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/src/nisse_dev/loop/reader.py

@@ -11,6 +11,7 @@ The driver's model reads for now; the classifier role takes over in M2.6.
 from typing import Any
 
 from nisse_core.log.canonical import StoredEvent, ToolCall, UserMessage
+from nisse_core.models.calls import purpose
 from nisse_core.models.llm import LLMClient, LLMError
 
 
@@ -65,19 +66,20 @@ class GoAheadReader:
             return False
         prompt = f"The proposal:\n\n{proposal}\n\nThe operator's reply:\n\n{reply}"
         try:
-            produced = self._client.complete(
-                [
-                    StoredEvent(
-                        id=0,
-                        ts="",
-                        event=UserMessage(text=prompt, source="go-ahead reader"),
-                        actor="orchestrator",
-                    )
-                ],
-                tools=[VERDICT],
-                model=model or self._model,
-                system=SYSTEM,
-            )
+            with purpose("go-ahead reading", role="classifier"):
+                produced = self._client.complete(
+                    [
+                        StoredEvent(
+                            id=0,
+                            ts="",
+                            event=UserMessage(text=prompt, source="go-ahead reader"),
+                            actor="orchestrator",
+                        )
+                    ],
+                    tools=[VERDICT],
+                    model=model or self._model,
+                    system=SYSTEM,
+                )
         except LLMError:
             return False  # unread: the driver reads it as an answer instead
         return any(_yes(event) for event in produced)