feat: add pre-flight provider check script (#508)

- Checks OpenRouter balance via /api/v1/auth/key
- Tests Nous and Anthropic API keys
- Verifies Ollama is running
- Pre-flight check before session launch
- Returns exit code for automation

Closes #508

bin/nostr-agent-demo.py

@@ -1,3 +1,4 @@
+#!/usr/bin/env python3
 """
 Full Nostr agent-to-agent communication demo - FINAL WORKING
 """

bin/preflight-provider-check.py

@@ -0,0 +1,271 @@
+#!/usr/bin/env python3
+"""
+Pre-Flight Provider Check Script
+Issue #508: [Robustness] Credential drain detection — provider health checks
+
+Pre-flight check before session launch: verifies provider credentials and balance.
+
+Usage:
+  python3 preflight-provider-check.py              # Check all providers
+  python3 preflight-provider-check.py --launch      # Check and return exit code
+  python3 preflight-provider-check.py --balance     # Check OpenRouter balance
+"""
+
+import os, sys, json, yaml, urllib.request
+from datetime import datetime, timezone
+from pathlib import Path
+
+# Configuration
+HERMES_HOME = Path(os.environ.get("HERMES_HOME", Path.home() / ".hermes"))
+LOG_DIR = Path.home() / ".local" / "timmy" / "fleet-health"
+LOG_FILE = LOG_DIR / "preflight-check.log"
+
+def log(msg):
+    """Log message to file and optionally console."""
+    timestamp = datetime.now(timezone.utc).strftime("%Y-%m-%d %H:%M:%S")
+    log_entry = "[" + timestamp + "] " + msg
+    
+    LOG_DIR.mkdir(parents=True, exist_ok=True)
+    with open(LOG_FILE, "a") as f:
+        f.write(log_entry + "\n")
+    
+    if "--quiet" not in sys.argv:
+        print(log_entry)
+
+def get_provider_api_key(provider):
+    """Get API key for a provider from .env or environment."""
+    env_file = HERMES_HOME / ".env"
+    if env_file.exists():
+        with open(env_file) as f:
+            for line in f:
+                line = line.strip()
+                if line.startswith(provider.upper() + "_API_KEY="):
+                    return line.split("=", 1)[1].strip().strip("'\"")
+    
+    return os.environ.get(provider.upper() + "_API_KEY")
+
+def check_openrouter_balance(api_key):
+    """Check OpenRouter balance via /api/v1/auth/key."""
+    if not api_key:
+        return False, "No API key", 0
+    
+    try:
+        req = urllib.request.Request(
+            "https://openrouter.ai/api/v1/auth/key",
+            headers={"Authorization": "Bearer " + api_key}
+        )
+        resp = urllib.request.urlopen(req, timeout=10)
+        data = json.loads(resp.read())
+        
+        # Check for credits
+        credits = data.get("data", {}).get("limit", 0)
+        usage = data.get("data", {}).get("usage", 0)
+        remaining = credits - usage if credits else None
+        
+        if remaining is not None and remaining <= 0:
+            return False, "No credits remaining", 0
+        elif remaining is not None:
+            return True, "Credits available", remaining
+        else:
+            return True, "Unlimited or unknown balance", None
+    
+    except urllib.error.HTTPError as e:
+        if e.code == 401:
+            return False, "Invalid API key", 0
+        else:
+            return False, "HTTP " + str(e.code), 0
+    except Exception as e:
+        return False, str(e)[:100], 0
+
+def check_nous_key(api_key):
+    """Check Nous API key with minimal test call."""
+    if not api_key:
+        return False, "No API key"
+    
+    try:
+        req = urllib.request.Request(
+            "https://inference.nousresearch.com/v1/models",
+            headers={"Authorization": "Bearer " + api_key}
+        )
+        resp = urllib.request.urlopen(req, timeout=10)
+        
+        if resp.status == 200:
+            return True, "Valid key"
+        else:
+            return False, "HTTP " + str(resp.status)
+    
+    except urllib.error.HTTPError as e:
+        if e.code == 401:
+            return False, "Invalid API key"
+        elif e.code == 403:
+            return False, "Forbidden"
+        else:
+            return False, "HTTP " + str(e.code)
+    except Exception as e:
+        return False, str(e)[:100]
+
+def check_anthropic_key(api_key):
+    """Check Anthropic API key with minimal test call."""
+    if not api_key:
+        return False, "No API key"
+    
+    try:
+        req = urllib.request.Request(
+            "https://api.anthropic.com/v1/models",
+            headers={
+                "x-api-key": api_key,
+                "anthropic-version": "2023-06-01"
+            }
+        )
+        resp = urllib.request.urlopen(req, timeout=10)
+        
+        if resp.status == 200:
+            return True, "Valid key"
+        else:
+            return False, "HTTP " + str(resp.status)
+    
+    except urllib.error.HTTPError as e:
+        if e.code == 401:
+            return False, "Invalid API key"
+        elif e.code == 403:
+            return False, "Forbidden"
+        else:
+            return False, "HTTP " + str(e.code)
+    except Exception as e:
+        return False, str(e)[:100]
+
+def check_ollama():
+    """Check if Ollama is running."""
+    try:
+        req = urllib.request.Request("http://localhost:11434/api/tags")
+        resp = urllib.request.urlopen(req, timeout=5)
+        
+        if resp.status == 200:
+            data = json.loads(resp.read())
+            models = data.get("models", [])
+            return True, str(len(models)) + " models loaded"
+        else:
+            return False, "HTTP " + str(resp.status)
+    
+    except Exception as e:
+        return False, str(e)[:100]
+
+def get_configured_provider():
+    """Get the configured provider from global config."""
+    config_file = HERMES_HOME / "config.yaml"
+    if not config_file.exists():
+        return None
+    
+    try:
+        with open(config_file) as f:
+            config = yaml.safe_load(f)
+        
+        model_config = config.get("model", {})
+        if isinstance(model_config, dict):
+            return model_config.get("provider")
+    except:
+        pass
+    
+    return None
+
+def run_preflight_check():
+    """Run pre-flight check on all providers."""
+    log("=== Pre-Flight Provider Check ===")
+    
+    results = {}
+    
+    # Check OpenRouter
+    or_key = get_provider_api_key("openrouter")
+    or_ok, or_msg, or_balance = check_openrouter_balance(or_key)
+    results["openrouter"] = {"healthy": or_ok, "message": or_msg, "balance": or_balance}
+    
+    # Check Nous
+    nous_key = get_provider_api_key("nous")
+    nous_ok, nous_msg = check_nous_key(nous_key)
+    results["nous"] = {"healthy": nous_ok, "message": nous_msg}
+    
+    # Check Anthropic
+    anthropic_key = get_provider_api_key("anthropic")
+    anthropic_ok, anthropic_msg = check_anthropic_key(anthropic_key)
+    results["anthropic"] = {"healthy": anthropic_ok, "message": anthropic_msg}
+    
+    # Check Ollama
+    ollama_ok, ollama_msg = check_ollama()
+    results["ollama"] = {"healthy": ollama_ok, "message": ollama_msg}
+    
+    # Get configured provider
+    configured = get_configured_provider()
+    
+    # Summary
+    healthy_count = sum(1 for r in results.values() if r["healthy"])
+    total_count = len(results)
+    
+    log("Results: " + str(healthy_count) + "/" + str(total_count) + " providers healthy")
+    
+    for provider, result in results.items():
+        status = "HEALTHY" if result["healthy"] else "UNHEALTHY"
+        extra = ""
+        if provider == "openrouter" and result.get("balance") is not None:
+            extra = " (balance: " + str(result["balance"]) + ")"
+        
+        log("  " + provider + ": " + status + " - " + result["message"] + extra)
+    
+    if configured:
+        log("Configured provider: " + configured)
+        if configured in results and not results[configured]["healthy"]:
+            log("WARNING: Configured provider " + configured + " is UNHEALTHY!")
+    
+    return results, configured
+
+def check_launch_readiness():
+    """Check if we're ready to launch sessions."""
+    results, configured = run_preflight_check()
+    
+    # Check if configured provider is healthy
+    if configured and configured in results:
+        if not results[configured]["healthy"]:
+            log("LAUNCH BLOCKED: Configured provider " + configured + " is unhealthy")
+            return False, configured + " is unhealthy"
+    
+    # Check if at least one provider is healthy
+    healthy_providers = [p for p, r in results.items() if r["healthy"]]
+    if not healthy_providers:
+        log("LAUNCH BLOCKED: No healthy providers available")
+        return False, "No healthy providers"
+    
+    log("LAUNCH READY: " + str(len(healthy_providers)) + " healthy providers available")
+    return True, "Ready"
+
+def show_balance():
+    """Show OpenRouter balance."""
+    api_key = get_provider_api_key("openrouter")
+    if not api_key:
+        print("No OpenRouter API key found")
+        return
+    
+    ok, msg, balance = check_openrouter_balance(api_key)
+    
+    if ok:
+        if balance is not None:
+            print("OpenRouter balance: " + str(balance) + " credits")
+        else:
+            print("OpenRouter: " + msg)
+    else:
+        print("OpenRouter: " + msg)
+
+def main():
+    if "--balance" in sys.argv:
+        show_balance()
+    elif "--launch" in sys.argv:
+        ready, message = check_launch_readiness()
+        if ready:
+            print("READY")
+            sys.exit(0)
+        else:
+            print("BLOCKED: " + message)
+            sys.exit(1)
+    else:
+        run_preflight_check()
+
+if __name__ == "__main__":
+    main()

