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.

backend/llm.py

@@ -23,16 +23,13 @@ _clients: Dict[str, OpenAI] = {}
 # call_json when routing a no-image (text) call. Module-global mirrors the
 # set_stage/cost pattern (single-user tool).
 _text_local = False
-
-# Per-job model override (user picked a model in the UI). Same module-global
+# Per-job model overrides (user picked models in the UI). Same module-global
 # pattern: set by the job runner before the pipeline starts, cleared after.
-_model_override: Optional[str] = None
-
-
-def set_model_override(model: Optional[str]) -> None:
-    """Override the model for all OpenRouter calls (vision + text), or None to clear."""
-    global _model_override
-    _model_override = (model or "").strip() or None
+# Vision applies to image calls, text to no-image calls on OpenRouter (and to
+# the local->cloud fallback). The LOCAL endpoint's model name is never taken
+# from these overrides - hybrid local keeps LOCAL_TEXT_MODEL.
+_vision_model_override: Optional[str] = None
+_text_model_override: Optional[str] = None
 
 
 def set_text_backend(local: bool) -> None:
@@ -40,6 +37,13 @@ def set_text_backend(local: bool) -> None:
     global _text_local
     _text_local = bool(local)
 
+
+def set_model_overrides(vision: Optional[str] = None, text: Optional[str] = None) -> None:
+    """Per-run OpenRouter vision/text model picks. None/blank clears to defaults."""
+    global _vision_model_override, _text_model_override
+    _vision_model_override = (vision or "").strip() or None
+    _text_model_override = (text or "").strip() or None
+
 # --- per-job cost accounting -------------------------------------------------
 # OpenRouter returns the real USD cost of each call when we request usage
 # accounting. We accumulate it in a module-level counter; the runner resets it
@@ -177,17 +181,22 @@ def _resolve_backend(has_images: bool, model_override: Optional[str]) -> Dict[st
         return {
             "base_url": config.LOCAL_BASE_URL,
             "api_key": config.LOCAL_API_KEY,
+            # Local model name comes from per-call args or LOCAL_TEXT_MODEL —
+            # never the UI's OpenRouter picks, which a local server won't serve.
             "model": model_override or config.LOCAL_TEXT_MODEL or config.TEXT_MODEL,
             "usage": False,          # local has no OpenRouter usage accounting
             "local": True,
         }
     # Vision, or text-on-OpenRouter (default / fallback). A per-job override
     # (user's UI model pick) wins over per-call and env defaults.
-    default_model = config.MODEL if has_images else config.TEXT_MODEL
+    if has_images:
+        model = _vision_model_override or model_override or config.MODEL
+    else:
+        model = _text_model_override or model_override or config.TEXT_MODEL
     return {
         "base_url": config.AI_BASE_URL,
         "api_key": config.AI_API_KEY,
-        "model": _model_override or model_override or default_model,
+        "model": model,
         "usage": True,
         "local": False,
     }
@@ -362,7 +371,8 @@ def call_json(
                     _models["text_local"].add(be["model"])
                     _models["fallback_count"] += 1
                 be = {"base_url": config.AI_BASE_URL, "api_key": config.AI_API_KEY,
-                      "model": config.TEXT_MODEL, "usage": True, "local": False}
+                      "model": _text_model_override or config.TEXT_MODEL,
+                      "usage": True, "local": False}
                 cache_key = None       # don't cache fallback under the local-model key
                 fell_back = True
                 continue