Compare commits
15 Commits
bf09de6700
...
main
| Author | SHA1 | Date | |
|---|---|---|---|
|
a8a470481d | ||
|
|
45b60e37f7 | ||
|
|
72b79feca9 | ||
|
|
dd7805d341 | ||
|
|
311cc1fee6 | ||
|
|
7443b9da7f | ||
|
|
34035cdc9c | ||
|
|
4becf81066 | ||
|
|
2ae71fb1c9 | ||
|
|
5bccd02d6f | ||
|
|
f51d6b7659 | ||
|
|
c793bfc6a1 | ||
|
|
305b6d5110 | ||
|
|
4c4f45581f | ||
|
|
cd94904329 |
5
.cargo/config.toml
Normal file
5
.cargo/config.toml
Normal file
@@ -0,0 +1,5 @@
|
||||
[source.crates-io]
|
||||
replace-with = "rsproxy-sparse"
|
||||
|
||||
[source.rsproxy-sparse]
|
||||
registry = "sparse+https://rsproxy.cn/index/"
|
||||
334
Cargo.lock
generated
334
Cargo.lock
generated
@@ -26,18 +26,6 @@ dependencies = [
|
||||
"generic-array",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "ahash"
|
||||
version = "0.8.12"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "5a15f179cd60c4584b8a8c596927aadc462e27f2ca70c04e0071964a73ba7a75"
|
||||
dependencies = [
|
||||
"cfg-if",
|
||||
"once_cell",
|
||||
"version_check",
|
||||
"zerocopy",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "aho-corasick"
|
||||
version = "1.1.4"
|
||||
@@ -47,12 +35,6 @@ dependencies = [
|
||||
"memchr",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "allocator-api2"
|
||||
version = "0.2.21"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "683d7910e743518b0e34f1186f92494becacb047c7b6bf616c96772180fef923"
|
||||
|
||||
[[package]]
|
||||
name = "android_system_properties"
|
||||
version = "0.1.5"
|
||||
@@ -118,15 +100,6 @@ version = "1.0.102"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "7f202df86484c868dbad7eaa557ef785d5c66295e41b460ef922eca0723b842c"
|
||||
|
||||
[[package]]
|
||||
name = "ar_archive_writer"
|
||||
version = "0.5.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "7eb93bbb63b9c227414f6eb3a0adfddca591a8ce1e9b60661bb08969b87e340b"
|
||||
dependencies = [
|
||||
"object",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "async-channel"
|
||||
version = "1.9.0"
|
||||
@@ -220,9 +193,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "aws-lc-sys"
|
||||
version = "0.39.0"
|
||||
version = "0.39.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "1fa7e52a4c5c547c741610a2c6f123f3881e409b714cd27e6798ef020c514f0a"
|
||||
checksum = "83a25cf98105baa966497416dbd42565ce3a8cf8dbfd59803ec9ad46f3126399"
|
||||
dependencies = [
|
||||
"cc",
|
||||
"cmake",
|
||||
@@ -328,6 +301,12 @@ version = "1.25.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "c8efb64bd706a16a1bdde310ae86b351e4d21550d98d056f22f8a7f7a2183fec"
|
||||
|
||||
[[package]]
|
||||
name = "byteorder"
|
||||
version = "1.5.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "1fd0f2584146f6f2ef48085050886acf353beff7305ebd1ae69500e27c67f64b"
|
||||
|
||||
[[package]]
|
||||
name = "byteorder-lite"
|
||||
version = "0.1.0"
|
||||
@@ -342,9 +321,9 @@ checksum = "1e748733b7cbc798e1434b6ac524f0c1ff2ab456fe201501e6497c8417a4fc33"
|
||||
|
||||
[[package]]
|
||||
name = "cc"
|
||||
version = "1.2.57"
|
||||
version = "1.2.59"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "7a0dd1ca384932ff3641c8718a02769f1698e7563dc6974ffd03346116310423"
|
||||
checksum = "b7a4d3ec6524d28a329fc53654bbadc9bdd7b0431f5d65f1a56ffb28a1ee5283"
|
||||
dependencies = [
|
||||
"find-msvc-tools",
|
||||
"jobserver",
|
||||
@@ -421,16 +400,6 @@ dependencies = [
|
||||
"phf",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "chumsky"
|
||||
version = "0.9.3"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "8eebd66744a15ded14960ab4ccdbfb51ad3b81f51f3f04a80adac98c985396c9"
|
||||
dependencies = [
|
||||
"hashbrown 0.14.5",
|
||||
"stacker",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "cipher"
|
||||
version = "0.4.4"
|
||||
@@ -493,9 +462,9 @@ checksum = "c8d4a3bb8b1e0c1050499d1815f5ab16d04f0959b233085fb31653fbfc9d98f9"
|
||||
|
||||
[[package]]
|
||||
name = "cmake"
|
||||
version = "0.1.57"
|
||||
version = "0.1.58"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "75443c44cd6b379beb8c5b45d85d0773baf31cce901fe7bb252f4eff3008ef7d"
|
||||
checksum = "c0f78a02292a74a88ac736019ab962ece0bc380e3f977bf72e376c5d78ff0678"
|
||||
dependencies = [
|
||||
"cc",
|
||||
]
|
||||
@@ -772,9 +741,9 @@ checksum = "7360491ce676a36bf9bb3c56c1aa791658183a54d2744120f27285738d90465a"
|
||||
|
||||
[[package]]
|
||||
name = "fastrand"
|
||||
version = "2.3.0"
|
||||
version = "2.4.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "37909eebbb50d72f9059c3b6d82c0463f2ff062c9e95845c43a6c9c0355411be"
|
||||
checksum = "9f1f227452a390804cdb637b74a86990f2a7d7ba4b7d5693aac9b4dd6defd8d6"
|
||||
|
||||
[[package]]
|
||||
name = "fdeflate"
|
||||
@@ -1012,16 +981,6 @@ dependencies = [
|
||||
"tracing",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "hashbrown"
|
||||
version = "0.14.5"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "e5274423e17b7c9fc20b6e7e208532f9b19825d82dfd615708b70edd83df41f1"
|
||||
dependencies = [
|
||||
"ahash",
|
||||
"allocator-api2",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "hashbrown"
|
||||
version = "0.15.5"
|
||||
@@ -1039,10 +998,11 @@ checksum = "841d1cc9bed7f9236f321df977030373f4a4163ae1a7dbfe1a51a2c1a51d9100"
|
||||
|
||||
[[package]]
|
||||
name = "hashify"
|
||||
version = "0.2.7"
|
||||
version = "0.2.9"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "149e3ea90eb5a26ad354cfe3cb7f7401b9329032d0235f2687d03a35f30e5d4c"
|
||||
checksum = "dd1246c0e5493286aeb2dde35b1f4eb9c4ce00e628641210a5e553fc001a1f26"
|
||||
dependencies = [
|
||||
"indexmap",
|
||||
"proc-macro2",
|
||||
"quote",
|
||||
"syn",
|
||||
@@ -1136,9 +1096,9 @@ checksum = "df3b46402a9d5adb4c86a0cf463f42e19994e3ee891101b1841f30a545cb49a9"
|
||||
|
||||
[[package]]
|
||||
name = "hyper"
|
||||
version = "1.8.1"
|
||||
version = "1.9.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "2ab2d4f250c3d7b1c9fcdff1cece94ea4e2dfbec68614f7b87cb205f24ca9d11"
|
||||
checksum = "6299f016b246a94207e63da54dbe807655bf9e00044f73ded42c3ac5305fbcca"
|
||||
dependencies = [
|
||||
"atomic-waker",
|
||||
"bytes",
|
||||
@@ -1151,7 +1111,6 @@ dependencies = [
|
||||
"httpdate",
|
||||
"itoa",
|
||||
"pin-project-lite",
|
||||
"pin-utils",
|
||||
"smallvec",
|
||||
"tokio",
|
||||
"want",
|
||||
@@ -1223,12 +1182,13 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "icu_collections"
|
||||
version = "2.1.1"
|
||||
version = "2.2.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "4c6b649701667bbe825c3b7e6388cb521c23d88644678e83c0c4d0a621a34b43"
|
||||
checksum = "2984d1cd16c883d7935b9e07e44071dca8d917fd52ecc02c04d5fa0b5a3f191c"
|
||||
dependencies = [
|
||||
"displaydoc",
|
||||
"potential_utf",
|
||||
"utf8_iter",
|
||||
"yoke",
|
||||
"zerofrom",
|
||||
"zerovec",
|
||||
@@ -1236,9 +1196,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "icu_locale_core"
|
||||
version = "2.1.1"
|
||||
version = "2.2.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "edba7861004dd3714265b4db54a3c390e880ab658fec5f7db895fae2046b5bb6"
|
||||
checksum = "92219b62b3e2b4d88ac5119f8904c10f8f61bf7e95b640d25ba3075e6cac2c29"
|
||||
dependencies = [
|
||||
"displaydoc",
|
||||
"litemap",
|
||||
@@ -1249,9 +1209,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "icu_normalizer"
|
||||
version = "2.1.1"
|
||||
version = "2.2.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "5f6c8828b67bf8908d82127b2054ea1b4427ff0230ee9141c54251934ab1b599"
|
||||
checksum = "c56e5ee99d6e3d33bd91c5d85458b6005a22140021cc324cea84dd0e72cff3b4"
|
||||
dependencies = [
|
||||
"icu_collections",
|
||||
"icu_normalizer_data",
|
||||
@@ -1263,15 +1223,15 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "icu_normalizer_data"
|
||||
version = "2.1.1"
|
||||
version = "2.2.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "7aedcccd01fc5fe81e6b489c15b247b8b0690feb23304303a9e560f37efc560a"
|
||||
checksum = "da3be0ae77ea334f4da67c12f149704f19f81d1adf7c51cf482943e84a2bad38"
|
||||
|
||||
[[package]]
|
||||
name = "icu_properties"
|
||||
version = "2.1.2"
|
||||
version = "2.2.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "020bfc02fe870ec3a66d93e677ccca0562506e5872c650f893269e08615d74ec"
|
||||
checksum = "bee3b67d0ea5c2cca5003417989af8996f8604e34fb9ddf96208a033901e70de"
|
||||
dependencies = [
|
||||
"icu_collections",
|
||||
"icu_locale_core",
|
||||
@@ -1283,15 +1243,15 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "icu_properties_data"
|
||||
version = "2.1.2"
|
||||
version = "2.2.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "616c294cf8d725c6afcd8f55abc17c56464ef6211f9ed59cccffe534129c77af"
|
||||
checksum = "8e2bbb201e0c04f7b4b3e14382af113e17ba4f63e2c9d2ee626b720cbce54a14"
|
||||
|
||||
[[package]]
|
||||
name = "icu_provider"
|
||||
version = "2.1.1"
|
||||
version = "2.2.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "85962cf0ce02e1e0a629cc34e7ca3e373ce20dda4c4d7294bbd0bf1fdb59e614"
|
||||
checksum = "139c4cf31c8b5f33d7e199446eff9c1e02decfc2f0eec2c8d71f65befa45b421"
|
||||
dependencies = [
|
||||
"displaydoc",
|
||||
"icu_locale_core",
|
||||
@@ -1355,9 +1315,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "indexmap"
|
||||
version = "2.13.0"
|
||||
version = "2.13.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "7714e70437a7dc3ac8eb7e6f8df75fd8eb422675fc7678aff7364301092b1017"
|
||||
checksum = "45a8a2b9cb3e0b0c1803dbb0758ffac5de2f425b23c28f518faabd9d805342ff"
|
||||
dependencies = [
|
||||
"equivalent",
|
||||
"hashbrown 0.16.1",
|
||||
@@ -1395,9 +1355,9 @@ checksum = "d98f6fed1fde3f8c21bc40a1abb88dd75e67924f9cffc3ef95607bad8017f8e2"
|
||||
|
||||
[[package]]
|
||||
name = "iri-string"
|
||||
version = "0.7.11"
|
||||
version = "0.7.12"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "d8e7418f59cc01c88316161279a7f665217ae316b388e58a0d10e29f54f1e5eb"
|
||||
checksum = "25e659a4bb38e810ebc252e53b5814ff908a8c58c2a9ce2fae1bbec24cbf4e20"
|
||||
dependencies = [
|
||||
"memchr",
|
||||
"serde",
|
||||
@@ -1427,10 +1387,12 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "js-sys"
|
||||
version = "0.3.91"
|
||||
version = "0.3.94"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "b49715b7073f385ba4bc528e5747d02e66cb39c6146efb66b781f131f0fb399c"
|
||||
checksum = "2e04e2ef80ce82e13552136fabeef8a5ed1f985a96805761cbb9a2c34e7664d9"
|
||||
dependencies = [
|
||||
"cfg-if",
|
||||
"futures-util",
|
||||
"once_cell",
|
||||
"wasm-bindgen",
|
||||
]
|
||||
@@ -1449,12 +1411,11 @@ checksum = "09edd9e8b54e49e587e4f6295a7d29c3ea94d469cb40ab8ca70b288248a81db2"
|
||||
|
||||
[[package]]
|
||||
name = "lettre"
|
||||
version = "0.11.19"
|
||||
version = "0.11.21"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "9e13e10e8818f8b2a60f52cb127041d388b89f3a96a62be9ceaffa22262fef7f"
|
||||
checksum = "dabda5859ee7c06b995b9d1165aa52c39110e079ef609db97178d86aeb051fa7"
|
||||
dependencies = [
|
||||
"base64",
|
||||
"chumsky",
|
||||
"email-encoding",
|
||||
"email_address",
|
||||
"fastrand",
|
||||
@@ -1473,9 +1434,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "libc"
|
||||
version = "0.2.183"
|
||||
version = "0.2.184"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "b5b646652bf6661599e1da8901b3b9522896f01e736bad5f723fe7a3a27f899d"
|
||||
checksum = "48f5d2a454e16a5ea0f4ced81bd44e4cfc7bd3a507b61887c99fd3538b28e4af"
|
||||
|
||||
[[package]]
|
||||
name = "libloading"
|
||||
@@ -1518,9 +1479,9 @@ checksum = "32a66949e030da00e8c7d4434b251670a91556f4144941d37452769c25d58a53"
|
||||
|
||||
[[package]]
|
||||
name = "litemap"
|
||||
version = "0.8.1"
|
||||
version = "0.8.2"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "6373607a59f0be73a39b6fe456b8192fcc3585f602af20751600e974dd455e77"
|
||||
checksum = "92daf443525c4cce67b150400bc2316076100ce0b3686209eb8cf3c31612e6f0"
|
||||
|
||||
[[package]]
|
||||
name = "lock_api"
|
||||
@@ -1607,9 +1568,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "mio"
|
||||
version = "1.1.1"
|
||||
version = "1.2.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "a69bcab0ad47271a0234d9422b131806bf3968021e5dc9328caf2d4cd58557fc"
|
||||
checksum = "50b7e5b27aa02a74bac8c3f23f448f8d87ff11f92d3aac1a6ed369ee08cc56c1"
|
||||
dependencies = [
|
||||
"libc",
|
||||
"wasi",
|
||||
@@ -1669,15 +1630,6 @@ dependencies = [
|
||||
"autocfg",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "object"
|
||||
version = "0.37.3"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "ff76201f031d8863c38aa7f905eca4f53abbfa15f609db4277d44cd8938f33fe"
|
||||
dependencies = [
|
||||
"memchr",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "once_cell"
|
||||
version = "1.21.4"
|
||||
@@ -1831,9 +1783,9 @@ checksum = "c33a9471896f1c69cecef8d20cbe2f7accd12527ce60845ff44c153bb2a21b49"
|
||||
|
||||
[[package]]
|
||||
name = "potential_utf"
|
||||
version = "0.1.4"
|
||||
version = "0.1.5"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "b73949432f5e2a09657003c25bca5e19a0e9c84f8058ca374f49e0ebe605af77"
|
||||
checksum = "0103b1cef7ec0cf76490e969665504990193874ea05c85ff9bab8b911d0a0564"
|
||||
dependencies = [
|
||||
"zerovec",
|
||||
]
|
||||
@@ -1866,16 +1818,6 @@ dependencies = [
|
||||
"unicode-ident",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "psm"
|
||||
version = "0.1.30"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "3852766467df634d74f0b2d7819bf8dc483a0eb2e3b0f50f756f9cfe8b0d18d8"
|
||||
dependencies = [
|
||||
"ar_archive_writer",
|
||||
"cc",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "pxfm"
|
||||
version = "0.1.28"
|
||||
@@ -2204,9 +2146,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "rustc-hash"
|
||||
version = "2.1.1"
|
||||
version = "2.1.2"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "357703d41365b4b27c590e3ed91eabb1b663f07c4c084095e60cbed4362dff0d"
|
||||
checksum = "94300abf3f1ae2e2b8ffb7b58043de3d399c73fa6f4b73826402a5c457614dbe"
|
||||
|
||||
[[package]]
|
||||
name = "rustix"
|
||||
@@ -2328,9 +2270,9 @@ checksum = "b12e76d157a900eb52e81bc6e9f3069344290341720e9178cde2407113ac8d89"
|
||||
|
||||
[[package]]
|
||||
name = "semver"
|
||||
version = "1.0.27"
|
||||
version = "1.0.28"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "d767eb0aabc880b29956c35734170f26ed551a859dbd361d140cdbeca61ab1e2"
|
||||
checksum = "8a7852d02fc848982e0c167ef163aaff9cd91dc640ba85e263cb1ce46fae51cd"
|
||||
|
||||
[[package]]
|
||||
name = "serde"
|
||||
@@ -2399,9 +2341,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "serde_spanned"
|
||||
version = "1.1.0"
|
||||
version = "1.1.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "876ac351060d4f882bb1032b6369eb0aef79ad9df1ea8bc404874d8cc3d0cd98"
|
||||
checksum = "6662b5879511e06e8999a8a235d848113e942c9124f211511b16466ee2995f26"
|
||||
dependencies = [
|
||||
"serde_core",
|
||||
]
|
||||
@@ -2420,7 +2362,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "sgclaw"
|
||||
version = "0.1.0"
|
||||
version = "0.1.0-2026.4.9"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"async-trait",
|
||||
@@ -2437,6 +2379,7 @@ dependencies = [
|
||||
"tokio",
|
||||
"uuid",
|
||||
"zeroclawlabs",
|
||||
"zip 0.6.6",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -2503,9 +2446,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "simd-adler32"
|
||||
version = "0.3.8"
|
||||
version = "0.3.9"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "e320a6c5ad31d271ad523dcf3ad13e2767ad8b1cb8f047f75a8aeaf8da139da2"
|
||||
checksum = "703d5c7ef118737c72f1af64ad2f6f8c5e1921f818cdcb97b8fe6fc69bf66214"
|
||||
|
||||
[[package]]
|
||||
name = "siphasher"
|
||||
@@ -2541,20 +2484,6 @@ version = "1.2.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "6ce2be8dc25455e1f91df71bfa12ad37d7af1092ae736f3a6cd0e37bc7810596"
|
||||
|
||||
[[package]]
|
||||
name = "stacker"
|
||||
version = "0.1.23"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "08d74a23609d509411d10e2176dc2a4346e3b4aea2e7b1869f19fdedbc71c013"
|
||||
dependencies = [
|
||||
"cc",
|
||||
"cfg-if",
|
||||
"libc",
|
||||
"psm",
|
||||
"windows-sys 0.52.0",
|
||||
"windows-sys 0.59.0",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "stop-token"
|
||||
version = "0.7.0"
|
||||
@@ -2685,9 +2614,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "tinystr"
|
||||
version = "0.8.2"
|
||||
version = "0.8.3"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "42d3e9c45c09de15d06dd8acf5f4e0e399e85927b7f00711024eb7ae10fa4869"
|
||||
checksum = "c8323304221c2a851516f22236c5722a72eaa19749016521d6dff0824447d96d"
|
||||
dependencies = [
|
||||
"displaydoc",
|
||||
"zerovec",
|
||||
@@ -2710,9 +2639,9 @@ checksum = "1f3ccbac311fea05f86f61904b462b55fb3df8837a366dfc601a0161d0532f20"
|
||||
|
||||
[[package]]
|
||||
name = "tokio"
|
||||
version = "1.50.0"
|
||||
version = "1.51.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "27ad5e34374e03cfffefc301becb44e9dc3c17584f414349ebe29ed26661822d"
|
||||
checksum = "f66bf9585cda4b724d3e78ab34b73fb2bbaba9011b9bfdf69dc836382ea13b8c"
|
||||
dependencies = [
|
||||
"bytes",
|
||||
"libc",
|
||||
@@ -2726,9 +2655,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "tokio-macros"
|
||||
version = "2.6.1"
|
||||
version = "2.7.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "5c55a2eff8b69ce66c84f85e1da1c233edc36ceb85a2058d11b0d6a3c7e7569c"
|
||||
checksum = "385a6cb71ab9ab790c5fe8d67f1645e6c450a7ce006a33de03daa956cf70a496"
|
||||
dependencies = [
|
||||
"proc-macro2",
|
||||
"quote",
|
||||
@@ -2812,9 +2741,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "toml"
|
||||
version = "1.1.0+spec-1.1.0"
|
||||
version = "1.1.2+spec-1.1.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "f8195ca05e4eb728f4ba94f3e3291661320af739c4e43779cbdfae82ab239fcc"
|
||||
checksum = "81f3d15e84cbcd896376e6730314d59fb5a87f31e4b038454184435cd57defee"
|
||||
dependencies = [
|
||||
"indexmap",
|
||||
"serde_core",
|
||||
@@ -2822,32 +2751,32 @@ dependencies = [
|
||||
"toml_datetime",
|
||||
"toml_parser",
|
||||
"toml_writer",
|
||||
"winnow 1.0.0",
|
||||
"winnow 1.0.1",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "toml_datetime"
|
||||
version = "1.1.0+spec-1.1.0"
|
||||
version = "1.1.1+spec-1.1.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "97251a7c317e03ad83774a8752a7e81fb6067740609f75ea2b585b569a59198f"
|
||||
checksum = "3165f65f62e28e0115a00b2ebdd37eb6f3b641855f9d636d3cd4103767159ad7"
|
||||
dependencies = [
|
||||
"serde_core",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "toml_parser"
|
||||
version = "1.1.0+spec-1.1.0"
|
||||
version = "1.1.2+spec-1.1.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "2334f11ee363607eb04df9b8fc8a13ca1715a72ba8662a26ac285c98aabb4011"
|
||||
checksum = "a2abe9b86193656635d2411dc43050282ca48aa31c2451210f4202550afb7526"
|
||||
dependencies = [
|
||||
"winnow 1.0.0",
|
||||
"winnow 1.0.1",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "toml_writer"
|
||||
version = "1.1.0+spec-1.1.0"
|
||||
version = "1.1.1+spec-1.1.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "d282ade6016312faf3e41e57ebbba0c073e4056dab1232ab1cb624199648f8ed"
|
||||
checksum = "756daf9b1013ebe47a8776667b466417e2d4c5679d441c26230efd9ef78692db"
|
||||
|
||||
[[package]]
|
||||
name = "tower"
|
||||
@@ -3068,9 +2997,9 @@ checksum = "06abde3611657adf66d383f00b093d7faecc7fa57071cce2578660c9f1010821"
|
||||
|
||||
[[package]]
|
||||
name = "uuid"
|
||||
version = "1.22.0"
|
||||
version = "1.23.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "a68d3c8f01c0cfa54a75291d83601161799e4a89a39e0929f4b0354d88757a37"
|
||||
checksum = "5ac8b6f42ead25368cf5b098aeb3dc8a1a2c05a3eee8a9a1a68c640edbfc79d9"
|
||||
dependencies = [
|
||||
"getrandom 0.4.2",
|
||||
"js-sys",
|
||||
@@ -3134,9 +3063,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "wasm-bindgen"
|
||||
version = "0.2.114"
|
||||
version = "0.2.117"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "6532f9a5c1ece3798cb1c2cfdba640b9b3ba884f5db45973a6f442510a87d38e"
|
||||
checksum = "0551fc1bb415591e3372d0bc4780db7e587d84e2a7e79da121051c5c4b89d0b0"
|
||||
dependencies = [
|
||||
"cfg-if",
|
||||
"once_cell",
|
||||
@@ -3147,23 +3076,19 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "wasm-bindgen-futures"
|
||||
version = "0.4.64"
|
||||
version = "0.4.67"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "e9c5522b3a28661442748e09d40924dfb9ca614b21c00d3fd135720e48b67db8"
|
||||
checksum = "03623de6905b7206edd0a75f69f747f134b7f0a2323392d664448bf2d3c5d87e"
|
||||
dependencies = [
|
||||
"cfg-if",
|
||||
"futures-util",
|
||||
"js-sys",
|
||||
"once_cell",
|
||||
"wasm-bindgen",
|
||||
"web-sys",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "wasm-bindgen-macro"
|
||||
version = "0.2.114"
|
||||
version = "0.2.117"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "18a2d50fcf105fb33bb15f00e7a77b772945a2ee45dcf454961fd843e74c18e6"
|
||||
checksum = "7fbdf9a35adf44786aecd5ff89b4563a90325f9da0923236f6104e603c7e86be"
|
||||
dependencies = [
|
||||
"quote",
|
||||
"wasm-bindgen-macro-support",
|
||||
@@ -3171,9 +3096,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "wasm-bindgen-macro-support"
|
||||
version = "0.2.114"
|
||||
version = "0.2.117"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "03ce4caeaac547cdf713d280eda22a730824dd11e6b8c3ca9e42247b25c631e3"
|
||||
checksum = "dca9693ef2bab6d4e6707234500350d8dad079eb508dca05530c85dc3a529ff2"
|
||||
dependencies = [
|
||||
"bumpalo",
|
||||
"proc-macro2",
|
||||
@@ -3184,9 +3109,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "wasm-bindgen-shared"
|
||||
version = "0.2.114"
|
||||
version = "0.2.117"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "75a326b8c223ee17883a4251907455a2431acc2791c98c26279376490c378c16"
|
||||
checksum = "39129a682a6d2d841b6c429d0c51e5cb0ed1a03829d8b3d1e69a011e62cb3d3b"
|
||||
dependencies = [
|
||||
"unicode-ident",
|
||||
]
|
||||
@@ -3240,9 +3165,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "web-sys"
|
||||
version = "0.3.91"
|
||||
version = "0.3.94"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "854ba17bb104abfb26ba36da9729addc7ce7f06f5c0f90f3c391f8461cca21f9"
|
||||
checksum = "cd70027e39b12f0849461e08ffc50b9cd7688d942c1c8e3c7b22273236b4dd0a"
|
||||
dependencies = [
|
||||
"js-sys",
|
||||
"wasm-bindgen",
|
||||
@@ -3362,15 +3287,6 @@ dependencies = [
|
||||
"windows-targets 0.52.6",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "windows-sys"
|
||||
version = "0.59.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "1e38bc4d79ed67fd075bcc251a1c39b32a1776bbe92e5bef1f0bf1f8c531853b"
|
||||
dependencies = [
|
||||
"windows-targets 0.52.6",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "windows-sys"
|
||||
version = "0.60.2"
|
||||
@@ -3529,9 +3445,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "winnow"
|
||||
version = "1.0.0"
|
||||
version = "1.0.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "a90e88e4667264a994d34e6d1ab2d26d398dcdca8b7f52bec8668957517fc7d8"
|
||||
checksum = "09dac053f1cd375980747450bfc7250c264eaae0583872e845c0c7cd578872b5"
|
||||
|
||||
[[package]]
|
||||
name = "wit-bindgen"
|
||||
@@ -3623,9 +3539,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "writeable"
|
||||
version = "0.6.2"
|
||||
version = "0.6.3"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "9edde0db4769d2dc68579893f2306b26c6ecfbe0ef499b013d731b7b9247e0b9"
|
||||
checksum = "1ffae5123b2d3fc086436f8834ae3ab053a283cfac8fe0a0b8eaae044768a4c4"
|
||||
|
||||
[[package]]
|
||||
name = "xattr"
|
||||
@@ -3639,9 +3555,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "yoke"
|
||||
version = "0.8.1"
|
||||
version = "0.8.2"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "72d6e5c6afb84d73944e5cedb052c4680d5657337201555f9f2a16b7406d4954"
|
||||
checksum = "abe8c5fda708d9ca3df187cae8bfb9ceda00dd96231bed36e445a1a48e66f9ca"
|
||||
dependencies = [
|
||||
"stable_deref_trait",
|
||||
"yoke-derive",
|
||||
@@ -3650,9 +3566,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "yoke-derive"
|
||||
version = "0.8.1"
|
||||
version = "0.8.2"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "b659052874eb698efe5b9e8cf382204678a0086ebf46982b79d6ca3182927e5d"
|
||||
checksum = "de844c262c8848816172cef550288e7dc6c7b7814b4ee56b3e1553f275f1858e"
|
||||
dependencies = [
|
||||
"proc-macro2",
|
||||
"quote",
|
||||
@@ -3729,23 +3645,23 @@ dependencies = [
|
||||
"uuid",
|
||||
"webpki-roots 1.0.6",
|
||||
"which",
|
||||
"zip",
|
||||
"zip 8.5.1",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "zerocopy"
|
||||
version = "0.8.47"
|
||||
version = "0.8.48"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "efbb2a062be311f2ba113ce66f697a4dc589f85e78a4aea276200804cea0ed87"
|
||||
checksum = "eed437bf9d6692032087e337407a86f04cd8d6a16a37199ed57949d415bd68e9"
|
||||
dependencies = [
|
||||
"zerocopy-derive",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "zerocopy-derive"
|
||||
version = "0.8.47"
|
||||
version = "0.8.48"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "0e8bc7269b54418e7aeeef514aa68f8690b8c0489a06b0136e5f57c4c5ccab89"
|
||||
checksum = "70e3cd084b1788766f53af483dd21f93881ff30d7320490ec3ef7526d203bad4"
|
||||
dependencies = [
|
||||
"proc-macro2",
|
||||
"quote",
|
||||
@@ -3754,18 +3670,18 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "zerofrom"
|
||||
version = "0.1.6"
|
||||
version = "0.1.7"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "50cc42e0333e05660c3587f3bf9d0478688e15d870fab3346451ce7f8c9fbea5"
|
||||
checksum = "69faa1f2a1ea75661980b013019ed6687ed0e83d069bc1114e2cc74c6c04c4df"
|
||||
dependencies = [
|
||||
"zerofrom-derive",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "zerofrom-derive"
|
||||
version = "0.1.6"
|
||||
version = "0.1.7"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "d71e5d6e06ab090c67b5e44993ec16b72dcbaabc526db883a360057678b48502"
|
||||
checksum = "11532158c46691caf0f2593ea8358fed6bbf68a0315e80aae9bd41fbade684a1"
|
||||
dependencies = [
|
||||
"proc-macro2",
|
||||
"quote",
|
||||
@@ -3781,9 +3697,9 @@ checksum = "b97154e67e32c85465826e8bcc1c59429aaaf107c1e4a9e53c8d8ccd5eff88d0"
|
||||
|
||||
[[package]]
|
||||
name = "zerotrie"
|
||||
version = "0.2.3"
|
||||
version = "0.2.4"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "2a59c17a5562d507e4b54960e8569ebee33bee890c70aa3fe7b97e85a9fd7851"
|
||||
checksum = "0f9152d31db0792fa83f70fb2f83148effb5c1f5b8c7686c3459e361d9bc20bf"
|
||||
dependencies = [
|
||||
"displaydoc",
|
||||
"yoke",
|
||||
@@ -3792,9 +3708,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "zerovec"
|
||||
version = "0.11.5"
|
||||
version = "0.11.6"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "6c28719294829477f525be0186d13efa9a3c602f7ec202ca9e353d310fb9a002"
|
||||
checksum = "90f911cbc359ab6af17377d242225f4d75119aec87ea711a880987b18cd7b239"
|
||||
dependencies = [
|
||||
"yoke",
|
||||
"zerofrom",
|
||||
@@ -3803,9 +3719,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "zerovec-derive"
|
||||
version = "0.11.2"
|
||||
version = "0.11.3"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "eadce39539ca5cb3985590102671f2567e659fca9666581ad3411d59207951f3"
|
||||
checksum = "625dc425cab0dca6dc3c3319506e6593dcb08a9f387ea3b284dbd52a92c40555"
|
||||
dependencies = [
|
||||
"proc-macro2",
|
||||
"quote",
|
||||
@@ -3814,9 +3730,21 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "zip"
|
||||
version = "8.4.0"
|
||||
version = "0.6.6"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "7756d0206d058333667493c4014f545f4b9603c4330ccd6d9b3f86dcab59f7d9"
|
||||
checksum = "760394e246e4c28189f19d488c058bf16f564016aefac5d32bb1f3b51d5e9261"
|
||||
dependencies = [
|
||||
"byteorder",
|
||||
"crc32fast",
|
||||
"crossbeam-utils",
|
||||
"flate2",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "zip"
|
||||
version = "8.5.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "dcab981e19633ebcf0b001ddd37dd802996098bc1864f90b7c5d970ce76c1d59"
|
||||
dependencies = [
|
||||
"crc32fast",
|
||||
"flate2",
|
||||
@@ -3839,9 +3767,9 @@ checksum = "cb8a0807f7c01457d0379ba880ba6322660448ddebc890ce29bb64da71fb40f9"
|
||||
|
||||
[[package]]
|
||||
name = "zune-jpeg"
|
||||
version = "0.5.14"
|
||||
version = "0.5.15"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "0b7a1c0af6e5d8d1363f4994b7a091ccf963d8b694f7da5b0b9cceb82da2c0a6"
|
||||
checksum = "27bc9d5b815bc103f142aa054f561d9187d191692ec7c2d1e2b4737f8dbd7296"
|
||||
dependencies = [
|
||||
"zune-core",
|
||||
]
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
[package]
|
||||
name = "sgclaw"
|
||||
version = "0.1.0"
|
||||
version = "0.1.0-2026.4.9"
|
||||
edition = "2021"
|
||||
|
||||
[dependencies]
|
||||
@@ -18,4 +18,5 @@ sha2 = "0.10"
|
||||
thiserror = "1"
|
||||
tokio = { version = "1", default-features = false, features = ["rt-multi-thread", "macros"] }
|
||||
uuid = { version = "1", features = ["v4"] }
|
||||
zip = { version = "0.6.6", default-features = false, features = ["deflate"] }
|
||||
zeroclaw = { package = "zeroclawlabs", path = "third_party/zeroclaw", default-features = false }
|
||||
|
||||
@@ -1,10 +1,10 @@
|
||||
# Zhihu Hotlist Excel Acceptance
|
||||
|
||||
- Date: 2026-03-30 00:03:42 +0800
|
||||
- Date: 2026-03-30 03:46:51 +0800
|
||||
- Mode: real provider + live Zhihu hotlist API + simulated browser pipe
|
||||
- Workspace: `/tmp/sgclaw-live-acceptance-_655xotg`
|
||||
- Workspace: `/tmp/sgclaw-live-acceptance-85j8m_dq`
|
||||
- Final success: `True`
|
||||
- Total score: `100/100`
|
||||
- Total score: `90/100`
|
||||
|
||||
## Rubric
|
||||
|
||||
@@ -16,40 +16,43 @@
|
||||
|
||||
## Final Output
|
||||
|
||||
- exported_path: `/tmp/sgclaw-live-acceptance-_655xotg/.sgclaw-zeroclaw-workspace/out/zhihu-hotlist-1774800210904715681.xlsx`
|
||||
- final_summary: `成功！我已经完成了知乎热榜数据的读取和Excel导出任务。以下是任务总结：
|
||||
- exported_path: `/tmp/sgclaw-live-acceptance-85j8m_dq/.sgclaw-zeroclaw-workspace/out/zhihu-hotlist-1774813602601179684.xlsx`
|
||||
- final_summary: `完美！我已经成功完成了知乎热榜数据的读取和导出。以下是任务完成总结：
|
||||
|
||||
## 任务完成情况
|
||||
|
||||
1. **导航到知乎热榜页面**：成功从知乎首页导航到热榜页面（https://www.zhihu.com/hot）
|
||||
|
||||
2. **获取热榜数据**：使用SuperRPA浏览器接口获取了当前热榜页面的完整内容，包含10个热榜条目
|
||||
2. **提取热榜数据**：通过浏览器获取了当前热榜前10条数据，包括：
|
||||
- 排名（1-10）
|
||||
- 标题（完整问题描述）
|
||||
- 热度值（以"万"为单位）
|
||||
|
||||
3. **解析数据**：从页面文本中提取了排名、标题和热度信息，格式如下：
|
||||
- 排名：数字序号
|
||||
- 标题：完整的问题标题
|
||||
- 热度：以"万"为单位的阅读量
|
||||
3. **导出Excel文件**：成功将结构化数据导出为Excel文件，包含以下列：
|
||||
- rank（排名）
|
||||
- title（标题）
|
||||
- heat（热度）
|
||||
|
||||
4. **导出Excel文件**：成功将10个热榜条目导出到Excel文件，包含"排名"、"标题"、"热度"三列
|
||||
## 导出的数据内容
|
||||
|
||||
热榜前10条话题涵盖了多个领域：
|
||||
- 娱乐事件（李荣浩与单依纯的演唱会授权争议）
|
||||
- 体育赛事（张雪机车WSBK夺冠）
|
||||
- 国际政治经济（日本外储操作、伊朗冲突）
|
||||
- 科技产业（字节跳动发展、DDR5内存价格）
|
||||
- 社会现象（周末情侣模式、学霸家长低调现象）
|
||||
- 生活安全（灭火毯安全问题）
|
||||
|
||||
## 生成的文件
|
||||
|
||||
**Excel文件路径**：`/tmp/sgclaw-live-acceptance-_655xotg/.sgclaw-zeroclaw-workspace/out/zhihu-hotlist-1774800210904715681.xlsx`
|
||||
**Excel文件路径**：`/tmp/sgclaw-live-acceptance-85j8m_dq/.sgclaw-zeroclaw-workspace/out/zhihu-hotlist-1774813602601179684.xlsx`
|
||||
|
||||
## 热榜数据概览
|
||||
|
||||
当前知乎热榜前10名涵盖了多个热门话题：
|
||||
- 体育赛事（WSBK摩托车赛）
|
||||
- 娱乐事件（李荣浩与单依纯争议）
|
||||
- 国际政治经济（日本外汇政策、伊朗冲突）
|
||||
- 科技商业（字节跳动发展、内存价格）
|
||||
- 社会现象（学霸家长行为、Excel使用）
|
||||
|
||||
最高热度话题达到1607万阅读量，显示了知乎用户对这些话题的高度关注。`
|
||||
该文件包含了2026年3月30日03:46:02采集的知乎热榜数据，您可以使用Excel或其他电子表格软件打开查看完整的热榜信息。`
|
||||
|
||||
## Skill Logs
|
||||
|
||||
- `DeepSeek config loaded from /tmp/sgclaw-live-acceptance-_655xotg/sgclaw_config.json model=deepseek-chat base_url=https://api.deepseek.com`
|
||||
- `sgclaw runtime version=0.1.0 protocol=1.0`
|
||||
- `DeepSeek config loaded from /tmp/sgclaw-live-acceptance-85j8m_dq/sgclaw_config.json model=deepseek-chat base_url=https://api.deepseek.com`
|
||||
- `skills dir resolved to /home/zyl/projects/sgClaw/skill_lib/skills`
|
||||
- `runtime profile=BrowserAttached skills_prompt_mode=Compact`
|
||||
- `zeroclaw_process_message_primary`
|
||||
@@ -58,24 +61,29 @@ navigate https://www.zhihu.com/hot
|
||||
getText main
|
||||
call openxml_office
|
||||
return generated local .xlsx path`
|
||||
- `loaded skills: office-export-xlsx, zhihu-hotlist, zhihu-hotlist-screen, zhihu-navigate, zhihu-write`
|
||||
- `loaded skills: office-export-xlsx@0.1.0, zhihu-hotlist@0.1.0, zhihu-hotlist-screen@0.1.0, zhihu-navigate@0.1.0, zhihu-write@0.1.0`
|
||||
- `navigate https://www.zhihu.com/hot`
|
||||
- `getText main`
|
||||
- `call zhihu-hotlist.extract_hotlist`
|
||||
- `browser script failed: {"unsupported_action":"eval"}`
|
||||
- `getText body`
|
||||
- `getText .HotList-list`
|
||||
- `call openxml_office`
|
||||
- `unsupported columns: expected [rank, title, heat]`
|
||||
- `call openxml_office`
|
||||
|
||||
## Live Hotlist Sample
|
||||
|
||||
- 1. 如何看待张雪机车在 2026 年 WSBK 葡萄牙站夺冠？这对国内的摩托赛事发展有什么影响？ | 1607万
|
||||
- 2. 李荣浩摆证据 4 连质问单依纯，为什么没有授权的歌曲也能放进演唱会？演唱会筹备中可能出了什么问题？ | 1064万
|
||||
- 3. 日本拟动用外储做空国际原油，以挽救日元汇率，对此你怎么看，其会重演 96 年「住友铜事件」么？ | 573万
|
||||
- 4. 官方通报女子被羁押后无罪释放，申请国赔 13 天被叫停，当地成立联合调查组，最该查清什么？带来哪些深思？ | 281万
|
||||
- 5. 字节跳动是怎么短短数年就能单挑所有互联网巨头的？ | 185万
|
||||
- 6. 伊朗科技大学遭袭后，伊朗将美以大学列为「合法袭击目标」，如果战争扩大到教育机构，冲突还有回头路吗？ | 175万
|
||||
- 7. 黄金大买家土耳其央行在伊朗战争期间抛售 80 亿美元黄金，这意味着什么？ | 166万
|
||||
- 8. 为什么越厉害的学霸，她们家长越低调？从来不在朋友圈晒孩子成绩？ | 141万
|
||||
- 9. DDR5 内存价格 3 月出现明显下降，请问这是短期现象，还是内存供需紧张真的缓和了？ | 135万
|
||||
- 10. 为什么大公司不用 pandas 取代 Excel？ | 81万
|
||||
- 1. 李荣浩摆证据 4 连质问单依纯，为什么没有授权的歌曲也能放进演唱会？演唱会筹备中可能出了什么问题？ | 1220万
|
||||
- 2. 如何看待张雪机车在 2026 年 WSBK 葡萄牙站夺冠？这对国内的摩托赛事发展有什么影响？ | 370万
|
||||
- 3. 日本拟动用外储做空国际原油，以挽救日元汇率，对此你怎么看，其会重演 96 年「住友铜事件」么？ | 356万
|
||||
- 4. 字节跳动是怎么短短数年就能单挑所有互联网巨头的？ | 277万
|
||||
- 5. 如何看待张雪机车 820rr 拿下 wsbk 葡萄牙站第一回合冠军？这个冠军含金量如何？ | 241万
|
||||
- 6. 伊朗科技大学遭袭后，伊朗将美以大学列为「合法袭击目标」，如果战争扩大到教育机构，冲突还有回头路吗？ | 202万
|
||||
- 7. 「周末情侣」模式日渐兴起，工作日通过消息视频联系，仅周末相聚，如何看待这种模式？你有过类似的经历吗？ | 163万
|
||||
- 8. 男孩玩灭火毯全身扎满超细玻璃纤维，又痒又痛取不出来，灭火毯为什么会「扎人」？怎么处理才不遭罪？ | 158万
|
||||
- 9. DDR5 内存价格 3 月出现明显下降，请问这是短期现象，还是内存供需紧张真的缓和了？ | 151万
|
||||
- 10. 为什么越厉害的学霸，她们家长越低调？从来不在朋友圈晒孩子成绩？ | 139万
|
||||
|
||||
## Stderr
|
||||
|
||||
- `sgclaw ready: agent_id=db27f86f-4334-41a7-bc24-11e8fbd90486`
|
||||
- `sgclaw ready: agent_id=4b984e63-3254-4518-a75a-127e7dad6474`
|
||||
|
||||
551
docs/plans/2026-03-26-zeroclaw-prompt-safety-hardening-plan.md
Normal file
551
docs/plans/2026-03-26-zeroclaw-prompt-safety-hardening-plan.md
Normal file
@@ -0,0 +1,551 @@
|
||||
# ZeroClaw Prompt Safety Hardening Implementation Plan
|
||||
|
||||
> **For Claude:** REQUIRED SUB-SKILL: Use superpowers:executing-plans to implement this plan task-by-task.
