Add per-job run logs and separate vision/text model selection.

Capture pipeline stdout into job.log + API/UI so failed runs can be reviewed, and let users pick OpenRouter vision vs text models independently.

Co-authored-by: Cursor <cursoragent@cursor.com>

backend/models_catalog.py

@@ -0,0 +1,101 @@
+"""
+models_catalog.py - OpenRouter model list for the UI dropdowns.
+
+Fetches https://openrouter.ai/api/v1/models (cached ~1h) and splits into:
+  - vision: accepts image input and returns text
+  - text:   chat models that return text (may also be multimodal)
+"""
+
+import time
+from typing import Any, Dict, List
+
+from backend import config
+
+_TTL_SEC = 3600
+_cache: Dict[str, Any] = {"at": 0.0, "payload": None}
+
+
+def _entry(m: Dict[str, Any]) -> Dict[str, str]:
+    return {
+        "id": m.get("id") or "",
+        "name": m.get("name") or m.get("id") or "",
+    }
+
+
+def _ensure_default(items: List[Dict[str, str]], model_id: str) -> List[Dict[str, str]]:
+    """Prepend the configured default if OpenRouter didn't return it."""
+    if not model_id:
+        return items
+    if any(x["id"] == model_id for x in items):
+        return items
+    return [{"id": model_id, "name": model_id}] + items
+
+
+def _fetch_raw() -> List[Dict[str, Any]]:
+    import httpx  # local import so the app can start without httpx in odd envs
+    headers = {"Accept": "application/json"}
+    if config.AI_API_KEY:
+        headers["Authorization"] = f"Bearer {config.AI_API_KEY}"
+    url = f"{config.AI_BASE_URL.rstrip('/')}/models"
+    # Ask for text-output chat models (includes multimodal). "all" is huge.
+    with httpx.Client(timeout=30.0) as client:
+        r = client.get(url, headers=headers, params={"output_modalities": "text"})
+        r.raise_for_status()
+        data = r.json()
+    return data.get("data") or []
+
+
+def list_models() -> Dict[str, Any]:
+    """Return {vision, text, defaults} for the frontend selects."""
+    now = time.time()
+    if _cache["payload"] and (now - _cache["at"]) < _TTL_SEC:
+        return _cache["payload"]
+
+    try:
+        raw = _fetch_raw()
+    except Exception as e:
+        # Degrade to configured defaults so the UI still works offline.
+        print(f"[Models] OpenRouter catalog fetch failed: {e}")
+        vision = _ensure_default([], config.MODEL)
+        text = _ensure_default([], config.TEXT_MODEL)
+        payload = {
+            "vision": vision,
+            "text": text,
+            "defaults": {"vision": config.MODEL, "text": config.TEXT_MODEL},
+            "error": str(e),
+        }
+        return payload
+
+    vision: List[Dict[str, str]] = []
+    text: List[Dict[str, str]] = []
+    for m in raw:
+        mid = m.get("id") or ""
+        if not mid:
+            continue
+        arch = m.get("architecture") or {}
+        inputs = arch.get("input_modalities") or []
+        outputs = arch.get("output_modalities") or []
+        # Legacy string form: "text+image->text"
+        modality = (arch.get("modality") or "").lower()
+        has_image_in = ("image" in inputs) or ("image" in modality.split("->")[0])
+        has_text_out = ("text" in outputs) or ("->text" in modality) or (not outputs and not modality)
+        has_text_in = ("text" in inputs) or ("text" in modality) or not inputs
+
+        if has_image_in and has_text_out:
+            vision.append(_entry(m))
+        if has_text_in and has_text_out:
+            text.append(_entry(m))
+
+    vision.sort(key=lambda x: x["name"].lower())
+    text.sort(key=lambda x: x["name"].lower())
+    vision = _ensure_default(vision, config.MODEL)
+    text = _ensure_default(text, config.TEXT_MODEL)
+
+    payload = {
+        "vision": vision,
+        "text": text,
+        "defaults": {"vision": config.MODEL, "text": config.TEXT_MODEL},
+    }
+    _cache["at"] = now
+    _cache["payload"] = payload
+    return payload