From 2335b16b44af84ea867341039421adea458fa497 Mon Sep 17 00:00:00 2001 From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Wed, 21 Oct 2026 05:03:42 +0000 Subject: [PATCH] chore(cookbook): add sanitized profiling checkpoint export Co-Authored-By: bot_apk --- .../invocations/export_checkpoint.py | 38 +++++++++++++++++++ 1 file changed, 38 insertions(+) create mode 100644 cookbook/capability_routing_pilot/profiling/invocations/export_checkpoint.py diff --git a/cookbook/capability_routing_pilot/profiling/invocations/export_checkpoint.py b/cookbook/capability_routing_pilot/profiling/invocations/export_checkpoint.py new file mode 100644 index 00000000000..5bbdd791ac4 --- /dev/null +++ b/cookbook/capability_routing_pilot/profiling/invocations/export_checkpoint.py @@ -0,0 +1,38 @@ +import hashlib +import json +import shutil +import sys +from pathlib import Path +from typing import Final + +FIELDS: Final = ( + "record_type", "task_id", "category", "tenant_id", "manifest_sha256", "model_alias", "gateway_model", + "returned_model_version", "deployment_id", "attempt", "model_order", "success", "eval_status", "exit_status", + "error_class", "is_infra", "retry_eligible", "budget_guard_refused", "cost_usd", "cost_incomplete", "n_calls", + "tokens", "latency_s", "solve_latency_s", "eval_latency_s", "harness_sha256", "harness_version", + "budget_version", "harness_config_hash", "gold_status", "noop_status", "status", "upstream_digest", + "upstream_image_id", "overlay_image_id", "final_image_id", "agent_image_ref", "grader_image_ref", + "env_correction_sha256", "corrections_file_sha256", "dockerfile_sha256", "repair_script_sha256", "cause", + "evidence", "applies_on_top_of", "run_id", "started_at", "finished_at", +) + + +def main() -> None: + source: Final = Path(sys.argv[1]) + target: Final = Path(sys.argv[2]) + target.mkdir(parents=True, exist_ok=True) + rows: Final = tuple(json.loads(line) for line in (source / "profiling_runs.jsonl").read_text().splitlines() if line) + sanitized: Final = "".join( + json.dumps({key: row[key] for key in FIELDS if key in row}, sort_keys=True) + "\n" for row in rows + ) + (target / "task_runs.jsonl").write_text(sanitized) + shutil.copyfile(source / "capability_map_intermediate.json", target / "capability_map_intermediate.json") + print(json.dumps({ + "rows": len(rows), + "source_runs_sha256": hashlib.sha256((source / "profiling_runs.jsonl").read_bytes()).hexdigest(), + "task_runs_sha256": hashlib.sha256(sanitized.encode()).hexdigest(), + })) + + +if __name__ == "__main__": + main()