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
61 lines
1.6 KiB
JSON
61 lines
1.6 KiB
JSON
{
|
|
"schema_version": 1,
|
|
"experiment": "10-3",
|
|
"run_dir": "exp10-3-talkact-anthropic-caller-20260803-v2",
|
|
"passed": true,
|
|
"gates": {
|
|
"source_commit": true,
|
|
"exact_campaign_shape": true,
|
|
"two_seeds_per_task_condition": true,
|
|
"summary_has_16_fresh_rows": true,
|
|
"all_episode_records_complete": true,
|
|
"anthropic_slow_model": true,
|
|
"anthropic_fast_model": true,
|
|
"explicit_anthropic_caller_override": true,
|
|
"provider_usage_retained": true,
|
|
"no_runtime_provider_errors": true,
|
|
"real_concurrent_duplex_events": true,
|
|
"bidirectional_bridge_observed": true,
|
|
"voice_latency_samples": true,
|
|
"deterministic_checks_retained": true,
|
|
"judge_results_retained": true,
|
|
"duplex_strawman_aggregate": true,
|
|
"no_credential_material": true
|
|
},
|
|
"counts": {
|
|
"episodes": 16,
|
|
"duplex": 8,
|
|
"strawman": 8,
|
|
"fast_to_slow_relays": 39,
|
|
"slow_to_fast_events": 33,
|
|
"voice_latency_samples": 91,
|
|
"files_hashed": 23
|
|
},
|
|
"comparison": [
|
|
{
|
|
"condition": "duplex",
|
|
"n_episodes": 8,
|
|
"task_success": 1.0,
|
|
"partial_credit": 1.0,
|
|
"probe_correct": 0.833,
|
|
"voice_lat_p50": 2.32,
|
|
"voice_lat_p90": 2.85,
|
|
"voice_lat_max": 4.03,
|
|
"wall_time_mean": 207.2,
|
|
"n_lat_samples": 47
|
|
},
|
|
{
|
|
"condition": "strawman",
|
|
"n_episodes": 8,
|
|
"task_success": 1.0,
|
|
"partial_credit": 1.0,
|
|
"probe_correct": 0.917,
|
|
"voice_lat_p50": 12.52,
|
|
"voice_lat_p90": 21.14,
|
|
"voice_lat_max": 37.29,
|
|
"wall_time_mean": 178.0,
|
|
"n_lat_samples": 44
|
|
}
|
|
]
|
|
}
|