liqiang/ai-agent-book
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

ai-agent-book 精选快照（<2MB 代码与文档，来自 github.com/bojieli/ai-agent-book）
Build latest book artifacts / build (push) Canceled after 0s
Details
dependency resolution / resolve (3.11) (push) Canceled after 0s
Details
dependency resolution / resolve (3.13) (push) Canceled after 0s
Details
deploy-pages / build (push) Canceled after 0s
Details
deploy-pages / deploy (push) Canceled after 0s
Details
i18n consistency check / check (push) Canceled after 0s
Details
provider adoption tests / test (chapter2/context-compression) (push) Canceled after 0s
Details
provider adoption tests / test (chapter2/prompt-injection) (push) Canceled after 0s
Details
provider adoption tests / test (chapter2/system-hint) (push) Canceled after 0s
Details
provider adoption tests / test (chapter3/log-sanitization) (push) Canceled after 0s
Details
web-search-agent tests / test (push) Canceled after 0s
Details
web-search-agent tests / agentbook (push) Canceled after 0s
Details

Browse Source
This commit is contained in:
liqiang
2026-08-20 13:12:50 +00:00
commit b119135836
10275 changed files with 3284984 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
chapter7/agent-cost-analysis/runs/exp7-9-gpt56-20260730-v1/report.json
+426
View File
@@ -0,0 +1,426 @@
{
"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
}
]
}
]
}
chapter7/agent-cost-analysis/runs/exp7-9-gpt56-20260730-v1/trace.json
+426
View File
@@ -0,0 +1,426 @@
{
"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
}
]
}
]
}
chapter7/agent-cost-analysis/runs/exp7-9-kimi25-20260730-v2/manifest.json
+54
View File
@@ -0,0 +1,54 @@
{
"schema_version": 1,
"experiment": "7-9",
"status": "incomplete",
"generated_at_utc": "2026-07-29T22:31:57.870199+00:00",
"run_dir": "chapter7/agent-cost-analysis/runs/exp7-9-kimi25-20260730-v2",
"git_commit": "4a7f37cf278bd15948c409f14533017c4c7fbc29",
"command": "python demo.py --live --scenario all --model kimi-k2.5 --save-trace TRACE --output REPORT",
"provider_receipt_count": 32,
"status_reasons": [
"The real 2x2 run covers one eight-turn refund workflow; the manuscript asks for several representative task types and aggregate task-level p50/p95/p99.",
"Reasoning-token usage and provider response IDs are recorded, but success-quality equivalence across optimizations is not independently judged.",
"The 32 measured calls have unique provider response IDs; 16 cache-warmup calls were intentionally excluded from measured traces and do not have retained receipts."
],
"inputs": [
{
"path": "chapter7/agent-cost-analysis/agent.py",
"bytes": 17109,
"sha256": "30866b34ead7ff2897964aaf1e07867691102982971903f8a2a4172c48bfd718"
},
{
"path": "chapter7/agent-cost-analysis/tracer.py",
"bytes": 12309,
"sha256": "fb673ac8f10ca037b6df3822e00e6cbb21b8381b731736fb1b2a30748e7226fe"
},
{
"path": "chapter7/agent-cost-analysis/demo.py",
"bytes": 13477,
"sha256": "75dc27633829fe2a730c5654a38f6af90fd58eceee630dfa985e386fa536c104"
},
{
"path": "chapter7/agent-cost-analysis/config.py",
"bytes": 5701,
"sha256": "0a92de4849994e74b28e3b5ad6c308cc154a2b984d8827f859b7f15d9fbbb463"
},
{
"path": "chapter7/model-benchmark/campaign_config.json",
"bytes": 8103,
"sha256": "9a839ad907852798b35af5b4623814c343943ae1596a78d650d1a1affc93b17a"
}
],
"artifacts": [
{
"path": "chapter7/agent-cost-analysis/runs/exp7-9-kimi25-20260730-v2/report.json",
"bytes": 17810,
"sha256": "92b0ee29c7df3dd28778d625fe699662dee56a5401141631ead450cd2ca37ace"
},
{
"path": "chapter7/agent-cost-analysis/runs/exp7-9-kimi25-20260730-v2/trace.json",
