fix: null guard on assignees in orchestrator dispatch

Resolves #355 #356

Components:
- orchestrator.py: Full sovereign orchestrator with 6 subsystems
  1. Backlog reader (fetches from timmy-config, the-nexus, timmy-home)
  2. Priority scorer (0-100 based on severity, age, assignment state)
  3. Agent roster (groq/ezra/bezalel with health checks)
  4. Dispatcher (matches issues to agents by type/strength)
  5. Consolidated report (terminal + Telegram)
  6. Main loop (--once, --daemon, --dry-run)
- orchestrate.sh: Shell wrapper with env setup

Dry-run tested: 348 issues scanned, 3 agents detected UP.
stdlib only, no pip dependencies.

.gitignore

@@ -1,9 +1,8 @@
-# Secrets
+*.pyc
-*.token
+*.pyo
-*.key
+*.egg-info/
-*.secret
+dist/
-
+build/
-# Local state
 *.db
 *.db-wal
 *.db-shm

bin/agent-loop.sh

@@ -0,0 +1,273 @@
+#!/usr/bin/env bash
+# agent-loop.sh — Universal agent dev loop with Genchi Genbutsu verification
+#
+# Usage: agent-loop.sh <agent-name> [num-workers]
+#   agent-loop.sh claude 2
+#   agent-loop.sh gemini 1
+#
+# Dispatches via agent-dispatch.sh, then verifies with genchi-genbutsu.sh.
+
+set -uo pipefail
+
+AGENT="${1:?Usage: agent-loop.sh <agent-name> [num-workers]}"
+NUM_WORKERS="${2:-1}"
+
+# Resolve agent tool and model from config or fallback
+case "$AGENT" in
+  claude) TOOL="claude"; MODEL="sonnet" ;;
+  gemini) TOOL="gemini"; MODEL="gemini-2.5-pro-preview-05-06" ;;
+  grok)   TOOL="opencode"; MODEL="grok-3-fast" ;;
+  *)      TOOL="$AGENT"; MODEL="" ;;
+esac
+
+# === CONFIG ===
+GITEA_URL="${GITEA_URL:-https://forge.alexanderwhitestone.com}"
+GITEA_TOKEN="${GITEA_TOKEN:-}"
+WORKTREE_BASE="$HOME/worktrees"
+LOG_DIR="$HOME/.hermes/logs"
+LOCK_DIR="$LOG_DIR/${AGENT}-locks"
+SKIP_FILE="$LOG_DIR/${AGENT}-skip-list.json"
+ACTIVE_FILE="$LOG_DIR/${AGENT}-active.json"
+TIMEOUT=600
+COOLDOWN=30
+
+mkdir -p "$LOG_DIR" "$WORKTREE_BASE" "$LOCK_DIR"
+[ -f "$SKIP_FILE" ] || echo '{}' > "$SKIP_FILE"
+echo '{}' > "$ACTIVE_FILE"
+
+# === SHARED FUNCTIONS ===
+log() {
+  echo "[$(date '+%Y-%m-%d %H:%M:%S')] ${AGENT}: $*" >> "$LOG_DIR/${AGENT}-loop.log"
+}
+
+lock_issue() {
+  local key="$1"
+  mkdir "$LOCK_DIR/$key.lock" 2>/dev/null && echo $$ > "$LOCK_DIR/$key.lock/pid"
+}
+
+unlock_issue() {
+  rm -rf "$LOCK_DIR/$1.lock" 2>/dev/null
+}
+
+mark_skip() {
+  local issue_num="$1" reason="$2"
+  python3 -c "
+import json, time, fcntl
+with open('${SKIP_FILE}', 'r+') as f:
+    fcntl.flock(f, fcntl.LOCK_EX)
+    try: skips = json.load(f)
+    except: skips = {}
+    failures = skips.get(str($issue_num), {}).get('failures', 0) + 1
+    skip_hours = 6 if failures >= 3 else 1
+    skips[str($issue_num)] = {'until': time.time() + (skip_hours * 3600), 'reason': '$reason', 'failures': failures}
+    f.seek(0); f.truncate()
+    json.dump(skips, f, indent=2)
+" 2>/dev/null
+}
+
+get_next_issue() {
+  python3 -c "
+import json, sys, time, urllib.request, os
+token = '${GITEA_TOKEN}'
+base = '${GITEA_URL}'
+repos = ['Timmy_Foundation/the-nexus', 'Timmy_Foundation/timmy-config', 'Timmy_Foundation/hermes-agent']
+try:
+    with open('${SKIP_FILE}') as f: skips = json.load(f)
+except: skips = {}
+try:
+    with open('${ACTIVE_FILE}') as f: active = json.load(f); active_issues = {v['issue'] for v in active.values()}
+except: active_issues = set()
+all_issues = []
+for repo in repos:
+    url = f'{base}/api/v1/repos/{repo}/issues?state=open&type=issues&limit=50&sort=created'
+    req = urllib.request.Request(url, headers={'Authorization': f'token {token}'})
+    try:
+        resp = urllib.request.urlopen(req, timeout=10)
+        issues = json.loads(resp.read())
+        for i in issues: i['_repo'] = repo
+        all_issues.extend(issues)
+    except: continue
+for i in sorted(all_issues, key=lambda x: x['title'].lower()):
+    assignees = [a['login'] for a in (i.get('assignees') or [])]
+    if assignees and '${AGENT}' not in assignees: continue
+    num_str = str(i['number'])
+    if num_str in active_issues: continue
+    if skips.get(num_str, {}).get('until', 0) > time.time(): continue
+    lock = '${LOCK_DIR}/' + i['_repo'].replace('/', '-') + '-' + num_str + '.lock'
+    if os.path.isdir(lock): continue
+    owner, name = i['_repo'].split('/')
+    print(json.dumps({'number': i['number'], 'title': i['title'], 'repo_owner': owner, 'repo_name': name, 'repo': i['_repo']}))
+    sys.exit(0)
+print('null')
+" 2>/dev/null
+}
+
+# === WORKER FUNCTION ===
+run_worker() {
+  local worker_id="$1"
+  log "WORKER-${worker_id}: Started"
+
+  while true; do
+    issue_json=$(get_next_issue)
+    if [ "$issue_json" = "null" ] || [ -z "$issue_json" ]; then
+      sleep 30
+      continue
+    fi
+
+    issue_num=$(echo "$issue_json" | python3 -c "import sys,json; print(json.load(sys.stdin)['number'])")
+    issue_title=$(echo "$issue_json" | python3 -c "import sys,json; print(json.load(sys.stdin)['title'])")
+    repo_owner=$(echo "$issue_json" | python3 -c "import sys,json; print(json.load(sys.stdin)['repo_owner'])")
+    repo_name=$(echo "$issue_json" | python3 -c "import sys,json; print(json.load(sys.stdin)['repo_name'])")
+    issue_key="${repo_owner}-${repo_name}-${issue_num}"
+    branch="${AGENT}/issue-${issue_num}"
+    worktree="${WORKTREE_BASE}/${AGENT}-w${worker_id}-${issue_num}"
+
+    if ! lock_issue "$issue_key"; then
+      sleep 5
+      continue
+    fi
+
+    log "WORKER-${worker_id}: === ISSUE #${issue_num}: ${issue_title} (${repo_owner}/${repo_name}) ==="
+
+    # Clone / checkout
+    rm -rf "$worktree" 2>/dev/null
+    CLONE_URL="http://${AGENT}:${GITEA_TOKEN}@143.198.27.163:3000/${repo_owner}/${repo_name}.git"
+    if git ls-remote --heads "$CLONE_URL" "$branch" 2>/dev/null | grep -q "$branch"; then
+      git clone --depth=50 -b "$branch" "$CLONE_URL" "$worktree" >/dev/null 2>&1
+    else
+      git clone --depth=1 -b main "$CLONE_URL" "$worktree" >/dev/null 2>&1
+      cd "$worktree" && git checkout -b "$branch" >/dev/null 2>&1
+    fi
+    cd "$worktree"
+
+    # Generate prompt
+    prompt=$(bash "$(dirname "$0")/agent-dispatch.sh" "$AGENT" "$issue_num" "${repo_owner}/${repo_name}")
+
+    CYCLE_START=$(date +%s)
+    set +e
+    if [ "$TOOL" = "claude" ]; then
+      env -u CLAUDECODE gtimeout "$TIMEOUT" claude \
+        --print --model "$MODEL" --dangerously-skip-permissions \
+        -p "$prompt" </dev/null >> "$LOG_DIR/${AGENT}-${issue_num}.log" 2>&1
+    elif [ "$TOOL" = "gemini" ]; then
+      gtimeout "$TIMEOUT" gemini -p "$prompt" --yolo \
+        </dev/null >> "$LOG_DIR/${AGENT}-${issue_num}.log" 2>&1
+    else
+      gtimeout "$TIMEOUT" "$TOOL" "$prompt" \
+        </dev/null >> "$LOG_DIR/${AGENT}-${issue_num}.log" 2>&1
+    fi
+    exit_code=$?
+    set -e
+    CYCLE_END=$(date +%s)
+    CYCLE_DURATION=$((CYCLE_END - CYCLE_START))
+
+    # Salvage
+    cd "$worktree" 2>/dev/null || true
+    DIRTY=$(git status --porcelain 2>/dev/null | wc -l | tr -d ' ')
+    if [ "${DIRTY:-0}" -gt 0 ]; then
+      git add -A 2>/dev/null
+      git commit -m "WIP: ${AGENT} progress on #${issue_num}
+
+Automated salvage commit — agent session ended (exit $exit_code)." 2>/dev/null || true
+    fi
+
+    UNPUSHED=$(git log --oneline "origin/main..HEAD" 2>/dev/null | wc -l | tr -d ' ')
+    if [ "${UNPUSHED:-0}" -gt 0 ]; then
+      git push -u origin "$branch" 2>/dev/null && \
+        log "WORKER-${worker_id}: Pushed $UNPUSHED commit(s) on $branch" || \
+        log "WORKER-${worker_id}: Push failed for $branch"
+    fi
+
+    # Create PR if needed
+    pr_num=$(curl -sf "${GITEA_URL}/api/v1/repos/${repo_owner}/${repo_name}/pulls?state=open&head=${repo_owner}:${branch}&limit=1" \
+      -H "Authorization: token ${GITEA_TOKEN}" | python3 -c "
+import sys,json
+prs = json.load(sys.stdin)
+print(prs[0]['number'] if prs else '')
+" 2>/dev/null)
+
+    if [ -z "$pr_num" ] && [ "${UNPUSHED:-0}" -gt 0 ]; then
+      pr_num=$(curl -sf -X POST "${GITEA_URL}/api/v1/repos/${repo_owner}/${repo_name}/pulls" \
+        -H "Authorization: token ${GITEA_TOKEN}" \
+        -H "Content-Type: application/json" \
+        -d "$(python3 -c "
+import json
+print(json.dumps({
+    'title': '${AGENT}: Issue #${issue_num}',
+    'head': '${branch}',
+    'base': 'main',
+    'body': 'Automated PR for issue #${issue_num}.\nExit code: ${exit_code}'
+}))
+")" | python3 -c "import sys,json; print(json.load(sys.stdin).get('number',''))" 2>/dev/null)
+      [ -n "$pr_num" ] && log "WORKER-${worker_id}: Created PR #${pr_num} for issue #${issue_num}"
+    fi
+
+    # ── Genchi Genbutsu: verify world state before declaring success ──
+    VERIFIED="false"
+    if [ "$exit_code" -eq 0 ]; then
+      log "WORKER-${worker_id}: SUCCESS #${issue_num} — running genchi-genbutsu"
+      SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+      if verify_result=$("$SCRIPT_DIR/genchi-genbutsu.sh" "$repo_owner" "$repo_name" "$issue_num" "$branch" "$AGENT" 2>/dev/null); then
+        VERIFIED="true"
+        log "WORKER-${worker_id}: VERIFIED #${issue_num}"
+        if [ -n "$pr_num" ]; then
+          curl -sf -X POST "${GITEA_URL}/api/v1/repos/${repo_owner}/${repo_name}/pulls/${pr_num}/merge" \
+            -H "Authorization: token ${GITEA_TOKEN}" \
+            -H "Content-Type: application/json" \
+            -d '{"Do": "squash"}' >/dev/null 2>&1 || true
+          curl -sf -X PATCH "${GITEA_URL}/api/v1/repos/${repo_owner}/${repo_name}/issues/${issue_num}" \
+            -H "Authorization: token ${GITEA_TOKEN}" \
+            -H "Content-Type: application/json" \
+            -d '{"state": "closed"}' >/dev/null 2>&1 || true
+          log "WORKER-${worker_id}: PR #${pr_num} merged, issue #${issue_num} closed"
+        fi
+        consecutive_failures=0
+      else
+        verify_details=$(echo "$verify_result" | python3 -c "import sys,json; print(json.load(sys.stdin).get('details','unknown'))" 2>/dev/null || echo "unverified")
+        log "WORKER-${worker_id}: UNVERIFIED #${issue_num} — $verify_details"
+        mark_skip "$issue_num" "unverified" 1
+        consecutive_failures=$((consecutive_failures + 1))
+      fi
+    elif [ "$exit_code" -eq 124 ]; then
+      log "WORKER-${worker_id}: TIMEOUT #${issue_num} (work saved in PR)"
+      consecutive_failures=$((consecutive_failures + 1))
+    else
+      log "WORKER-${worker_id}: FAILED #${issue_num} exit ${exit_code} (work saved in PR)"
+      consecutive_failures=$((consecutive_failures + 1))
+    fi
+
+    # ── METRICS ──
+    python3 -c "
+import json, datetime
+print(json.dumps({
+    'ts': datetime.datetime.utcnow().isoformat() + 'Z',
+    'agent': '${AGENT}',
+    'worker': $worker_id,
+    'issue': $issue_num,
+    'repo': '${repo_owner}/${repo_name}',
+    'outcome': 'success' if $exit_code == 0 else 'timeout' if $exit_code == 124 else 'failed',
+    'exit_code': $exit_code,
+    'duration_s': $CYCLE_DURATION,
+    'pr': '${pr_num:-}',
+    'verified': ${VERIFIED:-false}
+}))
+" >> "$LOG_DIR/${AGENT}-metrics.jsonl" 2>/dev/null
+
+    rm -rf "$worktree" 2>/dev/null
+    unlock_issue "$issue_key"
+    sleep "$COOLDOWN"
+  done
+}
+
+# === MAIN ===
+log "=== Agent Loop Started — ${AGENT} with ${NUM_WORKERS} worker(s) ==="
+
+rm -rf "$LOCK_DIR"/*.lock 2>/dev/null
+
+for i in $(seq 1 "$NUM_WORKERS"); do
+  run_worker "$i" &
+  log "Launched worker $i (PID $!)"
+  sleep 3
+done
+
+wait

bin/claude-loop.sh

@@ -468,24 +468,32 @@ print(json.dumps({
       [ -n "$pr_num" ] && log "WORKER-${worker_id}: Created PR #${pr_num} for issue #${issue_num}"
     fi
 
-    # ── Merge + close on success ──
+    # ── Genchi Genbutsu: verify world state before declaring success ──
+    VERIFIED="false"
     if [ "$exit_code" -eq 0 ]; then
-      log "WORKER-${worker_id}: SUCCESS #${issue_num}"
+      log "WORKER-${worker_id}: SUCCESS #${issue_num} — running genchi-genbutsu"
-
+      SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-      if [ -n "$pr_num" ]; then
+      if verify_result=$("$SCRIPT_DIR/genchi-genbutsu.sh" "$repo_owner" "$repo_name" "$issue_num" "$branch" "claude" 2>/dev/null); then
-        curl -sf -X POST "${GITEA_URL}/api/v1/repos/${repo_owner}/${repo_name}/pulls/${pr_num}/merge" \
+        VERIFIED="true"
-          -H "Authorization: token ${GITEA_TOKEN}" \
+        log "WORKER-${worker_id}: VERIFIED #${issue_num}"
-          -H "Content-Type: application/json" \
+        if [ -n "$pr_num" ]; then
-          -d '{"Do": "squash"}' >/dev/null 2>&1 || true
+          curl -sf -X POST "${GITEA_URL}/api/v1/repos/${repo_owner}/${repo_name}/pulls/${pr_num}/merge" \
-        curl -sf -X PATCH "${GITEA_URL}/api/v1/repos/${repo_owner}/${repo_name}/issues/${issue_num}" \
+            -H "Authorization: token ${GITEA_TOKEN}" \
-          -H "Authorization: token ${GITEA_TOKEN}" \
+            -H "Content-Type: application/json" \
-          -H "Content-Type: application/json" \
+            -d '{"Do": "squash"}' >/dev/null 2>&1 || true
-          -d '{"state": "closed"}' >/dev/null 2>&1 || true
+          curl -sf -X PATCH "${GITEA_URL}/api/v1/repos/${repo_owner}/${repo_name}/issues/${issue_num}" \
-        log "WORKER-${worker_id}: PR #${pr_num} merged, issue #${issue_num} closed"
+            -H "Authorization: token ${GITEA_TOKEN}" \
+            -H "Content-Type: application/json" \
+            -d '{"state": "closed"}' >/dev/null 2>&1 || true
+          log "WORKER-${worker_id}: PR #${pr_num} merged, issue #${issue_num} closed"
+        fi
+        consecutive_failures=0
+      else
+        verify_details=$(echo "$verify_result" | python3 -c "import sys,json; print(json.load(sys.stdin).get('details','unknown'))" 2>/dev/null || echo "unverified")
+        log "WORKER-${worker_id}: UNVERIFIED #${issue_num} — $verify_details"
+        consecutive_failures=$((consecutive_failures + 1))
       fi
 
