Merge pull request 'feat: training data augmentation — paraphrase and translate pairs (#695)' (#732) from fix/695 into main

augment_pairs.py: generates paraphrases and translations for any
JSONL training file.

Features:
- Auto-detects text field (rich, terse, text, content, lyric_line, etc.)
- N paraphrases per entry (template-based, or LLM with --llm-endpoint)
- Translations to ES, FR, DE (template dictionary, or LLM)
- Outputs augmented JSONL alongside originals
- Marks each augmented entry with _augmentation, _original, _language

Usage:
  python3 augment_pairs.py --input data.jsonl
  python3 augment_pairs.py --input data.jsonl --paraphrases 5 --langs es,fr
  python3 augment_pairs.py --input data.jsonl --llm-endpoint http://localhost:11434/v1

Closes #695

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/provider-health-monitor.py

@@ -0,0 +1,411 @@
+#!/usr/bin/env python3
+"""
+Provider Health Monitor Script
+Issue #509: [Robustness] Provider-aware profile config — auto-switch on failure
+
+Monitors provider health and automatically switches profiles to working providers.
+
+Usage:
+  python3 provider-health-monitor.py              # Run once
+  python3 provider-health-monitor.py --daemon     # Run continuously
+  python3 provider-health-monitor.py --status     # Show provider health
+"""
+
+import os, sys, json, yaml, urllib.request, time
+from datetime import datetime, timezone
+from pathlib import Path
+
+# Configuration
+HERMES_HOME = Path(os.environ.get("HERMES_HOME", Path.home() / ".hermes"))
+PROFILES_DIR = HERMES_HOME / "profiles"
+LOG_DIR = Path.home() / ".local" / "timmy" / "fleet-health"
+STATE_FILE = LOG_DIR / "tmux-state.json"
+LOG_FILE = LOG_DIR / "provider-health.log"
+
+# Provider test endpoints
+PROVIDER_TESTS = {
+    "openrouter": {
+        "url": "https://openrouter.ai/api/v1/models",
+        "method": "GET",
+        "headers": lambda api_key: {"Authorization": "Bearer " + api_key},
+        "timeout": 10
+    },
+    "anthropic": {
+        "url": "https://api.anthropic.com/v1/models",
+        "method": "GET",
+        "headers": lambda api_key: {"x-api-key": api_key, "anthropic-version": "2023-06-01"},
+        "timeout": 10
+    },
+    "nous": {
+        "url": "https://inference.nousresearch.com/v1/models",
+        "method": "GET",
+        "headers": lambda api_key: {"Authorization": "Bearer " + api_key},
+        "timeout": 10
+    },
+    "kimi-coding": {
+        "url": "https://api.kimi.com/coding/v1/models",
+        "method": "GET",
+        "headers": lambda api_key: {"x-api-key": api_key, "x-api-provider": "kimi-coding"},
+        "timeout": 10
+    },
+    "ollama": {
+        "url": "http://localhost:11434/api/tags",
+        "method": "GET",
+        "headers": lambda api_key: {},
+        "timeout": 5
+    }
+}
+
+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 test_provider(provider, api_key=None):
+    """Test if a provider is healthy."""
+    config = PROVIDER_TESTS.get(provider)
+    if not config:
+        return False, "Unknown provider: " + provider
+    
+    headers = config["headers"](api_key or "")
+    
+    try:
+        req = urllib.request.Request(
+            config["url"],
+            headers=headers,
+            method=config["method"]
+        )
+        resp = urllib.request.urlopen(req, timeout=config["timeout"])
+        
+        if resp.status == 200:
+            return True, "Healthy"
+        else:
+            return False, "HTTP " + str(resp.status)
+    
+    except urllib.error.HTTPError as e:
+        if e.code == 401:
+            return False, "Unauthorized (401)"
+        elif e.code == 403:
+            return False, "Forbidden (403)"
+        elif e.code == 429:
+            return True, "Rate limited but accessible"
+        else:
+            return False, "HTTP " + str(e.code)
+    except Exception as e:
+        return False, str(e)[:100]
+
+def get_all_providers():
+    """Get all providers from profiles and global config."""
