feat(api): §10 JSON-lines call logging (full prompt + seed, injectable sink)

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

api/app/call_log.py

@@ -0,0 +1,55 @@
+"""Structured JSON-lines logging of every model call (charter §10 — the seed and
+the full prompt logged with every call; §4 — free eval/replay infrastructure).
+
+One JSON object per line: everything needed to replay the call (canon_log +
+messages + model + seed) against a candidate model. No secrets to redact — the
+client never sends keys, the canon log carries no PII, and the prompt is exactly
+what we want on record.
+"""
+
+import json
+import sys
+from datetime import datetime, timezone
+from typing import Callable
+
+from . import config
+
+
+def _default_write(line: str) -> None:
+    path = config.call_log_path()
+    if path:
+        with open(path, "a", encoding="utf-8") as handle:
+            handle.write(line + "\n")
+    else:
+        sys.stdout.write(line + "\n")
+
+
+def record(
+    *,
+    role: str,
+    model: str,
+    options: dict,
+    messages: list[dict],
+    canon_log: dict,
+    ok: bool,
+    latency_ms: int,
+    response: str | None = None,
+    error: str | None = None,
+    write: Callable[[str], None] = _default_write,
+) -> dict:
+    rec: dict = {
+        "ts": datetime.now(timezone.utc).isoformat(),
+        "role": role,
+        "model": model,
+        "options": options,
+        "messages": messages,
+        "canon_log": canon_log,
+        "ok": ok,
+        "latency_ms": latency_ms,
+    }
+    if ok:
+        rec["response"] = response
+    else:
+        rec["error"] = error
+    write(json.dumps(rec, ensure_ascii=False))
+    return rec

api/tests/test_call_log.py

@@ -0,0 +1,34 @@
+import json
+
+from app.call_log import record
+
+
+def test_success_record_shape():
+    captured = []
+    rec = record(
+        role="narrator", model="qwen3.5:latest", options={"seed": 7},
+        messages=[{"role": "user", "content": "x"}], canon_log={"a": 1},
+        ok=True, latency_ms=120, response="prose", write=captured.append,
+    )
+    assert len(captured) == 1
+    parsed = json.loads(captured[0])
+    assert parsed["ok"] is True
+    assert parsed["response"] == "prose"
+    assert parsed["options"]["seed"] == 7
+    assert parsed["role"] == "narrator"
+    assert parsed["canon_log"] == {"a": 1}
+    assert "error" not in parsed
+    assert "ts" in parsed
+    assert rec["response"] == "prose"
+
+
+def test_failure_record_shape():
+    captured = []
+    record(
+        role="narrator", model="m", options={}, messages=[], canon_log={},
+        ok=False, latency_ms=5, error="ModelError: down", write=captured.append,
+    )
+    parsed = json.loads(captured[0])
+    assert parsed["ok"] is False
+    assert parsed["error"] == "ModelError: down"
+    assert "response" not in parsed