-      consecutive_failures=0
-
     elif [ "$exit_code" -eq 124 ]; then
       log "WORKER-${worker_id}: TIMEOUT #${issue_num} (work saved in PR)"
       consecutive_failures=$((consecutive_failures + 1))
@@ -522,6 +530,7 @@ print(json.dumps({
 import json, datetime
 print(json.dumps({
     'ts': datetime.datetime.utcnow().isoformat() + 'Z',
+    'agent': 'claude',
     'worker': $worker_id,
     'issue': $issue_num,
     'repo': '${repo_owner}/${repo_name}',
@@ -534,7 +543,8 @@ print(json.dumps({
     'lines_removed': ${LINES_REMOVED:-0},
     'salvaged': ${DIRTY:-0},
     'pr': '${pr_num:-}',
-    'merged': $( [ '$OUTCOME' = 'success' ] && [ -n '${pr_num:-}' ] && echo 'true' || echo 'false' )
+    'merged': $( [ '$OUTCOME' = 'success' ] && [ -n '${pr_num:-}' ] && echo 'true' || echo 'false' ),
+    'verified': ${VERIFIED:-false}
 }))
 " >> "$METRICS_FILE" 2>/dev/null
 

bin/gemini-loop.sh

@@ -521,61 +521,63 @@ print(json.dumps({
       [ -n "$pr_num" ] && log "WORKER-${worker_id}: Created PR #${pr_num} for issue #${issue_num}"
     fi
 
-    # ── Verify finish semantics / classify failures ──
+    # ── Genchi Genbutsu: verify world state before declaring success ──
+    VERIFIED="false"
     if [ "$exit_code" -eq 0 ]; then
-      log "WORKER-${worker_id}: SUCCESS #${issue_num} exited 0 — verifying push + PR + proof"
+      log "WORKER-${worker_id}: SUCCESS #${issue_num} exited 0 — running genchi-genbutsu"
-      if ! remote_branch_exists "$branch"; then
+      SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-        log "WORKER-${worker_id}: BLOCKED #${issue_num} remote branch missing"
+      if verify_result=$("$SCRIPT_DIR/genchi-genbutsu.sh" "$repo_owner" "$repo_name" "$issue_num" "$branch" "gemini" 2>/dev/null); then
-        post_issue_comment "$repo_owner" "$repo_name" "$issue_num" "Loop gate blocked completion: remote branch ${branch} was not found on origin after Gemini exited. Issue remains open for retry."
+        VERIFIED="true"
-        mark_skip "$issue_num" "missing_remote_branch" 1
+        log "WORKER-${worker_id}: VERIFIED #${issue_num}"
-        consecutive_failures=$((consecutive_failures + 1))
+        pr_state=$(get_pr_state "$repo_owner" "$repo_name" "$pr_num")
-      elif [ -z "$pr_num" ]; then
+        if [ "$pr_state" = "open" ]; then
-        log "WORKER-${worker_id}: BLOCKED #${issue_num} no PR found"
+          curl -sf -X POST "${GITEA_URL}/api/v1/repos/${repo_owner}/${repo_name}/pulls/${pr_num}/merge" \
-        post_issue_comment "$repo_owner" "$repo_name" "$issue_num" "Loop gate blocked completion: branch ${branch} exists remotely, but no PR was found. Issue remains open for retry."
+            -H "Authorization: token ${GITEA_TOKEN}" \
-        mark_skip "$issue_num" "missing_pr" 1
+            -H "Content-Type: application/json" \
-        consecutive_failures=$((consecutive_failures + 1))
+            -d '{"Do": "squash"}' >/dev/null 2>&1 || true
+          pr_state=$(get_pr_state "$repo_owner" "$repo_name" "$pr_num")
+        fi
+        if [ "$pr_state" = "merged" ]; then
+          curl -sf -X PATCH "${GITEA_URL}/api/v1/repos/${repo_owner}/${repo_name}/issues/${issue_num}" \
+            -H "Authorization: token ${GITEA_TOKEN}" \
+            -H "Content-Type: application/json" \
+            -d '{"state": "closed"}' >/dev/null 2>&1 || true
+          issue_state=$(get_issue_state "$repo_owner" "$repo_name" "$issue_num")
+          if [ "$issue_state" = "closed" ]; then
+            log "WORKER-${worker_id}: VERIFIED #${issue_num} branch pushed, PR merged, comment present, issue closed"
+            consecutive_failures=0
+          else
+            log "WORKER-${worker_id}: BLOCKED #${issue_num} issue did not close after merge"
+            mark_skip "$issue_num" "issue_close_unverified" 1
+            consecutive_failures=$((consecutive_failures + 1))
+          fi
+        else
+          log "WORKER-${worker_id}: BLOCKED #${issue_num} merge not verified (state=${pr_state})"
+          mark_skip "$issue_num" "merge_unverified" 1
+          consecutive_failures=$((consecutive_failures + 1))
+        fi
       else
-        pr_files=$(get_pr_file_count "$repo_owner" "$repo_name" "$pr_num")
+        verify_details=$(echo "$verify_result" | python3 -c "import sys,json; print(json.load(sys.stdin).get('details','unknown'))" 2>/dev/null || echo "unverified")
-        if [ "${pr_files:-0}" -eq 0 ]; then
+        verify_checks=$(echo "$verify_result" | python3 -c "import sys,json; print(json.load(sys.stdin).get('checks',''))" 2>/dev/null || echo "")
-          log "WORKER-${worker_id}: BLOCKED #${issue_num} PR #${pr_num} has 0 changed files"
+        log "WORKER-${worker_id}: UNVERIFIED #${issue_num} — $verify_details"
-          curl -sf -X PATCH "${GITEA_URL}/api/v1/repos/${repo_owner}/${repo_name}/pulls/${pr_num}"             -H "Authorization: token ${GITEA_TOKEN}"             -H "Content-Type: application/json"             -d '{"state": "closed"}' >/dev/null 2>&1 || true
+        if echo "$verify_checks" | grep -q '"branch": false'; then
+          post_issue_comment "$repo_owner" "$repo_name" "$issue_num" "Loop gate blocked completion: remote branch ${branch} was not found on origin after Gemini exited. Issue remains open for retry."
+          mark_skip "$issue_num" "missing_remote_branch" 1
+        elif echo "$verify_checks" | grep -q '"pr": false'; then
+          post_issue_comment "$repo_owner" "$repo_name" "$issue_num" "Loop gate blocked completion: branch ${branch} exists remotely, but no PR was found. Issue remains open for retry."
+          mark_skip "$issue_num" "missing_pr" 1
+        elif echo "$verify_checks" | grep -q '"files": false'; then
+          curl -sf -X PATCH "${GITEA_URL}/api/v1/repos/${repo_owner}/${repo_name}/pulls/${pr_num}" \
+            -H "Authorization: token ${GITEA_TOKEN}" \
+            -H "Content-Type: application/json" \
+            -d '{"state": "closed"}' >/dev/null 2>&1 || true
           post_issue_comment "$repo_owner" "$repo_name" "$issue_num" "PR #${pr_num} was closed automatically: it had 0 changed files (empty commit). Issue remains open for retry."
           mark_skip "$issue_num" "empty_commit" 2
-          consecutive_failures=$((consecutive_failures + 1))
         else
-          proof_status=$(proof_comment_status "$repo_owner" "$repo_name" "$issue_num" "$branch")
+          post_issue_comment "$repo_owner" "$repo_name" "$issue_num" "Loop gate blocked completion: PR #${pr_num} exists, but required verification failed ($verify_details). Issue remains open for retry."
-          proof_state="${proof_status%%|*}"
+          mark_skip "$issue_num" "unverified" 1
-          proof_url="${proof_status#*|}"
-          if [ "$proof_state" != "ok" ]; then
-            log "WORKER-${worker_id}: BLOCKED #${issue_num} proof missing or incomplete (${proof_state})"
-            post_issue_comment "$repo_owner" "$repo_name" "$issue_num" "Loop gate blocked completion: PR #${pr_num} exists and has ${pr_files} changed file(s), but the required Proof block from Gemini is missing or incomplete. Issue remains open for retry."
-            mark_skip "$issue_num" "missing_proof" 1
-            consecutive_failures=$((consecutive_failures + 1))
-          else
-            log "WORKER-${worker_id}: PROOF verified ${proof_url}"
-            pr_state=$(get_pr_state "$repo_owner" "$repo_name" "$pr_num")
-            if [ "$pr_state" = "open" ]; then
-              curl -sf -X POST "${GITEA_URL}/api/v1/repos/${repo_owner}/${repo_name}/pulls/${pr_num}/merge"                 -H "Authorization: token ${GITEA_TOKEN}"                 -H "Content-Type: application/json"                 -d '{"Do": "squash"}' >/dev/null 2>&1 || true
-              pr_state=$(get_pr_state "$repo_owner" "$repo_name" "$pr_num")
-            fi
-            if [ "$pr_state" = "merged" ]; then
-              curl -sf -X PATCH "${GITEA_URL}/api/v1/repos/${repo_owner}/${repo_name}/issues/${issue_num}"                 -H "Authorization: token ${GITEA_TOKEN}"                 -H "Content-Type: application/json"                 -d '{"state": "closed"}' >/dev/null 2>&1 || true
-              issue_state=$(get_issue_state "$repo_owner" "$repo_name" "$issue_num")
-              if [ "$issue_state" = "closed" ]; then
-                log "WORKER-${worker_id}: VERIFIED #${issue_num} branch pushed, PR merged, proof present, issue closed"
-                consecutive_failures=0
-              else
-                log "WORKER-${worker_id}: BLOCKED #${issue_num} issue did not close after merge"
-                mark_skip "$issue_num" "issue_close_unverified" 1
-                consecutive_failures=$((consecutive_failures + 1))
-              fi
-            else
-              log "WORKER-${worker_id}: BLOCKED #${issue_num} merge not verified (state=${pr_state})"
-              mark_skip "$issue_num" "merge_unverified" 1
-              consecutive_failures=$((consecutive_failures + 1))
-            fi
-          fi
         fi
+        consecutive_failures=$((consecutive_failures + 1))
       fi
     elif [ "$exit_code" -eq 124 ]; then
       log "WORKER-${worker_id}: TIMEOUT #${issue_num} (work saved in PR)"
@@ -621,7 +623,8 @@ print(json.dumps({
     'lines_removed': ${LINES_REMOVED:-0},
     'salvaged': ${DIRTY:-0},
     'pr': '${pr_num:-}',
-    'merged': $( [ '$OUTCOME' = 'success' ] && [ -n '${pr_num:-}' ] && echo 'true' || echo 'false' )
+    'merged': $( [ '$OUTCOME' = 'success' ] && [ -n '${pr_num:-}' ] && echo 'true' || echo 'false' ),
+    'verified': ${VERIFIED:-false}
 }))
 " >> "$LOG_DIR/gemini-metrics.jsonl" 2>/dev/null
 

bin/genchi-genbutsu.sh

@@ -0,0 +1,179 @@
+#!/usr/bin/env bash
+# genchi-genbutsu.sh — 現地現物 — Go and see. Verify world state, not log vibes.
+#
+# Post-completion verification that goes and LOOKS at the actual artifacts.
+# Performs 5 world-state checks:
+#   1. Branch exists on remote
+#   2. PR exists
+#   3. PR has real file changes (> 0)
+#   4. PR is mergeable
+#   5. Issue has a completion comment from the agent
+#
+# Usage: genchi-genbutsu.sh <repo_owner> <repo_name> <issue_num> <branch> <agent_name>
+# Returns: JSON to stdout, logs JSONL, exit 0 = VERIFIED, exit 1 = UNVERIFIED
+
+set -euo pipefail
+
+GITEA_URL="${GITEA_URL:-https://forge.alexanderwhitestone.com}"
+GITEA_TOKEN="${GITEA_TOKEN:-}"
+LOG_DIR="${LOG_DIR:-$HOME/.hermes/logs}"
+VERIFY_LOG="$LOG_DIR/genchi-genbutsu.jsonl"
+
+if [ $# -lt 5 ]; then
+  echo "Usage: $0 <repo_owner> <repo_name> <issue_num> <branch> <agent_name>" >&2
+  exit 2
+fi
+
+repo_owner="$1"
+repo_name="$2"
+issue_num="$3"
+branch="$4"
+agent_name="$5"
+
+mkdir -p "$LOG_DIR"
+
+# ── Helpers ──────────────────────────────────────────────────────────
+
+check_branch_exists() {
+  # Use Gitea API instead of git ls-remote so we don't need clone credentials
+  curl -sf "${GITEA_URL}/api/v1/repos/${repo_owner}/${repo_name}/branches/${branch}" \
+    -H "Authorization: token ${GITEA_TOKEN}" >/dev/null 2>&1
+}
+
+get_pr_num() {
+  curl -sf "${GITEA_URL}/api/v1/repos/${repo_owner}/${repo_name}/pulls?state=all&head=${repo_owner}:${branch}&limit=1" \
+    -H "Authorization: token ${GITEA_TOKEN}" 2>/dev/null | python3 -c "
+import sys, json
+prs = json.load(sys.stdin)
+print(prs[0]['number'] if prs else '')
+"
+}
+
+check_pr_files() {
+  local pr_num="$1"
+  curl -sf "${GITEA_URL}/api/v1/repos/${repo_owner}/${repo_name}/pulls/${pr_num}/files" \
+    -H "Authorization: token ${GITEA_TOKEN}" 2>/dev/null | python3 -c "
+import sys, json
+try:
+    files = json.load(sys.stdin)
+    print(len(files) if isinstance(files, list) else 0)
+except:
+    print(0)
+"
+}
+
+check_pr_mergeable() {
+  local pr_num="$1"
+  curl -sf "${GITEA_URL}/api/v1/repos/${repo_owner}/${repo_name}/pulls/${pr_num}" \
+    -H "Authorization: token ${GITEA_TOKEN}" 2>/dev/null | python3 -c "
+import sys, json
+pr = json.load(sys.stdin)
+print('true' if pr.get('mergeable') else 'false')
+"
+}
+
+check_completion_comment() {
+  curl -sf "${GITEA_URL}/api/v1/repos/${repo_owner}/${repo_name}/issues/${issue_num}/comments" \
+    -H "Authorization: token ${GITEA_TOKEN}" 2>/dev/null | AGENT="$agent_name" python3 -c "
+import os, sys, json
+agent = os.environ.get('AGENT', '').lower()
+try:
+    comments = json.load(sys.stdin)
+except:
+    sys.exit(1)
+for c in reversed(comments):
+    user = ((c.get('user') or {}).get('login') or '').lower()
+    if user == agent:
+        sys.exit(0)
+sys.exit(1)
+"
+}
+
+# ── Run checks ───────────────────────────────────────────────────────
+
+ts=$(date -u '+%Y-%m-%dT%H:%M:%SZ')
+status="VERIFIED"
+details=()
+checks_json='{}'
+
+# Check 1: branch
+if check_branch_exists; then
+  checks_json=$(echo "$checks_json" | python3 -c "import sys,json;d=json.load(sys.stdin);d['branch']=True;print(json.dumps(d))")
+else
+  checks_json=$(echo "$checks_json" | python3 -c "import sys,json;d=json.load(sys.stdin);d['branch']=False;print(json.dumps(d))")
+  status="UNVERIFIED"
+  details+=("remote branch ${branch} not found")
+fi
+
+# Check 2: PR exists
+pr_num=$(get_pr_num)
+if [ -n "$pr_num" ]; then
+  checks_json=$(echo "$checks_json" | python3 -c "import sys,json;d=json.load(sys.stdin);d['pr']=True;print(json.dumps(d))")
+else
+  checks_json=$(echo "$checks_json" | python3 -c "import sys,json;d=json.load(sys.stdin);d['pr']=False;print(json.dumps(d))")
+  status="UNVERIFIED"
+  details+=("no PR found for branch ${branch}")
+fi
+
+# Check 3: PR has real file changes
+if [ -n "$pr_num" ]; then
+  file_count=$(check_pr_files "$pr_num")
+  if [ "${file_count:-0}" -gt 0 ]; then
+    checks_json=$(echo "$checks_json" | python3 -c "import sys,json;d=json.load(sys.stdin);d['files']=True;print(json.dumps(d))")
+  else
+    checks_json=$(echo "$checks_json" | python3 -c "import sys,json;d=json.load(sys.stdin);d['files']=False;print(json.dumps(d))")
+    status="UNVERIFIED"
+    details+=("PR #${pr_num} has 0 changed files")
+  fi
+
+  # Check 4: PR is mergeable
+  if [ "$(check_pr_mergeable "$pr_num")" = "true" ]; then
+    checks_json=$(echo "$checks_json" | python3 -c "import sys,json;d=json.load(sys.stdin);d['mergeable']=True;print(json.dumps(d))")
+  else
+    checks_json=$(echo "$checks_json" | python3 -c "import sys,json;d=json.load(sys.stdin);d['mergeable']=False;print(json.dumps(d))")
+    status="UNVERIFIED"
+    details+=("PR #${pr_num} is not mergeable")
+  fi
+else
+  checks_json=$(echo "$checks_json" | python3 -c "import sys,json;d=json.load(sys.stdin);d['files']=None;d['mergeable']=None;print(json.dumps(d))")
+fi
+
+# Check 5: completion comment from agent
+if check_completion_comment; then
+  checks_json=$(echo "$checks_json" | python3 -c "import sys,json;d=json.load(sys.stdin);d['comment']=True;print(json.dumps(d))")
+else
+  checks_json=$(echo "$checks_json" | python3 -c "import sys,json;d=json.load(sys.stdin);d['comment']=False;print(json.dumps(d))")
+  status="UNVERIFIED"
+  details+=("no completion comment from ${agent_name} on issue #${issue_num}")
+fi
+
+# Build detail string
+detail_str=$(IFS="; "; echo "${details[*]:-all checks passed}")
+
+# ── Output ───────────────────────────────────────────────────────────
+
+result=$(python3 -c "
+import json
+print(json.dumps({
+    'status': '$status',
+    'repo': '${repo_owner}/${repo_name}',
+    'issue': $issue_num,
+    'branch': '$branch',
+    'agent': '$agent_name',
+    'pr': '$pr_num',
+    'checks': $checks_json,
+    'details': '$detail_str',
+    'ts': '$ts'
+}, indent=2))
+")
+
+printf '%s\n' "$result"
+
+# Append to JSONL log
+printf '%s\n' "$result" >> "$VERIFY_LOG"
+
+if [ "$status" = "VERIFIED" ]; then
+  exit 0
+else
+  exit 1
+fi

bin/kaizen-retro.sh

@@ -0,0 +1,45 @@
+#!/usr/bin/env bash
+# kaizen-retro.sh — Automated retrospective after every burn cycle.
+#
+# Runs daily after the morning report.
+# Analyzes success rates by agent, repo, and issue type.
+# Identifies max-attempts issues, generates ONE concrete improvement,
+# and posts the retro to Telegram + the master morning-report issue.
+#
+# Usage:
+#   ./bin/kaizen-retro.sh [--dry-run]
+
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+REPO_ROOT="${SCRIPT_DIR%/bin}"
+PYTHON="${PYTHON3:-python3}"
+
+# Source local env if available so TELEGRAM_BOT_TOKEN is picked up
+HOME_DIR="${HOME:-$(eval echo ~$(whoami))}"
+for env_file in "$HOME_DIR/.hermes/.env" "$HOME_DIR/.timmy/.env" "$REPO_ROOT/.env"; do
+  if [ -f "$env_file" ]; then
+    # shellcheck source=/dev/null
+    set -a
+    # shellcheck source=/dev/null
+    source "$env_file"
+    set +a
+  fi
+done
+
+# If the configured Gitea URL is unreachable but localhost works, prefer localhost
+if ! curl -sf "${GITEA_URL:-http://localhost:3000}/api/v1/version" >/dev/null 2>&1; then
+  if curl -sf http://localhost:3000/api/v1/version >/dev/null 2>&1; then
+    export GITEA_URL="http://localhost:3000"
+  fi
+fi
+
+# Ensure the Python script exists
+RETRO_PY="$REPO_ROOT/scripts/kaizen_retro.py"
+if [ ! -f "$RETRO_PY" ]; then
+  echo "ERROR: kaizen_retro.py not found at $RETRO_PY" >&2
+  exit 1
+fi
+
+# Run
+exec "$PYTHON" "$RETRO_PY" "$@"

cron/jobs.json

@@ -137,7 +137,38 @@
       "paused_reason": null,
       "skills": [],
       "skill": null
+    },
+    {
+      "id": "kaizen-retro-349",
+      "name": "Kaizen Retro",
+      "prompt": "Run the automated burn-cycle retrospective. Execute: cd /root/wizards/ezra/workspace/timmy-config && ./bin/kaizen-retro.sh",
+      "model": "hermes3:latest",
+      "provider": "ollama",
+      "base_url": "http://localhost:11434/v1",
+      "schedule": {
+        "kind": "interval",
+        "minutes": 1440,
+        "display": "every 1440m"
+      },
+      "schedule_display": "daily at 07:30",
+      "repeat": {
+        "times": null,
+        "completed": 0
+      },
+      "enabled": true,
+      "created_at": "2026-04-07T15:30:00.000000Z",
+      "next_run_at": "2026-04-08T07:30:00.000000Z",
+      "last_run_at": null,
+      "last_status": null,
+      "last_error": null,
+      "deliver": "local",
+      "origin": null,
+      "state": "scheduled",
+      "paused_at": null,
+      "paused_reason": null,
+      "skills": [],
+      "skill": null
     }
   ],
   "updated_at": "2026-04-07T15:00:00+00:00"
-}
+}

fleet/auto_restart.py

@@ -0,0 +1,272 @@
+#!/usr/bin/env python3
+"""
+Auto-Restart Agent — Self-healing process monitor for fleet machines.
+
+Detects dead services and restarts them automatically.
+Escalates after 3 attempts (prevents restart loops).
+Logs all actions to ~/.local/timmy/fleet-health/restarts.log
+Alerts via Telegram if service cannot be recovered.
+
+Prerequisite: FLEET-006 (health check) must be running to detect failures.
+
+Usage:
+  python3 auto_restart.py          # Run checks now
+  python3 auto_restart.py --daemon # Run continuously (every 60s)
+  python3 auto_restart.py --status  # Show restart history
+"""
+
+import os
+import sys
+import json
+import time
+import subprocess
+from datetime import datetime, timezone
+from pathlib import Path
+
+# === CONFIG ===
+LOG_DIR = Path(os.path.expanduser("~/.local/timmy/fleet-health"))
+RESTART_LOG = LOG_DIR / "restarts.log"
+COOLDOWN_FILE = LOG_DIR / "restart_cooldowns.json"
+MAX_RETRIES = 3
+COOLDOWN_PERIOD = 3600  # 1 hour between escalation alerts
+
+# Services definition: name, check command, restart command
+# Local services:
+LOCAL_SERVICES = {
+    "hermes-gateway": {
+        "check": "pgrep -f 'hermes gateway' > /dev/null 2>/dev/null",
+        "restart": "cd ~/code-claw && ./restart-gateway.sh 2>/dev/null || launchctl kickstart -k ai.hermes.gateway 2>/dev/null",
+        "critical": True,
+    },
+    "ollama": {
+        "check": "pgrep -f 'ollama serve' > /dev/null 2>/dev/null",
+        "restart": "launchctl kickstart -k com.ollama.ollama 2>/dev/null || /opt/homebrew/bin/brew services restart ollama 2>/dev/null",
+        "critical": False,
+    },
+    "codeclaw-heartbeat": {
+        "check": "launchctl list | grep 'ai.timmy.codeclaw-qwen-heartbeat' > /dev/null 2>/dev/null",
+        "restart": "launchctl kickstart -k ai.timmy.codeclaw-qwen-heartbeat 2>/dev/null",
+        "critical": False,
+    },
+}
+
+# VPS services to restart via SSH
+VPS_SERVICES = {
+    "ezra": {
+        "ip": "143.198.27.163",
+        "user": "root",
+        "services": {
+            "gitea": {
+                "check": "systemctl is-active gitea 2>/dev/null | grep -q active",
+                "restart": "systemctl restart gitea 2>/dev/null",
+                "critical": True,
+            },
+            "nginx": {
+                "check": "systemctl is-active nginx 2>/dev/null | grep -q active",
+                "restart": "systemctl restart nginx 2>/dev/null",
+                "critical": False,
+            },
+            "hermes-agent": {
+                "check": "pgrep -f 'hermes gateway' > /dev/null 2>/dev/null",
+                "restart": "cd /root/wizards/ezra/hermes-agent && source .venv/bin/activate && nohup hermes gateway run --replace > /dev/null 2>&1 &",
+                "critical": True,
+            },
+        },
+    },
+    "allegro": {
+        "ip": "167.99.126.228",
+        "user": "root",
+        "services": {
+            "hermes-agent": {
+                "check": "pgrep -f 'hermes gateway' > /dev/null 2>/dev/null",
+                "restart": "cd /root/wizards/allegro/hermes-agent && source .venv/bin/activate && nohup hermes gateway run --replace > /dev/null 2>&1 &",
+                "critical": True,
+            },
+        },
+    },
+    "bezalel": {
+        "ip": "159.203.146.185",
+        "user": "root",
+        "services": {
+            "hermes-agent": {
+                "check": "pgrep -f 'hermes gateway' > /dev/null 2>/dev/null",
+                "restart": "cd /root/wizards/bezalel/hermes/venv/bin/activate && nohup hermes gateway run > /dev/null 2>&1 &",
+                "critical": True,
+            },
+            "evennia": {
+                "check": "pgrep -f 'evennia' > /dev/null 2>/dev/null",
+                "restart": "cd /root/.evennia/timmy_world && evennia restart 2>/dev/null",
+                "critical": False,
+            },
+        },
+    },
+}
+
+TELEGRAM_TOKEN_FILE = Path(os.path.expanduser("~/.config/telegram/special_bot"))
+TELEGRAM_CHAT = "-1003664764329"
+
+
+def send_telegram(message):
+    if not TELEGRAM_TOKEN_FILE.exists():
+        return False
+    token = TELEGRAM_TOKEN_FILE.read_text().strip()
+    url = f"https://api.telegram.org/bot{token}/sendMessage"
+    body = json.dumps({
+        "chat_id": TELEGRAM_CHAT,
+        "text": f"[AUTO-RESTART]\n{message}",
+    }).encode()
+    try:
+        import urllib.request
+        req = urllib.request.Request(url, data=body, headers={"Content-Type": "application/json"}, method="POST")
+        urllib.request.urlopen(req, timeout=10)
+        return True
+    except Exception:
+        return False
+
+
+def get_cooldowns():
+    if COOLDOWN_FILE.exists():
+        try:
+            return json.loads(COOLDOWN_FILE.read_text())
+        except json.JSONDecodeError:
+            pass
+    return {}
+
+
+def save_cooldowns(data):
+    COOLDOWN_FILE.write_text(json.dumps(data, indent=2))
+
+
+def check_service(check_cmd, timeout=10):
+    try:
+        proc = subprocess.run(check_cmd, shell=True, capture_output=True, timeout=timeout)
+        return proc.returncode == 0
+    except (subprocess.TimeoutExpired, subprocess.SubprocessError):
+        return False
+
+
+def restart_service(restart_cmd, timeout=30):
+    try:
+        proc = subprocess.run(restart_cmd, shell=True, capture_output=True, timeout=timeout)
+        return proc.returncode == 0
+    except (subprocess.TimeoutExpired, subprocess.SubprocessError) as e:
+        return False
+
+
+def try_restart_via_ssh(name, host_config, service_name):
+    ip = host_config["ip"]
+    user = host_config["user"]
+    service = host_config["services"][service_name]
+
+    restart_cmd = f'ssh -o StrictHostKeyChecking=no -o ConnectTimeout=10 {user}@{ip} "{service["restart"]}"'
+    return restart_service(restart_cmd, timeout=30)
+
+
+def log_restart(service_name, machine, attempt, success):
+    ts = datetime.now(timezone.utc).isoformat()
+    status = "SUCCESS" if success else "FAILED"
+    log_entry = f"{ts} [{status}] {machine}/{service_name} (attempt {attempt})\n"
+
+    RESTART_LOG.parent.mkdir(parents=True, exist_ok=True)
+    with open(RESTART_LOG, "a") as f:
+        f.write(log_entry)
+
+    print(f"  [{status}] {machine}/{service_name} - attempt {attempt}")
+
+
+def check_and_restart():
+    """Run all restart checks."""
+    results = []
+    cooldowns = get_cooldowns()
+    now = time.time()
+
+    # Check local services
+    for name, service in LOCAL_SERVICES.items():
+        if not check_service(service["check"]):
+            cooldown_key = f"local/{name}"
+            retries = cooldowns.get(cooldown_key, {"count": 0, "last": 0}).get("count", 0)
+
+            if retries >= MAX_RETRIES:
+                last = cooldowns.get(cooldown_key, {}).get("last", 0)
+                if now - last < COOLDOWN_PERIOD and service["critical"]:
+                    send_telegram(f"CRITICAL: local/{name} failed {MAX_RETRIES} restart attempts. Needs human intervention.")
+                    cooldowns[cooldown_key] = {"count": 0, "last": now}
+                    save_cooldowns(cooldowns)
+                    continue
+
+            success = restart_service(service["restart"])
+            log_restart(name, "local", retries + 1, success)
+
+            cooldowns[cooldown_key] = {"count": retries + 1 if not success else 0, "last": now}
+            save_cooldowns(cooldowns)
+            if success:
+                # Verify it actually started
+                time.sleep(3)
+                if check_service(service["check"]):
+                    print(f"  VERIFIED: local/{name} is running")
+                else:
+                    print(f"  WARNING: local/{name} restart command returned success but process not detected")
+
+    # Check VPS services
+    for host, host_config in VPS_SERVICES.items():
+        for service_name, service in host_config["services"].items():
+            check_cmd = f'ssh -o StrictHostKeyChecking=no -o ConnectTimeout=5 {host_config["user"]}@{host_config["ip"]} "{service["check"]}"'
+            if not check_service(check_cmd):
+                cooldown_key = f"{host}/{service_name}"
+                retries = cooldowns.get(cooldown_key, {"count": 0, "last": 0}).get("count", 0)
+
+                if retries >= MAX_RETRIES:
+                    last = cooldowns.get(cooldown_key, {}).get("last", 0)
+                    if now - last < COOLDOWN_PERIOD and service["critical"]:
+                        send_telegram(f"CRITICAL: {host}/{service_name} failed {MAX_RETRIES} restart attempts. Needs human intervention.")
+                        cooldowns[cooldown_key] = {"count": 0, "last": now}
+                        save_cooldowns(cooldowns)
+                        continue
+
+                success = try_restart_via_ssh(host, host_config, service_name)
+                log_restart(service_name, host, retries + 1, success)
+
+                cooldowns[cooldown_key] = {"count": retries + 1 if not success else 0, "last": now}
+                save_cooldowns(cooldowns)
+
+    return results
+
+
+def daemon_mode():
+    """Run continuously every 60 seconds."""
+    print("Auto-restart agent running in daemon mode (60s interval)")
+    print(f"Monitoring {len(LOCAL_SERVICES)} local + {sum(len(h['services']) for h in VPS_SERVICES.values())} remote services")
+    print(f"Max retries per cycle: {MAX_RETRIES}")
+    print(f"Cooldown after max retries: {COOLDOWN_PERIOD}s")
+    while True:
+        check_and_restart()
+        time.sleep(60)
+
+
+def show_status():
+    """Show restart history and cooldowns."""
+    cooldowns = get_cooldowns()
+    print("=== Restart Cooldowns ===")
+    for key, data in sorted(cooldowns.items()):
+        count = data.get("count", 0)
+        if count > 0:
+            print(f"  {key}: {count} failures, last at {datetime.fromtimestamp(data.get('last',0), tz=timezone.utc).strftime('%H:%M')}")
+
+    print("\n=== Restart Log (last 20) ===")
+    if RESTART_LOG.exists():
+        lines = RESTART_LOG.read_text().strip().split("\n")
+        for line in lines[-20:]:
+            print(f"  {line}")
+    else:
+        print("  No restarts logged yet.")
+
+
+if __name__ == "__main__":
+    LOG_DIR.mkdir(parents=True, exist_ok=True)
+
+    if len(sys.argv) > 1 and sys.argv[1] == "--daemon":
+        daemon_mode()
+    elif len(sys.argv) > 1 and sys.argv[1] == "--status":
+        show_status()
+    else:
+        check_and_restart()

fleet/capacity-inventory.md

@@ -0,0 +1,191 @@
+# Capacity Inventory - Fleet Resource Baseline
+
+**Last audited:** 2026-04-07 16:00 UTC
+**Auditor:** Timmy (direct inspection)
+
+---
+
+## Fleet Resources (Paperclips Model)
+
+Three primary resources govern the fleet:
+
+| Resource | Role | Generation | Consumption |
+|----------|------|-----------|-------------|
+| **Capacity** | Compute hours available across fleet. Determines what work can be done. | Through healthy utilization of VPS/Mac agents | Fleet improvements consume it (investing in automation, orchestration, sovereignty) |
+| **Uptime** | % time services are running. Earned at Fibonacci milestones. | When services stay up naturally | Degrades on any failure |
+| **Innovation** | Only generates when capacity is <70% utilized. Fuels Phase 3+. | When you leave capacity free | Phase 3+ buildings consume it (requires spare capacity to build) |
+
+### The Tension
+- Run fleet at 95%+ capacity: maximum productivity, ZERO Innovation
+- Run fleet at <70% capacity: Innovation generates but slower progress
+- This forces the Paperclips question: optimize now or invest in future capability?
+
+---
+
+## VPS Resource Baselines
+
+### Ezra (143.198.27.163) - "Forge"
+
+| Metric | Value | Utilization |
+|--------|-------|-------------|
+| **OS** | Ubuntu 24.04 (6.8.0-106-generic) | |
+| **vCPU** | 4 vCPU (DO basic droplet, shared) | Load: 10.76/7.59/7.04 (very high) |
+| **RAM** | 7,941 MB total | 2,104 used / 5,836 available (26% used, 74% free) |
+| **Disk** | 154 GB vda1 | 111 GB used / 44 GB free (72%) **WARNING** |
+| **Swap** | 6,143 MB | 643 MB used (10%) |
+| **Uptime** | 7 days, 18 hours | |
+
+### Key Processes (sorted by memory)
+| Process | RSS | %CPU | Notes |
+|---------|-----|------|-------|
+| Gitea | 556 MB | 83.5% | Web service, high CPU due to API load |
+| MemPalace (ezra) | 268 MB | 136% | Mining project files - HIGH CPU |
+| Hermes gateway (ezra) | 245 MB | 1.7% | Agent gateway |
+| Ollama | 230 MB | 0.1% | Model serving |
+| PostgreSQL | 138 MB | ~0% | Gitea database |
+
+**Capacity assessment:** 26% memory used, but 72% disk is getting tight. CPU load is very high (10.76 on 4vCPU = 269% utilization). Ezra is CPU-bound, not RAM-bound.
+
+### Allegro (167.99.126.228)
+
+| Metric | Value | Utilization |
+|--------|-------|-------------|
+| **OS** | Ubuntu 24.04 (6.8.0-106-generic) | |
+| **vCPU** | 4 vCPU (DO basic droplet, shared) | Moderate load |
+| **RAM** | 7,941 MB total | 1,591 used / 6,349 available (20% used, 80% free) |
+| **Disk** | 154 GB vda1 | 41 GB used / 114 GB free (27%) **GOOD** |
+| **Swap** | 8,191 MB | 686 MB used (8%) |
+| **Uptime** | 7 days, 18 hours | |
+
+### Key Processes (sorted by memory)
+| Process | RSS | %CPU | Notes |
+|---------|-----|------|-------|
+| Hermes gateway (allegro) | 680 MB | 0.9% | Main agent gateway |
+| Gitea | 181 MB | 1.2% | Secondary gitea? |
+| Systemd-journald | 160 MB | 0.0% | System logging |
+| Ezra Hermes gateway | 58 MB | 0.0% | Running ezra agent here |
+| Bezalel Hermes gateway | 58 MB | 0.0% | Running bezalel agent here |
+| Dockerd | 48 MB | 0.0% | Docker daemon |
+
+**Capacity assessment:** 20% memory used, 27% disk used. Allegro has headroom. Also running hermes gateways for Ezra and Bezalel (cross-host agent execution).
+
+### Bezalel (159.203.146.185)
+
+| Metric | Value | Utilization |
+|--------|-------|-------------|
+| **OS** | Ubuntu 24.04 (6.8.0-71-generic) | |
+| **vCPU** | 2 vCPU (DO basic droplet, shared) | Load varies |
+| **RAM** | 1,968 MB total | 817 used / 1,151 available (42% used, 58% free) |
+| **Disk** | 48 GB vda1 | 12 GB used / 37 GB free (24%) **GOOD** |
+| **Swap** | 2,047 MB | 448 MB used (22%) |
+| **Uptime** | 7 days, 18 hours | |
+
+### Key Processes (sorted by memory)
+| Process | RSS | %CPU | Notes |
+|---------|-----|------|-------|
+| Hermes gateway | 339 MB | 7.7% | Agent gateway (16.8% of RAM) |
+| uv pip install | 137 MB | 56.6% | Installing packages (temporary) |
+| Mender | 27 MB | 0.0% | Device management |
+
+**Capacity assessment:** 42% memory used, only 2GB total RAM. Bezalel is the most constrained. 2 vCPU means less compute headroom than Ezra/Allegro. Disk is fine.
+
+### Mac Local (M3 Max)
+
+| Metric | Value | Utilization |
+|--------|-------|-------------|
+| **OS** | macOS 26.3.1 | |
+| **CPU** | Apple M3 Max (14 cores) | Very capable |
+| **RAM** | 36 GB | ~8 GB used (22%) |
+| **Disk** | 926 GB total | ~624 GB used / 302 GB free (68%) |
+
+### Key Processes
+| Process | Memory | Notes |
+|---------|--------|-------|
+| Hermes gateway | 500 MB | Primary gateway |
+| Hermes agents (x3) | ~560 MB total | Multiple sessions |
+| Ollama | ~20 MB base + model memory | Model loading varies |
+| OpenClaw | 350 MB | Gateway process |
+| Evennia (server+portal) | 56 MB | Game world |
+
+---
+
+## Resource Summary
+
+| Resource | Ezra | Allegro | Bezalel | Mac Local | TOTAL |
+|----------|------|---------|---------|-----------|-------|
+| **vCPU** | 4 | 4 | 2 | 14 (M3 Max) | 24 |
+| **RAM** | 8 GB (26% used) | 8 GB (20% used) | 2 GB (42% used) | 36 GB (22% used) | 54 GB |
+| **Disk** | 154 GB (72%) | 154 GB (27%) | 48 GB (24%) | 926 GB (68%) | 1,282 GB |
+| **Cost** | $12/mo | $12/mo | $12/mo | owned | $36/mo |
+
+### Utilization by Category
+| Category | Estimated Daily Hours | % of Fleet Capacity |
+|----------|----------------------|---------------------|
+| Hermes agents | ~3-4 hrs active | 5-7% |
+| Ollama inference | ~1-2 hrs | 2-4% |
+| Gitea services | 24/7 | 5-10% |
+| Evennia | 24/7 | <1% |
+| Idle | ~18-20 hrs | ~80-90% |
+
+### Capacity Utilization: ~15-20% active
+**Innovation rate:** GENERATING (capacity < 70%)
+**Recommendation:** Good — Innovation is generating because most capacity is free.
+This means Phase 3+ capabilities (orchestration, load balancing, etc.) are accessible NOW.
+
+---
+
+## Uptime Baseline
+
+**Baseline period:** 2026-04-07 14:00-16:00 UTC (2 hours, ~24 checks at 5-min intervals)
+
+| Service | Checks | Uptime | Status |
+|---------|--------|--------|--------|
+| Ezra | 24/24 | 100.0% | GOOD |
+| Allegro | 24/24 | 100.0% | GOOD |
+| Bezalel | 24/24 | 100.0% | GOOD |
+| Gitea | 23/24 | 95.8% | GOOD |
+| Hermes Gateway | 23/24 | 95.8% | GOOD |
+| Ollama | 24/24 | 100.0% | GOOD |
+| OpenClaw | 24/24 | 100.0% | GOOD |
+| Evennia | 24/24 | 100.0% | GOOD |
+| Hermes Agent | 21/24 | 87.5% | **CHECK** |
+
+### Fibonacci Uptime Milestones
+| Milestone | Target | Current | Status |
+|-----------|--------|---------|--------|
+| 95% | 95% | 100% (VPS), 98.6% (avg) | REACHED |
+| 95.5% | 95.5% | 98.6% | REACHED |
+| 96% | 96% | 98.6% | REACHED |
+| 97% | 97% | 98.6% | REACHED |
+| 98% | 98% | 98.6% | REACHED |
+| 99% | 99% | 98.6% | APPROACHING |
+
+---
+
+## Risk Assessment
+
+| Risk | Severity | Mitigation |
+|------|----------|------------|
+| Ezra disk 72% used | MEDIUM | Move non-essential data, add monitoring alert at 85% |
+| Bezalel only 2GB RAM | HIGH | Cannot run large models locally. Good for Evennia, tight for agents |
+| Ezra CPU load 269% | HIGH | MemPalace mining consuming 136% CPU. Consider scheduling |
+| Mac disk 68% used | MEDIUM | 302 GB free still. Growing but not urgent |
+| No cross-VPS mesh | LOW | SSH works but no Tailscale. No private network between VPSes |
+
+---
+
+## Recommendations
+
+### Immediate (Phase 1-2)
+1. **Ezra disk cleanup:** 44 GB free at 72%. Docker images, old logs, and MemPalace mine data could be rotated.
+2. **Alert thresholds:** Add disk alerts at 85% (Ezra, Mac) before they become critical.
+
+### Short-term (Phase 3)
+3. **Load balancing:** Ezra is CPU-bound, Allegro has 80% RAM free. Move some agent processes from Ezra to Allegro.
+4. **Innovation investment:** Since fleet is at 15-20% utilization, Innovation is high. This is the time to build Phase 3 capabilities.
+
+### Medium-term (Phase 4)
+5. **Bezalel RAM upgrade:** 2GB is tight. Consider upgrade to 4GB ($24/mo instead of $12/mo).
+6. **Tailscale mesh:** Install on all VPSes for private inter-VPS network.
+
+---

fleet/milestones.md

@@ -0,0 +1,142 @@
+# Fleet Milestone Messages
+
+Every milestone marks passage through fleet evolution. When achieved, the message
+prints to the fleet log. Each one references a real achievement, not abstract numbers.
+
+**Source:** Inspired by Paperclips milestone messages (500 clips, 1000 clips, Full autonomy attained, etc.)
+
+---
+
+## Phase 1: Survival (Current)
+
+### M1: First Automated Health Check
+**Trigger:** `fleet/health_check.py` runs successfully for the first time.
+**Message:** "First automated health check runs. No longer watching the clock."
+
+### M2: First Auto-Restart
+**Trigger:** A dead process is detected and restarted without human intervention.
+**Message:** "A process failed at 3am and restarted itself. You found out in the morning."
+
+### M3: First Backup Completed
+**Trigger:** A backup pipeline runs end-to-end and verifies integrity.
+**Message:** "A backup completed. You did not have to think about it."
+
+### M4: 95% Uptime (30 days)
+**Trigger:** Uptime >= 95% over last 30 days.
+**Message:** "95% uptime over 30 days. The fleet stays up."
+
+### M5: Uptime 97%
+**Trigger:** Uptime >= 97% over last 30 days.
+**Message:** "97% uptime. Three nines of availability across four machines."
+
+---
+
+## Phase 2: Automation (unlock when: uptime >= 95% + capacity > 60%)
+
+### M6: Zero Manual Restarts (7 days)
+**Trigger:** 7 consecutive days with zero manual process restarts.
+**Message:** "Seven days. Zero manual restarts. The fleet heals itself."
+
+### M7: PR Auto-Merged
+**Trigger:** A PR passes CI, review, and merges without human touching it.
+**Message:** "A PR was tested, reviewed, and merged by agents. You just said 'looks good.'"
+
+### M8: Config Push Works
+**Trigger:** Config change pushed to all 3 VPSes atomically and verified.
+**Message:** "Config pushed to all three VPSes in one command. No SSH needed."
+
+### M9: 98% Uptime
+**Trigger:** Uptime >= 98% over last 30 days.
+**Message:** "98% uptime. Only 14 hours of downtime in a month. Most of it planned."
+
+---
+
+## Phase 3: Orchestration (unlock when: all Phase 2 buildings + Innovation > 100)
+
+### M10: Cross-Agent Delegation Works
+**Trigger:** Agent A creates issue, assigns to Agent B, Agent B works and creates PR.
+**Message:** "Agent Alpha created a task, Agent Beta completed it. They did not ask permission."
+
+### M11: First Model Running Locally on 2+ Machines
+**Trigger:** Ollama serving same model on Ezra and Allegro simultaneously.
+**Message:** "A model runs on two machines at once. No cloud. No rate limits."
+
+### M12: Fleet-Wide Burn Mode
+**Trigger:** All agents coordinated on single epic, produced coordinated PRs.
+**Message:** "All agents working the same epic. The fleet moves as one."
+
+---
+
+## Phase 4: Sovereignty (unlock when: zero cloud deps for core ops)
+
+### M13: First Entirely Local Inference Day
+**Trigger:** 24 hours with zero API calls to external providers.
+**Message:** "A model ran locally for the first time. No cloud. No rate limits. No one can turn it off."
+
+### M14: Sovereign Email
+**Trigger:** Stalwart email server sends and receives without Gmail relay.
+**Message:** "Email flows through our own server. No Google. No Microsoft. Ours."
+
+### M15: Sovereign Messaging
+**Trigger:** Telegram bot runs without cloud relay dependency.
+**Message:** "Messages arrive through our own infrastructure. No corporate middleman."
+
+---
+
+## Phase 5: Scale (unlock when: sovereignty stable + Innovation > 500)
+
+### M16: First Self-Spawned Agent
+**Trigger:** Agent lifecycle manager spawns a new agent instance due to load.
+**Message:** "A new agent appeared. You did not create it. The fleet built what it needed."
+
+### M17: Agent Retired Gracefully
+**Trigger:** An agent instance retires after idle timeout and cleans up its state.
+**Message:** "An agent retired. It served its purpose. Nothing was lost."
+
+### M18: Fleet Runs 24h Unattended
+**Trigger:** 24 hours with zero human intervention of any kind.
+**Message:** "A full day. No humans. No commands. The fleet runs itself."
+
+---
+
+## Phase 6: The Network (unlock when: 7 days zero human intervention)
+
+### M19: Fleet Creates Its Own Improvement Task
+**Trigger:** Fleet analyzes itself and creates an issue on Gitea.
+**Message:** "The fleet found something to improve. It created the task itself."
+
+### M20: First Outside Contribution
+**Trigger:** An external contributor's PR is reviewed and merged by fleet agents.
+**Message:** "Someone outside the fleet contributed. The fleet reviewed, tested, and merged. No human touched it."
+
+### M21: The Beacon
+**Trigger:** Infrastructure serves someone in need through automated systems.
+**Message:** "Someone found the Beacon. In the dark, looking for help. The infrastructure served its purpose. It was built for this."
+
+### M22: Permanent Light
+**Trigger:** 90 days of autonomous operation with continuous availability.
+**Message:** "Three months. The light never went out. Not for anyone."
+
+---
+
+## Fibonacci Uptime Milestones
+
+These trigger regardless of phase, based purely on uptime percentage:
+
+| Milestone | Uptime | Meaning |
+|-----------|--------|--------|
+| U1 | 95% | Basic reliability achieved |
+| U2 | 95.5% | Fewer than 16 hours/month downtime |
+| U3 | 96% | Fewer than 12 hours/month |
+| U4 | 97% | Fewer than 9 hours/month |
+| U5 | 97.5% | Fewer than 7 hours/month |
+| U6 | 98% | Fewer than 4.5 hours/month |
+| U7 | 98.3% | Fewer than 3 hours/month |
+| U8 | 98.6% | Less than 2.5 hours/month — approaching cloud tier |
+| U9 | 98.9% | Less than 1.5 hours/month |
+| U10 | 99% | Less than 1 hour/month — enterprise grade |
+| U11 | 99.5% | Less than 22 minutes/month |
+
+---
+
+*Every message is earned. None are given freely. Fleet evolution is not a checklist — it is a climb.*