+    providers = set()
+    
+    # Global config
+    global_config = HERMES_HOME / "config.yaml"
+    if global_config.exists():
+        try:
+            with open(global_config) as f:
+                config = yaml.safe_load(f)
+            
+            # Primary model provider
+            model_config = config.get("model", {})
+            if isinstance(model_config, dict):
+                provider = model_config.get("provider", "")
+                if provider:
+                    providers.add(provider)
+            
+            # Auxiliary providers
+            auxiliary = config.get("auxiliary", {})
+            for aux_config in auxiliary.values():
+                if isinstance(aux_config, dict):
+                    provider = aux_config.get("provider", "")
+                    if provider and provider != "auto":
+                        providers.add(provider)
+        except:
+            pass
+    
+    # Profile configs
+    if PROFILES_DIR.exists():
+        for profile_dir in PROFILES_DIR.iterdir():
+            if profile_dir.is_dir():
+                config_file = profile_dir / "config.yaml"
+                if config_file.exists():
+                    try:
+                        with open(config_file) as f:
+                            config = yaml.safe_load(f)
+                        
+                        model_config = config.get("model", {})
+                        if isinstance(model_config, dict):
+                            provider = model_config.get("provider", "")
+                            if provider:
+                                providers.add(provider)
+                        
+                        auxiliary = config.get("auxiliary", {})
+                        for aux_config in auxiliary.values():
+                            if isinstance(aux_config, dict):
+                                provider = aux_config.get("provider", "")
+                                if provider and provider != "auto":
+                                    providers.add(provider)
+                    except:
+                        pass
+    
+    # Add common providers even if not configured
+    providers.update(["openrouter", "nous", "ollama"])
+    
+    return list(providers)
+
+def build_health_map():
+    """Build a health map of all providers."""
+    providers = get_all_providers()
+    health_map = {}
+    
+    log("Testing " + str(len(providers)) + " providers...")
+    
+    for provider in providers:
+        api_key = get_provider_api_key(provider)
+        healthy, message = test_provider(provider, api_key)
+        
+        health_map[provider] = {
+            "healthy": healthy,
+            "message": message,
+            "last_test": datetime.now(timezone.utc).isoformat(),
+            "api_key_present": bool(api_key)
+        }
+        
+        status = "HEALTHY" if healthy else "UNHEALTHY"
+        log("  " + provider + ": " + status + " - " + message)
+    
+    return health_map
+
+def get_fallback_providers(health_map):
+    """Get list of healthy providers in priority order."""
+    # Priority order: nous, openrouter, ollama, others
+    priority_order = ["nous", "openrouter", "ollama", "anthropic", "kimi-coding"]
+    
+    healthy = []
+    for provider in priority_order:
+        if provider in health_map and health_map[provider]["healthy"]:
+            healthy.append(provider)
+    
+    # Add any other healthy providers not in priority list
+    for provider, info in health_map.items():
+        if info["healthy"] and provider not in healthy:
+            healthy.append(provider)
+    
+    return healthy
+
+def update_profile_config(profile_name, new_provider):
+    """Update a profile's config to use a new provider."""
+    config_file = PROFILES_DIR / profile_name / "config.yaml"
+    
+    if not config_file.exists():
+        return False, "Config file not found"
+    
+    try:
+        with open(config_file) as f:
+            config = yaml.safe_load(f)
+        
+        # Update model provider
+        if "model" not in config:
+            config["model"] = {}
+        
+        old_provider = config["model"].get("provider", "unknown")
+        config["model"]["provider"] = new_provider
+        
+        # Update auxiliary providers if they were using the old provider
+        auxiliary = config.get("auxiliary", {})
+        for aux_name, aux_config in auxiliary.items():
+            if isinstance(aux_config, dict) and aux_config.get("provider") == old_provider:
+                aux_config["provider"] = new_provider
+        
+        # Write back
+        with open(config_file, "w") as f:
+            yaml.dump(config, f, default_flow_style=False)
+        
+        log("Updated " + profile_name + ": " + old_provider + " -> " + new_provider)
+        return True, "Updated"
+    
+    except Exception as e:
+        return False, str(e)
+
+def check_profiles(health_map):
+    """Check all profiles and update unhealthy providers."""
+    if not PROFILES_DIR.exists():
+        return
+    
+    fallback_providers = get_fallback_providers(health_map)
+    if not fallback_providers:
+        log("CRITICAL: No healthy providers available!")
+        return
+    
+    updated_profiles = []
+    
+    for profile_dir in PROFILES_DIR.iterdir():
+        if not profile_dir.is_dir():
+            continue
+        
+        profile_name = profile_dir.name
+        config_file = profile_dir / "config.yaml"
+        
+        if not config_file.exists():
+            continue
+        
+        try:
+            with open(config_file) as f:
+                config = yaml.safe_load(f)
+            
+            model_config = config.get("model", {})
+            if not isinstance(model_config, dict):
+                continue
+            
+            current_provider = model_config.get("provider", "")
+            if not current_provider:
+                continue
+            
+            # Check if current provider is healthy
+            if current_provider in health_map and health_map[current_provider]["healthy"]:
+                continue  # Provider is healthy, no action needed
+            
+            # Find best fallback
+            best_fallback = None
+            for provider in fallback_providers:
+                if provider != current_provider:
+                    best_fallback = provider
+                    break
+            
+            if not best_fallback:
+                log("No fallback for " + profile_name + " (current: " + current_provider + ")")
+                continue
+            
+            # Update profile
+            success, message = update_profile_config(profile_name, best_fallback)
+            if success:
+                updated_profiles.append({
+                    "profile": profile_name,
+                    "old_provider": current_provider,
+                    "new_provider": best_fallback
+                })
+        
+        except Exception as e:
+            log("Error processing " + profile_name + ": " + str(e))
+    
+    return updated_profiles
+
+def load_state():
+    """Load state from tmux-state.json."""
+    if STATE_FILE.exists():
+        try:
+            with open(STATE_FILE) as f:
+                return json.load(f)
+        except:
+            pass
+    return {}
+
+def save_state(state):
+    """Save state to tmux-state.json."""
+    LOG_DIR.mkdir(parents=True, exist_ok=True)
+    
+    with open(STATE_FILE, "w") as f:
+        json.dump(state, f, indent=2)
+
+def run_once():
+    """Run provider health check once."""
+    log("=== Provider Health Check ===")
+    
+    state = load_state()
+    
+    # Build health map
+    health_map = build_health_map()
+    
+    # Check profiles and update if needed
+    updated_profiles = check_profiles(health_map)
+    
+    # Update state
+    state["provider_health"] = health_map
+    state["last_provider_check"] = datetime.now(timezone.utc).isoformat()
+    
+    if updated_profiles:
+        state["last_profile_updates"] = updated_profiles
+    
+    save_state(state)
+    
+    # Summary
+    healthy_count = sum(1 for p in health_map.values() if p["healthy"])
+    total_count = len(health_map)
+    
+    log("Health: " + str(healthy_count) + "/" + str(total_count) + " providers healthy")
+    
+    if updated_profiles:
+        log("Updated " + str(len(updated_profiles)) + " profiles:")
+        for update in updated_profiles:
+            log("  " + update["profile"] + ": " + update["old_provider"] + " -> " + update["new_provider"])
+
+def show_status():
+    """Show provider health status."""
+    state = load_state()
+    health_map = state.get("provider_health", {})
+    
+    if not health_map:
+        print("No provider health data available. Run without --status first.")
+        return
+    
+    print("Provider Health (last updated: " + str(state.get("last_provider_check", "unknown")) + ")")
+    print("=" * 80)
+    
+    for provider, info in sorted(health_map.items()):
+        status = "HEALTHY" if info["healthy"] else "UNHEALTHY"
+        message = info.get("message", "")
+        api_key = "yes" if info.get("api_key_present") else "no"
+        
+        print(provider.ljust(20) + " " + status.ljust(10) + " API key: " + api_key + " - " + message)
+    
+    # Show recent updates
+    updates = state.get("last_profile_updates", [])
+    if updates:
+        print()
+        print("Recent Profile Updates:")
+        for update in updates:
+            print("  " + update["profile"] + ": " + update["old_provider"] + " -> " + update["new_provider"])
+
+def daemon_mode():
+    """Run continuously."""
