsConfig is parsed from check_defs.config.thresholds JSONB.
+type thresholdsConfig map[string]metricThreshold
+
+// evaluateSeverity determines signal severity from check result and thresholds.
+func evaluateSeverity(kind string, signalKind string, config []byte, metrics map[string]float64) string {
+	var thresholds thresholdsConfig
+	if len(config) > 0 {
+		_ = json.Unmarshal(config, &thresholds)
+	}
+
+	for metric, value := range metrics {
+		t, ok := thresholds[metric]
+		if !ok {
+			continue
+		}
+		if t.Crit > 0 && value >= t.Crit {
+			return "critical"
+		}
+		if t.Warn > 0 && value >= t.Warn {
+			return "warning"
+		}
+	}
+
+	if signalKind == "down" {
+		return "critical"
+	}
+	return "warning"
+}
+
 var _ = uuid.UUID{} // ensure uuid import stays

migrations/016_fix_check_status_misattribution.up.sql

@@ -0,0 +1,16 @@
+-- 016_fix_check_status_misattribution.up.sql
+-- The scheduler historically wrote entity_status and metric_samples keyed by
+-- the *check* entity (check_defs.entity_id) instead of the entity being
+-- monitored (check_defs.target_id). Every real host/service/lxc/etc. entity
+-- was therefore permanently stuck at health='unknown' while all observed
+-- health and metrics accumulated on the internal probe entities instead.
+-- The Go fix (scheduler.go) starts writing to target_id going forward; this
+-- migration removes the now-orphaned check-entity rows so dashboard/fleet
+-- health rollups stop double-counting probes as if they were monitored
+-- entities. Historical metric_samples on check entities are left in place
+-- (time-series data, not safe to reattribute retroactively) but are no
+-- longer queried through any entity-scoped view once checks stop being
+-- written to.
+
+DELETE FROM entity_status
+WHERE entity_id IN (SELECT id FROM entities WHERE type = 'check');

plans/2026-07-08-control-room-webui.md

@@ -1,6 +1,20 @@
 # 2026-07-08 — Control room web UI
 
-**Status:** Planned
+**Status:** In Progress — N0-N3 (Nomos amendment: chat home + sessions), M1
+(dashboard/summary, Overview, Entities table, live event feed, shadcn-svelte
+component system), M2 (Operations ledger with approve/deny + cancel, Signals
+page with ack/resolve/mute, live nav badges), and M3 (graph explorer with
+`include=status` health coloring, per-relationship-type edge coloring +
+legend/filter, node-type filter, node search/highlight, entity detail page
+with uPlot metric charts, `#/entity/:slug` route) complete 2026-07-08. Event
+gap-fill (M2's
+other half) landed earlier in commit e8e230b, and approval creation's FK bug
+(gaps-plan A1) was already fixed, unblocking M2. While building M3, also
+fixed `GET /metrics` to make the `metric` query param genuinely optional
+(server now reports every metric recorded for the entity in range) — the
+implementation previously 400'd when it was omitted, contradicting its own
+documented-optional spec. M4 (agent activity, knowledge search page, audit,
+correlation grouping, polish) remains.
 
 ## Goal
 
@@ -31,8 +45,18 @@ Dependencies kept minimal:
 - `d3-force` — graph physics only; render SVG/canvas by hand
 - `uPlot` — ~45 KB canvas time-series, ideal for `/metrics` rollups
 - `openapi-typescript` — dev-only, generates `api-types.d.ts`
-- No SvelteKit (no SSR wanted — the Go binary is the server), no component
-  framework; hash router; hand-rolled dark-theme CSS.
+- No SvelteKit (no SSR wanted — the Go binary is the server); hash router.
+
+*Amendment 2026-07-08 (M1):* component library is
+[shadcn-svelte](https://www.shadcn-svelte.com/) over Tailwind CSS v4
+(`@tailwindcss/vite`), not hand-rolled CSS — Table, Card, Badge, Sidebar,
+Sheet, Select, Input, Button, Tabs, ScrollArea, Tooltip, Dialog,
+Dropdown-menu, Sonner installed via `npx shadcn-svelte add`. The existing
+dark GitHub-style palette (`app.css`) was ported into shadcn's CSS-variable
+theme contract (`--background`, `--card`, `--primary`, etc. under
+`@theme inline`) so old and new components share one palette. `d3-force` /
+`uPlot` remain the plan for the graph/charts milestones (M3), unaffected by
+this change.
 
 Build integration: commit a placeholder `web/dist/index.html` so backend-only
 `go build` never breaks; `make ui` runs the Vite build; add a node stage to

plans/2026-07-08-liveness-drift-and-ux-cohesion.md

@@ -0,0 +1,253 @@
+# 2026-07-08 — Liveness, drift, and UX cohesion
+
+**Status:** Code complete for Phases 1–4 core scope; not yet deployed to the
+live containers (pending explicit go-ahead — see below). Phase 5 partially
+covered by pre-existing endpoints; full CRUD UI deferred.
+
+- **Phase 1 (drift/staleness):** done. Health/metrics/events misattribution
+  fix, staleness sweep, `/entities` health+freshness, dashboard/fleet-health
+  `check`-entity exclusion, Entities table health column. Migration 016
+  applied to the live dev DB (safe cleanup, additive-only).
+- **Phase 2 (detail sidebar + legibility):** done. `EntityDetailContent`
+  extracted and shared between the full `#/entity/:slug` page and a new
+  `EntitySheet` opened from the Entities table (master-detail, no
+  navigation). Adds a **Monitoring** card (per-entity `check_defs`: kind,
+  interval, enabled/disabled with click-to-toggle) and renders attributes as
+  a key/value list instead of raw JSON.
+- **Phase 3 (sessions rejoin chat):** done. Fixed the click-does-nothing bug,
+  added a session rail inside Chat, fixed the local dev proxy to match
+  production's `/agent` prefix-stripping. **Also found and fixed a real
+  latent bug**: persisted `tool_calls` store the `tool_use`/`tool_result` as
+  two entries sharing one `id`; Chat.svelte's keyed `{#each tool (tool.id)}`
+  threw on the duplicate key and silently blanked the entire message list.
+  This had presumably never been noticed because sessions were never
+  clickable before this fix. Fixed in `chat.ts` by merging tool_calls by id
+  before rendering.
+- **Phase 4 (agent efficiency):** core piece done — prior turns' tool
+  calls/results are now replayed into the conversation (previously dropped
+  entirely), and a compact live fleet-health snapshot is injected into the
+  system prompt each turn so the agent starts oriented. Prompt caching and
+  reconsidering the default model are **not done** (lower priority, no
+  measured regression without them).
+- **Phase 5 (CRUD):** `PatchEntity` and a full `/checks` CRUD API
+  (list/create/patch, including enable/disable) already existed server-side;
+  the new Monitoring card's toggle uses `PatchCheck`. **Not done**: a
+  "run check now" endpoint (no scheduler on-demand entrypoint exists yet),
+  relationship editing, and an entity attribute editor UI.
+
+**Not yet deployed** — the live `oikos-api`/`oikos-scheduler`/nomos
+containers still run the pre-fix binaries; rebuilding and restarting them
+needs an explicit go-ahead since it touches the running homelab control
+plane.
+
+Addresses five felt problems with the current system: (1) the agent reports
+stale machine state as if it were fresh, (2) sessions can't be opened and feel
+disconnected from chat, (3) the Nomos agent re-derives state every turn and
+wastes iterations, (4) the UI feels dead — tables with no context, no sense of
+what is monitored, (5) no way to inspect or customize entities and their checks.
+
+The unifying UX principle for this plan: **master-detail with a detail
+sidebar**, not full-page navigation. Selecting an entity, session, or signal
+opens a right-hand detail panel over the current list, so the operator keeps
+context and drills in without losing their place. Full pages remain
+addressable (deep links) but are no longer the primary way to inspect a row.
+
+Sequencing is driven by pain: **drift/staleness is Phase 1.**
+
+---
+
+## Root causes (verified in code)
+
+### Drift / staleness — root cause was worse than a missing TTL
+Live-DB inspection (`oikos-postgres-1`) found the real cause: `check_defs` has
+two entity references — `entity_id` (the internal probe/"check" entity) and
+`target_id` (the host/service actually being observed). The scheduler wrote
+`entity_status`, `metric_samples`, and scheduler-sourced `events` keyed by
+`cd.EntityID` (the probe) instead of `cd.TargetID` (the target) —
+[scheduler.go:110-171](../internal/scheduler/scheduler.go) (pre-fix). Verified
+against the live database:
+
+```
+entity_status by type: only type='check' rows ever had real health (24
+healthy, 1 down); every host/service/lxc/vm/proxmox-host was frozen at
+'unknown' since creation.
+metric_samples: 17,559 rows, 100% attached to type='check' entities — zero
+attached to any real host or service.
+events: 45 of 46 scheduler-sourced rows attached to type='check' entities.
+```
+
+So this wasn't staleness in the TTL sense — the entities you actually care
+about (`host:hubris`, `service:authentik`, etc.) **never received an
+observation at all**. Every health check, metric, and event the scheduler
+produced was filed under an internal bookkeeping entity the UI doesn't even
+surface distinctly. This is the literal mechanism behind "the agent tells me
+stale/wrong state."
+
+**Fixed** (this session): `runCheck`/`resolveSignal` now resolve
+`targetID := cd.TargetID` and write status/metrics/events there, falling back
+to the check's own id only if `target_id` is unset. Signals remain keyed by
+the check entity (unchanged, matches their existing resolution logic). A new
+migration ([016_fix_check_status_misattribution](../migrations/016_fix_check_status_misattribution.up.sql))
+deletes the orphaned check-entity `entity_status` rows so rollups stop
+double-counting probes as monitored entities; historical `metric_samples` on
+check entities are left as-is (time-series data, not safe to reattribute).
+
+On top of the misattribution fix, a genuine staleness gap also existed and is
+now closed: `entity_status.health` was written only when a check ran, with no
+TTL — a stalled scheduler or disabled check_def would leave the last health
+value looking current forever.
+- `last_check_at` is recorded but was never surfaced. The Entities table
+  showed `entity.updated_at` (row mutation time), not observation time
+  ([Entities.svelte:108](../web/src/pages/Entities.svelte), pre-fix).
+- The `/entities` list endpoint returned neither `health` nor `last_check_at`
+  — only `/graph?include=status` and `/fleet/health` did
+  ([impl.go:344](../internal/httpapi/impl.go), pre-fix).
+
+### Sessions
+- Clicking a session calls `loadSessionMessages()` but never navigates to the
+  chat page ([Sessions.svelte:17](../web/src/pages/Sessions.svelte)); it mutates
+  the chat store while the user stays on the session list, so nothing appears to
+  happen. There is also no session switcher inside Chat.
+
+### Agent efficiency
+- Multi-turn history replay **drops all `tool_use`/`tool_result` pairs**; only
+  prior final text is replayed ([agent.go:108-127](../cmd/nomos/agent.go)). Each
+  new turn re-discovers the fleet from scratch, re-calling tools already run.
+- Cold start: the system prompt injects no fleet snapshot
+  ([agent.go:81](../cmd/nomos/agent.go)); default model is
+  `deepseek/deepseek-v4-flash` ([agent.go:34](../cmd/nomos/agent.go)); tool
+  schema + system prompt are rebuilt each call with no prompt caching.
+
+### Dead UI / no inspection
+- Entities table = slug/type/name/state/updated; no health, no last-seen, no
+  signal count.
+- EntityDetail dumps `JSON.stringify(attributes)` raw
+  ([EntityDetail.svelte:123](../web/src/pages/EntityDetail.svelte)) and never
+  shows the entity's `check_defs` — the operator cannot see *what is monitored*,
+  when it last ran, or what it returned.
+- No CRUD anywhere: no entity editor, no check management (enable/disable/edit/
+  run-now), no relationship editing. `check_defs` do not appear in the web app.
+
+---
+
+## Phase 1 — Kill the drift (highest priority)
+
+Goal: the system never presents stale observations as fresh, and freshness is
+visible everywhere health is.
+
+**Backend**
+- Add a staleness sweep to `housekeeping()`
+  ([scheduler.go:243](../internal/scheduler/scheduler.go)): for each
+  `entity_status` where `now() - last_check_at > staleAfter` (default
+  `max(3 × check interval, 5m)`), transition health to a new `stale` value and
+  emit a `health.stale` event once (not every pass).
+- Treat `stale` as a first-class health in dashboard rollups
+  ([dashboard.go:57](../internal/httpapi/dashboard.go)) and fleet health
+  ([impl.go:516](../internal/httpapi/impl.go)) — do not fold it into `unknown`.
+- Extend the `/entities` list response with `health` and `last_check_at`
+  (join `entity_status`), so the table can show freshness without N graph calls.
+- Nomos: when answering about state, tool results should carry `last_check_at`
+  and a stale flag so the agent can hedge ("healthy as of 4m ago") instead of
+  asserting stale data. (Verify the MCP topology/health tools include it.)
+
+**Frontend**
+- Entities table: replace the `Updated` column with **health dot + relative
+  "checked 2m ago"**, and add an **open-signal count** badge per row. Stale rows
+  get a distinct muted/amber treatment, not a green dot.
+- Global header: add an "as of {time}" and make the SSE connection dot a real
+  liveness indicator (last event received, reconnect state).
+
+**Acceptance:** disable a check or stop the scheduler → within one stale window
+the affected entity shows `stale` in the table and dashboard, an event fires,
+and asking Nomos "is X healthy?" yields a freshness-qualified answer.
+
+---
+
+## Phase 2 — Detail sidebar + entity legibility (less navigation)
+
+Goal: inspect any row in place; make an entity's monitoring self-evident.
+
+- Introduce a reusable **DetailSheet** (right-side panel) used across Entities,
+  Signals, Sessions, Executions. Row click opens the sheet; URL hash updates for
+  deep-linking; Esc / click-away closes. Full `#/entity/:slug` page remains for
+  direct links but reuses the same detail component.
+- Entity detail content (in the sheet):
+  - Header: slug, type, **health + freshness** ("checked 2m ago" / "stale
+    18m").
+  - **Monitoring card**: the entity's `check_defs` — kind, schedule, enabled,
+    last result + evidence, next run. This is the missing "what is watched."
+  - Attributes rendered as a key/value panel, not raw JSON.
+  - Relations, open signals, recent executions, metrics sparklines (reuse
+    existing EntityDetail sections).
+- Backend: endpoint to list `check_defs` for an entity with last-result join
+  (currently checks are only visible to the scheduler).
+
+**Acceptance:** from the Entities list, one click reveals what an entity is,
+what's monitoring it, when it was last seen, and its open signals — without a
+full page load or losing the list.
+
+---
+
+## Phase 3 — Sessions rejoin chat
+
+Goal: sessions are openable and live next to the conversation.
+
+- Fix: clicking a session navigates to `#/chat` and loads it
+  ([Sessions.svelte:17](../web/src/pages/Sessions.svelte)).
+- Add a **session rail inside Chat** (collapsible left list: title, last-active,
+  active highlight) so switching sessions never leaves the chat surface. The
+  standalone Sessions page becomes a thin wrapper / can be retired from nav.
+- Show session metadata (message count, last actor) and allow rename/delete.
+
+**Acceptance:** clicking any past session opens its transcript in the chat view;
+starting a new chat and switching back and forth works without navigation.
+
+---
+
+## Phase 4 — Agent efficiency
+
+Goal: stop re-deriving state; start each turn already oriented.
+
+- Persist and replay tool evidence across turns
+  ([agent.go:108-127](../cmd/nomos/agent.go)): either replay `tool_use`/
+  `tool_result` pairs with consistent ids, or persist a compacted per-turn
+  "evidence summary" and replay that. Removes redundant re-querying.
+- Inject a compact fleet snapshot (counts by health, open signals, stale set)
+  into the system prompt ([agent.go:81](../cmd/nomos/agent.go)) so the agent
+  starts oriented instead of spending iterations on discovery.
+- Add prompt caching for the system prompt + tool schema (rebuilt every call
+  today); revisit the default model
+  ([agent.go:34](../cmd/nomos/agent.go)) — evaluate a stronger default for
+  fewer, better tool calls.
+- Surface per-turn iteration/token/cost in the chat UI (data already logged to
+  `agent_activity`) so inefficiency is visible and measurable.
+
+**Acceptance:** a 3-turn conversation about the same entity does not re-call the
+same read tools each turn; median iterations-per-answer drops.
+
+---
+
+## Phase 5 — Customize & inspect (CRUD)
+
+Goal: manage the system from the UI, not just observe it.
+
+- Entity editor (attributes, state) via existing mutation endpoints.
+- Check management from the entity detail sheet: enable/disable, edit config/
+  thresholds, and **run-now** (trigger a single check pass on demand — new
+  scheduler entrypoint).
+- Relationship add/remove.
+- Raw DB-row view toggle in the detail sheet for power inspection.
+
+---
+
+## Suggested order of work
+
+1. Phase 1 backend (staleness sweep + `/entities` health/freshness) →
+   Phase 1 frontend (table freshness + liveness header).
+2. Phase 2 DetailSheet + entity monitoring card.
+3. Phase 3 sessions fix (small; can slot in earlier if desired).
+4. Phase 4 agent efficiency.
+5. Phase 5 CRUD.
+
+Phases 1–3 are the ones that most directly turn "the system feels dead and I
+don't trust it" into "it's alive and I can see and act on it."

plans/2026-07-08-signal-triggers.md

@@ -0,0 +1,387 @@
+# 2026-07-08 — Signal triggers: host health checks
+
+**Status:** Implemented (Phases 1-5 complete)
+
+## Goal
+
+Add a comprehensive set of signal triggers for host-level monitoring —
+network reachability, CPU/memory/disk pressure, thermal state, pending
+updates, disk health, ZFS pool status, and process liveness. Every check
+raises properly deduped signals through the existing `UpsertSignal` path
+and feeds the OODA pipeline (observe → classify → decide → act).
+
+---
+
+## 1. New check kinds
+
+| Kind | What it measures | Signal kind | Severity mapping |
+|------|-----------------|-------------|------------------|
+| `ping` | ICMP reachability + RTT | `ping-unreachable` | down → critical |
+| `cpu` | Usage % + thermal (Linux only) | `cpu-pressure`, `cpu-thermal` | >90% → warning, >95% → critical; temp >85°C → critical |
+| `memory` | RAM usage % | `memory-pressure` | >90% → warning, >95% → critical |
+| `load` | Load avg / CPU count | `load-pressure` | >CPU×2 → warning, >CPU×4 → critical |
+| `swap` | Swap usage % | `swap-pressure` | >50% → warning, >80% → critical |
+| `disk-usage` | Already exists as `disk` — enhance with inode %, per-mountpoint | `disk-full` | >85% → warning, >95% → critical |
+| `disk-smart` | SMART pre-failure attributes | `disk-smart-fail` | any fail → critical |
+| `updates` | Pending apt updates (security, critical) | `updates-pending` | security >0 → warning, critical-reboot >0 → critical |
+| `zfs` | Pool health + scrub status | `zfs-degraded`, `zfs-scrub-overdue` | degraded → critical, scrub >30d → warning |
+| `process` | Process/service running | `process-down` | not running → critical |
+| `uptime` | Detect unexpected reboots | `uptime-bounce` | < previous → warning |
+
+---
+
+## 2. Execution model
+
+Two tiers based on where the check runs:
+
+### Tier A: Local (scheduler host)
+
+`ping`, `http`, `tcp`, `cert-expiry` — run directly from the scheduler process. Already implemented for `http`/`tcp`/`disk`/`cert-expiry`. Add `ping` here.
+
+### Tier B: Remote via SSH (`ssh-script`)
+
+`cpu`, `memory`, `load`, `swap`, `disk-smart`, `updates`, `zfs`, `process`, `uptime` — run on the target host via SSH. The existing `ssh-script` kind (defined in OpenAPI, not implemented in scheduler) is the one generic mechanism.
+
+### Why one `ssh-script` kind instead of separate kinds per metric
+
+The check runs a small allowlisted shell snippet on the target host via SSH.
+The script outputs JSON with `health`, `signalKind`, `evidence`, and optional
+`metrics` (name→value map). This keeps the scheduler simple — one code path for
+all remote checks — while the check definition's `config.script` field encodes
+what to run.
+
+### SSH config shape
+
+```json
+{
+  "host": "192.168.30.10",
+  "port": 22,
+  "user": "root",
+  "script": "cpu_check.sh",
+  "timeout_s": 10
+}
+```
+
+Scripts live in `/opt/oikos/checks/` on each host, deployed by the Homelab sync
+timer alongside the AGENTS.md context. They are allowlisted — the scheduler only
+executes scripts whose names match `^[a-z][a-z0-9_-]+\.sh$` and that exist in the
+check directory.
+
+---
+
+## 3. Check scripts (per host, `/opt/oikos/checks/`)
+
+### `cpu_check.sh`
+```sh
+#!/usr/bin/env bash
+set -euo pipefail
+
+USAGE=$(top -bn1 | awk '/^%Cpu/ {print 100 - $8}')
+CORES=$(nproc)
+TEMP=""
+if [ -f /sys/class/thermal/thermal_zone0/temp ]; then
+  TEMP=$(echo "scale=1; $(cat /sys/class/thermal/thermal_zone0/temp) / 1000" | bc)
+fi
+
+echo "{\"health\":\"healthy\",\"metrics\":{\"cpu_pct\":$USAGE,\"cpu_temp\":$TEMP}}"
+```
+Signal raised by scheduler logic when `cpu_pct > threshold_pct` or `cpu_temp > threshold_temp`.
+
+### `memory_check.sh`
+```sh
+#!/usr/bin/env bash
+set -euo pipefail
+MEMINFO=$(awk '/MemTotal|MemAvailable|SwapTotal|SwapFree/ {printf "\"%s\":%d,", tolower($1), $2}' /proc/meminfo | sed 's/,$//')
+USED_PCT=$(python3 -c "print(round((1 - ${memavailable:-0}/${memtotal:-1})*100, 1))")
+echo "{\"health\":\"healthy\",\"metrics\":{\"mem_pct\":$USED_PCT}}"
+```
+Actual implementation would precompute from `/proc/meminfo` in bash directly (avoid python dependency).
+
+### `load_check.sh`
+```sh
+#!/usr/bin/env bash
+set -euo pipefail
+LOAD=$(awk '{print $1}' /proc/loadavg)
+CORES=$(nproc)
+echo "{\"health\":\"healthy\",\"metrics\":{\"load1\":$LOAD,\"cores\":$CORES}}"
+```
+Scheduler computes `load_pct = load1 / cores` and thresholds on that.
+
+### `swap_check.sh`
+Reports swap used / swap total from `/proc/meminfo`.
+
+### `disk_smart_check.sh`
+```sh
+#!/usr/bin/env bash
+set -euo pipefail
+FAIL=0
+for dev in $(lsblk -ndo NAME,TYPE | awk '$2=="disk"{print "/dev/"$1}'); do
+  smartctl -H "$dev" | grep -q "PASSED" || { FAIL=1; break; }
+done
+[ $FAIL -eq 0 ] && echo '{"health":"healthy"}' || echo '{"health":"degraded","signalKind":"disk-smart-fail","evidence":"SMART health check failed"}'
+```
+
+### `updates_check.sh`
+```sh
+#!/usr/bin/env bash
+set -euo pipefail
+apt update -qq >/dev/null 2>&1
+SECURITY=$(apt list --upgradable 2>/dev/null | grep -c '\-security' || true)
+REBOOT=$(test -f /var/run/reboot-required && echo 1 || echo 0)
+echo "{\"health\":\"healthy\",\"metrics\":{\"security_updates\":$SECURITY,\"reboot_required\":$REBOOT}}"
+```
+Scheduler thresholds: `security_updates > 0` → warning signal, `reboot_required > 0` → critical.
+
+### `zfs_check.sh`
+```sh
+#!/usr/bin/env bash
+set -euo pipefail
+STATUS=$(zpool status -x 2>&1)
+if echo "$STATUS" | grep -q "all pools are healthy"; then
+  echo '{"health":"healthy"}'
+else
+  echo "{\"health\":\"degraded\",\"signalKind\":\"zfs-degraded\",\"evidence\":\"$(echo $STATUS | head -1)\"}"
+fi
+```
+
+### `process_check.sh`
+Runs `systemctl is-active <service>` for a service name passed in config.
+Signal on `inactive`/`failed`.
+
+### `uptime_check.sh`
+Reads current uptime, compares to last stored value (in a temp file or via metric).
+Signal if uptime went backward (reboot detected).
+
+---
+
+## 4. Scheduler changes
+
+### `internal/scheduler/scheduler.go`
+
+Add two new cases to `executeCheck()`:
+
+```go
+case "ping":
+    return checkPing(ctx, cd)
+case "ssh-script":
+    return checkSSHScript(ctx, cd)
+```
+
+Additional changes:
+- **Metric recording**: stop hardcoding `probe_latency_ms`. Each check returns
+  a `map[string]float64` of metrics, and the scheduler writes all of them.
+  Change `executeCheck` signature from `(health, signalKind, evidence, err)`
+  to also return `metrics map[string]float64`.
+- **Threshold evaluation for metric-based checks** (`cpu`, `memory`, `load`,
+  `swap`, `updates`): the scheduler reads `config.thresholds` from check config
+  JSONB and evaluates metrics against them.
+
+### `checkPing()`
+
+Uses `golang.org/x/net/icmp` + `golang.org/x/net/ipv4` for non-privileged
+ICMP echo (or falls back to `net.DialTimeout("ip4:icmp", ...)`).
+On macOS, `ping -c 1 -t <timeout>` via exec as fallback (ICMP raw sockets
+require root on macOS). Returns `probe_latency_ms` metric.
+
+Config:
+```json
+{
+  "host": "192.168.30.10",
+  "count": 1,
+  "timeout_s": 5
+}
+```
+
+### `checkSSHScript()`
+
+Connects via `golang.org/x/crypto/ssh` using agent forwarding or key file.
+Executes the allowlisted script path, validates JSON output, returns metrics
+and health.
+
+Config:
+```json
+{
+  "host": "192.168.30.10",
+  "port": 22,
+  "user": "root",
+  "script": "cpu_check.sh",
+  "thresholds": {
+    "cpu_pct": {"warn": 90, "crit": 95},
+    "cpu_temp": {"crit": 85}
+  },
+  "timeout_s": 10
+}
+```
+
+### Threshold config schema
+
+Each check kind with metric-based thresholds adds a `thresholds` key:
+
+```json
+{
+  "thresholds": {
+    "<metric_name>": {"warn": <float>, "crit": <float>}
+  }
+}
+```
+
+Missing thresholds → no signal raised; metrics still recorded.
+
+---
+
+## 5. DB and migration
+
+No schema migration needed. `check_defs.config` is JSONB — new check kinds
+use it with their own config shapes. `signals` table handles any `kind` string.
+
+One small addition: add the new signal kinds to the OpenAPI `CheckKind` enum
+and the generated code (`api/openapi.yaml` line 2247, `internal/httpapi/gen/api.gen.go` line 84).
+
+---
+
+## 6. Seed data: default checks per host
+
+Add to `seeds/inventory.yaml` or a new `seeds/checks.yaml` — a set of default
+checks per entity type:
+
+- Every `machine`, `workstation`, `proxmox-host`, `lxc` gets:
+  - `cpu` (via ssh-script)
+  - `memory` (via ssh-script)
+  - `load` (via ssh-script)
+  - `swap` (via ssh-script)
+  - `disk-usage` (local or ssh-script for remote)
+  - `updates` (via ssh-script)
+  - `uptime` (via ssh-script)
+- Every `machine`, `proxmox-host`, `standalone-server` additionally gets:
+  - `disk-smart` (via ssh-script)
+  - `zfs` (via ssh-script) if `storage-pool` edges exist
+- Every `service` gets:
+  - `process` (via ssh-script, `systemctl is-active`)
+
+Default intervals:
+- `cpu`, `memory`, `load`: 60s
+- `disk-usage`, `swap`: 300s
+- `ping`: 30s
+- `updates`: 3600s (hourly)
+- `disk-smart`, `zfs`: 86400s (daily)
+- `process`: 30s
+
+---
+
+## 7. Policy integration
+
+New approval rule for `ssh-script` checks:
+
+```yaml
+# ssh-script execution is read_only on the target — it only reads metrics
+- entity_type: machine
+  action: health-check
+  risk_class: read_only
+  autonomy: auto
+```
+
+The `ping` kind is `read_only` (no mutation). All new checks are `read_only`
+— they observe state, no action taken automatically. The *response* to signals
+(restart service, clear cache, apt upgrade) goes through the existing
+classification → approval → execution pipeline separately.
+
+---
+
+## 8. Other common important signals (per user request)
+
+Beyond the core checks above, these are worth including:
+
+| # | Trigger | Why important |
+|---|---------|---------------|
+| 11 | **Inode exhaustion** | Filesystem can be "full" with free space but zero inodes (Docker overlay, mail queues). Distinct from disk-usage. |
+| 12 | **OOM kills** | `dmesg | grep -i 'out of memory'` count since last boot. Indicates memory pressure beyond usage %. |
+| 13 | **Journal errors** | `journalctl -p err -S -1h --no-pager | wc -l`. Catches kernel panics, segfaults, service failures. |
+| 14 | **Docker/container health** | `docker ps --filter health=unhealthy`. Catches containers in unhealthy state. |
+| 15 | **Caddy/nginx error rate** | Parse access logs for 5xx rate over last 5min. Expensive, do at 300s interval. |
+| 16 | **Time drift** | `chronyc tracking | grep 'System time'`. NTP offset > 1s → warning (affects TLS, auth, DB). |
+| 17 | **Open file descriptors** | `/proc/sys/fs/file-nr` ratio used/total. >80% → warning (service exhaustion). |
+| 18 | **Backup freshness** | Check timestamp of last backup file. >schedule+grace → critical. |
+
+All of these (11–18) are implemented as `ssh-script` checks with
+corresponding scripts in `/opt/oikos/checks/`.
+
+---
+
+## 9. Implementation order
+
+### Phase 1: Foundation (2-3 days)
+
+1. **Refactor `executeCheck`** to return metrics map. Update all existing check
+   functions (`http`, `tcp`, `disk`, `cert-expiry`).
+2. **Add `ping` kind** — ICMP reachability on the scheduler host.
+3. **Add `ssh-script` kind** — SSH execution engine, script allowlisting,
+   JSON output parsing.
+4. **Add threshold evaluation** — scheduler reads `config.thresholds` and
+   compares against returned metrics to decide health/signal.
+
+### Phase 2: Host check scripts (1-2 days)
+
+5. Write and test each script in `/opt/oikos/checks/`:
+   `cpu_check.sh`, `memory_check.sh`, `load_check.sh`, `swap_check.sh`,
+   `disk_smart_check.sh`, `updates_check.sh`, `zfs_check.sh`,
+   `process_check.sh`, `uptime_check.sh`, `oom_check.sh`, `journal_check.sh`,
+   `time_check.sh`, `fd_check.sh`.
+6. Add `tools/setup-checks.sh` to auto-deploy scripts via the sync timer
+   (same pattern as `tools/setup-caveman.sh`).
+
+### Phase 3: Seed data + API (1 day)
+
+7. Add `seeds/checks.yaml` with default check definitions per entity type.
+8. Add new check kinds to OpenAPI spec and regenerate Go types.
+9. Add a `/api/v1/checks/defaults/{entity_type}` endpoint that returns
+   recommended checks for a given entity type (convenience for operators).
+
+### Phase 4: Policy + observability (1 day)
+
+10. Add `read_only` policy rules for `ping` and `ssh-script` actions.
+11. Add per-check-kind metric recording (not just `probe_latency_ms`).
+12. Wire `cpu_temp`, `mem_pct`, `load_pct`, etc. into `query_metrics` and
+    the MCP `get_trend` tool.
+
+### Phase 5: Docker + service signals (1 day)
+
+13. `docker_health_check.sh` — `docker ps --filter health=unhealthy`.
+14. `caddy_error_rate.sh` — parse Caddy JSON logs for 5xx.
+15. `backup_freshness.sh` — check last backup timestamp.
+
+---
+
+## 10. Dependencies
+
+| Dependency | For | Risk |
+|------------|-----|------|
+| `golang.org/x/crypto/ssh` | SSH client in scheduler | Already in `go.mod` (used by deployer) |
+| `golang.org/x/net/icmp` + `ipv4` | ICMP ping | New dep; macOS needs root for raw sockets → exec fallback |
+| `smartmontools` on hosts | `disk_smart_check.sh` | Already installed on Proxmox; add to LXCs |
+| `zfsutils-linux` on hosts | `zfs_check.sh` | Already on Proxmox; add to LXCs with ZFS |
+| SSH key on scheduler | `ssh-script` to all hosts | Already deployed (Homelab sync SSH keys) |
+
+---
+
+## 11. Risks and mitigations
+
+| Risk | Mitigation |
+|------|------------|
+| `ssh-script` is a remote exec vector | Scripts are allowlisted by name (`^[a-z][a-z0-9_-]+\.sh$`), deployed via git (auditable), and read-only (no mutation). SSH key restricted to a dedicated `oikos-check` user with sudo only for `systemctl is-active`. |
+| ICMP requires root on macOS | Fallback to `ping` CLI via `os/exec`. Production runs on Linux (strong) where raw sockets work. |
+| Metrics cardinality explosion | Metrics are per-check-definition, not per-script-output. The script returns a fixed set of known metric names. TimescaleDB handles the volume. |
+| Check script drift between hosts | Scripts deploy via `tools/setup-checks.sh` in the sync timer — same mechanism that keeps AGENTS.md in sync. Checksum validation before execution. |
+
+---
+
+## 12. Verification
+
+- **Unit tests**: each check function (`checkPing`, `checkSSHScript`) tested
+  with mock SSH server and mock ICMP responses.
+- **Integration test**: deploy to `strong` (macOS scheduler host), define
+  checks for `hubris` (Proxmox), `dns` (LXC), `caddy` (LXC), run scheduler
+  with `--check-interval 10s`, verify signals appear in `get_signal_history`.
+- **MCP smoke test**: `search_knowledge("signal triggers")`, `get_signal_history`,
+  `query_metrics(metric=["cpu_pct", "mem_pct"])`, `get_trend`.
+- **Policy smoke test**: `preflight(service:caddy, restart)` still returns
+  correct risk class despite new check kinds in the DB.