"bytes": 17810,
"sha256": "92b0ee29c7df3dd28778d625fe699662dee56a5401141631ead450cd2ca37ace"
}
]
}
chapter7/agent-cost-analysis/runs/exp7-9-kimi25-20260730-v2/report.json
+554
View File
@@ -0,0 +1,554 @@
{
"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": 0.01574031350707,
"component_costs": {
"uncached_input_cost": 0.0118080062343888,
"cached_input_cost": 0.0,
"output_cost": 0.0039323072726812,
"uncached_input_tokens": 19974,
"cached_input_tokens": 0,
"output_tokens": 1267,
"tool_ctx_tokens": 10749
},
"cost_distribution": {
"n": 8,
"mean": 0.00196753918838375,
"p50": 0.0019544041559152,
"p95": 0.0026135574027031996,
"p99": 0.0026135574027031996,
"max": 0.0026135574027031996
},
"spans": [
{
"step": "turn-1",
"tool": "query_order",
"kind": "llm",
"prompt_tokens": 1015,
"cached_tokens": 0,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 300,
"latency_s": 5.299084663391113,
"response_id": "chatcmpl-6a6a7cb80695ae5455eab84a",
"response_model": "kimi-k2.5",
"response_created": 1785363640
},
{
"step": "turn-2",
"tool": "query_logistics",
"kind": "llm",
"prompt_tokens": 1706,
"cached_tokens": 0,
"completion_tokens": 147,
"reasoning_tokens": 1,
"tool_ctx_tokens": 899,
"latency_s": 5.079176902770996,
"response_id": "chatcmpl-6a6a7cbd80925af8edb8bb5e",
"response_model": "kimi-k2.5",
"response_created": 1785363646
},
{
"step": "turn-3",
"tool": "check_refund_policy",
"kind": "llm",
"prompt_tokens": 2081,
"cached_tokens": 0,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 1164,
"latency_s": 3.0797362327575684,
"response_id": "chatcmpl-6a6a7cc24511d264b10f37dd",
"response_model": "kimi-k2.5",
"response_created": 1785363651
},
{
"step": "turn-4",
"tool": "query_knowledge_base",
"kind": "llm",
"prompt_tokens": 2466,
"cached_tokens": 0,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 1482,
"latency_s": 3.4901974201202393,
"response_id": "chatcmpl-6a6a7cc5edbcdbb3613f3353",
"response_model": "kimi-k2.5",
"response_created": 1785363654
},
{
"step": "turn-5",
"tool": "query_user_history",
"kind": "llm",
"prompt_tokens": 2753,
"cached_tokens": 0,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 1585,
"latency_s": 6.93122410774231,
"response_id": "chatcmpl-6a6a7cc97f6a7380b55ebedb",
"response_model": "kimi-k2.5",
"response_created": 1785363658
},
{
"step": "turn-6",
"tool": "issue_refund",
"kind": "llm",
"prompt_tokens": 3048,
"cached_tokens": 0,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 1693,
"latency_s": 5.43744421005249,
"response_id": "chatcmpl-6a6a7cd0d7374244555b9001",
"response_model": "kimi-k2.5",
"response_created": 1785363665
},
{
"step": "turn-7",
"tool": "send_notification",
"kind": "llm",
"prompt_tokens": 3324,
"cached_tokens": 0,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 1779,
"latency_s": 5.579896926879883,
"response_id": "chatcmpl-6a6a7cd56f58f5f62fa2981a",
"response_model": "kimi-k2.5",
"response_created": 1785363670
},
{
"step": "turn-8",
"tool": "close_ticket",
"kind": "llm",
"prompt_tokens": 3581,
"cached_tokens": 0,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 1847,
"latency_s": 5.334557056427002,
"response_id": "chatcmpl-6a6a7cdb2e6a18d37452de21",
"response_model": "kimi-k2.5",
"response_created": 1785363676
}
]
},
{
"key": "kv",
"name": "KV 仅缓存(稳定前缀/不压缩)",
"total_cost": 0.0082537957670069,
"component_costs": {
"uncached_input_cost": 0.0027956374027448,
"cached_input_cost": 0.0015289547279445,
"output_cost": 0.0039292036363176,
"uncached_input_tokens": 4729,
"cached_input_tokens": 14779,
"output_tokens": 1266,
"tool_ctx_tokens": 10749
},
"cost_distribution": {
"n": 8,
"mean": 0.0010317244708758625,
"p50": 0.001053935792344,
"p95": 0.0011930969351368,
"p99": 0.0011930969351368,
"max": 0.0011930969351368
},
"spans": [
{
"step": "turn-1",
"tool": "query_order",
"kind": "llm",
"prompt_tokens": 955,
"cached_tokens": 955,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 300,
"latency_s": 2.981578826904297,
"response_id": "chatcmpl-6a6a7d043905097c262cd2d8",
"response_model": "kimi-k2.5",
"response_created": 1785363716
},
{
"step": "turn-2",
"tool": "query_logistics",
"kind": "llm",
"prompt_tokens": 1652,
"cached_tokens": 512,
"completion_tokens": 146,
"reasoning_tokens": 1,
"tool_ctx_tokens": 899,
"latency_s": 8.04120397567749,
"response_id": "chatcmpl-6a6a7d07d5eb4229617017c7",
"response_model": "kimi-k2.5",
"response_created": 1785363719
},
{
"step": "turn-3",
"tool": "check_refund_policy",
"kind": "llm",
"prompt_tokens": 2023,
"cached_tokens": 1024,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 1164,
"latency_s": 6.327085256576538,
"response_id": "chatcmpl-6a6a7d0f3905097c262cd2f5",
"response_model": "kimi-k2.5",
"response_created": 1785363727
},
{
"step": "turn-4",
"tool": "query_knowledge_base",
"kind": "llm",
"prompt_tokens": 2408,
"cached_tokens": 1792,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 1482,
"latency_s": 4.883957862854004,
"response_id": "chatcmpl-6a6a7d15bb40cba1f65cc486",
"response_model": "kimi-k2.5",
"response_created": 1785363733
},
{
"step": "turn-5",
"tool": "query_user_history",
"kind": "llm",
"prompt_tokens": 2696,
"cached_tokens": 2048,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 1585,
"latency_s": 5.0474817752838135,
"response_id": "chatcmpl-6a6a7d1adc87cefde7ebcca2",
"response_model": "kimi-k2.5",
"response_created": 1785363738
},
{
"step": "turn-6",
"tool": "issue_refund",
"kind": "llm",
"prompt_tokens": 2986,
"cached_tokens": 2560,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 1693,
"latency_s": 3.6142687797546387,
"response_id": "chatcmpl-6a6a7d1f3905097c262cd332",
"response_model": "kimi-k2.5",
"response_created": 1785363743
},
{
"step": "turn-7",
"tool": "send_notification",
"kind": "llm",
"prompt_tokens": 3266,
"cached_tokens": 2816,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 1779,
"latency_s": 3.981088161468506,
"response_id": "chatcmpl-6a6a7d233905097c262cd33e",
"response_model": "kimi-k2.5",
"response_created": 1785363747
},
{
"step": "turn-8",
"tool": "close_ticket",
"kind": "llm",
"prompt_tokens": 3522,
"cached_tokens": 3072,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 1847,
"latency_s": 5.233341217041016,
"response_id": "chatcmpl-6a6a7d27d5eb42296170182d",
"response_model": "kimi-k2.5",
"response_created": 1785363751
}
]
},
{
"key": "compress",
"name": "仅压缩(前缀不稳定/摘要)",
"total_cost": 0.0125982511692596,
"component_costs": {
"uncached_input_cost": 0.0089390638965752,
"cached_input_cost": 0.0,
"output_cost": 0.0036591872726844,
"uncached_input_tokens": 15121,
"cached_input_tokens": 0,
"output_tokens": 1179,
"tool_ctx_tokens": 6036
},
"cost_distribution": {
"n": 8,
"mean": 0.00157478139615745,
"p50": 0.0016801018182384,
"p95": 0.0018338057143504,
"p99": 0.0018338057143504,
"max": 0.0018338057143504
},
"spans": [
{
"step": "turn-1",
"tool": "query_order",
"kind": "llm",
"prompt_tokens": 1010,
"cached_tokens": 0,
"completion_tokens": 121,
"reasoning_tokens": 1,
"tool_ctx_tokens": 300,
"latency_s": 3.843111276626587,
"response_id": "chatcmpl-6a6a7d2c96a5dde81c3844dd",
"response_model": "kimi-k2.5",
"response_created": 1785363756
},
{
"step": "turn-2",
"tool": "query_logistics",
"kind": "llm",
"prompt_tokens": 1671,
"cached_tokens": 0,
"completion_tokens": 110,
"reasoning_tokens": 1,
"tool_ctx_tokens": 899,
"latency_s": 3.103135108947754,
"response_id": "chatcmpl-6a6a7d3006fe5c9e72518409",
"response_model": "kimi-k2.5",
"response_created": 1785363760
},
{
"step": "turn-3",
"tool": "check_refund_policy",
"kind": "llm",
"prompt_tokens": 2002,
"cached_tokens": 0,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 1164,
"latency_s": 5.465490102767944,
"response_id": "chatcmpl-6a6a7d3384ead76d6951b7bb",
"response_model": "kimi-k2.5",
"response_created": 1785363763
},
{
"step": "turn-4",
"tool": "query_knowledge_base",
"kind": "llm",
"prompt_tokens": 2136,
"cached_tokens": 0,
"completion_tokens": 149,
"reasoning_tokens": 1,
"tool_ctx_tokens": 1231,
"latency_s": 3.5718801021575928,
"response_id": "chatcmpl-6a6a7d3880925af8edb8bcdd",
"response_model": "kimi-k2.5",
"response_created": 1785363769
},
{
"step": "turn-5",
"tool": "query_user_history",
"kind": "llm",
"prompt_tokens": 1916,
"cached_tokens": 0,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 780,
"latency_s": 3.5103132724761963,
"response_id": "chatcmpl-6a6a7d3cfa52c1b646ff684d",
"response_model": "kimi-k2.5",
"response_created": 1785363772
},
{
"step": "turn-6",
"tool": "issue_refund",
"kind": "llm",
"prompt_tokens": 2022,
"cached_tokens": 0,
"completion_tokens": 159,
"reasoning_tokens": 1,
"tool_ctx_tokens": 677,
"latency_s": 3.597494125366211,
"response_id": "chatcmpl-6a6a7d3f8a024a47783f03bf",
"response_model": "kimi-k2.5",
"response_created": 1785363776
},
{
"step": "turn-7",
"tool": "send_notification",
"kind": "llm",
"prompt_tokens": 2102,
"cached_tokens": 0,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 486,
"latency_s": 9.166883945465088,
"response_id": "chatcmpl-6a6a7d43503e5013c8fe6ef8",
"response_model": "kimi-k2.5",
"response_created": 1785363779
},
{
"step": "turn-8",
"tool": "close_ticket",
"kind": "llm",
"prompt_tokens": 2262,
"cached_tokens": 0,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 499,
"latency_s": 4.3432776927948,
"response_id": "chatcmpl-6a6a7d4c687ea3db1a5a4d6c",
"response_model": "kimi-k2.5",
"response_created": 1785363789
}
]
},
{
"key": "both",
"name": "B 优化(KV缓存+压缩)",
"total_cost": 0.009057608026520501,
"component_costs": {
"uncached_input_cost": 0.0042445922080159995,
"cached_input_cost": 0.0008403612730964999,
"output_cost": 0.003972654545408001,
"uncached_input_tokens": 7180,
"cached_input_tokens": 8123,
"output_tokens": 1280,
"tool_ctx_tokens": 6036
},
"cost_distribution": {
"n": 8,
"mean": 0.0011322010033150626,
"p50": 0.0011570356364336,
"p95": 0.0014060359481248,
"p99": 0.0014060359481248,
"max": 0.0014060359481248
},
"spans": [
{
"step": "turn-1",
"tool": "query_order",
"kind": "llm",
"prompt_tokens": 955,
"cached_tokens": 955,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 300,
"latency_s": 3.2073097229003906,
"response_id": "chatcmpl-6a6a7d7658a6e8702ecebaee",
"response_model": "kimi-k2.5",
"response_created": 1785363830
},
{
"step": "turn-2",
"tool": "query_logistics",
"kind": "llm",
"prompt_tokens": 1652,
"cached_tokens": 512,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 899,
"latency_s": 7.249981880187988,
"response_id": "chatcmpl-6a6a7d792d20c6aa1053113f",
"response_model": "kimi-k2.5",
"response_created": 1785363833
},
{
"step": "turn-3",
"tool": "check_refund_policy",
"kind": "llm",
