Files
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

81 lines
16 KiB
JSON

{"id": "test-ar-000", "gold_label": "ar", "source_label": "ar", "prediction": "ar", "response": "ar", "correct": true, "input_tokens": 114, "output_tokens": 2, "latency_seconds": 0.021567012183368206}
{"id": "test-ar-001", "gold_label": "ar", "source_label": "ar", "prediction": "ar", "response": "ar", "correct": true, "input_tokens": 156, "output_tokens": 2, "latency_seconds": 0.021308219991624355}
{"id": "test-ar-002", "gold_label": "ar", "source_label": "ar", "prediction": "ar", "response": "ar", "correct": true, "input_tokens": 156, "output_tokens": 2, "latency_seconds": 0.021030287258327007}
{"id": "test-ar-003", "gold_label": "ar", "source_label": "ar", "prediction": "ar", "response": "ar", "correct": true, "input_tokens": 91, "output_tokens": 2, "latency_seconds": 0.020903524942696095}
{"id": "test-bg-000", "gold_label": "ot", "source_label": "bg", "prediction": "ru", "response": "ru", "correct": false, "input_tokens": 147, "output_tokens": 2, "latency_seconds": 0.020970353856682777}
{"id": "test-bg-001", "gold_label": "ot", "source_label": "bg", "prediction": "ru", "response": "ru", "correct": false, "input_tokens": 69, "output_tokens": 2, "latency_seconds": 0.021014241501688957}
{"id": "test-bg-002", "gold_label": "ot", "source_label": "bg", "prediction": "ru", "response": "ru", "correct": false, "input_tokens": 118, "output_tokens": 2, "latency_seconds": 0.021321195177733898}
{"id": "test-bg-003", "gold_label": "ot", "source_label": "bg", "prediction": "ot", "response": "ot", "correct": true, "input_tokens": 85, "output_tokens": 2, "latency_seconds": 0.020931887440383434}
{"id": "test-de-000", "gold_label": "de", "source_label": "de", "prediction": "de", "response": "de", "correct": true, "input_tokens": 174, "output_tokens": 2, "latency_seconds": 0.021052807569503784}
{"id": "test-de-001", "gold_label": "de", "source_label": "de", "prediction": "de", "response": "de", "correct": true, "input_tokens": 43, "output_tokens": 2, "latency_seconds": 0.021180440671741962}
{"id": "test-de-002", "gold_label": "de", "source_label": "de", "prediction": "de", "response": "de", "correct": true, "input_tokens": 60, "output_tokens": 2, "latency_seconds": 0.02106414269655943}
{"id": "test-de-003", "gold_label": "de", "source_label": "de", "prediction": "de", "response": "de", "correct": true, "input_tokens": 43, "output_tokens": 2, "latency_seconds": 0.021330668590962887}
{"id": "test-el-000", "gold_label": "el", "source_label": "el", "prediction": "el", "response": "el", "correct": true, "input_tokens": 165, "output_tokens": 2, "latency_seconds": 0.021219544112682343}
{"id": "test-el-001", "gold_label": "el", "source_label": "el", "prediction": "el", "response": "el", "correct": true, "input_tokens": 111, "output_tokens": 2, "latency_seconds": 0.020995447412133217}
{"id": "test-el-002", "gold_label": "el", "source_label": "el", "prediction": "el", "response": "el", "correct": true, "input_tokens": 92, "output_tokens": 2, "latency_seconds": 0.020973561331629753}
{"id": "test-el-003", "gold_label": "el", "source_label": "el", "prediction": "el", "response": "el", "correct": true, "input_tokens": 92, "output_tokens": 2, "latency_seconds": 0.02086208201944828}
{"id": "test-en-000", "gold_label": "en", "source_label": "en", "prediction": "en", "response": "en", "correct": true, "input_tokens": 50, "output_tokens": 2, "latency_seconds": 0.021106958389282227}
{"id": "test-en-001", "gold_label": "en", "source_label": "en", "prediction": "en", "response": "en", "correct": true, "input_tokens": 69, "output_tokens": 2, "latency_seconds": 0.021015582606196404}
{"id": "test-en-002", "gold_label": "en", "source_label": "en", "prediction": "en", "response": "en", "correct": true, "input_tokens": 81, "output_tokens": 2, "latency_seconds": 0.020907645113766193}
{"id": "test-en-003", "gold_label": "en", "source_label": "en", "prediction": "en", "response": "en", "correct": true, "input_tokens": 57, "output_tokens": 2, "latency_seconds": 0.020868214778602123}