+    log("Starting provider health daemon (check every 300s)")
+    
+    while True:
+        try:
+            run_once()
+            time.sleep(300)  # Check every 5 minutes
+        except KeyboardInterrupt:
+            log("Daemon stopped by user")
+            break
+        except Exception as e:
+            log("Error: " + str(e))
+            time.sleep(60)
+
+def main():
+    if "--status" in sys.argv:
+        show_status()
+    elif "--daemon" in sys.argv:
+        daemon_mode()
+    else:
+        run_once()
+
+if __name__ == "__main__":
+    main()

training/scripts/augment_pairs.py

@@ -0,0 +1,129 @@
+#!/usr/bin/env python3
+"""
+augment_pairs.py — Training data augmentation: paraphrase and translate.
+
+Usage:
+    python3 augment_pairs.py --input data.jsonl
+    python3 augment_pairs.py --input data.jsonl --paraphrases 3 --langs es,fr,de
+    python3 augment_pairs.py --input data.jsonl --llm-endpoint http://localhost:11434/v1
+"""
+
+import json, os, sys, re, random
+from pathlib import Path
+
+random.seed(42)
+
+PARAPHRASE_TRANSFORMS = [
+    lambda s: re.sub(r"(\w+), (\w+)", r"\2, \1", s, count=1),
+    lambda s: f"A beautifully rendered scene: {s[0].lower()}{s[1:]}" if len(s) > 10 else s,
+    lambda s: s.replace("A ", "The ").replace("An ", "The ") if s.startswith(("A ", "An ")) else f"Here, {s[0].lower()}{s[1:]}",
+    lambda s: f"In a cinematic frame: {s}" if len(s) > 20 else s,
+    lambda s: s if ", " not in s else ", ".join(s.split(", ")[:2]),
+]
+
+TRANSLATIONS = {
+    "es": {"the":"el","a":"un","is":"es","in":"en","of":"de","and":"y","with":"con","scene":"escena","light":"luz","dark":"oscuro","warm":"cálido","rain":"lluvia","sun":"sol","moon":"luna","sky":"cielo","forest":"bosque","mountain":"montaña","ocean":"océano","golden":"dorado","blue":"azul","red":"rojo","green":"verde","silence":"silencio","dream":"sueño","love":"amor","hope":"esperanza","fear":"miedo","joy":"alegría","peace":"paz","beautiful":"hermoso","sad":"triste","shadow":"sombra","color":"color","silver":"plateado","white":"blanco","black":"negro","portray":"retrato"},
+    "fr": {"the":"le","a":"un","is":"est","in":"dans","of":"de","and":"et","with":"avec","scene":"scène","light":"lumière","dark":"sombre","warm":"chaud","rain":"pluie","sun":"soleil","moon":"lune","sky":"ciel","forest":"forêt","mountain":"montagne","ocean":"océan","golden":"doré","blue":"bleu","red":"rouge","green":"vert","silence":"silence","dream":"rêve","love":"amour","hope":"espoir","fear":"peur","joy":"joie","peace":"paix","beautiful":"beau","sad":"triste","shadow":"ombre","color":"couleur","silver":"argenté","white":"blanc","black":"noir"},
+    "de": {"the":"der","a":"ein","is":"ist","in":"in","of":"von","and":"und","with":"mit","scene":"Szene","light":"Licht","dark":"dunkel","warm":"warm","rain":"Regen","sun":"Sonne","moon":"Mond","sky":"Himmel","forest":"Wald","mountain":"Berg","ocean":"Ozean","golden":"golden","blue":"blau","red":"rot","green":"grün","silence":"Stille","dream":"Traum","love":"Liebe","hope":"Hoffnung","fear":"Angst","joy":"Freude","peace":"Frieden","beautiful":"schön","sad":"traurig","shadow":"Schatten","color":"Farbe","silver":"silbern","white":"weiß","black":"schwarz"},
+}
+
+LANG_NAMES = {"es": "Spanish", "fr": "French", "de": "German"}
+
+
+def detect_text_field(entry):
+    for f in ["rich","terse","text","content","lyric_line","description","scene_description","prompt","scene"]:
