mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-09-21 20:16:18 +00:00
* feat(subagents): add opt-in parent context snapshots * test(subagents): package synthetic snapshot evaluation * fix(subagents): preserve output text and defer snapshot capture * docs(subagents): keep snapshot guidance within chain budget * fix(subagents): omit unpaired tool calls from snapshots * fix(subagents): safely omit unserializable snapshot media
17 lines
13 KiB
JSON
17 lines
13 KiB
JSON
{"arm": "isolated_handoff", "artifact_correct": true, "artifact_sha256": "ce4ddd82ecabba9cad2d41a7c7f2999f02238060785cb3b3cfb7cb983bc0beba", "case": "email_cleanup", "clean_success": true, "error_type": null, "executor_status": "completed", "first_artifact_correct": true, "fresh_public_check": true, "grader_pair_rerun": false, "lead_seconds": 15.315155624994077, "lead_usage": {"cached_tokens": 800, "complete": true, "completion_tokens": 539, "prompt_tokens": 2170, "requests": 1, "total_tokens": 2709}, "repetition": 3, "seconds": 53.378815791977104, "stop_reason": null, "usage": {"cached_tokens": 800, "complete": true, "completion_tokens": 1919, "prompt_tokens": 15313, "requests": 7, "total_tokens": 17232}, "worker_usage": {"cached_tokens": 0, "complete": true, "completion_tokens": 1380, "prompt_tokens": 13143, "requests": 6, "total_tokens": 14523}}
|
|
{"arm": "snapshot", "artifact_correct": true, "artifact_sha256": "51f7da0c4134f2064d03bb66391ffb91fe23c14bc486e53a7c46885c2ab569d8", "case": "email_cleanup", "clean_success": true, "error_type": null, "executor_status": "completed", "first_artifact_correct": true, "fresh_public_check": true, "grader_pair_rerun": false, "lead_seconds": 3.4351640829991084, "lead_usage": {"cached_tokens": 800, "complete": true, "completion_tokens": 128, "prompt_tokens": 2135, "requests": 1, "total_tokens": 2263}, "repetition": 3, "seconds": 36.725939958007075, "stop_reason": null, "usage": {"cached_tokens": 800, "complete": true, "completion_tokens": 1344, "prompt_tokens": 14018, "requests": 7, "total_tokens": 15362}, "worker_usage": {"cached_tokens": 0, "complete": true, "completion_tokens": 1216, "prompt_tokens": 11883, "requests": 6, "total_tokens": 13099}}
|
|
{"arm": "isolated_handoff", "artifact_correct": true, "artifact_sha256": "b67da883daa296d34053adc67bf1ab94b241a2756f158b8276c36dbee282f2a7", "case": "fresh_evidence", "clean_success": true, "error_type": null, "executor_status": "completed", "first_artifact_correct": true, "fresh_public_check": true, "grader_pair_rerun": false, "lead_seconds": 11.029128458991181, "lead_usage": {"cached_tokens": 800, "complete": true, "completion_tokens": 355, "prompt_tokens": 2138, "requests": 1, "total_tokens": 2493}, "repetition": 3, "seconds": 21.05541508301394, "stop_reason": null, "usage": {"cached_tokens": 800, "complete": true, "completion_tokens": 651, "prompt_tokens": 7840, "requests": 5, "total_tokens": 8491}, "worker_usage": {"cached_tokens": 0, "complete": true, "completion_tokens": 296, "prompt_tokens": 5702, "requests": 4, "total_tokens": 5998}}
|
|
{"arm": "snapshot", "artifact_correct": true, "artifact_sha256": "b67da883daa296d34053adc67bf1ab94b241a2756f158b8276c36dbee282f2a7", "case": "fresh_evidence", "clean_success": true, "error_type": null, "executor_status": "completed", "first_artifact_correct": true, "fresh_public_check": true, "grader_pair_rerun": false, "lead_seconds": 3.1425372500088997, "lead_usage": {"cached_tokens": 800, "complete": true, "completion_tokens": 131, "prompt_tokens": 2103, "requests": 1, "total_tokens": 2234}, "repetition": 3, "seconds": 12.320582874992397, "stop_reason": null, "usage": {"cached_tokens": 800, "complete": true, "completion_tokens": 449, "prompt_tokens": 6227, "requests": 4, "total_tokens": 6676}, "worker_usage": {"cached_tokens": 0, "complete": true, "completion_tokens": 318, "prompt_tokens": 4124, "requests": 3, "total_tokens": 4442}}