{"id": "test-es-000", "gold_label": "es", "source_label": "es", "prediction": "es", "response": "es", "correct": true, "input_tokens": 149, "output_tokens": 2, "latency_seconds": 0.021015141159296036}
{"id": "test-es-001", "gold_label": "es", "source_label": "es", "prediction": "es", "response": "es", "correct": true, "input_tokens": 63, "output_tokens": 2, "latency_seconds": 0.020898624323308468}
{"id": "test-es-002", "gold_label": "es", "source_label": "es", "prediction": "es", "response": "es", "correct": true, "input_tokens": 134, "output_tokens": 2, "latency_seconds": 0.020956451073288918}
{"id": "test-es-003", "gold_label": "es", "source_label": "es", "prediction": "es", "response": "es", "correct": true, "input_tokens": 72, "output_tokens": 2, "latency_seconds": 0.020912745036184788}
{"id": "test-fr-000", "gold_label": "fr", "source_label": "fr", "prediction": "fr", "response": "fr", "correct": true, "input_tokens": 71, "output_tokens": 2, "latency_seconds": 0.020891825668513775}
{"id": "test-fr-001", "gold_label": "fr", "source_label": "fr", "prediction": "fr", "response": "fr", "correct": true, "input_tokens": 57, "output_tokens": 2, "latency_seconds": 0.020838186144828796}
{"id": "test-fr-002", "gold_label": "fr", "source_label": "fr", "prediction": "fr", "response": "fr", "correct": true, "input_tokens": 85, "output_tokens": 2, "latency_seconds": 0.02096572984009981}
{"id": "test-fr-003", "gold_label": "fr", "source_label": "fr", "prediction": "fr", "response": "fr", "correct": true, "input_tokens": 65, "output_tokens": 2, "latency_seconds": 0.020963875576853752}
{"id": "test-hi-000", "gold_label": "hi", "source_label": "hi", "prediction": "hi", "response": "hi", "correct": true, "input_tokens": 86, "output_tokens": 2, "latency_seconds": 0.02084300108253956}
{"id": "test-hi-001", "gold_label": "hi", "source_label": "hi", "prediction": "hi", "response": "hi", "correct": true, "input_tokens": 86, "output_tokens": 2, "latency_seconds": 0.020935524255037308}
{"id": "test-hi-002", "gold_label": "hi", "source_label": "hi", "prediction": "hi", "response": "hi", "correct": true, "input_tokens": 153, "output_tokens": 2, "latency_seconds": 0.020963420160114765}
{"id": "test-hi-003", "gold_label": "hi", "source_label": "hi", "prediction": "hi", "response": "hi", "correct": true, "input_tokens": 124, "output_tokens": 2, "latency_seconds": 0.02094507310539484}
{"id": "test-it-000", "gold_label": "ot", "source_label": "it", "prediction": "ot", "response": "ot", "correct": true, "input_tokens": 44, "output_tokens": 2, "latency_seconds": 0.020852336660027504}
{"id": "test-it-001", "gold_label": "ot", "source_label": "it", "prediction": "ot", "response": "ot", "correct": true, "input_tokens": 49, "output_tokens": 2, "latency_seconds": 0.020954391919076443}
{"id": "test-it-002", "gold_label": "ot", "source_label": "it", "prediction": "ot", "response": "ot", "correct": true, "input_tokens": 96, "output_tokens": 2, "latency_seconds": 0.02085470873862505}
{"id": "test-it-003", "gold_label": "ot", "source_label": "it", "prediction": "ot", "response": "ot", "correct": true, "input_tokens": 44, "output_tokens": 2, "latency_seconds": 0.0210230415686965}
{"id": "test-ja-000", "gold_label": "ot", "source_label": "ja", "prediction": "ot", "response": "ot", "correct": true, "input_tokens": 193, "output_tokens": 2, "latency_seconds": 0.021084836684167385}
{"id": "test-ja-001", "gold_label": "ot", "source_label": "ja", "prediction": "ot", "response": "ot", "correct": true, "input_tokens": 100, "output_tokens": 2, "latency_seconds": 0.020785780623555183}
{"id": "test-ja-002", "gold_label": "ot", "source_label": "ja", "prediction": "ot", "response": "ot", "correct": true, "input_tokens": 121, "output_tokens": 2, "latency_seconds": 0.021001679822802544}
{"id": "test-ja-003", "gold_label": "ot", "source_label": "ja", "prediction": "ot", "response": "ot", "correct": true, "input_tokens": 134, "output_tokens": 2, "latency_seconds": 0.020998574793338776}
