Verbose per-call LLM logging, raw request/response dumps, and end-of-log cost summary.

- [LLM] line per call: stage, model, prompt size, output size, cost, parsed item counts
- LLM_RAW_DUMP: full prompt/response JSON per call under outputs/<job>/llm_raw/
- Cost block at tail of job.log (per-stage, per-model, cached vs live)
- Agent mode: reset llm cost counters per job; review finalization now teed into job.log + dumps

backend/main.py

@@ -20,7 +20,7 @@ from fastapi.responses import HTMLResponse, JSONResponse, Response
 from fastapi.staticfiles import StaticFiles
 
 import backend.jobs
-from backend import config
+from backend import config, llm
 from backend.jobs import PIPELINE_MODES, create_job, get_job, _set
 from backend.pipeline.pdf_processor import render_page_jpeg
 from backend.review.feedback import decision_to_label, write_label
@@ -186,7 +186,20 @@ def save_review_decisions(job_id: str, payload: dict):
 def _finalize_job(job_id: str, out_dir: str) -> None:
     """Background finalization: the ONE place the final report email may fire."""
     try:
-        report = finalize_review(job_id, out_dir)
+        # Re-open the job's log tee + raw dump dir so the finalization LLM
+        # calls (clarification reruns, RFI drafting) land in job.log / llm_raw.
+        with backend.jobs.capture_job_output(job_id, out_dir):
+            print("\n=== Review finalization ===")
+            llm.reset_cost()  # finalization-only cost attribution
+            report = finalize_review(job_id, out_dir)
+            cost = llm.get_cost()
+            backend.jobs._log_cost_summary({
+                "cost_usd": round(cost["usd"], 4),
+                "llm_calls": cost["calls"],
+                "cached_calls": cost.get("cached", 0),
+                "cost_by_stage": cost.get("by_stage", {}),
+                "models_used": cost.get("models", {}),
+            }, label="finalization")
     except Exception as e:
         try:
             _set(job_id, status="finalization_error", error=str(e),