scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-29 06:33:28 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 267

chore(cookbook): add sanitized profiling checkpoint export

Browse source 
Co-Authored-By: bot_apk <apk@cognition.ai>
This commit is contained in:
Devin AI 2026-10-21 05:03:42 +00:00
parent 4d18c700cc
commit 2335b16b44
1 changed files with 38 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

38
cookbook/capability_routing_pilot/profiling/invocations/export_checkpoint.py Normal file
View file

@ -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()