plans/2026-07-09-chat-sessions-improvements.md

@@ -0,0 +1,160 @@
+# 2026-07-09 — Chat sessions: reliability, cost, and session-management fixes
+
+**Status:** Planned
+
+## Goal
+
+Fix concrete problems found by inspecting the *actual* production Nomos chat
+data (`agent_sessions`/`agent_messages` on the `oikos` Postgres, 24 sessions /
+52 messages as of 2026-07-09), not a code-review of the UI in the abstract.
+Findings below are backed by real rows, not hypotheticals.
+
+## How this was investigated
+
+Queried `oikos-postgres-1` directly (`docker exec oikos-postgres-1 psql -U oikos
+-d oikos`) since this runs on mac-mini, the same host as the production
+containers. Pulled session list, per-message content sizes, tool-call
+breakdowns, and cross-checked against `cmd/nomos/agent.go` to explain what was
+observed.
+
+---
+
+## Findings
+
+### 1. ~17% of turns come back completely empty, silently
+
+4 of 24 sessions ("hi" ×3, "what services are healthy?") have an assistant
+message with `text=""` and zero tool calls — the model returned a blank
+completion. `cmd/nomos/agent.go:175-183` treats `len(msg.ToolCalls) == 0` as a
+normal final answer and emits `text: ""` + `done`. No `error` event fires, so
+[chat.ts](../web/src/lib/stores/chat.ts) never sets `$error`, and
+[Chat.svelte](../web/src/pages/Chat.svelte) renders a permanently-blank
+assistant bubble (the "…" typing dots only show while `$streaming` is true;
+once `done` fires they vanish, leaving nothing). The user has no idea the turn
+failed and no obvious way to retry — they have to notice the silence and
+retype.
+
+**Fix:** in `agent.chat()`, if `msg.Content == "" && len(msg.ToolCalls) == 0`,
+treat it as a retryable failure: log it, retry once against the provider
+before giving up, and if still empty, emit a real `error` event instead of an
+empty `text`/`done` pair. On the frontend, surface a "Nomos didn't respond —
+retry?" affordance on empty assistant messages rather than a silent blank
+bubble.
+
+### 2. A tool-heavy turn came back as a canned non-English refusal
+
+The session "what are the termals of hubris?" ran 22 tool calls and then
+returned, verbatim: `关于这个问题，我没有相关信息，您可以尝试问我其它问题，我会尽力为您解答~`
+("I don't have relevant information on this, try asking me something else").
+This is after successfully gathering data via tools — the model discarded its
+own tool results and emitted a boilerplate deflection in the wrong language.
+`NOMOS_MODEL` is currently a DeepSeek flash-tier model on OpenRouter, which is
+consistent with this kind of degraded-tier fallback text leaking through.
+
+**Fix:** add a response-quality guard in `agent.chat()` — if the final text
+doesn't match the conversation's language/looks like a canned refusal (simple
+heuristic: non-ASCII-majority reply to an ASCII-majority conversation, or
+matches a small denylist of known refusal boilerplate), treat it like the
+empty-response case (retry, then surface an error rather than showing it to
+the operator as a real answer). Separately, reconsider whether the flash-tier
+model is worth the latency/cost tradeoff given it's producing failures like
+this in a small sample — worth an eval pass against a couple of alternative
+OpenRouter models on the same 24 real prompts before deciding.
+
+### 3. Simple fleet questions fan out into dozens of individual tool calls
+
+"Are any of the proxmox hosts saturated?" (2 hosts) triggered **70 tool
+calls** in one turn, 21 of them individual `get_lxc_state` calls — one per LXC
+container — instead of using the already-available `list_lxcs()` bulk tool.
+Similar pattern in "What should be updated with high priority?" (68 calls) and
+"What needs updating?" (54 calls). Each `get_lxc_state` is a live `pct status`
+SSH round-trip to the Proxmox host, so this is 21 sequential SSH round trips
+to answer a question `list_lxcs()` already answers in one call. This is the
+direct cause of both slow responses and the huge persisted payloads in
+finding 4.
+
+**Fix:** two angles, not mutually exclusive:
+- **Prompt-level**: tighten the Nomos system prompt (`nomos/SOUL.md`) to
+  explicitly prefer bulk tools (`list_lxcs`, `get_state_snapshot`,
+  `query_metrics`) over per-entity tools when the question is fleet-wide, and
+  only fall back to `get_lxc_state`/`tail_log` for a specific named entity.
+- **Tool-level**: `get_lxc_state` already exists per-slug; consider whether
+  `list_lxcs()`'s summary is actually sufficient for "saturated" (CPU/mem %
+  per container) — if it's missing that field, that's *why* the model loops
+  per-container, and the real fix is enriching `list_lxcs()` rather than
+  prompting around the gap.
+
+### 4. Tool results are persisted raw and unbounded, inflating messages to 100KB+
+
+Message content sizes in `agent_messages.content` (JSONB) range up to
+**106KB** for a single assistant turn. Even a plain "hi" greeting produced a
+44KB message, because `get_state_snapshot()`'s full result — every entity in
+the DB, including ~15 `document:containers/*` rows that are all
+`state: <nil>, health: unknown` and contribute nothing — gets embedded
+verbatim in the `tool_calls[].result` field and stored as-is
+(`cmd/nomos/store.go:68-76` just JSON-inserts whatever the tool returned).
+This bloats the DB, and every time a session is opened via
+[loadSessionMessages](../web/src/lib/stores/chat.ts#L56) or the
+[SessionRail](../web/src/lib/components/SessionRail.svelte)/
+[Sessions](../web/src/pages/Sessions.svelte) page loads history, the browser
+downloads and parses all of it just to render a collapsed tool-call summary.
+
+**Fix:**
+- Filter `get_state_snapshot()`'s result server-side (in the MCP tool, not
+  the agent) to drop entities with no meaningful state/health signal, or add
+  a `type` filter param the agent can pass.
+- In `store.saveMessage`, cap persisted tool-result size (e.g. truncate to a
+  few KB with a `"...truncated, N bytes"` marker) — the full result already
+  served its purpose informing that turn's answer; historical replay
+  (`agent.chat()`'s history-replay loop at `agent.go:122-137`) doesn't need
+  the full blob, just enough for the model to know what it already checked.
+
+### 5. No session hygiene: duplicate/typo'd titles, no delete/archive
+
+Session titles are the raw, unprocessed first user message
+(`store.createSession`), with no dedup, normalization, or cleanup. Real
+production titles include **6 sessions titled "hi"**, **2 titled "say ok"**,
+and typos preserved verbatim ("what are the **termals** of hubris?", "whats
+the **termans** of strong", "Are any of the **proxomox** hosts saturated?").
+Neither [Sessions.svelte](../web/src/pages/Sessions.svelte) nor
+[SessionRail.svelte](../web/src/lib/components/SessionRail.svelte) nor the
+`store`/API layer (`cmd/nomos/store.go`, `web/src/lib/api.ts`) has any delete
+or archive path — grepped the whole stack, confirmed absent. Throwaway test
+sessions accumulate forever with no way to clean them from the UI.
+
+**Fix:**
+- Add `DELETE /sessions/{id}` to the nomos gateway + a matching store method
+  and wire a delete affordance into `SessionRail`/`Sessions` (hover trash
+  icon, confirm on click).
+- Generate titles from the assistant's actual answer once the turn completes
+  (or a cheap follow-up summarization call) instead of the raw first message,
+  so distinct "hi" sessions become distinguishable by what was actually
+  discussed.
+
+---
+
+## Implementation order
+
+1. **Empty-response + refusal-leak guard** (`cmd/nomos/agent.go`) — highest
+   user-visible impact, smallest change, no schema/API changes.
+2. **Bulk-tool prompting fix** (`nomos/SOUL.md`) — cheap, directly cuts
+   latency and tool-call volume; re-run the same 24 real prompts against the
+   updated prompt to confirm `get_lxc_state` fan-out drops.
+3. **Tool-result truncation on persist** (`cmd/nomos/store.go`) — bounds
+   future DB growth; pair with a one-off cleanup pass on the 52 existing rows
+   if the table needs to be shrunk immediately.
+4. **`get_state_snapshot` filtering** — coordinate with whichever MCP tool
+   file defines it; verify with `jsonb_pretty` on a fresh "hi" session that
+   payload drops well below the current ~44KB.
+5. **Session delete + title generation** — UI + gateway change, lowest risk,
+   can ship independently of 1-4.
+
+## Verification
+
+- Re-run the same 24 real user prompts (recorded in this plan's investigation)
+  against the patched agent; confirm zero empty/refusal-leak responses and
+  `get_lxc_state`-style fan-out drops to O(hosts) not O(containers).
+- `docker exec oikos-postgres-1 psql -U oikos -d oikos -c "SELECT max(length(content::text)) FROM agent_messages;"`
+  before/after — expect the ceiling to move from ~106KB to low single-digit KB.
+- Manually delete a test session via the new UI affordance, confirm it's gone
+  from both `SessionRail` and the `agent_sessions` table.

plans/index.md

@@ -11,8 +11,9 @@ went sideways, open an investigation.
 | 2026-07-05 | [Oikos Prometheus LXC](2026-07-05-oikos-prometheus-lxc.md) | Planned |
 | 2026-07-08 | [Plan vs implementation cross-reference](2026-07-08-plan-implementation-audit.md) | Planned |
 | 2026-07-08 | [Oikos gaps, broken things, and improvements](2026-07-08-oikos-gaps-and-improvements.md) | Planned |
-| 2026-07-08 | [Control room web UI](2026-07-08-control-room-webui.md) | Planned |
+| 2026-07-08 | [Control room web UI](2026-07-08-control-room-webui.md) | In Progress |
 | 2026-07-08 | [Nomos resident agent (renames Hermes)](2026-07-08-nomos-resident-agent.md) | In Progress |
+| 2026-07-09 | [Chat sessions: reliability, cost, and session-management fixes](2026-07-09-chat-sessions-improvements.md) | Planned |
 
 ## Done
 

tools/setup-checks.sh

@@ -0,0 +1,13 @@
+#!/usr/bin/env bash
+# setup-checks.sh — deploy check scripts to /opt/oikos/checks on each host.
+# Auto-setup hook: tools/*.setup.sh runs after every git pull.
+set -euo pipefail
+
+CLONE_DIR="${HOMELAB_CONTEXT_DIR:-/opt/homelab}"
+CHECK_SETUP="$CLONE_DIR/checks/install.sh"
+
+if [ -f "$CHECK_SETUP" ]; then
+  bash "$CHECK_SETUP" || echo "[setup-checks] WARNING: install.sh exited with code $?"
+else
+  echo "[setup-checks] no checks/install.sh found, skipping"
+fi

web/components.json

@@ -0,0 +1,17 @@
+{
+	"$schema": "https://shadcn-svelte.com/schema.json",
+	"style": "vega",
+	"tailwind": {
+		"css": "src/app.css",
+		"baseColor": "zinc"
+	},
+	"aliases": {
+		"components": "$lib/components",
+		"utils": "$lib/utils",
+		"ui": "$lib/components/ui",
+		"hooks": "$lib/hooks",
+		"lib": "$lib"
+	},
+	"typescript": true,
+	"registry": "https://shadcn-svelte.com/registry"
+}

web/index.html

@@ -4,7 +4,10 @@
     <meta charset="UTF-8" />
     <meta name="viewport" content="width=device-width, initial-scale=1.0" />
     <title>Oikos — Control Room</title>
-    <link rel="icon" type="image/svg+xml" href="data:image/svg+xml,<svg xmlns='http://www.w3.org/2000/svg' viewBox='0 0 100 100'><text y='.9em' font-size='90'>🏠</text></svg>" />
+    <link rel="icon" type="image/svg+xml" href="favicon.svg" />
+    <link rel="apple-touch-icon" href="apple-touch-icon.png" />
+    <link rel="icon" type="image/png" sizes="192x192" href="android-chrome-192.png" />
+    <link rel="icon" type="image/png" sizes="512x512" href="android-chrome-512.png" />
   </head>
   <body>
     <div id="app"></div>

web/package.json

@@ -9,10 +9,27 @@
     "preview": "vite preview"
   },
   "devDependencies": {
+    "@internationalized/date": "^3.12.2",
+    "@lucide/svelte": "^1.23.0",
     "@sveltejs/vite-plugin-svelte": "^5.0.0",
+    "@tailwindcss/vite": "^4.3.2",
     "@tsconfig/svelte": "^5.0.0",
+    "@types/d3-force": "^3.0.10",
+    "bits-ui": "^2.18.1",
+    "mode-watcher": "^1.1.0",
     "svelte": "^5.0.0",
+    "svelte-sonner": "^1.1.1",
+    "tailwind-variants": "^3.2.2",
+    "tailwindcss": "^4.3.2",
     "typescript": "^5.5.0",
     "vite": "^6.0.0"
+  },
+  "dependencies": {
+    "clsx": "^2.1.1",
+    "d3-force": "^3.0.0",
+    "dompurify": "^3.4.11",
+    "marked": "^18.0.5",
+    "tailwind-merge": "^3.6.0",
+    "uplot": "^1.6.32"
   }
 }

web/public/favicon.svg

@@ -0,0 +1,4 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<svg width="91" height="100" version="1.1" xmlns="http://www.w3.org/2000/svg">
+ <path fill="#ffffff" d="m45.601 1q20.993 0 33.71 15.946 10.799 13.625 10.799 31.287 0 12.414-5.9548 25.131-5.9548 12.717-16.451 19.176-10.395 6.4592-23.213 6.4592-20.892 0-33.205-16.653-10.395-14.029-10.395-31.489 0-12.717 6.2577-25.232 6.3584-12.616 16.653-18.57 10.295-6.0556 21.801-6.0556zm-3.128 6.5605q-5.3492 0-10.799 3.2296-5.3492 3.1287-8.68 11.102-3.3305 7.9735-3.3305 20.488 0 20.185 7.973 34.82 8.0743 14.634 21.195 14.634 9.7896 0 16.149-8.0743 6.3584-8.0743 6.3584-27.755 0-24.627-10.597-38.756-7.1657-9.6888-18.268-9.6888z"/>
+</svg>

web/src/App.svelte

@@ -1,155 +1,232 @@
 <script lang="ts">
-  import Chat from '$lib/../pages/Chat.svelte'
-  import Sessions from '$lib/../pages/Sessions.svelte'
+  import Chat from './pages/Chat.svelte'
+  import Sessions from './pages/Sessions.svelte'
+  import Overview from './pages/Overview.svelte'
+  import Entities from './pages/Entities.svelte'
+  import Events from './pages/Events.svelte'
+  import Ops from './pages/Ops.svelte'
+  import Signals from './pages/Signals.svelte'
+  import Graph from './pages/Graph.svelte'
+  import EntityDetail from './pages/EntityDetail.svelte'
+  import Agent from './pages/Agent.svelte'
+  import Knowledge from './pages/Knowledge.svelte'
+  import Audit from './pages/Audit.svelte'
   import { newChat } from '$lib/stores/chat'
+  import { summary, subscribeContext, openSignalCount } from '$lib/stores/context'
+  import { connectionState } from '$lib/stores/events'
   import { onMount } from 'svelte'
-  import { slide } from 'svelte/transition'
+  import * as Sidebar from '$lib/components/ui/sidebar'
+  import * as Sheet from '$lib/components/ui/sheet'
+  import { Button } from '$lib/components/ui/button'
+  import { Badge } from '$lib/components/ui/badge'
+  import { Separator } from '$lib/components/ui/separator'
+  import { Toaster } from '$lib/components/ui/sonner'
+  import PlusIcon from '@lucide/svelte/icons/plus'
+  import MessageSquareIcon from '@lucide/svelte/icons/message-square'
+  import LayoutDashboardIcon from '@lucide/svelte/icons/layout-dashboard'
+  import DatabaseIcon from '@lucide/svelte/icons/database'
+  import ActivityIcon from '@lucide/svelte/icons/activity'
+  import PanelRightIcon from '@lucide/svelte/icons/panel-right'
+  import ShieldCheckIcon from '@lucide/svelte/icons/shield-check'
+  import SirenIcon from '@lucide/svelte/icons/siren'
+  import NetworkIcon from '@lucide/svelte/icons/share-2'
+  import BotIcon from '@lucide/svelte/icons/bot'
+  import SearchIcon from '@lucide/svelte/icons/search'
+  import ScrollTextIcon from '@lucide/svelte/icons/scroll-text'
 
   let page = $state('chat')
+  let routeParam = $state('')
   let drawerOpen = $state(false)
 
+  const approvalsPending = $derived($summary?.approvals_pending ?? 0)
+  const openSignals = $derived(openSignalCount($summary))
+
   onMount(() => {
     function sync() {
-      page = location.hash.slice(2) || 'chat'
+      const path = location.hash.slice(2) || 'chat'
+      const [head, ...rest] = path.split('/')
+      page = head || 'chat'
+      routeParam = rest.join('/')
     }
     sync()
     window.addEventListener('hashchange', sync)
-    return () => window.removeEventListener('hashchange', sync)
+    const unsubscribeCtx = subscribeContext()
+
+    return () => {
+      window.removeEventListener('hashchange', sync)
+      unsubscribeCtx()
+    }
   })
 
   function navigate(p: string) {
     location.hash = '#/' + p
   }
+
+  const navItems = [
+    { id: 'overview', label: 'Overview', icon: LayoutDashboardIcon },
+    { id: 'entities', label: 'Entities', icon: DatabaseIcon },
+    { id: 'graph', label: 'Graph', icon: NetworkIcon },
+    { id: 'ops', label: 'Operations', icon: ShieldCheckIcon, badge: () => approvalsPending },
+    { id: 'signals', label: 'Signals', icon: SirenIcon, badge: () => openSignals },
+    { id: 'events', label: 'Events', icon: ActivityIcon },
+    { id: 'agent', label: 'Agent', icon: BotIcon },
+    { id: 'knowledge', label: 'Knowledge', icon: SearchIcon },
+    { id: 'audit', label: 'Audit', icon: ScrollTextIcon }
+  ]
 </script>
 
-<div class="app">
-  <nav class="sidebar">
-    <div class="logo">Oikos</div>
-    <button class="nav-btn" onclick={() => { newChat(); navigate('chat') }}>
-      <span class="nav-icon">✚</span>
-      <span>New</span>
-    </button>
-    <button class="nav-btn" class:active={page === 'chat'} onclick={() => navigate('chat')}>
-      <span class="nav-icon">💬</span>
-      <span>Chat</span>
-    </button>
-    <button class="nav-btn" class:active={page === 'sessions'} onclick={() => navigate('sessions')}>
-      <span class="nav-icon">📋</span>
-      <span>Sessions</span>
-    </button>
+<Toaster />
 
-    <div class="spacer"></div>
+<Sidebar.Provider class="h-svh" style="--header-height: calc(var(--spacing) * 12);">
+  <Sidebar.Root collapsible="icon" variant="inset">
+    <Sidebar.Header>
+      <Sidebar.Menu>
+        <Sidebar.MenuItem>
+          <Sidebar.MenuButton
+            class="data-[slot=sidebar-menu-button]:!p-1.5"
+            onclick={() => navigate('overview')}
+            tooltipContent="Oikos"
+          >
+            {#snippet child({ props })}
+              <button {...props}>
+                <svg viewBox="0 0 91 100" class="!size-5 shrink-0 fill-white" aria-hidden="true" role="img">
+                  <title>Oikos</title>
+                  <path d="m45.601 1q20.993 0 33.71 15.946 10.799 13.625 10.799 31.287 0 12.414-5.9548 25.131-5.9548 12.717-16.451 19.176-10.395 6.4592-23.213 6.4592-20.892 0-33.205-16.653-10.395-14.029-10.395-31.489 0-12.717 6.2577-25.232 6.3584-12.616 16.653-18.57 10.295-6.0556 21.801-6.0556zm-3.128 6.5605q-5.3492 0-10.799 3.2296-5.3492 3.1287-8.68 11.102-3.3305 7.9735-3.3305 20.488 0 20.185 7.973 34.82 8.0743 14.634 21.195 14.634 9.7896 0 16.149-8.0743 6.3584-8.0743 6.3584-27.755 0-24.627-10.597-38.756-7.1657-9.6888-18.268-9.6888z" />
+                </svg>
+              </button>
+            {/snippet}
+          </Sidebar.MenuButton>
+        </Sidebar.MenuItem>
+      </Sidebar.Menu>
+      <Sidebar.Menu>
+        <Sidebar.MenuItem>
+          <Sidebar.MenuButton
+            class="bg-primary text-primary-foreground hover:bg-primary/90 hover:text-primary-foreground active:bg-primary/90 active:text-primary-foreground min-w-8 duration-200 ease-linear"
+            onclick={() => { newChat(); navigate('chat') }}
+            tooltipContent="New chat"
+          >
+            {#snippet child({ props })}
+              <button {...props}>
+                <PlusIcon />
+                <span>New chat</span>
+              </button>
+            {/snippet}
+          </Sidebar.MenuButton>
+        </Sidebar.MenuItem>
+      </Sidebar.Menu>
+    </Sidebar.Header>
 
-    <button class="drawer-toggle" onclick={() => drawerOpen = !drawerOpen}>
-      Chat {drawerOpen ? '▼' : '▲'}
-    </button>
-  </nav>
+    <Sidebar.Content>
+      <Sidebar.Group>
+        <Sidebar.Menu>
+          <Sidebar.MenuItem>
+            <Sidebar.MenuButton isActive={page === 'chat'} onclick={() => navigate('chat')} tooltipContent="Chat">
+              {#snippet child({ props })}
+                <button {...props}>
+                  <MessageSquareIcon />
+                  <span>Chat</span>
+                </button>
+              {/snippet}
+            </Sidebar.MenuButton>
+          </Sidebar.MenuItem>
+          {#each navItems as item}
+            <Sidebar.MenuItem>
+              <Sidebar.MenuButton
+                isActive={page === item.id}
+                onclick={() => navigate(item.id)}
+                tooltipContent={item.label}
+              >
+                {#snippet child({ props })}
+                  <button {...props}>
+                    <item.icon />
+                    <span>{item.label}</span>
+                  </button>
+                {/snippet}
+              </Sidebar.MenuButton>
+              {#if item.badge?.()}
+                <Sidebar.MenuBadge>{item.badge()}</Sidebar.MenuBadge>
+              {/if}
+            </Sidebar.MenuItem>
+          {/each}
+        </Sidebar.Menu>
+      </Sidebar.Group>
+    </Sidebar.Content>
 