fleet/resource_tracker.py

@@ -0,0 +1,231 @@
+#!/usr/bin/env python3
+"""
+Fleet Resource Tracker — Tracks Capacity, Uptime, and Innovation.
+
+Paperclips-inspired tension model:
+- Capacity: spent on fleet improvements, generates through utilization
+- Uptime: earned when services stay up, Fibonacci milestones unlock capabilities
+- Innovation: only generates when capacity < 70%. Fuels Phase 3+.
+
+This is the heart of the fleet progression system.
+"""
+
+import os
+import json
+import time
+import socket
+from datetime import datetime, timezone
+from pathlib import Path
+
+# === CONFIG ===
+DATA_DIR = Path(os.path.expanduser("~/.local/timmy/fleet-resources"))
+RESOURCES_FILE = DATA_DIR / "resources.json"
+
+# Tension thresholds
+INNOVATION_THRESHOLD = 0.70  # Innovation only generates when capacity < 70%
+INNOVATION_RATE = 5.0        # Innovation generated per hour when under threshold
+CAPACITY_REGEN_RATE = 2.0    # Capacity regenerates per hour of healthy operation
+FIBONACCI = [95.0, 95.5, 96.0, 97.0, 97.5, 98.0, 98.3, 98.6, 98.9, 99.0, 99.5]
+
+
+def init():
+    DATA_DIR.mkdir(parents=True, exist_ok=True)
+    if not RESOURCES_FILE.exists():
+        data = {
+            "capacity": {
+                "current": 100.0,
+                "max": 100.0,
+                "spent_on": [],
+                "history": []
+            },
+            "uptime": {
+                "current_pct": 100.0,
+                "milestones_reached": [],
+                "total_checks": 0,
+                "successful_checks": 0,
+                "history": []
+            },
+            "innovation": {
+                "current": 0.0,
+                "total_generated": 0.0,
+                "spent_on": [],
+                "last_calculated": time.time()
+            }
+        }
+        RESOURCES_FILE.write_text(json.dumps(data, indent=2))
+        print("Initialized resource tracker")
+    return RESOURCES_FILE.exists()
+
+
+def load():
+    if RESOURCES_FILE.exists():
+        return json.loads(RESOURCES_FILE.read_text())
+    return None
+
+
+def save(data):
+    RESOURCES_FILE.write_text(json.dumps(data, indent=2))
+
+
+def update_uptime(checks: dict):
+    """Update uptime stats from health check results.
+		checks = {'ezra': True, 'allegro': True, 'bezalel': True, 'gitea': True, ...}
+		"""
+    data = load()
+    if not data:
+        return
+
+    data["uptime"]["total_checks"] += 1
+    successes = sum(1 for v in checks.values() if v)
+    total = len(checks)
+
+    # Overall uptime percentage
+    overall = successes / max(total, 1) * 100.0
+    data["uptime"]["successful_checks"] += successes
+
+    # Calculate rolling uptime
+    if "history" not in data["uptime"]:
+        data["uptime"]["history"] = []
+    data["uptime"]["history"].append({
+        "ts": datetime.now(timezone.utc).isoformat(),
+        "checks": checks,
+        "overall": round(overall, 2)
+    })
+
+    # Keep last 1000 checks
+    if len(data["uptime"]["history"]) > 1000:
+        data["uptime"]["history"] = data["uptime"]["history"][-1000:]
+
+    # Calculate current uptime %, last 100 checks
+    recent = data["uptime"]["history"][-100:]
+    recent_ok = sum(c["overall"] for c in recent) / max(len(recent), 1)
+    data["uptime"]["current_pct"] = round(recent_ok, 2)
+
+    # Check Fibonacci milestones
+    new_milestones = []
+    for fib in FIBONACCI:
+        if fib not in data["uptime"]["milestones_reached"] and recent_ok >= fib:
+            data["uptime"]["milestones_reached"].append(fib)
+            new_milestones.append(fib)
+
+    save(data)
+
+    if new_milestones:
+        print(f"  UPTIME MILESTONE: {','.join(str(m) + '%') for m in new_milestones}")
+        print(f"  Current uptime: {recent_ok:.1f}%")
+
+    return data["uptime"]
+
+
+def spend_capacity(amount: float, purpose: str):
+    """Spend capacity on a fleet improvement."""
+    data = load()
+    if not data:
+        return False
+    if data["capacity"]["current"] < amount:
+        print(f"  INSUFFICIENT CAPACITY: Need {amount}, have {data['capacity']['current']:.1f}")
+        return False
+    data["capacity"]["current"] -= amount
+    data["capacity"]["spent_on"].append({
+        "purpose": purpose,
+        "amount": amount,
+        "ts": datetime.now(timezone.utc).isoformat()
+    })
+    save(data)
+    print(f"  Spent {amount} capacity on: {purpose}")
+    return True
+
+
+def regenerate_resources():
+    """Regenerate capacity and calculate innovation."""
+    data = load()
+    if not data:
+        return
+
+    now = time.time()
+    last = data["innovation"]["last_calculated"]
+    hours = (now - last) / 3600.0
+    if hours < 0.1:  # Only update every ~6 minutes
+        return
+
+    # Regenerate capacity
+    capacity_gain = CAPACITY_REGEN_RATE * hours
+    data["capacity"]["current"] = min(
+        data["capacity"]["max"],
+        data["capacity"]["current"] + capacity_gain
+    )
+
+    # Calculate capacity utilization
+    utilization = 1.0 - (data["capacity"]["current"] / data["capacity"]["max"])
+
+    # Generate innovation only when under threshold
+    innovation_gain = 0.0
+    if utilization < INNOVATION_THRESHOLD:
+        innovation_gain = INNOVATION_RATE * hours * (1.0 - utilization / INNOVATION_THRESHOLD)
+        data["innovation"]["current"] += innovation_gain
+        data["innovation"]["total_generated"] += innovation_gain
+
+    # Record history
+    if "history" not in data["capacity"]:
+        data["capacity"]["history"] = []
+    data["capacity"]["history"].append({
+        "ts": datetime.now(timezone.utc).isoformat(),
+        "capacity": round(data["capacity"]["current"], 1),
+        "utilization": round(utilization * 100, 1),
+        "innovation": round(data["innovation"]["current"], 1),
+        "innovation_gain": round(innovation_gain, 1)
+    })
+    # Keep last 500 capacity records
+    if len(data["capacity"]["history"]) > 500:
+        data["capacity"]["history"] = data["capacity"]["history"][-500:]
+
+    data["innovation"]["last_calculated"] = now
+
+    save(data)
+    print(f"  Capacity: {data['capacity']['current']:.1f}/{data['capacity']['max']:.1f}")
+    print(f"  Utilization: {utilization*100:.1f}%")
+    print(f"  Innovation: {data['innovation']['current']:.1f} (+{innovation_gain:.1f} this period)")
+
+    return data
+
+
+def status():
+    """Print current resource status."""
+    data = load()
+    if not data:
+        print("Resource tracker not initialized. Run --init first.")
+        return
+
+    print("\n=== Fleet Resources ===")
+    print(f"  Capacity: {data['capacity']['current']:.1f}/{data['capacity']['max']:.1f}")
+
+    utilization = 1.0 - (data["capacity"]["current"] / data["capacity"]["max"])
+    print(f"  Utilization: {utilization*100:.1f}%")
+
+    innovation_status = "GENERATING" if utilization < INNOVATION_THRESHOLD else "BLOCKED"
+    print(f"  Innovation: {data['innovation']['current']:.1f} [{innovation_status}]")
+
+    print(f"  Uptime: {data['uptime']['current_pct']:.1f}%")
+    print(f"  Milestones: {', '.join(str(m)+'%' for m in data['uptime']['milestones_reached']) or 'None yet'}")
+
+    # Phase gate checks
+    phase_2_ok = data['uptime']['current_pct'] >= 95.0
+    phase_3_ok = phase_2_ok and data['innovation']['current'] > 100
+    phase_5_ok = phase_2_ok and data['innovation']['current'] > 500
+
+    print(f"\n  Phase Gates:")
+    print(f"    Phase 2 (Automation): {'UNLOCKED' if phase_2_ok else 'LOCKED (need 95% uptime)'}")
+    print(f"    Phase 3 (Orchestration): {'UNLOCKED' if phase_3_ok else 'LOCKED (need 95% uptime + 100 innovation)'}")
+    print(f"    Phase 5 (Scale): {'UNLOCKED' if phase_5_ok else 'LOCKED (need 95% uptime + 500 innovation)'}")
+
+
+if __name__ == "__main__":
+    import sys
+    init()
+    if len(sys.argv) > 1 and sys.argv[1] == "status":
+        status()
+    elif len(sys.argv) > 1 and sys.argv[1] == "regen":
+        regenerate_resources()
+    else:
+        regenerate_resources()
+        status()

gitea_client.py

@@ -146,6 +146,7 @@ class PullRequest:
     additions: int = 0
     deletions: int = 0
     created_at: str = ""
+    updated_at: str = ""
     closed_at: str = ""
 
     @classmethod
@@ -166,6 +167,7 @@ class PullRequest:
             additions=d.get("additions", 0),
             deletions=d.get("deletions", 0),
             created_at=d.get("created_at", ""),
+            updated_at=d.get("updated_at", ""),
             closed_at=d.get("closed_at", ""),
         )
 
@@ -314,6 +316,7 @@ class GiteaClient:
         direction: str = "desc",
         limit: int = 30,
         page: int = 1,
+        since: Optional[str] = None,
     ) -> list[Issue]:
         """List issues for a repo."""
         raw = self._get(
@@ -326,6 +329,7 @@ class GiteaClient:
             direction=direction,
             limit=limit,
             page=page,
+            since=since,
         )
         return [Issue.from_dict(i) for i in raw]
 

hermes-sovereign/orchestrator/orchestrate.sh

@@ -0,0 +1,39 @@
+#!/usr/bin/env bash
+# orchestrate.sh — Sovereign Orchestrator wrapper
+# Sets environment and runs orchestrator.py
+#
+# Usage:
+#   ./orchestrate.sh              # dry-run (safe default)
+#   ./orchestrate.sh --once       # single live dispatch cycle
+#   ./orchestrate.sh --daemon     # continuous (every 15 min)
+#   ./orchestrate.sh --dry-run    # explicit dry-run
+
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+HERMES_DIR="${HOME}/.hermes"
+
+# Load Gitea token
+if [[ -z "${GITEA_TOKEN:-}" ]]; then
+    if [[ -f "${HERMES_DIR}/gitea_token_vps" ]]; then
+        export GITEA_TOKEN="$(cat "${HERMES_DIR}/gitea_token_vps")"
+    else
+        echo "[FATAL] No GITEA_TOKEN and ~/.hermes/gitea_token_vps not found"
+        exit 1
+    fi
+fi
+
+# Load Telegram token
+if [[ -z "${TELEGRAM_BOT_TOKEN:-}" ]]; then
+    if [[ -f "${HOME}/.config/telegram/special_bot" ]]; then
+        export TELEGRAM_BOT_TOKEN="$(cat "${HOME}/.config/telegram/special_bot")"
+    fi
+fi
+
+# Run preflight checks if available
+if [[ -x "${HERMES_DIR}/bin/api-key-preflight.sh" ]]; then
+    "${HERMES_DIR}/bin/api-key-preflight.sh" 2>/dev/null || true
+fi
+
+# Run the orchestrator
+exec python3 "${SCRIPT_DIR}/orchestrator.py" "$@"