{"id": "test-nl-000", "gold_label": "ot", "source_label": "nl", "prediction": "ot", "response": "ot", "correct": true, "input_tokens": 76, "output_tokens": 2, "latency_seconds": 0.020837283693253994}
{"id": "test-nl-001", "gold_label": "ot", "source_label": "nl", "prediction": "ot", "response": "ot", "correct": true, "input_tokens": 46, "output_tokens": 2, "latency_seconds": 0.020906995981931686}
{"id": "test-nl-002", "gold_label": "ot", "source_label": "nl", "prediction": "ot", "response": "ot", "correct": true, "input_tokens": 44, "output_tokens": 2, "latency_seconds": 0.02119743824005127}
{"id": "test-nl-003", "gold_label": "ot", "source_label": "nl", "prediction": "ot", "response": "ot", "correct": true, "input_tokens": 81, "output_tokens": 2, "latency_seconds": 0.020859770476818085}
{"id": "test-pl-000", "gold_label": "ot", "source_label": "pl", "prediction": "ot", "response": "ot", "correct": true, "input_tokens": 64, "output_tokens": 2, "latency_seconds": 0.0209045996889472}
{"id": "test-pl-001", "gold_label": "ot", "source_label": "pl", "prediction": "ot", "response": "ot", "correct": true, "input_tokens": 60, "output_tokens": 2, "latency_seconds": 0.02100309729576111}
{"id": "test-pl-002", "gold_label": "ot", "source_label": "pl", "prediction": "ot", "response": "ot", "correct": true, "input_tokens": 71, "output_tokens": 2, "latency_seconds": 0.020983186550438404}
{"id": "test-pl-003", "gold_label": "ot", "source_label": "pl", "prediction": "ot", "response": "ot", "correct": true, "input_tokens": 90, "output_tokens": 2, "latency_seconds": 0.020953955128788948}
{"id": "test-pt-000", "gold_label": "ot", "source_label": "pt", "prediction": "ot", "response": "ot", "correct": true, "input_tokens": 62, "output_tokens": 2, "latency_seconds": 0.02100022416561842}
{"id": "test-pt-001", "gold_label": "ot", "source_label": "pt", "prediction": "es", "response": "es", "correct": false, "input_tokens": 51, "output_tokens": 2, "latency_seconds": 0.021064297296106815}
{"id": "test-pt-002", "gold_label": "ot", "source_label": "pt", "prediction": "ot", "response": "ot", "correct": true, "input_tokens": 46, "output_tokens": 2, "latency_seconds": 0.020892093889415264}
{"id": "test-pt-003", "gold_label": "ot", "source_label": "pt", "prediction": "ot", "response": "ot", "correct": true, "input_tokens": 62, "output_tokens": 2, "latency_seconds": 0.020917534828186035}
{"id": "test-ru-000", "gold_label": "ru", "source_label": "ru", "prediction": "ru", "response": "ru", "correct": true, "input_tokens": 94, "output_tokens": 2, "latency_seconds": 0.020882914774119854}
{"id": "test-ru-001", "gold_label": "ru", "source_label": "ru", "prediction": "ru", "response": "ru", "correct": true, "input_tokens": 55, "output_tokens": 2, "latency_seconds": 0.02089247014373541}
{"id": "test-ru-002", "gold_label": "ru", "source_label": "ru", "prediction": "ru", "response": "ru", "correct": true, "input_tokens": 55, "output_tokens": 2, "latency_seconds": 0.02086214069277048}
{"id": "test-ru-003", "gold_label": "ru", "source_label": "ru", "prediction": "ru", "response": "ru", "correct": true, "input_tokens": 104, "output_tokens": 2, "latency_seconds": 0.020866707898676395}
{"id": "test-sw-000", "gold_label": "ot", "source_label": "sw", "prediction": "ot", "response": "ot", "correct": true, "input_tokens": 101, "output_tokens": 2, "latency_seconds": 0.02101822104305029}
{"id": "test-sw-001", "gold_label": "ot", "source_label": "sw", "prediction": "ot", "response": "ot", "correct": true, "input_tokens": 97, "output_tokens": 2, "latency_seconds": 0.02105732262134552}
{"id": "test-sw-002", "gold_label": "ot", "source_label": "sw", "prediction": "ot", "response": "ot", "correct": true, "input_tokens": 80, "output_tokens": 2, "latency_seconds": 0.020854887552559376}
{"id": "test-sw-003", "gold_label": "ot", "source_label": "sw", "prediction": "ot", "response": "ot", "correct": true, "input_tokens": 73, "output_tokens": 2, "latency_seconds": 0.020936796441674232}
