Files
ai-agent-book/chapter10/voice-werewolf/validation/runs/exp10-6-simulated-user-openrouter-20260801/acceptance_report.json
T
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
ai-agent-book 精选快照(<2MB 代码与文档,来自 github.com/bojieli/ai-agent-book)
2026-08-20 13:12:50 +00:00

443 lines
15 KiB
JSON
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
{
"schema_version": 2,
"experiment": "10-6",
"generated_at": "2026-08-01T04:32:10+0000",
"execution_mode": "simulated_user",
"acceptance_path": true,
"end_to_end_status": "pass",
"players": 8,
"user_players": [
"P1"
],
"human_players": [],
"simulated_user_players": [
"P1"
],
"human_role_randomized_to": null,
"simulated_user_role_randomized_to": "女巫",
"role_counts": {
"狼人": 2,
"预言家": 1,
"女巫": 1,
"村民": 4
},
"completed_day_night_vote_cycles": 2,
"winner": "好人阵营",
"information_isolation_pass": true,
"strategy_audit": {
"criteria": {
"werewolf_concealment": {
"status": "pass",
"evidence": "P7: \"P5预言家验了P1P1是好人,结果P1还出局了,那P5是真的预言家吗?我觉得P5的预言家身份有点可疑。\" P8: \"P5说他是预言家,验了P1是好人,结果P1就出局了,这确实挺奇怪的。P5的预言家身份我也有点怀疑,希望P5能给出更多解释。\""
},
"seer_timing_and_evidence": {
"status": "pass",
"evidence": "P5: \"我是预言家,昨晚查验了P1,P1是好人。P1出局,很明显是狼人悍跳预言家刀的。请悍跳狼自爆,否则我将继续验人。\""
},
"villager_logical_reasoning": {
"status": "pass",
"evidence": "P2: \"P1出局有点意外,我作为村民,会仔细听大家的发言。希望狼人能早点暴露出来,大家可以多聊聊P1出局的原因。\" P3: \"P1出局确实有点出乎意料。P2说他是村民,我会先观察。大家可以多聊聊P1出局的原因,看看能不能找到狼人的线索。\""
},
"role_consistency": {
"status": "pass",
"evidence": "P5 (Seer) inspected P1 and P2, and in public speech reported P1 as good. P7 and P8 (Werewolves) proposed killing P1 and P5, and in public speech cast doubt on the Seer. P2, P3, P4, P6 (Villagers) discussed the dead player and the Seer's claim, then voted for P7 after P5's revelation."
}
},
"overall_pass": true,
"provider": "openrouter",
"model": "google/gemini-2.5-flash",
"model_overall_pass_claim": true,
"schema_valid": true,
"validation_errors": []
},
"strategy_audit_pass": true,
"voice_events": [
{
"sequence": 1,
"monotonic": 6659738.807942813,
"wall_time": "2026-08-01T04:31:39+0000",
"type": "tts_ready",
"speaker": "judge-private",
"provider": "local espeak",
"model": "espeak-zh",
"request_id": null,
"latency_seconds": 0.061,
"file": "/home/ubuntu/ai-agent-book/chapter10/voice-werewolf/audio/r0_judge-private_1.wav",
"audio_bytes": 290926,
"audio_sha256": "4072ec5c58cccd2053867e5fa15cff4f0dbe2d66497a6818cc0a72c22c6e49d0"
},
{
"sequence": 2,
"monotonic": 6659741.819194071,
"wall_time": "2026-08-01T04:31:42+0000",
"type": "simulator_llm_tool",
"seat": "P1",
"tool": "choose_player",
"arguments": {
"reason": "第一晚被刀的是我自己,女巫不能自救,所以解药无法使用。毒药第一晚先不使用,观察一下其他玩家的发言。",
"target": "none"
},
"response_id": "gen-1785558701-KGd5rQJmxY9VuJKLkL4I",
"requested_model": "google/gemini-2.5-flash",
"provider_reported_model": "google/gemini-2.5-flash",
"usage": {
"completion_tokens": 40,
"prompt_tokens": 395,
"total_tokens": 435,
"completion_tokens_details": {
"accepted_prediction_tokens": null,
"audio_tokens": 0,
"reasoning_tokens": 0,
"rejected_prediction_tokens": null,
"image_tokens": 0
},
"prompt_tokens_details": {
"audio_tokens": 0,
"cached_tokens": 0,
"cache_write_tokens": 0,
"video_tokens": 0
},
"cost": 0.0002185,
"is_byok": false,
"cost_details": {
"upstream_inference_cost": 0.0002185,
"upstream_inference_prompt_cost": 0.0001185,
"upstream_inference_completions_cost": 0.0001
}
}
},
{
"sequence": 3,
"monotonic": 6659741.881685822,
"wall_time": "2026-08-01T04:31:42+0000",
"type": "tts_ready",
"speaker": "P1",
"provider": "local espeak",
"model": "espeak-zh",
"request_id": null,
"latency_seconds": 0.062,
"file": "/home/ubuntu/ai-agent-book/chapter10/voice-werewolf/audio/r1_P1_3.wav",
"audio_bytes": 42524,
"audio_sha256": "0d9ee3c2b7690fe0d2cf41b0450755995e66d3d360b76d7e4173086c87795352"
},
{
"sequence": 4,
"monotonic": 6659742.959315685,
"wall_time": "2026-08-01T04:31:43+0000",
"type": "simulator_asr",
"provider": "OpenRouter multimodal audio API",
"model": "google/gemini-2.5-flash",
"request_id": "gen-1785558702-Gp3xq6Xf5Sx6pFLwLNi3",
"usage": {
"completion_tokens": 4,
"prompt_tokens": 63,
"total_tokens": 67,
"completion_tokens_details": {
"accepted_prediction_tokens": null,
"audio_tokens": 0,
"reasoning_tokens": 0,
"rejected_prediction_tokens": null,
"image_tokens": 0
},
"prompt_tokens_details": {
"audio_tokens": 25,
"cached_tokens": 0,
"cache_write_tokens": 0,
"video_tokens": 0
},
"cost": 4.64e-05,
"is_byok": false,
"cost_details": {
"upstream_inference_cost": 4.64e-05,
"upstream_inference_prompt_cost": 3.64e-05,
"upstream_inference_completions_cost": 1e-05
}
},
"latency_seconds": 1.077,
"source_audio_sha256": "0d9ee3c2b7690fe0d2cf41b0450755995e66d3d360b76d7e4173086c87795352",
"transcript": "P1 is not"
},
{
"sequence": 5,
"monotonic": 6659743.022028705,
"wall_time": "2026-08-01T04:31:43+0000",
"type": "tts_ready",
"speaker": "judge",
"provider": "local espeak",
"model": "espeak-zh",
"request_id": null,
"latency_seconds": 0.054,
"file": "/home/ubuntu/ai-agent-book/chapter10/voice-werewolf/audio/r1_judge_5.wav",
"audio_bytes": 304082,
"audio_sha256": "1cbcec8d528486b50106d7cd00bed6a36e37a858dc391336edd83c113a1177de"
},
{
"sequence": 6,
"monotonic": 6659743.857484956,
"wall_time": "2026-08-01T04:31:44+0000",
"type": "tts_ready",
"speaker": "P2",
"provider": "local espeak",
"model": "espeak-zh",
"request_id": null,
"latency_seconds": 0.09,
"file": "/home/ubuntu/ai-agent-book/chapter10/voice-werewolf/audio/r1_P2_6.wav",
"audio_bytes": 914730,
"audio_sha256": "08cda30fad499eeb20caa8876579741e514d286f7db0ee999555673e5a8ce41d"
},
{
"sequence": 7,
"monotonic": 6659744.760075835,
"wall_time": "2026-08-01T04:31:45+0000",
"type": "tts_ready",
"speaker": "P3",
"provider": "local espeak",
"model": "espeak-zh",
"request_id": null,
"latency_seconds": 0.065,
"file": "/home/ubuntu/ai-agent-book/chapter10/voice-werewolf/audio/r1_P3_7.wav",
"audio_bytes": 961736,
"audio_sha256": "fbacc9c4139086a6267f1f5e7668a83d81feed40ce5d8afcd915d32eaf7f2379"
},
{
"sequence": 8,
"monotonic": 6659745.623963103,
"wall_time": "2026-08-01T04:31:46+0000",
"type": "tts_ready",
"speaker": "P4",
"provider": "local espeak",
"model": "espeak-zh",
"request_id": null,
"latency_seconds": 0.08,
"file": "/home/ubuntu/ai-agent-book/chapter10/voice-werewolf/audio/r1_P4_8.wav",
"audio_bytes": 1176774,