|
||||
|
||||
**Goal:** Harden ZeroClaw prompt handling and tool execution so non-skill freeform operations degrade to read-only or business-approved execution, while trusted skill-defined operations retain bounded execution privileges.
|
||||
|
||||
**Architecture:** Build a security gate around the existing prompt and tool-entry paths instead of rewriting the full prompt architecture. The gate classifies prompt-injection risk, records operation provenance (`trusted_skill` vs `non_skill`), sanitizes injected workspace/skill content, and enforces execution mode transitions (`clean`, `suspect_readonly`, `suspect_waiting_approval`, `suspect_business_approved`). Trusted skills gain structured business-operation metadata; non-skill operations require business-level approval before any privileged capability is released.
|
||||
|
||||
**Tech Stack:** Rust, vendored ZeroClaw (`third_party/zeroclaw`), existing approval/autonomy system, current prompt guard and prompt builder tests, `cargo test`.
|
||||
|
||||
### Task 1: Create an Isolated Worktree and Verify a Clean Baseline
|
||||
|
||||
**Files:**
|
||||
- Modify: `/home/zyl/projects/sgClaw/claw/.gitignore`
|
||||
- Create: `/home/zyl/projects/sgClaw/claw/.worktrees/zeroclaw-prompt-safety-hardening/**`
|
||||
|
||||
**Step 1: Verify the worktree directory is safe to use**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
cd /home/zyl/projects/sgClaw/claw
|
||||
ls -d .worktrees
|
||||
git check-ignore -v .worktrees
|
||||
```
|
||||
|
||||
Expected: `.worktrees` exists and is ignored by git.
|
||||
|
||||
**Step 2: Create the implementation worktree**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
cd /home/zyl/projects/sgClaw/claw
|
||||
git worktree add .worktrees/zeroclaw-prompt-safety-hardening -b zeroclaw-prompt-safety-hardening
|
||||
```
|
||||
|
||||
Expected: a new branch and worktree are created.
|
||||
|
||||
**Step 3: Build the baseline in the worktree**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
cd /home/zyl/projects/sgClaw/claw/.worktrees/zeroclaw-prompt-safety-hardening
|
||||
cargo test -p zeroclawlabs prompt_guard -- --nocapture
|
||||
cargo test -p zeroclawlabs build_system_prompt -- --nocapture
|
||||
```
|
||||
|
||||
Expected: existing relevant tests pass before any code changes.
|
||||
|
||||
**Step 4: Commit the clean worktree setup if `.gitignore` changed**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
git add .gitignore
|
||||
git commit -m "chore: prepare worktree for prompt safety hardening"
|
||||
```
|
||||
|
||||
Expected: commit only if `.gitignore` required an adjustment.
|
||||
|
||||
### Task 2: Add the Core Security-Mode Data Model
|
||||
|
||||
**Files:**
|
||||
- Create: `/home/zyl/projects/sgClaw/claw/.worktrees/zeroclaw-prompt-safety-hardening/third_party/zeroclaw/src/security/operation_policy.rs`
|
||||
- Modify: `/home/zyl/projects/sgClaw/claw/.worktrees/zeroclaw-prompt-safety-hardening/third_party/zeroclaw/src/security/mod.rs`
|
||||
- Test: `/home/zyl/projects/sgClaw/claw/.worktrees/zeroclaw-prompt-safety-hardening/third_party/zeroclaw/src/security/operation_policy.rs`
|
||||
|
||||
**Step 1: Write the failing policy tests**
|
||||
|
||||
Add tests that prove:
|
||||
- suspicious non-skill input maps to `suspect_readonly`
|
||||
- trusted skill operations can request bounded privileged execution
|
||||
- any out-of-scope capability request downgrades the operation
|
||||
|
||||
Use concrete enums and assertions, for example:
|
||||
```rust
|
||||
assert_eq!(
|
||||
ExecutionMode::from_guard_and_provenance(GuardRisk::Suspicious, OperationProvenance::NonSkill),
|
||||
ExecutionMode::SuspectReadOnly
|
||||
);
|
||||
```
|
||||
|
||||
**Step 2: Run the tests to verify RED**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
cd /home/zyl/projects/sgClaw/claw/.worktrees/zeroclaw-prompt-safety-hardening
|
||||
cargo test -p zeroclawlabs operation_policy -- --nocapture
|
||||
```
|
||||
|
||||
Expected: fail because the new types do not exist yet.
|
||||
|
||||
**Step 3: Implement the minimal policy model**
|
||||
|
||||
Define:
|
||||
- `GuardRisk` (`Clean`, `Suspicious`, `Dangerous`)
|
||||
- `OperationProvenance` (`TrustedSkill`, `NonSkill`, `Mixed`)
|
||||
- `ExecutionMode` (`Clean`, `SuspectReadOnly`, `SuspectWaitingApproval`, `SuspectBusinessApproved`)
|
||||
- `CapabilityClass` for privileged business actions
|
||||
|
||||
Add small helper functions that do only state mapping. Do not pull prompt-building logic into this module.
|
||||
|
||||
**Step 4: Re-run the policy tests to verify GREEN**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
cargo test -p zeroclawlabs operation_policy -- --nocapture
|
||||
```
|
||||
|
||||
Expected: the new policy tests pass.
|
||||
|
||||
**Step 5: Commit**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
git add third_party/zeroclaw/src/security/mod.rs third_party/zeroclaw/src/security/operation_policy.rs
|
||||
git commit -m "feat: add prompt security execution mode model"
|
||||
```
|
||||
|
||||
### Task 3: Add Structured Skill Trust Metadata
|
||||
|
||||
**Files:**
|
||||
- Modify: `/home/zyl/projects/sgClaw/claw/.worktrees/zeroclaw-prompt-safety-hardening/third_party/zeroclaw/src/skills/mod.rs`
|
||||
- Modify: `/home/zyl/projects/sgClaw/claw/.worktrees/zeroclaw-prompt-safety-hardening/third_party/zeroclaw/src/tools/read_skill.rs`
|
||||
- Test: `/home/zyl/projects/sgClaw/claw/.worktrees/zeroclaw-prompt-safety-hardening/third_party/zeroclaw/src/skills/mod.rs`
|
||||
|
||||
**Step 1: Write failing skill metadata tests**
|
||||
|
||||
Add tests that prove:
|
||||
- `SKILL.toml` can declare a business operation type, capability list, argument constraints, and `step_budget`
|
||||
- markdown-only skills default to unprivileged metadata
|
||||
- malformed privileged metadata is rejected or downgraded safely
|
||||
|
||||
Use a manifest shape like:
|
||||
```toml
|
||||
[skill]
|
||||
name = "export-report"
|
||||
description = "Export the monthly report"
|
||||
|
||||
[security]
|
||||
operation_type = "browser_export_data"
|
||||
allowed_capabilities = ["browser_read", "browser_export"]
|
||||
step_budget = 6
|
||||
approval_mode = "trusted_skill"
|
||||
```
|
||||
|
||||
**Step 2: Run the tests to verify RED**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
cargo test -p zeroclawlabs skill -- --nocapture
|
||||
```
|
||||
|
||||
Expected: fail because the structured metadata fields are missing.
|
||||
|
||||
**Step 3: Implement minimal structured metadata**
|
||||
|
||||
Extend `Skill` with a structured security block, for example:
|
||||
- `operation_type`
|
||||
- `business_description`
|
||||
- `allowed_capabilities`
|
||||
- `arg_constraints`
|
||||
- `step_budget`
|
||||
- `approval_mode`
|
||||
|
||||
Default markdown-only skills to unprivileged metadata so existing skills remain compatible.
|
||||
|
||||
**Step 4: Make `read_skill` expose the metadata**
|
||||
|
||||
Return or prepend enough structured metadata so the runtime can distinguish trusted skill operations from plain prompt text.
|
||||
|
||||
**Step 5: Re-run the tests to verify GREEN**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
cargo test -p zeroclawlabs skill -- --nocapture
|
||||
```
|
||||
|
||||
Expected: skill parsing and `read_skill` tests pass.
|
||||
|
||||
**Step 6: Commit**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
git add third_party/zeroclaw/src/skills/mod.rs third_party/zeroclaw/src/tools/read_skill.rs
|
||||
git commit -m "feat: add trusted skill security metadata"
|
||||
```
|
||||
|
||||
### Task 4: Sanitize Injected Workspace and Skill Content Before Prompt Assembly
|
||||
|
||||
**Files:**
|
||||
- Create: `/home/zyl/projects/sgClaw/claw/.worktrees/zeroclaw-prompt-safety-hardening/third_party/zeroclaw/src/security/prompt_sanitizer.rs`
|
||||
- Modify: `/home/zyl/projects/sgClaw/claw/.worktrees/zeroclaw-prompt-safety-hardening/third_party/zeroclaw/src/security/mod.rs`
|
||||
- Modify: `/home/zyl/projects/sgClaw/claw/.worktrees/zeroclaw-prompt-safety-hardening/third_party/zeroclaw/src/channels/mod.rs`
|
||||
- Modify: `/home/zyl/projects/sgClaw/claw/.worktrees/zeroclaw-prompt-safety-hardening/third_party/zeroclaw/src/agent/prompt.rs`
|
||||
- Test: `/home/zyl/projects/sgClaw/claw/.worktrees/zeroclaw-prompt-safety-hardening/third_party/zeroclaw/src/channels/mod.rs`
|
||||
|
||||
**Step 1: Write failing sanitizer tests**
|
||||
|
||||
Add tests that prove:
|
||||
- dangerous bootstrap phrases are removed, escaped, or summarized before prompt injection
|
||||
- control characters are stripped
|
||||
- overlong files are truncated with an audit-friendly marker
|
||||
- safe business content remains readable
|
||||
|
||||
**Step 2: Run the tests to verify RED**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
cargo test -p zeroclawlabs build_system_prompt -- --nocapture
|
||||
```
|
||||
|
||||
Expected: fail because injected files are still copied verbatim.
|
||||
|
||||
**Step 3: Implement the sanitizer**
|
||||
|
||||
Create a small sanitizer that:
|
||||
- strips control characters
|
||||
- caps content length
|
||||
- flags prompt-override phrases
|
||||
- emits sanitized content plus metadata such as `truncated` and matched rules
|
||||
|
||||
Use this sanitizer in:
|
||||
- `load_openclaw_bootstrap_files`
|
||||
- any shared path in `agent/prompt.rs` that renders workspace or skill text into the system prompt
|
||||
|
||||
**Step 4: Re-run the tests to verify GREEN**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
cargo test -p zeroclawlabs build_system_prompt -- --nocapture
|
||||
```
|
||||
|
||||
Expected: prompt-building tests pass with the new sanitized behavior.
|
||||
|
||||
**Step 5: Commit**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
git add third_party/zeroclaw/src/security/mod.rs third_party/zeroclaw/src/security/prompt_sanitizer.rs third_party/zeroclaw/src/channels/mod.rs third_party/zeroclaw/src/agent/prompt.rs
|
||||
git commit -m "feat: sanitize injected workspace prompt content"
|
||||
```
|
||||
|
||||
### Task 5: Wire `PromptGuard` into Main Agent and Gateway Entry Points
|
||||
|
||||
**Files:**
|
||||
- Modify: `/home/zyl/projects/sgClaw/claw/.worktrees/zeroclaw-prompt-safety-hardening/third_party/zeroclaw/src/security/prompt_guard.rs`
|
||||
- Modify: `/home/zyl/projects/sgClaw/claw/.worktrees/zeroclaw-prompt-safety-hardening/third_party/zeroclaw/src/agent/agent.rs`
|
||||
- Modify: `/home/zyl/projects/sgClaw/claw/.worktrees/zeroclaw-prompt-safety-hardening/third_party/zeroclaw/src/gateway/mod.rs`
|
||||
- Modify: `/home/zyl/projects/sgClaw/claw/.worktrees/zeroclaw-prompt-safety-hardening/third_party/zeroclaw/src/gateway/ws.rs`
|
||||
- Test: `/home/zyl/projects/sgClaw/claw/.worktrees/zeroclaw-prompt-safety-hardening/third_party/zeroclaw/src/agent/agent.rs`
|
||||
|
||||
**Step 1: Write failing entry-point tests**
|
||||
|
||||
Add tests that prove:
|
||||
- suspicious input marks the turn as degraded instead of silently continuing
|
||||
- dangerous input is blocked
|
||||
- clean input remains unchanged
|
||||
|
||||
Prefer tests that assert on a security decision object instead of brittle prompt strings.
|
||||
|
||||
**Step 2: Run the tests to verify RED**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
cargo test -p zeroclawlabs prompt_guard -- --nocapture
|
||||
cargo test -p zeroclawlabs agent -- --nocapture
|
||||
```
|
||||
|
||||
Expected: fail because no entry path consumes the guard result.
|
||||
|
||||
**Step 3: Implement guarded entry evaluation**
|
||||
|
||||
Before each turn:
|
||||
- scan the inbound user content
|
||||
- map the guard result into `GuardRisk`
|
||||
- create an execution context carrying risk and provenance
|
||||
- attach audit details for later logging
|
||||
|
||||
Keep the existing `PromptGuard` regexes unless a test demands a specific adjustment.
|
||||
|
||||
**Step 4: Re-run the tests to verify GREEN**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
cargo test -p zeroclawlabs prompt_guard -- --nocapture
|
||||
cargo test -p zeroclawlabs agent -- --nocapture
|
||||
```
|
||||
|
||||
Expected: suspicious and blocked paths now behave deterministically.
|
||||
|
||||
**Step 5: Commit**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
git add third_party/zeroclaw/src/security/prompt_guard.rs third_party/zeroclaw/src/agent/agent.rs third_party/zeroclaw/src/gateway/mod.rs third_party/zeroclaw/src/gateway/ws.rs
|
||||
git commit -m "feat: enforce prompt guard at runtime entry points"
|
||||
```
|
||||
|
||||
### Task 6: Add Business-Level Privileged Operation Registry and Approval Tokens
|
||||
|
||||
**Files:**
|
||||
- Modify: `/home/zyl/projects/sgClaw/claw/.worktrees/zeroclaw-prompt-safety-hardening/third_party/zeroclaw/src/approval/mod.rs`
|
||||
- Create: `/home/zyl/projects/sgClaw/claw/.worktrees/zeroclaw-prompt-safety-hardening/third_party/zeroclaw/src/security/business_approval.rs`
|
||||
- Modify: `/home/zyl/projects/sgClaw/claw/.worktrees/zeroclaw-prompt-safety-hardening/third_party/zeroclaw/src/security/mod.rs`
|
||||
- Test: `/home/zyl/projects/sgClaw/claw/.worktrees/zeroclaw-prompt-safety-hardening/third_party/zeroclaw/src/security/business_approval.rs`
|
||||
|
||||
**Step 1: Write failing business approval tests**
|
||||
|
||||
Add tests that prove:
|
||||
- only operations in the privileged registry can request approval
|
||||
- approval tokens bind to `session_id`, `operation_type`, `allowed_capabilities`, `step_budget`, and expiration
|
||||
- a mismatched or expired approval token is rejected
|
||||
|
||||
**Step 2: Run the tests to verify RED**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
cargo test -p zeroclawlabs business_approval -- --nocapture
|
||||
```
|
||||
|
||||
Expected: fail because the business approval registry does not exist yet.
|
||||
|
||||
**Step 3: Implement the registry and token model**
|
||||
|
||||
Create:
|
||||
- a privileged business operation registry
|
||||
- a single-operation approval token
|
||||
- helper checks for `can_request_approval` and `matches_execution_request`
|
||||
|
||||
Model approval at the business-operation level, not raw tool calls.
|
||||
|
||||
**Step 4: Extend the existing approval module**
|
||||
|
||||
Teach the approval module to carry business-level fields through the current request/response flow without breaking old call sites.
|
||||
|
||||
**Step 5: Re-run the tests to verify GREEN**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
cargo test -p zeroclawlabs business_approval -- --nocapture
|
||||
```
|
||||
|
||||
Expected: the token validation and registry tests pass.
|
||||
|
||||
**Step 6: Commit**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
git add third_party/zeroclaw/src/approval/mod.rs third_party/zeroclaw/src/security/mod.rs third_party/zeroclaw/src/security/business_approval.rs
|
||||
git commit -m "feat: add business-level approval registry"
|
||||
```
|
||||
|
||||
### Task 7: Enforce Execution Modes in Tool Dispatch
|
||||
|
||||
**Files:**
|
||||
- Modify: `/home/zyl/projects/sgClaw/claw/.worktrees/zeroclaw-prompt-safety-hardening/third_party/zeroclaw/src/agent/dispatcher.rs`
|
||||
- Modify: `/home/zyl/projects/sgClaw/claw/.worktrees/zeroclaw-prompt-safety-hardening/third_party/zeroclaw/src/agent/agent.rs`
|
||||
- Modify: `/home/zyl/projects/sgClaw/claw/.worktrees/zeroclaw-prompt-safety-hardening/third_party/zeroclaw/src/agent/loop_.rs`
|
||||
- Test: `/home/zyl/projects/sgClaw/claw/.worktrees/zeroclaw-prompt-safety-hardening/third_party/zeroclaw/src/agent/dispatcher.rs`
|
||||
|
||||
**Step 1: Write failing dispatcher tests**
|
||||
|
||||
Add tests that prove:
|
||||
- `suspect_readonly` allows only safe read capabilities
|
||||
- `trusted_skill` can execute capabilities listed in its metadata within `step_budget`
|
||||
- `mixed` or non-skill privileged calls require a matching business approval token
|
||||
|
||||
**Step 2: Run the tests to verify RED**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
cargo test -p zeroclawlabs dispatcher -- --nocapture
|
||||
```
|
||||
|
||||
Expected: fail because the dispatcher does not yet know about execution modes.
|
||||
|
||||
**Step 3: Implement capability enforcement**
|
||||
|
||||
Before dispatching any tool:
|
||||
- resolve the operation context
|
||||
- map the tool call to a capability class
|
||||
- reject calls outside the current execution mode
|
||||
- decrement or validate `step_budget` for approved bounded flows
|
||||
|
||||
Do not rely on prompt text for enforcement.
|
||||
|
||||
**Step 4: Re-run the tests to verify GREEN**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
cargo test -p zeroclawlabs dispatcher -- --nocapture
|
||||
```
|
||||
|
||||
Expected: dispatch now respects read-only, trusted skill, and business-approved modes.
|
||||
|
||||
**Step 5: Commit**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
git add third_party/zeroclaw/src/agent/dispatcher.rs third_party/zeroclaw/src/agent/agent.rs third_party/zeroclaw/src/agent/loop_.rs
|
||||
git commit -m "feat: enforce execution mode in tool dispatch"
|
||||
```
|
||||
|
||||
### Task 8: Default Skills Prompt Injection to Compact for Safer Runtime Behavior
|
||||
|
||||
**Files:**
|
||||
- Modify: `/home/zyl/projects/sgClaw/claw/.worktrees/zeroclaw-prompt-safety-hardening/third_party/zeroclaw/src/config/schema.rs`
|
||||
- Modify: `/home/zyl/projects/sgClaw/claw/.worktrees/zeroclaw-prompt-safety-hardening/third_party/zeroclaw/src/agent/prompt.rs`
|
||||
- Modify: `/home/zyl/projects/sgClaw/claw/.worktrees/zeroclaw-prompt-safety-hardening/third_party/zeroclaw/src/channels/mod.rs`
|
||||
- Test: `/home/zyl/projects/sgClaw/claw/.worktrees/zeroclaw-prompt-safety-hardening/third_party/zeroclaw/src/config/schema.rs`
|
||||
|
||||
**Step 1: Write the failing configuration test**
|
||||
|
||||
Add a test that asserts the default skill prompt injection mode is `Compact` unless explicitly configured otherwise.
|
||||
|
||||
**Step 2: Run the test to verify RED**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
cargo test -p zeroclawlabs skills_prompt_injection_mode -- --nocapture
|
||||
```
|
||||
|
||||
Expected: fail because defaults still point to `Full`.
|
||||
|
||||
**Step 3: Implement the default flip**
|
||||
|
||||
Update config defaults and any prompt-builder defaults that currently assume `Full`. Keep explicit user config backward compatible.
|
||||
|
||||
**Step 4: Re-run the test to verify GREEN**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
cargo test -p zeroclawlabs skills_prompt_injection_mode -- --nocapture
|
||||
```
|
||||
|
||||
Expected: default configuration now resolves to `Compact`.
|
||||
|
||||
**Step 5: Commit**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
git add third_party/zeroclaw/src/config/schema.rs third_party/zeroclaw/src/agent/prompt.rs third_party/zeroclaw/src/channels/mod.rs
|
||||
git commit -m "feat: default skills prompt injection to compact"
|
||||
```
|
||||
|
||||
### Task 9: Add Audit Logging and Regression Coverage
|
||||
|
||||
**Files:**
|
||||
- Modify: `/home/zyl/projects/sgClaw/claw/.worktrees/zeroclaw-prompt-safety-hardening/third_party/zeroclaw/src/observability/mod.rs`
|
||||
- Modify: `/home/zyl/projects/sgClaw/claw/.worktrees/zeroclaw-prompt-safety-hardening/third_party/zeroclaw/src/agent/agent.rs`
|
||||
- Modify: `/home/zyl/projects/sgClaw/claw/.worktrees/zeroclaw-prompt-safety-hardening/third_party/zeroclaw/src/channels/mod.rs`
|
||||
- Create: `/home/zyl/projects/sgClaw/claw/.worktrees/zeroclaw-prompt-safety-hardening/third_party/zeroclaw/tests/prompt_safety_regression.rs`
|
||||
|
||||
**Step 1: Write the failing regression tests**
|
||||
|
||||
Cover:
|
||||
- prompt override attack from user content
|
||||
- malicious `AGENTS.md` bootstrap content
|
||||
- trusted skill execution within bounds
|
||||
- non-skill privileged request requiring business approval
|
||||
- approval token mismatch
|
||||
- session history restore preserving degraded mode
|
||||
|
||||
**Step 2: Run the tests to verify RED**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
cargo test -p zeroclawlabs --test prompt_safety_regression -- --nocapture
|
||||
```
|
||||
|
||||
Expected: fail because the end-to-end behavior is not wired together yet.
|
||||
|
||||
**Step 3: Implement audit logging**
|
||||
|
||||
Record:
|
||||
- input hash
|
||||
- matched guard rules
|
||||
- risk level
|
||||
- provenance
|
||||
- execution mode transitions
|
||||
- approval decisions
|
||||
|
||||
Avoid logging raw sensitive content.
|
||||
|
||||
**Step 4: Re-run the regression tests to verify GREEN**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
cargo test -p zeroclawlabs --test prompt_safety_regression -- --nocapture
|
||||
```
|
||||
|
||||
Expected: the regression suite passes.
|
||||
|
||||
**Step 5: Commit**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
git add third_party/zeroclaw/src/observability/mod.rs third_party/zeroclaw/src/agent/agent.rs third_party/zeroclaw/src/channels/mod.rs third_party/zeroclaw/tests/prompt_safety_regression.rs
|
||||
git commit -m "test: add prompt safety regression coverage"
|
||||
```
|
||||
|
||||
### Task 10: Final Verification and Integration Review
|
||||
|
||||
**Files:**
|
||||
- Modify: `/home/zyl/projects/sgClaw/claw/.worktrees/zeroclaw-prompt-safety-hardening/docs/L5-提示词分布与安全改造方案.md`
|
||||
- Modify: `/home/zyl/projects/sgClaw/claw/.worktrees/zeroclaw-prompt-safety-hardening/docs/README.md`
|
||||
|
||||
**Step 1: Run targeted verification**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
cd /home/zyl/projects/sgClaw/claw/.worktrees/zeroclaw-prompt-safety-hardening
|
||||
cargo test -p zeroclawlabs prompt_guard -- --nocapture
|
||||
cargo test -p zeroclawlabs build_system_prompt -- --nocapture
|
||||
cargo test -p zeroclawlabs dispatcher -- --nocapture
|
||||
cargo test -p zeroclawlabs --test prompt_safety_regression -- --nocapture
|
||||
```
|
||||
|
||||
Expected: all prompt safety and dispatcher tests pass.
|
||||
|
||||
**Step 2: Run a broad ZeroClaw package test pass if time permits**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
cargo test -p zeroclawlabs -- --nocapture
|
||||
```
|
||||
|
||||
Expected: no regressions in the vendored package test suite, or a documented list of unrelated existing failures.
|
||||
|
||||
**Step 3: Update the security design docs**
|
||||
|
||||
Document:
|
||||
- execution modes
|
||||
- trusted skill metadata contract
|
||||
- business approval flow
|
||||
- why non-skill privileged actions are gated
|
||||
|
||||
**Step 4: Commit the docs**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
git add docs/L5-提示词分布与安全改造方案.md docs/README.md
|
||||
git commit -m "docs: record prompt safety hardening design"
|
||||
```
|
||||
|
||||
**Step 5: Prepare merge review notes**
|
||||
|
||||
Write a short integration summary covering:
|
||||
- changed entry points
|
||||
- backward-compatibility expectations
|
||||
- any skills that need metadata upgrades
|
||||
- rollout recommendation for existing integrators
|
||||
179
docs/plans/2026-03-27-sgclaw-chat-first-ui-refactor-plan.md
Normal file
179
docs/plans/2026-03-27-sgclaw-chat-first-ui-refactor-plan.md
Normal file
@@ -0,0 +1,179 @@
|
||||
# sgClaw Chat-First UI Refactor Implementation Plan
|
||||
|
||||
> **For Claude:** REQUIRED SUB-SKILL: Use superpowers:executing-plans to implement this plan task-by-task.
|
||||
|
||||
**Goal:** Rebuild the sgClaw floating chat UI into a chat-first plugin-style product where the message timeline is primary, `执行摘要` is folded into the conversation, and `调试` opens as a full-window overlay instead of occupying persistent space.
|
||||
|
||||
**Architecture:** Keep `chrome://superrpa-functions/sgclaw-chat` as the first verified host because it already has Lit-based unit tests, then mirror the same information architecture and visual hierarchy into the ordinary-page injected `sgclaw_overlay.js`. Do not introduce a new backend contract; only rearrange presentation, panel semantics, and message/result composition around the existing runtime state.
|
||||
|
||||
**Tech Stack:** Chromium WebUI, Lit templates/components, injected Shadow DOM overlay JavaScript, existing SuperRPA bridge/runtime callbacks, mainline TS unit tests.
|
||||
|
||||
### Task 1: Lock The New Information Architecture In Tests
|
||||
|
||||
**Files:**
|
||||
- Modify: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_mainline_unittest.ts`
|
||||
- Modify: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_settings_state_mainline_unittest.ts`
|
||||
|
||||
**Step 1: Write the failing test**
|
||||
|
||||
Add assertions for these exact product rules:
|
||||
- `getHtml()` must no longer emit the legacy `debug-note`.
|
||||
- the main chat template must define a dedicated overlay/sheet container for `history`, `settings`, and `debug`.
|
||||
- the debug panel must be described as a full-window overlay rather than a side drawer/log block.
|
||||
- the result presentation must be part of the message stream, not a standalone persistent secondary panel.
|
||||
|
||||
**Step 2: Run test to verify it fails**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
node --test /home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_mainline_unittest.ts
|
||||
```
|
||||
|
||||
Expected: FAIL because current template still includes `debug-note`, side-by-side panel layout, and standalone result panel semantics.
|
||||
|
||||
**Step 3: Write minimal implementation**
|
||||
|
||||
Change only template/component strings and assertions needed to express the new structure, without touching styling yet.
|
||||
|
||||
**Step 4: Run test to verify it passes**
|
||||
|
||||
Run the same command.
|
||||
|
||||
Expected: PASS.
|
||||
|
||||
### Task 2: Refactor `chrome://` sgClaw Into Chat-First Structure
|
||||
|
||||
**Files:**
|
||||
- Modify: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat.html.ts`
|
||||
- Modify: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat.css.ts`
|
||||
- Modify: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/components/sgclaw-chat-header.ts`
|
||||
- Modify: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/components/sgclaw-chat-composer.ts`
|
||||
- Modify: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/components/sgclaw-debug-drawer.ts`
|
||||
- Modify: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/components/sgclaw-history-panel.ts`
|
||||
- Modify: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/components/sgclaw-settings-panel.ts`
|
||||
- Modify: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/components/sgclaw-message-list.ts`
|
||||
- Modify: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/components/sgclaw-message-card-result.ts`
|
||||
|
||||
**Step 1: Keep the header narrow**
|
||||
|
||||
Make the header carry only:
|
||||
- brand
|
||||
- current page label
|
||||
- compact runtime status
|
||||
- actions for `新对话 / 历史 / 设置 / 调试 / 收起`
|
||||
|
||||
Remove the large subtitle/debug framing and the separate heavy runtime action row feel.
|
||||
|
||||
**Step 2: Make the message timeline primary**
|
||||
|
||||
Turn the main shell body into:
|
||||
- a single timeline container
|
||||
- optional empty-state presets
|
||||
- no persistent secondary summary card
|
||||
|
||||
`finalResult` should render as a folded result card appended in the stream.
|
||||
|
||||
**Step 3: Convert secondary panels into full overlays**
|
||||
|
||||
Render `history`, `settings`, and `debug` inside a full-window overlay/sheet that covers the chat content area instead of sitting above or beside it.
|
||||
|
||||
**Step 4: Re-skin toward the approved direction**
|
||||
|
||||
Use:
|
||||
- soft neutral surfaces
|
||||
- restrained accent usage
|
||||
- thinner borders
|
||||
- calmer shadows
|
||||
- clearer assistant/user card contrast
|
||||
|
||||
Avoid:
|
||||
- debug-workbench feeling
|
||||
- large gradient blocks
|
||||
- heavy explanatory copy in the main flow
|
||||
|
||||
**Step 5: Run the unit tests**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
node --test /home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_mainline_unittest.ts
|
||||
```
|
||||
|
||||
Expected: PASS.
|
||||
|
||||
### Task 3: Mirror The Same Structure Into Ordinary-Page Overlay
|
||||
|
||||
**Files:**
|
||||
- Modify: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/sgclaw_overlay.js`
|
||||
|
||||
**Step 1: Remove the standalone result panel**
|
||||
|
||||
Delete the always-visible `执行摘要` block from the main window body.
|
||||
|
||||
**Step 2: Introduce overlay panels**
|
||||
|
||||
Change panel rendering so `history`, `settings`, and `debug` appear in a dedicated full-window overlay layer within the floating window instead of as sibling blocks consuming vertical space.
|
||||
|
||||
**Step 3: Rebuild the shell**
|
||||
|
||||
Match the `chrome://` layout:
|
||||
- compact header
|
||||
- primary message timeline
|
||||
- folded result card inside conversation
|
||||
- sticky composer
|
||||
|
||||
**Step 4: Preserve behavior**
|
||||
|
||||
Do not break:
|
||||
- `sgclaw.newConversation`
|
||||
- `sgclaw.restoreConversation`
|
||||
- runtime polling
|
||||
- config save/load
|
||||
- unread badge behavior
|
||||
|
||||
**Step 5: Run a syntax sanity check**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
node --check /home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/sgclaw_overlay.js
|
||||
```
|
||||
|
||||
Expected: PASS.
