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
17 KiB
JSON
Raw Permalink 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.
{"id": "test-ar-000", "gold_label": "ar", "source_label": "ar", "prediction": null, "response": "إن الاستم", "correct": false, "input_tokens": 114, "output_tokens": 8, "latency_seconds": 0.06024326104670763}
{"id": "test-ar-001", "gold_label": "ar", "source_label": "ar", "prediction": null, "response": "أن يكون", "correct": false, "input_tokens": 156, "output_tokens": 8, "latency_seconds": 0.06023324280977249}
{"id": "test-ar-002", "gold_label": "ar", "source_label": "ar", "prediction": null, "response": "أن يكون", "correct": false, "input_tokens": 156, "output_tokens": 8, "latency_seconds": 0.05917225405573845}
{"id": "test-ar-003", "gold_label": "ar", "source_label": "ar", "prediction": null, "response": "هذا هو ", "correct": false, "input_tokens": 91, "output_tokens": 8, "latency_seconds": 0.059281811118125916}
{"id": "test-bg-000", "gold_label": "ot", "source_label": "bg", "prediction": null, "response": "Освен че", "correct": false, "input_tokens": 147, "output_tokens": 8, "latency_seconds": 0.059322684071958065}
{"id": "test-bg-001", "gold_label": "ot", "source_label": "bg", "prediction": null, "response": "Общата би", "correct": false, "input_tokens": 69, "output_tokens": 8, "latency_seconds": 0.0591945294290781}
{"id": "test-bg-002", "gold_label": "ot", "source_label": "bg", "prediction": null, "response": "Тънкост", "correct": false, "input_tokens": 118, "output_tokens": 8, "latency_seconds": 0.059487082064151764}
{"id": "test-bg-003", "gold_label": "ot", "source_label": "bg", "prediction": null, "response": "Просматри", "correct": false, "input_tokens": 85, "output_tokens": 8, "latency_seconds": 0.05959406774491072}
{"id": "test-de-000", "gold_label": "de", "source_label": "de", "prediction": null, "response": "Die Abdeckung (dünnes", "correct": false, "input_tokens": 174, "output_tokens": 8, "latency_seconds": 0.05979781597852707}
{"id": "test-de-001", "gold_label": "de", "source_label": "de", "prediction": null, "response": "Besser etwas größ", "correct": false, "input_tokens": 43, "output_tokens": 8, "latency_seconds": 0.05983380135148764}
{"id": "test-de-002", "gold_label": "de", "source_label": "de", "prediction": null, "response": "Schade, wie könn", "correct": false, "input_tokens": 60, "output_tokens": 8, "latency_seconds": 0.05958701949566603}
{"id": "test-de-003", "gold_label": "de", "source_label": "de", "prediction": null, "response": "Dich und Robust, alles", "correct": false, "input_tokens": 43, "output_tokens": 8, "latency_seconds": 0.059297237545251846}
{"id": "test-el-000", "gold_label": "el", "source_label": "el", "prediction": null, "response": "Το Κρίσ", "correct": false, "input_tokens": 165, "output_tokens": 8, "latency_seconds": 0.059339928440749645}
{"id": "test-el-001", "gold_label": "el", "source_label": "el", "prediction": null, "response": "Πολιτεί", "correct": false, "input_tokens": 111, "output_tokens": 8, "latency_seconds": 0.05949285626411438}
{"id": "test-el-002", "gold_label": "el", "source_label": "el", "prediction": null, "response": "Και είναι δ", "correct": false, "input_tokens": 92, "output_tokens": 8, "latency_seconds": 0.059603940695524216}
{"id": "test-el-003", "gold_label": "el", "source_label": "el", "prediction": null, "response": "Και είναι δ", "correct": false, "input_tokens": 92, "output_tokens": 8, "latency_seconds": 0.05931456387042999}
{"id": "test-en-000", "gold_label": "en", "source_label": "en", "prediction": null, "response": "I'm sorry for the confusion, but", "correct": false, "input_tokens": 50, "output_tokens": 8, "latency_seconds": 0.059724729508161545}
{"id": "test-en-001", "gold_label": "en", "source_label": "en", "prediction": null, "response": "I'm sorry for the misunderstanding, but", "correct": false, "input_tokens": 69, "output_tokens": 8, "latency_seconds": 0.05924297962337732}
{"id": "test-en-002", "gold_label": "en", "source_label": "en", "prediction": null, "response": "I'm sorry for the inconvenience, but", "correct": false, "input_tokens": 81, "output_tokens": 8, "latency_seconds": 0.059761520475149155}