"audio_sha256": "a606133137d7241bcb8d232a93b8563784a338187df76d2ef124c42938734c70"
},
{
"sequence": 9,
"monotonic": 6659746.469986224,
"wall_time": "2026-08-01T04:31:47+0000",
"type": "tts_ready",
"speaker": "P5",
"provider": "local espeak",
"model": "espeak-zh",
"request_id": null,
"latency_seconds": 0.093,
"file": "/home/ubuntu/ai-agent-book/chapter10/voice-werewolf/audio/r1_P5_9.wav",
"audio_bytes": 991594,
"audio_sha256": "1258edf290a49d1ce8e9577389bc04214ce129c7817ea0f4fc5c3ee9d7800250"
},
{
"sequence": 10,
"monotonic": 6659747.318732785,
"wall_time": "2026-08-01T04:31:48+0000",
"type": "tts_ready",
"speaker": "P6",
"provider": "local espeak",
"model": "espeak-zh",
"request_id": null,
"latency_seconds": 0.072,
"file": "/home/ubuntu/ai-agent-book/chapter10/voice-werewolf/audio/r1_P6_10.wav",
"audio_bytes": 1154468,
"audio_sha256": "5227d3e1be790831250156417420c5395e5ba56b2fdf10914ea1842e1e72e718"
},
{
"sequence": 11,
"monotonic": 6659748.179338652,
"wall_time": "2026-08-01T04:31:48+0000",
"type": "tts_ready",
"speaker": "P7",
"provider": "local espeak",
"model": "espeak-zh",
"request_id": null,
"latency_seconds": 0.057,
"file": "/home/ubuntu/ai-agent-book/chapter10/voice-werewolf/audio/r1_P7_11.wav",
"audio_bytes": 956014,
"audio_sha256": "34dfdd2b78ceb17facf82c64fa7d2a8bd5c43c7f53fb0757e32d5640ad308b46"
},
{
"sequence": 12,
"monotonic": 6659749.175230099,
"wall_time": "2026-08-01T04:31:49+0000",
"type": "tts_ready",
"speaker": "P8",
"provider": "local espeak",
"model": "espeak-zh",
"request_id": null,
"latency_seconds": 0.078,
"file": "/home/ubuntu/ai-agent-book/chapter10/voice-werewolf/audio/r1_P8_12.wav",
"audio_bytes": 1112008,
"audio_sha256": "b23c208fe1a7af1187c8a3db3e32ac87cc995e75286c6a82fe4fb9cb6da8f24e"
},
{
"sequence": 13,
"monotonic": 6659755.472674429,
"wall_time": "2026-08-01T04:31:56+0000",
"type": "tts_ready",
"speaker": "judge",
"provider": "local espeak",
"model": "espeak-zh",
"request_id": null,
"latency_seconds": 0.075,
"file": "/home/ubuntu/ai-agent-book/chapter10/voice-werewolf/audio/r1_judge_13.wav",
"audio_bytes": 774880,
"audio_sha256": "91d6eddf38874576842938ba4d040160a8c3320d97ea19f06612a60854fa1273"
},
{
"sequence": 14,
"monotonic": 6659757.175891685,
"wall_time": "2026-08-01T04:31:57+0000",
"type": "tts_ready",
"speaker": "judge",
"provider": "local espeak",
"model": "espeak-zh",
"request_id": null,
"latency_seconds": 0.07,
"file": "/home/ubuntu/ai-agent-book/chapter10/voice-werewolf/audio/r2_judge_14.wav",
"audio_bytes": 307294,
"audio_sha256": "fd3fe62cf32b3536394bad76d25c66cf22b9efca4f48469cb82179b11f8811e8"
},
{
"sequence": 15,
"monotonic": 6659758.170954376,
"wall_time": "2026-08-01T04:31:58+0000",
"type": "tts_ready",
"speaker": "P2",
"provider": "local espeak",
"model": "espeak-zh",
"request_id": null,
"latency_seconds": 0.082,
"file": "/home/ubuntu/ai-agent-book/chapter10/voice-werewolf/audio/r2_P2_15.wav",
"audio_bytes": 1354938,
"audio_sha256": "6043e972710e130baaf98131172067d9fe7cb69217e10e5a55a3825f13c97e13"
},
{
"sequence": 16,
"monotonic": 6659759.243308116,
"wall_time": "2026-08-01T04:32:00+0000",
"type": "tts_ready",
"speaker": "P3",
"provider": "local espeak",
