Prepare Frontier code trace fidelity campaign

runs/frontier-code-trace-v0/test_code_trace_preflight.py

@@ -0,0 +1,80 @@
+#!/usr/bin/env python3
+
+from __future__ import annotations
+
+import json
+import subprocess
+import sys
+import tempfile
+import unittest
+from pathlib import Path
+
+
+ROOT = Path(__file__).resolve().parent
+
+
+class CodeTracePreflightTest(unittest.TestCase):
+    def test_audit_and_materialize_512_block_window(self) -> None:
+        with tempfile.TemporaryDirectory() as tmp:
+            root = Path(tmp)
+            source = root / "051315-051317.jsonl"
+            with source.open("w") as stream:
+                for index in range(4501):
+                    input_tokens = 513 if index % 2 else 512
+                    stream.write(
+                        json.dumps(
+                            {
+                                "chat_id": index,
+                                "parent_chat_id": index - 1 if index % 2 else -1,
+                                "timestamp": float(index),
+                                "input_length": input_tokens,
+                                "output_length": 32,
+                                "hash_ids": [index // 2]
+                                if input_tokens == 512
+                                else [index // 2, 100000 + index],
+                            }
+                        )
+                        + "\n"
+                    )
+            audit = root / "audit.json"
+            subprocess.run(
+                [
+                    sys.executable,
+                    str(ROOT / "audit_code_trace.py"),
+                    "--source",
+                    str(source),
+                    "--output",
+                    str(audit),
+                ],
+                check=True,
+            )
+            payload = json.loads(audit.read_text())
+            self.assertEqual(payload["data_gate"], "PASS")
+            self.assertEqual(
+                payload["selected"]["hash_contract"]["exact_source_block_size"], 512
+            )
+            self.assertEqual(payload["max_model_len_recommendation"], 40960)
+            output = root / "window"
+            subprocess.run(
+                [
+                    sys.executable,
+                    str(ROOT / "prepare_code_window.py"),
+                    "--audit",
+                    str(audit),
+                    "--output-root",
+                    str(output),
+                ],
+                check=True,
+            )
+            manifest = json.loads((output / "window-manifest.json").read_text())
+            rows = [
+                json.loads(line)
+                for line in (output / "code-raw-window.jsonl").read_text().splitlines()
+            ]
+        self.assertEqual(manifest["requests"], len(rows))
+        self.assertGreaterEqual(manifest["duration_s"], 3600)
+        self.assertEqual(rows[0]["sampling_u"], rows[1]["sampling_u"])
+
+
+if __name__ == "__main__":
+    unittest.main()