"prompt_tokens": 2038,
"cached_tokens": 1024,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 1164,
"latency_s": 4.833154916763306,
"response_id": "chatcmpl-6a6a7d80f9aa90a3ebfd7fe5",
"response_model": "kimi-k2.5",
"response_created": 1785363841
},
{
"step": "turn-4",
"tool": "query_knowledge_base",
"kind": "llm",
"prompt_tokens": 2172,
"cached_tokens": 768,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 1231,
"latency_s": 5.391065835952759,
"response_id": "chatcmpl-6a6a7d852d20c6aa10531154",
"response_model": "kimi-k2.5",
"response_created": 1785363846
},
{
"step": "turn-5",
"tool": "query_user_history",
"kind": "llm",
"prompt_tokens": 1962,
"cached_tokens": 1024,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 780,
"latency_s": 5.175268888473511,
"response_id": "chatcmpl-6a6a7d8b2d20c6aa10531162",
"response_model": "kimi-k2.5",
"response_created": 1785363851
},
{
"step": "turn-6",
"tool": "issue_refund",
"kind": "llm",
"prompt_tokens": 2063,
"cached_tokens": 1024,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 677,
"latency_s": 5.356127977371216,
"response_id": "chatcmpl-6a6a7d90a183ecb32232c19d",
"response_model": "kimi-k2.5",
"response_created": 1785363856
},
{
"step": "turn-7",
"tool": "send_notification",
"kind": "llm",
"prompt_tokens": 2148,
"cached_tokens": 1280,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 486,
"latency_s": 7.17538595199585,
"response_id": "chatcmpl-6a6a7d953905097c262cd43c",
"response_model": "kimi-k2.5",
"response_created": 1785363862
},
{
"step": "turn-8",
"tool": "close_ticket",
"kind": "llm",
"prompt_tokens": 2313,
"cached_tokens": 1536,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 499,
"latency_s": 5.300028085708618,
"response_id": "chatcmpl-6a6a7d9d56e2191f9ae786d6",
"response_model": "kimi-k2.5",
"response_created": 1785363869
}
]
}
]
}
chapter7/agent-cost-analysis/runs/exp7-9-kimi25-20260730-v2/trace.json
+554
View File
@@ -0,0 +1,554 @@
{
"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": 0.01574031350707,
"component_costs": {
"uncached_input_cost": 0.0118080062343888,
"cached_input_cost": 0.0,
"output_cost": 0.0039323072726812,
"uncached_input_tokens": 19974,
"cached_input_tokens": 0,
"output_tokens": 1267,
"tool_ctx_tokens": 10749
},
"cost_distribution": {
"n": 8,
"mean": 0.00196753918838375,
"p50": 0.0019544041559152,
"p95": 0.0026135574027031996,
"p99": 0.0026135574027031996,
"max": 0.0026135574027031996
},
"spans": [
{
"step": "turn-1",
"tool": "query_order",
"kind": "llm",
"prompt_tokens": 1015,
"cached_tokens": 0,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 300,
"latency_s": 5.299084663391113,
"response_id": "chatcmpl-6a6a7cb80695ae5455eab84a",
"response_model": "kimi-k2.5",
"response_created": 1785363640
},
{
"step": "turn-2",
"tool": "query_logistics",
"kind": "llm",
"prompt_tokens": 1706,
"cached_tokens": 0,
"completion_tokens": 147,
"reasoning_tokens": 1,
"tool_ctx_tokens": 899,
"latency_s": 5.079176902770996,
"response_id": "chatcmpl-6a6a7cbd80925af8edb8bb5e",
"response_model": "kimi-k2.5",
"response_created": 1785363646
},
{
"step": "turn-3",
"tool": "check_refund_policy",
"kind": "llm",
"prompt_tokens": 2081,
"cached_tokens": 0,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 1164,
"latency_s": 3.0797362327575684,
"response_id": "chatcmpl-6a6a7cc24511d264b10f37dd",
"response_model": "kimi-k2.5",
"response_created": 1785363651
},
{
"step": "turn-4",
"tool": "query_knowledge_base",
"kind": "llm",
"prompt_tokens": 2466,
"cached_tokens": 0,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 1482,