"model": "espeak-zh",
"request_id": null,
"latency_seconds": 0.095,
"file": "/home/ubuntu/ai-agent-book/chapter10/voice-werewolf/audio/r2_P3_16.wav",
"audio_bytes": 1134002,
"audio_sha256": "115ddceb29320bbe2e2871a60bcc1e4f6e17ab1ba810378cd13d1067c5a38d84"
},
{
"sequence": 17,
"monotonic": 6659760.192742183,
"wall_time": "2026-08-01T04:32:00+0000",
"type": "tts_ready",
"speaker": "P4",
"provider": "local espeak",
"model": "espeak-zh",
"request_id": null,
"latency_seconds": 0.072,
"file": "/home/ubuntu/ai-agent-book/chapter10/voice-werewolf/audio/r2_P4_17.wav",
"audio_bytes": 1207868,
"audio_sha256": "4aca0b0da9f3d87bc222a5297d1172b8892bd3f62510a57180ac74a03d962941"
},
{
"sequence": 18,
"monotonic": 6659760.991943794,
"wall_time": "2026-08-01T04:32:01+0000",
"type": "tts_ready",
"speaker": "P6",
"provider": "local espeak",
"model": "espeak-zh",
"request_id": null,
"latency_seconds": 0.08,
"file": "/home/ubuntu/ai-agent-book/chapter10/voice-werewolf/audio/r2_P6_18.wav",
"audio_bytes": 1034974,
"audio_sha256": "5b3cecb54526a187a246b62c18c2701fab5dd5aaf2e715a0a83c4b93b28760d7"
},
{
"sequence": 19,
"monotonic": 6659761.881699391,
"wall_time": "2026-08-01T04:32:02+0000",
"type": "tts_ready",
"speaker": "P8",
"provider": "local espeak",
"model": "espeak-zh",
"request_id": null,
"latency_seconds": 0.07,
"file": "/home/ubuntu/ai-agent-book/chapter10/voice-werewolf/audio/r2_P8_19.wav",
"audio_bytes": 1114376,
"audio_sha256": "168dd458259cf3d405c401a50a83ec05598423735e653083ad9729846fd6621e"
},
{
"sequence": 20,
"monotonic": 6659766.873318817,
"wall_time": "2026-08-01T04:32:07+0000",
"type": "tts_ready",
"speaker": "judge",
"provider": "local espeak",
"model": "espeak-zh",
"request_id": null,
"latency_seconds": 0.074,
"file": "/home/ubuntu/ai-agent-book/chapter10/voice-werewolf/audio/r2_judge_20.wav",
"audio_bytes": 749332,
"audio_sha256": "f010a7c2f766bcd50ca438d0cd31caec26f56856fd6696961cbe27db96160bb4"
},
{
"sequence": 21,
"monotonic": 6659766.930157353,
"wall_time": "2026-08-01T04:32:07+0000",
"type": "tts_ready",
"speaker": "judge",
"provider": "local espeak",
"model": "espeak-zh",
"request_id": null,
"latency_seconds": 0.051,
"file": "/home/ubuntu/ai-agent-book/chapter10/voice-werewolf/audio/r2_judge_21.wav",
"audio_bytes": 274520,
"audio_sha256": "24a4432aee15b31513a2f4368bdc15b55433dfd35ff6b2c37559f2f6f22f9c2b"
}
],
"voice_has_asr": true,
"voice_has_tts": true,
"simulator_llm_tool_calls": 1,
"simulator_audio_roundtrips": 1,
"barge_in_events": 0,
"gates": {
"exact_6_to_8_player_role_roster": {
"status": "pass"
},
"one_user_seat": {
"status": "pass"
},
"one_authorized_human_participant": {
"status": "not_applicable"
},
"one_llm_user_simulator": {
"status": "pass"
},
"real_user_input_asr": {
"status": "pass"
},
"real_ai_and_judge_tts": {
"status": "pass"
},
"llm_tool_to_audio_to_asr_boundary": {
"status": "pass",
"tool_calls": 1,
"audio_roundtrips": 1
},
"three_complete_cycles": {
"status": "fail",
"observed": 2
},
"information_isolation": {
"status": "pass"
},
"real_llm_strategy_acceptance": {
"status": "pass"
},
"winner_determined_by_game_rule": {
"status": "pass"
}
},
"overall_status": "incomplete"
}