hermes-sovereign/orchestrator/orchestrator.py

@@ -0,0 +1,645 @@
+#!/usr/bin/env python3
+"""
+Sovereign Orchestrator v1
+Reads the Gitea backlog, scores/prioritizes issues, dispatches to agents.
+
+Usage:
+    python3 orchestrator.py --once     # single dispatch cycle
+    python3 orchestrator.py --daemon   # run every 15 min
+    python3 orchestrator.py --dry-run  # score and report, no dispatch
+"""
+
+import json
+import os
+import sys
+import time
+import subprocess
+import urllib.request
+import urllib.error
+import urllib.parse
+from datetime import datetime, timezone
+
+# ---------------------------------------------------------------------------
+# CONFIG
+# ---------------------------------------------------------------------------
+
+GITEA_API = "https://forge.alexanderwhitestone.com/api/v1"
+GITEA_OWNER = "Timmy_Foundation"
+REPOS = ["timmy-config", "the-nexus", "timmy-home"]
+
+TELEGRAM_CHAT_ID = "-1003664764329"
+DAEMON_INTERVAL = 900  # 15 minutes
+
+# Tags that mark issues we should never auto-dispatch
+FILTER_TAGS = ["[EPIC]", "[DO NOT CLOSE]", "[PERMANENT]", "[PHILOSOPHY]", "[MORNING REPORT]"]
+
+# Known agent usernames on Gitea (for assignee detection)
+AGENT_USERNAMES = {"groq", "ezra", "bezalel", "allegro", "timmy", "thetimmyc"}
+
+# ---------------------------------------------------------------------------
+# AGENT ROSTER
+# ---------------------------------------------------------------------------
+
+AGENTS = {
+    "groq": {
+        "type": "loop",
+        "endpoint": "local",
+        "strengths": ["code", "bug-fix", "small-changes"],
+        "repos": ["the-nexus", "hermes-agent", "timmy-config", "timmy-home"],
+        "max_concurrent": 1,
+    },
+    "ezra": {
+        "type": "gateway",
+        "endpoint": "http://143.198.27.163:8643/v1/chat/completions",
+        "ssh": "root@143.198.27.163",
+        "strengths": ["research", "architecture", "complex", "multi-file"],
+        "repos": ["timmy-config", "the-nexus", "timmy-home"],
+        "max_concurrent": 1,
+    },
+    "bezalel": {
+        "type": "gateway",
+        "endpoint": "http://159.203.146.185:8643/v1/chat/completions",
+        "ssh": "root@159.203.146.185",
+        "strengths": ["ci", "infra", "ops", "testing"],
+        "repos": ["timmy-config", "hermes-agent", "the-nexus"],
+        "max_concurrent": 1,
+    },
+}
+
+# ---------------------------------------------------------------------------
+# CREDENTIALS
+# ---------------------------------------------------------------------------
+
+def load_gitea_token():
+    """Read Gitea token from env or file."""
+    token = os.environ.get("GITEA_TOKEN", "")
+    if token:
+        return token.strip()
+    token_path = os.path.expanduser("~/.hermes/gitea_token_vps")
+    try:
+        with open(token_path) as f:
+            return f.read().strip()
+    except FileNotFoundError:
+        print(f"[FATAL] No GITEA_TOKEN env and {token_path} not found")
+        sys.exit(1)
+
+
+def load_telegram_token():
+    """Read Telegram bot token from file."""
+    path = os.path.expanduser("~/.config/telegram/special_bot")
+    try:
+        with open(path) as f:
+            return f.read().strip()
+    except FileNotFoundError:
+        return ""
+
+
+GITEA_TOKEN = ""
+TELEGRAM_TOKEN = ""
+
+# ---------------------------------------------------------------------------
+# HTTP HELPERS (stdlib only)
+# ---------------------------------------------------------------------------
+
+def gitea_request(path, method="GET", data=None):
+    """Make an authenticated Gitea API request."""
+    url = f"{GITEA_API}{path}"
+    headers = {
+        "Authorization": f"token {GITEA_TOKEN}",
+        "Content-Type": "application/json",
+        "Accept": "application/json",
+    }
+    body = json.dumps(data).encode() if data else None
+    req = urllib.request.Request(url, data=body, headers=headers, method=method)
+    try:
+        with urllib.request.urlopen(req, timeout=30) as resp:
+            return json.loads(resp.read().decode())
+    except urllib.error.HTTPError as e:
+        body_text = e.read().decode() if e.fp else ""
+        print(f"[API ERROR] {method} {url} -> {e.code}: {body_text[:200]}")
+        return None
+    except Exception as e:
+        print(f"[API ERROR] {method} {url} -> {e}")
+        return None
+
+
+def send_telegram(message):
+    """Send message to Telegram group."""
+    if not TELEGRAM_TOKEN:
+        print("[WARN] No Telegram token, skipping notification")
+        return False
+    url = f"https://api.telegram.org/bot{TELEGRAM_TOKEN}/sendMessage"
+    data = json.dumps({
+        "chat_id": TELEGRAM_CHAT_ID,
+        "text": message,
+        "parse_mode": "Markdown",
+        "disable_web_page_preview": True,
+    }).encode()
+    req = urllib.request.Request(url, data=data, headers={"Content-Type": "application/json"})
+    try:
+        with urllib.request.urlopen(req, timeout=15) as resp:
+            return resp.status == 200
+    except Exception as e:
+        print(f"[TELEGRAM ERROR] {e}")
+        return False
+
+
+# ---------------------------------------------------------------------------
+# 1. BACKLOG READER
+# ---------------------------------------------------------------------------
+
+def fetch_issues(repo):
+    """Fetch all open issues from a repo, handling pagination."""
+    issues = []
+    page = 1
+    while True:
+        result = gitea_request(
+            f"/repos/{GITEA_OWNER}/{repo}/issues?state=open&type=issues&limit=50&page={page}"
+        )
+        if not result:
+            break
+        issues.extend(result)
+        if len(result) < 50:
+            break
+        page += 1
+    return issues
+
+
+def should_filter(issue):
+    """Check if issue title contains any filter tags."""
+    title = issue.get("title", "").upper()
+    for tag in FILTER_TAGS:
+        if tag.upper().replace("[", "").replace("]", "") in title.replace("[", "").replace("]", ""):
+            return True
+    # Also filter pull requests
+    if issue.get("pull_request"):
+        return True
+    return False
+
+
+def read_backlog():
+    """Read and filter the full backlog across all repos."""
+    backlog = []
+    for repo in REPOS:
+        print(f"  Fetching {repo}...")
+        issues = fetch_issues(repo)
+        for issue in issues:
+            if should_filter(issue):
+                continue
+            assignees = [a.get("login", "") for a in (issue.get("assignees") or [])]
+            labels = [l.get("name", "") for l in (issue.get("labels") or [])]
+            backlog.append({
+                "repo": repo,
+                "number": issue["number"],
+                "title": issue["title"],
+                "labels": labels,
+                "assignees": assignees,
+                "created_at": issue.get("created_at", ""),
+                "comments": issue.get("comments", 0),
+                "url": issue.get("html_url", ""),
+            })
+    print(f"  Total actionable issues: {len(backlog)}")
+    return backlog
+
+
+# ---------------------------------------------------------------------------
+# 2. PRIORITY SCORER
+# ---------------------------------------------------------------------------
+
+def score_issue(issue):
+    """Score an issue 0-100 based on priority signals."""
+    score = 0
+    title_upper = issue["title"].upper()
+    labels_upper = [l.upper() for l in issue["labels"]]
+    all_text = title_upper + " " + " ".join(labels_upper)
+
+    # Critical / Bug: +30
+    if any(tag in all_text for tag in ["CRITICAL", "BUG"]):
+        score += 30
+
+    # P0 / Urgent: +25
+    if any(tag in all_text for tag in ["P0", "URGENT"]):
+        score += 25
+
+    # P1: +15
+    if "P1" in all_text:
+        score += 15
+
+    # OPS / Security: +10
+    if any(tag in all_text for tag in ["OPS", "SECURITY"]):
+        score += 10
+
+    # Unassigned: +10
+    if not issue["assignees"]:
+        score += 10
+
+    # Age > 7 days: +5
+    try:
+        created = issue["created_at"].replace("Z", "+00:00")
+        created_dt = datetime.fromisoformat(created)
+        age_days = (datetime.now(timezone.utc) - created_dt).days
+        if age_days > 7:
+            score += 5
+    except (ValueError, AttributeError):
+        pass
+
+    # Has comments: +5
+    if issue["comments"] > 0:
+        score += 5
+
+    # Infrastructure repo: +5
+    if issue["repo"] == "timmy-config":
+        score += 5
+
+    # Already assigned to an agent: -10
+    if any(a.lower() in AGENT_USERNAMES for a in issue["assignees"]):
+        score -= 10
+
+    issue["score"] = max(0, min(100, score))
+    return issue
+
+
+def prioritize_backlog(backlog):
+    """Score and sort the backlog by priority."""
+    scored = [score_issue(i) for i in backlog]
+    scored.sort(key=lambda x: x["score"], reverse=True)
+    return scored
+
+
+# ---------------------------------------------------------------------------
+# 3. AGENT HEALTH CHECKS
+# ---------------------------------------------------------------------------
+
+def check_process(pattern):
+    """Check if a local process matching pattern is running."""
+    try:
+        result = subprocess.run(
+            ["pgrep", "-f", pattern],
+            capture_output=True, text=True, timeout=5
+        )
+        return result.returncode == 0
+    except Exception:
+        return False
+
+
+def check_ssh_service(host, service_name):
+    """Check if a remote service is running via SSH."""
+    try:
+        result = subprocess.run(
+            ["ssh", "-o", "ConnectTimeout=5", "-o", "StrictHostKeyChecking=no",
+             f"root@{host}",
+             f"systemctl is-active {service_name} 2>/dev/null || pgrep -f {service_name}"],
+            capture_output=True, text=True, timeout=15
+        )
+        return result.returncode == 0
+    except Exception:
+        return False
+
+
+def check_agent_health(name, agent):
+    """Check if an agent is alive and available."""
+    if agent["type"] == "loop":
+        alive = check_process(f"agent-loop.*{name}")
+    elif agent["type"] == "gateway":
+        host = agent["ssh"].split("@")[1]
+        service = f"hermes-{name}"
+        alive = check_ssh_service(host, service)
+    else:
+        alive = False
+    return alive
+
+
+def get_agent_status():
+    """Get health status for all agents."""
+    status = {}
+    for name, agent in AGENTS.items():
+        alive = check_agent_health(name, agent)
+        status[name] = {
+            "alive": alive,
+            "type": agent["type"],
+            "strengths": agent["strengths"],
+        }
+        symbol = "UP" if alive else "DOWN"
+        print(f"  {name}: {symbol} ({agent['type']})")
+    return status
+
+
+# ---------------------------------------------------------------------------
+# 4. DISPATCHER
+# ---------------------------------------------------------------------------
+
+def classify_issue(issue):
+    """Classify issue type based on title and labels."""
+    title = issue["title"].upper()
+    labels = " ".join(issue["labels"]).upper()
+    all_text = title + " " + labels
+
+    types = []
+    if any(w in all_text for w in ["BUG", "FIX", "BROKEN", "ERROR", "CRASH"]):
+        types.append("bug-fix")
+    if any(w in all_text for w in ["OPS", "DEPLOY", "CI", "INFRA", "PIPELINE", "MONITOR"]):
+        types.append("ops")
+    if any(w in all_text for w in ["SECURITY", "AUTH", "TOKEN", "CERT"]):
+        types.append("ops")
+    if any(w in all_text for w in ["RESEARCH", "AUDIT", "INVESTIGATE", "EXPLORE"]):
+        types.append("research")
+    if any(w in all_text for w in ["ARCHITECT", "DESIGN", "REFACTOR", "REWRITE"]):
+        types.append("architecture")
+    if any(w in all_text for w in ["TEST", "TESTING", "QA", "VALIDATE"]):
+        types.append("testing")
+    if any(w in all_text for w in ["CODE", "IMPLEMENT", "ADD", "CREATE", "BUILD"]):
+        types.append("code")
+    if any(w in all_text for w in ["SMALL", "QUICK", "SIMPLE", "MINOR", "TWEAK"]):
+        types.append("small-changes")
+    if any(w in all_text for w in ["COMPLEX", "MULTI", "LARGE", "OVERHAUL"]):
+        types.append("complex")
+
+    if not types:
+        types = ["code"]  # default
+
+    return types
+
+
+def match_agent(issue, agent_status, dispatched_this_cycle):
+    """Find the best available agent for an issue."""
+    issue_types = classify_issue(issue)
+    candidates = []
+
+    for name, agent in AGENTS.items():
+        # Agent must be alive
+        if not agent_status.get(name, {}).get("alive", False):
+            continue
+
+        # Agent must handle this repo
+        if issue["repo"] not in agent["repos"]:
+            continue
+
+        # Agent must not already be dispatched this cycle
+        if dispatched_this_cycle.get(name, 0) >= agent["max_concurrent"]:
+            continue
+
+        # Score match based on overlapping strengths
+        overlap = len(set(issue_types) & set(agent["strengths"]))
+        candidates.append((name, overlap))
+
+    if not candidates:
+        return None
+
+    # Sort by overlap score descending, return best match
+    candidates.sort(key=lambda x: x[1], reverse=True)
+    return candidates[0][0]
+
+
+def assign_issue(repo, number, agent_name):
+    """Assign an issue to an agent on Gitea."""
+    # First get current assignees to not clobber
+    result = gitea_request(f"/repos/{GITEA_OWNER}/{repo}/issues/{number}")
+    if not result:
+        return False
+
+    current = [a.get("login", "") for a in (result.get("assignees") or [])]
+    if agent_name in current:
+        print(f"    Already assigned to {agent_name}")
+        return True
+
+    new_assignees = current + [agent_name]
+    patch_result = gitea_request(
+        f"/repos/{GITEA_OWNER}/{repo}/issues/{number}",
+        method="PATCH",
+        data={"assignees": new_assignees}
+    )
+    return patch_result is not None
+
+
+def dispatch_to_gateway(agent_name, agent, issue):
+    """Trigger work on a gateway agent via SSH."""
+    host = agent["ssh"]
+    repo = issue["repo"]
+    number = issue["number"]
+    title = issue["title"]
+
+    # Try to trigger dispatch via SSH
+    cmd = (
+        f'ssh -o ConnectTimeout=10 -o StrictHostKeyChecking=no {host} '
+        f'"echo \'Dispatched by orchestrator: {repo}#{number} - {title}\' '
+        f'>> /tmp/hermes-dispatch.log"'
+    )
+    try:
+        subprocess.run(cmd, shell=True, timeout=20, capture_output=True)
+        return True
+    except Exception as e:
+        print(f"    [WARN] SSH dispatch to {agent_name} failed: {e}")
+        return False
+
+
+def dispatch_cycle(backlog, agent_status, dry_run=False):
+    """Run one dispatch cycle. Returns dispatch report."""
+    dispatched = []
+    skipped = []
+    dispatched_count = {}  # agent_name -> count dispatched this cycle
+
+    # Only dispatch unassigned issues (or issues not assigned to agents)
+    for issue in backlog:
+        agent_assigned = any(a.lower() in AGENT_USERNAMES for a in issue["assignees"])
+
+        if agent_assigned:
+            skipped.append((issue, "already assigned to agent"))
+            continue
+
+        if issue["score"] < 5:
+            skipped.append((issue, "score too low"))
+            continue
+
+        best_agent = match_agent(issue, agent_status, dispatched_count)
+        if not best_agent:
+            skipped.append((issue, "no available agent"))
+            continue
+
+        if dry_run:
+            dispatched.append({
+                "agent": best_agent,
+                "repo": issue["repo"],
+                "number": issue["number"],
+                "title": issue["title"],
+                "score": issue["score"],
+                "dry_run": True,
+            })
+            dispatched_count[best_agent] = dispatched_count.get(best_agent, 0) + 1
+            continue
+
+        # Actually dispatch
+        print(f"  Dispatching {issue['repo']}#{issue['number']} -> {best_agent}")
+        success = assign_issue(issue["repo"], issue["number"], best_agent)
+        if success:
+            agent = AGENTS[best_agent]
+            if agent["type"] == "gateway":
+                dispatch_to_gateway(best_agent, agent, issue)
+
+            dispatched.append({
+                "agent": best_agent,
+                "repo": issue["repo"],
+                "number": issue["number"],
+                "title": issue["title"],
+                "score": issue["score"],
+            })
+            dispatched_count[best_agent] = dispatched_count.get(best_agent, 0) + 1
+        else:
+            skipped.append((issue, "assignment failed"))
+
+    return dispatched, skipped
+
+
+# ---------------------------------------------------------------------------
+# 5. CONSOLIDATED REPORT
+# ---------------------------------------------------------------------------
+
+def generate_report(backlog, dispatched, skipped, agent_status, dry_run=False):
+    """Generate dispatch cycle report."""
+    now = datetime.now().strftime("%Y-%m-%d %H:%M")
+    mode = " [DRY RUN]" if dry_run else ""
+
+    lines = []
+    lines.append(f"=== Sovereign Orchestrator Report{mode} ===")
+    lines.append(f"Time: {now}")
+    lines.append(f"Total backlog: {len(backlog)} issues")
+    lines.append("")
+
+    # Agent health
+    lines.append("-- Agent Health --")
+    for name, info in agent_status.items():
+        symbol = "UP" if info["alive"] else "DOWN"
+        lines.append(f"  {name}: {symbol} ({info['type']})")
+    lines.append("")
+
+    # Dispatched
+    lines.append(f"-- Dispatched: {len(dispatched)} --")
+    for d in dispatched:
+        dry = " (dry-run)" if d.get("dry_run") else ""
+        lines.append(f"  [{d['score']}] {d['repo']}#{d['number']} -> {d['agent']}{dry}")
+        lines.append(f"       {d['title'][:60]}")
+    lines.append("")
+
+    # Skipped (top 10)
+    skip_summary = {}
+    for issue, reason in skipped:
+        skip_summary[reason] = skip_summary.get(reason, 0) + 1
+    lines.append(f"-- Skipped: {len(skipped)} --")
+    for reason, count in sorted(skip_summary.items(), key=lambda x: -x[1]):
+        lines.append(f"  {reason}: {count}")
+    lines.append("")
+
+    # Top 5 unassigned
+    unassigned = [i for i in backlog if not i["assignees"]][:5]
+    lines.append("-- Top 5 Unassigned (by priority) --")
+    for i in unassigned:
+        lines.append(f"  [{i['score']}] {i['repo']}#{i['number']}: {i['title'][:55]}")
+    lines.append("")
+
+    report = "\n".join(lines)
+    return report
+
+
+def format_telegram_report(backlog, dispatched, skipped, agent_status, dry_run=False):
+    """Format a compact Telegram message."""
+    mode = " DRY RUN" if dry_run else ""
+    now = datetime.now().strftime("%H:%M")
+
+    parts = [f"*Orchestrator{mode}* ({now})"]
+    parts.append(f"Backlog: {len(backlog)} | Dispatched: {len(dispatched)} | Skipped: {len(skipped)}")
+
+    # Agent status line
+    agent_line = " | ".join(
+        f"{'✅' if v['alive'] else '❌'}{k}" for k, v in agent_status.items()
+    )
+    parts.append(agent_line)
+
+    if dispatched:
+        parts.append("")
+        parts.append("*Dispatched:*")
+        for d in dispatched[:5]:
+            dry = " 🔍" if d.get("dry_run") else ""
+            parts.append(f"  `{d['repo']}#{d['number']}` → {d['agent']}{dry}")
+
+    # Top unassigned
+    unassigned = [i for i in backlog if not i["assignees"]][:3]
+    if unassigned:
+        parts.append("")
+        parts.append("*Top unassigned:*")
+        for i in unassigned:
+            parts.append(f"  [{i['score']}] `{i['repo']}#{i['number']}` {i['title'][:40]}")
+
+    return "\n".join(parts)
+
+
+# ---------------------------------------------------------------------------
+# 6. MAIN
+# ---------------------------------------------------------------------------
+
+def run_cycle(dry_run=False):
+    """Execute one full orchestration cycle."""
+    global GITEA_TOKEN, TELEGRAM_TOKEN
+    GITEA_TOKEN = load_gitea_token()
+    TELEGRAM_TOKEN = load_telegram_token()
+
+    print("\n[1/4] Reading backlog...")
+    backlog = read_backlog()
+
+    print("\n[2/4] Scoring and prioritizing...")
+    backlog = prioritize_backlog(backlog)
+    for i in backlog[:10]:
+        print(f"  [{i['score']:3d}] {i['repo']}/{i['number']}: {i['title'][:55]}")
+
+    print("\n[3/4] Checking agent health...")
+    agent_status = get_agent_status()
+
+    print("\n[4/4] Dispatching...")
+    dispatched, skipped = dispatch_cycle(backlog, agent_status, dry_run=dry_run)
+
+    # Generate reports
+    report = generate_report(backlog, dispatched, skipped, agent_status, dry_run=dry_run)
+    print("\n" + report)
+
+    # Send Telegram notification
+    if dispatched or not dry_run:
+        tg_msg = format_telegram_report(backlog, dispatched, skipped, agent_status, dry_run=dry_run)
+        send_telegram(tg_msg)
+
+    return backlog, dispatched, skipped
+
+
+def main():
+    import argparse
+    parser = argparse.ArgumentParser(description="Sovereign Orchestrator v1")
+    parser.add_argument("--once", action="store_true", help="Single dispatch cycle")
+    parser.add_argument("--daemon", action="store_true", help="Run every 15 min")
+    parser.add_argument("--dry-run", action="store_true", help="Score/report only, no dispatch")
+    parser.add_argument("--interval", type=int, default=DAEMON_INTERVAL,
+                        help=f"Daemon interval in seconds (default: {DAEMON_INTERVAL})")
+    args = parser.parse_args()
+
+    if not any([args.once, args.daemon, args.dry_run]):
+        args.dry_run = True  # safe default
+        print("[INFO] No mode specified, defaulting to --dry-run")
+
+    print("=" * 60)
+    print("  SOVEREIGN ORCHESTRATOR v1")
+    print("=" * 60)
+
+    if args.daemon:
+        print(f"[DAEMON] Running every {args.interval}s (Ctrl+C to stop)")
+        cycle = 0
+        while True:
+            cycle += 1
+            print(f"\n--- Cycle {cycle} ---")
+            try:
+                run_cycle(dry_run=args.dry_run)
+            except Exception as e:
+                print(f"[ERROR] Cycle failed: {e}")
+            print(f"[DAEMON] Sleeping {args.interval}s...")
+            time.sleep(args.interval)
+    else:
+        run_cycle(dry_run=args.dry_run)
+
+
+if __name__ == "__main__":
+    main()

