Files
ai-agent-book/chapter7/agent-cost-analysis/runs/exp7-9-gpt56-20260730-v1/trace.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

426 lines
12 KiB
JSON

{
"model": "kimi-k2.5",
"pricing": {
"input": 0.5911688312,
"cached": 0.1034545455,
"output": 3.1036363636
},
"scenarios": [
{
"key": "naive",
"name": "A 朴素(无缓存/无压缩)",
"total_cost": 0.0152468353252392,
"component_costs": {
"uncached_input_cost": 0.0115224716889192,
"cached_input_cost": 0.0,
"output_cost": 0.00372436363632,
"uncached_input_tokens": 19491,
"cached_input_tokens": 0,
"output_tokens": 1200,
"tool_ctx_tokens": 10749
},
"cost_distribution": {
"n": 8,
"mean": 0.0019058544156549,
"p50": 0.0019094753247440002,
"p95": 0.0025698109091944,
"p99": 0.0025698109091944,
"max": 0.0025698109091944
},
"spans": [
{
"step": "turn-1",
"tool": "query_order",
"kind": "llm",
"prompt_tokens": 1013,
"cached_tokens": 0,
"completion_tokens": 120,
"tool_ctx_tokens": 300,
"latency_s": 2.287337064743042
},
{
"step": "turn-2",
"tool": "query_logistics",
"kind": "llm",
"prompt_tokens": 1670,
"cached_tokens": 0,
"completion_tokens": 120,
"tool_ctx_tokens": 899,
"latency_s": 3.4959402084350586
},
{
"step": "turn-3",
"tool": "check_refund_policy",
"kind": "llm",
"prompt_tokens": 2008,
"cached_tokens": 0,
"completion_tokens": 160,
"tool_ctx_tokens": 1164,
"latency_s": 5.752177000045776
},
{
"step": "turn-4",
"tool": "query_knowledge_base",
"kind": "llm",
"prompt_tokens": 2390,
"cached_tokens": 0,
"completion_tokens": 160,
"tool_ctx_tokens": 1482,
"latency_s": 3.8040597438812256
},
{
"step": "turn-5",
"tool": "query_user_history",
"kind": "llm",
"prompt_tokens": 2682,
"cached_tokens": 0,
"completion_tokens": 160,
"tool_ctx_tokens": 1585,
"latency_s": 6.000391006469727
},
{
"step": "turn-6",
"tool": "issue_refund",
"kind": "llm",
"prompt_tokens": 2970,
"cached_tokens": 0,
"completion_tokens": 160,
"tool_ctx_tokens": 1693,
"latency_s": 5.413041353225708
},
{
"step": "turn-7",
"tool": "send_notification",
"kind": "llm",
"prompt_tokens": 3251,
"cached_tokens": 0,
"completion_tokens": 160,
"tool_ctx_tokens": 1779,
"latency_s": 5.660830974578857
},
{
"step": "turn-8",
"tool": "close_ticket",
"kind": "llm",
"prompt_tokens": 3507,
"cached_tokens": 0,
"completion_tokens": 160,
"tool_ctx_tokens": 1847,
"latency_s": 5.281260013580322
}
]
},
{
"key": "kv",
"name": "KV 仅缓存(稳定前缀/不压缩)",
"total_cost": 0.0079609602864777,
"component_costs": {
"uncached_input_cost": 0.0029623470131432,
"cached_input_cost": 0.0014759860006485,
"output_cost": 0.003522627272686,
"uncached_input_tokens": 5011,
"cached_input_tokens": 14267,
"output_tokens": 1135,
"tool_ctx_tokens": 10749
},
"cost_distribution": {
"n": 8,
"mean": 0.0009951200358097126,
"p50": 0.001072025558548,
"p95": 0.0011735883637072,
"p99": 0.0011735883637072,
"max": 0.0011735883637072
},
"spans": [
{
"step": "turn-1",
"tool": "query_order",
"kind": "llm",
"prompt_tokens": 955,
"cached_tokens": 955,
"completion_tokens": 129,
"tool_ctx_tokens": 300,
"latency_s": 5.202546119689941
},
{
"step": "turn-2",
"tool": "query_logistics",
"kind": "llm",
"prompt_tokens": 1620,
"cached_tokens": 512,
"completion_tokens": 145,
"tool_ctx_tokens": 899,
"latency_s": 4.699679136276245
},
{
"step": "turn-3",
"tool": "check_refund_policy",
"kind": "llm",
"prompt_tokens": 1990,
"cached_tokens": 1024,
"completion_tokens": 160,
"tool_ctx_tokens": 1164,
"latency_s": 4.436970949172974
},
{
"step": "turn-4",
"tool": "query_knowledge_base",
"kind": "llm",
"prompt_tokens": 2375,
"cached_tokens": 1536,
"completion_tokens": 160,
"tool_ctx_tokens": 1482,
"latency_s": 5.637408018112183
},
{
"step": "turn-5",
"tool": "query_user_history",
"kind": "llm",
"prompt_tokens": 2663,
"cached_tokens": 2048,
"completion_tokens": 160,
"tool_ctx_tokens": 1585,
"latency_s": 4.351202964782715
},
{
"step": "turn-6",
"tool": "issue_refund",
"kind": "llm",
"prompt_tokens": 2953,
"cached_tokens": 2304,
"completion_tokens": 160,
"tool_ctx_tokens": 1693,
"latency_s": 5.36053204536438
},
{
"step": "turn-7",
"tool": "send_notification",
"kind": "llm",
"prompt_tokens": 3233,
"cached_tokens": 2816,
"completion_tokens": 160,
"tool_ctx_tokens": 1779,
"latency_s": 4.889960765838623
},
{
"step": "turn-8",
"tool": "close_ticket",
"kind": "llm",
"prompt_tokens": 3489,
"cached_tokens": 3072,
"completion_tokens": 61,
"tool_ctx_tokens": 1847,
"latency_s": 1.9250061511993408
}
]
},
{
"key": "compress",
"name": "仅压缩(前缀不稳定/摘要)",
"total_cost": 0.0132817901303144,
"component_costs": {
"uncached_input_cost": 0.009309135584906399,
"cached_input_cost": 0.0,
"output_cost": 0.003972654545408001,
"uncached_input_tokens": 15747,
"cached_input_tokens": 0,
"output_tokens": 1280,
"tool_ctx_tokens": 6036
},
"cost_distribution": {
"n": 8,
"mean": 0.0016602237662893,
"p50": 0.0017338981818776,
"p95": 0.00189765194812,
"p99": 0.00189765194812,
"max": 0.00189765194812
},
"spans": [
{
"step": "turn-1",
"tool": "query_order",
"kind": "llm",
"prompt_tokens": 1012,
"cached_tokens": 0,
"completion_tokens": 160,
"tool_ctx_tokens": 300,
"latency_s": 5.470736980438232
},
{
"step": "turn-2",
"tool": "query_logistics",
"kind": "llm",
"prompt_tokens": 1710,
"cached_tokens": 0,
"completion_tokens": 160,
"tool_ctx_tokens": 899,
"latency_s": 4.1132972240448
},
{
"step": "turn-3",
"tool": "check_refund_policy",
"kind": "llm",
"prompt_tokens": 2093,
"cached_tokens": 0,
"completion_tokens": 160,
"tool_ctx_tokens": 1164,
"latency_s": 3.5907950401306152
},
{
"step": "turn-4",
"tool": "query_knowledge_base",
"kind": "llm",
"prompt_tokens": 2227,
"cached_tokens": 0,
"completion_tokens": 160,
"tool_ctx_tokens": 1231,
"latency_s": 3.2491540908813477
},
{
"step": "turn-5",
"tool": "query_user_history",
"kind": "llm",
"prompt_tokens": 2021,
"cached_tokens": 0,
"completion_tokens": 160,
"tool_ctx_tokens": 780,
"latency_s": 7.461982250213623
},
{
"step": "turn-6",
"tool": "issue_refund",
"kind": "llm",
"prompt_tokens": 2114,
"cached_tokens": 0,
"completion_tokens": 160,
"tool_ctx_tokens": 677,
"latency_s": 4.925306081771851
},
{
"step": "turn-7",
"tool": "send_notification",
"kind": "llm",
"prompt_tokens": 2200,
"cached_tokens": 0,
"completion_tokens": 160,
"tool_ctx_tokens": 486,
"latency_s": 5.416359186172485
},
{
"step": "turn-8",
"tool": "close_ticket",
"kind": "llm",
"prompt_tokens": 2370,
"cached_tokens": 0,
"completion_tokens": 160,
"tool_ctx_tokens": 499,
"latency_s": 4.96558403968811
}
]
},
{
"key": "both",
"name": "B 优化(KV缓存+压缩)",
"total_cost": 0.0086632688576729,
"component_costs": {
"uncached_input_cost": 0.0041033028573592,
"cached_input_cost": 0.0008138769094485001,
"output_cost": 0.0037460890908652,
"uncached_input_tokens": 6941,
"cached_input_tokens": 7867,
"output_tokens": 1207,
"tool_ctx_tokens": 6036
},
"cost_distribution": {
"n": 8,
"mean": 0.0010829086072091125,
"p50": 0.0011068749610916,
"p95": 0.0013616982857848,
"p99": 0.0013616982857848,
"max": 0.0013616982857848
},
"spans": [
{
"step": "turn-1",
"tool": "query_order",
"kind": "llm",
"prompt_tokens": 955,
"cached_tokens": 955,
"completion_tokens": 116,
"tool_ctx_tokens": 300,
"latency_s": 2.2258410453796387
},
{
"step": "turn-2",
"tool": "query_logistics",
"kind": "llm",
"prompt_tokens": 1607,
"cached_tokens": 512,
"completion_tokens": 131,
"tool_ctx_tokens": 899,
"latency_s": 4.5919647216796875
},
{
"step": "turn-3",
"tool": "check_refund_policy",
"kind": "llm",
"prompt_tokens": 1963,
"cached_tokens": 1024,
"completion_tokens": 160,
"tool_ctx_tokens": 1164,
"latency_s": 7.6671669483184814
},
{
"step": "turn-4",
"tool": "query_knowledge_base",
"kind": "llm",
"prompt_tokens": 2097,
"cached_tokens": 768,
"completion_tokens": 160,
"tool_ctx_tokens": 1231,
"latency_s": 5.431225061416626
},
{
"step": "turn-5",
"tool": "query_user_history",
"kind": "llm",
"prompt_tokens": 1887,
"cached_tokens": 768,
"completion_tokens": 160,
"tool_ctx_tokens": 780,
"latency_s": 5.2519941329956055
},
{
"step": "turn-6",
"tool": "issue_refund",
"kind": "llm",
"prompt_tokens": 1988,
"cached_tokens": 1024,
"completion_tokens": 160,
"tool_ctx_tokens": 677,
"latency_s": 4.7071919441223145
},
{
"step": "turn-7",
"tool": "send_notification",
"kind": "llm",
"prompt_tokens": 2073,
"cached_tokens": 1280,
"completion_tokens": 160,
"tool_ctx_tokens": 486,
"latency_s": 5.377019882202148
},
{
"step": "turn-8",
"tool": "close_ticket",
"kind": "llm",
"prompt_tokens": 2238,
"cached_tokens": 1536,
"completion_tokens": 160,
"tool_ctx_tokens": 499,
"latency_s": 4.964300155639648
}
]
}
]
}