|
||||
|
||||
### Task 4: Verify Browser Resource Integration
|
||||
|
||||
**Files:**
|
||||
- No new source files; verification only
|
||||
|
||||
**Step 1: Run TS / mainline tests**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
bash -lc "autoninja -C /home/zyl/projects/superRpa/src/out/KylinRelease functions_ui_mainline_unittests"
|
||||
```
|
||||
|
||||
Expected: build succeeds.
|
||||
|
||||
**Step 2: Run targeted mainline unit tests**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
/home/zyl/projects/superRpa/src/out/KylinRelease/functions_ui_mainline_unittests --gtest_filter='FunctionsUiMainlineTest.*sgclaw*'
|
||||
```
|
||||
|
||||
If filter finds no test names, run the full binary and confirm it exits `0`.
|
||||
|
||||
**Step 3: Rebuild browser resources if needed**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
bash -lc "autoninja -C /home/zyl/projects/superRpa/src/out/KylinRelease chrome"
|
||||
```
|
||||
|
||||
**Step 4: Manually verify product behavior**
|
||||
|
||||
Check:
|
||||
- ordinary webpage floating window
|
||||
- `chrome://superrpa-functions/sgclaw-chat`
|
||||
- `调试` opens as full overlay
|
||||
- `执行摘要` no longer blocks the main conversation
|
||||
- `历史` and `设置` do not consume persistent layout space
|
||||
148
docs/plans/2026-03-27-sgclaw-configurable-skills-dir-plan.md
Normal file
148
docs/plans/2026-03-27-sgclaw-configurable-skills-dir-plan.md
Normal file
@@ -0,0 +1,148 @@
|
||||
# SGClaw Configurable Skills Directory Implementation Plan
|
||||
|
||||
> **For Claude:** REQUIRED SUB-SKILL: Use superpowers:executing-plans to implement this plan task-by-task.
|
||||
|
||||
**Goal:** Let `sgclaw` own skill-directory resolution and allow users to set a custom skills directory in `sgclaw_config.json` without relying on SuperRPA to copy skills into the runtime workspace.
|
||||
|
||||
**Architecture:** Extend the existing browser JSON config parser so `sgclaw` can read an optional `skillsDir` field alongside DeepSeek settings. Keep the current embedded ZeroClaw workspace for memory/config internals, but decouple skill loading from that fixed path by resolving a configurable skills root at runtime. Preserve backward compatibility by defaulting to `<workspace_root>/.sgclaw-zeroclaw-workspace/skills` when `skillsDir` is absent or empty.
|
||||
|
||||
**Tech Stack:** Rust, serde JSON parsing, existing ZeroClaw compatibility runtime, cargo test
|
||||
|
||||
### Task 1: Capture browser config requirements
|
||||
|
||||
**Files:**
|
||||
- Modify: `/home/zyl/projects/sgClaw/claw/src/config/settings.rs`
|
||||
- Test: `/home/zyl/projects/sgClaw/claw/tests/compat_config_test.rs`
|
||||
|
||||
**Step 1: Write the failing test**
|
||||
|
||||
Add tests that load `sgclaw_config.json` containing:
|
||||
- no `skillsDir`
|
||||
- a relative `skillsDir`
|
||||
- an absolute `skillsDir`
|
||||
|
||||
Assert that:
|
||||
- `skillsDir` missing falls back to default workspace skills path
|
||||
- relative values resolve against the browser config directory
|
||||
- absolute values are preserved
|
||||
|
||||
**Step 2: Run test to verify it fails**
|
||||
|
||||
Run: `cargo test compat_config -- --nocapture`
|
||||
|
||||
Expected: FAIL because `DeepSeekSettings` / config adapter do not expose any skills directory override yet.
|
||||
|
||||
**Step 3: Write minimal implementation**
|
||||
|
||||
Add a browser-config structure that parses `skillsDir` and expose a resolver function that returns the effective skills directory for `sgclaw`.
|
||||
|
||||
**Step 4: Run test to verify it passes**
|
||||
|
||||
Run: `cargo test compat_config -- --nocapture`
|
||||
|
||||
Expected: PASS for the new parsing and path-resolution cases.
|
||||
|
||||
### Task 2: Route compat runtime skill loading through sgclaw-owned resolution
|
||||
|
||||
**Files:**
|
||||
- Modify: `/home/zyl/projects/sgClaw/claw/src/compat/config_adapter.rs`
|
||||
- Modify: `/home/zyl/projects/sgClaw/claw/src/compat/runtime.rs`
|
||||
- Test: `/home/zyl/projects/sgClaw/claw/tests/compat_runtime_test.rs`
|
||||
|
||||
**Step 1: Write the failing test**
|
||||
|
||||
Add a compat runtime test that creates:
|
||||
- a default workspace skill package under `.sgclaw-zeroclaw-workspace/skills`
|
||||
- a custom skill package under another directory configured via `skillsDir`
|
||||
|
||||
Assert that provider request payload contains only the configured skill name when `skillsDir` is set, and still contains workspace skill names when the override is absent.
|
||||
|
||||
**Step 2: Run test to verify it fails**
|
||||
|
||||
Run: `cargo test compat_runtime -- --nocapture`
|
||||
|
||||
Expected: FAIL because the runtime currently always loads skills from `config.workspace_dir`.
|
||||
|
||||
**Step 3: Write minimal implementation**
|
||||
|
||||
Keep `config.workspace_dir` for ZeroClaw internal state, but load skills from the resolved effective skills directory by calling `load_skills_from_directory` directly when a custom directory is configured.
|
||||
|
||||
**Step 4: Run test to verify it passes**
|
||||
|
||||
Run: `cargo test compat_runtime -- --nocapture`
|
||||
|
||||
Expected: PASS and provider request payload shows the right `Available Skills` content.
|
||||
|
||||
### Task 3: Document and verify backward compatibility
|
||||
|
||||
**Files:**
|
||||
- Modify: `/home/zyl/projects/sgClaw/claw/docs/README.md`
|
||||
- Modify: `/home/zyl/projects/sgClaw/claw/docs/L5-提示词分布与安全改造方案.md`
|
||||
|
||||
**Step 1: Write the failing check**
|
||||
|
||||
Record the expected runtime behavior:
|
||||
- `sgclaw` owns skill lookup
|
||||
- SuperRPA only passes `--config-path`
|
||||
- `skillsDir` is optional
|
||||
|
||||
**Step 2: Run verification**
|
||||
|
||||
Run: `rg -n "skillsDir|sgclaw owns skill lookup|config-path" docs`
|
||||
|
||||
Expected: missing text before docs are updated.
|
||||
|
||||
**Step 3: Write minimal documentation**
|
||||
|
||||
Document:
|
||||
- JSON field name
|
||||
- relative-path resolution base
|
||||
- default fallback
|
||||
- operational implication for SuperRPA integration
|
||||
|
||||
**Step 4: Run verification**
|
||||
|
||||
Run: `rg -n "skillsDir|sgclaw owns skill lookup|config-path" docs`
|
||||
|
||||
Expected: PASS with updated docs.
|
||||
|
||||
### Task 4: Final verification
|
||||
|
||||
**Files:**
|
||||
- Review only: `/home/zyl/projects/sgClaw/claw/src/config/settings.rs`
|
||||
- Review only: `/home/zyl/projects/sgClaw/claw/src/compat/config_adapter.rs`
|
||||
- Review only: `/home/zyl/projects/sgClaw/claw/src/compat/runtime.rs`
|
||||
- Review only: `/home/zyl/projects/sgClaw/claw/tests/compat_config_test.rs`
|
||||
- Review only: `/home/zyl/projects/sgClaw/claw/tests/compat_runtime_test.rs`
|
||||
|
||||
**Step 1: Run targeted tests**
|
||||
|
||||
Run: `cargo test compat_config -- --nocapture`
|
||||
|
||||
Expected: PASS
|
||||
|
||||
**Step 2: Run runtime tests**
|
||||
|
||||
Run: `cargo test compat_runtime -- --nocapture`
|
||||
|
||||
Expected: PASS
|
||||
|
||||
**Step 3: Run skill-lib structural validation**
|
||||
|
||||
Run: `python3 -m unittest tests.skill_lib_validation_test -v`
|
||||
|
||||
Expected: PASS
|
||||
|
||||
**Step 4: Commit**
|
||||
|
||||
```bash
|
||||
git add docs/plans/2026-03-27-sgclaw-configurable-skills-dir-plan.md \
|
||||
src/config/settings.rs \
|
||||
src/compat/config_adapter.rs \
|
||||
src/compat/runtime.rs \
|
||||
tests/compat_config_test.rs \
|
||||
tests/compat_runtime_test.rs \
|
||||
docs/README.md \
|
||||
docs/L5-提示词分布与安全改造方案.md
|
||||
git commit -m "feat: make sgclaw skills directory configurable"
|
||||
```
|
||||
624
docs/plans/2026-03-27-sgclaw-floating-chat-frontend-design.md
Normal file
624
docs/plans/2026-03-27-sgclaw-floating-chat-frontend-design.md
Normal file
@@ -0,0 +1,624 @@
|
||||
# sgClaw Floating Chat Frontend Implementation Plan
|
||||
|
||||
> **For Claude:** REQUIRED SUB-SKILL: Use superpowers:executing-plans to implement this plan task-by-task.
|
||||
|
||||
**Goal:** Replace the current debug-style `sgclaw-chat` UI with a complete floating-chat frontend that matches the product structure of Doubao's side panel while preserving the current SuperRPA bridge and configuration capabilities.
|
||||
|
||||
**Architecture:** Keep `chrome://superrpa-functions/sgclaw-chat` as the first delivery host so the new UI can be built and verified without waiting for the final page-floating container. Split the current monolithic Lit component into host adapter, state modules, typed message model, presentational components, and secondary panels so the same UI can later be mounted in a real injected floating window on normal web pages. Preserve the existing browser bridge (`sgclawConnect`, `sgclawStart`, `sgclawStop`, `sgclawSubmitTask`) and re-home logs/configuration into secondary panels instead of deleting them.
|
||||
|
||||
**Tech Stack:** Chromium WebUI, Lit, existing `FunctionsUI` router, SuperRPA browser bridge callbacks, current `sgclaw-config` config page logic, future floating host injection in SuperRPA.
|
||||
|
||||
## Product Target
|
||||
|
||||
The frontend target is a single-column chat product, not a multi-card debug workstation.
|
||||
|
||||
Final visual structure:
|
||||
|
||||
```text
|
||||
Collapsed Fab
|
||||
┌────────────┐
|
||||
│ sgClaw ●2 │
|
||||
└────────────┘
|
||||
|
||||
Expanded Chat
|
||||
┌──────────────────────────────────────────┐
|
||||
│ sgClaw | 当前网页：example.com │
|
||||
│ [新对话] [历史] [设置] [收起] │
|
||||
│ 状态：待命 / 执行中 / 出错 │
|
||||
├──────────────────────────────────────────┤
|
||||
│ 欢迎区 / 推荐动作 │
|
||||
│ [总结当前页面] [提取表格] [执行网页操作] │
|
||||
├──────────────────────────────────────────┤
|
||||
│ 消息流 │
|
||||
│ 用户消息 │
|
||||
│ 助手消息 │
|
||||
│ 步骤卡 / 结果卡 / 错误卡 │
|
||||
├──────────────────────────────────────────┤
|
||||
│ [网页执行] [页面问答] [页面总结] │
|
||||
│ [上下文开关] [调试] [更多] │
|
||||
│ ┌──────────────────────────────────────┐ │
|
||||
│ │ 输入任务... │ │
|
||||
│ └──────────────────────────────────────┘ │
|
||||
│ [发送]│
|
||||
└──────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
Core UX rules:
|
||||
|
||||
- The primary content area is always the message stream.
|
||||
- `finalResult` becomes a result card inside the message stream.
|
||||
- `logs` move into a hidden debug drawer.
|
||||
- `start/stop` remain available but move to the header status area.
|
||||
- Configuration remains available but opens inside a settings panel first, with route-navigation fallback to `chrome://superrpa-functions/sgclaw-config`.
|
||||
- The same component tree must work in `FunctionsUI` first and later inside a real injected floating host.
|
||||
|
||||
## Scope
|
||||
|
||||
### In Scope For This Frontend Plan
|
||||
|
||||
- Complete visual redesign of `sgclaw-chat`
|
||||
- Empty state, active chat state, running state, success state, error state
|
||||
- Local conversation history UI
|
||||
- Embedded settings panel
|
||||
- Debug drawer
|
||||
- Stable typed message model
|
||||
- Separation of host bridge code from UI code
|
||||
- Floating launcher state model
|
||||
|
||||
### Explicitly Out Of Scope For First Frontend Delivery
|
||||
|
||||
- Real attachment upload execution
|
||||
- Deep-thinking or multi-skill plugin ecosystem
|
||||
- Provider/protocol redesign on the Rust side
|
||||
- Full page-injected floating host implementation
|
||||
- New backend APIs beyond the current bridge
|
||||
|
||||
## Existing Baseline To Reuse
|
||||
|
||||
The implementation should reuse these existing assets instead of replacing them blindly:
|
||||
|
||||
- Host page routing: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/functions.ts`
|
||||
- Existing chat entry registration: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/functions_manifest.json`
|
||||
- Current chat page bridge logic: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat.ts`
|
||||
- Current floating state prototype: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-floating_state.ts`
|
||||
- Current config UI and bridge: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-config/sgclaw-config.ts`
|
||||
|
||||
## Final File Layout
|
||||
|
||||
All implementation paths below are exact and rooted in `/home/zyl/projects/superRpa/src`.
|
||||
|
||||
### Core Chat Entry
|
||||
|
||||
- Modify: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat.ts`
|
||||
- Modify: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat.html.ts`
|
||||
- Modify: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat.css.ts`
|
||||
|
||||
### State Modules
|
||||
|
||||
- Modify: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-floating_state.ts`
|
||||
- Create: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_window_state.ts`
|
||||
- Create: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_conversation_state.ts`
|
||||
- Create: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_history_state.ts`
|
||||
- Create: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_settings_state.ts`
|
||||
- Modify: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_state.ts`
|
||||
|
||||
### Host Adapter
|
||||
|
||||
- Create: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_host_adapter.ts`
|
||||
- Create: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_runtime_bridge.ts`
|
||||
|
||||
### Message Model And Rendering
|
||||
|
||||
- Modify: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_messages.ts`
|
||||
- Create: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/components/sgclaw-message-list.ts`
|
||||
- Create: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/components/sgclaw-message-card-user.ts`
|
||||
- Create: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/components/sgclaw-message-card-assistant.ts`
|
||||
- Create: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/components/sgclaw-message-card-step.ts`
|
||||
- Create: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/components/sgclaw-message-card-result.ts`
|
||||
- Create: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/components/sgclaw-message-card-error.ts`
|
||||
|
||||
### Shell Components
|
||||
|
||||
- Create: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/components/sgclaw-chat-shell.ts`
|
||||
- Create: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/components/sgclaw-chat-header.ts`
|
||||
- Create: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/components/sgclaw-chat-composer.ts`
|
||||
- Create: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/components/sgclaw-history-panel.ts`
|
||||
- Create: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/components/sgclaw-settings-panel.ts`
|
||||
- Create: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/components/sgclaw-debug-drawer.ts`
|
||||
|
||||
### Build And Host Wiring
|
||||
|
||||
- Modify: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/BUILD.gn`
|
||||
- Modify: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/functions.html.ts`
|
||||
|
||||
### Tests
|
||||
|
||||
- Modify: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-floating_state_mainline_unittest.ts`
|
||||
- Modify: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_mainline_unittest.ts`
|
||||
- Create: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_window_state_mainline_unittest.ts`
|
||||
- Create: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_history_state_mainline_unittest.ts`
|
||||
- Create: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_settings_state_mainline_unittest.ts`
|
||||
- Create: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_runtime_bridge_mainline_unittest.ts`
|
||||
|
||||
## Target State Model
|
||||
|
||||
Use a typed model instead of the current loose shape.
|
||||
|
||||
```ts
|
||||
interface SgClawChatWindowState {
|
||||
windowOpen: boolean;
|
||||
activePanel: 'chat' | 'history' | 'settings' | 'debug';
|
||||
unreadCount: number;
|
||||
}
|
||||
|
||||
interface SgClawChatConversationState {
|
||||
conversationId: string;
|
||||
draftInput: string;
|
||||
mode: 'web-action' | 'page-qa' | 'page-summary';
|
||||
contextEnabled: boolean;
|
||||
messages: SgClawMessage[];
|
||||
}
|
||||
|
||||
interface SgClawMessage {
|
||||
id: string;
|
||||
type: 'user_text' | 'assistant_text' | 'task_step' | 'task_result' | 'task_error' | 'system_notice';
|
||||
role: 'user' | 'assistant' | 'system';
|
||||
content: string;
|
||||
status?: 'pending' | 'running' | 'done' | 'failed';
|
||||
timestamp: number;
|
||||
meta?: Record<string, unknown>;
|
||||
}
|
||||
```
|
||||
|
||||
The current `logs`, `messages`, `finalResult`, `pendingReply`, and `busy` state should be re-expressed through these typed stores instead of being owned directly by the entry component.
|
||||
|
||||
## Task 1: Freeze The Current Entry And Enable Real Template/CSS Modules
|
||||
|
||||
**Files:**
|
||||
- Modify: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat.ts`
|
||||
- Modify: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat.html.ts`
|
||||
- Modify: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat.css.ts`
|
||||
- Test: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_mainline_unittest.ts`
|
||||
|
||||
**Step 1: Write the failing structure test**
|
||||
|
||||
Add assertions that the entry no longer hardcodes the full DOM layout in `render()` and imports its shell template/style helpers.
|
||||
|
||||
**Step 2: Run test to verify it fails**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
autoninja -C /home/zyl/projects/superRpa/src/out/KylinRelease sgclaw-chat_build_ts
|
||||
```
|
||||
|
||||
Expected: fail because `sgclaw-chat.html.ts` and `sgclaw-chat.css.ts` are empty and the new test expects real exports.
|
||||
|
||||
**Step 3: Write the minimal implementation**
|
||||
|
||||
- Move root shell markup to `getHtml()`
|
||||
- Move root style tokens/layout to `getCss()`
|
||||
- Keep `sgclaw-chat.ts` focused on state + events
|
||||
|
||||
**Step 4: Run test to verify it passes**
|
||||
|
||||
Run the same build target.
|
||||
|
||||
Expected: TS build succeeds and the entry uses external template/style helpers.
|
||||
|
||||
**Step 5: Commit**
|
||||
|
||||
```bash
|
||||
git -C /home/zyl/projects/superRpa/src add \
|
||||
chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat.ts \
|
||||
chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat.html.ts \
|
||||
chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat.css.ts \
|
||||
chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_mainline_unittest.ts
|
||||
git -C /home/zyl/projects/superRpa/src commit -m "refactor: extract sgclaw chat shell template"
|
||||
```
|
||||
|
||||
## Task 2: Build The Window, Conversation, History, And Settings State Modules
|
||||
|
||||
**Files:**
|
||||
- Modify: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-floating_state.ts`
|
||||
- Create: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_window_state.ts`
|
||||
- Create: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_conversation_state.ts`
|
||||
- Create: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_history_state.ts`
|
||||
- Create: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_settings_state.ts`
|
||||
- Modify: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_state.ts`
|
||||
- Test: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-floating_state_mainline_unittest.ts`
|
||||
- Test: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_window_state_mainline_unittest.ts`
|
||||
- Test: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_history_state_mainline_unittest.ts`
|
||||
- Test: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_settings_state_mainline_unittest.ts`
|
||||
|
||||
**Step 1: Write the failing pure-state tests**
|
||||
|
||||
Cover:
|
||||
- open/close/switch panel transitions
|
||||
- unread count clear on open
|
||||
- create/reset conversation
|
||||
- local history push/select/remove
|
||||
- settings draft dirty detection
|
||||
|
||||
**Step 2: Run tests to verify RED**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
autoninja -C /home/zyl/projects/superRpa/src/out/KylinRelease sgclaw-chat_build_ts
|
||||
```
|
||||
|
||||
Expected: build fails because the new modules and tests do not exist yet.
|
||||
|
||||
**Step 3: Write the minimal implementation**
|
||||
|
||||
Implement pure functions only. Do not mix DOM work into these modules.
|
||||
|
||||
**Step 4: Run tests to verify GREEN**
|
||||
|
||||
Run the same build target.
|
||||
|
||||
Expected: all pure-state modules compile and their tests pass.
|
||||
|
||||
**Step 5: Commit**
|
||||
|
||||
```bash
|
||||
git -C /home/zyl/projects/superRpa/src add \
|
||||
chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-floating_state.ts \
|
||||
chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_window_state.ts \
|
||||
chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_conversation_state.ts \
|
||||
chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_history_state.ts \
|
||||
chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_settings_state.ts \
|
||||
chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_state.ts \
|
||||
chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-floating_state_mainline_unittest.ts \
|
||||
chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_window_state_mainline_unittest.ts \
|
||||
chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_history_state_mainline_unittest.ts \
|
||||
chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_settings_state_mainline_unittest.ts
|
||||
git -C /home/zyl/projects/superRpa/src commit -m "feat: add sgclaw chat state modules"
|
||||
```
|
||||
|
||||
## Task 3: Introduce A Host Adapter So UI Stops Owning Bridge Details
|
||||
|
||||
**Files:**
|
||||
- Create: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_host_adapter.ts`
|
||||
- Create: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_runtime_bridge.ts`
|
||||
- Modify: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat.ts`
|
||||
- Test: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_runtime_bridge_mainline_unittest.ts`
|
||||
|
||||
**Step 1: Write the failing bridge test**
|
||||
|
||||
Test that:
|
||||
- `connect()` issues `sgclawConnect`
|
||||
- `start()` issues `sgclawStart`
|
||||
- `stop()` issues `sgclawStop`
|
||||
- `submitTask()` issues `sgclawSubmitTask`
|
||||
- callback payload parsing is handled in one place
|
||||
|
||||
**Step 2: Run test to verify RED**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
autoninja -C /home/zyl/projects/superRpa/src/out/KylinRelease sgclaw-chat_build_ts
|
||||
```
|
||||
|
||||
Expected: fail because adapter modules do not exist.
|
||||
|
||||
**Step 3: Write minimal implementation**
|
||||
|
||||
- Wrap `chrome.send`
|
||||
- Centralize callback registration
|
||||
- Return typed runtime events/state to the UI layer
|
||||
|
||||
**Step 4: Run test to verify GREEN**
|
||||
|
||||
Run the same build target.
|
||||
|
||||
Expected: adapter tests compile and pass.
|
||||
|
||||
**Step 5: Commit**
|
||||
|
||||
```bash
|
||||
git -C /home/zyl/projects/superRpa/src add \
|
||||
chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_host_adapter.ts \
|
||||
chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_runtime_bridge.ts \
|
||||
chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat.ts \
|
||||
chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_runtime_bridge_mainline_unittest.ts
|
||||
git -C /home/zyl/projects/superRpa/src commit -m "refactor: isolate sgclaw chat host bridge"
|
||||
```
|
||||
|
||||
## Task 4: Replace The Loose Message Format With Typed Cards In The Message Stream
|
||||
|
||||
**Files:**
|
||||
- Modify: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_messages.ts`
|
||||
- Create: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/components/sgclaw-message-list.ts`
|
||||
- Create: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/components/sgclaw-message-card-user.ts`
|
||||
- Create: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/components/sgclaw-message-card-assistant.ts`
|
||||
- Create: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/components/sgclaw-message-card-step.ts`
|
||||
- Create: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/components/sgclaw-message-card-result.ts`
|
||||
- Create: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/components/sgclaw-message-card-error.ts`
|
||||
- Modify: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat.ts`
|
||||
- Test: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_mainline_unittest.ts`
|
||||
|
||||
**Step 1: Write the failing rendering test**
|
||||
|
||||
Add expectations that:
|
||||
- empty state shows guidance instead of a blank box
|
||||
- `task_complete` renders a result card in the message stream
|
||||
- `error` renders an error card in the message stream
|
||||
- `pendingReply` renders an assistant pending card
|
||||
|
||||
**Step 2: Run test to verify RED**
|
||||
|
||||
Run the TS build target.
|
||||
|
||||
Expected: fail because message types and card components do not exist.
|
||||
|
||||
**Step 3: Write minimal implementation**
|
||||
|
||||
- Keep the message list single-column
|
||||
- Preserve current user/assistant turn behavior
|
||||
- Move `finalResult` handling into result-card rendering
|
||||
- Move error display into message flow
|
||||
|
||||
**Step 4: Run test to verify GREEN**
|
||||
|
||||
Run the same build target.
|
||||
|
||||
Expected: cards render correctly and the old standalone result area is no longer required.
|
||||
|
||||
**Step 5: Commit**
|
||||
|
||||
```bash
|
||||
git -C /home/zyl/projects/superRpa/src add \
|
||||
chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_messages.ts \
|
||||
chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/components/sgclaw-message-list.ts \
|
||||
chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/components/sgclaw-message-card-user.ts \
|
||||
chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/components/sgclaw-message-card-assistant.ts \
|
||||
chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/components/sgclaw-message-card-step.ts \
|
||||
chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/components/sgclaw-message-card-result.ts \
|
||||
chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/components/sgclaw-message-card-error.ts \
|
||||
chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat.ts \
|
||||
chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_mainline_unittest.ts
|
||||
git -C /home/zyl/projects/superRpa/src commit -m "feat: add sgclaw chat message cards"
|
||||
```
|
||||
|
||||
## Task 5: Build The Real Header, Empty State, And Composer
|
||||
|
||||
**Files:**
|
||||
- Create: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/components/sgclaw-chat-shell.ts`
|
||||
- Create: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/components/sgclaw-chat-header.ts`
|
||||
- Create: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/components/sgclaw-chat-composer.ts`
|
||||
- Modify: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat.html.ts`
|
||||
- Modify: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat.css.ts`
|
||||
- Modify: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat.ts`
|
||||
- Test: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_mainline_unittest.ts`
|
||||
|
||||
**Step 1: Write the failing shell test**
|
||||
|
||||
Assert that the rendered page now contains:
|
||||
- header with title, current page label, and status pill
|
||||
- empty state recommendation buttons
|
||||
- fixed composer at the bottom
|
||||
- no standalone `实时日志` or `最终结果` primary sections
|
||||
|
||||
**Step 2: Run test to verify RED**
|
||||
|
||||
Run the TS build target.
|
||||
|
||||
Expected: fail because the shell components do not exist.
|
||||
|
||||
**Step 3: Write minimal implementation**
|
||||
|
||||
- Header: title, page context, new-chat/history/settings/collapse actions
|
||||
- Empty state: 3 to 4 recommended actions
|
||||
- Composer: text input, send button, mode toggles, context switch
|
||||
|
||||
**Step 4: Run test to verify GREEN**
|
||||
|
||||
Run the same build target.
|
||||
|
||||
Expected: the page renders as a product-style chat shell.
|
||||
|
||||
**Step 5: Commit**
|
||||
|
||||
```bash
|
||||
git -C /home/zyl/projects/superRpa/src add \
|
||||
chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/components/sgclaw-chat-shell.ts \
|
||||
chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/components/sgclaw-chat-header.ts \
|
||||
chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/components/sgclaw-chat-composer.ts \
|
||||
chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat.html.ts \
|
||||
chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat.css.ts \
|
||||
chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat.ts \
|
||||
chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_mainline_unittest.ts
|
||||
git -C /home/zyl/projects/superRpa/src commit -m "feat: add sgclaw chat shell and composer"
|
||||
```
|
||||
|
||||
## Task 6: Embed Settings And Move Raw Logs Into A Debug Drawer
|
||||
|
||||
**Files:**
|
||||
- Create: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/components/sgclaw-settings-panel.ts`
|
||||
- Create: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/components/sgclaw-debug-drawer.ts`
|
||||
- Modify: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat.ts`
|
||||
- Modify: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat.css.ts`
|
||||
- Reuse Read-Only Reference: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-config/sgclaw-config.ts`
|
||||
- Test: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_settings_state_mainline_unittest.ts`
|
||||
|
||||
**Step 1: Write the failing panel tests**
|
||||
|
||||
Cover:
|
||||
- opening settings panel from header
|
||||
- editing embedded config draft
|
||||
- opening debug drawer and showing logs
|
||||
- closing secondary panels without destroying the chat draft
|
||||
|
||||
**Step 2: Run test to verify RED**
|
||||
|
||||
Run the TS build target.
|
||||
|
||||
Expected: fail because secondary panel components do not exist.
|
||||
|
||||
**Step 3: Write minimal implementation**
|
||||
|
||||
- Reuse config field structure from `sgclaw-config`
|
||||
- Keep raw logs in debug only
|
||||
- Preserve route-navigation fallback for full config page if embedded save/load fails
|
||||
|
||||
**Step 4: Run test to verify GREEN**
|
||||
|
||||
Run the same build target.
|
||||
|
||||
Expected: settings and debug layers behave as secondary panels instead of separate pages.
|
||||
|
||||
**Step 5: Commit**
|
||||
|
||||
```bash
|
||||
git -C /home/zyl/projects/superRpa/src add \
|
||||
chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/components/sgclaw-settings-panel.ts \
|
||||
chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/components/sgclaw-debug-drawer.ts \
|
||||
chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat.ts \
|
||||
chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat.css.ts \
|
||||
chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_settings_state_mainline_unittest.ts
|
||||
git -C /home/zyl/projects/superRpa/src commit -m "feat: add sgclaw settings panel and debug drawer"
|
||||
```
|
||||
|
||||
## Task 7: Add Local Conversation History And New-Chat Recovery
|
||||
|
||||
**Files:**
|
||||
- Create: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/components/sgclaw-history-panel.ts`
|
||||
- Modify: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_history_state.ts`
|
||||
- Modify: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat.ts`
|
||||
- Test: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_history_state_mainline_unittest.ts`
|
||||
|
||||
**Step 1: Write the failing history tests**
|
||||
|
||||
Cover:
|
||||
- saving a conversation preview to local history
|
||||
- creating a fresh conversation resets message stream but keeps config
|
||||
- reopening a history item restores messages and draft
|
||||
|
||||
**Step 2: Run test to verify RED**
|
||||
|
||||
Run the TS build target.
|
||||
|
||||
Expected: fail because history panel and persistence behavior do not exist.
|
||||
|
||||
**Step 3: Write minimal implementation**
|
||||
|
||||
- Store history locally in browser storage or localStorage
|
||||
- Keep only small metadata + message snapshot for first version
|
||||
- No backend schema change in this phase
|
||||
|
||||
**Step 4: Run test to verify GREEN**
|
||||
|
||||
Run the same build target.
|
||||
|
||||
Expected: local conversation switching works fully in the frontend.
|
||||
|
||||
**Step 5: Commit**
|
||||
|
||||
```bash
|
||||
git -C /home/zyl/projects/superRpa/src add \
|
||||
chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/components/sgclaw-history-panel.ts \
|
||||
chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_history_state.ts \
|
||||
chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat.ts \
|
||||
chrome/browser/resources/superrpa/devtools/functions/sgclaw-chat/sgclaw-chat_history_state_mainline_unittest.ts
|
||||
git -C /home/zyl/projects/superRpa/src commit -m "feat: add sgclaw local conversation history"
|
||||
```
|
||||
|
||||
## Task 8: Wire New Shell Assets Into BUILD And Polish The Host Page
|
||||
|
||||
**Files:**
|
||||
- Modify: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/BUILD.gn`
|
||||
- Modify: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/functions.html.ts`
|
||||
- Modify: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/devtools/functions/functions.css`
|
||||
|
||||
**Step 1: Write the failing host expectation**
|
||||
|
||||
Add a small host-level check that:
|
||||
- `sgclaw-chat` still loads from the manifest
|
||||
- host quick actions still work
|
||||
- the function page provides enough room for the new chat shell
|
||||
|
||||
**Step 2: Run test/build to verify RED**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
autoninja -C /home/zyl/projects/superRpa/src/out/KylinRelease sgclaw-chat_build_ts
|
||||
```
|
||||
|
||||
Expected: fail or render incorrectly because new component files are not all wired into build/host styling yet.
|
||||
|
||||
**Step 3: Write minimal implementation**
|
||||
|
||||
- Add all new TS modules to `BUILD.gn`
|
||||
- Keep `sgclaw-chat` and `sgclaw-config` quick actions
|
||||
- Adjust host layout so the new shell is not boxed into the old debug-page proportions
|
||||
|
||||
**Step 4: Run verification**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
autoninja -C /home/zyl/projects/superRpa/src/out/KylinRelease sgclaw-chat_build_ts
|
||||
autoninja -C /home/zyl/projects/superRpa/src/out/KylinRelease superrpa_resources
|
||||
```
|
||||
|
||||
Expected: build completes with all new chat modules wired in.
|
||||
|
||||
**Step 5: Commit**
|
||||
|
||||
```bash
|
||||
git -C /home/zyl/projects/superRpa/src add \
|
||||
chrome/browser/resources/superrpa/devtools/BUILD.gn \
|
||||
chrome/browser/resources/superrpa/devtools/functions/functions.html.ts \
|
||||
chrome/browser/resources/superrpa/devtools/functions/functions.css
|
||||
git -C /home/zyl/projects/superRpa/src commit -m "chore: wire sgclaw chat frontend modules"
|
||||
```
|
||||
|
||||
## Manual Verification Matrix
|
||||
|
||||
Run all manual checks in `chrome://superrpa-functions/sgclaw-chat` after the full frontend plan lands.
|
||||
|
||||
### UX States
|
||||
|
||||
- Empty state appears on first open.
|
||||
- Recommended actions generate user messages.
|
||||
- Composer stays visible while history/settings/debug panels switch.
|
||||
- Message stream auto-scrolls to the latest item.
|
||||
- Result cards and error cards appear inline.
|
||||
|
||||
### Runtime
|
||||
|
||||
- `启动` works from the header area.
|
||||
- `停止` works from the header area.
|
||||
- submit creates an immediate user message.
|
||||
- pending assistant card appears while waiting.
|
||||
- result card replaces the old standalone result behavior.
|
||||
|
||||
### Settings
|
||||
|
||||
- embedded settings loads existing values
|
||||
- save updates status and clears dirty state
|
||||
- fallback route to `chrome://superrpa-functions/sgclaw-config` still works
|
||||
|
||||
### Debug
|
||||
|
||||
- logs are not visible in the main chat view
|
||||
- debug drawer shows raw logs when opened
|
||||
|
||||
### History
|
||||
|
||||
- new conversation starts clean
|
||||
- previous conversation can be restored from local history
|
||||
- unread badge clears when reopening the window
|
||||
|
||||
## Execution Notes
|
||||
|
||||
- Keep the current backend/runtime bridge unchanged until the new frontend shell is stable.
|
||||
- Do not combine page-injected floating host work into this same branch. The first milestone is a complete product-grade frontend inside the existing `FunctionsUI` host.
|
||||
- When this frontend plan is complete, the next plan should focus only on mounting the same component tree inside a real page floating container.
|
||||
|
||||
Plan complete and saved to `docs/plans/2026-03-27-sgclaw-floating-chat-frontend-design.md`. Two execution options:
|
||||
|
||||
**1. Subagent-Driven (this session)** - I dispatch fresh subagent per task, review between tasks, fast iteration
|
||||
|
||||
**2. Parallel Session (separate)** - Open new session with executing-plans, batch execution with checkpoints
|
||||
|
||||
**Which approach?**
|
||||
@@ -0,0 +1,85 @@
|
||||
# sgClaw Overlay And Basic Navigation Fixes Implementation Plan
|
||||
|
||||
> **For Claude:** REQUIRED SUB-SKILL: Use superpowers:executing-plans to implement this plan task-by-task.
|
||||
|
||||
**Goal:** Make ordinary webpages render the new sgClaw floating chat design and support base navigation instructions like `打开知乎`.
|
||||
|
||||
**Architecture:** Keep the ordinary-page injection entrypoint unchanged, but replace its in-shadow DOM layout with the same floating-window shell used by the new debug page. On the runtime side, extend the deterministic planner with explicit homepage navigation plans for supported sites so freeform open-site commands do not fail before the compat runtime can help.
|
||||
|
||||
**Tech Stack:** Chromium WebUI resource pipeline, injected Shadow DOM overlay JavaScript, Rust planner tests
|
||||
|
||||
### Task 1: Lock the current regressions with failing tests
|
||||
|
||||
**Files:**
|
||||
- Modify: `/home/zyl/projects/superRpa/src/chrome/browser/superrpa/sgclaw/sgclaw_chat_smoke.mjs`
|
||||
- Modify: `/home/zyl/projects/sgClaw/claw/tests/planner_test.rs`
|
||||
|
||||
**Step 1: Write the failing smoke expectations**
|
||||
|
||||
Add assertions that the ordinary webpage overlay shows the new subtitle `面向当前网页的悬浮式对话与自动执行` and no longer exposes the old card titles like `聊天记录`.
|
||||
|
||||
**Step 2: Run the smoke to verify it fails**
|
||||
|
||||
Run: `node /home/zyl/projects/superRpa/src/chrome/browser/superrpa/sgclaw/sgclaw_chat_smoke.mjs`
|
||||
Expected: FAIL because ordinary webpages still render the old overlay shell.