scripts/kaizen_retro.py

@@ -0,0 +1,526 @@
+#!/usr/bin/env python3
+"""
+Kaizen Retro — Automated retrospective after every burn cycle.
+
+Reads overnight Gitea activity, fleet state, and loop logs.
+Generates ONE concrete improvement suggestion and posts it.
+
+Usage:
+    python3 scripts/kaizen_retro.py [--dry-run]
+"""
+
+from __future__ import annotations
+
+import argparse
+import json
+import os
+import sys
+import urllib.error
+import urllib.request
+from datetime import datetime, timedelta, timezone
+from pathlib import Path
+from typing import Any, Optional
+
+# Ensure repo root is on path so we can import gitea_client
+REPO_ROOT = Path(__file__).resolve().parent.parent
+sys.path.insert(0, str(REPO_ROOT))
+
+from gitea_client import GiteaClient, GiteaError
+
+# ---------------------------------------------------------------------------
+# Configuration
+# ---------------------------------------------------------------------------
+
+REPOS = [
+    "Timmy_Foundation/the-nexus",
+    "Timmy_Foundation/timmy-config",
+    "Timmy_Foundation/timmy-home",
+    "Timmy_Foundation/the-door",
+    "Timmy_Foundation/turboquant",
+    "Timmy_Foundation/hermes-agent",
+    "Timmy_Foundation/.profile",
+]
+
+HERMES_HOME = Path.home() / ".hermes"
+TIMMY_HOME = Path.home() / ".timmy"
+WORKFORCE_STATE_PATH = HERMES_HOME / "workforce-state.json"
+FLEET_ROUTING_PATH = HERMES_HOME / "fleet-routing.json"
+CHANNEL_DIR_PATH = REPO_ROOT / "channel_directory.json"
+REPORTS_DIR = REPO_ROOT / "reports"
+MORNING_REPORT_REPO = "Timmy_Foundation/timmy-config"
+
+TELEGRAM_BOT_TOKEN = os.environ.get("TELEGRAM_BOT_TOKEN")
+TELEGRAM_CHAT_ID = os.environ.get("TELEGRAM_HOME_CHANNEL", "-1003664764329")
+TELEGRAM_MAX_LEN = 4000  # leave headroom below the 4096 hard limit
+
+STALE_DAYS = 7
+MAX_ATTEMPT_COMMENT_THRESHOLD = 5
+
+ISSUE_TYPE_KEYWORDS = {
+    "bug": ["bug", "fix", "crash", "error", "regression", "broken"],
+    "feature": ["feature", "implement", "add", "support", "enable"],
+    "docs": ["doc", "readme", "wiki", "guide", "documentation"],
+    "kaizen": ["kaizen", "retro", "improvement", "continuous"],
+    "devops": ["deploy", "ci", "cd", "docker", "server", "infra"],
+}
+
+BLOCKER_LABELS = {"blocked", "timeout", "stale", "help wanted", "wontfix", "duplicate"}
+
+
+# ---------------------------------------------------------------------------
+# Helpers
+# ---------------------------------------------------------------------------
+
+def load_json(path: Path) -> Any:
+    if not path.exists():
+        return None
+    with open(path) as f:
+        return json.load(f)
+
+
+def iso_day_ago(days: int = 1) -> str:
+    return (datetime.now(timezone.utc) - timedelta(days=days)).isoformat()
+
+
+def classify_issue_type(issue: dict) -> str:
+    title = (issue.get("title", "") or "").lower()
+    body = (issue.get("body", "") or "").lower()
+    labels = [l.get("name", "").lower() for l in issue.get("labels", []) or []]
+    text = f"{title} {body} {' '.join(labels)}"
+    words = set(text.split())
+
+    best = "other"
+    best_score = 0
+    for kind, keywords in ISSUE_TYPE_KEYWORDS.items():
+        # Short keywords (<=3 chars) require whole-word match to avoid false positives like
+        # "ci" inside "cleanup" or "cd" inside "abcde".
+        score = sum(
+            1 for kw in keywords
+            if (len(kw) <= 3 and kw in words) or (len(kw) > 3 and kw in text)
+        )
+        # label match is stronger
+        for label in labels:
+            label_words = set(label.split())
+            if any(
+                (len(kw) <= 3 and kw in label_words) or (len(kw) > 3 and kw in label)
+                for kw in keywords
+            ):
+                score += 3
+        if score > best_score:
+            best_score = score
+            best = kind
+    return best
+
+
+def is_max_attempts_candidate(issue: dict) -> bool:
+    """Heuristic for issues that consumed excessive attempts."""
+    labels = {l.get("name", "").lower() for l in issue.get("labels", []) or []}
+    if labels & BLOCKER_LABELS:
+        return True
+    if issue.get("comments", 0) >= MAX_ATTEMPT_COMMENT_THRESHOLD:
+        return True
+    created = issue.get("created_at")
+    if created:
+        try:
+            created_dt = datetime.fromisoformat(created.replace("Z", "+00:00"))
+            if datetime.now(timezone.utc) - created_dt > timedelta(days=STALE_DAYS):
+                return True
+        except Exception:
+            pass
+    return False
+
+
+def telegram_send(text: str, bot_token: str, chat_id: str) -> list[dict]:
+    """Post text to Telegram, chunking if it exceeds the message limit."""
+    url = f"https://api.telegram.org/bot{bot_token}/sendMessage"
+    chunks = []
+    if len(text) <= TELEGRAM_MAX_LEN:
+        chunks = [text]
+    else:
+        # Split on newlines to preserve readability
+        lines = text.splitlines(keepends=True)
+        current = ""
+        for line in lines:
+            if len(current) + len(line) > TELEGRAM_MAX_LEN:
+                if current:
+                    chunks.append(current)
+                current = line
+            else:
+                current += line
+        if current:
+            chunks.append(current)
+    results = []
+    for i, chunk in enumerate(chunks):
+        prefix = f"*(part {i + 1}/{len(chunks)})*\n" if len(chunks) > 1 else ""
+        payload = {"chat_id": chat_id, "text": prefix + chunk, "parse_mode": "Markdown"}
+        data = json.dumps(payload).encode()
+        req = urllib.request.Request(url, data=data, headers={"Content-Type": "application/json"})
+        with urllib.request.urlopen(req, timeout=30) as resp:
+            results.append(json.loads(resp.read().decode()))
+    return results
+
+
+def find_latest_morning_report_issue(client: GiteaClient) -> Optional[int]:
+    try:
+        issues = client.list_issues(MORNING_REPORT_REPO, state="open", sort="created", direction="desc", limit=20)
+        for issue in issues:
+            if "good morning report" in issue.title.lower() or "morning report" in issue.title.lower():
+                return issue.number
+        # fallback to closed
+        issues = client.list_issues(MORNING_REPORT_REPO, state="closed", sort="created", direction="desc", limit=20)
+        for issue in issues:
+            if "good morning report" in issue.title.lower() or "morning report" in issue.title.lower():
+                return issue.number
+    except Exception:
+        pass
+    return None
+
+
+def fmt_pct(num: float, den: float) -> str:
+    if den == 0:
+        return "N/A"
+    return f"{num/den:.0%}"
+
+
+# ---------------------------------------------------------------------------
+# Analysis
+# ---------------------------------------------------------------------------
+
+def gather_metrics(client: GiteaClient, since: str) -> dict:
+    """Collect overnight metrics from Gitea."""
+    metrics = {
+        "closed_issues": [],
+        "merged_prs": [],
+        "closed_prs": [],
+        "open_issues": [],
+        "max_attempts_issues": [],
+        "by_agent": {},
+        "by_repo": {},
+        "by_type": {},
+    }
+
+    for repo in REPOS:
+        repo_short = repo.split("/")[1]
+        metrics["by_repo"][repo_short] = {
+            "closed": 0,
+            "merged_prs": 0,
+            "closed_prs": 0,
+            "open": 0,
+            "max_attempts": 0,
+            "successes": 0,
+            "failures": 0,
+        }
+
+        # Closed issues since window
+        try:
+            closed = client.list_issues(repo, state="closed", since=since, sort="updated", direction="desc", limit=100)
+            for issue in closed:
+                issue_dict = {
+                    "number": issue.number,
+                    "title": issue.title,
+                    "repo": repo_short,
+                    "type": classify_issue_type({"title": issue.title, "body": issue.body, "labels": [{"name": lb.name} for lb in issue.labels]}),
+                    "assignee": issue.assignees[0].login if issue.assignees else "unassigned",
+                }
+                metrics["closed_issues"].append(issue_dict)
+                metrics["by_repo"][repo_short]["closed"] += 1
+                metrics["by_repo"][repo_short]["successes"] += 1
+
+                agent = issue_dict["assignee"]
+                if agent not in metrics["by_agent"]:
+                    metrics["by_agent"][agent] = {"successes": 0, "failures": 0, "closed": 0, "repos": set()}
+                metrics["by_agent"][agent]["successes"] += 1
+                metrics["by_agent"][agent]["closed"] += 1
+                metrics["by_agent"][agent]["repos"].add(repo_short)
+
+                t = issue_dict["type"]
+                if t not in metrics["by_type"]:
+                    metrics["by_type"][t] = {"successes": 0, "failures": 0, "total": 0}
+                metrics["by_type"][t]["successes"] += 1
+                metrics["by_type"][t]["total"] += 1
+        except Exception as exc:
+            print(f"Warning: could not load closed issues for {repo}: {exc}", file=sys.stderr)
+
+        # Open issues (for stale / max-attempts detection)
+        try:
+            open_issues = client.list_issues(repo, state="open", sort="created", direction="desc", limit=100)
+            metrics["by_repo"][repo_short]["open"] = len(open_issues)
+            for issue in open_issues:
+                issue_raw = {
+                    "number": issue.number,
+                    "title": issue.title,
+                    "labels": [{"name": lb.name} for lb in issue.labels],
+                    "comments": issue.comments,
+                    "created_at": issue.created_at,
+                }
+                if is_max_attempts_candidate(issue_raw):
+                    metrics["max_attempts_issues"].append({
+                        "number": issue.number,
+                        "title": issue.title,
+                        "repo": repo_short,
+                        "type": classify_issue_type({"title": issue.title, "body": issue.body, "labels": issue_raw["labels"]}),
+                        "assignee": issue.assignees[0].login if issue.assignees else "unassigned",
+                    })
+                    metrics["by_repo"][repo_short]["max_attempts"] += 1
+                    metrics["by_repo"][repo_short]["failures"] += 1
+
+                    agent = issue.assignees[0].login if issue.assignees else "unassigned"
+                    if agent not in metrics["by_agent"]:
+                        metrics["by_agent"][agent] = {"successes": 0, "failures": 0, "closed": 0, "repos": set()}
+                    metrics["by_agent"][agent]["failures"] += 1
+                    metrics["by_agent"][agent]["repos"].add(repo_short)
+
+                    t = classify_issue_type({"title": issue.title, "body": issue.body, "labels": issue_raw["labels"]})
+                    if t not in metrics["by_type"]:
+                        metrics["by_type"][t] = {"successes": 0, "failures": 0, "total": 0}
+                    metrics["by_type"][t]["failures"] += 1
+                    metrics["by_type"][t]["total"] += 1
+        except Exception as exc:
+            print(f"Warning: could not load open issues for {repo}: {exc}", file=sys.stderr)
+
+        # PRs merged / closed since window (filter client-side; Gitea PR API ignores since)
+        try:
+            prs = client.list_pulls(repo, state="closed", sort="updated", limit=100)
+            since_dt = datetime.fromisoformat(since.replace("Z", "+00:00"))
+            for pr in prs:
+                updated = pr.updated_at or pr.created_at or ""
+                try:
+                    updated_dt = datetime.fromisoformat(updated.replace("Z", "+00:00"))
+                    if updated_dt < since_dt:
+                        continue
+                except Exception:
+                    pass
+                if pr.merged:
+                    metrics["merged_prs"].append({
+                        "number": pr.number,
+                        "title": pr.title,
+                        "repo": repo_short,
+                        "user": pr.user.login if pr.user else "unknown",
+                    })
+                    metrics["by_repo"][repo_short]["merged_prs"] += 1
+                else:
+                    metrics["closed_prs"].append({
+                        "number": pr.number,
+                        "title": pr.title,
+                        "repo": repo_short,
+                        "user": pr.user.login if pr.user else "unknown",
+                    })
+                    metrics["by_repo"][repo_short]["closed_prs"] += 1
+        except Exception as exc:
+            print(f"Warning: could not load PRs for {repo}: {exc}", file=sys.stderr)
+
+    # Convert sets to lists for JSON serialization
+    for agent in metrics["by_agent"].values():
+        agent["repos"] = sorted(agent["repos"])
+
+    return metrics
+
+
+def load_workforce_state() -> dict:
+    return load_json(WORKFORCE_STATE_PATH) or {}
+
+
+def load_fleet_routing() -> list[dict]:
+    data = load_json(FLEET_ROUTING_PATH)
+    if data and "agents" in data:
+        return data["agents"]
+    return []
+
+
+def generate_suggestion(metrics: dict, fleet: list[dict]) -> str:
+    """Generate ONE concrete improvement suggestion based on the data."""
+    by_agent = metrics["by_agent"]
+    by_repo = metrics["by_repo"]
+    by_type = metrics["by_type"]
+    max_attempts = metrics["max_attempts_issues"]
+
+    suggestions: list[str] = []
+
+    # 1. Agent with poor repo performance
+    for agent, stats in by_agent.items():
+        total = stats["successes"] + stats["failures"]
+        if total >= 3 and stats["successes"] == 0:
+            repos = ", ".join(stats["repos"])
+            suggestions.append(
+                f"🎯 **{agent}** has a 0% verify rate over the last cycle (0/{total}) on repos: {repos}. "
+                f"Consider removing these repos from {agent}'s routing or providing targeted onboarding."
+            )
+
+    # 2. Repo with highest failure concentration
+    repo_failures = [(r, s) for r, s in by_repo.items() if s["failures"] > 0]
+    if repo_failures:
+        repo_failures.sort(key=lambda x: x[1]["failures"], reverse=True)
+        worst_repo, worst_stats = repo_failures[0]
+        total_repo = worst_stats["successes"] + worst_stats["failures"]
+        if worst_stats["failures"] >= 2:
+            suggestions.append(
+                f"🎯 **{worst_repo}** has the most friction ({worst_stats['failures']} blocked/stale issues, "
+                f"{fmt_pct(worst_stats['successes'], total_repo)} success). "
+                f"Consider splitting issues in {worst_repo} into smaller chunks or assigning a stronger agent."
+            )
+
+    # 3. Max-attempts pattern
+    if len(max_attempts) >= 3:
+        type_counts: dict[str, int] = {}
+        for issue in max_attempts:
+            type_counts[issue["type"]] = type_counts.get(issue["type"], 0) + 1
+        top_type = max(type_counts, key=type_counts.get) if type_counts else "unknown"
+        suggestions.append(
+            f"🎯 **{len(max_attempts)} issues** hit max-attempts or went stale. "
+            f"The dominant type is **{top_type}**. "
+            f"Consider adding acceptance criteria templates or pre-flight checklists for {top_type} issues."
+        )
+
+    # 4. Issue type disparity
+    for t, stats in by_type.items():
+        total = stats["total"]
+        if total >= 3 and stats["successes"] == 0:
+            suggestions.append(
+                f"🎯 **{t}** issues have a 0% closure rate ({stats['failures']} stale). "
+                f"Consider routing all {t} issues to a specialist agent or creating a dedicated playbook."
+            )
+
+    # 5. Fleet routing gap (if fleet data exists)
+    active_agents = {a["name"] for a in fleet if a.get("active")}
+    assigned_agents = set(by_agent.keys())
+    idle_agents = active_agents - assigned_agents - {"unassigned"}
+    if len(idle_agents) >= 2:
+        suggestions.append(
+            f"🎯 **{len(idle_agents)} active agents** have no assignments this cycle: {', '.join(idle_agents)}. "
+            f"Consider expanding their repo lists or investigating why they aren't receiving work."
+        )
+
+    if suggestions:
+        return suggestions[0]
+
+    # Fallback: celebrate or nudge
+    total_closed = len(metrics["closed_issues"])
+    total_merged = len(metrics["merged_prs"])
+    if total_closed >= 5 or total_merged >= 3:
+        return (
+            f"🎯 Strong cycle: {total_closed} issues closed, {total_merged} PRs merged. "
+            f"Next improvement: write down the top 3 patterns that made this cycle successful so we can replicate them."
+        )
+
+    return (
+        "🎯 Low activity this cycle. Next improvement: ensure at least one agent loop is actively polling "
+        "for unassigned issues so work doesn't sit idle."
+    )
+
+
+def build_report(metrics: dict, suggestion: str, since: str) -> str:
+    now = datetime.now(timezone.utc).strftime("%Y-%m-%d %H:%M UTC")
+    period = since[:10]
+
+    lines = [
+        f"# 🌀 Kaizen Retro — {now}",
+        f"*Period: {period} → now*\n",
+        "## Numbers",
+        f"- **Issues closed:** {len(metrics['closed_issues'])}",
+        f"- **PRs merged:** {len(metrics['merged_prs'])}",
+        f"- **PRs closed without merge:** {len(metrics['closed_prs'])}",
+        f"- **Max-attempts / stale issues:** {len(metrics['max_attempts_issues'])}",
+        "",
+        "## By Agent",
+    ]
+
+    for agent, stats in sorted(metrics["by_agent"].items(), key=lambda x: x[1]["successes"] + x[1]["failures"], reverse=True):
+        total = stats["successes"] + stats["failures"]
+        rate = fmt_pct(stats["successes"], total)
+        lines.append(f"- **{agent}**: {stats['successes']} closed, {stats['failures']} stale / max-attempts — verify rate {rate}")
+
+    lines.extend(["", "## By Repo"])
+    for repo, stats in sorted(metrics["by_repo"].items(), key=lambda x: x[1]["successes"] + x[1]["failures"], reverse=True):
+        total = stats["successes"] + stats["failures"]
+        if total == 0 and stats["open"] == 0:
+            continue
+        rate = fmt_pct(stats["successes"], total)
+        lines.append(
+            f"- **{repo}**: {stats['successes']} closed, {stats['failures']} stale, {stats['open']} open — verify rate {rate}"
+        )
+
+    lines.extend(["", "## By Issue Type"])
+    for t, stats in sorted(metrics["by_type"].items(), key=lambda x: x[1]["total"], reverse=True):
+        total = stats["total"]
+        rate = fmt_pct(stats["successes"], total)
+        lines.append(f"- **{t}**: {stats['successes']} closed, {stats['failures']} stale — verify rate {rate}")
+
+    if metrics["max_attempts_issues"]:
+        lines.extend(["", "## Max-Attempts / Stale Issues"])
+        for issue in metrics["max_attempts_issues"][:10]:
+            lines.append(f"- {issue['repo']}#{issue['number']} ({issue['type']}, assignee: {issue['assignee']}) — {issue['title']}")
+        if len(metrics["max_attempts_issues"]) > 10:
+            lines.append(f"- … and {len(metrics['max_attempts_issues']) - 10} more")
+
+    lines.extend(["", "## One Concrete Improvement", suggestion, ""])
+
+    return "\n".join(lines)
+
+
+# ---------------------------------------------------------------------------
+# Main
+# ---------------------------------------------------------------------------
+
+def main() -> int:
+    parser = argparse.ArgumentParser(description="Kaizen Retro — automated burn-cycle retrospective")
+    parser.add_argument("--dry-run", action="store_true", help="Print report but do not post")
+    parser.add_argument("--since", type=str, help="ISO timestamp for lookback window (default: 24h ago)")
+    parser.add_argument("--post-to", type=str, help="Override Telegram chat ID")
+    args = parser.parse_args()
+
+    since = args.since or iso_day_ago(1)
+    client = GiteaClient()
+
+    print("Gathering metrics since", since)
+    metrics = gather_metrics(client, since)
+    fleet = load_fleet_routing()
+    suggestion = generate_suggestion(metrics, fleet)
+    report = build_report(metrics, suggestion, since)
+
+    print(report)
+
+    # Save JSON snapshot
+    REPORTS_DIR.mkdir(parents=True, exist_ok=True)
+    snapshot_path = REPORTS_DIR / f"kaizen-retro-{datetime.now(timezone.utc).strftime('%Y%m%d')}.json"
+    snapshot = {
+        "generated_at": datetime.now(timezone.utc).isoformat(),
+        "since": since,
+        "metrics": metrics,
+        "suggestion": suggestion,
+        "report_markdown": report,
+    }
+    with open(snapshot_path, "w") as f:
+        json.dump(snapshot, f, indent=2)
+    print(f"\nSnapshot saved to {snapshot_path}")
+
+    if args.dry_run:
+        return 0
+
+    # Post to Telegram
+    chat_id = args.post_to or TELEGRAM_CHAT_ID
+    bot_token = TELEGRAM_BOT_TOKEN
+    if bot_token and chat_id:
+        try:
+            telegram_send(report, bot_token, chat_id)
+            print("Posted to Telegram.")
+        except Exception as exc:
+            print(f"Failed to post to Telegram: {exc}", file=sys.stderr)
+    else:
+        print("Telegram not configured (set TELEGRAM_BOT_TOKEN and TELEGRAM_HOME_CHANNEL).", file=sys.stderr)
+
+    # Comment on latest morning report issue
+    morning_issue = find_latest_morning_report_issue(client)
+    if morning_issue:
+        try:
+            client.create_comment(MORNING_REPORT_REPO, morning_issue, report)
+            print(f"Commented on morning report issue #{morning_issue}.")
+        except Exception as exc:
+            print(f"Failed to comment on morning report issue: {exc}", file=sys.stderr)
+    else:
+        print("No morning report issue found to comment on.", file=sys.stderr)
+
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())

tasks.py

@@ -1860,22 +1860,56 @@ def good_morning_report():
         except Exception:
             pass
 
+    # Genchi Genbutsu: count verified completions from the last 24h
+    verified_completions = 0
+    raw_completions = 0
+    metrics_dir = Path.home() / ".hermes" / "logs"
+    for metrics_file in metrics_dir.glob("*-metrics.jsonl"):
+        try:
+            with open(metrics_file) as mf:
+                for line in mf:
+                    line = line.strip()
+                    if not line:
+                        continue
+                    try:
+                        row = json.loads(line)
+                    except json.JSONDecodeError:
+                        continue
+                    ts = row.get("ts", "")
+                    if not ts:
+                        continue
+                    try:
+                        from datetime import datetime as _dt, timezone as _tz, timedelta as _td
+                        row_time = _dt.fromisoformat(ts.replace("Z", "+00:00"))
+                        if (now - row_time) > _td(hours=24):
+                            continue
+                    except Exception:
+                        continue
+                    if row.get("outcome") != "success":
+                        continue
+                    raw_completions += 1
+                    if row.get("verified") is True:
+                        verified_completions += 1
+        except Exception:
+            pass
+
     # --- BUILD THE REPORT ---
-    
+
     body = f"""Good morning, Alexander. It's {day_name}.
 