bin/soul_eval_gate.py

@@ -1,3 +1,4 @@
+#!/usr/bin/env python3
 """
 Soul Eval Gate — The Conscience of the Training Pipeline
 

cron/jobs.json

@@ -196,7 +196,37 @@
       "paused_reason": null,
       "skills": [],
       "skill": null
+    },
+    {
+      "id": "tmux-supervisor-513",
+      "name": "Autonomous Cron Supervisor",
+      "prompt": "Load the tmux-supervisor skill and execute the monitoring protocol.\n\nCheck both `dev` and `timmy` tmux sessions for idle panes. Only send Telegram notifications on actionable events (idle, overflow, failure). Be silent when all agents are working.\n\nSteps:\n1. List all tmux sessions (skip 'Alexander')\n2. For each session, list windows and panes\n3. Capture each pane and classify state (idle vs active)\n4. For idle panes: read context, craft context-aware prompt\n5. Send /queue prompts to idle panes\n6. Verify prompts landed\n7. Only notify via Telegram if:\n   - A pane was prompted (idle detected)\n   - A pane shows context overflow (>80%)\n   - A pane is stuck or crashed\n8. If all panes are active: respond with [SILENT]",
+      "schedule": {
+        "kind": "interval",
+        "minutes": 7,
+        "display": "every 7m"
+      },
+      "schedule_display": "every 7m",
+      "repeat": {
+        "times": null,
+        "completed": 0
+      },
+      "enabled": true,
+      "created_at": "2026-04-15T03:00:00.000000+00:00",
+      "next_run_at": null,
+      "last_run_at": null,
+      "last_status": null,
+      "last_error": null,
+      "deliver": "telegram",
+      "origin": null,
+      "state": "scheduled",
+      "paused_at": null,
+      "paused_reason": null,
+      "skills": [
+        "tmux-supervisor"
+      ],
+      "skill": "tmux-supervisor"
     }
   ],
   "updated_at": "2026-04-13T02:00:00+00:00"
-}
+}

cron/pipeline-scheduler.yml

@@ -0,0 +1,9 @@
+- name: Nightly Pipeline Scheduler
+  schedule: '*/30 18-23,0-8 * * *' # Every 30 min, off-peak hours only
+  tasks:
+    - name: Check and start pipelines
+      shell: "bash scripts/nightly-pipeline-scheduler.sh"
+      env:
+        PIPELINE_TOKEN_LIMIT: "500000"
+        PIPELINE_PEAK_START: "9"
+        PIPELINE_PEAK_END: "18"

