Merge main: dual model dropdowns + richer job logs, adapted for agent-mode.

- llm.py: set_model_overrides(vision, text) replaces the single job override;
  UI picks still beat per-call agent model args, but never name the hybrid
  local model (avoids main's hybrid footgun); local->cloud fallback uses the
  text pick.
- jobs.py: timestamped line-split tee (job_log.py), in-memory log + log_tail
  polls, full log on terminal states (done/error/needs_review/finalization_error),
  log-only disk recovery, error email links to the run log, and failed runs now
  append the full traceback to job.log. Keeps pipeline_mode, job.json, and the
  review gate.
- models.py: vision/text split via architecture modalities, pricing kept;
  /models returns {vision, text, defaults}; /check takes vision_model/text_model
  (replacing model); /health adds text_model. models_catalog.py dropped.
- UI: two priced dropdowns (OpenRouter compute only) + live run-log panel.
- Tests updated for dual overrides and the /models shape; new coverage for
  traceback capture and local-model immunity.

tests/api/test_models_api.py

@@ -11,12 +11,23 @@ _PAYLOAD = {
             "name": "GPT-4o",
             "pricing": {"prompt": "0.0000025", "completion": "0.00001"},
             "context_length": 128000,
+            "architecture": {"input_modalities": ["text", "image"],
+                             "output_modalities": ["text"]},
         },
         {
             "id": "google/gemini-2.5-pro",
             "name": "Gemini 2.5 Pro",
             "pricing": {"prompt": "0.00000125", "completion": "0.00001"},
             "context_length": 1000000,
+            "architecture": {"modality": "text+image->text"},
+        },
+        {
+            "id": "meta-llama/llama-3.1-70b-instruct",
+            "name": "Llama 3.1 70B Instruct",
+            "pricing": {"prompt": "0.0000005", "completion": "0.0000008"},
+            "context_length": 131072,
+            "architecture": {"input_modalities": ["text"],
+                             "output_modalities": ["text"]},
         },
     ]
 }
@@ -34,14 +45,27 @@ def test_models_endpoint_normalizes_pricing(monkeypatch):
     response = client.get("/models")
     assert response.status_code == 200
     body = response.json()
-    assert body["default"] == config.MODEL
-    assert body["default_text"] == config.TEXT_MODEL
-    by_id = {m["id"]: m for m in body["models"]}
+    assert body["defaults"] == {"vision": config.MODEL, "text": config.TEXT_MODEL}
+    by_id = {m["id"]: m for m in body["text"]}
     assert by_id["openai/gpt-4o"]["prompt_usd_per_mtok"] == 2.5
     assert by_id["openai/gpt-4o"]["completion_usd_per_mtok"] == 10.0
     assert by_id["openai/gpt-4o"]["context_length"] == 128000
 
 
+def test_models_endpoint_splits_vision_and_text(monkeypatch):
+    _reset_cache()
+    monkeypatch.setattr(models, "_fetch_openrouter_models", lambda: _PAYLOAD["data"])
+    client = TestClient(app)
+    body = client.get("/models").json()
+    vision_ids = {m["id"] for m in body["vision"]}
+    text_ids = {m["id"] for m in body["text"]}
+    # Both modality shapes (structured and legacy string) are recognized.
+    assert vision_ids == {"openai/gpt-4o", "google/gemini-2.5-pro"}
+    # Text list is the full catalog; vision models appear in both.
+    assert text_ids == {"openai/gpt-4o", "google/gemini-2.5-pro",
+                        "meta-llama/llama-3.1-70b-instruct"}
+
+
 def test_models_endpoint_caches(monkeypatch):
     _reset_cache()
     calls = []