-  <main class="main">
-    {#if page === 'chat'}
-      <Chat />
-    {:else if page === 'sessions'}
-      <Sessions />
-    {:else}
-      <Chat />
-    {/if}
-  </main>
+    <Sidebar.Footer>
+      <Button variant="ghost" size="sm" class="justify-start gap-2" onclick={() => (drawerOpen = true)}>
+        <PanelRightIcon />
+        <span>Chat drawer</span>
+      </Button>
+    </Sidebar.Footer>
+  </Sidebar.Root>
 
-  {#if drawerOpen}
-    <aside class="drawer" transition:slide={{ axis: 'x' }}>
-      <Chat />
-    </aside>
-  {/if}
-</div>
+  <Sidebar.Inset class="min-h-0 overflow-hidden">
+    <header class="flex h-(--header-height) shrink-0 items-center gap-1 border-b px-4 lg:gap-2 lg:px-6">
+      <Sidebar.Trigger class="-ms-1" />
+      <Separator orientation="vertical" class="mx-2 data-[orientation=vertical]:h-4" />
+      <span class="text-base font-medium capitalize">{page === 'entity' ? routeParam : page}</span>
+      <div class="ms-auto flex items-center gap-2.5">
+      {#if $summary}
+        <div class="hidden items-center gap-2.5 text-xs text-muted-foreground sm:flex">
+          <span class="flex items-center gap-1" title="healthy"><span class="size-2 rounded-full bg-success"></span>{$summary.health.healthy}</span>
+          <span class="flex items-center gap-1" title="degraded"><span class="size-2 rounded-full bg-warning"></span>{$summary.health.degraded}</span>
+          <span class="flex items-center gap-1" title="down"><span class="size-2 rounded-full bg-destructive"></span>{$summary.health.down}</span>
+        </div>
+        {#if approvalsPending}
+          <button type="button" onclick={() => navigate('ops')}>
+            <Badge variant="destructive" class="cursor-pointer">{approvalsPending} approval{approvalsPending === 1 ? '' : 's'}</Badge>
+          </button>
+        {/if}
+        {#if openSignals}
+          <button type="button" onclick={() => navigate('signals')}>
+            <Badge variant="secondary" class="cursor-pointer">{openSignals} signal{openSignals === 1 ? '' : 's'}</Badge>
+          </button>
+        {/if}
+      {/if}
+      <span
+        class="size-2 rounded-full {$connectionState === 'open' ? 'bg-success' : $connectionState === 'connecting' ? 'animate-pulse bg-warning' : 'bg-destructive'}"
+        title="event stream: {$connectionState}"
+      ></span>
+      </div>
+    </header>
+    <main class="min-h-0 flex-1 overflow-hidden">
+      {#if page === 'overview'}
+        <Overview />
+      {:else if page === 'entities'}
+        <Entities />
+      {:else if page === 'graph'}
+        <Graph />
+      {:else if page === 'entity' && routeParam}
+        <EntityDetail slug={routeParam} />
+      {:else if page === 'ops'}
+        <Ops />
+      {:else if page === 'signals'}
+        <Signals />
+      {:else if page === 'events'}
+        <Events />
+      {:else if page === 'sessions'}
+        <Sessions />
+      {:else if page === 'agent'}
+        <Agent />
+      {:else if page === 'knowledge'}
+        <Knowledge />
+      {:else if page === 'audit'}
+        <Audit />
+      {:else}
+        <Chat />
+      {/if}
+    </main>
+  </Sidebar.Inset>
+</Sidebar.Provider>
 
-<style>
-  .app {
-    display: flex;
-    height: 100vh;
-    overflow: hidden;
-  }
-
-  .sidebar {
-    width: 56px;
-    background: var(--bg-surface);
-    border-right: 1px solid var(--border);
-    display: flex;
-    flex-direction: column;
-    align-items: center;
-    padding: 0.75rem 0;
-    gap: 0.5rem;
-  }
-
-  .logo {
-    font-size: 1.25rem;
-    font-weight: 700;
-    color: var(--accent-blue);
-    margin-bottom: 0.5rem;
-    user-select: none;
-  }
-
-  .nav-btn {
-    display: flex;
-    flex-direction: column;
-    align-items: center;
-    gap: 2px;
-    padding: 0.5rem;
-    border: none;
-    background: none;
-    color: var(--text-muted);
-    font-family: inherit;
-    font-size: 0.625rem;
-    cursor: pointer;
-    border-radius: 6px;
-    width: 44px;
-    transition: background 0.15s, color 0.15s;
-  }
-
-  .nav-btn:hover {
-    background: var(--bg-hover);
-    color: var(--text);
-  }
-
-  .nav-btn.active {
-    background: var(--bg-active);
-    color: var(--accent-blue);
-  }
-
-  .nav-icon {
-    font-size: 1rem;
-  }
-
-  .spacer {
-    flex: 1;
-  }
-
-  .drawer-toggle {
-    border: none;
-    background: none;
-    color: var(--text-muted);
-    font-family: inherit;
-    font-size: 0.625rem;
-    cursor: pointer;
-    padding: 0.5rem;
-  }
-
-  .drawer-toggle:hover {
-    color: var(--text);
-  }
-
-  .main {
-    flex: 1;
-    overflow: hidden;
-    display: flex;
-    flex-direction: column;
-  }
-
-  .drawer {
-    width: 380px;
-    border-left: 1px solid var(--border);
-    background: var(--bg);
-    overflow: hidden;
-    display: flex;
-    flex-direction: column;
-  }
-</style>
+<Sheet.Root bind:open={drawerOpen}>
+  <Sheet.Content side="right" class="w-[400px] p-0 sm:max-w-[400px]">
+    <Sheet.Header class="sr-only">
+      <Sheet.Title>Nomos chat</Sheet.Title>
+      <Sheet.Description>Persistent chat drawer</Sheet.Description>
+    </Sheet.Header>
+    <div class="flex h-full flex-col">
+      <Chat showRail={false} />
+    </div>
+  </Sheet.Content>
+</Sheet.Root>

web/src/app.css

@@ -1,33 +1,122 @@
+@import 'tailwindcss';
+
+@custom-variant dark (&:is(.dark *));
+
+/* Neutral gray theme matching shadcn/ui's canonical dark palette (0-chroma
+   OKLCH grays) — the app is dark-only, so :root carries the dark values
+   directly rather than gating behind a .dark class. --success/--warning are
+   Oikos-specific semantic status colors (real health state), kept
+   distinguishable rather than desaturated to match the neutral chrome. */
 :root {
-  --bg: #0d1117;
-  --bg-surface: #161b22;
-  --bg-deeper: #0a0e13;
-  --bg-hover: #21262d;
-  --bg-active: #292e36;
-  --border: #30363d;
-  --text: #e6edf3;
-  --text-muted: #8b949e;
-  --accent-blue: #58a6ff;
-  --accent-green: #3fb950;
-  --accent-red: #f85149;
-  --accent-orange: #d29922;
+  --radius: 0.625rem;
+  --background: oklch(0.145 0 0);
+  --foreground: oklch(0.985 0 0);
+  --card: oklch(0.205 0 0);
+  --card-foreground: oklch(0.985 0 0);
+  --popover: oklch(0.205 0 0);
+  --popover-foreground: oklch(0.985 0 0);
+  --primary: oklch(0.922 0 0);
+  --primary-foreground: oklch(0.205 0 0);
+  --secondary: oklch(0.269 0 0);
+  --secondary-foreground: oklch(0.985 0 0);
+  --muted: oklch(0.269 0 0);
+  --muted-foreground: oklch(0.708 0 0);
+  --accent: oklch(0.371 0 0);
+  --accent-foreground: oklch(0.985 0 0);
+  --destructive: oklch(0.704 0.191 22.216);
+  --destructive-foreground: oklch(0.985 0 0);
+  --success: #3fb950;
+  --warning: #d29922;
+  --border: oklch(1 0 0 / 10%);
+  --input: oklch(1 0 0 / 15%);
+  --ring: oklch(0.556 0 0);
+  --sidebar: oklch(0.205 0 0);
+  --sidebar-foreground: oklch(0.985 0 0);
+  --sidebar-primary: oklch(0.488 0.243 264.376);
+  --sidebar-primary-foreground: oklch(0.985 0 0);
+  --sidebar-accent: oklch(0.269 0 0);
+  --sidebar-accent-foreground: oklch(0.985 0 0);
+  --sidebar-border: oklch(1 0 0 / 10%);
+  --sidebar-ring: oklch(0.439 0 0);
   --font-mono: 'SF Mono', 'Fira Code', 'Cascadia Code', monospace;
+
+  /* legacy aliases still referenced by Chat/Sessions/App */
+  --bg: var(--background);
+  --bg-surface: var(--card);
+  --bg-deeper: oklch(0.11 0 0);
+  --bg-hover: var(--secondary);
+  --bg-active: var(--accent);
+  --text: var(--foreground);
+  --text-muted: var(--muted-foreground);
+  /* accent-blue stays a real blue (matches --sidebar-primary) for the few
+     spots that want an interactive "pop" — everything else (buttons,
+     links, focus rings) rides the neutral --primary now. */
+  --accent-blue: var(--sidebar-primary);
+  --accent-green: var(--success);
+  --accent-red: var(--destructive);
+  --accent-orange: var(--warning);
 }
 
-*, *::before, *::after {
-  box-sizing: border-box;
-  margin: 0;
-  padding: 0;
+@theme inline {
+  --radius-sm: calc(var(--radius) - 4px);
+  --radius-md: calc(var(--radius) - 2px);
+  --radius-lg: var(--radius);
+  --radius-xl: calc(var(--radius) + 4px);
+  --color-background: var(--background);
+  --color-foreground: var(--foreground);
+  --color-card: var(--card);
+  --color-card-foreground: var(--card-foreground);
+  --color-popover: var(--popover);
+  --color-popover-foreground: var(--popover-foreground);
+  --color-primary: var(--primary);
+  --color-primary-foreground: var(--primary-foreground);
+  --color-secondary: var(--secondary);
+  --color-secondary-foreground: var(--secondary-foreground);
+  --color-muted: var(--muted);
+  --color-muted-foreground: var(--muted-foreground);
+  --color-accent: var(--accent);
+  --color-accent-foreground: var(--accent-foreground);
+  --color-destructive: var(--destructive);
+  --color-destructive-foreground: var(--destructive-foreground);
+  --color-success: var(--success);
+  --color-warning: var(--warning);
+  --color-border: var(--border);
+  --color-input: var(--input);
+  --color-ring: var(--ring);
+  --color-sidebar: var(--sidebar);
+  --color-sidebar-foreground: var(--sidebar-foreground);
+  --color-sidebar-primary: var(--sidebar-primary);
+  --color-sidebar-primary-foreground: var(--sidebar-primary-foreground);
+  --color-sidebar-accent: var(--sidebar-accent);
+  --color-sidebar-accent-foreground: var(--sidebar-accent-foreground);
+  --color-sidebar-border: var(--sidebar-border);
+  --color-sidebar-ring: var(--sidebar-ring);
+  --font-mono: var(--font-mono);
 }
 
-html, body {
-  height: 100%;
-  background: var(--bg);
-  color: var(--text);
-  font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, sans-serif;
-  font-size: 14px;
-  line-height: 1.4;
-  -webkit-font-smoothing: antialiased;
+@layer base {
+  * {
+    @apply border-border outline-ring/50;
+  }
+  html,
+  body {
+    @apply bg-background text-foreground;
+    height: 100%;
+    font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, sans-serif;
+    font-size: 14px;
+    line-height: 1.4;
+    -webkit-font-smoothing: antialiased;
+  }
+  /* Tailwind's preflight resets <button> to cursor: default; every button
+     and native interactive element in this app is clickable, so restore
+     the pointer cursor app-wide instead of annotating each one. */
+  button:not(:disabled),
+  [role='button']:not([aria-disabled='true']),
+  a[href],
+  summary,
+  select {
+    cursor: pointer;
+  }
 }
 
 #app {

web/src/lib/api.ts

@@ -1,4 +1,5 @@
 const BASE = '/agent'
+const API = '/api/v1'
 
 export interface Session {
   id: string
@@ -90,3 +91,420 @@ export function streamChat(
 
   return controller
 }
+
+export interface DashboardSummary {
+  entities_by_type: Record<string, number>
+  entities_by_state: Record<string, number>
+  health: { healthy: number; degraded: number; down: number; unknown: number }
+  signals_by_severity: Record<string, number>
+  approvals_pending: number
+  executions_by_state: Record<string, number>
+  event_rate: { bucket: string; count: number }[]
+}
+
+export async function fetchDashboardSummary(): Promise<DashboardSummary | null> {
+  const res = await fetch(`${API}/dashboard/summary`)
+  if (!res.ok) return null
+  return res.json()
+}
+
+export type EntityHealth = 'healthy' | 'degraded' | 'down' | 'unknown' | 'stale'
+
+export interface Entity {
+  id: string
+  slug: string
+  type: string
+  name: string
+  state?: string | null
+  attributes: Record<string, unknown>
+  version: number
+  created_at: string
+  updated_at: string
+  health?: EntityHealth | null
+  last_check_at?: string | null
+}
+
+export interface EntityFilters {
+  type?: string
+  state?: string
+  q?: string
+}
+
+export async function fetchEntities(filters: EntityFilters = {}): Promise<Entity[]> {
+  const params = new URLSearchParams()
+  if (filters.type) params.set('type', filters.type)
+  if (filters.state) params.set('state', filters.state)
+  if (filters.q) params.set('q', filters.q)
+  params.set('limit', '200')
+  const res = await fetch(`${API}/entities?${params}`)
+  if (!res.ok) return []
+  const data = await res.json()
+  return data.items ?? []
+}
+
+export interface EventFilters {
+  type?: string
+  severity?: string
+}
+
+export async function fetchEvents(filters: EventFilters = {}): Promise<import('./stores/events').OikosEvent[]> {
+  const params = new URLSearchParams()
+  if (filters.type) params.set('type', filters.type)
+  if (filters.severity) params.set('severity', filters.severity)
+  params.set('limit', '100')
+  const res = await fetch(`${API}/events?${params}`)
+  if (!res.ok) return []
+  const data = await res.json()
+  return data.items ?? []
+}
+
+export interface Approval {
+  id: string
+  slug: string
+  subject?: string | null
+  action: string
+  risk_class: string
+  kind: 'execution' | 'policy-change' | 'pattern-activation'
+  payload?: Record<string, unknown> | null
+  status: 'pending' | 'approved' | 'denied' | 'expired' | 'revoked'
+  expires_at: string
+  decided_at?: string | null
+  decided_by?: string | null
+  created_at: string
+}
+
+export async function fetchApprovals(status?: string): Promise<Approval[]> {
+  const params = new URLSearchParams()
+  if (status) params.set('status', status)
+  params.set('limit', '200')
+  const res = await fetch(`${API}/approvals?${params}`)
+  if (!res.ok) return []
+  const data = await res.json()
+  return data.items ?? []
+}
+
+export async function decideApproval(
+  id: string,
+  decision: 'approve' | 'deny' | 'revoke',
+  note?: string
+): Promise<Approval | null> {
+  const res = await fetch(`${API}/approvals/${id}/decision`, {
+    method: 'POST',
+    headers: { 'Content-Type': 'application/json' },
+    body: JSON.stringify({ decision, note })
+  })
+  if (!res.ok) return null
+  return res.json()
+}
+
+export interface Execution {
+  id: string
+  slug: string
+  target?: string | null
+  action: string
+  risk_class: string
+  status: string
+  approval_id?: string | null
+  agent_id?: string | null
+  result?: Record<string, unknown> | null
+  duration_ms?: number | null
+  verified: boolean
+  correlation_id: string
+  started_at?: string | null
+  completed_at?: string | null
+  created_at: string
+}
+
+export async function fetchExecutions(status?: string): Promise<Execution[]> {
+  const params = new URLSearchParams()
+  if (status) params.set('status', status)
+  params.set('limit', '200')
+  const res = await fetch(`${API}/executions?${params}`)
+  if (!res.ok) return []
+  const data = await res.json()
+  return data.items ?? []
+}
+
+export async function cancelExecution(id: string): Promise<Execution | null> {
+  const res = await fetch(`${API}/executions/${id}/cancel`, { method: 'POST' })
+  if (!res.ok) return null
+  return res.json()
+}
+
+export interface Signal {
+  id: string
+  slug: string
+  kind: string
+  severity: 'info' | 'warning' | 'critical'
+  state: 'raised' | 'acknowledged' | 'acting' | 'muted' | 'resolved' | 'failed'
+  target?: string | null
+  evidence?: string | null
+  likely_cause?: string | null
+  occurrence_count: number
+  flap_count: number
+  hold_down_until?: string | null
+  mute_until?: string | null
+  first_seen_at: string
+  last_seen_at: string
+}
+
+export async function fetchSignals(filters: { state?: string; severity?: string } = {}): Promise<Signal[]> {
+  const params = new URLSearchParams()
+  if (filters.state) params.set('state', filters.state)
+  if (filters.severity) params.set('severity', filters.severity)
+  params.set('limit', '200')
+  const res = await fetch(`${API}/signals?${params}`)
+  if (!res.ok) return []
+  const data = await res.json()
+  return data.items ?? []
+}
+
+export async function ackSignal(id: string): Promise<Signal | null> {
+  const res = await fetch(`${API}/signals/${id}/ack`, { method: 'POST' })
+  if (!res.ok) return null
+  return res.json()
+}
+
+export async function resolveSignal(id: string, note?: string): Promise<Signal | null> {
+  const res = await fetch(`${API}/signals/${id}/resolve`, {
+    method: 'POST',
+    headers: { 'Content-Type': 'application/json' },
+    body: JSON.stringify({ note })
+  })
+  if (!res.ok) return null
+  return res.json()
+}
+
+export async function muteSignal(id: string, muteUntil: string, note?: string): Promise<Signal | null> {
+  const res = await fetch(`${API}/signals/${id}/mute`, {
+    method: 'POST',
+    headers: { 'Content-Type': 'application/json' },
+    body: JSON.stringify({ mute_until: muteUntil, note })
+  })
+  if (!res.ok) return null
+  return res.json()
+}
+
+export interface Relationship {
+  source: string
+  target: string
+  type: string
+  attributes?: Record<string, unknown> | null
+  valid_from: string
+  valid_to?: string | null
+}
+
+export type Health = 'healthy' | 'degraded' | 'down' | 'unknown'
+
+export interface GraphView {
+  nodes: Entity[]
+  edges: Relationship[]
+  truncated?: boolean
+  health?: Record<string, Health>
+}
+
+export interface GraphFilters {
+  root?: string
+  depth?: number
+  relType?: string[]
+  includeStatus?: boolean
+}
+
+export async function fetchGraph(filters: GraphFilters = {}): Promise<GraphView | null> {
+  const params = new URLSearchParams()
+  if (filters.root) params.set('root', filters.root)
+  if (filters.depth) params.set('depth', String(filters.depth))
+  for (const rt of filters.relType ?? []) params.append('rel_type', rt)
+  if (filters.includeStatus) params.append('include', 'status')
+  const res = await fetch(`${API}/graph?${params}`)
+  if (!res.ok) return null
+  return res.json()
+}
+
+export interface BlastRadiusItem {
+  entity: Entity
+  depth: number
+}
+
+export async function fetchBlastRadius(id: string): Promise<BlastRadiusItem[]> {
+  const res = await fetch(`${API}/entities/${id}/blast-radius`)
+  if (!res.ok) return []
+  const data = await res.json()
+  return data.items ?? []
+}
+
+export async function fetchEntity(id: string): Promise<Entity | null> {
+  const res = await fetch(`${API}/entities/${id}`)
+  if (!res.ok) return null
+  return res.json()
+}
+
+export interface MetricSample {
+  ts: string
+  value?: number | null
+  avg?: number | null
+  min?: number | null
+  max?: number | null
+}
+
+export interface MetricSeries {
+  entity_id: string
+  metric: string
+  rollup: 'raw' | '1h' | '1d'
+  samples: MetricSample[]
+}
+
+export async function fetchMetrics(entityId: string): Promise<MetricSeries[]> {
+  const params = new URLSearchParams({ entity_id: entityId, rollup: 'auto' })
+  const res = await fetch(`${API}/metrics?${params}`)
+  if (!res.ok) return []
+  const data = await res.json()
+  return data.items ?? []
+}
+
+export interface KnowledgeHit {
+  id: string
+  slug: string
+  type: 'document' | 'runbook' | 'investigation'
+  title: string
+}
+
+export async function fetchEntityKnowledge(entityId: string): Promise<KnowledgeHit[]> {
+  const res = await fetch(`${API}/knowledge/${entityId}`)
+  if (!res.ok) return []
+  const data = await res.json()
+  return data.items ?? []
+}
+
+export async function fetchEntityEvents(entityId: string): Promise<import('./stores/events').OikosEvent[]> {
+  const params = new URLSearchParams({ entity_id: entityId, limit: '50' })
+  const res = await fetch(`${API}/events?${params}`)
+  if (!res.ok) return []
+  const data = await res.json()
+  return data.items ?? []
+}
+
+export async function fetchEntitySignals(entityId: string): Promise<Signal[]> {
+  const params = new URLSearchParams({ entity_id: entityId, limit: '50' })
+  const res = await fetch(`${API}/signals?${params}`)
+  if (!res.ok) return []
+  const data = await res.json()
+  return data.items ?? []
+}
+
+export async function fetchEntityExecutions(entityId: string): Promise<Execution[]> {
+  const params = new URLSearchParams({ target: entityId, limit: '50' })
+  const res = await fetch(`${API}/executions?${params}`)
+  if (!res.ok) return []
+  const data = await res.json()
+  return data.items ?? []
+}
+
+export interface Check {
+  id: string
+  slug: string
+  kind: 'http' | 'tcp' | 'disk' | 'cert-expiry' | 'drift' | 'ping' | 'ssh-script'
+  target?: string | null
+  target_type?: string | null
+  config?: Record<string, unknown>
+  interval_s: number
+  timeout_s: number
+  zone?: string | null
+  enabled: boolean
+  version: number
+}
+
+export async function fetchChecksForTarget(targetSlug: string): Promise<Check[]> {
+  const params = new URLSearchParams({ target: targetSlug, limit: '50' })
+  const res = await fetch(`${API}/checks?${params}`)
+  if (!res.ok) return []
+  const data = await res.json()
+  return data.items ?? []
+}
+
+export async function patchCheck(id: string, version: number, patch: { enabled?: boolean; interval_s?: number; timeout_s?: number }): Promise<Check | null> {
+  const res = await fetch(`${API}/checks/${id}`, {
+    method: 'PATCH',
+    headers: { 'Content-Type': 'application/json', 'If-Match': `"${version}"` },
+    body: JSON.stringify(patch)
+  })
+  if (!res.ok) return null
+  return res.json()
+}
+
+export interface AgentActivity {
+  id: number
+  ts: string
+  agent_id: string
+  session_id?: string | null
+  activity_type: 'tool_call' | 'reasoning' | 'decision' | 'mcp_query' | 'escalation'
+  tool_name?: string | null
+  entity_id?: string | null
+  input_summary?: string | null
+  output_summary?: string | null
+  duration_ms?: number | null
+  token_count?: number | null
+  success?: boolean | null
+  correlation_id?: string | null
+}
+
+export async function fetchAgentActivity(filters: {
+  agent_id?: string
+  activity_type?: string
+  entity_id?: string
+  limit?: number
+} = {}): Promise<AgentActivity[]> {
+  const params = new URLSearchParams()
+  if (filters.agent_id) params.set('agent_id', filters.agent_id)
+  if (filters.activity_type) params.set('activity_type', filters.activity_type)
+  if (filters.entity_id) params.set('entity_id', filters.entity_id)
+  params.set('limit', String(filters.limit ?? 200))
+  const res = await fetch(`${API}/agent-activity?${params}`)
+  if (!res.ok) return []
+  const data = await res.json()
+  return data.items ?? []
+}
+
+export async function searchKnowledge(q: string, limit = 50): Promise<KnowledgeHit[]> {
+  const params = new URLSearchParams({ q, limit: String(limit) })
+  const res = await fetch(`${API}/knowledge/search?${params}`)
+  if (!res.ok) return []
+  const data = await res.json()
+  return data.items ?? []
+}
+
+export interface AuditEntry {
+  id: number
+  ts: string
+  actor_type: 'agent' | 'operator' | 'system' | 'scheduler'
+  actor_id?: string | null
+  action: string
+  entity_id?: string | null
+  method?: string | null
+  path?: string | null
+  status_code?: number | null
+  detail?: Record<string, unknown>
+  source_ip?: string | null
+  correlation_id?: string | null
+}
+
+export async function fetchAudit(filters: {
+  actor_type?: string
+  actor_id?: string
+  entity_id?: string
+  action?: string
+  correlation_id?: string
+  limit?: number
+} = {}): Promise<AuditEntry[]> {
+  const params = new URLSearchParams()
+  if (filters.actor_type) params.set('actor_type', filters.actor_type)
+  if (filters.actor_id) params.set('actor_id', filters.actor_id)
+  if (filters.entity_id) params.set('entity_id', filters.entity_id)
+  if (filters.action) params.set('action', filters.action)
+  if (filters.correlation_id) params.set('correlation_id', filters.correlation_id)
+  params.set('limit', String(filters.limit ?? 200))
+  const res = await fetch(`${API}/audit?${params}`)
+  if (!res.ok) return []
+  const data = await res.json()
+  return data.items ?? []
+}