{"id": "test-en-003", "gold_label": "en", "source_label": "en", "prediction": null, "response": "Im sorry for the inconvenience,", "correct": false, "input_tokens": 57, "output_tokens": 8, "latency_seconds": 0.05949122551828623}
{"id": "test-es-000", "gold_label": "es", "source_label": "es", "prediction": null, "response": "La compré para mi mujer", "correct": false, "input_tokens": 149, "output_tokens": 8, "latency_seconds": 0.05953405052423477}
{"id": "test-es-001", "gold_label": "es", "source_label": "es", "prediction": null, "response": "No se sujeta bien al", "correct": false, "input_tokens": 63, "output_tokens": 8, "latency_seconds": 0.05952043551951647}
{"id": "test-es-002", "gold_label": "es", "source_label": "es", "prediction": null, "response": "Hola, pero no es exact", "correct": false, "input_tokens": 134, "output_tokens": 8, "latency_seconds": 0.0594380721449852}
{"id": "test-es-003", "gold_label": "es", "source_label": "es", "prediction": null, "response": "No me ha llegado el ped", "correct": false, "input_tokens": 72, "output_tokens": 8, "latency_seconds": 0.059360750019550323}
{"id": "test-fr-000", "gold_label": "fr", "source_label": "fr", "prediction": null, "response": "Au bout de 1 mois", "correct": false, "input_tokens": 71, "output_tokens": 8, "latency_seconds": 0.05943280924111605}
{"id": "test-fr-001", "gold_label": "fr", "source_label": "fr", "prediction": null, "response": "Livraison vraiment d", "correct": false, "input_tokens": 57, "output_tokens": 8, "latency_seconds": 0.05940195545554161}
{"id": "test-fr-002", "gold_label": "fr", "source_label": "fr", "prediction": null, "response": "Copie chinoise de l'", "correct": false, "input_tokens": 85, "output_tokens": 8, "latency_seconds": 0.05936688371002674}
{"id": "test-fr-003", "gold_label": "fr", "source_label": "fr", "prediction": null, "response": "Je vous aimez de v", "correct": false, "input_tokens": 65, "output_tokens": 8, "latency_seconds": 0.059392811730504036}
{"id": "test-hi-000", "gold_label": "hi", "source_label": "hi", "prediction": null, "response": "इसलिए", "correct": false, "input_tokens": 86, "output_tokens": 8, "latency_seconds": 0.059750827960669994}
{"id": "test-hi-001", "gold_label": "hi", "source_label": "hi", "prediction": null, "response": "इसलिए", "correct": false, "input_tokens": 86, "output_tokens": 8, "latency_seconds": 0.0595023175701499}
{"id": "test-hi-002", "gold_label": "hi", "source_label": "hi", "prediction": null, "response": "और, ज़", "correct": false, "input_tokens": 153, "output_tokens": 8, "latency_seconds": 0.05994911026209593}
{"id": "test-hi-003", "gold_label": "hi", "source_label": "hi", "prediction": null, "response": "उह, म", "correct": false, "input_tokens": 124, "output_tokens": 8, "latency_seconds": 0.059514570981264114}
{"id": "test-it-000", "gold_label": "ot", "source_label": "it", "prediction": null, "response": "Una persona stelleva di c", "correct": false, "input_tokens": 44, "output_tokens": 8, "latency_seconds": 0.05949304159730673}
{"id": "test-it-001", "gold_label": "ot", "source_label": "it", "prediction": null, "response": "Diversi bambini saltano", "correct": false, "input_tokens": 49, "output_tokens": 8, "latency_seconds": 0.05926634185016155}
{"id": "test-it-002", "gold_label": "ot", "source_label": "it", "prediction": null, "response": "Il mese scorso è mig", "correct": false, "input_tokens": 96, "output_tokens": 8, "latency_seconds": 0.05920985620468855}
{"id": "test-it-003", "gold_label": "ot", "source_label": "it", "prediction": null, "response": "A per diem, or a day", "correct": false, "input_tokens": 44, "output_tokens": 8, "latency_seconds": 0.059299188666045666}
{"id": "test-ja-000", "gold_label": "ot", "source_label": "ja", "prediction": null, "response": "SSDへシス", "correct": false, "input_tokens": 193, "output_tokens": 8, "latency_seconds": 0.05936930328607559}
{"id": "test-ja-001", "gold_label": "ot", "source_label": "ja", "prediction": null, "response": "このこと", "correct": false, "input_tokens": 100, "output_tokens": 8, "latency_seconds": 0.05920923221856356}
{"id": "test-ja-002", "gold_label": "ot", "source_label": "ja", "prediction": null, "response": "もう、見る", "correct": false, "input_tokens": 121, "output_tokens": 8, "latency_seconds": 0.05940388608723879}
{"id": "test-ja-003", "gold_label": "ot", "source_label": "ja", "prediction": null, "response": "なんだか", "correct": false, "input_tokens": 134, "output_tokens": 8, "latency_seconds": 0.059428741224110126}