scripts/captcha_bypass_handler.py

@@ -1,3 +1,4 @@
+#!/usr/bin/env python3
 import json
 from hermes_tools import browser_navigate, browser_vision
 

scripts/diagram_meaning_extractor.py

@@ -1,3 +1,4 @@
+#!/usr/bin/env python3
 import json
 from hermes_tools import browser_navigate, browser_vision
 

scripts/nightly-pipeline-scheduler.md

@@ -0,0 +1,50 @@
+# Nightly Pipeline Scheduler
+
+Auto-starts batch pipelines when inference is available.
+
+## What It Does
+
+1. Checks inference provider health (OpenRouter, Ollama, RunPod)
+2. Checks if it's off-peak hours (configurable, default: after 6PM)
+3. Checks interactive session load (don't fight with live users)
+4. Checks daily token budget (configurable limit)
+5. Starts the highest-priority incomplete pipeline
+
+## Pipeline Priority Order
+
+| Priority | Pipeline | Deps | Max Tokens |
+|----------|----------|------|------------|
+| 1 | playground-factory | none | 100,000 |
+| 2 | training-factory | none | 150,000 |
+| 3 | knowledge-mine | training-factory running | 80,000 |
+| 4 | adversary | knowledge-mine running | 50,000 |
+| 5 | codebase-genome | none | 120,000 |
+
+## Usage
+
+```bash
+# Normal run (used by cron)
+./scripts/nightly-pipeline-scheduler.sh
+
+# Dry run (show what would start)
+./scripts/nightly-pipeline-scheduler.sh --dry-run
+
+# Status report
+./scripts/nightly-pipeline-scheduler.sh --status
+
+# Force start during peak hours
+./scripts/nightly-pipeline-scheduler.sh --force
+```
+
+## Configuration
+
+Set via environment variables:
+- `PIPELINE_TOKEN_LIMIT`: Daily token budget (default: 500,000)
+- `PIPELINE_PEAK_START`: Peak hours start (default: 9)
+- `PIPELINE_PEAK_END`: Peak hours end (default: 18)
+- `HERMES_HOME`: Hermes home directory (default: ~/.hermes)
+
+## Cron
+
+Runs every 30 minutes. Off-peak only (unless --force).
+See `cron/pipeline-scheduler.yml`.