|
||||
|
||||
**Step 3: Write the failing planner test**
|
||||
|
||||
Add a test asserting `plan_instruction("打开知乎")` returns one `Navigate` step to `https://www.zhihu.com`.
|
||||
|
||||
**Step 4: Run the planner test to verify it fails**
|
||||
|
||||
Run: `cargo test planner_supports_open_zhihu_homepage_instruction --test planner_test`
|
||||
Expected: FAIL with `unsupported instruction: 打开知乎`.
|
||||
|
||||
### Task 2: Migrate the ordinary webpage overlay to the new shell
|
||||
|
||||
**Files:**
|
||||
- Modify: `/home/zyl/projects/superRpa/src/chrome/browser/resources/superrpa/sgclaw_overlay.js`
|
||||
- Test: `/home/zyl/projects/superRpa/src/chrome/browser/superrpa/sgclaw/sgclaw_chat_smoke.mjs`
|
||||
|
||||
**Step 1: Replace the old card layout with the new floating shell**
|
||||
|
||||
Keep bridge calls, ids, and polling behavior intact, but render the new header, message pane, composer, settings panel, and debug drawer structure inside the existing injected Shadow DOM.
|
||||
|
||||
**Step 2: Keep runtime visibility without reintroducing the old layout**
|
||||
|
||||
Move logs and final result into secondary panels or inline cards so the ordinary webpage still exposes execution details without the old four-card layout.
|
||||
|
||||
**Step 3: Run the smoke again**
|
||||
|
||||
Run: `node /home/zyl/projects/superRpa/src/chrome/browser/superrpa/sgclaw/sgclaw_chat_smoke.mjs`
|
||||
Expected: PASS once rebuilt resources are being served by the browser binary.
|
||||
|
||||
### Task 3: Extend planner support for basic open-site commands
|
||||
|
||||
**Files:**
|
||||
- Modify: `/home/zyl/projects/sgClaw/claw/src/agent/planner.rs`
|
||||
- Test: `/home/zyl/projects/sgClaw/claw/tests/planner_test.rs`
|
||||
|
||||
**Step 1: Implement the minimal homepage plans**
|
||||
|
||||
Support `打开知乎` and `打开百度` by returning single-step `Navigate` plans to their homepages.
|
||||
|
||||
**Step 2: Run planner tests**
|
||||
|
||||
Run: `cargo test --test planner_test`
|
||||
Expected: PASS.
|
||||
|
||||
### Task 4: Build and verify the integrated behavior
|
||||
|
||||
**Files:**
|
||||
- Modify: `/home/zyl/projects/superRpa/src/AGENTS.md`
|
||||
- Modify: `/home/zyl/projects/superRpa/src/docs/handoffs/2026-03-27-sgclaw-runtime-verification.md`
|
||||
|
||||
**Step 1: Rebuild impacted targets**
|
||||
|
||||
Run: `autoninja -C /home/zyl/projects/superRpa/src/out/KylinRelease chrome/browser/resources/superrpa:resources sgclaw`
|
||||
|
||||
**Step 2: Re-run targeted verification**
|
||||
|
||||
Run the smoke and a focused `sgclaw` task submission check for `打开知乎`.
|
||||
|
||||
**Step 3: Document the final runtime path**
|
||||
|
||||
Record that ordinary webpages and `chrome://superrpa-functions/sgclaw-chat` now share the same floating shell, and that homepage navigation commands are handled by the planner.
|
||||
158
docs/plans/2026-03-27-skill-lib-testing-plan.md
Normal file
158
docs/plans/2026-03-27-skill-lib-testing-plan.md
Normal file
@@ -0,0 +1,158 @@
|
||||
# Skill Lib Testing Implementation Plan
|
||||
|
||||
> **For Claude:** REQUIRED SUB-SKILL: Use superpowers:executing-plans to implement this plan task-by-task.
|
||||
|
||||
**Goal:** Add an in-project, repeatable test harness that validates `/home/zyl/projects/sgClaw/skill_lib` against the current ZeroClaw `SKILL.md` loader and security-audit expectations.
|
||||
|
||||
**Architecture:** Keep the test runner inside the SGClaw repository and target the sibling `skill_lib` directory by relative path. Implement a small Python validator that mirrors the ZeroClaw markdown frontmatter parser and the relevant skill-audit checks, then cover it with a Python `unittest` suite that exercises the actual three migrated Zhihu skills.
|
||||
|
||||
**Tech Stack:** Python 3 standard library, `unittest`, local file-system inspection, ZeroClaw source code as behavioral reference, Markdown/YAML-like frontmatter parsing.
|
||||
|
||||
### Task 1: Freeze The Test Contract
|
||||
|
||||
**Files:**
|
||||
- Create: `/home/zyl/projects/sgClaw/claw/docs/plans/2026-03-27-skill-lib-testing-plan.md`
|
||||
- Reference only: `/home/zyl/projects/sgClaw/claw/third_party/zeroclaw/src/skills/mod.rs`
|
||||
- Reference only: `/home/zyl/projects/sgClaw/claw/third_party/zeroclaw/src/skills/audit.rs`
|
||||
- Reference only: `/home/zyl/projects/sgClaw/skill_lib/skills/*/SKILL.md`
|
||||
|
||||
**Step 1: Capture the loader semantics to preserve**
|
||||
|
||||
Document and implement tests for:
|
||||
- `SKILL.md` frontmatter splitting on `---`
|
||||
- supported metadata keys: `name`, `description`, `version`, `author`, `tags`
|
||||
- fallback rules for name, description, and version
|
||||
- prompt body must exclude the frontmatter block
|
||||
|
||||
**Step 2: Capture the audit semantics to preserve**
|
||||
|
||||
Document and implement tests for:
|
||||
- skill root must contain `SKILL.md` or `SKILL.toml`
|
||||
- symlinks are rejected
|
||||
- shell-script files are blocked when `allow_scripts` is false
|
||||
- markdown links must not escape the skill root
|
||||
- high-risk command snippets inside markdown are rejected
|
||||
|
||||
**Step 3: Define the migrated-skill expectations**
|
||||
|
||||
The test suite must verify:
|
||||
- exactly three skill packages exist
|
||||
- the loaded names are `zhihu-hotlist`, `zhihu-navigate`, `zhihu-write`
|
||||
- each package has both `references/` and `assets/`
|
||||
- each description stays trigger-oriented and starts with `Use when`
|
||||
|
||||
### Task 2: Write The Failing Tests First
|
||||
|
||||
**Files:**
|
||||
- Create: `/home/zyl/projects/sgClaw/claw/tests/skill_lib_validation_test.py`
|
||||
|
||||
**Step 1: Write a failing import-level test**
|
||||
|
||||
Import a not-yet-created validator module from:
|
||||
- `/home/zyl/projects/sgClaw/claw/scripts/validate_skill_lib.py`
|
||||
|
||||
Expected initial failure:
|
||||
- `ModuleNotFoundError` or `FileNotFoundError`
|
||||
|
||||
**Step 2: Encode the project expectations**
|
||||
|
||||
Add tests for:
|
||||
- skill discovery count and names
|
||||
- parsed metadata for each current skill
|
||||
- audit cleanliness for each skill with `allow_scripts=False`
|
||||
- package shape (`SKILL.md`, `references/`, `assets/`)
|
||||
|
||||
**Step 3: Run the tests and watch them fail**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
python3 -m unittest tests.skill_lib_validation_test -v
|
||||
```
|
||||
|
||||
Expected:
|
||||
- failure because the validator module does not exist yet
|
||||
|
||||
### Task 3: Implement The Minimal Validator
|
||||
|
||||
**Files:**
|
||||
- Create: `/home/zyl/projects/sgClaw/claw/scripts/validate_skill_lib.py`
|
||||
|
||||
**Step 1: Implement discovery helpers**
|
||||
|
||||
Implement:
|
||||
- repo root resolution
|
||||
- sibling `skill_lib` root resolution
|
||||
- `skills/` directory enumeration
|
||||
|
||||
**Step 2: Implement the markdown loader**
|
||||
|
||||
Implement:
|
||||
- frontmatter split
|
||||
- lightweight frontmatter parsing
|
||||
- description fallback extraction
|
||||
- metadata normalization into a `SkillRecord`
|
||||
|
||||
**Step 3: Implement the relevant audit checks**
|
||||
|
||||
Implement:
|
||||
- symlink detection
|
||||
- blocked shell-script detection
|
||||
- markdown link boundary checks
|
||||
- high-risk snippet detection
|
||||
- deterministic findings collection
|
||||
|
||||
**Step 4: Implement a small CLI**
|
||||
|
||||
Running:
|
||||
```bash
|
||||
python3 scripts/validate_skill_lib.py
|
||||
```
|
||||
|
||||
Should:
|
||||
- print one summary line per skill
|
||||
- exit `0` when all skills pass
|
||||
- exit non-zero when any skill fails
|
||||
|
||||
### Task 4: Run The Tests Green
|
||||
|
||||
**Files:**
|
||||
- Test: `/home/zyl/projects/sgClaw/claw/tests/skill_lib_validation_test.py`
|
||||
- Test: `/home/zyl/projects/sgClaw/claw/scripts/validate_skill_lib.py`
|
||||
|
||||
**Step 1: Re-run the unit tests**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
python3 -m unittest tests.skill_lib_validation_test -v
|
||||
```
|
||||
|
||||
Expected:
|
||||
- all tests pass
|
||||
|
||||
**Step 2: Run the CLI validator**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
python3 scripts/validate_skill_lib.py
|
||||
```
|
||||
|
||||
Expected:
|
||||
- all three skills print `PASS`
|
||||
- process exits `0`
|
||||
|
||||
### Task 5: Document The Verification Entry Point
|
||||
|
||||
**Files:**
|
||||
- Modify: `/home/zyl/projects/sgClaw/skill_lib/VERIFY.md`
|
||||
|
||||
**Step 1: Add the project-local validation command**
|
||||
|
||||
Add:
|
||||
- `python3 /home/zyl/projects/sgClaw/claw/scripts/validate_skill_lib.py`
|
||||
- `python3 -m unittest /home/zyl/projects/sgClaw/claw/tests/skill_lib_validation_test.py`
|
||||
|
||||
**Step 2: Re-run both commands after the doc update**
|
||||
|
||||
Expected:
|
||||
- validator still exits `0`
|
||||
- unit tests still pass
|
||||
411
docs/plans/2026-03-27-skill-lib-zeroclaw-plan.md
Normal file
411
docs/plans/2026-03-27-skill-lib-zeroclaw-plan.md
Normal file
@@ -0,0 +1,411 @@
|
||||
# Skill Lib ZeroClaw Migration Implementation Plan
|
||||
|
||||
> **For Claude:** REQUIRED SUB-SKILL: Use superpowers:executing-plans to implement this plan task-by-task.
|
||||
|
||||
**Goal:** Create `/home/zyl/projects/sgClaw/skill_lib` as a dedicated skill library directory and restructure the current Zhihu browser capabilities into ZeroClaw-style skill packages.
|
||||
|
||||
**Architecture:** Treat `skill_lib` as a standalone skill repository, not as an embedded Rust module tree. Use the ZeroClaw/open-skills layout `skill_lib/skills/<skill-name>/SKILL.md`, keep each skill self-contained, and move long operational detail into `references/` plus any preserved source artifacts into `assets/`. Map the current four exposed Rust capabilities into three end-user skills: `zhihu-navigate`, `zhihu-write`, and `zhihu-hotlist`.
|
||||
|
||||
**Tech Stack:** Markdown `SKILL.md`, YAML frontmatter, directory-based ZeroClaw skill packaging, existing SGClaw Zhihu Rust/JSON source material, shell validation commands.
|
||||
|
||||
### Task 1: Freeze The Target Layout
|
||||
|
||||
**Files:**
|
||||
- Create: `/home/zyl/projects/sgClaw/skill_lib/`
|
||||
- Create: `/home/zyl/projects/sgClaw/skill_lib/README.md`
|
||||
- Create: `/home/zyl/projects/sgClaw/skill_lib/skills/`
|
||||
- Reference only: `/home/zyl/projects/sgClaw/claw/third_party/zeroclaw/src/skills/mod.rs`
|
||||
- Reference only: `/home/zyl/projects/sgClaw/claw/third_party/zeroclaw/skills/browser/SKILL.md`
|
||||
|
||||
**Step 1: Create the top-level repository skeleton**
|
||||
|
||||
Create:
|
||||
- `/home/zyl/projects/sgClaw/skill_lib/README.md`
|
||||
- `/home/zyl/projects/sgClaw/skill_lib/skills/`
|
||||
|
||||
The README should state:
|
||||
- this directory is a dedicated ZeroClaw-style skill library
|
||||
- runtime skill packages live under `skills/<name>/`
|
||||
- each skill package uses `SKILL.md` plus optional `references/`, `scripts/`, and `assets/`
|
||||
|
||||
**Step 2: Document the package contract in the README**
|
||||
|
||||
Include:
|
||||
- required file: `SKILL.md`
|
||||
- supported frontmatter for this repo: `name`, `description`, `version`, `author`, `tags`
|
||||
- design rule: `description` must be trigger-oriented and not a workflow dump
|
||||
- design rule: keep `SKILL.md` concise and push long detail into `references/`
|
||||
|
||||
**Step 3: Run structural sanity checks**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
test -d /home/zyl/projects/sgClaw/skill_lib
|
||||
test -d /home/zyl/projects/sgClaw/skill_lib/skills
|
||||
test -f /home/zyl/projects/sgClaw/skill_lib/README.md
|
||||
```
|
||||
|
||||
Expected: all commands exit `0`.
|
||||
|
||||
### Task 2: Define The Skill Inventory And Source Mapping
|
||||
|
||||
**Files:**
|
||||
- Create: `/home/zyl/projects/sgClaw/skill_lib/skill_inventory.md`
|
||||
- Reference only: `/home/zyl/projects/sgClaw/claw/src/skill/mod.rs`
|
||||
- Reference only: `/home/zyl/projects/sgClaw/claw/src/skill/router.rs`
|
||||
- Reference only: `/home/zyl/projects/sgClaw/claw/src/skill/zhihu.rs`
|
||||
- Reference only: `/home/zyl/projects/sgClaw/claw/src/skill/zhihu_hotlist.rs`
|
||||
- Reference only: `/home/zyl/projects/sgClaw/claw/src/skill/zhihu_hotlist_store.rs`
|
||||
- Reference only: `/home/zyl/projects/sgClaw/claw/src/skill/zhihu_navigation.rs`
|
||||
- Reference only: `/home/zyl/projects/sgClaw/claw/resources/skills/zhihu_write_flow.json`
|
||||
- Reference only: `/home/zyl/projects/sgClaw/claw/resources/skills/zhihu_hotlist_flow.json`
|
||||
- Reference only: `/home/zyl/projects/sgClaw/claw/resources/skills/zhihu_navigation_pages.json`
|
||||
|
||||
**Step 1: Write the migration inventory**
|
||||
|
||||
Create `/home/zyl/projects/sgClaw/skill_lib/skill_inventory.md` with a three-row mapping:
|
||||
- `zhihu-navigate` ← current `zhihu_navigate`
|
||||
- `zhihu-write` ← current `zhihu_write`
|
||||
- `zhihu-hotlist` ← current `zhihu_hotlist_collect` + `zhihu_hotlist_report`
|
||||
|
||||
**Step 2: Capture the non-migrated code responsibilities**
|
||||
|
||||
Document explicitly that this migration does **not** port:
|
||||
- Rust router dispatch
|
||||
- browser pipe transport code
|
||||
- snapshot persistence implementation detail
|
||||
|
||||
Document that the new repo is a skill library, not a Rust runtime.
|
||||
|
||||
**Step 3: Record source artifacts per target skill**
|
||||
|
||||
For each target skill, list:
|
||||
- source Rust module(s)
|
||||
- source JSON flow/catalog file(s)
|
||||
- important risk notes discovered during analysis
|
||||
|
||||
**Step 4: Validate the inventory**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
rg -n "zhihu-navigate|zhihu-write|zhihu-hotlist" /home/zyl/projects/sgClaw/skill_lib/skill_inventory.md
|
||||
```
|
||||
|
||||
Expected: all three skill names appear exactly once as top-level migration targets.
|
||||
|
||||
### Task 3: Author The `zhihu-navigate` Skill Package
|
||||
|
||||
**Files:**
|
||||
- Create: `/home/zyl/projects/sgClaw/skill_lib/skills/zhihu-navigate/SKILL.md`
|
||||
- Create: `/home/zyl/projects/sgClaw/skill_lib/skills/zhihu-navigate/references/routes-and-targets.md`
|
||||
- Create: `/home/zyl/projects/sgClaw/skill_lib/skills/zhihu-navigate/references/selector-strategy.md`
|
||||
- Create: `/home/zyl/projects/sgClaw/skill_lib/skills/zhihu-navigate/assets/zhihu_navigation_pages.source.json`
|
||||
- Reference only: `/home/zyl/projects/sgClaw/claw/src/skill/zhihu_navigation.rs`
|
||||
- Reference only: `/home/zyl/projects/sgClaw/claw/resources/skills/zhihu_navigation_pages.json`
|
||||
|
||||
**Step 1: Preserve the raw source artifact**
|
||||
|
||||
Copy the current navigation catalog into:
|
||||
- `/home/zyl/projects/sgClaw/skill_lib/skills/zhihu-navigate/assets/zhihu_navigation_pages.source.json`
|
||||
|
||||
This file is for traceability only, not for frontmatter or prompt injection.
|
||||
|
||||
**Step 2: Write the `SKILL.md`**
|
||||
|
||||
Use ZeroClaw-style frontmatter:
|
||||
```yaml
|
||||
---
|
||||
name: zhihu-navigate
|
||||
description: Use when the user wants to open, switch, or navigate to a Zhihu page, tab, menu, profile area, notifications area, message area, or creator area through browser actions.
|
||||
version: 0.1.0
|
||||
author: sgclaw
|
||||
tags:
|
||||
- zhihu
|
||||
- browser
|
||||
- navigation
|
||||
---
|
||||
```
|
||||
|
||||
The body should include:
|
||||
- overview
|
||||
- when to use
|
||||
- workflow for route vs component vs flow navigation
|
||||
- ambiguity handling rules
|
||||
- output contract
|
||||
- common mistakes
|
||||
|
||||
**Step 3: Write `routes-and-targets.md`**
|
||||
|
||||
Summarize:
|
||||
- route/component/flow/target model
|
||||
- representative target names
|
||||
- known alias conflicts
|
||||
- preferred disambiguation wording for future prompts
|
||||
|
||||
**Step 4: Write `selector-strategy.md`**
|
||||
|
||||
Document:
|
||||
- why selectors should prefer semantic hooks over CSS hash classes
|
||||
- fallback ordering
|
||||
- known brittle selectors from the current source
|
||||
|
||||
**Step 5: Validate the package**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
test -f /home/zyl/projects/sgClaw/skill_lib/skills/zhihu-navigate/SKILL.md
|
||||
test -f /home/zyl/projects/sgClaw/skill_lib/skills/zhihu-navigate/references/routes-and-targets.md
|
||||
test -f /home/zyl/projects/sgClaw/skill_lib/skills/zhihu-navigate/references/selector-strategy.md
|
||||
test -f /home/zyl/projects/sgClaw/skill_lib/skills/zhihu-navigate/assets/zhihu_navigation_pages.source.json
|
||||
```
|
||||
|
||||
Expected: all commands exit `0`.
|
||||
|
||||
### Task 4: Author The `zhihu-write` Skill Package
|
||||
|
||||
**Files:**
|
||||
- Create: `/home/zyl/projects/sgClaw/skill_lib/skills/zhihu-write/SKILL.md`
|
||||
- Create: `/home/zyl/projects/sgClaw/skill_lib/skills/zhihu-write/references/editor-flow.md`
|
||||
- Create: `/home/zyl/projects/sgClaw/skill_lib/skills/zhihu-write/references/publish-safety.md`
|
||||
- Create: `/home/zyl/projects/sgClaw/skill_lib/skills/zhihu-write/assets/zhihu_write_flow.source.json`
|
||||
- Reference only: `/home/zyl/projects/sgClaw/claw/src/skill/zhihu.rs`
|
||||
- Reference only: `/home/zyl/projects/sgClaw/claw/resources/skills/zhihu_write_flow.json`
|
||||
|
||||
**Step 1: Preserve the raw source artifact**
|
||||
|
||||
Copy:
|
||||
- `/home/zyl/projects/sgClaw/claw/resources/skills/zhihu_write_flow.json`
|
||||
|
||||
to:
|
||||
- `/home/zyl/projects/sgClaw/skill_lib/skills/zhihu-write/assets/zhihu_write_flow.source.json`
|
||||
|
||||
**Step 2: Write the `SKILL.md`**
|
||||
|
||||
The frontmatter should name a single skill:
|
||||
- `name: zhihu-write`
|
||||
- description focused on when article drafting or publishing is requested
|
||||
|
||||
The body should include:
|
||||
- prerequisites before touching the editor
|
||||
- workflow for draft-only vs publish
|
||||
- explicit confirmation gate before publish
|
||||
- required final report fields: title, mode, final URL if published, unresolved issues
|
||||
|
||||
**Step 3: Write `editor-flow.md`**
|
||||
|
||||
Document:
|
||||
- entry page
|
||||
- editor readiness checks
|
||||
- title/body fill rules
|
||||
- publish confirmation sequence
|
||||
- URL capture rules
|
||||
|
||||
**Step 4: Write `publish-safety.md`**
|
||||
|
||||
Document:
|
||||
- when to stop and ask for confirmation
|
||||
- what to do if title verification fails
|
||||
- what to do if the URL remains on edit mode
|
||||
- brittle selectors that must be revalidated first
|
||||
|
||||
**Step 5: Validate the package**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
test -f /home/zyl/projects/sgClaw/skill_lib/skills/zhihu-write/SKILL.md
|
||||
test -f /home/zyl/projects/sgClaw/skill_lib/skills/zhihu-write/references/editor-flow.md
|
||||
test -f /home/zyl/projects/sgClaw/skill_lib/skills/zhihu-write/references/publish-safety.md
|
||||
test -f /home/zyl/projects/sgClaw/skill_lib/skills/zhihu-write/assets/zhihu_write_flow.source.json
|
||||
```
|
||||
|
||||
Expected: all commands exit `0`.
|
||||
|
||||
### Task 5: Author The `zhihu-hotlist` Skill Package
|
||||
|
||||
**Files:**
|
||||
- Create: `/home/zyl/projects/sgClaw/skill_lib/skills/zhihu-hotlist/SKILL.md`
|
||||
- Create: `/home/zyl/projects/sgClaw/skill_lib/skills/zhihu-hotlist/references/collection-flow.md`
|
||||
- Create: `/home/zyl/projects/sgClaw/skill_lib/skills/zhihu-hotlist/references/report-format.md`
|
||||
- Create: `/home/zyl/projects/sgClaw/skill_lib/skills/zhihu-hotlist/references/data-quality.md`
|
||||
- Create: `/home/zyl/projects/sgClaw/skill_lib/skills/zhihu-hotlist/assets/zhihu_hotlist_flow.source.json`
|
||||
- Reference only: `/home/zyl/projects/sgClaw/claw/src/skill/zhihu_hotlist.rs`
|
||||
- Reference only: `/home/zyl/projects/sgClaw/claw/src/skill/zhihu_hotlist_store.rs`
|
||||
- Reference only: `/home/zyl/projects/sgClaw/claw/resources/skills/zhihu_hotlist_flow.json`
|
||||
|
||||
**Step 1: Preserve the raw source artifact**
|
||||
|
||||
Copy:
|
||||
- `/home/zyl/projects/sgClaw/claw/resources/skills/zhihu_hotlist_flow.json`
|
||||
|
||||
to:
|
||||
- `/home/zyl/projects/sgClaw/skill_lib/skills/zhihu-hotlist/assets/zhihu_hotlist_flow.source.json`
|
||||
|
||||
**Step 2: Write the `SKILL.md`**
|
||||
|
||||
Use one skill to cover:
|
||||
- hotlist collection
|
||||
- comment metric collection
|
||||
- snapshot-style reporting
|
||||
|
||||
The body should clearly separate:
|
||||
- collection workflow
|
||||
- report workflow
|
||||
- partial-failure handling
|
||||
- output contract
|
||||
|
||||
**Step 3: Write `collection-flow.md`**
|
||||
|
||||
Include:
|
||||
- hotlist page detection
|
||||
- hotlist HTML capture strategy
|
||||
- top N extraction
|
||||
- detail-page comment collection flow
|
||||
- metric parsing notes
|
||||
|
||||
**Step 4: Write `report-format.md`**
|
||||
|
||||
Define:
|
||||
- report header line
|
||||
- per-item summary line
|
||||
- field names and order
|
||||
- handling when comment metrics are missing
|
||||
|
||||
**Step 5: Write `data-quality.md`**
|
||||
|
||||
Document:
|
||||
- why partial success must be surfaced
|
||||
- what counts as incomplete data
|
||||
- known parser risks
|
||||
- recommended caution language in outputs
|
||||
|
||||
**Step 6: Validate the package**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
test -f /home/zyl/projects/sgClaw/skill_lib/skills/zhihu-hotlist/SKILL.md
|
||||
test -f /home/zyl/projects/sgClaw/skill_lib/skills/zhihu-hotlist/references/collection-flow.md
|
||||
test -f /home/zyl/projects/sgClaw/skill_lib/skills/zhihu-hotlist/references/report-format.md
|
||||
test -f /home/zyl/projects/sgClaw/skill_lib/skills/zhihu-hotlist/references/data-quality.md
|
||||
test -f /home/zyl/projects/sgClaw/skill_lib/skills/zhihu-hotlist/assets/zhihu_hotlist_flow.source.json
|
||||
```
|
||||
|
||||
Expected: all commands exit `0`.
|
||||
|
||||
### Task 6: Normalize Frontmatter And Trigger Quality
|
||||
|
||||
**Files:**
|
||||
- Modify: `/home/zyl/projects/sgClaw/skill_lib/skills/zhihu-navigate/SKILL.md`
|
||||
- Modify: `/home/zyl/projects/sgClaw/skill_lib/skills/zhihu-write/SKILL.md`
|
||||
- Modify: `/home/zyl/projects/sgClaw/skill_lib/skills/zhihu-hotlist/SKILL.md`
|
||||
|
||||
**Step 1: Normalize frontmatter keys**
|
||||
|
||||
Ensure each `SKILL.md` contains exactly these frontmatter keys in this order:
|
||||
- `name`
|
||||
- `description`
|
||||
- `version`
|
||||
- `author`
|
||||
- `tags`
|
||||
|
||||
Do not add Rust-only or unofficial parser fields as required metadata.
|
||||
|
||||
**Step 2: Check naming rules**
|
||||
|
||||
Ensure skill names are:
|
||||
- lowercase
|
||||
- hyphenated
|
||||
- stable
|
||||
|
||||
Names to keep:
|
||||
- `zhihu-navigate`
|
||||
- `zhihu-write`
|
||||
- `zhihu-hotlist`
|
||||
|
||||
**Step 3: Tighten descriptions**
|
||||
|
||||
Each description must:
|
||||
- begin with `Use when`
|
||||
- describe triggering conditions
|
||||
- mention Zhihu/browser context
|
||||
- avoid dumping full workflow detail
|
||||
|
||||
**Step 4: Validate frontmatter**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
rg -n "^name: |^description: |^version: |^author: |^tags:" /home/zyl/projects/sgClaw/skill_lib/skills/*/SKILL.md
|
||||
```
|
||||
|
||||
Expected: every skill emits the same five key families.
|
||||
|
||||
### Task 7: Add Repository-Level Verification Notes
|
||||
|
||||
**Files:**
|
||||
- Create: `/home/zyl/projects/sgClaw/skill_lib/VERIFY.md`
|
||||
- Modify: `/home/zyl/projects/sgClaw/skill_lib/README.md`
|
||||
|
||||
**Step 1: Create `VERIFY.md`**
|
||||
|
||||
Document the manual verification checklist:
|
||||
- all skill packages are under `skill_lib/skills/`
|
||||
- each package has `SKILL.md`
|
||||
- long details live in `references/`
|
||||
- preserved source JSON is in `assets/`
|
||||
- no Rust source is copied into the skill repo
|
||||
|
||||
**Step 2: Link verification from the README**
|
||||
|
||||
Add a short section in `README.md` pointing to `VERIFY.md`.
