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/jobs.py

@@ -21,7 +21,8 @@ import traceback
 import uuid
 import shutil
 import threading
-from typing import Dict, List, Optional
+from contextlib import contextmanager
+from typing import Dict, Iterator, List, Optional
 
 from backend import config
 from backend import llm
@@ -139,6 +140,12 @@ def _run(
             _append_log(job_id, f"[Jobs] Job {job_id} failed: {e}", log_path)
             for ln in traceback.format_exc().rstrip().splitlines():
                 _append_log(job_id, ln, log_path)
+            # Cost-so-far for the failed run (counters are reset per job).
+            cost = llm.get_cost()
+            _append_log(job_id,
+                        f"[Jobs] Estimated LLM cost before failure: "
+                        f"${cost['usd']:.4f} over {cost['calls']} live calls "
+                        f"({cost.get('cached', 0)} cached)", log_path)
         except Exception:
             pass
         print(f"[Jobs] Job {job_id} failed: {e}")
@@ -170,6 +177,9 @@ def _run_pipeline(job_id: str, pdf_path: str, out_dir: str,
         }, f, indent=2)
     # Keep a copy of the source PDF so its sheets can be viewed later.
     shutil.copy2(pdf_path, os.path.join(out_dir, "source.pdf"))
+    # Raw per-call LLM request/response dumps land in <out_dir>/llm_raw/.
+    if config.LLM_RAW_DUMP:
+        llm.set_raw_dump_dir(os.path.join(out_dir, "llm_raw"))
     runner = run_agent_pipeline if pipeline_mode == "agent" else run_pipeline
     runner_kwargs = {
         "out_dir": out_dir,
@@ -192,9 +202,11 @@ def _run_pipeline(job_id: str, pdf_path: str, out_dir: str,
     try:
         report = runner(pdf_path, **runner_kwargs)
     finally:
+        llm.set_raw_dump_dir(None)
         if pipeline_mode == "agent":
             llm.set_model_overrides(None, None)
     report.setdefault("summary", {})["pipeline_mode"] = pipeline_mode
+    _log_cost_summary(report.get("summary", {}))
     if report["summary"].get("agent_status") == "needs_review":
         # Human-review gate: hold the job, don't email the unreviewed report.
         _set(job_id, status="needs_review", report=report,
@@ -208,6 +220,55 @@ def _run_pipeline(job_id: str, pdf_path: str, out_dir: str,
         _notify(job_id, report, out_dir)
 
 
+def _log_cost_summary(summary: Dict, label: str = "this run") -> None:
+    """
+    End-of-log estimated LLM cost block, printed inside the job's stdio tee so
+    it lands at the tail of job.log. Both runners populate the same summary
+    fields (cost_usd / llm_calls / cached_calls / cost_by_stage / models_used).
+    Hybrid note: local text calls carry no usage accounting, so the dollar
+    figure covers OpenRouter calls only (local call counts still appear).
+    """
+    if summary.get("cost_usd") is None and not summary.get("llm_calls"):
+        return
+    print(f"\n=== Estimated LLM cost ({label}) ===")
+    print(f"  Total: ${summary.get('cost_usd', 0.0):.4f} across "
+          f"{summary.get('llm_calls', 0)} live calls "
+          f"({summary.get('cached_calls', 0)} cached at $0)")
+    for name, bucket in (summary.get("cost_by_stage") or {}).items():
+        print(f"    {name}: ${bucket.get('usd', 0.0):.4f} "
+              f"({bucket.get('calls', 0)} live, {bucket.get('cached', 0)} cached)")
+    mu = summary.get("models_used") or {}
+    if mu.get("vision"):
+        print(f"  Vision models: {', '.join(mu['vision'])}")
+    if mu.get("text_local"):
+        print(f"  Text models (local): {', '.join(mu['text_local'])}")
+    if mu.get("text_cloud"):
+        print(f"  Text models (cloud): {', '.join(mu['text_cloud'])}")
+    if mu.get("fallback_count"):
+        print(f"  Local->cloud fallbacks: {mu['fallback_count']}")
+    if mu.get("text_local"):
+        print("  Note: local calls have no cost accounting; "
+              "the dollar total covers OpenRouter usage only.")
+
+
+@contextmanager
+def capture_job_output(job_id: str, out_dir: str) -> Iterator[None]:
+    """
+    Re-open the stdio tee + raw LLM dump dir for post-run work that still
+    belongs to this job (review finalization): lines append to job.log and
+    the in-memory log, raw dumps resume under <out_dir>/llm_raw/. The tee is
+    process-global — same overlapping-job caveat as the main run.
+    """
+    log_path = os.path.join(out_dir, "job.log")
+    if config.LLM_RAW_DUMP:
+        llm.set_raw_dump_dir(os.path.join(out_dir, "llm_raw"))
+    try:
+        with capture_stdio(lambda raw: _append_log(job_id, raw, log_path)):
+            yield
+    finally:
+        llm.set_raw_dump_dir(None)
+
+
 def _notify(job_id: str, report: Dict, out_dir: str) -> None:
     email = _jobs[job_id].get("email")
     if not email: