liqiang
b119135836
Build latest book artifacts / build (push) Canceled after 0s
dependency resolution / resolve (3.11) (push) Canceled after 0s
dependency resolution / resolve (3.13) (push) Canceled after 0s
deploy-pages / build (push) Canceled after 0s
deploy-pages / deploy (push) Canceled after 0s
i18n consistency check / check (push) Canceled after 0s
provider adoption tests / test (chapter2/context-compression) (push) Canceled after 0s
provider adoption tests / test (chapter2/prompt-injection) (push) Canceled after 0s
provider adoption tests / test (chapter2/system-hint) (push) Canceled after 0s
provider adoption tests / test (chapter3/log-sanitization) (push) Canceled after 0s
web-search-agent tests / test (push) Canceled after 0s
web-search-agent tests / agentbook (push) Canceled after 0s
114 lines
4.2 KiB
JSON
114 lines
4.2 KiB
JSON
{
|
|
"schema_version": 2,
|
|
"experiment": "9-8",
|
|
"run_id": "exp9-8-hermes-gpt56luna-autonomous-20260802-v2",
|
|
"source_repository": "https://github.com/NousResearch/hermes-agent.git",
|
|
"started_from_commit": "85c8956ec7f2b4607509980794995e1c5e21e292",
|
|
"provider": "openrouter",
|
|
"requested_model": "openai/gpt-5.6-luna",
|
|
"credential_environment_variable": "OPENROUTER_API_KEY",
|
|
"candidate_gaps_supplied_in_prompt": false,
|
|
"task_prompt_sha256": "58030253cdc72c767bf16cb61daa62447e5819d1e1bd61157892aeddcbe69a6b",
|
|
"proposer_exit_codes": [
|
|
0,
|
|
0,
|
|
0,
|
|
0
|
|
],
|
|
"acceptance_reviewer_exit_codes": [
|
|
3,
|
|
3,
|
|
3,
|
|
0
|
|
],
|
|
"interaction_rounds": 4,
|
|
"independent_acceptance_reviews": 4,
|
|
"terminal_reviewer_verdict": "ACCEPT",
|
|
"review_findings_corrected": [
|
|
"the first parser did not understand production XML-wrapped tool responses",
|
|
"batch and sample trajectory writers initially omitted the evaluation metadata",
|
|
"one failed result could be double-counted",
|
|
"the Mini-SWE trajectory writer initially remained outside the shared contract"
|
|
],
|
|
"final_candidate": {
|
|
"autonomously_selected": "evidence-backed learning signals for persisted trajectories",
|
|
"implemented": "conservative evaluation metadata shared across standard, batch, sample, and Mini-SWE trajectory persistence paths",
|
|
"deferred": [
|
|
"automatic mutation from a single trajectory",
|
|
"product-level ablation campaign runner",
|
|
"generic multi-agent reviewer without an artifact contract"
|
|
],
|
|
"status": "candidate_patch_accepted_by_terminal_reviewer_not_merged"
|
|
},
|
|
"independent_checks": [
|
|
{
|
|
"command": [
|
|
"uv",
|
|
"run",
|
|
"--with",
|
|
"pytest",
|
|
"pytest",
|
|
"tests/agent/test_trajectory.py",
|
|
"-q"
|
|
],
|
|
"exit_code": 0,
|
|
"output": "...... [100%]\n6 passed in 0.14s\n"
|
|
},
|
|
{
|
|
"command": [
|
|
"uv",
|
|
"run",
|
|
"--with",
|
|
"pytest",
|
|
"pytest",
|
|
"tests/test_batch_runner_checkpoint.py",
|
|
"tests/test_batch_runner_durability.py",
|
|
"tests/integration/test_batch_runner.py",
|
|
"tests/test_trajectory_compressor.py",
|
|
"-q"
|
|
],
|
|
"exit_code": 0,
|
|
"output": "...................................... [100%]\n38 passed in 0.65s\n"
|
|
},
|
|
{
|
|
"command": [
|
|
"python3",
|
|
"-m",
|
|
"py_compile",
|
|
"agent/trajectory.py",
|
|
"agent/agent_runtime_helpers.py",
|
|
"batch_runner.py",
|
|
"run_agent.py",
|
|
"mini_swe_runner.py",
|
|
"tests/agent/test_trajectory.py"
|
|
],
|
|
"exit_code": 0,
|
|
"output": ""
|
|
},
|
|
{
|
|
"command": [
|
|
"git",
|
|
"diff",
|
|
"--check"
|
|
],
|
|
"exit_code": 0,
|
|
"output": ""
|
|
}
|
|
],
|
|
"patch_apply_check": "passed",
|
|
"patch_sha256": "34bb72f632fd1df25791449b067e98b04ae5ff23666c3f84627b3f86a6a1a83c",
|
|
"report_sha256": "4f172e504f3b9ae1a559169032c2947ee2bd6fcb7f65b87c87ad1f55c9be5348",
|
|
"transcript_sha256": {
|
|
"hermes-transcript.txt": "22b45b9a25fbc3784fb91fe9ff01b2496aa035b4501681bb1b9c6bdd407e0409",
|
|
"hermes-review-autonomous-1.txt": "f1d2c6309cec09116a09ecd445d431cb2dc2a4a47ae48115e040de4f9545148e",
|
|
"hermes-review-autonomous-2.txt": "551cee2afd80deadf08ebd34a4fb37d511bc42f024be729db4676c4f041b87e3",
|
|
"hermes-review-autonomous-3.txt": "180aaf86b7610266070ffa3148ff4c7fa3fa58e8be1a995433d132879b680adc",
|
|
"hermes-acceptance-review-1.txt": "8a6e7dd17c0b1c0d2564b2c7cedf2257f4c25e835044f8e799d9e4b11a3c1bb8",
|
|
"hermes-acceptance-review-2.txt": "b1fd124820695cf083e3aa9fa05e830292358e379d5fa860032a4a61048645a3",
|
|
"hermes-acceptance-review-3.txt": "df5eb2171e648b3f84819ad7372f89df544c47c217e0d9904a6c7ff4933851dc",
|
|
"hermes-acceptance-review-4.txt": "6ee462b65d817a727f80f933d1fdd7de43ffd03bd24e3e085a1894af5348edbf"
|
|
},
|
|
"credential_scan": "passed",
|
|
"claim_boundary": "The run demonstrates autonomous audit, candidate generation, repeated correction under independent rejection, and terminal acceptance. It does not demonstrate downstream task-quality uplift; the proposed ablation campaign was not run."
|
|
}
|