{"id": "test-th-000", "gold_label": "ot", "source_label": "th", "prediction": "ot", "response": "ot", "correct": true, "input_tokens": 259, "output_tokens": 2, "latency_seconds": 0.02173076570034027}
{"id": "test-th-001", "gold_label": "ot", "source_label": "th", "prediction": "ot", "response": "ot", "correct": true, "input_tokens": 257, "output_tokens": 2, "latency_seconds": 0.021232523024082184}
{"id": "test-th-002", "gold_label": "ot", "source_label": "th", "prediction": "ot", "response": "ot", "correct": true, "input_tokens": 108, "output_tokens": 2, "latency_seconds": 0.020946724340319633}
{"id": "test-th-003", "gold_label": "ot", "source_label": "th", "prediction": "ot", "response": "ot", "correct": true, "input_tokens": 122, "output_tokens": 2, "latency_seconds": 0.020870834589004517}
{"id": "test-tr-000", "gold_label": "tr", "source_label": "tr", "prediction": "tr", "response": "tr", "correct": true, "input_tokens": 92, "output_tokens": 2, "latency_seconds": 0.02091517671942711}
{"id": "test-tr-001", "gold_label": "tr", "source_label": "tr", "prediction": "tr", "response": "tr", "correct": true, "input_tokens": 92, "output_tokens": 2, "latency_seconds": 0.020825224928557873}
{"id": "test-tr-002", "gold_label": "tr", "source_label": "tr", "prediction": "tr", "response": "tr", "correct": true, "input_tokens": 71, "output_tokens": 2, "latency_seconds": 0.02104836329817772}
{"id": "test-tr-003", "gold_label": "tr", "source_label": "tr", "prediction": "tr", "response": "tr", "correct": true, "input_tokens": 120, "output_tokens": 2, "latency_seconds": 0.02091341372579336}
{"id": "test-ur-000", "gold_label": "ur", "source_label": "ur", "prediction": "ur", "response": "ur", "correct": true, "input_tokens": 129, "output_tokens": 2, "latency_seconds": 0.02105330489575863}
{"id": "test-ur-001", "gold_label": "ur", "source_label": "ur", "prediction": "ur", "response": "ur", "correct": true, "input_tokens": 117, "output_tokens": 2, "latency_seconds": 0.021038753911852837}
{"id": "test-ur-002", "gold_label": "ur", "source_label": "ur", "prediction": "ur", "response": "ur", "correct": true, "input_tokens": 166, "output_tokens": 2, "latency_seconds": 0.02175528835505247}
{"id": "test-ur-003", "gold_label": "ur", "source_label": "ur", "prediction": "ur", "response": "ur", "correct": true, "input_tokens": 64, "output_tokens": 2, "latency_seconds": 0.022008763626217842}
{"id": "test-vi-000", "gold_label": "vi", "source_label": "vi", "prediction": "vi", "response": "vi", "correct": true, "input_tokens": 123, "output_tokens": 2, "latency_seconds": 0.02193110343068838}
{"id": "test-vi-001", "gold_label": "vi", "source_label": "vi", "prediction": "vi", "response": "vi", "correct": true, "input_tokens": 176, "output_tokens": 2, "latency_seconds": 0.021714639849960804}
{"id": "test-vi-002", "gold_label": "vi", "source_label": "vi", "prediction": "vi", "response": "vi", "correct": true, "input_tokens": 66, "output_tokens": 2, "latency_seconds": 0.021408547647297382}
{"id": "test-vi-003", "gold_label": "vi", "source_label": "vi", "prediction": "vi", "response": "vi", "correct": true, "input_tokens": 103, "output_tokens": 2, "latency_seconds": 0.0215337872505188}
{"id": "test-zh-000", "gold_label": "zh", "source_label": "zh", "prediction": "zh", "response": "zh", "correct": true, "input_tokens": 85, "output_tokens": 2, "latency_seconds": 0.02103542722761631}
{"id": "test-zh-001", "gold_label": "zh", "source_label": "zh", "prediction": "zh", "response": "zh", "correct": true, "input_tokens": 109, "output_tokens": 2, "latency_seconds": 0.02097904495894909}
{"id": "test-zh-002", "gold_label": "zh", "source_label": "zh", "prediction": "zh", "response": "zh", "correct": true, "input_tokens": 99, "output_tokens": 2, "latency_seconds": 0.02109034825116396}
{"id": "test-zh-003", "gold_label": "zh", "source_label": "zh", "prediction": "zh", "response": "zh", "correct": true, "input_tokens": 69, "output_tokens": 2, "latency_seconds": 0.021113927476108074}