web/src/lib/components/EntityDetailContent.svelte

@@ -0,0 +1,297 @@
+<script lang="ts">
+  import { onMount, tick } from 'svelte'
+  import uPlot from 'uplot'
+  import 'uplot/dist/uPlot.min.css'
+  import {
+    fetchEntity,
+    fetchGraph,
+    fetchMetrics,
+    fetchEntityEvents,
+    fetchEntitySignals,
+    fetchEntityExecutions,
+    fetchEntityKnowledge,
+    fetchChecksForTarget,
+    patchCheck,
+    type Entity,
+    type Relationship,
+    type MetricSeries,
+    type Signal,
+    type Execution,
+    type KnowledgeHit,
+    type Check
+  } from '$lib/api'
+  import { relativeTime } from '$lib/utils'
+  import type { OikosEvent } from '$lib/stores/events'
+  import * as Card from '$lib/components/ui/card'
+  import { Badge } from '$lib/components/ui/badge'
+  import { Skeleton } from '$lib/components/ui/skeleton'
+  import { toast } from 'svelte-sonner'
+
+  let { slug }: { slug: string } = $props()
+
+  let entity = $state<Entity | null>(null)
+  let relations = $state<Relationship[]>([])
+  let metrics = $state<MetricSeries[]>([])
+  let events = $state<OikosEvent[]>([])
+  let signals = $state<Signal[]>([])
+  let executions = $state<Execution[]>([])
+  let knowledge = $state<KnowledgeHit[]>([])
+  let checks = $state<Check[]>([])
+  let loading = $state(true)
+  let chartContainers: Record<string, HTMLDivElement> = {}
+
+  async function load(s: string) {
+    loading = true
+    entity = await fetchEntity(s)
+    if (!entity) {
+      loading = false
+      return
+    }
+    const [graphView, m, ev, sig, exec, kh, ch] = await Promise.all([
+      fetchGraph({ root: entity.id, depth: 1 }),
+      fetchMetrics(entity.id),
+      fetchEntityEvents(entity.id),
+      fetchEntitySignals(entity.id),
+      fetchEntityExecutions(entity.id),
+      fetchEntityKnowledge(entity.id),
+      fetchChecksForTarget(entity.slug)
+    ])
+    relations = graphView?.edges ?? []
+    metrics = m
+    events = ev
+    signals = sig
+    executions = exec
+    knowledge = kh
+    checks = ch
+    loading = false
+
+    await tick()
+    renderCharts()
+  }
+
+  onMount(() => {
+    load(slug)
+  })
+
+  $effect(() => {
+    if (slug) load(slug)
+  })
+
+  function renderCharts() {
+    for (const series of metrics) {
+      const el = chartContainers[series.metric]
+      if (!el) continue
+      el.innerHTML = ''
+      const xs = series.samples.map((s) => new Date(s.ts).getTime() / 1000)
+      const ys = series.samples.map((s) => s.value ?? s.avg ?? null)
+      new uPlot(
+        {
+          width: el.clientWidth || 400,
+          height: 160,
+          series: [{}, { label: series.metric, stroke: '#58a6ff', width: 2 }],
+          axes: [{ stroke: '#8b949e' }, { stroke: '#8b949e' }],
+          scales: { x: { time: true } },
+          legend: { show: false }
+        },
+        [xs, ys],
+        el
+      )
+    }
+  }
+
+  function severityVariant(sev: string): 'default' | 'secondary' | 'destructive' {
+    if (sev === 'critical') return 'destructive'
+    if (sev === 'warning') return 'secondary'
+    return 'default'
+  }
+
+  const healthDot: Record<string, string> = {
+    healthy: 'bg-success',
+    degraded: 'bg-warning',
+    down: 'bg-destructive',
+    stale: 'bg-warning/50',
+    unknown: 'bg-muted-foreground/40'
+  }
+
+  async function toggleCheck(check: Check) {
+    const updated = await patchCheck(check.id, check.version, { enabled: !check.enabled })
+    if (updated) {
+      checks = checks.map((c) => (c.id === check.id ? updated : c))
+      toast.success(`${check.slug} ${updated.enabled ? 'enabled' : 'disabled'}`)
+    } else {
+      toast.error('Failed to update check')
+    }
+  }
+</script>
+
+<div class="@container flex h-full flex-col gap-4 overflow-y-auto p-4 md:p-6">
+  {#if loading}
+    <Skeleton class="h-8 w-48" />
+    <div class="grid grid-cols-1 gap-4 @lg:grid-cols-2">
+      <Skeleton class="h-40 w-full" />
+      <Skeleton class="h-40 w-full" />
+    </div>
+  {:else if !entity}
+    <p class="text-sm text-muted-foreground">Entity "{slug}" not found.</p>
+  {:else}
+    <div class="flex flex-wrap items-center gap-2">
+      <h1 class="font-mono text-lg font-semibold">{entity.slug}</h1>
+      <Badge variant="outline">{entity.type}</Badge>
+      {#if entity.state}<Badge>{entity.state}</Badge>{/if}
+      {#if entity.health}
+        <span class="flex items-center gap-1.5 text-xs text-muted-foreground" title="{entity.health} — checked {relativeTime(entity.last_check_at)}">
+          <span class="size-2 rounded-full {healthDot[entity.health] ?? healthDot.unknown}"></span>
+          {entity.health} · checked {relativeTime(entity.last_check_at)}
+        </span>
+      {/if}
+    </div>
+
+    <Card.Root>
+      <Card.Header>
+        <Card.Title class="text-sm">Monitoring ({checks.length})</Card.Title>
+      </Card.Header>
+      <Card.Content class="flex flex-col gap-1.5">
+        {#each checks as check (check.id)}
+          <div class="flex items-center justify-between gap-2 rounded-md border px-2.5 py-1.5 text-xs">
+            <div class="flex items-center gap-2">
+              <Badge variant="outline" class="font-mono">{check.kind}</Badge>
+              <span class="text-muted-foreground">every {check.interval_s}s</span>
+            </div>
+            <button
+              type="button"
+              class="cursor-pointer"
+              onclick={() => toggleCheck(check)}
+              title={check.enabled ? 'Click to disable' : 'Click to enable'}
+            >
+              <Badge variant={check.enabled ? 'default' : 'secondary'}>{check.enabled ? 'enabled' : 'disabled'}</Badge>
+            </button>
+          </div>
+        {:else}
+          <p class="text-xs text-muted-foreground">No checks configured for this entity.</p>
+        {/each}
+      </Card.Content>
+    </Card.Root>
+
+    <div class="grid grid-cols-1 gap-4 @2xl:grid-cols-2">
+      <Card.Root>
+        <Card.Header>
+          <Card.Title class="text-sm">Attributes</Card.Title>
+        </Card.Header>
+        <Card.Content>
+          {#if entity.attributes && Object.keys(entity.attributes).length}
+            <dl class="flex flex-col gap-1.5 text-xs">
+              {#each Object.entries(entity.attributes) as [key, value]}
+                <div class="flex items-start justify-between gap-3 border-b pb-1.5 last:border-0">
+                  <dt class="shrink-0 font-mono text-muted-foreground">{key}</dt>
+                  <dd class="min-w-0 flex-1 truncate text-right">
+                    {typeof value === 'object' ? JSON.stringify(value) : String(value)}
+                  </dd>
+                </div>
+              {/each}
+            </dl>
+          {:else}
+            <p class="text-xs text-muted-foreground">No attributes.</p>
+          {/if}
+        </Card.Content>
+      </Card.Root>
+
+      <Card.Root>
+        <Card.Header>
+          <Card.Title class="text-sm">Relations ({relations.length})</Card.Title>
+        </Card.Header>
+        <Card.Content class="flex flex-col gap-1">
+          {#each relations as rel}
+            <div class="flex items-center gap-1 font-mono text-xs">
+              <span>{rel.source}</span>
+              <span class="text-muted-foreground">—{rel.type}→</span>
+              <span>{rel.target}</span>
+            </div>
+          {:else}
+            <p class="text-xs text-muted-foreground">No direct relations.</p>
+          {/each}
+        </Card.Content>
+      </Card.Root>
+    </div>
+
+    {#if metrics.length}
+      <Card.Root>
+        <Card.Header>
+          <Card.Title class="text-sm">Metrics</Card.Title>
+        </Card.Header>
+        <Card.Content class="grid grid-cols-1 gap-4 @2xl:grid-cols-2">
+          {#each metrics as series (series.metric)}
+            <div>
+              <p class="mb-1 text-xs text-muted-foreground">{series.metric} ({series.rollup})</p>
+              <div bind:this={chartContainers[series.metric]}></div>
+            </div>
+          {/each}
+        </Card.Content>
+      </Card.Root>
+    {/if}
+
+    <div class="grid grid-cols-1 gap-4 @3xl:grid-cols-3">
+      <Card.Root>
+        <Card.Header>
+          <Card.Title class="text-sm">Open signals</Card.Title>
+        </Card.Header>
+        <Card.Content class="flex flex-col gap-1">
+          {#each signals as signal (signal.id)}
+            <div class="flex items-center justify-between text-xs">
+              <span>{signal.kind}</span>
+              <Badge variant={severityVariant(signal.severity)}>{signal.severity}</Badge>
+            </div>
+          {:else}
+            <p class="text-xs text-muted-foreground">None.</p>
+          {/each}
+        </Card.Content>
+      </Card.Root>
+
+      <Card.Root>
+        <Card.Header>
+          <Card.Title class="text-sm">Executions</Card.Title>
+        </Card.Header>
+        <Card.Content class="flex flex-col gap-1">
+          {#each executions as execution (execution.id)}
+            <div class="flex items-center justify-between text-xs">
+              <span>{execution.action}</span>
+              <Badge variant="outline">{execution.status}</Badge>
+            </div>
+          {:else}
+            <p class="text-xs text-muted-foreground">None.</p>
+          {/each}
+        </Card.Content>
+      </Card.Root>
+
+      <Card.Root>
+        <Card.Header>
+          <Card.Title class="text-sm">Knowledge</Card.Title>
+        </Card.Header>
+        <Card.Content class="flex flex-col gap-1">
+          {#each knowledge as hit (hit.id)}
+            <div class="text-xs">
+              <Badge variant="outline" class="mr-1">{hit.type}</Badge>{hit.title}
+            </div>
+          {:else}
+            <p class="text-xs text-muted-foreground">None linked.</p>
+          {/each}
+        </Card.Content>
+      </Card.Root>
+    </div>
+
+    <Card.Root>
+      <Card.Header>
+        <Card.Title class="text-sm">Recent events</Card.Title>
+      </Card.Header>
+      <Card.Content class="flex flex-col gap-1">
+        {#each events as ev (ev.id)}
+          <div class="flex items-center gap-2 text-xs">
+            <span class="font-mono text-muted-foreground">{new Date(ev.ts).toLocaleString()}</span>
+            <span>{ev.type}</span>
+          </div>
+        {:else}
+          <p class="text-xs text-muted-foreground">No events yet.</p>
+        {/each}
+      </Card.Content>
+    </Card.Root>
+  {/if}
+</div>

web/src/lib/components/EntitySheet.svelte

@@ -0,0 +1,18 @@
+<script lang="ts">
+  import EntityDetailContent from '$lib/components/EntityDetailContent.svelte'
+  import * as Sheet from '$lib/components/ui/sheet'
+
+  let { slug, open = $bindable(false) }: { slug: string | null; open?: boolean } = $props()
+</script>
+
+<Sheet.Root bind:open>
+  <Sheet.Content side="right" class="w-full p-0 sm:max-w-2xl">
+    <Sheet.Header class="sr-only">
+      <Sheet.Title>{slug ?? 'Entity detail'}</Sheet.Title>
+      <Sheet.Description>Entity detail panel</Sheet.Description>
+    </Sheet.Header>
+    {#if slug}
+      <EntityDetailContent {slug} />
+    {/if}
+  </Sheet.Content>
+</Sheet.Root>