scripts/nightly-pipeline-scheduler.sh

@@ -0,0 +1,383 @@
+#!/usr/bin/env bash
+# nightly-pipeline-scheduler.sh — Auto-start batch pipelines when inference is available.
+#
+# Checks provider health, pipeline progress, token budget, and interactive load.
+# Starts the highest-priority incomplete pipeline that can run.
+#
+# Usage:
+#   ./scripts/nightly-pipeline-scheduler.sh          # Normal run
+#   ./scripts/nightly-pipeline-scheduler.sh --dry-run # Show what would start
+#   ./scripts/nightly-pipeline-scheduler.sh --status  # Pipeline status report
+
+set -euo pipefail
+
+# --- Configuration ---
+HERMES_HOME="${HERMES_HOME:-$HOME/.hermes}"
+BUDGET_FILE="${HERMES_HOME}/pipeline_budget.json"
+STATE_FILE="${HERMES_HOME}/pipeline_state.json"
+LOG_FILE="${HERMES_HOME}/logs/pipeline-scheduler.log"
+TOKEN_DAILY_LIMIT="${PIPELINE_TOKEN_LIMIT:-500000}"
+PEAK_HOURS_START="${PIPELINE_PEAK_START:-9}"
+PEAK_HOURS_END="${PIPELINE_PEAK_END:-18}"
+
+# Pipeline definitions (priority order)
+# Each pipeline: name, script, max_tokens, dependencies
+PIPELINES=(
+    "playground-factory|scripts/pipeline_playground_factory.sh|100000|none"
+    "training-factory|scripts/pipeline_training_factory.sh|150000|none"
+    "knowledge-mine|scripts/pipeline_knowledge_mine.sh|80000|training-factory"
+    "adversary|scripts/pipeline_adversary.sh|50000|knowledge-mine"
+    "codebase-genome|scripts/pipeline_codebase_genome.sh|120000|none"
+)
+
+# --- Colors ---
+RED='\033[0;31m'
+GREEN='\033[0;32m'
+YELLOW='\033[0;33m'
+CYAN='\033[0;36m'
+NC='\033[0m'
+
+# --- Helpers ---
+now_hour() { date +%-H; }
+is_peak_hours() {
+    local h=$(now_hour)
+    [[ $h -ge $PEAK_HOURS_START && $h -lt $PEAK_HOURS_END ]]
+}
+
+ensure_dirs() {
+    mkdir -p "$(dirname "$LOG_FILE")" "$(dirname "$BUDGET_FILE")" "$(dirname "$STATE_FILE")"
+}
+
+log() { echo "[$(date '+%Y-%m-%d %H:%M:%S')] $*" | tee -a "$LOG_FILE"; }
+
+get_budget_used_today() {
+    if [[ -f "$BUDGET_FILE" ]]; then
+        local today=$(date +%Y-%m-%d)
+        python3 -c "
+import json, sys
+with open('$BUDGET_FILE') as f:
+    d = json.load(f)
+print(d.get('daily', {}).get('$today', {}).get('tokens_used', 0))
+" 2>/dev/null || echo 0
+    else
+        echo 0
+    fi
+}
+
+get_budget_remaining() {
+    local used=$(get_budget_used_today)
+    echo $((TOKEN_DAILY_LIMIT - used))
+}
+
+update_budget() {
+    local pipeline="$1"
+    local tokens="$2"
+    local today=$(date +%Y-%m-%d)
+    python3 -c "
+import json, os
+path = '$BUDGET_FILE'
+d = {}
+if os.path.exists(path):
+    with open(path) as f:
+        d = json.load(f)
+daily = d.setdefault('daily', {})
+day = daily.setdefault('$today', {'tokens_used': 0, 'pipelines': {}})
+day['tokens_used'] = day.get('tokens_used', 0) + $tokens
+day['pipelines']['$pipeline'] = day['pipelines'].get('$pipeline', 0) + $tokens
+with open(path, 'w') as f:
+    json.dump(d, f, indent=2)
+"
+}
+
+get_pipeline_state() {
+    if [[ -f "$STATE_FILE" ]]; then
+        cat "$STATE_FILE"
+    else
+        echo "{}"
+    fi
+}
+
+set_pipeline_state() {
+    local pipeline="$1"
+    local state="$2"  # running, complete, failed, skipped
+    python3 -c "
+import json, os
+path = '$STATE_FILE'
+d = {}
+if os.path.exists(path):
+    with open(path) as f:
+        d = json.load(f)
+d['$pipeline'] = {'state': '$state', 'updated': '$(date -Iseconds)'}
+with open(path, 'w') as f:
+    json.dump(d, f, indent=2)
+"
+}
+
+is_pipeline_complete() {
+    local pipeline="$1"
+    python3 -c "
+import json, os
+path = '$STATE_FILE'
+if not os.path.exists(path):
+    print('false')
+else:
+    with open(path) as f:
+        d = json.load(f)
+    state = d.get('$pipeline', {}).get('state', 'not_started')
+    print('true' if state == 'complete' else 'false')
+" 2>/dev/null || echo false
+}
+
+is_pipeline_running() {
+    local pipeline="$1"
+    python3 -c "
+import json, os
+path = '$STATE_FILE'
+if not os.path.exists(path):
+    print('false')
+else:
+    with open(path) as f:
+        d = json.load(f)
+    state = d.get('$pipeline', {}).get('state', 'not_started')
+    print('true' if state == 'running' else 'false')
+" 2>/dev/null || echo false
+}
+
+check_dependency() {
+    local dep="$1"
+    if [[ "$dep" == "none" ]]; then
+        return 0
+    fi
+    # For knowledge-mine: training-factory must be running or complete
+    if [[ "$dep" == "training-factory" ]]; then
+        local state=$(python3 -c "
+import json, os
+path = '$STATE_FILE'
+if not os.path.exists(path):
+    print('not_started')
+else:
+    with open(path) as f:
+        d = json.load(f)
+    print(d.get('training-factory', {}).get('state', 'not_started'))
+" 2>/dev/null || echo "not_started")
+        [[ "$state" == "running" || "$state" == "complete" ]]
+        return $?
+    fi
+    # For adversary: knowledge-mine must be at least 50% done
+    # Simplified: check if it's running (we'd need progress tracking for 50%)
+    if [[ "$dep" == "knowledge-mine" ]]; then
+        local state=$(python3 -c "
+import json, os
+path = '$STATE_FILE'
+if not os.path.exists(path):
+    print('not_started')
+else:
+    with open(path) as f:
+        d = json.load(f)
+    print(d.get('knowledge-mine', {}).get('state', 'not_started'))
+" 2>/dev/null || echo "not_started")
+        [[ "$state" == "running" || "$state" == "complete" ]]
+        return $?
+    fi
+    return 0
+}
+
+check_inference_available() {
+    # Check if any inference provider is responding
+    # 1. Check OpenRouter
+    local or_ok=$(curl -s -o /dev/null -w "%{http_code}" \
+        --connect-timeout 5 "https://openrouter.ai/api/v1/models" 2>/dev/null || echo "000")
+
+    # 2. Check local Ollama
+    local ollama_ok=$(curl -s -o /dev/null -w "%{http_code}" \
+        --connect-timeout 5 "http://localhost:11434/api/tags" 2>/dev/null || echo "000")
+
+    # 3. Check RunPod (if configured)
+    local runpod_ok="000"
+    if [[ -n "${RUNPOD_ENDPOINT:-}" ]]; then
+        runpod_ok=$(curl -s -o /dev/null -w "%{http_code}" \
+            --connect-timeout 5 "$RUNPOD_ENDPOINT/health" 2>/dev/null || echo "000")
+    fi
+
+    if [[ "$or_ok" == "200" || "$ollama_ok" == "200" || "$runpod_ok" == "200" ]]; then
+        return 0
+    fi
+    return 1
+}
+
+check_interactive_load() {
+    # Check if there are active interactive sessions (don't fight with live users)
+    # Look for tmux panes with active hermes sessions
+    local active=$(tmux list-panes -a -F '#{pane_pid} #{pane_current_command}' 2>/dev/null \
+        | grep -c "hermes\|python3" || echo 0)
+
+    # If more than 3 interactive sessions, skip pipeline start
+    if [[ $active -gt 3 ]]; then
+        return 1
+    fi
+    return 0
+}
+
+start_pipeline() {
+    local name="$1"
+    local script="$2"
+    local max_tokens="$3"
+    local budget_remaining="$4"
+    local mode="${5:-run}"
+
+    if [[ "$budget_remaining" -lt "$max_tokens" ]]; then
+        log "SKIP $name: insufficient budget ($budget_remaining < $max_tokens tokens)"
+        return 1
+    fi
+
+    if [[ ! -f "$script" ]]; then
+        log "SKIP $name: script not found ($script)"
+        return 1
+    fi
+
+    if [[ "$mode" == "dry-run" ]]; then
+        log "DRY-RUN: Would start $name (budget: $budget_remaining, needs: $max_tokens)"
+        return 0
+    fi
+
+    log "START $name (budget: $budget_remaining, max_tokens: $max_tokens)"
+    set_pipeline_state "$name" "running"
+
+    # Run in background, capture output
+    local log_path="${HERMES_HOME}/logs/pipeline-${name}.log"
+    bash "$script" --max-tokens "$max_tokens" >> "$log_path" 2>&1 &
+    local pid=$!
+
+    # Wait a moment to check if it started OK
+    sleep 2
+    if kill -0 $pid 2>/dev/null; then
+        log "RUNNING $name (PID: $pid, log: $log_path)"
+        # Record the PID
+        python3 -c "
+import json, os
+path = '$STATE_FILE'
+d = {}
+if os.path.exists(path):
+    with open(path) as f:
+        d = json.load(f)
+d['$name']['pid'] = $pid
+with open(path, 'w') as f:
+    json.dump(d, f, indent=2)
+"
+        return 0
+    else
+        log "FAIL $name: script exited immediately"
+        set_pipeline_state "$name" "failed"
+        return 1
+    fi
+}
+
+# --- Main ---
+main() {
+    local mode="${1:-run}"
+    ensure_dirs
+
+    log "=== Pipeline Scheduler ($mode) ==="
+
+    # Check 1: Is inference available?
+    if ! check_inference_available; then
+        log "No inference provider available. Skipping all pipelines."
+        exit 0
+    fi
+    log "Inference: AVAILABLE"
+
+    # Check 2: Is it peak hours?
+    if is_peak_hours && [[ "$mode" != "--force" ]]; then
+        local h=$(now_hour)
+        log "Peak hours ($h:00). Skipping pipeline start. Use --force to override."
+        exit 0
+    fi
+    log "Off-peak: OK"
+
+    # Check 3: Interactive load
+    if ! check_interactive_load && [[ "$mode" != "--force" ]]; then
+        log "High interactive load. Skipping pipeline start."
+        exit 0
+    fi
+    log "Interactive load: OK"
+
+    # Check 4: Token budget
+    local budget=$(get_budget_remaining)
+    log "Token budget remaining: $budget / $TOKEN_DAILY_LIMIT"
+
+    if [[ $budget -le 0 ]]; then
+        log "Daily token budget exhausted. Stopping."
+        exit 0
+    fi
+
+    # Check 5: Pipeline status
+    if [[ "$mode" == "--status" ]]; then
+        echo -e "${CYAN}Pipeline Status:${NC}"
+        echo "────────────────────────────────────────────────────"
+        for entry in "${PIPELINES[@]}"; do
+            IFS='|' read -r name script max_tokens dep <<< "$entry"
+            local state=$(python3 -c "
+import json, os
+path = '$STATE_FILE'
+if not os.path.exists(path):
+    print('not_started')
+else:
+    with open(path) as f:
+        d = json.load(f)
+    print(d.get('$name', {}).get('state', 'not_started'))
+" 2>/dev/null || echo "not_started")
+
+            local color=$NC
+            case "$state" in
+                running)  color=$YELLOW ;;
+                complete) color=$GREEN ;;
+                failed)   color=$RED ;;
+            esac
+            printf "  %-25s %b%s%b (max: %s tokens, dep: %s)\n" "$name" "$color" "$state" "$NC" "$max_tokens" "$dep"
+        done
+        echo "────────────────────────────────────────────────────"
+        echo "  Budget: $budget / $TOKEN_DAILY_LIMIT tokens remaining"
+        echo "  Peak hours: $PEAK_HOURS_START:00 - $PEAK_HOURS_END:00"
+        exit 0
+    fi
+
+    # Find and start the highest-priority incomplete pipeline
+    local started=0
+    for entry in "${PIPELINES[@]}"; do
+        IFS='|' read -r name script max_tokens dep <<< "$entry"
+
+        # Skip if already running or complete
+        if [[ "$(is_pipeline_running $name)" == "true" ]]; then
+            log "SKIP $name: already running"
+            continue
+        fi
+        if [[ "$(is_pipeline_complete $name)" == "true" ]]; then
+            log "SKIP $name: already complete"
+            continue
+        fi
+
+        # Check dependency
+        if ! check_dependency "$dep"; then
+            log "SKIP $name: dependency $dep not met"
+            continue
+        fi
+
+        # Try to start
+        if start_pipeline "$name" "$script" "$max_tokens" "$budget" "$mode"; then
+            started=1
+            # Only start one pipeline per run (let it claim tokens before next check)
+            # Exception: playground-factory and training-factory can run in parallel
+            if [[ "$name" != "playground-factory" && "$name" != "training-factory" ]]; then
+                break
+            fi
+        fi
+    done
+
+    if [[ $started -eq 0 ]]; then
+        log "No pipelines to start (all complete, running, or blocked)."
+    fi
+
+    log "=== Pipeline Scheduler done ==="
+}
+
+main "$@"

scripts/visual_pr_reviewer.py

@@ -1,3 +1,4 @@
+#!/usr/bin/env python3
 import json
 from hermes_tools import browser_navigate, browser_vision