Add scoped Agent-mode pipeline as experimental Classic fork.

Wire specialist waves, Brain consolidation, and Classic-compatible reports so Agent mode can run end-to-end via OpenRouter without changing the default Classic path.

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

backend/llm.py

@@ -237,18 +237,17 @@ def _repair_truncated(raw: str) -> Optional[Dict[str, Any]]:
         return None
 
 
-def _record_cost(response) -> None:
+def _response_cost(response) -> Optional[float]:
     """Pull OpenRouter's per-call USD cost out of the usage object, if present."""
     try:
         dump = response.model_dump()
     except Exception:
-        return
+        return None
     usage = dump.get("usage") or {}
     cost = usage.get("cost")
     if cost is None:
         cost = (usage.get("cost_details") or {}).get("upstream_inference_cost")
-    if isinstance(cost, (int, float)):
-        _add_cost(float(cost))
+    return float(cost) if isinstance(cost, (int, float)) else None
 
 
 def _parse(raw: str) -> Optional[Dict[str, Any]]:
@@ -268,6 +267,8 @@ def call_json(
     images_b64: Optional[List[str]] = None,
     max_tokens: int = 4096,
     model: Optional[str] = None,
+    usage_tracker: Optional[Any] = None,
+    usage_stage: str = "?",
 ) -> Optional[Dict[str, Any]]:
     """
     Send one chat completion expecting a JSON object back.
@@ -287,6 +288,10 @@ def call_json(
         hit = _cache_get(cache_key)
         if hit is not None:
             _add_cached()
+            if usage_tracker:
+                usage_tracker.record(
+                    usage_stage, be["model"], cached=True, has_images=has_images
+                )
             return hit
 
     content: List[Dict[str, Any]] = []
@@ -314,7 +319,13 @@ def call_json(
             if use_json_mode:
                 kwargs["response_format"] = {"type": "json_object"}
             response = client.chat.completions.create(**kwargs)
-            _record_cost(response)
+            usd = _response_cost(response)
+            if usd is not None:
+                _add_cost(usd)
+            if usage_tracker:
+                usage_tracker.record(
+                    usage_stage, be["model"], usd=usd or 0.0, has_images=has_images
+                )
             raw = _strip_fences(response.choices[0].message.content or "")
             parsed = _parse(raw)
             if parsed is not None: