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

nisse-dev/tests/test_delegation.py

@@ -702,3 +702,25 @@ def test_a_bad_request_is_not_given_the_benefit_of_the_doubt(
     result = build(BadRequestClient([]), store, ws, repo).run(brief="b", branch="d")
     assert result.status == "failed"
     assert not result.interrupted
+
+
+def test_a_delegation_is_recorded_as_a_run_of_its_own(
+    store: StateStore, ws: Workspace, repo: GitRepo
+) -> None:
+    # Its calls are the helper's turns (L7), inside the run that delegated.
+    from nisse_core.models import calls
+
+    seen: list[calls.Scope] = []
+
+    class Watching(ScriptedClient):
+        def complete(self, *args: Any, **kwargs: Any) -> list[CanonicalEvent]:
+            seen.append(calls.current())
+            return super().complete(*args, **kwargs)
+
+    client = Watching([[hand_back(succeeded=False, changed="nothing")]])
+    with calls.run(None, work_item=ITEM, role="driver"):
+        outer = calls.current().run
+        build(client, store, ws, repo).run(brief="look into it", branch="d1")
+    [scope] = seen
+    assert (scope.role, scope.work_item, scope.parent) == ("helper", ITEM, outer)
+    assert scope.run not in (None, outer)