"latency_s": 3.4901974201202393,
"response_id": "chatcmpl-6a6a7cc5edbcdbb3613f3353",
"response_model": "kimi-k2.5",
"response_created": 1785363654
},
{
"step": "turn-5",
"tool": "query_user_history",
"kind": "llm",
"prompt_tokens": 2753,
"cached_tokens": 0,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 1585,
"latency_s": 6.93122410774231,
"response_id": "chatcmpl-6a6a7cc97f6a7380b55ebedb",
"response_model": "kimi-k2.5",
"response_created": 1785363658
},
{
"step": "turn-6",
"tool": "issue_refund",
"kind": "llm",
"prompt_tokens": 3048,
"cached_tokens": 0,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 1693,
"latency_s": 5.43744421005249,
"response_id": "chatcmpl-6a6a7cd0d7374244555b9001",
"response_model": "kimi-k2.5",
"response_created": 1785363665
},
{
"step": "turn-7",
"tool": "send_notification",
"kind": "llm",
"prompt_tokens": 3324,
"cached_tokens": 0,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 1779,
"latency_s": 5.579896926879883,
"response_id": "chatcmpl-6a6a7cd56f58f5f62fa2981a",
"response_model": "kimi-k2.5",
"response_created": 1785363670
},
{
"step": "turn-8",
"tool": "close_ticket",
"kind": "llm",
"prompt_tokens": 3581,
"cached_tokens": 0,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 1847,
"latency_s": 5.334557056427002,
"response_id": "chatcmpl-6a6a7cdb2e6a18d37452de21",
"response_model": "kimi-k2.5",
"response_created": 1785363676
}
]
},
{
"key": "kv",
"name": "KV 仅缓存(稳定前缀/不压缩)",
"total_cost": 0.0082537957670069,
"component_costs": {
"uncached_input_cost": 0.0027956374027448,
"cached_input_cost": 0.0015289547279445,
"output_cost": 0.0039292036363176,
"uncached_input_tokens": 4729,
"cached_input_tokens": 14779,
"output_tokens": 1266,
"tool_ctx_tokens": 10749
},
"cost_distribution": {
"n": 8,
"mean": 0.0010317244708758625,
"p50": 0.001053935792344,
"p95": 0.0011930969351368,
"p99": 0.0011930969351368,
"max": 0.0011930969351368
},
"spans": [
{
"step": "turn-1",
"tool": "query_order",
"kind": "llm",
"prompt_tokens": 955,
"cached_tokens": 955,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 300,
"latency_s": 2.981578826904297,
"response_id": "chatcmpl-6a6a7d043905097c262cd2d8",
"response_model": "kimi-k2.5",
"response_created": 1785363716
},
{
"step": "turn-2",
"tool": "query_logistics",
"kind": "llm",
"prompt_tokens": 1652,
"cached_tokens": 512,
"completion_tokens": 146,
"reasoning_tokens": 1,
"tool_ctx_tokens": 899,
"latency_s": 8.04120397567749,
"response_id": "chatcmpl-6a6a7d07d5eb4229617017c7",
"response_model": "kimi-k2.5",
"response_created": 1785363719
},
{
"step": "turn-3",
"tool": "check_refund_policy",
"kind": "llm",
"prompt_tokens": 2023,
"cached_tokens": 1024,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 1164,
"latency_s": 6.327085256576538,
"response_id": "chatcmpl-6a6a7d0f3905097c262cd2f5",
"response_model": "kimi-k2.5",
"response_created": 1785363727
},
{
"step": "turn-4",
"tool": "query_knowledge_base",
"kind": "llm",
"prompt_tokens": 2408,
"cached_tokens": 1792,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 1482,
"latency_s": 4.883957862854004,
"response_id": "chatcmpl-6a6a7d15bb40cba1f65cc486",
"response_model": "kimi-k2.5",
"response_created": 1785363733
},
{
"step": "turn-5",
"tool": "query_user_history",
"kind": "llm",
"prompt_tokens": 2696,
"cached_tokens": 2048,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 1585,
"latency_s": 5.0474817752838135,
"response_id": "chatcmpl-6a6a7d1adc87cefde7ebcca2",
"response_model": "kimi-k2.5",
"response_created": 1785363738
},
{
"step": "turn-6",
"tool": "issue_refund",
"kind": "llm",
"prompt_tokens": 2986,
"cached_tokens": 2560,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 1693,
"latency_s": 3.6142687797546387,
"response_id": "chatcmpl-6a6a7d1f3905097c262cd332",
"response_model": "kimi-k2.5",
"response_created": 1785363743
},
{
"step": "turn-7",
"tool": "send_notification",
"kind": "llm",
"prompt_tokens": 3266,
"cached_tokens": 2816,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 1779,
"latency_s": 3.981088161468506,
"response_id": "chatcmpl-6a6a7d233905097c262cd33e",
"response_model": "kimi-k2.5",
"response_created": 1785363747
},
{
"step": "turn-8",
"tool": "close_ticket",
"kind": "llm",
"prompt_tokens": 3522,
"cached_tokens": 3072,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 1847,
"latency_s": 5.233341217041016,
"response_id": "chatcmpl-6a6a7d27d5eb42296170182d",
"response_model": "kimi-k2.5",
"response_created": 1785363751
}
]
},
{
"key": "compress",
"name": "仅压缩(前缀不稳定/摘要)",
"total_cost": 0.0125982511692596,
"component_costs": {
"uncached_input_cost": 0.0089390638965752,
"cached_input_cost": 0.0,
"output_cost": 0.0036591872726844,
"uncached_input_tokens": 15121,
"cached_input_tokens": 0,
"output_tokens": 1179,
"tool_ctx_tokens": 6036
},
"cost_distribution": {
"n": 8,
"mean": 0.00157478139615745,
"p50": 0.0016801018182384,
"p95": 0.0018338057143504,
"p99": 0.0018338057143504,
"max": 0.0018338057143504
},
"spans": [
{
"step": "turn-1",
"tool": "query_order",
"kind": "llm",
"prompt_tokens": 1010,
"cached_tokens": 0,
"completion_tokens": 121,
"reasoning_tokens": 1,
"tool_ctx_tokens": 300,
"latency_s": 3.843111276626587,
"response_id": "chatcmpl-6a6a7d2c96a5dde81c3844dd",
"response_model": "kimi-k2.5",
"response_created": 1785363756
},
{
"step": "turn-2",
"tool": "query_logistics",
"kind": "llm",
"prompt_tokens": 1671,
"cached_tokens": 0,
"completion_tokens": 110,
"reasoning_tokens": 1,
"tool_ctx_tokens": 899,
"latency_s": 3.103135108947754,
"response_id": "chatcmpl-6a6a7d3006fe5c9e72518409",
"response_model": "kimi-k2.5",
"response_created": 1785363760
},
{
"step": "turn-3",
"tool": "check_refund_policy",
"kind": "llm",
"prompt_tokens": 2002,
"cached_tokens": 0,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 1164,
"latency_s": 5.465490102767944,
"response_id": "chatcmpl-6a6a7d3384ead76d6951b7bb",
"response_model": "kimi-k2.5",
"response_created": 1785363763
},
{
"step": "turn-4",
"tool": "query_knowledge_base",
"kind": "llm",
"prompt_tokens": 2136,
"cached_tokens": 0,
"completion_tokens": 149,
"reasoning_tokens": 1,
"tool_ctx_tokens": 1231,
"latency_s": 3.5718801021575928,
"response_id": "chatcmpl-6a6a7d3880925af8edb8bcdd",
"response_model": "kimi-k2.5",
"response_created": 1785363769
},
{
"step": "turn-5",
"tool": "query_user_history",
"kind": "llm",
"prompt_tokens": 1916,
"cached_tokens": 0,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 780,
"latency_s": 3.5103132724761963,
"response_id": "chatcmpl-6a6a7d3cfa52c1b646ff684d",
"response_model": "kimi-k2.5",
"response_created": 1785363772
},
{
"step": "turn-6",
"tool": "issue_refund",
"kind": "llm",
"prompt_tokens": 2022,
"cached_tokens": 0,
"completion_tokens": 159,
"reasoning_tokens": 1,
"tool_ctx_tokens": 677,
"latency_s": 3.597494125366211,
"response_id": "chatcmpl-6a6a7d3f8a024a47783f03bf",
"response_model": "kimi-k2.5",
"response_created": 1785363776
},
{
"step": "turn-7",
"tool": "send_notification",
"kind": "llm",
"prompt_tokens": 2102,
"cached_tokens": 0,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 486,
"latency_s": 9.166883945465088,
"response_id": "chatcmpl-6a6a7d43503e5013c8fe6ef8",
"response_model": "kimi-k2.5",
"response_created": 1785363779
},
{
"step": "turn-8",
"tool": "close_ticket",
"kind": "llm",
"prompt_tokens": 2262,
"cached_tokens": 0,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 499,
"latency_s": 4.3432776927948,
"response_id": "chatcmpl-6a6a7d4c687ea3db1a5a4d6c",
"response_model": "kimi-k2.5",
"response_created": 1785363789
}
]
},
{
"key": "both",
"name": "B 优化(KV缓存+压缩)",
"total_cost": 0.009057608026520501,
"component_costs": {
"uncached_input_cost": 0.0042445922080159995,
"cached_input_cost": 0.0008403612730964999,
"output_cost": 0.003972654545408001,
"uncached_input_tokens": 7180,
"cached_input_tokens": 8123,
"output_tokens": 1280,
"tool_ctx_tokens": 6036
},
"cost_distribution": {
"n": 8,
"mean": 0.0011322010033150626,
"p50": 0.0011570356364336,
"p95": 0.0014060359481248,
"p99": 0.0014060359481248,
"max": 0.0014060359481248
},
"spans": [
{
"step": "turn-1",
"tool": "query_order",
"kind": "llm",
"prompt_tokens": 955,
"cached_tokens": 955,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 300,
"latency_s": 3.2073097229003906,
"response_id": "chatcmpl-6a6a7d7658a6e8702ecebaee",
"response_model": "kimi-k2.5",
"response_created": 1785363830
},
{
"step": "turn-2",
"tool": "query_logistics",
"kind": "llm",
"prompt_tokens": 1652,
"cached_tokens": 512,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 899,
"latency_s": 7.249981880187988,
"response_id": "chatcmpl-6a6a7d792d20c6aa1053113f",
"response_model": "kimi-k2.5",
"response_created": 1785363833
},
{
"step": "turn-3",
"tool": "check_refund_policy",
"kind": "llm",
"prompt_tokens": 2038,
"cached_tokens": 1024,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 1164,
"latency_s": 4.833154916763306,
"response_id": "chatcmpl-6a6a7d80f9aa90a3ebfd7fe5",
"response_model": "kimi-k2.5",
"response_created": 1785363841
},
{
"step": "turn-4",
"tool": "query_knowledge_base",
"kind": "llm",
"prompt_tokens": 2172,
"cached_tokens": 768,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 1231,
"latency_s": 5.391065835952759,
"response_id": "chatcmpl-6a6a7d852d20c6aa10531154",
"response_model": "kimi-k2.5",
"response_created": 1785363846
},
{
"step": "turn-5",
"tool": "query_user_history",
"kind": "llm",
"prompt_tokens": 1962,
"cached_tokens": 1024,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 780,
"latency_s": 5.175268888473511,
"response_id": "chatcmpl-6a6a7d8b2d20c6aa10531162",
"response_model": "kimi-k2.5",
"response_created": 1785363851
},
{
"step": "turn-6",
"tool": "issue_refund",
"kind": "llm",
"prompt_tokens": 2063,
"cached_tokens": 1024,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 677,
"latency_s": 5.356127977371216,
"response_id": "chatcmpl-6a6a7d90a183ecb32232c19d",
"response_model": "kimi-k2.5",
"response_created": 1785363856
},
{
"step": "turn-7",
"tool": "send_notification",
"kind": "llm",
"prompt_tokens": 2148,
"cached_tokens": 1280,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 486,
"latency_s": 7.17538595199585,
"response_id": "chatcmpl-6a6a7d953905097c262cd43c",
"response_model": "kimi-k2.5",
"response_created": 1785363862
},
{
"step": "turn-8",
"tool": "close_ticket",
"kind": "llm",
"prompt_tokens": 2313,
"cached_tokens": 1536,
"completion_tokens": 160,
"reasoning_tokens": 1,
"tool_ctx_tokens": 499,
"latency_s": 5.300028085708618,
"response_id": "chatcmpl-6a6a7d9d56e2191f9ae786d6",
"response_model": "kimi-k2.5",
"response_created": 1785363869
}
]
}
]
}