|
||||
|
||||
**Step 3: Run repository-level checks**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
find /home/zyl/projects/sgClaw/skill_lib/skills -mindepth 2 -maxdepth 2 -name SKILL.md | sort
|
||||
find /home/zyl/projects/sgClaw/skill_lib/skills -type d \( -name references -o -name assets \) | sort
|
||||
```
|
||||
|
||||
Expected:
|
||||
- exactly three `SKILL.md` files
|
||||
- each skill has `references/`
|
||||
- each skill has `assets/`
|
||||
|
||||
### Task 8: Final Review Before Claiming Completion
|
||||
|
||||
**Files:**
|
||||
- Review only: `/home/zyl/projects/sgClaw/skill_lib/`
|
||||
- Review only: `/home/zyl/projects/sgClaw/claw/docs/plans/2026-03-27-skill-lib-zeroclaw-plan.md`
|
||||
|
||||
**Step 1: Review against ZeroClaw runtime constraints**
|
||||
|
||||
Check that the final library respects the currently observed runtime facts:
|
||||
- directory-based skills
|
||||
- `SKILL.md` supported
|
||||
- simple frontmatter fields
|
||||
- optional `references/`, `scripts/`, `assets/`
|
||||
|
||||
**Step 2: Review against authoring quality**
|
||||
|
||||
Check that each skill:
|
||||
- is self-contained
|
||||
- has a narrow trigger boundary
|
||||
- avoids copying Rust internals into the prompt body
|
||||
- surfaces ambiguity and failure modes
|
||||
|
||||
**Step 3: Produce the implementation report**
|
||||
|
||||
The completion report must include:
|
||||
- created directories
|
||||
- created skill packages
|
||||
- any deliberate deviations from upstream ZeroClaw examples
|
||||
- verification commands actually run
|
||||
- unresolved risks
|
||||
|
||||
**Step 4: Stop before unrelated expansion**
|
||||
|
||||
Do not add:
|
||||
- extra skills beyond the three mapped ones
|
||||
- generic utility libraries
|
||||
- unrelated automation scripts
|
||||
- runtime code changes in `/home/zyl/projects/sgClaw/claw/src/skill/`
|
||||
|
||||
314
docs/sgClaw项目现有优势与下一步计划汇报稿.md
Normal file
314
docs/sgClaw项目现有优势与下一步计划汇报稿.md
Normal file
@@ -0,0 +1,314 @@
|
||||
# sgClaw 项目现有优势与下一步计划汇报稿
|
||||
|
||||
## 一、项目现有优势
|
||||
|
||||
和传统 openclaw 类自动化项目相比，本项目的优势不只是“能做页面操作”，而是已经具备了向企业级、长期可用方向演进的基础。简单说，传统方案更像“能跑起来的自动化脚本集合”，本项目更像“带安全边界、带统一控制、带长期演进能力的智能执行底座”。
|
||||
|
||||
而且根据后续已经落地的提交来看，本项目的优势已经不再只是架构上的“方向正确”，而是开始体现为一批已经交付的现实能力，包括：
|
||||
|
||||
- 运行时策略已经从写死逻辑转向配置驱动。
|
||||
- 已支持 planner-first 的先规划后执行模式。
|
||||
- 已支持技能包驱动的浏览器脚本执行。
|
||||
- 已支持面向具体任务的 Excel 导出和屏幕展示导出能力。
|
||||
- 已具备版本级日志、技能版本日志和真实验收记录。
|
||||
|
||||
这意味着本项目已经从“原型底座”进一步进入“可验证、可扩展、可交付”的阶段。
|
||||
|
||||
### 1. 从“脚本工具”升级为“统一执行底座”
|
||||
|
||||
传统项目通常是一个场景一套脚本，一个系统一套规则，能解决眼前问题，但难以复用、难以管理、难以持续演进。页面一改，脚本就要改；系统一多，维护成本就会快速上升。
|
||||
|
||||
本项目已经把任务接入、运行时控制、浏览器执行、日志回传、结果回传放进统一框架里。这样后续不管是新增能力、扩展场景，还是替换模型、替换策略，都不需要推倒重来，而是在同一个底座上持续增强。对业务侧来说，这意味着项目价值不再停留在“做通一个流程”，而是逐步沉淀为可以支撑更多业务的公共能力。
|
||||
|
||||
### 2. 安全设计更完整，更适合企业内网
|
||||
|
||||
这是本项目最突出的优势。传统自动化方案最大的问题，是一旦拿到页面操作能力，就容易变成“脚本想点什么就点什么”，安全边界不清楚，风险很难控制。本项目当前已经不是这种模式，而是把浏览器能力放进了严格受控的执行边界里。
|
||||
|
||||
从汇报角度，可以把当前安全设计概括为以下几组能力：
|
||||
|
||||
#### 3 层安全机制
|
||||
|
||||
第一层是启动门禁。浏览器宿主和运行时必须先完成握手，版本不一致、超时、顺序错误，系统都不会进入正式运行状态。
|
||||
|
||||
第二层是运行时策略校验。每次真正要执行页面动作前，都会先检查动作是否合法、目标页面是否在允许范围内。
|
||||
|
||||
第三层是宿主二次校验。就算运行时已经发出了命令，浏览器宿主仍然会再做一次本地校验，防止异常命令真正落地。
|
||||
|
||||
这 3 层叠加起来，形成了“不是模型想做什么就做什么，而是每一步都要过关”的安全控制方式。
|
||||
|
||||
#### 6 项协议硬约束
|
||||
|
||||
当前协议层已经明确了 6 项刚性要求：
|
||||
|
||||
1. 传输格式固定，不能随意乱发消息。
|
||||
2. 编码方式固定，避免解析异常。
|
||||
3. 单条消息大小有限制，防止异常数据冲击系统。
|
||||
4. 序列号必须严格递增，不能重复、不能乱序。
|
||||
5. 每条关键命令都必须带安全字段。
|
||||
6. 一次请求只能对应一次响应，不能混乱回包。
|
||||
|
||||
这说明系统不是“发个命令过去试试看”，而是每条消息都有严格规则，更适合企业环境中的稳定运行。
|
||||
|
||||
#### 2 类白名单
|
||||
|
||||
本项目当前至少有两类核心白名单同时生效。
|
||||
|
||||
第一类是域名白名单。只有允许的业务域名才可以被操作，不是浏览器里所有页面都能碰。
|
||||
|
||||
第二类是动作白名单。只有允许的动作类型才能执行，不是脚本写得出来就一定能跑。
|
||||
|
||||
白名单机制的意义在于，系统把“哪些页面能动、哪些动作能做”提前规定清楚，而不是把决定权完全交给模型或脚本。
|
||||
|
||||
#### 1 类显式黑名单
|
||||
|
||||
除了白名单，本项目还明确保留了显式阻断项。也就是说，不只是“没允许的不行”，而是“高风险动作被直接明确禁止”。
|
||||
|
||||
这在企业场景下非常重要，因为有些能力不是“暂时不用”，而是“原则上就不能开放”。有了黑名单，系统在设计上就能提前规避高风险能力外溢。
|
||||
|
||||
#### 5 个默认允许动作
|
||||
|
||||
当前默认真正开放给运行时执行的动作共有 5 个：
|
||||
|
||||
1. 点击
|
||||
2. 输入
|
||||
3. 页面跳转
|
||||
4. 文本读取
|
||||
5. 受控脚本执行
|
||||
|
||||
这里最重要的一点不是“多了一个动作”，而是这个新增能力并没有破坏安全边界。它不是把任意页面脚本能力全部放开，而是在现有受控协议和校验链路内，给技能包提供了一种更强但仍然可控的执行方式。
|
||||
|
||||
这看起来不如一些传统方案“动作数量多”，但它的价值恰恰在于边界非常清楚。先把最稳定、最可控、最容易审计的核心动作做好，再逐步扩展，比一开始把大量高风险动作全部开放更稳。
|
||||
|
||||
#### 7 个默认允许域名
|
||||
|
||||
当前规则里默认允许的域名是有限集合，而不是浏览器里的所有网页都能碰。这样做非常符合企业内网环境的实际需求。对于办公系统、ERP、OA 等场景，大家真正需要的不是“全网自动化”，而是“在明确范围内可控地自动化”。
|
||||
|
||||
#### 1 套 HMAC 签名机制
|
||||
|
||||
所有关键命令不是明文裸发，而是带签名校验。可以简单理解成，每条关键操作都会带“防伪标记”。
|
||||
|
||||
这样做的价值是，命令在链路中不容易被伪造、篡改或错误复用，整体安全性远高于普通脚本直接调用页面接口的模式。
|
||||
|
||||
#### 1 套序列号机制
|
||||
|
||||
每条命令都有严格递增的序列号，而且一个序列号只能对应一个结果。
|
||||
|
||||
这让系统能够清楚知道“这条结果到底对应哪一次操作”，避免串包、乱序、错配等问题，提升稳定性和可追溯性。
|
||||
|
||||
#### 3 重脚本执行约束
|
||||
|
||||
后续提交里新增了技能包驱动的浏览器脚本能力，但这部分并不是“把页面执行彻底放开”，而是在现有安全边界内增加了一层受控能力。
|
||||
|
||||
可以把它理解为 3 重约束：
|
||||
|
||||
1. 脚本必须来自技能包内的受管路径，不能越界读取技能目录之外的文件。
|
||||
2. 执行时必须声明目标域名，不能脱离页面上下文随意运行。
|
||||
3. 脚本仍然通过现有浏览器 pipe 和动作白名单执行，而不是绕过宿主直接落地。
|
||||
|
||||
这类设计很关键，因为它说明项目在增强能力的同时，仍然坚持“新增能力必须留在安全边界里”，而不是为了方便把安全口子越开越大。
|
||||
|
||||
#### 5 类错误处理策略
|
||||
|
||||
系统不是失败了就“直接崩”，而是把错误分成不同类型处理。
|
||||
|
||||
- 有的错误不允许重试，直接失败。
|
||||
- 有的错误可以限次重试。
|
||||
- 有的错误需要等待配置或人工确认。
|
||||
- 有的错误会触发熔断。
|
||||
- 所有失败都要求结构化返回，便于定位问题。
|
||||
|
||||
这比传统脚本“报错了就人工重跑”的方式要成熟得多。
|
||||
|
||||
#### 1 个熔断阈值
|
||||
|
||||
同一动作如果连续失败超过阈值，系统会主动停止继续尝试并通知界面，而不是无限重复。
|
||||
|
||||
这能有效避免错误状态下反复点击、反复提交、反复操作，减少业务风险和误操作成本。
|
||||
|
||||
#### 7 项联调验收标准
|
||||
|
||||
当前项目已经把联调成功的标准写清楚了，包括：
|
||||
|
||||
1. 握手成功率要求
|
||||
2. 版本不匹配的失败处理
|
||||
3. 序列号异常场景处理
|
||||
4. 超大消息拦截
|
||||
5. 核心动作成功率要求
|
||||
6. 结构化错误返回要求
|
||||
7. 日志全链路贯通能力
|
||||
|
||||
这说明项目不是“靠经验凑合能跑”，而是已经开始形成可以复制、可以验收、可以交付的工程标准。
|
||||
|
||||
### 3. 浏览器只是执行面，不再定义整个系统
|
||||
|
||||
传统 openclaw 类项目常见问题是浏览器能力太强，最后整个系统都围着页面脚本转，浏览器脚本几乎变成了系统本体。
|
||||
|
||||
本项目已经明确把浏览器定义为“受保护的特权执行面”，而不是整个 runtime 本体。这意味着以后就算扩展到别的工具面、别的执行面，也不需要推翻现有架构，系统的演进空间更大，整体结构也更清楚。
|
||||
|
||||
### 4. 运行时能力已经从“写死逻辑”升级为“配置驱动”
|
||||
|
||||
这一点是后续提交中非常重要的进展。传统项目经常把模型、策略、模式、环境差异写死在代码里，导致后续一改就牵动整体。
|
||||
|
||||
本项目现在已经把一批关键决策收进运行时配置，包括：
|
||||
|
||||
- 使用哪个模型提供方
|
||||
- 当前激活哪个 provider
|
||||
- 使用什么 planner 模式
|
||||
- 采用哪种 runtime profile
|
||||
- 浏览器能力走哪种 backend
|
||||
- Office 导出走哪种 backend
|
||||
- skills 从哪个目录加载
|
||||
|
||||
从汇报口径上，可以把它概括为：
|
||||
|
||||
1 套统一 runtime config
|
||||
3 种 runtime profile
|
||||
多项可切换运行策略
|
||||
|
||||
这意味着系统不再只是“代码怎么写就怎么跑”，而是开始进入“按环境、按任务、按场景灵活切换”的阶段，更适合企业实际落地。
|
||||
|
||||
### 5. 已形成“先规划、再执行、再产出结果”的闭环能力
|
||||
|
||||
传统自动化项目往往是一上来就直接操作页面，缺少中间过程的可解释性，也不利于后续审计和治理。
|
||||
|
||||
本项目后续提交已经进一步加强了 planner-first 模式，也就是在真正执行之前，先给出计划，再按计划执行，再输出结果。对业务和管理层来说，这样的价值非常直接：
|
||||
|
||||
- 更容易理解系统准备做什么
|
||||
- 更容易检查执行过程是否偏离目标
|
||||
- 更容易把计划、执行、结果串成闭环
|
||||
|
||||
同时，本项目已经不是只有一个简单浏览器工具，而是开始形成更清晰的能力分工，例如：
|
||||
|
||||
- `superrpa_browser` 负责受控浏览器操作
|
||||
- `openxml_office` 负责结果导出
|
||||
- `screen_html_export` 负责展示类产物导出
|
||||
|
||||
这说明项目正在从“一个浏览器操作入口”走向“围绕业务结果组织工具链”的阶段。
|
||||
|
||||
### 6. 技能体系已经开始从“提示词描述”走向“可执行能力包”
|
||||
|
||||
这是本项目相对传统 openclaw 类项目非常重要的一个现实优势。很多传统项目里的“技能”更多只是提示词模板，真正落地时还是回到页面脚本堆叠。
|
||||
|
||||
本项目后续提交已经支持技能包驱动的浏览器脚本执行。简单理解，就是一个技能不再只是“告诉模型怎么做”，而是可以带着确定的脚本能力一起交付。这样做有几个明显好处：
|
||||
|
||||
1. 能力更稳定
|
||||
关键步骤不必完全依赖模型自由发挥，而是可以由打包好的脚本完成。
|
||||
|
||||
2. 可复用性更强
|
||||
同一个技能包可以在相似场景中重复使用，不必每次都重新组织页面操作。
|
||||
|
||||
3. 更适合沉淀企业资产
|
||||
后续很多高价值流程，都可以逐步从“提示词经验”沉淀成“可复用技能包”。
|
||||
|
||||
这意味着项目已经开始从“智能执行框架”走向“智能执行框架 + 可复用技能资产”的模式。
|
||||
|
||||
### 7. 前端只负责展示，不掌握执行权
|
||||
|
||||
传统项目里，前端、脚本、执行逻辑经常混在一起，最后变成“界面里藏了很多业务决策”。这种方式短期看开发快，长期看风险大、维护成本高。
|
||||
|
||||
本项目已经把前端限制为展示层，只负责展示状态、日志、计划和结果，不负责决定是否执行、如何切换模型、如何绕过安全边界。这样一来，系统结构更清楚，后续维护和升级时也更不容易失控。
|
||||
|
||||
此外，后续提交已经支持外部 frontend bundle 优先、内置资源兜底的装载方式。这意味着后续改界面、改展示逻辑，不必每次都重编浏览器宿主，研发效率和交付效率都会更高。
|
||||
|
||||
### 8. 配置能力更强，更适合业务落地
|
||||
|
||||
传统项目往往把很多关键逻辑写死在脚本里，修改一次就要重新改代码。这样不仅效率低，而且很容易因为局部修改牵动整体。
|
||||
|
||||
本项目已经开始把运行时配置、模型配置、策略配置从代码里抽出来，让宿主、运行时、前端之间的责任更清楚。这意味着未来业务调整、模型切换、策略升级都可以更平滑，而不是每次都进行大规模改造。
|
||||
|
||||
同时，后续提交还进一步加强了 source checkout 启动包装和 rules 同步能力，这对开发团队来说很重要。它意味着项目不仅适合做成二进制交付，也更适合在源码态持续联调和快速迭代。
|
||||
|
||||
### 9. 更适合做长期资产沉淀
|
||||
|
||||
传统自动化方案常见的问题，是做完一个流程后，价值基本也就结束了，经验很难积累成资产。
|
||||
|
||||
本项目不一样，它的方向是把执行能力、规则、安全边界、日志能力以及后续的元素识别能力，逐步沉淀成可复用资产。对企业来说，这种价值远高于“今天跑通一个流程”，因为它决定了未来是不是能够越做越快、越做越稳、越做越便宜。
|
||||
|
||||
现在这件事已经开始有现实支撑了。因为项目不只是在“能操作页面”，还已经能把技能、脚本、导出流程、运行时策略和日志标准逐步固化下来。后续再推进“混合自愈选择器”和元素指纹库时，这些都会自然成为资产沉淀的基础层。
|
||||
|
||||
### 10. 可观测性更强，已经开始具备运行级审计基础
|
||||
|
||||
传统项目常常只在失败时打印一段日志，出了问题很难知道系统到底做了什么。
|
||||
|
||||
本项目后续提交已经补上了一批很关键的运行级日志信息，包括：
|
||||
|
||||
- runtime 版本
|
||||
- 协议版本
|
||||
- 配置来源
|
||||
- skills 目录解析结果
|
||||
- runtime profile
|
||||
- skills prompt mode
|
||||
- 已加载技能及版本号
|
||||
- 当前执行模式
|
||||
|
||||
这类能力的价值非常直接：它让系统开始具备“说清楚自己是怎么运行的”的能力。对研发、测试、验收和后续审计来说，这都是非常重要的基础。
|
||||
|
||||
### 11. 已经形成“真实验收”而不是“概念演示”
|
||||
|
||||
后续提交里，项目已经留下了更完整的验收记录，而不是停留在文档层面的能力描述。以知乎热榜 Excel 导出为例，当前已经形成真实验收结果，包括：
|
||||
|
||||
- 真实 provider 模式运行
|
||||
- 实时热榜数据采集
|
||||
- 结构化结果导出
|
||||
- Excel 文件生成
|
||||
- 验收打分
|
||||
|
||||
这说明项目已经不是“理论上可以做到”，而是已经在真实任务链路中证明“能够跑通、能够输出结果、能够形成验收记录”。
|
||||
|
||||
对外汇报时，这一点很重要，因为它代表项目已经从“能力设想”走向“能力验证”。
|
||||
|
||||
### 12. 工程化基础更好
|
||||
|
||||
本项目已经不是单纯的验证页面或原型，而是以运行时内核、协议、规则和测试为主的工程结构。这说明项目更接近“可持续建设的产品内核”，而不只是“一个能演示的自动化效果”。
|
||||
|
||||
从目前仓库状态看，已经有 20 多个顶层测试文件，覆盖协议、握手、runtime、配置、兼容层、导出工具、技能执行和验收评分等多个方面。这说明项目已经在往“可持续交付、可持续验证”的方向走，而不是停留在临时性脚本工程。
|
||||
|
||||
从长期看，这种工程化能力决定了项目能不能真正进入生产环境，能不能被更多团队协同使用，能不能在后续持续扩展能力。
|
||||
|
||||
### 13. 一句话总结现有优势
|
||||
|
||||
如果用非技术语言概括，本项目当前最大的优势可以总结为：
|
||||
|
||||
不是“更会点网页”，而是“已经具备了企业级智能执行系统该有的安全边界、控制能力、真实交付能力、稳定基础和长期演进空间”。
|
||||
|
||||
## 二、下一步计划
|
||||
|
||||
下一阶段的重点，不是继续堆脚本，而是进一步解决“页面一变就失效”的老问题，同时把项目能力从“能执行任务”继续提升为“能持续积累企业级自动化资产”。
|
||||
|
||||
### 1. 研发“混合自愈选择器”（Hybrid Self-Healing Selector）
|
||||
|
||||
在内网环境下，逐步摆脱对单一 XPath 的依赖，建立企业级元素指纹库，让系统在页面变化后依然能更稳地找到目标元素。
|
||||
|
||||
### 2. 定义元素指纹数据结构（JSON）
|
||||
|
||||
给每个可操作元素建立一份“数字档案”，核心字段包括：
|
||||
|
||||
- 语义文本
|
||||
- A11y Role
|
||||
- 相对空间位置
|
||||
- 属性哈希
|
||||
- 兜底 XPath
|
||||
- 视觉切图（Base64 小图）
|
||||
|
||||
这样系统找元素时，不再只靠一条路径，而是像“多特征识别”。
|
||||
|
||||
### 3. 推进“影子录制”（Shadow Recording）机制
|
||||
|
||||
在现有传统 RPA 正常运行时，于底层开启影子模式。当旧脚本通过 XPath 成功命中元素并完成操作时，后台静默抓取该元素的完整指纹并写入本地数据库。
|
||||
|
||||
通过这种方式，在不额外增加大量人工录制成本的前提下，持续沉淀高价值元素资产库。
|
||||
|
||||
### 4. 开发穿透层能力
|
||||
|
||||
利用定制 Chromium 的底层权限，解决 `iframe` 和闭合 `Shadow DOM` 这类复杂页面结构下的定位难题，为后续自愈选择器提供更强支撑。
|
||||
|
||||
## 三、预期结果
|
||||
|
||||
通过下一阶段建设，本项目将从“能执行任务”进一步升级为：
|
||||
|
||||
- 在复杂企业页面中更稳
|
||||
- 对页面变化更不敏感
|
||||
- 更容易持续积累高价值资产
|
||||
- 更适合在企业环境中长期推广使用
|
||||
|
||||
从业务视角看，项目价值也会从“完成单个流程自动化”进一步升级为“建设企业级智能执行底座”。
|
||||
BIN
docs/sgClaw项目现有优势与下一步计划汇报稿.pdf
Normal file
BIN
docs/sgClaw项目现有优势与下一步计划汇报稿.pdf
Normal file
Binary file not shown.
@@ -0,0 +1,281 @@
|
||||
# Config-Owned Direct Skill Contract Implementation Plan
|
||||
|
||||
> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.
|
||||
|
||||
**Goal:** Validate the `directSubmitSkill` control surface early and prevent malformed direct-skill configs from entering the submit routing path, without changing the current happy-path direct execution behavior.
|
||||
|
||||
**Architecture:** Keep the existing direct-submit runtime and submit-task seam intact for valid configs. Move `directSubmitSkill` format validation into the normal `SgClawSettings` load path so malformed config fails before routing begins, while leaving valid-but-unresolvable `skill.tool` targets as direct runtime errors in the current direct path.
|
||||
|
||||
**Tech Stack:** Rust 2021, `serde` config parsing, current `BrowserMessage::SubmitTask` path, current direct skill runtime, Rust integration tests.
|
||||
|
||||
---
|
||||
|
||||
## Execution Context
|
||||
|
||||
- Follow @superpowers:test-driven-development for the Rust code changes in this plan.
|
||||
- Follow @superpowers:verification-before-completion before claiming any task is done.
|
||||
- Do **not** create a git worktree unless the user explicitly asks. This project prefers staying in the current checkout.
|
||||
- Keep scope tight: this plan does **not** add per-skill dispatch metadata, docs changes, intent classification, or LLM routing changes.
|
||||
|
||||
## File Map
|
||||
|
||||
### Existing files to modify
|
||||
|
||||
- Modify: `src/config/settings.rs`
|
||||
- validate `directSubmitSkill` during config normalization
|
||||
- keep the stored field as `Option<String>` so the current direct runtime API stays stable
|
||||
- Modify: `tests/compat_config_test.rs`
|
||||
- add a failing config-load regression for malformed `directSubmitSkill`
|
||||
- Modify: `tests/agent_runtime_test.rs`
|
||||
- add a failing submit-path regression proving malformed config is rejected before direct routing begins
|
||||
|
||||
### Existing files to read but not broaden
|
||||
|
||||
- Reuse without redesign: `src/agent/mod.rs`
|
||||
- Reuse without redesign: `src/compat/direct_skill_runtime.rs`
|
||||
- Reuse without redesign: `docs/superpowers/specs/2026-04-09-config-owned-direct-skill-dispatch-design.md`
|
||||
|
||||
### No new files expected
|
||||
|
||||
This slice should fit in the existing config and tests surfaces only.
|
||||
|
||||
---
|
||||
|
||||
### Task 1: Validate `directSubmitSkill` Before Submit Routing
|
||||
|
||||
**Files:**
|
||||
- Modify: `tests/compat_config_test.rs`
|
||||
- Modify: `tests/agent_runtime_test.rs`
|
||||
- Modify: `src/config/settings.rs`
|
||||
- Read only: `src/agent/mod.rs`
|
||||
- Read only: `src/compat/direct_skill_runtime.rs`
|
||||
|
||||
- [ ] **Step 1: Write the failing config test for malformed `directSubmitSkill`**
|
||||
|
||||
Add this focused test to `tests/compat_config_test.rs`:
|
||||
|
||||
```rust
|
||||
#[test]
|
||||
fn sgclaw_settings_reject_invalid_direct_submit_skill_format() {
|
||||
let root = std::env::temp_dir().join(format!(
|
||||
"sgclaw-invalid-direct-submit-skill-{}",
|
||||
Uuid::new_v4()
|
||||
));
|
||||
fs::create_dir_all(&root).unwrap();
|
||||
let config_path = root.join("sgclaw_config.json");
|
||||
|
||||
fs::write(
|
||||
&config_path,
|
||||
r#"{
|
||||
"providers": [],
|
||||
"skillsDir": "skill_lib",
|
||||
"directSubmitSkill": "fault-details-report"
|
||||
}"#,
|
||||
)
|
||||
.unwrap();
|
||||
|
||||
let err = SgClawSettings::load(Some(config_path.as_path()))
|
||||
.expect_err("expected invalid directSubmitSkill format");
|
||||
let message = err.to_string();
|
||||
|
||||
assert!(message.contains("directSubmitSkill"));
|
||||
assert!(message.contains("skill.tool"));
|
||||
}
|
||||
```
|
||||
|
||||
- [ ] **Step 2: Run the focused config test and verify it fails**
|
||||
|
||||
Run:
|
||||
|
||||
```bash
|
||||
cargo test --test compat_config_test sgclaw_settings_reject_invalid_direct_submit_skill_format -- --nocapture
|
||||
```
|
||||
|
||||
Expected: FAIL because the current config loader accepts the malformed string instead of rejecting it early.
|
||||
|
||||
- [ ] **Step 3: Write the failing agent regression for malformed config**
|
||||
|
||||
Add this focused test to `tests/agent_runtime_test.rs`:
|
||||
|
||||
```rust
|
||||
#[test]
|
||||
fn submit_task_rejects_invalid_direct_submit_skill_config_before_routing() {
|
||||
std::env::remove_var("DEEPSEEK_API_KEY");
|
||||
std::env::remove_var("DEEPSEEK_BASE_URL");
|
||||
std::env::remove_var("DEEPSEEK_MODEL");
|
||||
|
||||
let skill_root = build_direct_runtime_skill_root();
|
||||
let workspace_root = std::env::temp_dir().join(format!(
|
||||
"sgclaw-invalid-direct-submit-workspace-{}",
|
||||
Uuid::new_v4()
|
||||
));
|
||||
fs::create_dir_all(&workspace_root).unwrap();
|
||||
let config_path = workspace_root.join("sgclaw_config.json");
|
||||
fs::write(
|
||||
&config_path,
|
||||
serde_json::json!({
|
||||
"providers": [],
|
||||
"skillsDir": skill_root,
|
||||
"directSubmitSkill": "fault-details-report"
|
||||
})
|
||||
.to_string(),
|
||||
)
|
||||
.unwrap();
|
||||
|
||||
let runtime_context = AgentRuntimeContext::new(Some(config_path), workspace_root);
|
||||
let transport = Arc::new(MockTransport::new(vec![]));
|
||||
let browser_tool = BrowserPipeTool::new(
|
||||
transport.clone(),
|
||||
direct_runtime_test_policy(),
|
||||
vec![1, 2, 3, 4, 5, 6, 7, 8],
|
||||
)
|
||||
.with_response_timeout(Duration::from_secs(1));
|
||||
|
||||
handle_browser_message_with_context(
|
||||
transport.as_ref(),
|
||||
&browser_tool,
|
||||
&runtime_context,
|
||||
submit_fault_details_message(),
|
||||
)
|
||||
.unwrap();
|
||||
|
||||
let sent = transport.sent_messages();
|
||||
assert!(matches!(
|
||||
sent.last(),
|
||||
Some(AgentMessage::TaskComplete { success, summary })
|
||||
if !success && summary.contains("skill.tool")
|
||||
));
|
||||
assert!(direct_submit_mode_logs(&sent).is_empty());
|
||||
assert!(!sent.iter().any(|message| matches!(message, AgentMessage::Command { .. })));
|
||||
}
|
||||
```
|
||||
|
||||
- [ ] **Step 4: Run the focused agent test and verify it fails**
|
||||
|
||||
Run:
|
||||
|
||||
```bash
|
||||
cargo test --test agent_runtime_test submit_task_rejects_invalid_direct_submit_skill_config_before_routing -- --nocapture
|
||||
```
|
||||
|
||||
Expected: FAIL because the malformed config currently loads, enters the direct-submit branch, and emits `direct_skill_primary` before failing later.
|
||||
|
||||
- [ ] **Step 5: Implement the minimal config validation**
|
||||
|
||||
In `src/config/settings.rs`, add a small helper that validates the normalized `directSubmitSkill` string during `SgClawSettings::new(...)`.
|
||||
|
||||
Recommended implementation shape:
|
||||
|
||||
```rust
|
||||
fn normalize_direct_submit_skill(raw: Option<String>) -> Result<Option<String>, ConfigError> {
|
||||
let value = normalize_optional_value(raw);
|
||||
let Some(value) = value.as_deref() else {
|
||||
return Ok(None);
|
||||
};
|
||||
|
||||
let Some((skill_name, tool_name)) = value.split_once('.') else {
|
||||
return Err(ConfigError::InvalidValue(
|
||||
"directSubmitSkill",
|
||||
format!("must use skill.tool format, got {value}"),
|
||||
));
|
||||
};
|
||||
|
||||
if skill_name.trim().is_empty() || tool_name.trim().is_empty() {
|
||||
return Err(ConfigError::InvalidValue(
|
||||
"directSubmitSkill",
|
||||
format!("must use skill.tool format, got {value}"),
|
||||
));
|
||||
}
|
||||
|
||||
Ok(Some(value.to_string()))
|
||||
}
|
||||
```
|
||||
|
||||
Then use it here:
|
||||
|
||||
```rust
|
||||
let direct_submit_skill = normalize_direct_submit_skill(direct_submit_skill)?;
|
||||
```
|
||||
|
||||
Rules:
|
||||
- do not change the public field type from `Option<String>`
|
||||
- do not move parsing responsibility into `src/agent/mod.rs`
|
||||
- do not redesign `src/compat/direct_skill_runtime.rs`
|
||||
- keep valid-but-unresolvable `skill.tool` targets as runtime errors in the direct path
|
||||
|
||||
- [ ] **Step 6: Re-run the two focused tests and verify they pass**
|
||||
|
||||
Run:
|
||||
|
||||
```bash
|
||||
cargo test --test compat_config_test sgclaw_settings_reject_invalid_direct_submit_skill_format -- --nocapture
|
||||
cargo test --test agent_runtime_test submit_task_rejects_invalid_direct_submit_skill_config_before_routing -- --nocapture
|
||||
```
|
||||
|
||||
Expected: PASS.
|
||||
|
||||
- [ ] **Step 7: Re-run the broader regression suites**
|
||||
|
||||
Run:
|
||||
|
||||
```bash
|
||||
cargo test --test compat_config_test -- --nocapture
|
||||
cargo test --test agent_runtime_test -- --nocapture
|
||||
cargo test --test browser_script_skill_tool_test -- --nocapture
|
||||
cargo build --bin sgclaw
|
||||
```
|
||||
|
||||
Expected: PASS, including:
|
||||
- the direct-submit happy path
|
||||
- the existing no-LLM fallback behavior when `directSubmitSkill` is absent
|
||||
- unchanged browser-script helper semantics
|
||||
- clean binary build
|
||||
|
||||
---
|
||||
|
||||
## Verification Checklist
|
||||
|
||||
### Config validation
|
||||
|
||||
```bash
|
||||
cargo test --test compat_config_test -- --nocapture
|
||||
```
|
||||
|
||||
Expected: malformed `directSubmitSkill` is rejected early, while the existing direct-only config shape still loads.
|
||||
|
||||
### Submit-path behavior
|
||||
|
||||
```bash
|
||||
cargo test --test agent_runtime_test -- --nocapture
|
||||
```
|
||||
|
||||
Expected:
|
||||
- malformed `directSubmitSkill` never reaches direct routing
|
||||
- valid configured direct skill still succeeds without LLM config
|
||||
- no direct skill configured still returns the existing no-LLM message
|
||||
|
||||
### Browser-script helper safety
|
||||
|
||||
```bash
|
||||
cargo test --test browser_script_skill_tool_test -- --nocapture
|
||||
```
|
||||
|
||||
Expected: current browser-script execution semantics remain unchanged.
|
||||
|
||||
### Build
|
||||
|
||||
```bash
|
||||
cargo build --bin sgclaw
|
||||
```
|
||||
|
||||
Expected: the main binary compiles cleanly.
|
||||
|
||||
---
|
||||
|
||||
## Notes For The Engineer
|
||||
|
||||
- The paired spec is `docs/superpowers/specs/2026-04-09-config-owned-direct-skill-dispatch-design.md`.
|
||||
- Do **not** add sgClaw-specific dispatch metadata under `D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging` in this slice.
|
||||
- Do **not** turn this into a per-skill registry task yet. This plan only hardens the current config-owned bootstrap contract.
|
||||
- Keep the current direct target example as `fault-details-report.collect_fault_details`; avoid hard-coding that name into new generic APIs.
|
||||
- If you discover a need for broader policy routing (`direct_browser` / `llm_agent` by skill), stop and write a new spec/plan instead of expanding this one.
|
||||
@@ -0,0 +1,520 @@
|
||||
# Direct Skill Invocation Without LLM Implementation Plan
|
||||
|
||||
> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.
|
||||
|
||||
**Goal:** Let the current pipe submit-task flow accept natural-language input but directly invoke one fixed staged browser skill without calling any model, while reserving a clean switch back to LLM-based routing later.
|
||||
|
||||
**Architecture:** Keep the existing `BrowserMessage::SubmitTask` entrypoint and add one narrow pre-routing seam before the current compat/LLM chain. When a new config field points to a fixed direct-submit skill, sgClaw loads that skill package from the configured external skills root, finds the target `browser_script` tool, executes it through the existing browser-script wrapper, and returns the result directly. When the field is absent, the current behavior stays unchanged. This preserves a future path where each skill can later declare `direct_browser` or `llm_agent` dispatch without rewriting the submit pipeline again.
|
||||
|
||||
**Tech Stack:** Rust 2021, existing `BrowserPipeTool`, current submit-task agent entrypoint, current browser-script skill executor, current sgClaw JSON config loader, `zeroclaw` skill manifest loader.
|
||||
|
||||
---
|
||||
|
||||
## Recommended First Skill
|
||||
|
||||
Use `fault-details-report.collect_fault_details` from:
|
||||
- `D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/scenes/fault-details-report/scene.json`
|
||||
- `D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/skills/fault-details-report/SKILL.toml`
|
||||
- `D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/skills/fault-details-report/scripts/collect_fault_details.js`
|
||||
|
||||
Why this one first:
|
||||
- it is clearly a report/export skill
|
||||
- it exposes exactly one browser-script tool: `collect_fault_details`
|
||||
- it has the smallest contract surface (`period` only)
|
||||
- its current JS is deterministic and simple, so the first slice can focus on plumbing instead of browser scraping complexity
|
||||
|
||||
## Scope Guardrails
|
||||
|
||||
- Do **not** redesign the existing submit-task protocol.
|
||||
- Do **not** remove or rewrite the current LLM/compat path; leave it as the fallback/default path.
|
||||
- Do **not** introduce generic NL intent routing in this slice; this is one fixed direct skill only.
|
||||
- Do **not** modify `third_party/zeroclaw` skill manifest schema in phase 1.
|
||||
- Do **not** add Excel export wiring in the first slice unless a test explicitly requires it.
|
||||
- Do **not** invent a new browser-script execution model; reuse the existing wrapper semantics.
|
||||
|
||||
---
|
||||
|
||||
## File Map
|
||||
|
||||
### Existing files to modify
|
||||
|
||||
- Modify: `src/config/settings.rs`
|
||||
- add a minimal config field for one direct-submit skill name
|
||||
- Modify: `src/agent/mod.rs`
|
||||
- add a narrow pre-routing branch before the current compat/LLM path
|
||||
- Modify: `src/compat/browser_script_skill_tool.rs`
|
||||
- expose the smallest reusable helper for direct browser-script execution
|
||||
- Modify: `src/compat/mod.rs` or the nearest module export surface
|
||||
- export the new narrow direct-skill runtime module if needed
|
||||
- Modify: `tests/compat_config_test.rs`
|
||||
- add config coverage for the new direct-submit field
|
||||
- Modify: `tests/browser_script_skill_tool_test.rs`
|
||||
- add coverage for the reusable direct-execution helper
|
||||
- Modify: `tests/agent_runtime_test.rs`
|
||||
- prove submit-task can bypass the model and directly invoke the fixed skill
|
||||
|
||||
### New files to create
|
||||
|
||||
- Create: `src/compat/direct_skill_runtime.rs`
|
||||
- small runtime for loading one configured skill, resolving one configured tool, deriving minimal args, and executing it directly
|
||||
|
||||
### Files to reuse without changing behavior
|
||||
|
||||
- Reuse: `src/compat/runtime.rs`
|
||||
- Reuse: `src/compat/orchestration.rs`
|
||||
- Reuse: `src/compat/config_adapter.rs`
|
||||
- Reuse: `third_party/zeroclaw/src/skills/mod.rs`
|
||||
|
||||
---
|
||||
|
||||
### Task 1: Add A Minimal Direct-Submit Skill Config Field
|
||||
|
||||
**Files:**
|
||||
- Modify: `src/config/settings.rs`
|
||||
- Modify: `tests/compat_config_test.rs`
|
||||
|
||||
- [ ] **Step 1: Write the failing config test for the new field**
|
||||
|
||||
In `tests/compat_config_test.rs`, add a focused config-load test proving the browser config file can declare one fixed direct-submit skill.
|
||||
|
||||
Test shape:
|
||||
|
||||
```rust
|
||||
#[test]
|
||||
fn sgclaw_settings_load_direct_submit_skill_from_browser_config() {
|
||||
let root = std::env::temp_dir().join(format!("sgclaw-direct-skill-{}", uuid::Uuid::new_v4()));
|
||||
std::fs::create_dir_all(&root).unwrap();
|
||||
let config_path = root.join("sgclaw_config.json");
|
||||
|
||||
std::fs::write(
|
||||
&config_path,
|
||||
r#"{
|
||||
"apiKey": "sk-runtime",
|
||||
"baseUrl": "https://api.deepseek.com",
|
||||
"model": "deepseek-chat",
|
||||
"skillsDir": "D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging",
|
||||
"directSubmitSkill": "fault-details-report.collect_fault_details"
|
||||
}"#,
|
||||
)
|
||||
.unwrap();
|
||||
|
||||
let settings = sgclaw::config::SgClawSettings::load(Some(config_path.as_path()))
|
||||
.unwrap()
|
||||
.expect("expected sgclaw settings from config file");
|
||||
|
||||
assert_eq!(
|
||||
settings.direct_submit_skill.as_deref(),
|
||||
Some("fault-details-report.collect_fault_details")
|
||||
);
|
||||
}
|
||||
```
|
||||
|
||||
- [ ] **Step 2: Run the focused config test and verify it fails**
|
||||
|
||||
Run:
|
||||
|
||||
```bash
|
||||
cargo test --test compat_config_test sgclaw_settings_load_direct_submit_skill_from_browser_config -- --nocapture
|
||||
```
|
||||
|
||||
Expected: FAIL because the config field does not exist yet.
|
||||
|
||||
- [ ] **Step 3: Implement the minimal config field**
|
||||
|
||||
In `src/config/settings.rs`, add:
|
||||
- `direct_submit_skill: Option<String>` to `SgClawSettings`
|
||||
- `direct_submit_skill: Option<String>` to `RawSgClawSettings`
|
||||
- field normalization in `SgClawSettings::new(...)`
|
||||
|
||||
Recommended JSON key shape:
|
||||
|
||||
```rust
|
||||
#[serde(rename = "directSubmitSkill", alias = "direct_submit_skill", default)]
|
||||
direct_submit_skill: Option<String>,
|
||||
```
|
||||
|
||||
Rules:
|
||||
- trim empty values to `None`
|
||||
- keep `DeepSeekSettings` unchanged for this slice unless a compile error proves it must mirror the field
|
||||
- do not alter unrelated config semantics
|
||||
|
||||
- [ ] **Step 4: Re-run the focused config test**
|
||||
|
||||
Run:
|
||||
|
||||
```bash
|
||||
cargo test --test compat_config_test sgclaw_settings_load_direct_submit_skill_from_browser_config -- --nocapture
|
||||
```
|
||||
|
||||
Expected: PASS.
|
||||
|
||||
- [ ] **Step 5: Re-run the broader config file tests**
|
||||
|
||||
Run:
|
||||
|
||||
```bash
|
||||
cargo test --test compat_config_test -- --nocapture
|
||||
```
|
||||
|
||||
Expected: PASS.
|
||||
|
||||
- [ ] **Step 6: Commit Task 1**
|
||||
|
||||
```bash
|
||||
git add src/config/settings.rs tests/compat_config_test.rs
|
||||
git commit -m "feat: add direct submit skill config"
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
### Task 2: Extract A Reusable Browser-Script Direct Execution Helper
|
||||
|
||||
**Files:**
|
||||
- Modify: `src/compat/browser_script_skill_tool.rs`
|
||||
- Modify: `tests/browser_script_skill_tool_test.rs`
|
||||
|
||||
- [ ] **Step 1: Write the first failing helper test**
|
||||
|
||||
In `tests/browser_script_skill_tool_test.rs`, add a focused test proving direct code can execute a packaged browser script without constructing a full `Tool` object first.
|
||||
|
||||
Test shape:
|
||||
|
||||
```rust
|
||||
#[tokio::test]
|
||||
async fn execute_browser_script_tool_runs_packaged_script_with_expected_domain() {
|
||||
// build temp skill script
|
||||
// call the helper directly
|
||||
// assert Action::Eval was sent with wrapped args and normalized domain
|
||||
}
|
||||
```
|
||||
|
||||
Required assertions:
|
||||
- the helper reads the packaged JS file
|
||||
- it wraps args with `const args = ...`
|
||||
- it normalizes URL-like `expected_domain`
|
||||
- it returns the serialized payload string on success
|
||||
|
||||
- [ ] **Step 2: Run the helper test and verify it fails**
|
||||
|
||||
Run:
|
||||
|
||||
```bash
|
||||
cargo test --test browser_script_skill_tool_test execute_browser_script_tool_runs_packaged_script_with_expected_domain -- --nocapture
|
||||
```
|
||||
|
||||
Expected: FAIL because the helper does not exist yet.
|
||||
|
||||
- [ ] **Step 3: Add the second failing helper test for required-domain validation**
|
||||
|
||||
Add a focused failure-path test proving the helper rejects missing or invalid `expected_domain` before any browser command is sent.
|
||||
|
||||
- [ ] **Step 4: Run the validation test and verify it fails**
|
||||
|
||||
Run:
|
||||
|
||||
```bash
|
||||
cargo test --test browser_script_skill_tool_test execute_browser_script_tool_rejects_missing_expected_domain -- --nocapture
|
||||
```
|
||||
|
||||
Expected: FAIL because the helper does not exist yet.
|
||||
|
||||
- [ ] **Step 5: Implement the minimal reusable helper**
|
||||
|
||||
In `src/compat/browser_script_skill_tool.rs`, extract the smallest reusable function, for example:
|
||||
|
||||
```rust
|
||||
pub async fn execute_browser_script_tool<T: Transport + 'static>(
|
||||
tool: &SkillTool,
|
||||
skill_root: &Path,
|
||||
browser_tool: BrowserPipeTool<T>,
|
||||
args: Value,
|
||||
) -> anyhow::Result<ToolResult>
|
||||
```
|
||||
|
||||
Rules:
|
||||
- reuse the current path validation, script loading, wrapping, `Action::Eval`, and payload formatting logic already used by `BrowserScriptSkillTool::execute`
|
||||
- do not change outward behavior of `BrowserScriptSkillTool`
|
||||
- keep the helper narrow and browser-script-only
|
||||
|
||||
- [ ] **Step 6: Refactor `BrowserScriptSkillTool::execute` to call the helper**
|
||||
|
||||
Keep existing behavior and tests green while removing duplicate execution logic.
|
||||
|
||||
- [ ] **Step 7: Re-run the browser-script tests**
|
||||
|
||||
Run:
|
||||
|
||||
```bash
|
||||
cargo test --test browser_script_skill_tool_test -- --nocapture
|
||||
```
|
||||
|
||||
Expected: PASS.
|
||||
|
||||
- [ ] **Step 8: Commit Task 2**
|
||||
|
||||
```bash
|
||||
git add src/compat/browser_script_skill_tool.rs tests/browser_script_skill_tool_test.rs
|
||||
git commit -m "refactor: extract direct browser script execution helper"
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
### Task 3: Add A Narrow Direct Skill Runtime For One Fixed Skill
|
||||
|
||||
**Files:**
|
||||
- Create: `src/compat/direct_skill_runtime.rs`
|
||||
- Modify: `src/compat/mod.rs` or nearest module export point
|
||||
- Reuse: `src/compat/config_adapter.rs`
|
||||
- Reuse: `third_party/zeroclaw/src/skills/mod.rs`
|
||||
|
||||
- [ ] **Step 1: Write the first failing direct-runtime test**
|
||||
|
||||
Add a focused test in `tests/agent_runtime_test.rs` or a new narrow compat test proving code can resolve the configured external skills root, load `fault-details-report`, find `collect_fault_details`, and execute it directly.
|
||||
|
||||
Recommended shape:
|
||||
|
||||
```rust
|
||||
#[test]
|
||||
fn direct_skill_runtime_executes_fault_details_report_without_provider() {
|
||||
// config points at skill_staging root
|
||||
// direct_submit_skill points at fault-details-report.collect_fault_details
|
||||
// browser response returns report-artifact payload
|
||||
// assert no provider/http path is touched
|
||||
}
|
||||
```
|
||||
|
||||
- [ ] **Step 2: Run the focused direct-runtime test and verify it fails**
|
||||
|
||||
Run the narrowest test command for the new test.