|
|
{"arm": "isolated_handoff", "artifact_correct": true, "artifact_sha256": "d84d2bc536389f202cb24e2cfd73267254132cbf1a74c32f5bc4a060c77763cd", "case": "invoice_total", "clean_success": false, "error_type": null, "executor_status": "failed", "first_artifact_correct": true, "fresh_public_check": true, "grader_pair_rerun": true, "lead_seconds": 20.053971458983142, "lead_usage": {"cached_tokens": 800, "complete": true, "completion_tokens": 689, "prompt_tokens": 2146, "requests": 1, "total_tokens": 2835}, "repetition": 3, "seconds": 51.09080704298685, "stop_reason": "turn_capped", "usage": {"cached_tokens": 800, "complete": true, "completion_tokens": 2469, "prompt_tokens": 20486, "requests": 8, "total_tokens": 22955}, "worker_usage": {"cached_tokens": 0, "complete": true, "completion_tokens": 1780, "prompt_tokens": 18340, "requests": 7, "total_tokens": 20120}}
|
|
{"arm": "snapshot", "artifact_correct": true, "artifact_sha256": "c14429bdec94d59f2a56057c37d2bb216b8ee1f5bef808e4bbad9f20963e770c", "case": "invoice_total", "clean_success": true, "error_type": null, "executor_status": "completed", "first_artifact_correct": true, "fresh_public_check": true, "grader_pair_rerun": true, "lead_seconds": 2.1613827499968465, "lead_usage": {"cached_tokens": 800, "complete": true, "completion_tokens": 95, "prompt_tokens": 2111, "requests": 1, "total_tokens": 2206}, "repetition": 3, "seconds": 17.383087750000414, "stop_reason": null, "usage": {"cached_tokens": 800, "complete": true, "completion_tokens": 597, "prompt_tokens": 11282, "requests": 6, "total_tokens": 11879}, "worker_usage": {"cached_tokens": 0, "complete": true, "completion_tokens": 502, "prompt_tokens": 9171, "requests": 5, "total_tokens": 9673}}
|
|
{"arm": "isolated_handoff", "artifact_correct": true, "artifact_sha256": "85778814616902cd34ab6f27215f1df8d6f45bde68272d8c662ecbbcc3d40825", "case": "pagination", "clean_success": true, "error_type": null, "executor_status": "completed", "first_artifact_correct": true, "fresh_public_check": true, "grader_pair_rerun": false, "lead_seconds": 20.995743667008355, "lead_usage": {"cached_tokens": 800, "complete": true, "completion_tokens": 714, "prompt_tokens": 2150, "requests": 1, "total_tokens": 2864}, "repetition": 3, "seconds": 47.94947958301054, "stop_reason": null, "usage": {"cached_tokens": 800, "complete": true, "completion_tokens": 1680, "prompt_tokens": 12961, "requests": 6, "total_tokens": 14641}, "worker_usage": {"cached_tokens": 0, "complete": true, "completion_tokens": 966, "prompt_tokens": 10811, "requests": 5, "total_tokens": 11777}}
|
|
{"arm": "snapshot", "artifact_correct": true, "artifact_sha256": "5c033d34a495c203cf8429e777f28baa5133d8c51b58cdc750b4ed9f0c3f01c2", "case": "pagination", "clean_success": false, "error_type": null, "executor_status": "failed", "first_artifact_correct": true, "fresh_public_check": true, "grader_pair_rerun": false, "lead_seconds": 2.6815264580072835, "lead_usage": {"cached_tokens": 800, "complete": true, "completion_tokens": 93, "prompt_tokens": 2115, "requests": 1, "total_tokens": 2208}, "repetition": 3, "seconds": 45.285928541998146, "stop_reason": "turn_capped", "usage": {"cached_tokens": 800, "complete": true, "completion_tokens": 1747, "prompt_tokens": 18317, "requests": 8, "total_tokens": 20064}, "worker_usage": {"cached_tokens": 0, "complete": true, "completion_tokens": 1654, "prompt_tokens": 16202, "requests": 7, "total_tokens": 17856}}