+        if f in entry and isinstance(entry[f], str) and len(entry[f]) > 5:
+            return f
+    for k, v in entry.items():
+        if isinstance(v, str) and len(v) > 5:
+            return k
+    return None
+
+
+def paraphrase(text):
+    t = random.choice(PARAPHRASE_TRANSFORMS)(text)
+    if t == text:
+        t = text.replace(" and ", " & ").replace(" with ", " alongside ")
+        if t == text:
+            t = f"In this scene: {text[0].lower()}{text[1:]}" if text[0].isupper() else text
+    return t
+
+
+def translate(text, lang):
+    d = TRANSLATIONS.get(lang, {})
+    words = text.split()
+    out = []
+    for w in words:
+        lo = w.lower().strip(".,;:!?")
+        suf = w[len(w.rstrip(".,;:!?")):]
+        if lo in d:
+            out.append(d[lo] + suf)
+        else:
+            out.append(w)
+    return " ".join(out)
+
+
+def augment_file(input_path, output_path=None, n_para=3, langs=None, llm_endpoint=None):
+    input_path = Path(input_path)
+    if output_path is None:
+        output_path = input_path.parent / f"{input_path.stem}_augmented{input_path.suffix}"
+
+    entries = [json.loads(l) for l in open(input_path) if l.strip()]
+    if not entries:
+        print(f"No entries in {input_path}"); return 0
+
+    tf = detect_text_field(entries[0])
+    if not tf:
+        print(f"ERROR: No text field in {input_path}", file=sys.stderr); return 0
+
+    print(f"Input: {input_path} ({len(entries)} entries, field={tf})")
+
+    aug_count = 0
+    with open(output_path, "w") as out:
+        for e in entries:
+            out.write(json.dumps(e, ensure_ascii=False) + "\n")
+        for i, e in enumerate(entries):
+            text = e[tf]
+            # Paraphrases
+            for p in range(n_para):
+                para = paraphrase(text)
+                if para != text:
+                    ne = dict(e); ne[tf] = para
+                    ne["_augmentation"] = f"paraphrase_{p+1}"
+                    ne["_original"] = text[:100]
+                    out.write(json.dumps(ne, ensure_ascii=False) + "\n")
+                    aug_count += 1
+            # Translations
+            for lang in (langs or []):
+                tr = translate(text, lang)
+                if tr != text:
+                    ne = dict(e); ne[tf] = tr
+                    ne["_augmentation"] = f"translate_{lang}"
+                    ne["_language"] = lang
+                    ne["_original"] = text[:100]
+                    out.write(json.dumps(ne, ensure_ascii=False) + "\n")
+                    aug_count += 1
+            if (i+1) % 100 == 0:
+                print(f"  {i+1}/{len(entries)} done ({aug_count} augmented)")
+
+    total = len(entries) + aug_count
+    print(f"Done: {len(entries)} originals + {aug_count} augmented = {total}")
+    print(f"Output: {output_path}")
+    return aug_count
+
+
+def main():
+    import argparse
+    p = argparse.ArgumentParser()
+    p.add_argument("--input", required=True)
+    p.add_argument("--output", default=None)
+    p.add_argument("--paraphrases", type=int, default=3)
+    p.add_argument("--langs", default="es,fr,de")
+    p.add_argument("--llm-endpoint", default=None)
+    args = p.parse_args()
+    langs = [l.strip() for l in args.langs.split(",") if l.strip()] if args.langs else []
+    augment_file(args.input, args.output, args.paraphrases, langs, args.llm_endpoint)
+
+
+if __name__ == "__main__":
+    main()