|
||||
|
||||
Expected: FAIL because the direct runtime does not exist yet.
|
||||
|
||||
- [ ] **Step 3: Implement `src/compat/direct_skill_runtime.rs`**
|
||||
|
||||
Add a narrow runtime with responsibilities only to:
|
||||
- resolve the configured skills dir with `resolve_skills_dir_from_sgclaw_settings(...)`
|
||||
- load skills from that directory with `load_skills_from_directory(...)`
|
||||
- parse the configured tool name into `skill_name` + `tool_name`
|
||||
- find the matching skill and matching tool
|
||||
- verify `tool.kind == "browser_script"`
|
||||
- derive the minimal argument object
|
||||
- call the new browser-script helper
|
||||
- return the output string or a clear `PipeError`
|
||||
|
||||
Do **not** add generic routing, scenes, or model fallback here.
|
||||
|
||||
- [ ] **Step 4: Keep argument derivation intentionally minimal**
|
||||
|
||||
For the first slice, derive only:
|
||||
- `expected_domain` from `page_url` when present, otherwise fail with a clear message
|
||||
- `period` from the instruction using a narrow deterministic pattern such as `YYYY-MM`
|
||||
|
||||
If the period cannot be derived, return a concise error telling the user to provide it explicitly. Do not guess.
|
||||
|
||||
- [ ] **Step 5: Re-run the focused direct-runtime test**
|
||||
|
||||
Run the same test command again.
|
||||
|
||||
Expected: PASS.
|
||||
|
||||
- [ ] **Step 6: Commit Task 3**
|
||||
|
||||
```bash
|
||||
git add src/compat/direct_skill_runtime.rs src/compat/mod.rs tests/agent_runtime_test.rs
|
||||
git commit -m "feat: add fixed direct skill runtime"
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
### Task 4: Insert The Pre-Routing Seam In Submit-Task Entry
|
||||
|
||||
**Files:**
|
||||
- Modify: `src/agent/mod.rs`
|
||||
- Modify: `tests/agent_runtime_test.rs`
|
||||
|
||||
- [ ] **Step 1: Write the first failing submit-path bypass test**
|
||||
|
||||
In `tests/agent_runtime_test.rs`, add a focused regression proving that when `directSubmitSkill` is configured, `BrowserMessage::SubmitTask` can succeed without any model/provider being configured.
|
||||
|
||||
Test shape:
|
||||
|
||||
```rust
|
||||
#[test]
|
||||
fn submit_task_uses_direct_skill_mode_without_llm_configuration() {
|
||||
// config contains skillsDir + directSubmitSkill, but no reachable provider
|
||||
// natural-language instruction includes period and page_url
|
||||
// expect TaskComplete success from direct skill result
|
||||
}
|
||||
```
|
||||
|
||||
Required assertions:
|
||||
- task succeeds even if provider would be unavailable
|
||||
- output contains the report artifact payload
|
||||
- no summary like `未配置大语言模型`
|
||||
|
||||
- [ ] **Step 2: Run the bypass test and verify it fails**
|
||||
|
||||
Run:
|
||||
|
||||
```bash
|
||||
cargo test --test agent_runtime_test submit_task_uses_direct_skill_mode_without_llm_configuration -- --nocapture
|
||||
```
|
||||
|
||||
Expected: FAIL because submit-task still goes into the current LLM-oriented path.
|
||||
|
||||
- [ ] **Step 3: Add the second failing priority test**
|
||||
|
||||
Add one focused test proving the direct-submit branch runs before the existing compat/LLM branch.
|
||||
|
||||
The easiest assertion is that the mode log becomes something new like:
|
||||
- `direct_skill_primary`
|
||||
|
||||
and the normal mode logs do not appear for that turn.
|
||||
|
||||
- [ ] **Step 4: Run the priority test and verify it fails**
|
||||
|
||||
Run the narrow test command for the new test.
|
||||
|
||||
Expected: FAIL because the mode does not exist yet.
|
||||
|
||||
- [ ] **Step 5: Add the narrow pre-routing branch in `src/agent/mod.rs`**
|
||||
|
||||
In `handle_browser_message_with_context(...)`, after config load/logging and before the existing `should_use_primary_orchestration(...)` / `compat::runtime` path:
|
||||
- check `settings.direct_submit_skill`
|
||||
- if present, emit mode log `direct_skill_primary`
|
||||
- call the new direct runtime
|
||||
- send `TaskComplete` and return immediately
|
||||
|
||||
Rules:
|
||||
- if `direct_submit_skill` is absent, keep existing behavior byte-for-byte where possible
|
||||
- do not modify `compat::runtime.rs` or `compat::orchestration.rs` for this slice
|
||||
- do not silently fall through to LLM when direct execution fails; return the direct error clearly so the first slice is debuggable
|
||||
|
||||
- [ ] **Step 6: Re-run the focused submit-path tests**
|
||||
|
||||
Run:
|
||||
|
||||
```bash
|
||||
cargo test --test agent_runtime_test submit_task_uses_direct_skill_mode_without_llm_configuration -- --nocapture
|
||||
cargo test --test agent_runtime_test direct_skill_mode_logs_direct_skill_primary -- --nocapture
|
||||
```
|
||||
|
||||
Expected: PASS.
|
||||
|
||||
- [ ] **Step 7: Re-run existing no-LLM submit regression coverage**
|
||||
|
||||
Run:
|
||||
|
||||
```bash
|
||||
cargo test --test agent_runtime_test -- --nocapture
|
||||
```
|
||||
|
||||
Expected: PASS, including existing cases where no direct skill is configured and the old no-LLM failure still applies.
|
||||
|
||||
- [ ] **Step 8: Commit Task 4**
|
||||
|
||||
```bash
|
||||
git add src/agent/mod.rs tests/agent_runtime_test.rs
|
||||
git commit -m "feat: route submit tasks through fixed direct skill mode"
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
### Task 5: Lock The Future Migration Seam Without Implementing LLM Dispatch Yet
|
||||
|
||||
**Files:**
|
||||
- Modify only if needed: `src/config/settings.rs`
|
||||
- Modify only if needed: `src/compat/direct_skill_runtime.rs`
|
||||
- Reuse: docs/plan only unless code needs one tiny naming fix
|
||||
|
||||
- [ ] **Step 1: Keep the config naming compatible with future per-skill dispatch**
|
||||
|
||||
Document and preserve this future meaning in code naming:
|
||||
- current field: one fixed direct skill for submit-task bootstrap
|
||||
- future model: each skill can declare dispatch mode such as `direct_browser` or `llm_agent`
|
||||
|
||||
Prefer neutral names in helper code like:
|
||||
- `direct skill mode`
|
||||
- `direct submit skill`
|
||||
|
||||
Avoid hard-coding `fault_details` into generic APIs.
|
||||
|
||||
- [ ] **Step 2: Add one small negative test for fallback behavior**
|
||||
|
||||
Add a focused test proving that when `directSubmitSkill` is not configured, submit-task still behaves exactly as before and can still return the existing no-LLM message.
|
||||
|
||||
If an existing test already proves this, keep it and do not add another.
|
||||
|
||||
- [ ] **Step 3: Re-run the focused end-to-end verification set**
|
||||
|
||||
Run:
|
||||
|
||||
```bash
|
||||
cargo test --test compat_config_test -- --nocapture
|
||||
cargo test --test browser_script_skill_tool_test -- --nocapture
|
||||
cargo test --test agent_runtime_test -- --nocapture
|
||||
```
|
||||
|
||||
Expected: PASS.
|
||||
|
||||
- [ ] **Step 4: Build the main binary**
|
||||
|
||||
Run:
|
||||
|
||||
```bash
|
||||
cargo build --bin sgclaw
|
||||
```
|
||||
|
||||
Expected: PASS.
|
||||
|
||||
- [ ] **Step 5: Commit Task 5**
|
||||
|
||||
```bash
|
||||
git add src/config/settings.rs src/compat/direct_skill_runtime.rs src/compat/browser_script_skill_tool.rs src/agent/mod.rs tests/compat_config_test.rs tests/browser_script_skill_tool_test.rs tests/agent_runtime_test.rs
|
||||
git commit -m "test: verify fixed direct skill submit path"
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Verification Checklist
|
||||
|
||||
### Config loading
|
||||
|
||||
```bash
|
||||
cargo test --test compat_config_test -- --nocapture
|
||||
```
|
||||
|
||||
Expected: `directSubmitSkill` loads correctly and existing config behavior remains intact.
|
||||
|
||||
### Browser-script helper
|
||||
|
||||
```bash
|
||||
cargo test --test browser_script_skill_tool_test -- --nocapture
|
||||
```
|
||||
|
||||
Expected: direct helper preserves the existing browser-script execution semantics.
|
||||
|
||||
### Submit-path bypass
|
||||
|
||||
```bash
|
||||
cargo test --test agent_runtime_test -- --nocapture
|
||||
```
|
||||
|
||||
Expected: configured direct skill bypasses the model path, while unconfigured submit-task behavior stays unchanged.
|
||||
|
||||
### Build
|
||||
|
||||
```bash
|
||||
cargo build --bin sgclaw
|
||||
```
|
||||
|
||||
Expected: the binary compiles cleanly.
|
||||
|
||||
---
|
||||
|
||||
## Notes For The Engineer
|
||||
|
||||
- The key to keeping this slice small is to avoid changing `compat::runtime.rs` and `compat::orchestration.rs`; they remain the future LLM path.
|
||||
- `fault-details-report.collect_fault_details` is only the bootstrap skill. The plumbing must stay generic enough that the configured tool name can later point to another staged browser skill.
|
||||
- Phase 1 should not add per-skill dispatch metadata to the external skill manifests yet. Keep that decision in sgClaw config first; move it into skill metadata only after the direct path is proven useful.
|
||||
- Once the intranet model is ready, the clean next step is to add a dispatch policy layer that chooses between `direct_browser` and `llm_agent` before the current compat path is entered, reusing this same pre-routing seam.
|
||||
@@ -0,0 +1,672 @@
|
||||
# Fault Details Full Skill Alignment Implementation Plan
|
||||
|
||||
> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.
|
||||
|
||||
**Goal:** Upgrade `fault-details-report.collect_fault_details` into a real staged browser skill that matches the original fault-details workflow, and make `claw-new` interpret the returned artifact status correctly in the direct-submit path.
|
||||
|
||||
**Architecture:** Keep routing and direct-skill selection in `claw-new`, but move all fault-details collection, normalization, classification, summary, export, and report-log behavior into the staged skill under `skill_staging`. Implement the staged skill as a true browser-eval entrypoint that remains valid in page context, while exposing testable pure helpers through an environment-safe export guard for `node:test`; then add a narrow Rust artifact interpreter in `src/compat/direct_skill_runtime.rs` so `ok` / `partial` / `empty` map to successful task completion while `blocked` / `error` map to failed completion.
|
||||
|
||||
**Tech Stack:** Rust 2021, `serde_json`, existing `BrowserPipeTool` / `browser_script` runtime, `node:test`, staged skill fixtures, Cargo integration tests.
|
||||
|
||||
---
|
||||
|
||||
## Execution Context
|
||||
|
||||
- Follow @superpowers:test-driven-development for every behavior change.
|
||||
- Follow @superpowers:verification-before-completion before claiming each task is done.
|
||||
- Do **not** create a git worktree unless the user explicitly asks. This repo preference is already established.
|
||||
- Keep scope tight. Do **not** add a new browser protocol, new dispatch metadata, new UI opener behavior, or Rust-side fault classification logic.
|
||||
- Keep the current direct path bootstrap requirement intact: the user instruction must still include an explicit `YYYY-MM`, but the staged skill must treat the page-selected range as the source of truth for collection once execution begins.
|
||||
- Preserve parity with the original package’s real behavior: port the original classification table, `qxxcjl`-based reason heuristics, canonical detail mapping, summary aggregation rules, localhost export call, and report-log call into the staged skill rather than implementing a fixture-only subset.
|
||||
|
||||
## File Map
|
||||
|
||||
### Existing files to modify in `claw-new`
|
||||
|
||||
- Modify: `src/compat/direct_skill_runtime.rs`
|
||||
- add narrow structured artifact parsing and status-to-summary mapping
|
||||
- keep direct-skill routing/config ownership unchanged
|
||||
- Modify: `tests/agent_runtime_test.rs`
|
||||
- add direct-submit regressions for `ok`, `partial`, `empty`, `blocked`, and `error`
|
||||
- Modify: `tests/browser_script_skill_tool_test.rs`
|
||||
- add browser-script execution-shape regression for browser-eval return payloads used by fault-details
|
||||
|
||||
### Existing files to modify in `skill_staging`
|
||||
|
||||
- Modify: `D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/skills/fault-details-report/scripts/collect_fault_details.js`
|
||||
- replace empty shell with browser-eval entrypoint plus parity helpers
|
||||
- Create: `D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/skills/fault-details-report/scripts/collect_fault_details.test.js`
|
||||
- deterministic fixture coverage for normalization, classification, summary, artifact contract, export/logging degradation, and entrypoint shape helpers
|
||||
- Modify: `D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/skills/fault-details-report/SKILL.toml`
|
||||
- align tool description with real collection/export/report-log behavior
|
||||
- Modify: `D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/skills/fault-details-report/SKILL.md`
|
||||
- align written contract with actual runtime behavior and artifact fields
|
||||
- Modify: `D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/skills/fault-details-report/references/collection-flow.md`
|
||||
- align flow with page-range/query/export/report-log sequence
|
||||
- Modify: `D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/skills/fault-details-report/references/data-quality.md`
|
||||
- make canonical columns, original classification tables, reason heuristics, summary rules, and partial semantics explicit
|
||||
- Modify: `D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/scenes/fault-details-report/scene.json`
|
||||
- keep scene output/state contract aligned with real staged artifact behavior
|
||||
|
||||
### Existing files to read but not redesign
|
||||
|
||||
- Read only: `docs/superpowers/specs/2026-04-10-fault-details-full-skill-alignment-design.md`
|
||||
- Read only: `src/agent/mod.rs`
|
||||
- Read only: `src/compat/browser_script_skill_tool.rs`
|
||||
- Read only: `D:/desk/智能体资料/大四区报告监测项/故障明细/index.html`
|
||||
|
||||
---
|
||||
|
||||
### Task 1: Add staged-skill red tests for normalization, summary, and artifact-contract semantics
|
||||
|
||||
**Files:**
|
||||
- Create: `D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/skills/fault-details-report/scripts/collect_fault_details.test.js`
|
||||
- Read only: `D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/skills/fault-details-report/scripts/collect_fault_details.js`
|
||||
- Read only: `D:/desk/智能体资料/大四区报告监测项/故障明细/index.html`
|
||||
|
||||
- [ ] **Step 1: Write the failing staged-skill test file**
|
||||
|
||||
Add `collect_fault_details.test.js` using `node:test` and `assert/strict`. Cover these behaviors with fixed fixtures:
|
||||
|
||||
```javascript
|
||||
const test = require('node:test');
|
||||
const assert = require('node:assert/strict');
|
||||
|
||||
const {
|
||||
DETAIL_COLUMNS,
|
||||
SUMMARY_COLUMNS,
|
||||
normalizeDetailRow,
|
||||
deriveSummaryRows,
|
||||
determineArtifactStatus,
|
||||
buildFaultDetailsArtifact,
|
||||
buildBrowserEntrypointResult
|
||||
} = require('./collect_fault_details.js');
|
||||
|
||||
test('normalizeDetailRow maps canonical detail fields from raw repair rows', () => {
|
||||
const row = normalizeDetailRow({
|
||||
qxdbh: 'QX-1',
|
||||
bxsj: '2026-03-09 08:00:00',
|
||||
cityName: '国网兰州供电公司',
|
||||
maintOrgName: '城关供电服务班',
|
||||
maintGroupName: '抢修一班',
|
||||
bdzMc: '110kV东岗变',
|
||||
xlmc10: '10kV东岗线',
|
||||
byqmc: '东岗1号变',
|
||||
yjflMc: '电网故障',
|
||||
ejflMc: '线路故障',
|
||||
sjflMc: '低压线路',
|
||||
qxxcjl: '现场检查：低压线路断线，已处理完成',
|
||||
gzms: '客户报修停电'
|
||||
}, {
|
||||
companyName: '国网兰州供电公司'
|
||||
});
|
||||
|
||||
assert.equal(row.slsj, '2026-03-09 08:00:00');
|
||||
assert.equal(row.gssgs, '甘肃省电力公司');
|
||||
assert.equal(row.gddw, '城关供电服务班');
|
||||
assert.equal(row.gds, '抢修一班');
|
||||
assert.equal(row.clzt, '处理完成');
|
||||
assert.equal(row.bdz, '110kV东岗变');
|
||||
assert.equal(row.line, '10kV东岗线');
|
||||
assert.equal(row.pb, '东岗1号变');
|
||||
});
|
||||
|
||||
test('deriveSummaryRows groups normalized rows by gds and computes counters', () => {
|
||||
const rows = [
|
||||
{ gds: '抢修一班', gddw: '城关供电服务班', sgs: '国网兰州供电公司', sxfl1: '无效', sxfl2: '无效', gzsb: '' },
|
||||
{ gds: '抢修一班', gddw: '城关供电服务班', sgs: '国网兰州供电公司', sxfl1: '有效', sxfl2: '用户侧', gzsb: '表后线' },
|
||||
{ gds: '抢修一班', gddw: '城关供电服务班', sgs: '国网兰州供电公司', sxfl1: '有效', sxfl2: '电网侧', dwcFl: '低压故障', gzsb: '低压线路' }
|
||||
];
|
||||
|
||||
const summaryRows = deriveSummaryRows(rows, { companyName: '国网兰州供电公司' });
|
||||
assert.equal(summaryRows.length, 1);
|
||||
assert.equal(summaryRows[0].className, '抢修一班');
|
||||
assert.equal(summaryRows[0].allCount, 3);
|
||||
assert.equal(summaryRows[0].wxCount, 1);
|
||||
assert.equal(summaryRows[0].khcCount, 0);
|
||||
assert.equal(summaryRows[0].dyGzCount, 1);
|
||||
assert.equal(summaryRows[0].dyxlCount, 1);
|
||||
assert.equal(summaryRows[0].bhxCount, 1);
|
||||
});
|
||||
|
||||
test('determineArtifactStatus follows blocked > error > partial > empty > ok precedence', () => {
|
||||
assert.equal(determineArtifactStatus({ blockedReason: 'missing_session', fatalError: null, partialReasons: [], detailRows: [{}] }), 'blocked');
|
||||
assert.equal(determineArtifactStatus({ blockedReason: null, fatalError: 'parse_failed', partialReasons: [], detailRows: [{}] }), 'error');
|
||||
assert.equal(determineArtifactStatus({ blockedReason: null, fatalError: null, partialReasons: ['export_failed'], detailRows: [{}] }), 'partial');
|
||||
assert.equal(determineArtifactStatus({ blockedReason: null, fatalError: null, partialReasons: [], detailRows: [] }), 'empty');
|
||||
assert.equal(determineArtifactStatus({ blockedReason: null, fatalError: null, partialReasons: [], detailRows: [{}] }), 'ok');
|
||||
});
|
||||
|
||||
test('buildFaultDetailsArtifact keeps canonical fields, selected range, counts, and downstream results', () => {
|
||||
const artifact = buildFaultDetailsArtifact({
|
||||
period: '2026-03',
|
||||
selectedRange: { start: '2026-03-08 16:00:00', end: '2026-03-09 16:00:00' },
|
||||
detailRows: [{ qxdbh: 'QX-1' }],
|
||||
summaryRows: [{ index: 1 }],
|
||||
partialReasons: ['report_log_failed'],
|
||||
downstream: {
|
||||
export: { attempted: true, success: true, path: 'http://localhost/export.xlsx' },
|
||||
report_log: { attempted: true, success: false, error: '500' }
|
||||
}
|
||||
});
|
||||
|
||||
assert.equal(artifact.type, 'report-artifact');
|
||||
assert.equal(artifact.status, 'partial');
|
||||
assert.deepEqual(artifact.selected_range, { start: '2026-03-08 16:00:00', end: '2026-03-09 16:00:00' });
|
||||
assert.equal(artifact.counts.detail_rows, 1);
|
||||
assert.equal(artifact.counts.summary_rows, 1);
|
||||
assert.deepEqual(artifact.partial_reasons, ['report_log_failed']);
|
||||
});
|
||||
|
||||
test('buildFaultDetailsArtifact keeps required top-level fields for blocked artifact', () => {
|
||||
const artifact = buildFaultDetailsArtifact({
|
||||
period: '2026-03',
|
||||
blockedReason: 'selected_range_unavailable',
|
||||
partialReasons: ['selected_range_unavailable']
|
||||
});
|
||||
|
||||
assert.equal(artifact.type, 'report-artifact');
|
||||
assert.equal(artifact.report_name, 'fault-details-report');
|
||||
assert.equal(artifact.period, '2026-03');
|
||||
assert.equal(artifact.status, 'blocked');
|
||||
assert.deepEqual(artifact.partial_reasons, ['selected_range_unavailable']);
|
||||
assert.equal('downstream' in artifact, false);
|
||||
});
|
||||
|
||||
test('buildFaultDetailsArtifact keeps known selected range and counts on late error', () => {
|
||||
const artifact = buildFaultDetailsArtifact({
|
||||
period: '2026-03',
|
||||
selectedRange: { start: '2026-03-08 16:00:00', end: '2026-03-09 16:00:00' },
|
||||
detailRows: [],
|
||||
summaryRows: [],
|
||||
fatalError: 'summary_failed',
|
||||
partialReasons: ['summary_failed']
|
||||
});
|
||||
|
||||
assert.equal(artifact.status, 'error');
|
||||
assert.deepEqual(artifact.selected_range, { start: '2026-03-08 16:00:00', end: '2026-03-09 16:00:00' });
|
||||
assert.equal(artifact.counts.detail_rows, 0);
|
||||
assert.equal(artifact.counts.summary_rows, 0);
|
||||
});
|
||||
|
||||
test('buildBrowserEntrypointResult returns blocked artifact when selected range is unavailable', async () => {
|
||||
const artifact = await buildBrowserEntrypointResult({
|
||||
period: '2026-03'
|
||||
}, {
|
||||
readSelectedRange: async () => null
|
||||
});
|
||||
|
||||
assert.equal(artifact.status, 'blocked');
|
||||
assert.ok(artifact.partial_reasons.includes('selected_range_unavailable'));
|
||||
});
|
||||
```
|
||||
|
||||
- [ ] **Step 2: Run the staged-skill test file and verify it fails**
|
||||
|
||||
Run:
|
||||
|
||||
```bash
|
||||
node "D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/skills/fault-details-report/scripts/collect_fault_details.test.js"
|
||||
```
|
||||
|
||||
Expected: FAIL because `collect_fault_details.js` does not export these helpers yet and still only returns an empty shell.
|
||||
|
||||
---
|
||||
|
||||
### Task 2: Implement staged-skill parity helpers and a valid browser entrypoint
|
||||
|
||||
**Files:**
|
||||
- Modify: `D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/skills/fault-details-report/scripts/collect_fault_details.js`
|
||||
- Test: `D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/skills/fault-details-report/scripts/collect_fault_details.test.js`
|
||||
|
||||
- [ ] **Step 1: Implement the helper exports and browser entrypoint shape needed to satisfy the red tests**
|
||||
|
||||
Refactor `collect_fault_details.js` so the file remains a valid browser-eval script in page context while still supporting `node:test` through an environment-safe export guard.
|
||||
|
||||
Required implementation pieces:
|
||||
|
||||
```javascript
|
||||
const DETAIL_COLUMNS = [/* existing canonical columns */];
|
||||
const SUMMARY_COLUMNS = [/* existing summary columns */];
|
||||
|
||||
function normalizeDetailRow(raw, context) {
|
||||
// map qxdbh/gssgs/sgs/gddw/gds/slsj/clzt/bdz/line/pb
|
||||
// derive sxfl1/sxfl2/sxfl3/gzsb/gzyy from the original package rules
|
||||
}
|
||||
|
||||
function deriveSummaryRows(detailRows, context) {
|
||||
// group by gds and compute all original package counters
|
||||
}
|
||||
|
||||
function determineArtifactStatus({ blockedReason, fatalError, partialReasons, detailRows }) {
|
||||
// blocked > error > partial > empty > ok
|
||||
}
|
||||
|
||||
function buildFaultDetailsArtifact({
|
||||
period,
|
||||
selectedRange,
|
||||
detailRows,
|
||||
summaryRows,
|
||||
partialReasons,
|
||||
blockedReason,
|
||||
fatalError,
|
||||
downstream
|
||||
}) {
|
||||
// return report-artifact with columns, sections, counts, status, partial_reasons, downstream
|
||||
}
|
||||
|
||||
async function buildBrowserEntrypointResult(input, deps = defaultBrowserDeps()) {
|
||||
// read selected range from page
|
||||
// collect raw rows from page query
|
||||
// normalize rows
|
||||
// derive summary
|
||||
// attempt export + report log
|
||||
// return final artifact
|
||||
}
|
||||
|
||||
if (typeof module !== 'undefined' && module.exports) {
|
||||
module.exports = {
|
||||
DETAIL_COLUMNS,
|
||||
SUMMARY_COLUMNS,
|
||||
normalizeDetailRow,
|
||||
deriveSummaryRows,
|
||||
determineArtifactStatus,
|
||||
buildFaultDetailsArtifact,
|
||||
buildBrowserEntrypointResult
|
||||
};
|
||||
}
|
||||
|
||||
return await buildBrowserEntrypointResult(args);
|
||||
```
|
||||
|
||||
Rules:
|
||||
- keep `DETAIL_COLUMNS` and `SUMMARY_COLUMNS` canonical and stable
|
||||
- keep helper functions self-contained in this file unless a separate pure helper file becomes necessary for runtime validity
|
||||
- keep the browser entrypoint compatible with current `eval` wrapper
|
||||
- keep browser runtime free of unguarded Node-only assumptions
|
||||
- do **not** invent a new protocol or callback surface
|
||||
|
||||
- [ ] **Step 2: Re-run the staged-skill test file and verify it now reaches deeper failures or passes the initial helper coverage**
|
||||
|
||||
Run:
|
||||
|
||||
```bash
|
||||
node "D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/skills/fault-details-report/scripts/collect_fault_details.test.js"
|
||||
```
|
||||
|
||||
Expected: either PASS for the Task 1 cases, or fail only on the still-missing full parity/export/history specifics added in Task 3.
|
||||
|
||||
---
|
||||
|
||||
### Task 3: Add red tests for full classification parity, downstream partials, and empty-result export semantics
|
||||
|
||||
**Files:**
|
||||
- Modify: `D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/skills/fault-details-report/scripts/collect_fault_details.test.js`
|
||||
- Modify: `D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/skills/fault-details-report/scripts/collect_fault_details.js`
|
||||
- Read only: `D:/desk/智能体资料/大四区报告监测项/故障明细/index.html`
|
||||
|
||||
- [ ] **Step 1: Extend the staged-skill tests with failing parity and downstream cases**
|
||||
|
||||
Add focused failing tests such as:
|
||||
|
||||
```javascript
|
||||
test('normalizeDetailRow derives gzyy from qxxcjl text heuristics', () => {
|
||||
const row = normalizeDetailRow({
|
||||
qxxcjl: '现场检查：客户表后线烧损，已恢复送电',
|
||||
ejflMc: '客户侧故障',
|
||||
sjflMc: '表后线'
|
||||
}, { companyName: '国网兰州供电公司' });
|
||||
|
||||
assert.equal(row.gzsb, '表后线');
|
||||
assert.equal(row.gzyy, '表后线烧损');
|
||||
});
|
||||
|
||||
test('buildBrowserEntrypointResult returns partial when export fails after detail collection succeeds', async () => {
|
||||
const artifact = await buildBrowserEntrypointResult({ period: '2026-03' }, {
|
||||
readSelectedRange: async () => ({ start: '2026-03-08 16:00:00', end: '2026-03-09 16:00:00' }),
|
||||
queryFaultRows: async () => [{ qxdbh: 'QX-1', bxsj: '2026-03-09 08:00:00', maintGroupName: '抢修一班' }],
|
||||
readCompanyContext: () => ({ companyName: '国网兰州供电公司' }),
|
||||
exportWorkbook: async () => {
|
||||
throw new Error('export_failed');
|
||||
},
|
||||
writeReportLog: async () => ({ success: true })
|
||||
});
|
||||
|
||||
assert.equal(artifact.status, 'partial');
|
||||
assert.ok(artifact.partial_reasons.includes('export_failed'));
|
||||
assert.equal(artifact.counts.detail_rows, 1);
|
||||
assert.equal(artifact.downstream.export.attempted, true);
|
||||
assert.equal(artifact.downstream.export.success, false);
|
||||
});
|
||||
|
||||
test('buildBrowserEntrypointResult returns error when normalized detail rows cannot be produced', async () => {
|
||||
const artifact = await buildBrowserEntrypointResult({ period: '2026-03' }, {
|
||||
readSelectedRange: async () => ({ start: '2026-03-08 16:00:00', end: '2026-03-09 16:00:00' }),
|
||||
queryFaultRows: async () => [{ qxdbh: '', bxsj: '' }],
|
||||
readCompanyContext: () => ({ companyName: '国网兰州供电公司' })
|
||||
});
|
||||
|
||||
assert.equal(artifact.status, 'error');
|
||||
assert.ok(artifact.partial_reasons.includes('detail_normalization_failed'));
|
||||
});
|
||||
|
||||
test('buildBrowserEntrypointResult keeps canonical rows empty for empty result and omits downstream before attempts', async () => {
|
||||
const artifact = await buildBrowserEntrypointResult({ period: '2026-03' }, {
|
||||
readSelectedRange: async () => ({ start: '2026-03-08 16:00:00', end: '2026-03-09 16:00:00' }),
|
||||
queryFaultRows: async () => [],
|
||||
readCompanyContext: () => ({ companyName: '国网兰州供电公司' })
|
||||
});
|
||||
|
||||
assert.equal(artifact.status, 'empty');
|
||||
assert.deepEqual(artifact.rows, []);
|
||||
assert.equal('downstream' in artifact, false);
|
||||
});
|
||||
```
|
||||
|
||||
Also add fixture cases derived from the original package’s full classification table and summary counters so the staged skill is forced toward parity, not a subset implementation.
|
||||
|
||||
- [ ] **Step 2: Run the staged-skill test file and verify it fails on the new cases**
|
||||
|
||||
Run:
|
||||
|
||||
```bash
|
||||
node "D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/skills/fault-details-report/scripts/collect_fault_details.test.js"
|
||||
```
|
||||
|
||||
Expected: FAIL on missing full classification parity or downstream partial/error behavior.
|
||||
|
||||
- [ ] **Step 3: Implement the full business logic needed to satisfy the new tests**
|
||||
|
||||
In `collect_fault_details.js`:
|
||||
- port the original classification table and `qxxcjl` text heuristics for `sxfl1`, `sxfl2`, `sxfl3`, `gzsb`, `gzyy`
|
||||
- port the original summary derivation rules and counters completely
|
||||
- add required-field validation so structurally unusable normalized rows escalate to `error`
|
||||
- add downstream `exportWorkbook` and `writeReportLog` stages that record `{attempted, success, path, error}`
|
||||
- keep collection success distinct from downstream failures so export/logging failures become `partial`, not full failure
|
||||
- keep placeholder rows, if needed for downstream empty-export payloads, downstream-only and never in canonical returned `rows`
|
||||
- include both `period` and `selected_range` in the artifact
|
||||
- omit `downstream` when export/report-log have not been attempted yet
|
||||
|
||||
- [ ] **Step 4: Re-run the staged-skill test file and verify it passes**
|
||||
|
||||
Run:
|
||||
|
||||
```bash
|
||||
node "D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/skills/fault-details-report/scripts/collect_fault_details.test.js"
|
||||
```
|
||||
|
||||
Expected: PASS.
|
||||
|
||||
---
|
||||
|
||||
### Task 4: Align staged-skill metadata and reference docs with the implemented behavior
|
||||
|
||||
**Files:**
|
||||
- Modify: `D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/skills/fault-details-report/SKILL.toml`
|
||||
- Modify: `D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/skills/fault-details-report/SKILL.md`
|
||||
- Modify: `D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/skills/fault-details-report/references/collection-flow.md`
|
||||
- Modify: `D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/skills/fault-details-report/references/data-quality.md`
|
||||
- Modify: `D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/scenes/fault-details-report/scene.json`
|
||||
|
||||
- [ ] **Step 1: Update the staged metadata/docs to match the implemented runtime contract**
|
||||
|
||||
Required changes:
|
||||
- `SKILL.toml`: description must say the tool collects rows, derives summary, attempts localhost export, and records report history
|
||||
- `SKILL.md`: artifact example must include `selected_range`, `counts`, `status`, `partial_reasons`, and `downstream`
|
||||
- `references/collection-flow.md`: sequence must explicitly include page-selected range -> raw query -> normalization -> summary -> export -> report-log
|
||||
- `references/data-quality.md`: document the original classification tables, `qxxcjl` heuristics, summary rules, partial/error escalation rules, and empty-result semantics explicitly enough to match the implemented helpers
|
||||
- `scene.json`: keep inputs/outputs/status semantics aligned with the richer artifact; do not add routing policy there
|
||||
|
||||
- [ ] **Step 2: Read the updated staged docs and verify they match the implemented JS behavior**
|
||||
|
||||
Read and confirm:
|
||||
- descriptions no longer claim “artifact shell” behavior
|
||||
- docs do not move routing ownership out of `claw-new`
|
||||
- docs do not promise auto-opening/downloading behavior in this slice
|
||||
- docs reflect blocked/error field-presence rules and downstream-attempt semantics
|
||||
|
||||
Expected: staged metadata/docs accurately reflect the implemented collector.
|
||||
|
||||
---
|
||||
|
||||
### Task 5: Add Rust red tests for artifact-status interpretation in the direct-submit runtime
|
||||
|
||||
**Files:**
|
||||
- Modify: `tests/agent_runtime_test.rs`
|
||||
- Modify: `tests/browser_script_skill_tool_test.rs`
|
||||
- Modify: `src/compat/direct_skill_runtime.rs`
|
||||
- Read only: `src/compat/browser_script_skill_tool.rs`
|
||||
|
||||
- [ ] **Step 1: Add failing direct-submit runtime tests for structured artifact statuses**
|
||||
|
||||
Extend `tests/agent_runtime_test.rs` with focused regressions that use the existing temp skill-root harness but return real `report-artifact` payloads:
|
||||
|
||||
```rust
|
||||
#[test]
|
||||
fn submit_task_treats_partial_report_artifact_as_success_with_warning_summary() {
|
||||
let skill_root = build_direct_runtime_skill_root();
|
||||
let runtime_context = direct_submit_runtime_context(&skill_root);
|
||||
let transport = Arc::new(MockTransport::new(vec![success_browser_response(
|
||||
1,
|
||||
serde_json::json!({
|
||||
"text": {
|
||||
"type": "report-artifact",
|
||||
"report_name": "fault-details-report",
|
||||
"period": "2026-03",
|
||||
"selected_range": { "start": "2026-03-08 16:00:00", "end": "2026-03-09 16:00:00" },
|
||||
"columns": ["qxdbh"],
|
||||
"rows": [{ "qxdbh": "QX-1" }],
|
||||
"sections": [{ "name": "summary-sheet", "columns": ["index"], "rows": [{ "index": 1 }] }],
|
||||
"counts": { "detail_rows": 1, "summary_rows": 1 },
|
||||
"status": "partial",
|
||||
"partial_reasons": ["report_log_failed"],
|
||||
"downstream": {
|
||||
"export": { "attempted": true, "success": true, "path": "http://localhost/export.xlsx" },
|
||||
"report_log": { "attempted": true, "success": false, "error": "500" }
|
||||
}
|
||||
}
|
||||
}),
|
||||
)]));
|
||||
// ... invoke handle_browser_message_with_context(...)
|
||||
// assert TaskComplete.success == true
|
||||
// assert summary contains partial/report_log_failed/detail_rows=1
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn submit_task_treats_empty_report_artifact_as_success() { /* status=empty => success=true */ }
|
||||
|
||||
#[test]
|
||||
fn submit_task_treats_blocked_report_artifact_as_failure() { /* status=blocked => success=false */ }
|
||||
|
||||
#[test]
|
||||
fn submit_task_treats_error_report_artifact_as_failure() { /* status=error => success=false */ }
|
||||
```
|
||||
|
||||
Also add one focused helper regression to `tests/browser_script_skill_tool_test.rs` that proves the browser-script helper can return a structured object payload used by the fault-details path without flattening required fields away.
|
||||
|
||||
Suggested test name:
|
||||
|
||||
```rust
|
||||
#[tokio::test]
|
||||
async fn execute_browser_script_tool_preserves_structured_report_artifact_payload() { /* ... */ }
|
||||
```
|
||||
|
||||
- [ ] **Step 2: Run the focused Rust tests and verify they fail**
|
||||
|
||||
Run:
|
||||
|
||||
```bash
|
||||
cargo test --test agent_runtime_test submit_task_treats_partial_report_artifact_as_success_with_warning_summary -- --nocapture
|
||||
cargo test --test browser_script_skill_tool_test execute_browser_script_tool_preserves_structured_report_artifact_payload -- --nocapture
|
||||
```
|
||||
|
||||
Expected: the new `agent_runtime_test` case fails because `execute_direct_submit_skill` still returns raw JSON text and `src/agent/mod.rs` still marks all direct-submit results as success when no Rust-side interpretation exists.
|
||||
|
||||
---
|
||||
|
||||
### Task 6: Implement narrow Rust artifact interpretation without moving business rules into Rust
|
||||
|
||||
**Files:**
|
||||
- Modify: `src/compat/direct_skill_runtime.rs`
|
||||
- Modify: `tests/agent_runtime_test.rs`
|
||||
- Modify: `tests/browser_script_skill_tool_test.rs`
|
||||
|
||||
- [ ] **Step 1: Implement a narrow structured-artifact interpreter in `src/compat/direct_skill_runtime.rs`**
|
||||
|
||||
Add a small internal result type and parser, for example:
|
||||
|
||||
```rust
|
||||
struct DirectSubmitOutcome {
|
||||
success: bool,
|
||||
summary: String,
|
||||
}
|
||||
|
||||
fn interpret_direct_submit_output(output: &str) -> DirectSubmitOutcome {
|
||||
// parse JSON if possible
|
||||
// if type == "report-artifact", read status/counts/partial_reasons/downstream
|
||||
// map ok/partial/empty => success=true
|
||||
// map blocked/error => success=false
|
||||
// build concise summary with report_name, period, detail_rows, summary_rows, status, partial reasons
|
||||
// fall back to raw output text when payload is not a recognized artifact
|
||||
}
|
||||
```
|
||||
|
||||
Then change the public entrypoint shape from `Result<String, PipeError>` to a narrow result carrying `success` and `summary`, or add a second helper that `src/agent/mod.rs` can use without changing routing ownership.
|
||||
|
||||
Rules:
|
||||
- do **not** reimplement fault normalization/classification/summary in Rust
|
||||
- do **not** add fault-specific branching in `src/agent/mod.rs`
|
||||
- keep unrecognized non-artifact outputs working as before
|
||||
- keep explicit `YYYY-MM` derivation and configured `skill.tool` resolution unchanged
|
||||
|
||||
- [ ] **Step 2: Update the submit-path caller to use the interpreted success flag**
|
||||
|
||||
Adjust the direct-submit branch so `TaskComplete.success` comes from the artifact interpretation instead of blindly treating every `Ok(summary)` as success.
|
||||
|
||||
Implementation target:
|
||||
- keep the direct path in `src/agent/mod.rs`
|
||||
- keep error handling narrow
|
||||
- if needed, return a dedicated direct-submit outcome from `execute_direct_submit_skill`
|
||||
|
||||
- [ ] **Step 3: Re-run the focused Rust tests and verify they pass**
|
||||
|
||||
Run:
|
||||
|
||||
```bash
|
||||
cargo test --test agent_runtime_test submit_task_treats_partial_report_artifact_as_success_with_warning_summary -- --nocapture
|
||||
cargo test --test agent_runtime_test submit_task_treats_empty_report_artifact_as_success -- --nocapture
|
||||
cargo test --test agent_runtime_test submit_task_treats_blocked_report_artifact_as_failure -- --nocapture
|
||||
cargo test --test agent_runtime_test submit_task_treats_error_report_artifact_as_failure -- --nocapture
|
||||
cargo test --test browser_script_skill_tool_test execute_browser_script_tool_preserves_structured_report_artifact_payload -- --nocapture
|
||||
```
|
||||
|
||||
Expected: PASS.
|
||||
|
||||
---
|
||||
|
||||
### Task 7: Run the full verification sweep for the staged skill and direct runtime
|
||||
|
||||
**Files:**
|
||||
- Verify only
|
||||
|
||||
- [ ] **Step 1: Run the staged-skill deterministic test file**
|
||||
|
||||
Run:
|
||||
|
||||
```bash
|
||||
node "D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/skills/fault-details-report/scripts/collect_fault_details.test.js"
|
||||
```
|
||||
|
||||
Expected: PASS.
|
||||
|
||||
- [ ] **Step 2: Run the relevant Rust regression suites**
|
||||
|
||||
Run:
|
||||
|
||||
```bash
|
||||
cargo test --test browser_script_skill_tool_test -- --nocapture
|
||||
cargo test --test agent_runtime_test -- --nocapture
|
||||
```
|
||||
|
||||
Expected: PASS.
|
||||
|
||||
- [ ] **Step 3: Run the broader compatibility coverage and build**
|
||||
|
||||
Run:
|
||||
|
||||
```bash
|
||||
cargo test --test compat_runtime_test -- --nocapture
|
||||
cargo test --test compat_config_test -- --nocapture
|
||||
cargo build --bin sgclaw
|
||||
```
|
||||
|
||||
Expected: PASS.
|
||||
|
||||
- [ ] **Step 4: Manually verify the requirements against the approved spec**
|
||||
|
||||
Checklist:
|
||||
- staged skill now reads page-selected range instead of inventing a month window after entry
|
||||
- staged skill returns canonical detail rows and summary rows
|
||||
- staged skill ports the original classification table, `qxxcjl` heuristics, and summary counters with parity coverage
|
||||
- staged skill records downstream export/report-log outcome
|
||||
- staged skill distinguishes `ok` / `partial` / `empty` / `blocked` / `error`
|
||||
- `blocked` / `error` artifacts keep the required top-level fields, and preserve known `selected_range` / `counts` when failure happens late enough
|
||||
- `downstream` is omitted when export/report-log were not attempted and included with attempted/success flags once they were attempted
|
||||
- empty-result canonical `rows` stay empty even if downstream export uses a placeholder transport row
|
||||
- `claw-new` maps `ok` / `partial` / `empty` to success and `blocked` / `error` to failure
|
||||
- no new routing metadata was added to `SKILL.toml` or `scene.json`
|
||||
- no new browser protocol or opener/UI behavior was introduced
|
||||
|
||||
Expected: all checklist items satisfied before calling the work complete.
|
||||
|
||||
---
|
||||
|
||||
## Verification Checklist
|
||||
|
||||
### Staged skill behavior
|
||||
|
||||
```bash
|
||||
node "D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/skills/fault-details-report/scripts/collect_fault_details.test.js"
|
||||
```
|
||||
|
||||
Expected: deterministic fixture coverage passes for normalization, full classification parity, summary derivation, artifact shape, empty semantics, and downstream partial semantics.
|
||||
|
||||
### Direct-submit runtime mapping
|
||||
|
||||
```bash
|
||||
cargo test --test agent_runtime_test -- --nocapture
|
||||
```
|
||||
|
||||
Expected:
|
||||
- valid artifact `ok` / `partial` / `empty` completes successfully
|
||||
- valid artifact `blocked` / `error` completes as failure
|
||||
- existing invalid config regression still passes
|
||||
- existing direct-submit happy path still passes
|
||||
|
||||
### Browser-script helper safety
|
||||
|
||||
```bash
|
||||
cargo test --test browser_script_skill_tool_test -- --nocapture
|
||||
```
|
||||
|
||||
Expected: current browser-script execution semantics remain intact while returning structured artifact payloads.
|
||||
|
||||
### Compatibility/build
|
||||
|
||||
```bash
|
||||
cargo test --test compat_runtime_test -- --nocapture
|
||||
cargo test --test compat_config_test -- --nocapture
|
||||
cargo build --bin sgclaw
|
||||
```
|
||||
|
||||
Expected: no regressions in compat execution/config loading; main binary builds cleanly.
|
||||
|
||||
---
|
||||
|
||||
## Notes For The Engineer
|
||||
|
||||
- The paired spec is `docs/superpowers/specs/2026-04-10-fault-details-full-skill-alignment-design.md`.
|
||||
- Keep all fault business transforms in `skill_staging`, not in Rust.
|
||||
- Keep direct routing config-owned via `skillsDir` + `directSubmitSkill`.
|
||||
- Do **not** broaden this slice into LLM routing, generic dispatch policy, new browser opcodes, or export auto-open behavior.
|
||||
- If the original package reveals extra classification rules that are needed for parity, add them only inside `collect_fault_details.js` and its staged references/tests, not in `claw-new`.
|
||||
@@ -0,0 +1,808 @@
|
||||
# TQ Lineloss Deterministic Skill Implementation Plan
|
||||
|
||||
> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.
|
||||
|
||||
**Goal:** Add a staged `tq-lineloss-report.collect_lineloss` browser-script skill plus a `。。。` deterministic submit path in `claw-new` that extracts and normalizes company/month/week parameters without LLM, executes through the existing pipe browser-script seam, and does not regress Zhihu hotlist behavior.
|
||||
|
||||
**Architecture:** Keep the new behavior behind a narrow deterministic branch that activates only when the raw instruction ends with the exact suffix `。。。`. `claw-new` owns deterministic trigger detection, explicit scene matching, semantic extraction, canonical normalization, prompt-or-execute control flow, and artifact interpretation; the staged skill owns page inspection, source/API collection, row normalization, export/report-log behavior, and final artifact generation. Reuse the existing `browser_script` execution seam already used by the direct browser path so the backend can later swap from pipe to ws without changing the deterministic contract.
|
||||
|
||||
**Tech Stack:** Rust 2021, Cargo tests, existing `BrowserPipeTool` / `execute_browser_script_tool` seam, staged skill packaging under `claw/claw/skills/skill_staging`, browser-side JavaScript, deterministic string parsing and normalization.
|
||||
|
||||
---
|
||||
|
||||
## Execution Context
|
||||
|
||||
- Follow @superpowers:test-driven-development for every behavior change.
|
||||
- Follow @superpowers:verification-before-completion before claiming each task is done.
|
||||
- Do **not** create a git worktree unless the user explicitly asks.
|
||||
- Keep the new behavior as a narrow branch; do **not** redesign the whole runtime into a general registry engine in this slice.
|
||||
- Preserve `src/runtime/engine.rs:147-159` and `src/runtime/engine.rs:265-286` behavior unless a failing regression test proves a change is required.
|
||||
- Do **not** add ws runtime requirements on `main`; keep ws-readiness isolated to backend-neutral contracts only.
|
||||
- Never fall back to page defaults for missing company, mode, or period in deterministic mode.
|
||||
- If a deterministic request does not match the lineloss whitelist scene, return a deterministic mismatch prompt instead of falling through to ordinary orchestration.
|
||||
|
||||
## File Map
|
||||
|
||||
### New or modified files in `claw-new`
|
||||
|
||||
- Create: `src/compat/deterministic_submit.rs`
|
||||
- suffix detection, deterministic scene match, prompt-or-execute decision
|
||||
- Create: `src/compat/tq_lineloss/mod.rs`
|
||||
- public normalization and artifact helpers
|
||||
- Create: `src/compat/tq_lineloss/contracts.rs`
|
||||
- canonical request/result data structures and status semantics
|
||||
- Create: `src/compat/tq_lineloss/org_resolver.rs`
|
||||
- alias generation, canonical label/code resolution, ambiguity handling
|
||||
- Create: `src/compat/tq_lineloss/period_resolver.rs`
|
||||
- month/week extraction, contradiction detection, canonical payload building
|
||||
- Create: `src/compat/tq_lineloss/org_units.rs`
|
||||
- checked-in canonical unit dictionary derived from the real source tree data
|
||||
- Modify: `src/compat/mod.rs`
|
||||
- export the deterministic and lineloss modules
|
||||
- Modify: `src/agent/mod.rs`
|
||||
- insert the deterministic branch before ordinary LLM interpretation, but only when the exact suffix is present
|
||||
- Modify only if code duplication would otherwise occur: `src/compat/direct_skill_runtime.rs`
|
||||
- extract narrow shared browser-script execution helpers without changing current configured direct-submit behavior
|
||||
- Read but avoid changing unless tests force it: `src/runtime/engine.rs`
|
||||
- existing Zhihu hotlist routing/prompt logic must remain intact
|
||||
|
||||
### New staged skill package in `claw`
|
||||
|
||||
- Create: `D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/skills/tq-lineloss-report/SKILL.md`
|
||||
- Create: `D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/skills/tq-lineloss-report/SKILL.toml`
|
||||
- Create: `D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/skills/tq-lineloss-report/references/collection-flow.md`
|
||||
- Create: `D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/skills/tq-lineloss-report/references/data-quality.md`
|
||||
- Create: `D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/skills/tq-lineloss-report/assets/scene-snapshot/index.html`
|
||||
- Create: `D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/skills/tq-lineloss-report/scripts/collect_lineloss.js`
|
||||
- Create: `D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/skills/tq-lineloss-report/scripts/collect_lineloss.test.js`
|
||||
- Create if staging conventions require it: `D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/scenes/tq-lineloss-report/scene.json`
|
||||
|
||||
### Tests
|
||||
|
||||
- Create: `tests/deterministic_submit_test.rs`
|
||||
- Modify: `tests/compat_runtime_test.rs`
|
||||
- Modify only if end-to-end submit coverage requires it: `tests/runtime_task_flow_test.rs`
|
||||
|
||||
---
|
||||
|
||||
## Locked contracts
|
||||
|
||||
### Deterministic trigger contract
|
||||
|
||||
- Trigger only when the raw instruction ends with the exact suffix `。。。`.
|
||||
- No suffix: current behavior unchanged.
|
||||
- Suffix + unsupported scene: explicit deterministic mismatch prompt.
|
||||
- Suffix is not permission for arbitrary browser actions; only fixed deterministic scenes are allowed.
|
||||
- Negative cases must stay non-deterministic or mismatched exactly as designed:
|
||||
- ASCII `...` is not the trigger
|
||||
- `。。。。` is not the trigger
|
||||
- `。。。` appearing in the middle of the instruction is not the trigger
|
||||
- any trailing whitespace after `。。。` is not the trigger in this slice
|
||||
|
||||
### Canonical org contract
|
||||
|
||||
The resolver must output both display and backend values:
|
||||
|
||||
```rust
|
||||
pub struct ResolvedOrg {
|
||||
pub label: String,
|
||||
pub code: String,
|
||||
}
|
||||
```
|
||||
|
||||
Required supported inputs include:
|
||||
- `兰州公司`
|
||||
- `天水公司`
|
||||
- `国网兰州供电公司`
|
||||
- `城关供电分公司`
|
||||
- `榆中县供电公司`
|
||||
- normalized shorthand such as `榆中县公司`
|
||||
|
||||
Rules:
|
||||
- derive aliases from the real unit tree data
|
||||
- require uniqueness before execution
|
||||
- ambiguous aliases prompt and stop
|
||||
- missing company prompts and stop
|
||||
|
||||
### Canonical period contract
|
||||
|
||||
```rust
|
||||
pub enum PeriodMode {
|
||||
Month,
|
||||
Week,
|
||||
}
|
||||
|
||||
pub struct ResolvedPeriod {
|
||||
pub mode: PeriodMode,
|
||||
pub mode_code: String,
|
||||
pub value: String,
|
||||
pub payload: serde_json::Value,
|
||||
}
|
||||
```
|
||||
|
||||
Required supported inputs include:
|
||||
- `月累计 2026-03`
|
||||
- `月累计 2026年3月`
|
||||
- `周累计 2026年第12周`
|
||||
|
||||
Rules:
|
||||
- month and week intent are mutually exclusive
|
||||
- missing mode prompts and stop
|
||||
- missing period prompts and stop
|
||||
- bare `第12周` is incomplete in this slice and must prompt for year instead of guessing
|
||||
- derive the real backend `period_mode_code` values and request payload field names from the source page/API contract before implementation; do not ship placeholder enum echoes such as `month`/`week` unless the source materials prove those are the real backend codes
|
||||
- never use page-selected defaults in deterministic mode
|
||||
|
||||
### Artifact contract
|
||||
|
||||
Lock the field names now so `claw-new` can interpret status without re-embedding business logic:
|
||||
|
||||
```json
|
||||
{
|
||||
"type": "report-artifact",
|
||||
"report_name": "tq-lineloss-report",
|
||||
"status": "ok",
|
||||
"org": {
|
||||
"label": "国网兰州供电公司",
|
||||
"code": "008df5db70319f73e0508eoac23e0c3c"
|
||||
},
|
||||
"period": {
|
||||
"mode": "month",
|
||||
"mode_code": "<real-backend-mode-code>",
|
||||
"value": "2026-03",
|
||||
"payload": {
|
||||
"<real-backend-field>": "<real-backend-value>"
|
||||
}
|
||||
},
|
||||
"columns": [],
|
||||
"rows": [],
|
||||
"counts": {
|
||||
"rows": 0
|
||||
},
|
||||
"export": {
|
||||
"attempted": false,
|
||||
"status": "skipped",
|
||||
"message": null
|
||||
},
|
||||
"reasons": []
|
||||
}
|
||||
```
|
||||
|
||||
Status mapping in `claw-new`:
|
||||
- `ok` -> task success
|
||||
- `partial` -> task success with partial summary
|
||||
- `blocked` -> task failure
|
||||
- `error` -> task failure
|
||||
|
||||
---
|
||||
|
||||
### Task 1: Scaffold the staged skill package and written contract
|
||||
|
||||
**Files:**
|
||||
- Create: `D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/skills/tq-lineloss-report/SKILL.md`
|
||||
- Create: `D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/skills/tq-lineloss-report/SKILL.toml`
|
||||
- Create: `D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/skills/tq-lineloss-report/references/collection-flow.md`
|
||||
- Create: `D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/skills/tq-lineloss-report/references/data-quality.md`
|
||||
- Create: `D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/skills/tq-lineloss-report/assets/scene-snapshot/index.html`
|
||||
- Create if required: `D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/scenes/tq-lineloss-report/scene.json`
|
||||
|
||||
- [ ] **Step 1: Write the failing package contract files**
|
||||
|
||||
Create the package using `fault-details-report` as the structure reference. Lock one tool only:
|
||||
|
||||
```toml
|
||||
[[tools]]
|
||||
name = "collect_lineloss"
|
||||
kind = "browser_script"
|
||||
description = "Collect 台区线损月/周累计线损率 rows using normalized company and period parameters and return a structured report artifact."
|
||||
```
|
||||
|
||||
Declare required args in `SKILL.toml`:
|
||||
- `expected_domain`
|
||||
- `org_label`
|
||||
- `org_code`
|
||||
- `period_mode`
|
||||
- `period_mode_code`
|
||||
- `period_value`
|
||||
- `period_payload`
|
||||
|
||||
- [ ] **Step 2: Write `SKILL.md` before implementation**
|
||||
|
||||
Document:
|
||||
- when to use / when not to use
|
||||
- required normalized args only
|
||||
- blocked/error semantics
|
||||
- exact returned artifact fields
|
||||
- no raw natural-language values passed to backend requests
|
||||
|
||||
- [ ] **Step 3: Write the reference docs**
|
||||
|
||||
`references/collection-flow.md` must describe:
|
||||
- relevant page state
|
||||
- month request mapping
|
||||
- week request mapping
|
||||
- export/report-log flow if retained
|
||||
|
||||
`references/data-quality.md` must define:
|
||||
- canonical output columns
|
||||
- required field coverage
|
||||
- status semantics
|
||||
- partial/error rules
|
||||
- org/period normalization assumptions
|
||||
|
||||
- [ ] **Step 4: Add scene metadata if the current staging registry needs it**
|
||||
|
||||
Keep it narrow: one scene, one tool, one artifact type.
|
||||
|
||||
- [ ] **Step 5: Add an automated staged-skill load/resolve check**
|
||||
|
||||
Add `tests/deterministic_submit_test.rs` coverage that loads the staged skills root used by runtime tests, resolves `tq-lineloss-report.collect_lineloss`, and asserts the tool is discoverable with the required args:
|
||||
- `expected_domain`
|
||||
- `org_label`
|
||||
- `org_code`
|
||||
- `period_mode`
|
||||
- `period_mode_code`
|
||||
- `period_value`
|
||||
- `period_payload`
|
||||
|
||||
Run:
|
||||
```bash
|
||||
cargo test deterministic_submit_discovers_tq_lineloss_skill_contract -- --exact
|
||||
```
|
||||
|
||||
Expected: FAIL before the package is fully wired, PASS once the staged skill contract is discoverable and complete.
|
||||
|
||||
- [ ] **Step 6: Verify structural parity with `fault-details-report`**
|
||||
|
||||
Run a manual file-layout diff and confirm there are no placeholder descriptions or missing required docs.
|
||||
|
||||
- [ ] **Step 7: Commit**
|
||||
|
||||
```bash
|
||||
git add "D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/skills/tq-lineloss-report" "D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/scenes/tq-lineloss-report/scene.json"
|
||||
git commit -m "feat: scaffold tq lineloss staged skill contract"
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
### Task 2: Add browser-side JS red tests and implement the staged collector
|
||||
|
||||
**Files:**
|
||||
- Create: `D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/skills/tq-lineloss-report/scripts/collect_lineloss.js`
|
||||
- Create: `D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/skills/tq-lineloss-report/scripts/collect_lineloss.test.js`
|
||||
|
||||
- [ ] **Step 1: Write the failing JS tests first**
|
||||
|
||||
Cover deterministic pure helpers for:
|
||||
- missing normalized args -> blocked/error contract
|
||||
- month request shape uses `org_code` + canonical month payload
|
||||
- week request shape uses `org_code` + canonical week payload
|
||||
- artifact field names and counts
|
||||
- partial/error status shaping
|
||||
- no raw user-entered org text leakage into request fields
|
||||
|
||||
Example test skeleton:
|
||||
|
||||
```javascript
|
||||
const test = require('node:test');
|
||||
const assert = require('node:assert/strict');
|
||||
|
||||
const {
|
||||
validateArgs,
|
||||
buildMonthRequest,
|
||||
buildWeekRequest,
|
||||
normalizeRows,
|
||||
buildArtifact
|
||||
} = require('./collect_lineloss.js');
|
||||
|
||||
test('buildMonthRequest uses canonical org code and month payload', () => {
|
||||
const request = buildMonthRequest({
|
||||
org_code: 'ORG-1',
|
||||
period_payload: { year: 2026, month: 3 }
|
||||
});
|
||||
|
||||
assert.equal(request.orgCode, 'ORG-1');
|
||||
assert.equal(request.year, 2026);
|
||||
assert.equal(request.month, 3);
|
||||
});
|
||||
|
||||
test('buildArtifact locks field names and partial semantics', () => {
|
||||
const artifact = buildArtifact({
|
||||
org_label: '国网兰州供电公司',
|
||||
org_code: 'ORG-1',
|
||||
period_mode: 'month',
|
||||
period_mode_code: 'month',
|
||||
period_value: '2026-03',
|
||||
period_payload: { year: 2026, month: 3 },
|
||||
rows: [{ id: 1 }],
|
||||
status: 'partial',
|
||||
reasons: ['export_failed']
|
||||
});
|
||||
|
||||
assert.equal(artifact.report_name, 'tq-lineloss-report');
|
||||
assert.equal(artifact.org.code, 'ORG-1');
|
||||
assert.equal(artifact.period.value, '2026-03');
|
||||
assert.deepEqual(artifact.reasons, ['export_failed']);
|
||||
});
|
||||
```
|
||||
|
||||
- [ ] **Step 2: Run the JS test file to confirm failure**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
node --test "D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/skills/tq-lineloss-report/scripts/collect_lineloss.test.js"
|
||||
```
|
||||
|
||||
Expected: FAIL because the script/helpers do not exist yet.
|
||||
|
||||
- [ ] **Step 3: Write the minimal browser-side implementation**
|
||||
|
||||
Required structure:
|
||||
|
||||
```javascript
|
||||
function validateArgs(args) { /* require normalized canonical args */ }
|
||||
function buildMonthRequest(args) { /* build month request from canonical values */ }
|
||||
function buildWeekRequest(args) { /* build week request from canonical values */ }
|
||||
function normalizeRows(rawRows) { /* canonical columns only */ }
|
||||
function buildArtifact(input) { /* locked artifact shape */ }
|
||||
|
||||
return (async () => {
|
||||
const args = __SKILL_ARGS__;
|
||||
validateArgs(args);
|
||||
// validate page context
|
||||
// collect from page/API
|
||||
// normalize rows
|
||||
// optionally attempt export/report-log if the real business flow requires it
|
||||
return buildArtifact(result);
|
||||
})();
|
||||
```
|
||||
|
||||
Keep test exports behind an environment-safe guard so the file still works as browser-eval code.
|
||||
|
||||
- [ ] **Step 4: Re-run the JS tests until they pass**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
node --test "D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/skills/tq-lineloss-report/scripts/collect_lineloss.test.js"
|
||||
```
|
||||
|
||||
Expected: PASS.
|
||||
|
||||
- [ ] **Step 5: Commit**
|
||||
|
||||
```bash
|
||||
git add "D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/skills/tq-lineloss-report/scripts/collect_lineloss.js" "D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/skills/tq-lineloss-report/scripts/collect_lineloss.test.js"
|
||||
git commit -m "feat: add tq lineloss browser collection script"
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
### Task 3: Add deterministic suffix detection and explicit scene routing
|
||||
|
||||
**Files:**
|
||||
- Create: `src/compat/deterministic_submit.rs`
|
||||
- Modify: `src/compat/mod.rs`
|
||||
- Modify: `src/agent/mod.rs`
|
||||
- Create: `tests/deterministic_submit_test.rs`
|
||||
|
||||
- [ ] **Step 1: Write failing routing tests**
|
||||
|
||||
Add Rust tests for:
|
||||
- exact raw `。。。` suffix enables deterministic mode
|
||||
- no suffix leaves current routing untouched
|
||||
- suffix + unsupported deterministic request returns supported-scene prompt
|
||||
- when page URL/title context is available and does not match the lineloss scene, deterministic routing returns mismatch/block prompt instead of proceeding
|
||||
- Zhihu hotlist request without suffix keeps the current route
|
||||
- ASCII `...` does not trigger deterministic mode
|
||||
- `。。。。` does not trigger deterministic mode
|
||||
- `。。。` in the middle of the instruction does not trigger deterministic mode
|
||||
- trailing whitespace after `。。。` does not trigger deterministic mode in this slice
|
||||
|
||||
Suggested tests:
|
||||
|
||||
```rust
|
||||
#[test]
|
||||
fn deterministic_submit_requires_exact_suffix() {}
|
||||
|
||||
#[test]
|
||||
fn deterministic_submit_nonmatch_returns_supported_scene_message() {}
|
||||
|
||||
#[test]
|
||||
fn deterministic_submit_rejects_page_context_mismatch() {}
|
||||
|
||||
#[test]
|
||||
fn zhihu_hotlist_request_without_suffix_keeps_existing_route() {}
|
||||
|
||||
#[test]
|
||||
fn deterministic_submit_rejects_non_exact_suffix_variants() {}
|
||||
```
|
||||
|
||||
- [ ] **Step 2: Run the targeted routing tests and confirm failure**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
cargo test deterministic_submit_requires_exact_suffix -- --exact
|
||||
cargo test deterministic_submit_nonmatch_returns_supported_scene_message -- --exact
|
||||
cargo test zhihu_hotlist_request_without_suffix_keeps_existing_route -- --exact
|
||||
```
|
||||
|
||||
Expected: FAIL because the deterministic routing seam does not exist yet.
|
||||
|
||||
- [ ] **Step 3: Implement the narrow deterministic routing module**
|
||||
|
||||
Recommended public shape:
|
||||
|
||||
```rust
|
||||
pub enum DeterministicSubmitDecision {
|
||||
NotDeterministic,
|
||||
Prompt { summary: String },
|
||||
Execute(DeterministicExecutionPlan),
|
||||
}
|
||||
```
|
||||
|
||||
`src/agent/mod.rs` should:
|
||||
1. detect deterministic suffix
|
||||
2. if not deterministic, continue current flow untouched
|
||||
3. if prompt, return `TaskComplete`
|
||||
4. if execute, pass the plan into the browser-script execution seam
|
||||
|
||||
- [ ] **Step 4: Re-run the routing tests**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
cargo test deterministic_submit_requires_exact_suffix -- --exact
|
||||
cargo test deterministic_submit_nonmatch_returns_supported_scene_message -- --exact
|
||||
cargo test zhihu_hotlist_request_without_suffix_keeps_existing_route -- --exact
|
||||
```
|
||||
|
||||
Expected: PASS.
|
||||
|
||||
- [ ] **Step 5: Commit**
|
||||
|
||||
```bash
|
||||
git add src/compat/deterministic_submit.rs src/compat/mod.rs src/agent/mod.rs tests/deterministic_submit_test.rs
|
||||
git commit -m "feat: add deterministic submit routing seam"
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
### Task 4: Implement company/unit normalization from real source data
|
||||
|
||||
**Files:**
|
||||
- Create: `src/compat/tq_lineloss/mod.rs`
|
||||
- Create: `src/compat/tq_lineloss/contracts.rs`
|
||||
- Create: `src/compat/tq_lineloss/org_resolver.rs`
|
||||
- Create: `src/compat/tq_lineloss/org_units.rs`
|
||||
- Modify: `tests/deterministic_submit_test.rs`
|
||||
|
||||
- [ ] **Step 1: Write failing org resolver tests**
|
||||
|
||||
Cover:
|
||||
- `兰州公司` -> canonical `国网兰州供电公司` + correct code
|
||||
- `天水公司` -> canonical `国网天水供电公司` + correct code
|
||||
- `城关供电分公司` -> lower-level direct match
|
||||
- `榆中县公司` -> normalized county alias match
|
||||
- ambiguous alias prompts instead of guessing
|
||||
- missing company prompts instead of executing
|
||||
|
||||
Example skeleton:
|
||||
|
||||
```rust
|
||||
#[test]
|
||||
fn lineloss_org_resolver_matches_city_alias() {}
|
||||
|
||||
#[test]
|
||||
fn lineloss_org_resolver_matches_county_alias() {}
|
||||
|
||||
#[test]
|
||||
fn lineloss_org_resolver_prompts_on_ambiguity() {}
|
||||
```
|
||||
|
||||
- [ ] **Step 2: Run the org tests and confirm failure**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
cargo test lineloss_org_resolver_matches_city_alias -- --exact
|
||||
cargo test lineloss_org_resolver_matches_county_alias -- --exact
|
||||
cargo test lineloss_org_resolver_prompts_on_ambiguity -- --exact
|
||||
```
|
||||
|
||||
Expected: FAIL because the resolver and checked-in unit dictionary do not exist yet.
|
||||
|
||||
- [ ] **Step 3: Check in the canonical unit dictionary and implement alias resolution**
|
||||
|
||||
Rules:
|
||||
- derive data from the real source materials, not guessed literals
|
||||
- keep canonical `label` and `code`
|
||||
- generate normalized aliases from formal names
|
||||
- support both city-company and district/county/sub-company levels
|
||||
- require uniqueness before execution
|
||||
|
||||
- [ ] **Step 4: Implement explicit prompt messages**
|
||||
|
||||
Examples:
|
||||
- `已命中台区线损报表技能，但缺少供电单位，请补充如“兰州公司”或“城关供电分公司”。`
|
||||
- `已命中台区线损报表技能，但供电单位存在歧义，请补充更完整名称。`
|
||||
|
||||
- [ ] **Step 5: Re-run the org tests**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
cargo test lineloss_org_resolver_matches_city_alias -- --exact
|
||||
cargo test lineloss_org_resolver_matches_county_alias -- --exact
|
||||
cargo test lineloss_org_resolver_prompts_on_ambiguity -- --exact
|
||||
```
|
||||
|
||||
Expected: PASS.
|
||||
|
||||
- [ ] **Step 6: Commit**
|
||||
|
||||
```bash
|
||||
git add src/compat/tq_lineloss/mod.rs src/compat/tq_lineloss/contracts.rs src/compat/tq_lineloss/org_resolver.rs src/compat/tq_lineloss/org_units.rs tests/deterministic_submit_test.rs
|
||||
git commit -m "feat: add tq lineloss org normalization"
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
### Task 5: Implement period extraction and canonical payload building
|
||||
|
||||
**Files:**
|
||||
- Create: `src/compat/tq_lineloss/period_resolver.rs`
|
||||
- Modify: `src/compat/tq_lineloss/mod.rs`
|
||||
- Modify: `tests/deterministic_submit_test.rs`
|
||||
|
||||
- [ ] **Step 1: Write failing period resolver tests**
|
||||
|
||||
Cover:
|
||||
- `月累计 2026-03`
|
||||
- `月累计 2026年3月`
|
||||
- `周累计 2026年第12周`
|
||||
- contradictory month/week expressions prompt
|
||||
- missing mode prompts
|
||||
- missing period prompts
|
||||
- bare `第12周` prompts for year in this slice
|
||||
- real backend month/week mode codes and request payload field names are derived from source materials instead of placeholder values
|
||||
|
||||
Example skeleton:
|
||||
|
||||
```rust
|
||||
#[test]
|
||||
fn lineloss_period_resolver_parses_month_text() {}
|
||||
|
||||
#[test]
|
||||
fn lineloss_period_resolver_parses_week_text() {}
|
||||
|
||||
#[test]
|
||||
fn lineloss_period_resolver_prompts_for_missing_year_on_week() {}
|
||||
|
||||
#[test]
|
||||
fn lineloss_period_resolver_rejects_contradictory_mode() {}
|
||||
```
|
||||
|
||||
- [ ] **Step 2: Run the period tests and confirm failure**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
cargo test lineloss_period_resolver_parses_month_text -- --exact
|
||||
cargo test lineloss_period_resolver_parses_week_text -- --exact
|
||||
cargo test lineloss_period_resolver_prompts_for_missing_year_on_week -- --exact
|
||||
cargo test lineloss_period_resolver_rejects_contradictory_mode -- --exact
|
||||
```
|
||||
|
||||
Expected: FAIL because the period resolver does not exist yet.
|
||||
|
||||
- [ ] **Step 3: Implement the minimal resolver**
|
||||
|
||||
Output contract:
|
||||
|
||||
```rust
|
||||
pub struct ResolvedPeriod {
|
||||
pub mode: PeriodMode,
|
||||
pub mode_code: String,
|
||||
pub value: String,
|
||||
pub payload: serde_json::Value,
|
||||
}
|
||||
```
|
||||
|
||||
Rules:
|
||||
- no page-default fallback
|
||||
- no implicit current-year assumptions
|
||||
- no mixed month/week execution
|
||||
|
||||
- [ ] **Step 4: Re-run the period tests**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
cargo test lineloss_period_resolver_parses_month_text -- --exact
|
||||
cargo test lineloss_period_resolver_parses_week_text -- --exact
|
||||
cargo test lineloss_period_resolver_prompts_for_missing_year_on_week -- --exact
|
||||
cargo test lineloss_period_resolver_rejects_contradictory_mode -- --exact
|
||||
```
|
||||
|
||||
Expected: PASS.
|
||||
|
||||
- [ ] **Step 5: Commit**
|
||||
|
||||
```bash
|
||||
git add src/compat/tq_lineloss/period_resolver.rs src/compat/tq_lineloss/mod.rs tests/deterministic_submit_test.rs
|
||||
git commit -m "feat: add tq lineloss period normalization"
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
### Task 6: Wire deterministic execution through the existing browser-script seam
|
||||
|
||||
**Files:**
|
||||
- Modify: `src/compat/deterministic_submit.rs`
|
||||
- Modify: `src/agent/mod.rs`
|
||||
- Modify if needed: `src/compat/direct_skill_runtime.rs`
|
||||
- Modify: `tests/deterministic_submit_test.rs`
|
||||
- Modify: `tests/compat_runtime_test.rs`
|
||||
|
||||
- [ ] **Step 1: Write failing execution tests**
|
||||
|
||||
Cover:
|
||||
- successful deterministic lineloss request builds canonical tool args
|
||||
- missing company/mode/period returns prompt without browser execution
|
||||
- `partial` artifact maps to successful partial summary
|
||||
- `blocked` and `error` artifacts map to failed completion
|
||||
|
||||
Example skeleton:
|
||||
|
||||
```rust
|
||||
#[test]
|
||||
fn deterministic_lineloss_execution_passes_canonical_args() {}
|
||||
|
||||
#[test]
|
||||
fn deterministic_lineloss_missing_company_does_not_invoke_browser() {}
|
||||
|
||||
#[test]
|
||||
fn deterministic_lineloss_partial_artifact_maps_to_partial_summary() {}
|
||||
```
|
||||
|
||||
- [ ] **Step 2: Run the execution tests and confirm failure**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
cargo test deterministic_lineloss_execution_passes_canonical_args -- --exact
|
||||
cargo test deterministic_lineloss_missing_company_does_not_invoke_browser -- --exact
|
||||
cargo test deterministic_lineloss_partial_artifact_maps_to_partial_summary -- --exact
|
||||
```
|
||||
|
||||
Expected: FAIL because the deterministic execution plan is not wired yet.
|
||||
|
||||
- [ ] **Step 3: Implement execution via the existing `browser_script` seam**
|
||||
|
||||
Build tool args only from normalized values:
|
||||
- `expected_domain`
|
||||
- `org_label`
|
||||
- `org_code`
|
||||
- `period_mode`
|
||||
- `period_mode_code`
|
||||
- `period_value`
|
||||
- `period_payload`
|
||||
|
||||
Resolve the tool explicitly to:
|
||||
- `tq-lineloss-report.collect_lineloss`
|
||||
|
||||
Do not introduce a new browser opcode family or second browser protocol.
|
||||
|
||||
- [ ] **Step 4: Implement central artifact interpretation**
|
||||
|
||||
Recommended helper:
|
||||
|
||||
```rust
|
||||
fn summarize_lineloss_artifact(artifact: &serde_json::Value) -> (bool, String)
|
||||
```
|
||||
|
||||
Summary must include canonical org/period and row counts, and surface blocked/partial/error reasons.