{"id": "test-nl-000", "gold_label": "ot", "source_label": "nl", "prediction": null, "response": "Het vlees, gev", "correct": false, "input_tokens": 76, "output_tokens": 8, "latency_seconds": 0.05941706243902445}
{"id": "test-nl-001", "gold_label": "ot", "source_label": "nl", "prediction": null, "response": "Hoe zijn de kunst", "correct": false, "input_tokens": 46, "output_tokens": 8, "latency_seconds": 0.05952310189604759}
{"id": "test-nl-002", "gold_label": "ot", "source_label": "nl", "prediction": null, "response": "In the water.", "correct": false, "input_tokens": 44, "output_tokens": 5, "latency_seconds": 0.03761201910674572}
{"id": "test-nl-003", "gold_label": "ot", "source_label": "nl", "prediction": null, "response": "De technologisch geplaat", "correct": false, "input_tokens": 81, "output_tokens": 8, "latency_seconds": 0.05957785062491894}
{"id": "test-pl-000", "gold_label": "ot", "source_label": "pl", "prediction": null, "response": "Opalona dziewczyna", "correct": false, "input_tokens": 64, "output_tokens": 8, "latency_seconds": 0.059507221914827824}
{"id": "test-pl-001", "gold_label": "ot", "source_label": "pl", "prediction": null, "response": "I'm sorry for any misunderstanding, but", "correct": false, "input_tokens": 60, "output_tokens": 8, "latency_seconds": 0.0593439182266593}
{"id": "test-pl-002", "gold_label": "ot", "source_label": "pl", "prediction": null, "response": "I'm sorry for the misunderstanding, but", "correct": false, "input_tokens": 71, "output_tokens": 8, "latency_seconds": 0.05937239807099104}
{"id": "test-pl-003", "gold_label": "ot", "source_label": "pl", "prediction": null, "response": "Średnia dla prz", "correct": false, "input_tokens": 90, "output_tokens": 8, "latency_seconds": 0.059316896833479404}
{"id": "test-pt-000", "gold_label": "ot", "source_label": "pt", "prediction": null, "response": "A Kollar-Kotelly ag", "correct": false, "input_tokens": 62, "output_tokens": 8, "latency_seconds": 0.059342941269278526}
{"id": "test-pt-001", "gold_label": "ot", "source_label": "pt", "prediction": null, "response": "A jovem mulher está", "correct": false, "input_tokens": 51, "output_tokens": 8, "latency_seconds": 0.05939680803567171}
{"id": "test-pt-002", "gold_label": "ot", "source_label": "pt", "prediction": null, "response": "Um grupo de homens f", "correct": false, "input_tokens": 46, "output_tokens": 8, "latency_seconds": 0.059792510233819485}
{"id": "test-pt-003", "gold_label": "ot", "source_label": "pt", "prediction": null, "response": "Uma criança está", "correct": false, "input_tokens": 62, "output_tokens": 8, "latency_seconds": 0.05932790972292423}
{"id": "test-ru-000", "gold_label": "ru", "source_label": "ru", "prediction": null, "response": "Моим детя", "correct": false, "input_tokens": 94, "output_tokens": 8, "latency_seconds": 0.05943390540778637}
{"id": "test-ru-001", "gold_label": "ru", "source_label": "ru", "prediction": null, "response": "Но я торо", "correct": false, "input_tokens": 55, "output_tokens": 8, "latency_seconds": 0.059396409429609776}
{"id": "test-ru-002", "gold_label": "ru", "source_label": "ru", "prediction": null, "response": "Но я торо", "correct": false, "input_tokens": 55, "output_tokens": 8, "latency_seconds": 0.05932094994932413}
{"id": "test-ru-003", "gold_label": "ru", "source_label": "ru", "prediction": null, "response": "Через каж", "correct": false, "input_tokens": 104, "output_tokens": 8, "latency_seconds": 0.05943276919424534}
{"id": "test-sw-000", "gold_label": "ot", "source_label": "sw", "prediction": null, "response": "Baada ya kukataa k", "correct": false, "input_tokens": 101, "output_tokens": 8, "latency_seconds": 0.05936537031084299}
{"id": "test-sw-001", "gold_label": "ot", "source_label": "sw", "prediction": null, "response": "Kwa hiyo, watu", "correct": false, "input_tokens": 97, "output_tokens": 8, "latency_seconds": 0.05964792147278786}
{"id": "test-sw-002", "gold_label": "ot", "source_label": "sw", "prediction": null, "response": "Ni nafasi yetu pekee", "correct": false, "input_tokens": 80, "output_tokens": 8, "latency_seconds": 0.05959350895136595}
{"id": "test-sw-003", "gold_label": "ot", "source_label": "sw", "prediction": null, "response": "Kwa upande mwingine,", "correct": false, "input_tokens": 73, "output_tokens": 8, "latency_seconds": 0.059357658959925175}
{"id": "test-th-000", "gold_label": "ot", "source_label": "th", "prediction": null, "response": "ชายหา", "correct": false, "input_tokens": 259, "output_tokens": 8, "latency_seconds": 0.06841117981821299}
{"id": "test-th-001", "gold_label": "ot", "source_label": "th", "prediction": null, "response": "อย่า", "correct": false, "input_tokens": 257, "output_tokens": 8, "latency_seconds": 0.060420410707592964}
{"id": "test-th-002", "gold_label": "ot", "source_label": "th", "prediction": null, "response": "บ่อย", "correct": false, "input_tokens": 108, "output_tokens": 8, "latency_seconds": 0.0594320222735405}
{"id": "test-th-003", "gold_label": "ot", "source_label": "th", "prediction": null, "response": "Farid Hilali is a renowned actor", "correct": false, "input_tokens": 122, "output_tokens": 8, "latency_seconds": 0.059269363060593605}
{"id": "test-tr-000", "gold_label": "tr", "source_label": "tr", "prediction": null, "response": "Kayıt olarak, u", "correct": false, "input_tokens": 92, "output_tokens": 8, "latency_seconds": 0.05965294037014246}
{"id": "test-tr-001", "gold_label": "tr", "source_label": "tr", "prediction": null, "response": "Kayıt olarak, u", "correct": false, "input_tokens": 92, "output_tokens": 8, "latency_seconds": 0.05943188723176718}
{"id": "test-tr-002", "gold_label": "tr", "source_label": "tr", "prediction": null, "response": "Konuşul, dedi", "correct": false, "input_tokens": 71, "output_tokens": 8, "latency_seconds": 0.05948237422853708}
{"id": "test-tr-003", "gold_label": "tr", "source_label": "tr", "prediction": null, "response": "Savaştan sonra yap", "correct": false, "input_tokens": 120, "output_tokens": 8, "latency_seconds": 0.05945493374019861}
{"id": "test-ur-000", "gold_label": "ur", "source_label": "ur", "prediction": null, "response": "شروع دو", "correct": false, "input_tokens": 129, "output_tokens": 8, "latency_seconds": 0.059702896513044834}
{"id": "test-ur-001", "gold_label": "ur", "source_label": "ur", "prediction": null, "response": "شرایط ", "correct": false, "input_tokens": 117, "output_tokens": 8, "latency_seconds": 0.05930099170655012}
{"id": "test-ur-002", "gold_label": "ur", "source_label": "ur", "prediction": null, "response": "انٹیلی ج", "correct": false, "input_tokens": 166, "output_tokens": 8, "latency_seconds": 0.05926219932734966}
{"id": "test-ur-003", "gold_label": "ur", "source_label": "ur", "prediction": null, "response": "دیکھو ", "correct": false, "input_tokens": 64, "output_tokens": 8, "latency_seconds": 0.05909104458987713}
{"id": "test-vi-000", "gold_label": "vi", "source_label": "vi", "prediction": null, "response": "Người c", "correct": false, "input_tokens": 123, "output_tokens": 8, "latency_seconds": 0.059413446113467216}
{"id": "test-vi-001", "gold_label": "vi", "source_label": "vi", "prediction": null, "response": "Đây là 5", "correct": false, "input_tokens": 176, "output_tokens": 8, "latency_seconds": 0.0593422232195735}
{"id": "test-vi-002", "gold_label": "vi", "source_label": "vi", "prediction": null, "response": "Nghiệp v", "correct": false, "input_tokens": 66, "output_tokens": 8, "latency_seconds": 0.05937460344284773}
{"id": "test-vi-003", "gold_label": "vi", "source_label": "vi", "prediction": null, "response": "Bạn đã ", "correct": false, "input_tokens": 103, "output_tokens": 8, "latency_seconds": 0.05925013776868582}
{"id": "test-zh-000", "gold_label": "zh", "source_label": "zh", "prediction": null, "response": "根本不是那", "correct": false, "input_tokens": 85, "output_tokens": 8, "latency_seconds": 0.059398721903562546}
{"id": "test-zh-001", "gold_label": "zh", "source_label": "zh", "prediction": null, "response": "邮寄地", "correct": false, "input_tokens": 109, "output_tokens": 8, "latency_seconds": 0.059589968994259834}
{"id": "test-zh-002", "gold_label": "zh", "source_label": "zh", "prediction": null, "response": "面料很好", "correct": false, "input_tokens": 99, "output_tokens": 8, "latency_seconds": 0.05934322252869606}
{"id": "test-zh-003", "gold_label": "zh", "source_label": "zh", "prediction": null, "response": "我订购的是", "correct": false, "input_tokens": 69, "output_tokens": 8, "latency_seconds": 0.05917076487094164}