The call record: every model call, for the operator's study (M6.6a)

nisse-core records each model call of every agent into a file beside its
state store (<state>.calls.db), for the status page (L7, X6):

- the request body exactly as sent (never headers), the raw response with
  its reasoning, the model asked and the one that answered, time, tokens
  and llama-server's own prompt reuse (timings.cache_n);
- its work item, role, run and purpose: Driver.run and nisse-dev's
  delegation loop open runs, nested; compaction, expert consults, the
  classifier and the go-ahead reader label their calls;
- provenance, worked out in BudgetedClient by comparing the events at
  each stage: each event sent with its log id and content as sent, which
  a compaction replaced, which fitting shortened (by how much) and
  dropped.

Content is stored once by hash, compressed. It is diagnostic only: the
agent never reads it, a failed write is logged once and recording stops
while the call goes on, and the file is deleted when the agent starts,
so its layout never migrates; CallReader refuses a layout it doesn't
know. While recording, the system prompt ends with one sentence saying
so. `call_record: false` in either agent's YAML turns it off.

The benchmark records each run beside that run's own state store, and
`--keep-runs DIR` keeps both for the page.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01J5Utyfzw7gF7UhjRDEtjTk

scripts/benchmark.py

@@ -66,6 +66,7 @@ def run(args: argparse.Namespace) -> int:
                     host=host,
                     note=args.note,
                     commit=commit,
+                    keep=args.keep_runs,
                 )
                 append(out, record)
                 verdict = "pass" if record.success else f"FAIL ({record.outcome})"
@@ -113,6 +114,11 @@ def main() -> int:
         "--note", default="", help='how the model was served, e.g. "vLLM 0.29, AWQ"'
     )
     run_p.add_argument("--config", help="agent config (default: NISSE_CONFIG)")
+    run_p.add_argument(
+        "--keep-runs",
+        type=Path,
+        help="keep each run's state store and call record here, for the status page",
+    )
     run_p.set_defaults(handler=run)
 
     report_p = sub.add_parser("report", help="compare stored results")