web/src/lib/components/SessionGraph.svelte

@@ -0,0 +1,441 @@
+<script lang="ts">
+  import { onDestroy, untrack } from 'svelte'
+  import {
+    forceSimulation,
+    forceLink,
+    forceManyBody,
+    forceCenter,
+    forceCollide,
+    forceX,
+    forceY,
+    type Simulation
+  } from 'd3-force'
+  import { fetchGraph, type Entity } from '$lib/api'
+  import { messages } from '$lib/stores/chat'
+  import { relativeTime } from '$lib/utils'
+  import { Badge } from '$lib/components/ui/badge'
+  import { Button } from '$lib/components/ui/button'
+  import EntitySheet from '$lib/components/EntitySheet.svelte'
+  import ExternalLinkIcon from '@lucide/svelte/icons/external-link'
+
+  interface Node extends Entity {
+    x?: number
+    y?: number
+    vx?: number
+    vy?: number
+    fx?: number | null
+    fy?: number | null
+    degree: number
+  }
+  interface Edge {
+    source: string | Node
+    target: string | Node
+    type: string
+  }
+
+  // Probe/bookkeeping entity types are excluded — a health conversation
+  // mentions dozens of check:… slugs that would swamp the fleet topology.
+  const EXCLUDED = new Set(['check', 'execution'])
+
+  // Slug shape: lowercase type prefix, then one or more colon-separated
+  // segments (host:hubris, check:ping:8cf, lxc:caddy, investigation:foo/bar).
+  const SLUG_RE = /\b[a-z][a-z-]*:[a-z0-9][a-z0-9._/-]*(?::[a-z0-9._/-]+)*/g
+
+  let nodes = $state<Node[]>([])
+  let links = $state<Edge[]>([])
+  let selected = $state<Node | null>(null)
+  let sheetSlug = $state<string | null>(null)
+  let sheetOpen = $state(false)
+
+  let sim: Simulation<Node, Edge> | null = null
+
+  // Non-reactive caches (persist across message deltas). resolvedVersion is a
+  // reactive counter bumped when async resolution finishes, so the reconcile
+  // effect re-runs once entities come back.
+  const resolvedCache = new Map<string, Node | null>()
+  const edgeCache: { source: string; target: string; type: string }[] = []
+  const edgeKeys = new Set<string>()
+  const resolving = new Set<string>()
+  let resolvedVersion = $state(0)
+
+  // container size drives the simulation coordinate space (1:1 with pixels so
+  // node dragging maps cleanly regardless of the resizable panel width).
+  let container = $state<HTMLDivElement | null>(null)
+  let cw = $state(300)
+  let ch = $state(300)
+
+  function collectSlugs(value: unknown, out: Set<string>) {
+    if (typeof value === 'string') {
+      const m = value.match(SLUG_RE)
+      if (m) for (const s of m) out.add(s.replace(/[.,;)\]]+$/, ''))
+    } else if (Array.isArray(value)) {
+      for (const v of value) collectSlugs(v, out)
+    } else if (value && typeof value === 'object') {
+      for (const v of Object.values(value)) collectSlugs(v, out)
+    }
+  }
+
+  // Only pull from what the conversation is *about*: message text and the
+  // arguments the agent passed to tools — never bulk result rows (a single
+  // get_health_summary would otherwise dump all 168 entities into the graph).
+  const candidateSlugs = $derived.by(() => {
+    const out = new Set<string>()
+    for (const m of $messages) {
+      collectSlugs(m.text, out)
+      for (const t of m.tools) collectSlugs(t.args, out)
+    }
+    return out
+  })
+
+  async function resolveSlugs(slugs: string[]) {
+    const todo = slugs.filter((s) => !resolvedCache.has(s) && !resolving.has(s))
+    if (!todo.length) return
+    for (const s of todo) resolving.add(s)
+    await Promise.all(
+      todo.map(async (s) => {
+        try {
+          const g = await fetchGraph({ root: s, depth: 1 })
+          const root = g?.nodes.find((n) => n.slug === s) ?? null
+          resolvedCache.set(s, root ? { ...root, degree: 0 } : null)
+          if (g && root) {
+            for (const e of g.edges) {
+              const k = `${e.source}|${e.target}|${e.type}`
+              if (!edgeKeys.has(k)) {
+                edgeKeys.add(k)
+                edgeCache.push({ source: e.source, target: e.target, type: e.type })
+              }
+            }
+          }
+        } catch {
+          resolvedCache.set(s, null)
+        } finally {
+          resolving.delete(s)
+        }
+      })
+    )
+    resolvedVersion++
+  }
+
+  function reconcile(cands: Set<string>) {
+    const desired: Node[] = []
+    const seen = new Set<string>()
+    for (const s of cands) {
+      const e = resolvedCache.get(s)
+      if (e && !EXCLUDED.has(e.type) && !seen.has(e.slug)) {
+        seen.add(e.slug)
+        desired.push(e)
+      }
+    }
+    const desiredSlugs = new Set(desired.map((e) => e.slug))
+    const current = nodes
+    const curSlugs = new Set(current.map((n) => n.slug))
+
+    let changed = desiredSlugs.size !== curSlugs.size
+    if (!changed) for (const s of desiredSlugs) if (!curSlugs.has(s)) { changed = true; break }
+    if (!changed) return
+
+    const bySlug = new Map(current.map((n) => [n.slug, n]))
+    const ls = edgeCache
+      .filter((e) => desiredSlugs.has(e.source) && desiredSlugs.has(e.target))
+      .map((e) => ({ ...e }))
+
+    const deg = new Map<string, number>()
+    for (const l of ls) {
+      deg.set(l.source as string, (deg.get(l.source as string) ?? 0) + 1)
+      deg.set(l.target as string, (deg.get(l.target as string) ?? 0) + 1)
+    }
+
+    const next = desired.map((e) => {
+      const p = bySlug.get(e.slug)
+      return { ...e, x: p?.x, y: p?.y, vx: p?.vx, vy: p?.vy, degree: deg.get(e.slug) ?? 0 }
+    })
+
+    nodes = next
+    links = ls
+    if (selected && !desiredSlugs.has(selected.slug)) selected = null
+    buildSim()
+  }
+
+  $effect(() => {
+    const cands = candidateSlugs
+    void resolvedVersion
+    const missing = [...cands].filter((s) => !resolvedCache.has(s))
+    if (missing.length) resolveSlugs(missing)
+    untrack(() => reconcile(cands))
+  })
+
+  function buildSim() {
+    sim?.stop()
+    if (!nodes.length) {
+      sim = null
+      return
+    }
+    sim = forceSimulation(nodes)
+      .force('link', forceLink<Node, Edge>(links).id((n) => n.slug).distance(48).strength(0.5))
+      .force('charge', forceManyBody().strength(-150).distanceMax(240))
+      .force('center', forceCenter(cw / 2, ch / 2))
+      .force('collide', forceCollide<Node>((n) => nodeRadius(n) + 6))
+      .force('x', forceX(cw / 2).strength(0.06))
+      .force('y', forceY(ch / 2).strength(0.06))
+      .velocityDecay(0.34)
+      .alphaDecay(0.045)
+      .on('tick', () => {
+        nodes = [...nodes]
+      })
+  }
+
+  // keep the layout centred as the panel resizes
+  $effect(() => {
+    const w = cw
+    const h = ch
+    if (sim) {
+      sim.force('center', forceCenter(w / 2, h / 2))
+      sim.force('x', forceX(w / 2).strength(0.06))
+      sim.force('y', forceY(h / 2).strength(0.06))
+      sim.alpha(0.3).restart()
+    }
+  })
+
+  $effect(() => {
+    if (!container) return
+    const ro = new ResizeObserver((entries) => {
+      const r = entries[0].contentRect
+      cw = Math.max(r.width, 1)
+      ch = Math.max(r.height, 1)
+    })
+    ro.observe(container)
+    return () => ro.disconnect()
+  })
+
+  onDestroy(() => sim?.stop())
+
+  const healthColor: Record<string, string> = {
+    healthy: 'var(--success)',
+    degraded: 'var(--warning)',
+    down: 'var(--destructive)',
+    stale: 'var(--warning)',
+    unknown: 'var(--muted-foreground)'
+  }
+  function nodeColor(n: Node): string {
+    return n.health ? healthColor[n.health] ?? 'var(--muted-foreground)' : 'var(--muted-foreground)'
+  }
+  function nodeRadius(n: Node): number {
+    return 6 + Math.min(Math.sqrt(n.degree) * 1.5, 6)
+  }
+  function shortName(slug: string): string {
+    return slug.split(':').pop() ?? slug
+  }
+
+  function endpoint(end: string | Node): Node | undefined {
+    return typeof end === 'object' ? end : nodes.find((n) => n.slug === end)
+  }
+  function endpointSlug(end: string | Node): string {
+    return typeof end === 'object' ? end.slug : end
+  }
+
+  // ─── drag / select ───────────────────────────────────────────────────
+  let dragState: { node: Node; moved: boolean } | null = null
+
+  function toLocal(clientX: number, clientY: number) {
+    const rect = container!.getBoundingClientRect()
+    return { x: clientX - rect.left, y: clientY - rect.top }
+  }
+
+  function onNodeDown(e: PointerEvent, node: Node) {
+    e.stopPropagation()
+    ;(e.currentTarget as Element).setPointerCapture(e.pointerId)
+    dragState = { node, moved: false }
+    sim?.alphaTarget(0.2).restart()
+  }
+  function onMove(e: PointerEvent) {
+    if (!dragState) return
+    const p = toLocal(e.clientX, e.clientY)
+    dragState.node.fx = p.x
+    dragState.node.fy = p.y
+    dragState.moved = true
+    nodes = [...nodes]
+  }
+  function onUp() {
+    if (!dragState) return
+    const { node, moved } = dragState
+    node.fx = null
+    node.fy = null
+    sim?.alphaTarget(0)
+    dragState = null
+    if (!moved) selected = selected?.slug === node.slug ? null : node
+  }
+
+  const selectedRelations = $derived(
+    selected
+      ? links
+          .filter((l) => endpointSlug(l.source) === selected!.slug || endpointSlug(l.target) === selected!.slug)
+          .map((l) => {
+            const outgoing = endpointSlug(l.source) === selected!.slug
+            return { dir: outgoing ? '→' : '←', type: l.type, other: outgoing ? endpointSlug(l.target) : endpointSlug(l.source) }
+          })
+      : []
+  )
+
+  function openFull() {
+    if (!selected) return
+    sheetSlug = selected.slug
+    sheetOpen = true
+  }
+</script>
+
+<aside class="flex h-full min-h-0 flex-col bg-card/40">
+  <div class="flex shrink-0 items-center justify-between border-b px-3 py-2">
+    <p class="text-[11px] font-semibold uppercase tracking-wider text-muted-foreground">Session graph</p>
+    {#if nodes.length}
+      <span class="text-[11px] text-muted-foreground">{nodes.length} {nodes.length === 1 ? 'entity' : 'entities'}</span>
+    {/if}
+  </div>
+
+  <div bind:this={container} class="relative min-h-0 flex-1 overflow-hidden">
+    {#if nodes.length === 0}
+      <div class="pointer-events-none absolute inset-0 flex flex-col items-center justify-center gap-4 px-6 text-center">
+        <svg viewBox="0 0 120 120" class="size-24 text-muted-foreground/40" fill="none">
+          <circle cx="60" cy="60" r="6" fill="currentColor">
+            <animate attributeName="opacity" values="0.4;1;0.4" dur="2.4s" repeatCount="indefinite" />
+          </circle>
+          <g stroke="currentColor" stroke-width="1" opacity="0.5">
+            <line x1="60" y1="60" x2="26" y2="34"><animate attributeName="opacity" values="0.1;0.5;0.1" dur="3s" repeatCount="indefinite" /></line>
+            <line x1="60" y1="60" x2="96" y2="40"><animate attributeName="opacity" values="0.1;0.5;0.1" dur="3.4s" repeatCount="indefinite" /></line>
+            <line x1="60" y1="60" x2="34" y2="92"><animate attributeName="opacity" values="0.1;0.5;0.1" dur="2.8s" repeatCount="indefinite" /></line>
+            <line x1="60" y1="60" x2="92" y2="90"><animate attributeName="opacity" values="0.1;0.5;0.1" dur="3.1s" repeatCount="indefinite" /></line>
+          </g>
+          <g fill="currentColor">
+            <circle cx="26" cy="34" r="3.5"><animate attributeName="opacity" values="0.2;0.7;0.2" dur="3s" repeatCount="indefinite" /></circle>
+            <circle cx="96" cy="40" r="3.5"><animate attributeName="opacity" values="0.2;0.7;0.2" dur="3.4s" repeatCount="indefinite" /></circle>
+            <circle cx="34" cy="92" r="3.5"><animate attributeName="opacity" values="0.2;0.7;0.2" dur="2.8s" repeatCount="indefinite" /></circle>
+            <circle cx="92" cy="90" r="3.5"><animate attributeName="opacity" values="0.2;0.7;0.2" dur="3.1s" repeatCount="indefinite" /></circle>
+          </g>
+        </svg>
+        <p class="max-w-[16rem] text-xs leading-relaxed text-muted-foreground">
+          Entities Nomos explores in this conversation appear here, wired up by their relationships.
+        </p>
+      </div>
+    {:else}
+      <svg
+        width={cw}
+        height={ch}
+        viewBox="0 0 {cw} {ch}"
+        class="h-full w-full touch-none select-none"
+        role="application"
+        aria-label="Session entity graph"
+        onpointermove={onMove}
+        onpointerup={onUp}
+        onpointercancel={onUp}
+      >
+        <g>
+          {#each links as link}
+            {@const s = endpoint(link.source)}
+            {@const t = endpoint(link.target)}
+            {#if s?.x != null && t?.x != null && s?.y != null && t?.y != null}
+              {@const focus = selected && (s.slug === selected.slug || t.slug === selected.slug)}
+              <line
+                x1={s.x}
+                y1={s.y}
+                x2={t.x}
+                y2={t.y}
+                stroke="var(--muted-foreground)"
+                stroke-width={focus ? 1.6 : 1}
+                opacity={selected ? (focus ? 0.7 : 0.12) : 0.35}
+              >
+                <title>{link.type}</title>
+              </line>
+            {/if}
+          {/each}
+        </g>
+        <g>
+          {#each nodes as node (node.slug)}
+            {#if node.x != null && node.y != null}
+              {@const r = nodeRadius(node)}
+              {@const isSel = selected?.slug === node.slug}
+              {@const dim = selected && !isSel && !selectedRelations.some((rel) => rel.other === node.slug)}
+              <g
+                transform="translate({node.x},{node.y})"
+                class="cursor-pointer"
+                opacity={dim ? 0.35 : 1}
+                role="button"
+                tabindex="0"
+                onpointerdown={(e) => onNodeDown(e, node)}
+                onkeydown={(e) => e.key === 'Enter' && (selected = node)}
+              >
+                {#if isSel}
+                  <circle r={r + 5} fill={nodeColor(node)} opacity="0.25" />
+                {/if}
+                <circle r={r} fill={nodeColor(node)} stroke={isSel ? 'var(--foreground)' : 'var(--background)'} stroke-width={isSel ? 2 : 1.5} />
+                <text
+                  y={r + 10}
+                  text-anchor="middle"
+                  font-size="9"
+                  fill={isSel ? 'var(--foreground)' : 'var(--muted-foreground)'}
+                  paint-order="stroke"
+                  stroke="var(--background)"
+                  stroke-width="2.5"
+                  class="pointer-events-none"
+                >
+                  {shortName(node.slug)}
+                </text>
+              </g>
+            {/if}
+          {/each}
+        </g>
+      </svg>
+    {/if}
+  </div>
+
+  {#if selected}
+    <div class="max-h-[55%] shrink-0 space-y-3 overflow-y-auto border-t p-3 text-xs">
+      <div class="flex flex-wrap items-center gap-1.5">
+        <span class="font-mono text-sm font-semibold">{selected.slug}</span>
+        <Badge variant="outline">{selected.type}</Badge>
+        {#if selected.state}<Badge variant="secondary">{selected.state}</Badge>{/if}
+      </div>
+      {#if selected.health}
+        <div class="flex items-center gap-1.5 text-muted-foreground">
+          <span class="size-2 rounded-full" style="background: {nodeColor(selected)}"></span>
+          {selected.health} · checked {relativeTime(selected.last_check_at)}
+        </div>
+      {/if}
+
+      {#if selected.attributes && Object.keys(selected.attributes).length}
+        <div>
+          <p class="mb-1 font-medium text-muted-foreground">Attributes</p>
+          <dl class="flex flex-col gap-1">
+            {#each Object.entries(selected.attributes).slice(0, 6) as [key, value]}
+              <div class="flex items-start justify-between gap-3 border-b pb-1 last:border-0">
+                <dt class="shrink-0 font-mono text-muted-foreground">{key}</dt>
+                <dd class="min-w-0 flex-1 truncate text-right">{typeof value === 'object' ? JSON.stringify(value) : String(value)}</dd>
+              </div>
+            {/each}
+          </dl>
+        </div>
+      {/if}
+
+      {#if selectedRelations.length}
+        <div>
+          <p class="mb-1 font-medium text-muted-foreground">Relations ({selectedRelations.length})</p>
+          <div class="flex flex-col gap-1">
+            {#each selectedRelations as rel}
+              <div class="flex items-center gap-1 font-mono">
+                <span class="text-muted-foreground">{rel.dir} {rel.type} →</span>
+                <button type="button" class="truncate hover:underline" onclick={() => { const n = nodes.find((x) => x.slug === rel.other); if (n) selected = n }}>
+                  {rel.other}
+                </button>
+              </div>
+            {/each}
+          </div>
+        </div>
+      {/if}
+
+      <Button variant="outline" size="sm" class="w-full" onclick={openFull}>
+        <ExternalLinkIcon class="mr-1 size-3.5" />
+        Full detail
+      </Button>
+    </div>
+  {/if}
+</aside>
+
+<EntitySheet slug={sheetSlug} bind:open={sheetOpen} />

web/src/lib/components/SessionRail.svelte

@@ -0,0 +1,41 @@
+<script lang="ts">
+  import { onMount } from 'svelte'
+  import { sessions, currentSession, loadSessions, loadSessionMessages, newChat } from '$lib/stores/chat'
+  import { relativeTime } from '$lib/utils'
+  import { Button } from '$lib/components/ui/button'
+  import { ScrollArea } from '$lib/components/ui/scroll-area'
+  import PlusIcon from '@lucide/svelte/icons/plus'
+
+  onMount(() => {
+    loadSessions()
+  })
+
+  // Pick up sessions created/renamed elsewhere (e.g. after a turn completes).
+  $effect(() => {
+    void $currentSession
+    loadSessions()
+  })
+</script>
+
+<aside class="flex h-full w-56 shrink-0 flex-col gap-2 overflow-y-auto border-r bg-card/50 p-2">
+  <Button variant="outline" size="sm" class="justify-start gap-2" onclick={() => newChat()}>
+    <PlusIcon class="size-3.5" />
+    New chat
+  </Button>
+  <ScrollArea class="min-h-0 flex-1">
+    <div class="flex flex-col gap-1 pr-2">
+      {#each $sessions as session (session.id)}
+        <button
+          type="button"
+          class="flex flex-col items-start gap-0.5 rounded-md border px-2 py-1.5 text-left text-xs transition-colors hover:bg-muted/60 {$currentSession === session.id ? 'border-primary bg-muted/50' : 'border-transparent'}"
+          onclick={() => loadSessionMessages(session.id)}
+        >
+          <span class="w-full truncate font-medium">{session.title || 'Untitled'}</span>
+          <span class="text-[11px] text-muted-foreground">{relativeTime(session.last_active_at)}</span>
+        </button>
+      {:else}
+        <p class="px-2 py-4 text-center text-xs text-muted-foreground">No sessions yet.</p>
+      {/each}
+    </div>
+  </ScrollArea>
+</aside>

web/src/lib/components/ToolCallGroup.svelte

@@ -0,0 +1,79 @@
+<script lang="ts">
+  import type { ToolCallResult } from '$lib/stores/chat'
+  import WrenchIcon from '@lucide/svelte/icons/wrench'
+  import CheckIcon from '@lucide/svelte/icons/check'
+  import XIcon from '@lucide/svelte/icons/x'
+  import ChevronDownIcon from '@lucide/svelte/icons/chevron-down'
+
+  // active = this message is the one currently streaming a round of tool
+  // calls. The group starts open while active (so progress is visible live)
+  // and auto-collapses the moment that round finishes; a loaded/historical
+  // message is never active, so it starts collapsed. Once the effect below
+  // fires the one-time auto-collapse, manual toggles are left alone.
+  let { tools, active = false }: { tools: ToolCallResult[]; active?: boolean } = $props()
+
+  let open = $state(active)
+  let wasActive = active
+
+  $effect(() => {
+    if (wasActive && !active) {
+      open = false
+    }
+    wasActive = active
+  })
+
+  const doneCount = $derived(tools.filter((t) => t.type === 'tool_result').length)
+  const hasError = $derived(tools.some((t) => t.type === 'tool_result' && t.error))
+  const inProgress = $derived(active && doneCount < tools.length)
+  const names = $derived(tools.map((t) => t.name).join(', '))
+
+  function toolSummary(args: unknown): string {
+    if (!args || typeof args !== 'object') return ''
+    return Object.entries(args as Record<string, unknown>)
+      .map(([k, v]) => `${k}=${typeof v === 'string' ? v : JSON.stringify(v)}`)
+      .join(' ')
+      .slice(0, 80)
+  }
+</script>
+
+{#if tools.length}
+  <details bind:open class="group w-fit max-w-full overflow-hidden rounded-lg border bg-card text-xs">
+    <summary class="flex cursor-pointer select-none items-center gap-2 px-2.5 py-1.5 hover:bg-muted/50 [&::-webkit-details-marker]:hidden">
+      {#if inProgress}
+        <WrenchIcon class="size-3 shrink-0 animate-pulse text-primary" />
+      {:else if hasError}
+        <XIcon class="size-3 shrink-0 text-destructive" />
+      {:else}
+        <CheckIcon class="size-3 shrink-0 text-success" />
+      {/if}
+      <span class="font-medium">{tools.length} tool{tools.length === 1 ? '' : 's'}</span>
+      <span class="max-w-64 truncate font-mono text-muted-foreground">{names}</span>
+      <ChevronDownIcon class="size-3 shrink-0 text-muted-foreground transition-transform group-open:rotate-180" />
+    </summary>
+    <div class="flex flex-col divide-y border-t">
+      {#each tools as tool (tool.id)}
+        <div class="p-2">
+          <div class="flex items-center gap-2">
+            {#if tool.type === 'tool_result' && tool.error}
+              <XIcon class="size-3 shrink-0 text-destructive" />
+            {:else if tool.type === 'tool_result'}
+              <CheckIcon class="size-3 shrink-0 text-success" />
+            {:else}
+              <WrenchIcon class="size-3 shrink-0 animate-pulse text-primary" />
+            {/if}
+            <span class="font-mono font-medium">{tool.name}</span>
+            <span class="max-w-64 truncate text-muted-foreground">{toolSummary(tool.args)}</span>
+          </div>
+          <div class="mt-1 max-h-48 overflow-y-auto rounded bg-background/60 p-2">
+            {#if tool.args}
+              <pre class="whitespace-pre-wrap break-all font-mono text-[11px] text-muted-foreground">{JSON.stringify(tool.args, null, 2)}</pre>
+            {/if}
+            {#if tool.type === 'tool_result'}
+              <pre class="mt-1 whitespace-pre-wrap break-all font-mono text-[11px] {tool.error ? 'text-destructive' : ''}">{tool.error ?? JSON.stringify(tool.result, null, 2)}</pre>
+            {/if}
+          </div>
+        </div>
+      {/each}
+    </div>
+  </details>
+{/if}

web/src/lib/components/ui/badge/badge.svelte

@@ -0,0 +1,49 @@
+<script lang="ts" module>
+	import { type VariantProps, tv } from "tailwind-variants";
+
+	export const badgeVariants = tv({
+		base: "h-5 gap-1 rounded-4xl border border-transparent px-2 py-0.5 text-xs font-medium transition-all has-data-[icon=inline-end]:pr-1.5 has-data-[icon=inline-start]:pl-1.5 [&>svg]:size-3! focus-visible:border-ring focus-visible:ring-ring/50 aria-invalid:ring-destructive/20 dark:aria-invalid:ring-destructive/40 aria-invalid:border-destructive group/badge inline-flex w-fit shrink-0 items-center justify-center overflow-hidden whitespace-nowrap transition-colors focus-visible:ring-[3px] [&>svg]:pointer-events-none",
+		variants: {
+			variant: {
+				default: "bg-primary text-primary-foreground [a]:hover:bg-primary/80",
+				secondary: "bg-secondary text-secondary-foreground [a]:hover:bg-secondary/80",
+				destructive: "bg-destructive/10 [a]:hover:bg-destructive/20 focus-visible:ring-destructive/20 dark:focus-visible:ring-destructive/40 text-destructive dark:bg-destructive/20",
+				outline: "border-border text-foreground [a]:hover:bg-muted [a]:hover:text-muted-foreground",
+				ghost: "hover:bg-muted hover:text-muted-foreground dark:hover:bg-muted/50",
+				link: "text-primary underline-offset-4 hover:underline",
+			},
+		},
+		defaultVariants: {
+			variant: "default",
+		},
+	});
+
+	export type BadgeVariant = VariantProps<typeof badgeVariants>["variant"];
+</script>
+
+<script lang="ts">
+	import type { HTMLAnchorAttributes } from "svelte/elements";
+	import { cn, type WithElementRef } from "$lib/utils.js";
+
+	let {
+		ref = $bindable(null),
+		href,
+		class: className,
+		variant = "default",
+		children,
+		...restProps
+	}: WithElementRef<HTMLAnchorAttributes> & {
+		variant?: BadgeVariant;
+	} = $props();
+</script>
+
+<svelte:element
+	this={href ? "a" : "span"}
+	bind:this={ref}
+	data-slot="badge"
+	{href}
+	class={cn(badgeVariants({ variant }), className)}
+	{...restProps}
+>
+	{@render children?.()}
+</svelte:element>

web/src/lib/components/ui/badge/index.ts

@@ -0,0 +1,2 @@
+export { default as Badge } from "./badge.svelte";
+export { badgeVariants, type BadgeVariant } from "./badge.svelte";

web/src/lib/components/ui/button/button.svelte

@@ -0,0 +1,82 @@
+<script lang="ts" module>
+	import { cn, type WithElementRef } from "$lib/utils.js";
+	import type { HTMLAnchorAttributes, HTMLButtonAttributes } from "svelte/elements";
+	import { type VariantProps, tv } from "tailwind-variants";
+
+	export const buttonVariants = tv({
+		base: "focus-visible:border-ring focus-visible:ring-ring/50 aria-invalid:ring-destructive/20 dark:aria-invalid:ring-destructive/40 aria-invalid:border-destructive dark:aria-invalid:border-destructive/50 rounded-md border border-transparent bg-clip-padding text-sm font-medium focus-visible:ring-3 active:not-aria-[haspopup]:translate-y-px aria-invalid:ring-3 [&_svg:not([class*='size-'])]:size-4 group/button inline-flex shrink-0 items-center justify-center whitespace-nowrap transition-all outline-none select-none disabled:pointer-events-none disabled:opacity-50 [&_svg]:pointer-events-none [&_svg]:shrink-0",
+		variants: {
+			variant: {
+				default: "bg-primary text-primary-foreground hover:bg-primary/80",
+				outline: "border-border bg-background hover:bg-muted hover:text-foreground dark:bg-input/30 dark:border-input dark:hover:bg-input/50 aria-expanded:bg-muted aria-expanded:text-foreground shadow-xs",
+				secondary: "bg-secondary text-secondary-foreground hover:bg-secondary/80 aria-expanded:bg-secondary aria-expanded:text-secondary-foreground",
+				ghost: "hover:bg-muted hover:text-foreground dark:hover:bg-muted/50 aria-expanded:bg-muted aria-expanded:text-foreground",
+				destructive: "bg-destructive/10 hover:bg-destructive/20 focus-visible:ring-destructive/20 dark:focus-visible:ring-destructive/40 dark:bg-destructive/20 text-destructive focus-visible:border-destructive/40 dark:hover:bg-destructive/30",
+				link: "text-primary underline-offset-4 hover:underline",
+			},
+			size: {
+				default: "h-9 gap-1.5 px-2.5 in-data-[slot=button-group]:rounded-md has-data-[icon=inline-end]:pr-2 has-data-[icon=inline-start]:pl-2",
+				xs: "h-6 gap-1 rounded-[min(var(--radius-md),8px)] px-2 text-xs in-data-[slot=button-group]:rounded-md has-data-[icon=inline-end]:pr-1.5 has-data-[icon=inline-start]:pl-1.5 [&_svg:not([class*='size-'])]:size-3",
+				sm: "h-8 gap-1 rounded-[min(var(--radius-md),10px)] px-2.5 in-data-[slot=button-group]:rounded-md has-data-[icon=inline-end]:pr-1.5 has-data-[icon=inline-start]:pl-1.5",
+				lg: "h-10 gap-1.5 px-2.5 has-data-[icon=inline-end]:pr-2 has-data-[icon=inline-start]:pl-2",
+				icon: "size-9",
+				"icon-xs": "size-6 rounded-[min(var(--radius-md),8px)] in-data-[slot=button-group]:rounded-md [&_svg:not([class*='size-'])]:size-3",
+				"icon-sm": "size-8 rounded-[min(var(--radius-md),10px)] in-data-[slot=button-group]:rounded-md",
+				"icon-lg": "size-10",
+			},
+		},
+		defaultVariants: {
+			variant: "default",
+			size: "default",
+		},
+	});
+
+	export type ButtonVariant = VariantProps<typeof buttonVariants>["variant"];
+	export type ButtonSize = VariantProps<typeof buttonVariants>["size"];
+
+	export type ButtonProps = WithElementRef<HTMLButtonAttributes> &
+		WithElementRef<HTMLAnchorAttributes> & {
+			variant?: ButtonVariant;
+			size?: ButtonSize;
+		};
+</script>
+
+<script lang="ts">
+	let {
+		class: className,
+		variant = "default",
+		size = "default",
+		ref = $bindable(null),
+		href = undefined,
+		type = "button",
+		disabled,
+		children,
+		...restProps
+	}: ButtonProps = $props();
+</script>
+
+{#if href}
+	<a
+		bind:this={ref}
+		data-slot="button"
+		class={cn(buttonVariants({ variant, size }), className)}
+		href={disabled ? undefined : href}
+		aria-disabled={disabled}
+		role={disabled ? "link" : undefined}
+		tabindex={disabled ? -1 : undefined}
+		{...restProps}
+	>
+		{@render children?.()}
+	</a>
+{:else}
+	<button
+		bind:this={ref}
+		data-slot="button"
+		class={cn(buttonVariants({ variant, size }), className)}
+		{type}
+		{disabled}
+		{...restProps}
+	>
+		{@render children?.()}
+	</button>
+{/if}

web/src/lib/components/ui/button/index.ts

@@ -0,0 +1,17 @@
+import Root, {
+	type ButtonProps,
+	type ButtonSize,
+	type ButtonVariant,
+	buttonVariants,
+} from "./button.svelte";
+
+export {
+	Root,
+	type ButtonProps as Props,
+	//
+	Root as Button,
+	buttonVariants,
+	type ButtonProps,
+	type ButtonSize,
+	type ButtonVariant,
+};

web/src/lib/components/ui/card/card-action.svelte

@@ -0,0 +1,23 @@
+<script lang="ts">
+	import { cn, type WithElementRef } from "$lib/utils.js";
+	import type { HTMLAttributes } from "svelte/elements";
+
+	let {
+		ref = $bindable(null),
+		class: className,
+		children,
+		...restProps
+	}: WithElementRef<HTMLAttributes<HTMLDivElement>> = $props();
+</script>
+
+<div
+	bind:this={ref}
+	data-slot="card-action"
+	class={cn(
+		"cn-card-action col-start-2 row-span-2 row-start-1 self-start justify-self-end",
+		className
+	)}
+	{...restProps}
+>
+	{@render children?.()}
+</div>

web/src/lib/components/ui/card/card-content.svelte

@@ -0,0 +1,20 @@
+<script lang="ts">
+	import type { HTMLAttributes } from "svelte/elements";
+	import { cn, type WithElementRef } from "$lib/utils.js";
+
+	let {
+		ref = $bindable(null),
+		class: className,
+		children,
+		...restProps
+	}: WithElementRef<HTMLAttributes<HTMLDivElement>> = $props();
+</script>
+
+<div
+	bind:this={ref}
+	data-slot="card-content"
+	class={cn("px-6 group-data-[size=sm]/card:px-4", className)}
+	{...restProps}
+>
+	{@render children?.()}
+</div>

web/src/lib/components/ui/card/card-description.svelte

@@ -0,0 +1,20 @@
+<script lang="ts">
+	import type { HTMLAttributes } from "svelte/elements";
+	import { cn, type WithElementRef } from "$lib/utils.js";
+
+	let {
+		ref = $bindable(null),
+		class: className,
+		children,
+		...restProps
+	}: WithElementRef<HTMLAttributes<HTMLParagraphElement>> = $props();
+</script>
+
+<p
+	bind:this={ref}
+	data-slot="card-description"
+	class={cn("text-muted-foreground text-sm", className)}
+	{...restProps}
+>
+	{@render children?.()}
+</p>

web/src/lib/components/ui/card/card-footer.svelte

@@ -0,0 +1,20 @@
+<script lang="ts">
+	import { cn, type WithElementRef } from "$lib/utils.js";
+	import type { HTMLAttributes } from "svelte/elements";
+
+	let {
+		ref = $bindable(null),
+		class: className,
+		children,
+		...restProps
+	}: WithElementRef<HTMLAttributes<HTMLDivElement>> = $props();
+</script>
+
+<div
+	bind:this={ref}
+	data-slot="card-footer"
+	class={cn("rounded-b-xl px-6 group-data-[size=sm]/card:px-4 [.border-t]:pt-6 group-data-[size=sm]/card:[.border-t]:pt-4 flex items-center", className)}
+	{...restProps}
+>
+	{@render children?.()}
+</div>

web/src/lib/components/ui/card/card-header.svelte

@@ -0,0 +1,23 @@
+<script lang="ts">
+	import { cn, type WithElementRef } from "$lib/utils.js";
+	import type { HTMLAttributes } from "svelte/elements";
+
+	let {
+		ref = $bindable(null),
+		class: className,
+		children,
+		...restProps
+	}: WithElementRef<HTMLAttributes<HTMLDivElement>> = $props();
+</script>
+
+<div
+	bind:this={ref}
+	data-slot="card-header"
+	class={cn(
+		"gap-1 rounded-t-xl px-6 group-data-[size=sm]/card:px-4 [.border-b]:pb-6 group-data-[size=sm]/card:[.border-b]:pb-4 group/card-header @container/card-header grid auto-rows-min items-start has-data-[slot=card-action]:grid-cols-[1fr_auto] has-data-[slot=card-description]:grid-rows-[auto_auto]",
+		className
+	)}
+	{...restProps}
+>
+	{@render children?.()}
+</div>

web/src/lib/components/ui/card/card-title.svelte

@@ -0,0 +1,20 @@
+<script lang="ts">
+	import type { HTMLAttributes } from "svelte/elements";
+	import { cn, type WithElementRef } from "$lib/utils.js";
+
+	let {
+		ref = $bindable(null),
+		class: className,
+		children,
+		...restProps
+	}: WithElementRef<HTMLAttributes<HTMLDivElement>> = $props();
+</script>
+
+<div
+	bind:this={ref}
+	data-slot="card-title"
+	class={cn("text-base leading-normal font-medium group-data-[size=sm]/card:text-sm", className)}
+	{...restProps}
+>
+	{@render children?.()}
+</div>

web/src/lib/components/ui/card/card.svelte

@@ -0,0 +1,22 @@
+<script lang="ts">
+	import type { HTMLAttributes } from "svelte/elements";
+	import { cn, type WithElementRef } from "$lib/utils.js";
+
+	let {
+		ref = $bindable(null),
+		class: className,
+		children,
+		size = "default",
+		...restProps
+	}: WithElementRef<HTMLAttributes<HTMLDivElement>> & { size?: "default" | "sm" } = $props();
+</script>
+
+<div
+	bind:this={ref}
+	data-slot="card"
+	data-size={size}
+	class={cn("ring-foreground/10 bg-card text-card-foreground gap-6 overflow-hidden rounded-xl py-6 text-sm shadow-xs ring-1 has-[>img:first-child]:pt-0 data-[size=sm]:gap-4 data-[size=sm]:py-4 *:[img:first-child]:rounded-t-xl *:[img:last-child]:rounded-b-xl group/card flex flex-col", className)}
+	{...restProps}
+>
+	{@render children?.()}
+</div>

web/src/lib/components/ui/card/index.ts

@@ -0,0 +1,25 @@
+import Root from "./card.svelte";
+import Content from "./card-content.svelte";
+import Description from "./card-description.svelte";
+import Footer from "./card-footer.svelte";
+import Header from "./card-header.svelte";
+import Title from "./card-title.svelte";
+import Action from "./card-action.svelte";
+
+export {
+	Root,
+	Content,
+	Description,
+	Footer,
+	Header,
+	Title,
+	Action,
+	//
+	Root as Card,
+	Content as CardContent,
+	Description as CardDescription,
+	Footer as CardFooter,
+	Header as CardHeader,
+	Title as CardTitle,
+	Action as CardAction,
+};

web/src/lib/components/ui/collapsible/collapsible-content.svelte

@@ -0,0 +1,7 @@
+<script lang="ts">
+	import { Collapsible as CollapsiblePrimitive } from "bits-ui";
+
+	let { ref = $bindable(null), ...restProps }: CollapsiblePrimitive.ContentProps = $props();
+</script>
+
+<CollapsiblePrimitive.Content bind:ref data-slot="collapsible-content" {...restProps} />

web/src/lib/components/ui/collapsible/collapsible-trigger.svelte

@@ -0,0 +1,7 @@
+<script lang="ts">
+	import { Collapsible as CollapsiblePrimitive } from "bits-ui";
+
+	let { ref = $bindable(null), ...restProps }: CollapsiblePrimitive.TriggerProps = $props();
+</script>
+
+<CollapsiblePrimitive.Trigger bind:ref data-slot="collapsible-trigger" {...restProps} />

web/src/lib/components/ui/collapsible/collapsible.svelte

@@ -0,0 +1,11 @@
+<script lang="ts">
+	import { Collapsible as CollapsiblePrimitive } from "bits-ui";
+
+	let {
+		ref = $bindable(null),
+		open = $bindable(false),
+		...restProps
+	}: CollapsiblePrimitive.RootProps = $props();
+</script>
+
+<CollapsiblePrimitive.Root bind:ref bind:open data-slot="collapsible" {...restProps} />

web/src/lib/components/ui/collapsible/index.ts

@@ -0,0 +1,13 @@
+import Root from "./collapsible.svelte";
+import Trigger from "./collapsible-trigger.svelte";
+import Content from "./collapsible-content.svelte";
+
+export {
+	Root,
+	Content,
+	Trigger,
+	//
+	Root as Collapsible,
+	Content as CollapsibleContent,
+	Trigger as CollapsibleTrigger,
+};

web/src/lib/components/ui/dialog/dialog-close.svelte

@@ -0,0 +1,11 @@
+<script lang="ts">
+	import { Dialog as DialogPrimitive } from "bits-ui";
+
+	let {
+		ref = $bindable(null),
+		type = "button",
+		...restProps
+	}: DialogPrimitive.CloseProps = $props();
+</script>
+
+<DialogPrimitive.Close bind:ref data-slot="dialog-close" {type} {...restProps} />

web/src/lib/components/ui/dialog/dialog-content.svelte

@@ -0,0 +1,48 @@
+<script lang="ts">
+	import { Dialog as DialogPrimitive } from "bits-ui";
+	import DialogPortal from "./dialog-portal.svelte";
+	import type { Snippet } from "svelte";
+	import * as Dialog from "./index.js";
+	import { cn, type WithoutChildrenOrChild } from "$lib/utils.js";
+	import type { ComponentProps } from "svelte";
+	import { Button } from "$lib/components/ui/button/index.js";
+	import XIcon from '@lucide/svelte/icons/x';
+
+	let {
+		ref = $bindable(null),
+		class: className,
+		portalProps,
+		children,
+		showCloseButton = true,
+		...restProps
+	}: WithoutChildrenOrChild<DialogPrimitive.ContentProps> & {
+		portalProps?: WithoutChildrenOrChild<ComponentProps<typeof DialogPortal>>;
+		children: Snippet;
+		showCloseButton?: boolean;
+	} = $props();
+</script>
+
+<DialogPortal {...portalProps}>
+	<Dialog.Overlay />
+	<DialogPrimitive.Content
+		bind:ref
+		data-slot="dialog-content"
+		class={cn(
+			"bg-popover text-popover-foreground data-open:animate-in data-closed:animate-out data-closed:fade-out-0 data-open:fade-in-0 data-closed:zoom-out-95 data-open:zoom-in-95 ring-foreground/10 grid max-w-[calc(100%-2rem)] gap-6 rounded-xl p-6 text-sm ring-1 duration-100 sm:max-w-md fixed top-1/2 left-1/2 z-50 w-full -translate-x-1/2 -translate-y-1/2 outline-none",
+			className
+		)}
+		{...restProps}
+	>
+		{@render children?.()}
+		{#if showCloseButton}
+			<DialogPrimitive.Close data-slot="dialog-close">
+				{#snippet child({ props })}
+					<Button variant="ghost" class="absolute top-4 right-4" size="icon-sm" {...props}>
+						<XIcon  />
+						<span class="sr-only">Close</span>
+					</Button>
+				{/snippet}
+			</DialogPrimitive.Close>
+		{/if}
+	</DialogPrimitive.Content>
+</DialogPortal>

web/src/lib/components/ui/dialog/dialog-description.svelte

@@ -0,0 +1,17 @@
+<script lang="ts">
+	import { Dialog as DialogPrimitive } from "bits-ui";
+	import { cn } from "$lib/utils.js";
+
+	let {
+		ref = $bindable(null),
+		class: className,
+		...restProps
+	}: DialogPrimitive.DescriptionProps = $props();
+</script>
+
+<DialogPrimitive.Description
+	bind:ref
+	data-slot="dialog-description"
+	class={cn("text-muted-foreground *:[a]:hover:text-foreground text-sm *:[a]:underline *:[a]:underline-offset-3", className)}
+	{...restProps}
+/>

web/src/lib/components/ui/dialog/dialog-footer.svelte

@@ -0,0 +1,32 @@
+<script lang="ts">
+	import { cn, type WithElementRef } from "$lib/utils.js";
+	import type { HTMLAttributes } from "svelte/elements";
+	import { Dialog as DialogPrimitive } from "bits-ui";
+	import { Button } from "$lib/components/ui/button/index.js";
+
+	let {
+		ref = $bindable(null),
+		class: className,
+		children,
+		showCloseButton = false,
+		...restProps
+	}: WithElementRef<HTMLAttributes<HTMLDivElement>> & {
+		showCloseButton?: boolean;
+	} = $props();
+</script>
+
+<div
+	bind:this={ref}
+	data-slot="dialog-footer"
+	class={cn("gap-2 flex flex-col-reverse gap-2 sm:flex-row sm:justify-end", className)}
+	{...restProps}
+>
+	{@render children?.()}
+	{#if showCloseButton}
+		<DialogPrimitive.Close>
+			{#snippet child({ props })}
+				<Button variant="outline" {...props}>Close</Button>
+			{/snippet}
+		</DialogPrimitive.Close>
+	{/if}
+</div>

web/src/lib/components/ui/dialog/dialog-header.svelte

@@ -0,0 +1,20 @@
+<script lang="ts">
+	import type { HTMLAttributes } from "svelte/elements";
+	import { cn, type WithElementRef } from "$lib/utils.js";
+
+	let {
+		ref = $bindable(null),
+		class: className,
+		children,
+		...restProps
+	}: WithElementRef<HTMLAttributes<HTMLDivElement>> = $props();
+</script>
+
+<div
+	bind:this={ref}
+	data-slot="dialog-header"
+	class={cn("gap-2 flex flex-col", className)}
+	{...restProps}
+>
+	{@render children?.()}
+</div>

web/src/lib/components/ui/dialog/dialog-overlay.svelte

@@ -0,0 +1,17 @@
+<script lang="ts">
+	import { Dialog as DialogPrimitive } from "bits-ui";
+	import { cn } from "$lib/utils.js";
+
+	let {
+		ref = $bindable(null),
+		class: className,
+		...restProps
+	}: DialogPrimitive.OverlayProps = $props();
+</script>
+
+<DialogPrimitive.Overlay
+	bind:ref
+	data-slot="dialog-overlay"
+	class={cn("data-open:animate-in data-closed:animate-out data-closed:fade-out-0 data-open:fade-in-0 bg-black/10 duration-100 supports-backdrop-filter:backdrop-blur-xs fixed inset-0 isolate z-50", className)}
+	{...restProps}
+/>

web/src/lib/components/ui/dialog/dialog-portal.svelte

@@ -0,0 +1,7 @@
+<script lang="ts">
+	import { Dialog as DialogPrimitive } from "bits-ui";
+
+	let { ...restProps }: DialogPrimitive.PortalProps = $props();
+</script>
+
+<DialogPrimitive.Portal {...restProps} />

web/src/lib/components/ui/dialog/dialog-title.svelte

@@ -0,0 +1,17 @@
+<script lang="ts">
+	import { Dialog as DialogPrimitive } from "bits-ui";
+	import { cn } from "$lib/utils.js";
+
+	let {
+		ref = $bindable(null),
+		class: className,
+		...restProps
+	}: DialogPrimitive.TitleProps = $props();
+</script>
+
+<DialogPrimitive.Title
+	bind:ref
+	data-slot="dialog-title"
+	class={cn("leading-none font-medium", className)}
+	{...restProps}
+/>

web/src/lib/components/ui/dialog/dialog-trigger.svelte

@@ -0,0 +1,11 @@
+<script lang="ts">
+	import { Dialog as DialogPrimitive } from "bits-ui";
+
+	let {
+		ref = $bindable(null),
+		type = "button",
+		...restProps
+	}: DialogPrimitive.TriggerProps = $props();
+</script>
+
+<DialogPrimitive.Trigger bind:ref data-slot="dialog-trigger" {type} {...restProps} />

web/src/lib/components/ui/dialog/dialog.svelte

@@ -0,0 +1,7 @@
+<script lang="ts">
+	import { Dialog as DialogPrimitive } from "bits-ui";
+
+	let { open = $bindable(false), ...restProps }: DialogPrimitive.RootProps = $props();
+</script>
+
+<DialogPrimitive.Root bind:open {...restProps} />

web/src/lib/components/ui/dialog/index.ts

@@ -0,0 +1,34 @@
+import Root from "./dialog.svelte";
+import Portal from "./dialog-portal.svelte";
+import Title from "./dialog-title.svelte";
+import Footer from "./dialog-footer.svelte";
+import Header from "./dialog-header.svelte";
+import Overlay from "./dialog-overlay.svelte";
+import Content from "./dialog-content.svelte";
+import Description from "./dialog-description.svelte";
+import Trigger from "./dialog-trigger.svelte";
+import Close from "./dialog-close.svelte";
+
+export {
+	Root,
+	Title,
+	Portal,
+	Footer,
+	Header,
+	Trigger,
+	Overlay,
+	Content,
+	Description,
+	Close,
+	//
+	Root as Dialog,
+	Title as DialogTitle,
+	Portal as DialogPortal,
+	Footer as DialogFooter,
+	Header as DialogHeader,
+	Trigger as DialogTrigger,
+	Overlay as DialogOverlay,
+	Content as DialogContent,
+	Description as DialogDescription,
+	Close as DialogClose,
+};

web/src/lib/components/ui/dropdown-menu/dropdown-menu-checkbox-group.svelte

@@ -0,0 +1,16 @@
+<script lang="ts">
+	import { DropdownMenu as DropdownMenuPrimitive } from "bits-ui";
+
+	let {
+		ref = $bindable(null),
+		value = $bindable([]),
+		...restProps
+	}: DropdownMenuPrimitive.CheckboxGroupProps = $props();
+</script>
+
+<DropdownMenuPrimitive.CheckboxGroup
+	bind:ref
+	bind:value
+	data-slot="dropdown-menu-checkbox-group"
+	{...restProps}
+/>

web/src/lib/components/ui/dropdown-menu/dropdown-menu-checkbox-item.svelte

@@ -0,0 +1,44 @@
+<script lang="ts">
+	import { DropdownMenu as DropdownMenuPrimitive } from "bits-ui";
+	import MinusIcon from '@lucide/svelte/icons/minus';
+	import CheckIcon from '@lucide/svelte/icons/check';
+	import { cn, type WithoutChildrenOrChild } from "$lib/utils.js";
+	import type { Snippet } from "svelte";
+
+	let {
+		ref = $bindable(null),
+		checked = $bindable(false),
+		indeterminate = $bindable(false),
+		class: className,
+		children: childrenProp,
+		...restProps
+	}: WithoutChildrenOrChild<DropdownMenuPrimitive.CheckboxItemProps> & {
+		children?: Snippet;
+	} = $props();
+</script>
+
+<DropdownMenuPrimitive.CheckboxItem
+	bind:ref
+	bind:checked
+	bind:indeterminate
+	data-slot="dropdown-menu-checkbox-item"
+	class={cn(
+		"focus:bg-accent focus:text-accent-foreground focus:**:text-accent-foreground gap-2 rounded-sm py-1.5 pr-8 pl-2 text-sm data-inset:pl-8 [&_svg:not([class*='size-'])]:size-4 relative flex cursor-default items-center outline-hidden select-none data-[disabled]:pointer-events-none data-[disabled]:opacity-50 [&_svg]:pointer-events-none [&_svg]:shrink-0",
+		className
+	)}
+	{...restProps}
+>
+	{#snippet children({ checked, indeterminate })}
+		<span
+			class="absolute right-2 flex items-center justify-center pointer-events-none"
+			data-slot="dropdown-menu-checkbox-item-indicator"
+		>
+			{#if indeterminate}
+				<MinusIcon  />
+			{:else if checked}
+				<CheckIcon  />
+			{/if}
+		</span>
+		{@render childrenProp?.()}
+	{/snippet}
+</DropdownMenuPrimitive.CheckboxItem>

web/src/lib/components/ui/dropdown-menu/dropdown-menu-content.svelte

@@ -0,0 +1,31 @@
+<script lang="ts">
+	import { cn, type WithoutChildrenOrChild } from "$lib/utils.js";
+	import DropdownMenuPortal from "./dropdown-menu-portal.svelte";
+	import { DropdownMenu as DropdownMenuPrimitive } from "bits-ui";
+	import type { ComponentProps } from "svelte";
+
+	let {
+		ref = $bindable(null),
+		sideOffset = 4,
+		align = "start",
+		portalProps,
+		class: className,
+		...restProps
+	}: DropdownMenuPrimitive.ContentProps & {
+		portalProps?: WithoutChildrenOrChild<ComponentProps<typeof DropdownMenuPortal>>;
+	} = $props();
+</script>
+
+<DropdownMenuPortal {...portalProps}>
+	<DropdownMenuPrimitive.Content
+		bind:ref
+		data-slot="dropdown-menu-content"
+		{sideOffset}
+		{align}
+		class={cn(
+			"data-open:animate-in data-closed:animate-out data-closed:fade-out-0 data-open:fade-in-0 data-closed:zoom-out-95 data-open:zoom-in-95 data-[side=bottom]:slide-in-from-top-2 data-[side=left]:slide-in-from-right-2 data-[side=right]:slide-in-from-left-2 data-[side=top]:slide-in-from-bottom-2 ring-foreground/10 bg-popover text-popover-foreground min-w-32 rounded-md p-1 shadow-md ring-1 duration-100 data-[side=inline-start]:slide-in-from-right-2 data-[side=inline-end]:slide-in-from-left-2 z-50 w-(--bits-dropdown-menu-anchor-width) overflow-x-hidden overflow-y-auto outline-none data-closed:overflow-hidden",
+			className
+		)}
+		{...restProps}
+	/>
+</DropdownMenuPortal>

web/src/lib/components/ui/dropdown-menu/dropdown-menu-group-heading.svelte

@@ -0,0 +1,22 @@
+<script lang="ts">
+	import { DropdownMenu as DropdownMenuPrimitive } from "bits-ui";
+	import { cn } from "$lib/utils.js";
+	import type { ComponentProps } from "svelte";
+
+	let {
+		ref = $bindable(null),
+		class: className,
+		inset,
+		...restProps
+	}: ComponentProps<typeof DropdownMenuPrimitive.GroupHeading> & {
+		inset?: boolean;
+	} = $props();
+</script>
+
+<DropdownMenuPrimitive.GroupHeading
+	bind:ref
+	data-slot="dropdown-menu-group-heading"
+	data-inset={inset}
+	class={cn("px-2 py-1.5 text-sm font-semibold data-[inset]:ps-8", className)}
+	{...restProps}
+/>

web/src/lib/components/ui/dropdown-menu/dropdown-menu-group.svelte

@@ -0,0 +1,7 @@
+<script lang="ts">
+	import { DropdownMenu as DropdownMenuPrimitive } from "bits-ui";
+
+	let { ref = $bindable(null), ...restProps }: DropdownMenuPrimitive.GroupProps = $props();
+</script>
+
+<DropdownMenuPrimitive.Group bind:ref data-slot="dropdown-menu-group" {...restProps} />

web/src/lib/components/ui/dropdown-menu/dropdown-menu-item.svelte

@@ -0,0 +1,27 @@
+<script lang="ts">
+	import { cn } from "$lib/utils.js";
+	import { DropdownMenu as DropdownMenuPrimitive } from "bits-ui";
+
+	let {
+		ref = $bindable(null),
+		class: className,
+		inset,
+		variant = "default",
+		...restProps
+	}: DropdownMenuPrimitive.ItemProps & {
+		inset?: boolean;
+		variant?: "default" | "destructive";
+	} = $props();
+</script>
+
+<DropdownMenuPrimitive.Item
+	bind:ref
+	data-slot="dropdown-menu-item"
+	data-inset={inset}
+	data-variant={variant}
+	class={cn(
+		"focus:bg-accent focus:text-accent-foreground data-[variant=destructive]:text-destructive data-[variant=destructive]:focus:bg-destructive/10 dark:data-[variant=destructive]:focus:bg-destructive/20 data-[variant=destructive]:focus:text-destructive data-[variant=destructive]:*:[svg]:text-destructive not-data-[variant=destructive]:focus:**:text-accent-foreground gap-2 rounded-sm px-2 py-1.5 text-sm data-inset:pl-8 [&_svg:not([class*='size-'])]:size-4 group/dropdown-menu-item relative flex cursor-default items-center outline-hidden select-none data-disabled:pointer-events-none data-disabled:opacity-50 data-[inset]:pl-8 [&_svg]:pointer-events-none [&_svg]:shrink-0",
+		className
+	)}
+	{...restProps}
+/>

web/src/lib/components/ui/dropdown-menu/dropdown-menu-label.svelte

@@ -0,0 +1,24 @@
+<script lang="ts">
+	import { cn, type WithElementRef } from "$lib/utils.js";
+	import type { HTMLAttributes } from "svelte/elements";
+
+	let {
+		ref = $bindable(null),
+		class: className,
+		inset,
+		children,
+		...restProps
+	}: WithElementRef<HTMLAttributes<HTMLDivElement>> & {
+		inset?: boolean;
+	} = $props();
+</script>
+
+<div
+	bind:this={ref}
+	data-slot="dropdown-menu-label"
+	data-inset={inset}
+	class={cn("text-muted-foreground px-2 py-1.5 text-xs font-medium data-inset:pl-8 data-[inset]:pl-8", className)}
+	{...restProps}
+>
+	{@render children?.()}
+</div>

web/src/lib/components/ui/dropdown-menu/dropdown-menu-portal.svelte

@@ -0,0 +1,7 @@
+<script lang="ts">
+	import { DropdownMenu as DropdownMenuPrimitive } from "bits-ui";
+
+	let { ...restProps }: DropdownMenuPrimitive.PortalProps = $props();
+</script>
+
+<DropdownMenuPrimitive.Portal {...restProps} />

web/src/lib/components/ui/dropdown-menu/dropdown-menu-radio-group.svelte

@@ -0,0 +1,16 @@
+<script lang="ts">
+	import { DropdownMenu as DropdownMenuPrimitive } from "bits-ui";
+
+	let {
+		ref = $bindable(null),
+		value = $bindable(),
+		...restProps
+	}: DropdownMenuPrimitive.RadioGroupProps = $props();
+</script>
+
+<DropdownMenuPrimitive.RadioGroup
+	bind:ref
+	bind:value
+	data-slot="dropdown-menu-radio-group"
+	{...restProps}
+/>