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/agents/runner.py

@@ -20,6 +20,7 @@ from backend.agents.linker import LinkerAgent, build_link_scopes, build_object_g
 from backend.agents.memory import ProjectMemory
 from backend.agents.orchestrator import Orchestrator
 from backend.agents.rfi_writer import RFIWriterAgent
+from backend.llm import reset_cost
 from backend.pipeline.pdf_processor import convert_pdf_to_images
 from backend.pipeline.report import build_report, to_markdown
 from backend.pipeline.sheet_index import derive_project_meta_from_cover
@@ -39,6 +40,10 @@ def run_agent_pipeline(
     if not os.path.isfile(pdf_path):
         raise FileNotFoundError(pdf_path)
 
+    # Keep the llm module's counters job-local (matches Classic): the job
+    # log's failure-path cost estimate in jobs.py reads llm.get_cost().
+    reset_cost()
+
     agent_dir = os.path.join(out_dir, "agent") if out_dir else None
     memory = ProjectMemory(artifact_dir=agent_dir)
     orchestrator = Orchestrator(memory=memory, on_stage=on_stage)