 ## Overnight Debrief
 
-**Heartbeat:** {tick_count} ticks logged overnight.
+|**Heartbeat:** {tick_count} ticks logged overnight.
-**Gitea:** {"up all night" if gitea_up else "⚠️ had downtime"}
+|**Gitea:** {"up all night" if gitea_up else "⚠️ had downtime"}
-**Local inference:** {"running steady" if local_inference_up else "⚠️ had downtime"}
+|**Local inference:** {"running steady" if local_inference_up else "⚠️ had downtime"}
-**Model status:** {model_status}
+|**Model status:** {model_status}
-**Models on disk:** {len(models_loaded)} ({', '.join(m for m in models_loaded if 'timmy' in m.lower() or 'hermes' in m.lower()) or 'none with our name'})
+|**Models on disk:** {len(models_loaded)} ({', '.join(m for m in models_loaded if 'timmy' in m.lower() or 'hermes' in m.lower()) or 'none with our name'})
-**Alerts:** {len(alerts)} {'— ' + '; '.join(alerts[-3:]) if alerts else '(clean night)'}
+|**Alerts:** {len(alerts)} {'— ' + '; '.join(alerts[-3:]) if alerts else '(clean night)'}
 {briefing_summary}
 
 **DPO training pairs staged:** {dpo_count} session files exported
 **Local model smoke test:** {smoke_result}
+**Verified completions (24h):** {verified_completions} {'(Genchi Genbutsu clean)' if verified_completions == raw_completions else f'({raw_completions - verified_completions} raw completions failed verification)'}
 
 ## Gitea Pulse
 
@@ -1915,6 +1949,29 @@ That's all. Have a good morning.
         return {"filed": False, "error": str(e)}
 
 
+# ── NEW 6b: Kaizen Retro ─────────────────────────────────────────────
+
+@huey.periodic_task(crontab(hour="7", minute="15"))  # 7:15 AM daily, after morning report
+def kaizen_retro():
+    """Run the automated burn-cycle retrospective."""
+    retro_script = Path(__file__).resolve().parent / "bin" / "kaizen-retro.sh"
+    if not retro_script.exists():
+        return {"ran": False, "error": "kaizen-retro.sh not found"}
+
+    result = subprocess.run(
+        ["bash", str(retro_script)],
+        capture_output=True,
+        text=True,
+        timeout=300,
+    )
+    return {
+        "ran": True,
+        "exit_code": result.returncode,
+        "stdout": result.stdout[-2000:] if result.stdout else "",
+        "stderr": result.stderr[-1000:] if result.stderr else "",
+    }
+
+
 # ── NEW 7: Repo Watchdog ─────────────────────────────────────────────
 
 @huey.periodic_task(crontab(minute="*/20"))  # every 20 minutes
@@ -2323,7 +2380,38 @@ def velocity_tracking():
         total_open += open_n
         total_closed += closed_n
         results.append({"repo": repo, "open": open_n, "closed": closed_n, "date": today})
-    data = {"date": today, "repos": results, "total_open": total_open, "total_closed": total_closed}
+
+    # Genchi Genbutsu: count verified completions from agent metrics
+    verified_completions = 0
+    raw_completions = 0
+    metrics_dir = Path.home() / ".hermes" / "logs"
+    for metrics_file in metrics_dir.glob("*-metrics.jsonl"):
+        try:
+            with open(metrics_file) as mf:
+                for line in mf:
+                    line = line.strip()
+                    if not line:
+                        continue
+                    try:
+                        row = json.loads(line)
+                    except json.JSONDecodeError:
+                        continue
+                    if row.get("outcome") != "success":
+                        continue
+                    raw_completions += 1
+                    if row.get("verified") is True:
+                        verified_completions += 1
+        except Exception:
+            pass
+
+    data = {
+        "date": today,
+        "repos": results,
+        "total_open": total_open,
+        "total_closed": total_closed,
+        "raw_completions": raw_completions,
+        "verified_completions": verified_completions,
+    }
     with open(report_file, "w") as f:
         json.dump(data, f, indent=2)
     # Dashboard
@@ -2333,14 +2421,16 @@ def velocity_tracking():
         for r in results:
             f.write(f"| {r['repo'].split('/')[-1]} | {r['open']} | {r['closed']} |\n")
         f.write(f"| **TOTAL** | **{total_open}** | **{total_closed}** |\n\n")
+        f.write(f"**Verified completions (Genchi Genbutsu):** {verified_completions}\n")
+        f.write(f"**Raw completions:** {raw_completions}\n\n")
         # Trend
         prior = sorted(glob.glob(os.path.join(report_dir, "velocity-*.json")))
         if len(prior) > 1:
-            f.write("## Recent Trend\n\n| Date | Total Open | Total Closed |\n|---|---|---|\n")
+            f.write("## Recent Trend\n\n| Date | Total Open | Total Closed | Verified |\n|---|---|---|---|\n")
             for pf in prior[-10:]:
                 pd = json.load(open(pf))
-                f.write(f"| {pd['date']} | {pd['total_open']} | {pd['total_closed']} |\n")
+                f.write(f"| {pd['date']} | {pd['total_open']} | {pd['total_closed']} | {pd.get('verified_completions', '-')} |\n")
-    msg = f"Velocity: {total_open} open, {total_closed} closed ({today})"
+    msg = f"Velocity: {total_open} open, {total_closed} closed, {verified_completions} verified ({today})"
     if len(prior) > 1:
         prev = json.load(open(prior[-2]))
         if total_open > prev["total_open"]:

tests/test_kaizen_retro.py

@@ -0,0 +1,283 @@
+"""Tests for the Kaizen Retro burn-cycle retrospective script."""
+
+from __future__ import annotations
+
+import importlib.util
+import json
+import sys
+from datetime import datetime, timedelta, timezone
+from pathlib import Path
+from unittest.mock import MagicMock, patch
+
+import pytest
+
+REPO_ROOT = Path(__file__).parent.parent
+
+# Load kaizen_retro.py as a module (it lives in scripts/, not a package)
+spec = importlib.util.spec_from_file_location("kaizen_retro", REPO_ROOT / "scripts" / "kaizen_retro.py")
+kr = importlib.util.module_from_spec(spec)
+spec.loader.exec_module(kr)
+
+
+# ── classify_issue_type ───────────────────────────────────────────────────
+
+class TestClassifyIssueType:
+    def test_classifies_bug_from_title(self):
+        issue = {"title": "Fix crash on startup", "body": "", "labels": []}
+        assert kr.classify_issue_type(issue) == "bug"
+
+    def test_classifies_feature_from_label(self):
+        issue = {"title": "Add dark mode", "body": "", "labels": [{"name": "enhancement"}]}
+        # label "enhancement" doesn't match any keyword directly, but "feature" and "add" are in title
+        assert kr.classify_issue_type(issue) == "feature"
+
+    def test_classifies_docs_from_label(self):
+        issue = {"title": "Update guide", "body": "", "labels": [{"name": "documentation"}]}
+        assert kr.classify_issue_type(issue) == "docs"
+
+    def test_label_match_stronger_than_title(self):
+        issue = {"title": "Something random", "body": "", "labels": [{"name": "bug"}]}
+        assert kr.classify_issue_type(issue) == "bug"
+
+    def test_kaizen_takes_precedence_with_both_labels(self):
+        issue = {"title": "Process improvement", "body": "", "labels": [{"name": "kaizen"}, {"name": "bug"}]}
+        # kaizen label gives +3, bug gives +3, tie goes to first seen? kaizen appears first in dict
+        assert kr.classify_issue_type(issue) == "kaizen"
+
+    def test_defaults_to_other(self):
+        issue = {"title": "Tidy up naming", "body": "No user-facing change", "labels": [{"name": "cleanup"}]}
+        assert kr.classify_issue_type(issue) == "other"
+
+
+# ── is_max_attempts_candidate ─────────────────────────────────────────────
+
+class TestIsMaxAttemptsCandidate:
+    def test_blocker_label_returns_true(self):
+        issue = {"labels": [{"name": "blocked"}], "comments": 0, "created_at": "2026-04-07T00:00:00Z"}
+        assert kr.is_max_attempts_candidate(issue) is True
+
+    def test_timeout_label_returns_true(self):
+        issue = {"labels": [{"name": "timeout"}], "comments": 0, "created_at": "2026-04-07T00:00:00Z"}
+        assert kr.is_max_attempts_candidate(issue) is True
+
+    def test_high_comment_count_returns_true(self):
+        issue = {"labels": [], "comments": 5, "created_at": "2026-04-07T00:00:00Z"}
+        assert kr.is_max_attempts_candidate(issue) is True
+
+    def test_fresh_issue_with_low_comments_returns_false(self):
+        now = datetime.now(timezone.utc)
+        issue = {"labels": [], "comments": 2, "created_at": now.isoformat()}
+        assert kr.is_max_attempts_candidate(issue) is False
+
+    def test_stale_age_returns_true(self):
+        old = datetime.now(timezone.utc) - timedelta(days=10)
+        issue = {"labels": [], "comments": 0, "created_at": old.isoformat()}
+        assert kr.is_max_attempts_candidate(issue) is True
+
+
+# ── fmt_pct ───────────────────────────────────────────────────────────────
+
+class TestFmtPct:
+    def test_basic_percentage(self):
+        assert kr.fmt_pct(3, 4) == "75%"
+
+    def test_zero_denominator(self):
+        assert kr.fmt_pct(0, 0) == "N/A"
+
+    def test_perfect_rate(self):
+        assert kr.fmt_pct(10, 10) == "100%"
+
+
+# ── generate_suggestion ───────────────────────────────────────────────────
+
+class TestGenerateSuggestion:
+    def test_agent_zero_success_rate(self):
+        metrics = {
+            "by_agent": {
+                "groq": {"successes": 0, "failures": 5, "closed": 0, "repos": ["timmy-home"]},
+            },
+            "by_repo": {},
+            "by_type": {},
+            "max_attempts_issues": [],
+            "closed_issues": [],
+            "merged_prs": [],
+            "closed_prs": [],
+        }
+        suggestion = kr.generate_suggestion(metrics, [])
+        assert "groq" in suggestion
+        assert "0%" in suggestion or "verify rate" in suggestion
+
+    def test_repo_with_most_failures(self):
+        metrics = {
+            "by_agent": {},
+            "by_repo": {
+                "the-nexus": {"successes": 2, "failures": 5, "closed": 2, "open": 3},
+            },
+            "by_type": {},
+            "max_attempts_issues": [],
+            "closed_issues": [],
+            "merged_prs": [],
+            "closed_prs": [],
+        }
+        suggestion = kr.generate_suggestion(metrics, [])
+        assert "the-nexus" in suggestion
+        assert "friction" in suggestion
+
+    def test_max_attempts_pattern(self):
+        metrics = {
+            "by_agent": {},
+            "by_repo": {},
+            "by_type": {},
+            "max_attempts_issues": [
+                {"type": "devops"}, {"type": "devops"}, {"type": "feature"}
+            ],
+            "closed_issues": [],
+            "merged_prs": [],
+            "closed_prs": [],
+        }
+        suggestion = kr.generate_suggestion(metrics, [])
+        assert "devops" in suggestion
+        assert "max-attempts" in suggestion.lower() or "stale" in suggestion.lower()
+
+    def test_idle_agents(self):
+        metrics = {
+            "by_agent": {},
+            "by_repo": {},
+            "by_type": {},
+            "max_attempts_issues": [],
+            "closed_issues": [],
+            "merged_prs": [],
+            "closed_prs": [],
+        }
+        fleet = [{"name": "allegro", "active": True}, {"name": "ezra", "active": True}]
+        suggestion = kr.generate_suggestion(metrics, fleet)
+        assert "idle" in suggestion.lower() or "no assignments" in suggestion.lower()
+
+    def test_fallback_celebration(self):
+        metrics = {
+            "by_agent": {},
+            "by_repo": {},
+            "by_type": {},
+            "max_attempts_issues": [],
+            "closed_issues": [{}, {}, {}, {}, {}],
+            "merged_prs": [{}, {}, {}],
+            "closed_prs": [],
+        }
+        suggestion = kr.generate_suggestion(metrics, [])
+        assert "Strong cycle" in suggestion
+
+    def test_fallback_low_activity(self):
+        metrics = {
+            "by_agent": {},
+            "by_repo": {},
+            "by_type": {},
+            "max_attempts_issues": [],
+            "closed_issues": [],
+            "merged_prs": [],
+            "closed_prs": [],
+        }
+        suggestion = kr.generate_suggestion(metrics, [])
+        assert "Low activity" in suggestion or "idle" in suggestion.lower()
+
+
+# ── build_report ──────────────────────────────────────────────────────────
+
+class TestBuildReport:
+    def test_report_contains_numbers_section(self):
+        metrics = {
+            "closed_issues": [{}, {}],
+            "merged_prs": [{}],
+            "closed_prs": [],
+            "max_attempts_issues": [],
+            "by_agent": {"ezra": {"successes": 2, "failures": 0, "repos": ["timmy-config"]}},
+            "by_repo": {"timmy-config": {"successes": 2, "failures": 0, "open": 1}},
+            "by_type": {"feature": {"successes": 2, "failures": 0, "total": 2}},
+        }
+        report = kr.build_report(metrics, "Do better.", "2026-04-06T00:00:00+00:00")
+        assert "## Numbers" in report
+        assert "Issues closed:** 2" in report
+        assert "PRs merged:** 1" in report
+        assert "## By Agent" in report
+        assert "## By Repo" in report
+        assert "## By Issue Type" in report
+        assert "Do better." in report
+
+    def test_report_skips_empty_repos(self):
+        metrics = {
+            "closed_issues": [],
+            "merged_prs": [],
+            "closed_prs": [],
+            "max_attempts_issues": [],
+            "by_agent": {},
+            "by_repo": {"unused-repo": {"successes": 0, "failures": 0, "open": 0}},
+            "by_type": {},
+        }
+        report = kr.build_report(metrics, "Nudge.", "2026-04-06T00:00:00+00:00")
+        assert "unused-repo" not in report
+
+    def test_report_truncates_max_attempts(self):
+        metrics = {
+            "closed_issues": [],
+            "merged_prs": [],
+            "closed_prs": [],
+            "max_attempts_issues": [{"repo": "r", "number": i, "type": "bug", "assignee": "a", "title": f"T{i}"} for i in range(15)],
+            "by_agent": {},
+            "by_repo": {},
+            "by_type": {},
+        }
+        report = kr.build_report(metrics, "Fix it.", "2026-04-06T00:00:00+00:00")
+        assert "and 5 more" in report
+
+
+# ── telegram_send ─────────────────────────────────────────────────────────
+
+class TestTelegramSend:
+    def test_short_message_sent_in_one_piece(self):
+        with patch("urllib.request.urlopen") as mock_urlopen:
+            mock_resp = MagicMock()
+            mock_resp.read.return_value = b'{"ok": true}'
+            mock_urlopen.return_value.__enter__.return_value = mock_resp
+
+            results = kr.telegram_send("Hello", "fake-token", "123")
+            assert len(results) == 1
+            assert results[0]["ok"] is True
+            # Verify payload
+            call_args = mock_urlopen.call_args
+            req = call_args[0][0]
+            payload = json.loads(req.data.decode())
+            assert payload["text"] == "Hello"
+            assert payload["chat_id"] == "123"
+
+    def test_long_message_chunked(self):
+        big_text = "Line\n" * 2000  # ~10k chars
+        with patch("urllib.request.urlopen") as mock_urlopen:
+            mock_resp = MagicMock()
+            mock_resp.read.return_value = b'{"ok": true}'
+            mock_urlopen.return_value.__enter__.return_value = mock_resp
+
+            results = kr.telegram_send(big_text, "fake-token", "123")
+            assert len(results) >= 2
+            # First chunk should have a part prefix
+            req = mock_urlopen.call_args_list[0][0][0]
+            payload = json.loads(req.data.decode())
+            assert "(part 1" in payload["text"]
+
+
+# ── load helpers ──────────────────────────────────────────────────────────
+
+class TestLoadHelpers:
+    def test_load_json_missing_returns_none(self, tmp_path):
+        missing = tmp_path / "does_not_exist.json"
+        assert kr.load_json(missing) is None
+
+    def test_load_json_valid(self, tmp_path):
+        p = tmp_path / "data.json"
+        p.write_text('{"a": 1}')
+        assert kr.load_json(p) == {"a": 1}
+
+    def test_iso_day_ago_format(self):
+        s = kr.iso_day_ago(1)
+        # Should be a valid ISO timestamp string
+        dt = datetime.fromisoformat(s)
+        now = datetime.now(timezone.utc)
+        assert now - dt < timedelta(days=2)