|
|
{"arm": "isolated_handoff", "artifact_correct": true, "artifact_sha256": "3969576296a00b984853f0d3df9b8e9d14547531fad9030ecb54a09b881aa21f", "case": "rate_limits", "clean_success": true, "error_type": null, "executor_status": "completed", "first_artifact_correct": true, "fresh_public_check": true, "grader_pair_rerun": false, "lead_seconds": 11.633464709011605, "lead_usage": {"cached_tokens": 800, "complete": true, "completion_tokens": 404, "prompt_tokens": 2145, "requests": 1, "total_tokens": 2549}, "repetition": 3, "seconds": 23.62317891701241, "stop_reason": null, "usage": {"cached_tokens": 800, "complete": true, "completion_tokens": 784, "prompt_tokens": 10097, "requests": 6, "total_tokens": 10881}, "worker_usage": {"cached_tokens": 0, "complete": true, "completion_tokens": 380, "prompt_tokens": 7952, "requests": 5, "total_tokens": 8332}}
|
|
{"arm": "snapshot", "artifact_correct": true, "artifact_sha256": "3969576296a00b984853f0d3df9b8e9d14547531fad9030ecb54a09b881aa21f", "case": "rate_limits", "clean_success": true, "error_type": null, "executor_status": "completed", "first_artifact_correct": true, "fresh_public_check": true, "grader_pair_rerun": false, "lead_seconds": 2.8648069170012604, "lead_usage": {"cached_tokens": 800, "complete": true, "completion_tokens": 109, "prompt_tokens": 2110, "requests": 1, "total_tokens": 2219}, "repetition": 3, "seconds": 13.528423583018593, "stop_reason": null, "usage": {"cached_tokens": 800, "complete": true, "completion_tokens": 475, "prompt_tokens": 6315, "requests": 4, "total_tokens": 6790}, "worker_usage": {"cached_tokens": 0, "complete": true, "completion_tokens": 366, "prompt_tokens": 4205, "requests": 3, "total_tokens": 4571}}
|
|
{"arm": "isolated_handoff", "artifact_correct": true, "artifact_sha256": "967e83e5697a804a07145a13e4b515846759217ae0e22eea843d36a020ce4dda", "case": "release_plan", "clean_success": true, "error_type": null, "executor_status": "completed", "first_artifact_correct": true, "fresh_public_check": true, "grader_pair_rerun": false, "lead_seconds": 11.788521833019331, "lead_usage": {"cached_tokens": 800, "complete": true, "completion_tokens": 451, "prompt_tokens": 2156, "requests": 1, "total_tokens": 2607}, "repetition": 3, "seconds": 26.08809720899444, "stop_reason": null, "usage": {"cached_tokens": 800, "complete": true, "completion_tokens": 948, "prompt_tokens": 10406, "requests": 6, "total_tokens": 11354}, "worker_usage": {"cached_tokens": 0, "complete": true, "completion_tokens": 497, "prompt_tokens": 8250, "requests": 5, "total_tokens": 8747}}
|
|
{"arm": "snapshot", "artifact_correct": true, "artifact_sha256": "a829b369b6c1d0d73e1d5f18d03305897f721430957fe51a03abfdbdc30d11cb", "case": "release_plan", "clean_success": true, "error_type": null, "executor_status": "completed", "first_artifact_correct": true, "fresh_public_check": true, "grader_pair_rerun": false, "lead_seconds": 3.1087247090181336, "lead_usage": {"cached_tokens": 800, "complete": true, "completion_tokens": 100, "prompt_tokens": 2121, "requests": 1, "total_tokens": 2221}, "repetition": 3, "seconds": 8.358779542002594, "stop_reason": null, "usage": {"cached_tokens": 800, "complete": true, "completion_tokens": 268, "prompt_tokens": 6437, "requests": 4, "total_tokens": 6705}, "worker_usage": {"cached_tokens": 0, "complete": true, "completion_tokens": 168, "prompt_tokens": 4316, "requests": 3, "total_tokens": 4484}}
|
|
{"arm": "isolated_handoff", "artifact_correct": true, "artifact_sha256": "75ffa09e8c5aa6e83969bf8bd799fbd171e6391e88645e8b38172713c43fe70d", "case": "self_contained", "clean_success": true, "error_type": null, "executor_status": "completed", "first_artifact_correct": true, "fresh_public_check": true, "grader_pair_rerun": false, "lead_seconds": 11.913002625020454, "lead_usage": {"cached_tokens": 800, "complete": true, "completion_tokens": 382, "prompt_tokens": 3581, "requests": 1, "total_tokens": 3963}, "repetition": 3, "seconds": 22.15061379200779, "stop_reason": null, "usage": {"cached_tokens": 800, "complete": true, "completion_tokens": 740, "prompt_tokens": 7619, "requests": 4, "total_tokens": 8359}, "worker_usage": {"cached_tokens": 0, "complete": true, "completion_tokens": 358, "prompt_tokens": 4038, "requests": 3, "total_tokens": 4396}}
|
|
{"arm": "snapshot", "artifact_correct": true, "artifact_sha256": "75ffa09e8c5aa6e83969bf8bd799fbd171e6391e88645e8b38172713c43fe70d", "case": "self_contained", "clean_success": true, "error_type": null, "executor_status": "completed", "first_artifact_correct": true, "fresh_public_check": true, "grader_pair_rerun": false, "lead_seconds": 3.143074624997098, "lead_usage": {"cached_tokens": 800, "complete": true, "completion_tokens": 110, "prompt_tokens": 3546, "requests": 1, "total_tokens": 3656}, "repetition": 3, "seconds": 13.189580083009787, "stop_reason": null, "usage": {"cached_tokens": 2400, "complete": true, "completion_tokens": 397, "prompt_tokens": 11963, "requests": 4, "total_tokens": 12360}, "worker_usage": {"cached_tokens": 1600, "complete": true, "completion_tokens": 287, "prompt_tokens": 8417, "requests": 3, "total_tokens": 8704}}
|
|
{"arm": "isolated_handoff", "artifact_correct": true, "artifact_sha256": "fb14ff2040ea608061ac22b11ffdcc61d764811d0a9b181aee9ef26181dbf610", "case": "storage_policy", "clean_success": true, "error_type": null, "executor_status": "completed", "first_artifact_correct": true, "fresh_public_check": true, "grader_pair_rerun": false, "lead_seconds": 12.194588833983289, "lead_usage": {"cached_tokens": 800, "complete": true, "completion_tokens": 461, "prompt_tokens": 2253, "requests": 1, "total_tokens": 2714}, "repetition": 3, "seconds": 24.530389916995773, "stop_reason": null, "usage": {"cached_tokens": 800, "complete": true, "completion_tokens": 867, "prompt_tokens": 10789, "requests": 6, "total_tokens": 11656}, "worker_usage": {"cached_tokens": 0, "complete": true, "completion_tokens": 406, "prompt_tokens": 8536, "requests": 5, "total_tokens": 8942}}
|
|
{"arm": "snapshot", "artifact_correct": true, "artifact_sha256": "fb14ff2040ea608061ac22b11ffdcc61d764811d0a9b181aee9ef26181dbf610", "case": "storage_policy", "clean_success": true, "error_type": null, "executor_status": "completed", "first_artifact_correct": true, "fresh_public_check": true, "grader_pair_rerun": false, "lead_seconds": 2.3858411660185084, "lead_usage": {"cached_tokens": 800, "complete": true, "completion_tokens": 105, "prompt_tokens": 2218, "requests": 1, "total_tokens": 2323}, "repetition": 3, "seconds": 14.331022500002291, "stop_reason": null, "usage": {"cached_tokens": 800, "complete": true, "completion_tokens": 519, "prompt_tokens": 8859, "requests": 5, "total_tokens": 9378}, "worker_usage": {"cached_tokens": 0, "complete": true, "completion_tokens": 414, "prompt_tokens": 6641, "requests": 4, "total_tokens": 7055}}
|