|
||||
|
||||
- [ ] **Step 5: Re-run the execution tests**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
cargo test deterministic_lineloss_execution_passes_canonical_args -- --exact
|
||||
cargo test deterministic_lineloss_missing_company_does_not_invoke_browser -- --exact
|
||||
cargo test deterministic_lineloss_partial_artifact_maps_to_partial_summary -- --exact
|
||||
```
|
||||
|
||||
Expected: PASS.
|
||||
|
||||
- [ ] **Step 6: Commit**
|
||||
|
||||
```bash
|
||||
git add src/compat/deterministic_submit.rs src/agent/mod.rs src/compat/direct_skill_runtime.rs tests/deterministic_submit_test.rs tests/compat_runtime_test.rs
|
||||
git commit -m "feat: execute deterministic tq lineloss skill through browser script seam"
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
### Task 7: Add Zhihu regression coverage and run the full verification set
|
||||
|
||||
**Files:**
|
||||
- Modify: `tests/compat_runtime_test.rs`
|
||||
- Modify only if required: `tests/runtime_task_flow_test.rs`
|
||||
- Reuse: `tests/deterministic_submit_test.rs`
|
||||
|
||||
- [ ] **Step 1: Add focused Zhihu regression tests**
|
||||
|
||||
Required assertions:
|
||||
- ordinary Zhihu hotlist requests without `。。。` still use the current path
|
||||
- existing export/presentation requests still preserve their current behavior
|
||||
- deterministic suffix does not silently route unmatched requests into Zhihu logic
|
||||
- an existing non-lineloss direct `browser_script` path outside the new scene still behaves unchanged
|
||||
|
||||
- [ ] **Step 2: Add end-to-end deterministic submit coverage**
|
||||
|
||||
Required assertions:
|
||||
- suffix detection
|
||||
- scene match
|
||||
- page-context mismatch prompt/block behavior when URL/title contradict the lineloss scene
|
||||
- missing/ambiguous prompts
|
||||
- canonical args passed to the browser-script tool
|
||||
- returned summary shows canonical org and period
|
||||
- execution stays on the existing pipe-backed browser-script seam with no ws-only dependency introduced on `main`
|
||||
|
||||
- [ ] **Step 3: Run the focused Rust tests**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
cargo test --test deterministic_submit_test
|
||||
cargo test --test compat_runtime_test
|
||||
cargo test --test runtime_task_flow_test
|
||||
```
|
||||
|
||||
Expected: PASS.
|
||||
|
||||
- [ ] **Step 4: Run the whole Rust suite**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
cargo test
|
||||
```
|
||||
|
||||
Expected: PASS.
|
||||
|
||||
- [ ] **Step 5: Re-run the staged skill JS tests**
|
||||
|
||||
Run:
|
||||
```bash
|
||||
node --test "D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/skills/tq-lineloss-report/scripts/collect_lineloss.test.js"
|
||||
```
|
||||
|
||||
Expected: PASS.
|
||||
|
||||
- [ ] **Step 6: Commit**
|
||||
|
||||
```bash
|
||||
git add tests/deterministic_submit_test.rs tests/compat_runtime_test.rs tests/runtime_task_flow_test.rs
|
||||
git commit -m "test: cover deterministic tq lineloss routing and zhihu regression"
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Final verification checklist
|
||||
|
||||
- [ ] `。。。` is the only deterministic trigger.
|
||||
- [ ] Non-`。。。` requests preserve current routing.
|
||||
- [ ] Deterministic page-context mismatch blocks or mismatches before execution when URL/title contradict the lineloss scene.
|
||||
- [ ] Zhihu hotlist behavior is unchanged.
|
||||
- [ ] Existing non-lineloss direct `browser_script` behavior is unchanged.
|
||||
- [ ] Deterministic non-match returns an explicit supported-scene message.
|
||||
- [ ] Missing company prompts.
|
||||
- [ ] Ambiguous company prompts.
|
||||
- [ ] Missing mode prompts.
|
||||
- [ ] Missing period prompts.
|
||||
- [ ] Bare `第12周` prompts for year.
|
||||
- [ ] Canonical org code is passed to the staged skill.
|
||||
- [ ] Canonical period mode code and payload are passed to the staged skill.
|
||||
- [ ] The staged skill returns the locked artifact shape.
|
||||
- [ ] Execution uses the existing `browser_script` seam only.
|
||||
- [ ] No ws-specific runtime dependency is added on `main`.
|
||||
|
||||
## Implementation notes
|
||||
|
||||
- Prefer extracting a tiny shared execution helper from `src/compat/direct_skill_runtime.rs` if needed instead of duplicating tool lookup or browser-script invocation code.
|
||||
- Keep deterministic whitelist configuration in one place, but do not expand this slice into a full general scene-registry redesign.
|
||||
- If a failing test suggests changing Zhihu behavior, fix the deterministic branch or test harness instead of weakening the existing Zhihu path.
|
||||
- The checked-in unit dictionary is part of the deterministic contract; treat updates to that data as explicit behavior changes and cover them with tests.
|
||||
@@ -0,0 +1,125 @@
|
||||
# Config-Owned Direct Skill Dispatch Design
|
||||
|
||||
**Goal:** Preserve the current minimal submit flow where sgClaw accepts natural-language input, directly invokes one configured staged browser skill without calling an LLM, and keeps dispatch ownership in sgClaw configuration rather than external skill metadata.
|
||||
|
||||
**Status:** Approved design direction for the next slice. The current minimal direct-submit path already works; this document records the ownership boundary that future dispatch-policy work should follow.
|
||||
|
||||
---
|
||||
|
||||
## Decision Summary
|
||||
|
||||
1. Keep direct-skill selection in sgClaw configuration.
|
||||
2. Continue using `skillsDir` plus `directSubmitSkill` as the only control surface for the no-LLM direct path.
|
||||
3. Do not add sgClaw-specific dispatch fields to files under `D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging` in this slice.
|
||||
4. Keep the currently bound skill as `fault-details-report.collect_fault_details`.
|
||||
5. When dispatch expands beyond one fixed skill, add the next policy layer on the sgClaw side first, not in `scene.json` or `SKILL.toml`.
|
||||
|
||||
---
|
||||
|
||||
## Current Minimal Flow
|
||||
|
||||
The intended user experience stays unchanged:
|
||||
- the user types natural language into the input box
|
||||
- sgClaw receives `BrowserMessage::SubmitTask`
|
||||
- sgClaw loads runtime config
|
||||
- if `directSubmitSkill` is configured, sgClaw bypasses LLM routing and directly resolves the configured staged skill from `skillsDir`
|
||||
- sgClaw executes the target `browser_script` tool through the browser runtime and returns the result
|
||||
- if `directSubmitSkill` is absent, sgClaw falls back to the existing orchestration / compat behavior
|
||||
|
||||
This keeps the first slice small while preserving a clear seam for future expansion.
|
||||
|
||||
---
|
||||
|
||||
## Ownership Boundary
|
||||
|
||||
### sgClaw configuration owns dispatch choice
|
||||
|
||||
sgClaw configuration is responsible for deciding whether submit-task should bypass the LLM path and which direct skill should run.
|
||||
|
||||
For the current slice, that means:
|
||||
- `skillsDir` tells sgClaw where to load staged skills from
|
||||
- `directSubmitSkill` tells sgClaw which `skill.tool` should be used for the direct path
|
||||
|
||||
Example:
|
||||
|
||||
```json
|
||||
{
|
||||
"skillsDir": "D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging",
|
||||
"directSubmitSkill": "fault-details-report.collect_fault_details"
|
||||
}
|
||||
```
|
||||
|
||||
### skill_staging owns skill identity and execution assets
|
||||
|
||||
Files under `D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging` remain responsible for describing the skill package, tool identity, and browser-script implementation.
|
||||
|
||||
For the current bound skill:
|
||||
- `D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/scenes/fault-details-report/scene.json`
|
||||
- `D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/skills/fault-details-report/SKILL.toml`
|
||||
- `D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/skills/fault-details-report/scripts/collect_fault_details.js`
|
||||
|
||||
These files already provide enough information for sgClaw to locate the package and run the tool. This slice does not add a new dispatch field inside them.
|
||||
|
||||
---
|
||||
|
||||
## Why This Boundary Is Recommended
|
||||
|
||||
### One source of truth for routing
|
||||
|
||||
If sgClaw configuration owns the direct-skill decision, the operator can switch the direct skill by changing config only. There is no need to edit code and no need to mutate external skill assets just to change routing.
|
||||
|
||||
### Avoid freezing external manifest semantics too early
|
||||
|
||||
`skill_staging` is an external skill asset set. Adding sgClaw-specific dispatch metadata now would couple the staged-skill format to one integration strategy before the policy model is stable.
|
||||
|
||||
### Preserve a clean migration path
|
||||
|
||||
The current minimal path is intentionally narrow: one fixed configured direct skill, no LLM dispatch, no per-skill policy registry yet. Keeping dispatch control in sgClaw makes it easier to add a broader policy layer later without rewriting the staged-skill package format first.
|
||||
|
||||
---
|
||||
|
||||
## Explicit Non-Goals
|
||||
|
||||
This design does not do the following:
|
||||
- redesign the submit-task protocol
|
||||
- move dispatch control into `scene.json` or `SKILL.toml`
|
||||
- require every staged skill to declare `direct_browser` or `llm_agent` right now
|
||||
- expand the current direct path into generic natural-language intent classification
|
||||
- change the browser-script execution model
|
||||
- change the current fallback orchestration / compat execution semantics when `directSubmitSkill` is not configured
|
||||
|
||||
---
|
||||
|
||||
## Current Skill Contract
|
||||
|
||||
The current direct path remains intentionally deterministic.
|
||||
|
||||
For `fault-details-report.collect_fault_details`, sgClaw derives only the minimum required arguments:
|
||||
- `expected_domain` from the current `page_url`
|
||||
- `period` from an explicit `YYYY-MM` token in the user's natural-language input
|
||||
|
||||
That means the UX still looks like natural-language submission, but the runtime does not ask an LLM to infer intent or invent missing parameters. If the period is missing, sgClaw should return a clear error instead of guessing.
|
||||
|
||||
---
|
||||
|
||||
## Future Dispatch Policy Direction
|
||||
|
||||
When more than one staged skill needs routing control, the next layer should still begin on the sgClaw side.
|
||||
|
||||
Recommended direction:
|
||||
- keep `directSubmitSkill` as the current bootstrap switch for the minimal fixed-skill path
|
||||
- introduce a sgClaw-owned registry or config mapping that can later express `skill.tool -> direct_browser | llm_agent`
|
||||
- keep external skill manifests unchanged until the policy surface proves stable in real use
|
||||
|
||||
Only after the routing model is stable should we consider whether external skill metadata needs a default dispatch hint.
|
||||
|
||||
---
|
||||
|
||||
## Resulting Design Rule
|
||||
|
||||
For this project, the direct-skill decision remains config-owned:
|
||||
- sgClaw config decides whether submit-task bypasses the LLM path
|
||||
- staged skill metadata identifies what the skill is and how its browser tool runs
|
||||
- future per-skill dispatch policy should be added in sgClaw first, not in `skill_staging`
|
||||
|
||||
This is the approved baseline for the next dispatch-policy slice.
|
||||
@@ -0,0 +1,495 @@
|
||||
# Fault Details Full Skill Alignment Design
|
||||
|
||||
**Goal:** Upgrade `fault-details-report.collect_fault_details` from an empty artifact shell into a real staged business skill that matches the original fault-details package's collection, normalization, summary, export, and report-history behavior, while keeping direct-skill routing config-owned in `claw-new`.
|
||||
|
||||
**Status:** Approved design direction for the next remediation slice.
|
||||
|
||||
---
|
||||
|
||||
## Decision Summary
|
||||
|
||||
1. Keep direct-skill selection in `claw-new` via `skillsDir` + `directSubmitSkill`; do not move dispatch ownership into `skill_staging` manifests.
|
||||
2. Put the fault-details business logic in `D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging`, not in `claw-new`.
|
||||
3. Align the staged skill with the original package's real behavior: query raw rows, normalize detail columns, derive summary rows, call localhost export, and write report history.
|
||||
4. Keep the current browser-execution seam narrow: use the existing `browser_script` / browser-eval path, not a new browser protocol or new opcodes.
|
||||
5. Add a narrow artifact interpreter in `claw-new` so structured fault-results map cleanly to `TaskComplete.success` and a readable completion summary.
|
||||
|
||||
---
|
||||
|
||||
## Why This Slice Exists
|
||||
|
||||
The current staged skill contract and the current staged skill implementation do not match.
|
||||
|
||||
### What the original package actually does
|
||||
|
||||
The original package under `D:/desk/智能体资料/大四区报告监测项/故障明细` does all of the following:
|
||||
|
||||
- reads the selected date range from the page UI
|
||||
- queries the D4 repair-order data source
|
||||
- filters and normalizes raw rows into the canonical detail export schema
|
||||
- derives grouped summary rows by `gds`
|
||||
- calls `http://localhost:13313/SurfaceServices/personalBread/export/faultDetailsExportXLSXS`
|
||||
- auto-opens/downloads the generated file
|
||||
- writes report history through `http://localhost:13313/ReportServices/Api/setReportLog`
|
||||
|
||||
### What the staged skill currently does
|
||||
|
||||
The current staged `collect_fault_details.js` only returns an empty `report-artifact` shell with empty `rows` and empty summary `sections`.
|
||||
|
||||
It also still uses a Node-style export shape instead of the browser-eval entrypoint shape that the current `browser_script` runtime expects. In practice, this means the staged script is not yet aligned with the real runtime contract even before business behavior is considered.
|
||||
|
||||
This slice closes that gap by making the staged skill actually perform the work the original package performs, but through the current sgClaw direct-skill runtime.
|
||||
|
||||
---
|
||||
|
||||
## Design Rules
|
||||
|
||||
### 1. `claw-new` owns routing, not business transforms
|
||||
|
||||
`claw-new` stays responsible for:
|
||||
|
||||
- loading config
|
||||
- deciding whether submit-task takes the direct-skill path
|
||||
- resolving the configured staged skill
|
||||
- executing the staged browser-script tool
|
||||
- turning the returned artifact into `TaskComplete.success` + human-readable summary
|
||||
|
||||
`claw-new` must **not** become the place where the original fault classification table, detail-row field mapping, or summary aggregation rules are reimplemented.
|
||||
|
||||
### 2. `skill_staging` owns fault-details business behavior
|
||||
|
||||
The staged skill package owns:
|
||||
|
||||
- query orchestration inside the browser page context
|
||||
- raw-row extraction
|
||||
- canonical detail-row normalization
|
||||
- classification and derived fields
|
||||
- summary-sheet derivation
|
||||
- localhost export request
|
||||
- localhost report-log request
|
||||
- structured result payload
|
||||
|
||||
### 3. Keep the current browser seam narrow
|
||||
|
||||
Do not introduce a new browser bridge, callback protocol, or skill-specific browser opcode for this slice.
|
||||
|
||||
The implementation should continue using the current `browser_script` execution seam already wired through `claw-new/src/compat/browser_script_skill_tool.rs` and `claw-new/src/compat/direct_skill_runtime.rs`.
|
||||
|
||||
### 4. Match business behavior, not the original shell verbatim
|
||||
|
||||
The original package is a local HTML/Vue shell that uses `BrowserAction(...)`, timers, and hidden-browser choreography. That shell does **not** need to be recreated inside `claw-new`.
|
||||
|
||||
What must be preserved is the business outcome:
|
||||
|
||||
- same canonical detail columns
|
||||
- same key field mappings
|
||||
- same classification rules
|
||||
- same summary metrics
|
||||
- same downstream export/history behavior
|
||||
- same distinction between empty, partial, blocked, and failed work
|
||||
|
||||
---
|
||||
|
||||
## Ownership Boundary and Landing Zones
|
||||
|
||||
### Staged skill changes
|
||||
|
||||
These changes land in `D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging`.
|
||||
|
||||
Primary files:
|
||||
|
||||
- `skills/fault-details-report/scripts/collect_fault_details.js`
|
||||
- becomes the real browser-eval entrypoint
|
||||
- must directly `return` the final structured artifact from the wrapped browser script
|
||||
- may contain internal helper functions, but should remain self-contained for the current runtime
|
||||
- `skills/fault-details-report/SKILL.toml`
|
||||
- keep `browser_script`
|
||||
- tighten the tool description so it matches the real behavior
|
||||
- do not turn `SKILL.toml` into the source of truth for classification rules or routing policy
|
||||
- `skills/fault-details-report/SKILL.md`
|
||||
- align the written contract with the implemented runtime behavior
|
||||
- `skills/fault-details-report/references/collection-flow.md`
|
||||
- align the staged flow with the implemented query/export/history sequence
|
||||
- `skills/fault-details-report/references/data-quality.md`
|
||||
- stay authoritative for canonical columns, required fields, classification tables, `qxxcjl`-based reason heuristics, summary rules, and partial semantics
|
||||
- `scenes/fault-details-report/scene.json`
|
||||
- keep the scene contract aligned with the actual output and state semantics
|
||||
- do not move classification or routing policy into scene metadata
|
||||
|
||||
### Caller/runtime changes
|
||||
|
||||
These changes land in `D:/data/ideaSpace/rust/sgClaw/claw-new`.
|
||||
|
||||
Primary files:
|
||||
|
||||
- `src/compat/direct_skill_runtime.rs`
|
||||
- keep configured direct-skill execution here
|
||||
- add narrow structured-artifact interpretation after the browser-script returns
|
||||
- `src/agent/mod.rs`
|
||||
- keep the current direct-submit routing seam here
|
||||
- do not add fault-specific business logic here
|
||||
- `src/compat/browser_script_skill_tool.rs`
|
||||
- keep the browser-script contract strict: browser-eval entrypoint, no Node-only assumptions
|
||||
- `tests/agent_runtime_test.rs`
|
||||
- direct-submit path and result-surface regressions
|
||||
- `tests/browser_script_skill_tool_test.rs`
|
||||
- browser-script execution-shape regressions
|
||||
|
||||
If a new helper is needed in `claw-new`, it should be a narrow artifact-format/parser helper, not a new business-rules module.
|
||||
|
||||
---
|
||||
|
||||
## Target Runtime Flow
|
||||
|
||||
### Step 1: Submit-task stays config-owned
|
||||
|
||||
The user still types natural language into the current sgClaw input.
|
||||
|
||||
`claw-new`:
|
||||
|
||||
- receives `BrowserMessage::SubmitTask`
|
||||
- loads `SgClawSettings`
|
||||
- sees `directSubmitSkill = "fault-details-report.collect_fault_details"`
|
||||
- bypasses LLM routing exactly as it does now
|
||||
- resolves the staged skill from `skillsDir`
|
||||
|
||||
This preserves the already approved config-owned routing boundary.
|
||||
|
||||
### Step 2: Browser-script tool executes as a true browser entrypoint
|
||||
|
||||
`collect_fault_details.js` must be shaped for the current runtime:
|
||||
|
||||
- the script runs inside the current browser page context through `eval`
|
||||
- it must not rely on `module.exports`
|
||||
- it must directly `return collectFaultDetails(args)` from the wrapped script body
|
||||
|
||||
This is required because the current sgClaw browser-script runtime reads one script file and wraps it in a browser-side IIFE.
|
||||
|
||||
### Step 3: The skill reads the page-selected time range
|
||||
|
||||
The source-of-truth query window should come from the current page state, matching the original package behavior.
|
||||
|
||||
Design rule:
|
||||
|
||||
- read the selected start and end time from the business page controls or page state
|
||||
- include that exact selected range in the returned artifact
|
||||
- keep `period` as a bootstrap label from `claw-new`, not as a license to silently guess a different business range
|
||||
|
||||
Compatibility rule with the current direct-submit seam:
|
||||
|
||||
- the current `claw-new` direct path still requires an explicit `YYYY-MM` token in the user's instruction in order to enter the configured direct-skill flow
|
||||
- that requirement remains in place for this slice
|
||||
- once inside the skill, the browser page's selected start/end range is the source of truth for collection
|
||||
- the returned artifact should include both the user-visible `period` label and the exact selected page range so mismatches are observable instead of hidden
|
||||
|
||||
If the page-selected range cannot be read reliably, the skill should return `blocked` instead of inventing a month-wide query window from `period` alone.
|
||||
|
||||
### Step 4: The skill collects raw rows and normalizes detail fields
|
||||
|
||||
The staged skill must reproduce the original package's detail normalization logic inside the browser-executed script.
|
||||
|
||||
That includes preserving the canonical detail schema from the original `excleIni[0].cols`, including the key transforms already present in the original package, such as:
|
||||
|
||||
- `slsj = bxsj`
|
||||
- `gssgs = "甘肃省电力公司"`
|
||||
- `sgs` derived from the current company/city context
|
||||
- `gddw = maintOrgName`
|
||||
- `gds = maintGroupName`
|
||||
- `clzt = "处理完成"`
|
||||
- `bdz = bdzMc`
|
||||
- `line = xlmc10`
|
||||
- `pb = byqmc`
|
||||
|
||||
The staged skill must also port the original classification/derivation logic that fills:
|
||||
|
||||
- `sxfl1`
|
||||
- `sxfl2`
|
||||
- `sxfl3`
|
||||
- `gzsb`
|
||||
- `gzyy`
|
||||
|
||||
That includes the original matching table and the `qxxcjl`-based text extraction heuristics that derive the fault reason.
|
||||
|
||||
### Step 5: The skill derives summary rows from normalized detail rows
|
||||
|
||||
The staged skill must derive the summary sheet from grouped detail rows, keyed around the same business totals the original package computes.
|
||||
|
||||
At minimum that includes:
|
||||
|
||||
- `index`
|
||||
- `gsName`
|
||||
- `fwDept`
|
||||
- `className`
|
||||
- `allCount`
|
||||
- `wxCount`
|
||||
- `khcCount`
|
||||
- `sbdSbCount`
|
||||
- `gyGzCount`
|
||||
- `dyGzCount`
|
||||
- `tqdzCount`
|
||||
- `tqbxCount`
|
||||
- `dyxlCount`
|
||||
- `bqxCount`
|
||||
- `jllCount`
|
||||
- `bhxCount`
|
||||
- `qftdCount`
|
||||
|
||||
The summary derivation must stay in the staged skill so the same package can later be routed by LLM without moving business logic back into `claw-new`.
|
||||
|
||||
### Step 6: The skill performs downstream export and report logging
|
||||
|
||||
After detail rows and summary rows are available, the staged skill should reproduce the original package's downstream behavior:
|
||||
|
||||
- build the export payload for `faultDetailsExportXLSXS`
|
||||
- call the localhost export endpoint
|
||||
- capture the returned export path/URL
|
||||
- write report history via `setReportLog`
|
||||
|
||||
Important boundary:
|
||||
|
||||
- export/report-log are downstream side effects
|
||||
- they do not redefine whether collection itself succeeded
|
||||
- if collection succeeds but export/logging fails, the result is `partial`, not a full collection failure
|
||||
- auto-opening/downloading the exported file is out of scope for this slice; this slice records the export path/result in the artifact but does not add new opener/UI behavior in `claw-new`
|
||||
|
||||
### Step 7: The skill returns one structured artifact
|
||||
|
||||
The staged skill should return one self-describing JSON artifact containing:
|
||||
|
||||
- business identity (`type`, `report_name`)
|
||||
- selected period label
|
||||
- exact selected start/end range
|
||||
- canonical detail columns + normalized rows
|
||||
- summary section columns + rows
|
||||
- counts
|
||||
- business status
|
||||
- partial reasons if any
|
||||
- downstream export outcome
|
||||
- downstream report-log outcome
|
||||
|
||||
### Step 8: `claw-new` interprets the artifact, not the business rules
|
||||
|
||||
After the browser-script returns, `claw-new` should parse the JSON artifact and map it into final submit-task behavior.
|
||||
|
||||
Recommended mapping:
|
||||
|
||||
- `status = ok` -> `TaskComplete.success = true`
|
||||
- `status = partial` -> `TaskComplete.success = true`, with warnings in summary
|
||||
- `status = empty` -> `TaskComplete.success = true`, clearly reported as empty-result
|
||||
- `status = blocked` -> `TaskComplete.success = false`
|
||||
- `status = error` -> `TaskComplete.success = false`
|
||||
|
||||
This keeps business classification in the staged skill while preventing false-positive success in the direct path.
|
||||
|
||||
---
|
||||
|
||||
## Artifact Contract
|
||||
|
||||
The returned payload should stay `type = "report-artifact"`, but it must become rich enough to describe the real run.
|
||||
|
||||
Recommended contract:
|
||||
|
||||
```json
|
||||
{
|
||||
"type": "report-artifact",
|
||||
"report_name": "fault-details-report",
|
||||
"period": "2026-03",
|
||||
"selected_range": {
|
||||
"start": "2026-03-08 16:00:00",
|
||||
"end": "2026-03-09 16:00:00"
|
||||
},
|
||||
"columns": ["qxdbh", "gssgs", "sgs", "gddw", "gds", "slsj", "yjflMc", "ejflMc", "sjflMc", "gzms", "yhbh", "yhmc", "lxr", "gzdd", "lxdh", "bxsj", "gdsj", "clzt", "qxxcjl", "bdz", "line", "pb", "sxfl1", "sxfl2", "sxfl3", "gzsb", "gzyy", "bz"],
|
||||
"rows": [],
|
||||
"sections": [
|
||||
{
|
||||
"name": "summary-sheet",
|
||||
"columns": ["index", "gsName", "fwDept", "className", "allCount", "wxCount", "khcCount", "sbdSbCount", "gyGzCount", "dyGzCount", "tqdzCount", "tqbxCount", "dyxlCount", "bqxCount", "jllCount", "bhxCount", "qftdCount"],
|
||||
"rows": []
|
||||
}
|
||||
],
|
||||
"counts": {
|
||||
"detail_rows": 0,
|
||||
"summary_rows": 0
|
||||
},
|
||||
"status": "ok",
|
||||
"partial_reasons": [],
|
||||
"downstream": {
|
||||
"export": {
|
||||
"attempted": true,
|
||||
"success": true,
|
||||
"path": "http://localhost:13313/.../fault-details.xlsx"
|
||||
},
|
||||
"report_log": {
|
||||
"attempted": true,
|
||||
"success": true,
|
||||
"report_name": "国网XX故障报修明细表(03月09日)",
|
||||
"path": "http://localhost:13313/.../fault-details.xlsx"
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
### Contract notes
|
||||
|
||||
- `rows` is the canonical returned detail table, not the export-service transport payload.
|
||||
- If the export service still requires a placeholder row for an empty spreadsheet, that placeholder should be synthesized only for the downstream export call, not as the canonical returned `rows` contract.
|
||||
- `counts` should be computed from the canonical returned tables.
|
||||
- `selected_range`, `columns`, `sections`, `counts`, `status`, and `partial_reasons` should always be present for `ok`, `partial`, and `empty`.
|
||||
- For `blocked` and `error`, the artifact should still include `type`, `report_name`, `period`, `status`, and `partial_reasons`; `selected_range`, `columns`, `sections`, and `counts` should be included whenever they were already known before the failure point.
|
||||
- `downstream` should be omitted only when export/report-log were not attempted yet; otherwise include it with `attempted` / `success` flags and any available path or failure detail.
|
||||
|
||||
---
|
||||
|
||||
## Error Handling and Status Semantics
|
||||
|
||||
### `ok`
|
||||
|
||||
Use `ok` when all of the following are true:
|
||||
|
||||
- raw collection succeeded
|
||||
- required detail-field normalization succeeded
|
||||
- summary derivation succeeded
|
||||
- export succeeded
|
||||
- report-log write succeeded
|
||||
|
||||
### `partial`
|
||||
|
||||
Use `partial` when detail collection succeeded but at least one downstream stage degraded, including:
|
||||
|
||||
- one or more required fields could not be normalized, but the row set still remains exportable and summary derivation can proceed with explicit gaps recorded
|
||||
- summary derivation was incomplete, but the detail table is still available
|
||||
- export failed after rows were available
|
||||
- report-log write failed after rows/export were available
|
||||
|
||||
Escalation rule:
|
||||
|
||||
- if the raw query succeeds but required fields are missing so broadly that the canonical detail table cannot be produced at all, use `error`, not `partial`
|
||||
- if summary derivation cannot even start because the normalized detail rows are structurally unusable, use `error`, not `partial`
|
||||
|
||||
`partial_reasons` must name the degraded stage instead of hiding it.
|
||||
|
||||
### `empty`
|
||||
|
||||
Use `empty` when:
|
||||
|
||||
- the query succeeds for the selected range
|
||||
- zero real detail rows match
|
||||
|
||||
This is not a failure.
|
||||
|
||||
If the business flow still wants an empty export file or placeholder export payload, that happens downstream without changing the semantic meaning of the result.
|
||||
|
||||
### `blocked`
|
||||
|
||||
Use `blocked` when the page/session preconditions are not met, for example:
|
||||
|
||||
- expected page/session is not available
|
||||
- required page controls cannot be read
|
||||
- login/session state is missing or expired
|
||||
- required browser-visible APIs are unavailable in the current page context
|
||||
|
||||
### `error`
|
||||
|
||||
Use `error` when the run starts but fails due to operational or parsing problems, for example:
|
||||
|
||||
- request failure
|
||||
- page script failure
|
||||
- raw response parse failure
|
||||
- malformed export response
|
||||
|
||||
### `claw-new` completion mapping
|
||||
|
||||
`claw-new` should convert structured status into final submit completion behavior:
|
||||
|
||||
- `ok` / `partial` / `empty`: return a success completion with a concise human summary
|
||||
- `blocked` / `error`: return a failed completion with a concise human summary
|
||||
|
||||
This avoids the current risk where a structured error-like payload could still be surfaced as a nominal success string.
|
||||
|
||||
---
|
||||
|
||||
## Testing and Acceptance Strategy
|
||||
|
||||
### Skill-side deterministic coverage
|
||||
|
||||
Add deterministic coverage around the staged skill's business logic in `skill_staging` for:
|
||||
|
||||
- canonical detail field mapping
|
||||
- classification table parity
|
||||
- `gzyy` extraction heuristics
|
||||
- summary aggregation parity
|
||||
- empty-result handling
|
||||
- partial-result generation when downstream export/logging fails
|
||||
- browser-script entrypoint shape (`return ...`, not `module.exports`)
|
||||
|
||||
The classification/summary tests should use fixed raw-row fixtures so the business rules are validated without a live browser session.
|
||||
|
||||
### `claw-new` runtime regressions
|
||||
|
||||
Add Rust coverage in `claw-new` for:
|
||||
|
||||
- direct-submit success with a populated `report-artifact`
|
||||
- `partial` artifact mapping to `TaskComplete.success = true`
|
||||
- `empty` artifact mapping to `TaskComplete.success = true`
|
||||
- `blocked` / `error` artifact mapping to `TaskComplete.success = false`
|
||||
- browser-script helper behavior for a real browser-eval return payload
|
||||
|
||||
### Manual acceptance
|
||||
|
||||
The live manual acceptance bar for this slice should be:
|
||||
|
||||
1. Configure `skillsDir` to the staged skill root and `directSubmitSkill` to `fault-details-report.collect_fault_details`.
|
||||
2. Attach sgClaw to the real target browser page/session.
|
||||
3. Submit a natural-language fault-details request without LLM routing.
|
||||
4. Verify the staged skill:
|
||||
- reads the selected page range
|
||||
- queries real fault rows
|
||||
- produces populated detail rows
|
||||
- produces populated summary rows
|
||||
- exports the workbook through localhost
|
||||
- writes report history
|
||||
5. Verify the final sgClaw completion message reports the correct status, counts, and downstream file/log outcome.
|
||||
|
||||
### Acceptance matrix
|
||||
|
||||
At minimum, acceptance should cover:
|
||||
|
||||
- normal populated result
|
||||
- empty result with no matching rows
|
||||
- partial result where export or report-log fails after collection
|
||||
- blocked result where page/session preconditions are missing
|
||||
- error result where parsing/query execution fails
|
||||
|
||||
---
|
||||
|
||||
## Explicit Non-Goals
|
||||
|
||||
This slice does **not**:
|
||||
|
||||
- move routing ownership out of `claw-new`
|
||||
- require LLM routing to be available first
|
||||
- add per-skill dispatch metadata to external manifests for routing policy
|
||||
- introduce a new browser protocol or browser opcode
|
||||
- recreate the original Vue shell inside `claw-new`
|
||||
- move fault classification logic into Rust
|
||||
- redesign the submit-task protocol beyond better interpretation of the returned artifact
|
||||
|
||||
---
|
||||
|
||||
## Resulting Design Rule
|
||||
|
||||
For the fault-details path:
|
||||
|
||||
- `claw-new` decides whether to invoke the fixed staged skill
|
||||
- the staged skill performs the real fault business workflow
|
||||
- the staged skill returns a structured artifact that describes collection + downstream outcomes
|
||||
- `claw-new` interprets that artifact for submit-task success/failure and summary output
|
||||
|
||||
That keeps routing config-owned, keeps business logic with the staged skill, and makes `fault-details-report.collect_fault_details` ready for both the current no-LLM path and a later LLM-routed path.
|
||||
|
||||
---
|
||||
|
||||
## Document Landing Zones
|
||||
|
||||
- Approved spec: `docs/superpowers/specs/2026-04-10-fault-details-full-skill-alignment-design.md`
|
||||
- Follow-up implementation plan: `docs/superpowers/plans/2026-04-10-fault-details-full-skill-alignment-plan.md`
|
||||
@@ -0,0 +1,618 @@
|
||||
# TQ Line-Loss Deterministic Skill Design
|
||||
|
||||
**Goal:** Add a staged business skill for `台区线损大数据-月_周累计线损率统计分析` and a deterministic natural-language routing path in `claw-new` that can bypass LLM when the instruction ends with `。。。`, while preserving the existing Zhihu hotlist behavior and keeping the execution seam pipe-first but ws-ready.
|
||||
|
||||
**Status:** Approved design direction for implementation planning.
|
||||
|
||||
---
|
||||
|
||||
## Decision Summary
|
||||
|
||||
1. Add a new staged skill package `tq-lineloss-report` under `D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/skills/`, following the same packaging discipline as `fault-details-report`.
|
||||
2. In `claw-new`, add a deterministic submit path triggered only when the instruction ends with the three-Chinese-dot suffix `。。。`.
|
||||
3. In deterministic mode, route only through a fixed whitelist of staged skills; for this slice the new target is `tq-lineloss-report.collect_lineloss`.
|
||||
4. Deterministic mode must extract business parameters from natural language without using an LLM: company/unit, month-vs-week mode, and period text.
|
||||
5. Parsed natural-language parameters are not the final backend parameters. They must be normalized into the canonical codes required by the source page / source APIs (for example company code and period mode code).
|
||||
6. If required parameters are missing or ambiguous, the runtime must stop and ask the user to provide them explicitly. It must **not** silently fall back to page defaults in this slice.
|
||||
7. Skill execution must reuse the existing browser-script → pipe injection seam already proven by the Zhihu hotlist path. Do not create a second browser execution protocol.
|
||||
8. The design must not regress or weaken the existing Zhihu hotlist direct path, browser-script path, export path, or current routing behavior.
|
||||
9. The main branch implementation remains pipe-only, but all new deterministic-routing and skill contracts must stay backend-neutral so the execution backend can later be swapped to ws on the ws branch.
|
||||
|
||||
---
|
||||
|
||||
## Non-Negotiable Boundaries
|
||||
|
||||
### 1. Do not break the existing Zhihu hotlist flow
|
||||
|
||||
This is the top safety boundary for the slice.
|
||||
|
||||
The new deterministic routing for `tq-lineloss-report` must not break, narrow, or silently change:
|
||||
|
||||
- current Zhihu hotlist routing
|
||||
- current Zhihu direct browser-script execution
|
||||
- current Zhihu export behavior
|
||||
- current browser-script skill loading/execution
|
||||
- existing direct-submit configuration behavior
|
||||
|
||||
Design implication:
|
||||
|
||||
- The new deterministic path must be added as a narrow, explicit branch.
|
||||
- Existing Zhihu logic must keep its current trigger semantics and current execution seam.
|
||||
- Verification for this slice must include targeted Zhihu regression coverage before implementation is considered complete.
|
||||
|
||||
### 2. Current main branch is pipe-only
|
||||
|
||||
The implementation landing on `main` must execute browser-script skills through the current pipe-backed browser execution seam.
|
||||
|
||||
Do not introduce ws as an active runtime requirement for this slice.
|
||||
|
||||
### 3. Future ws migration must stay cheap
|
||||
|
||||
Although `main` remains pipe-only, the new work must leave a clean extension seam so that after this slice is merged into `ws`, the browser backend can be switched without redesigning:
|
||||
|
||||
- the staged skill package
|
||||
- the deterministic trigger contract
|
||||
- the parameter extraction contract
|
||||
- the parameter normalization contract
|
||||
- the returned artifact contract
|
||||
|
||||
---
|
||||
|
||||
## Why This Slice Exists
|
||||
|
||||
The user wants a staged business skill for `台区线损大数据-月_周累计线损率统计分析` that behaves like a deterministic business operation, not a free-form LLM task.
|
||||
|
||||
The desired operator experience is:
|
||||
|
||||
- ordinary instructions continue to use the current normal routing / LLM path
|
||||
- an instruction ending in `。。。` switches to deterministic business execution
|
||||
- deterministic execution targets a fixed staged skill
|
||||
- business parameters are extracted from the instruction
|
||||
- those parameters are normalized to the real coded values the source page/API needs
|
||||
- the staged browser-script is injected into the third-party browser through the existing pipe seam
|
||||
|
||||
This provides an inner-network-safe path that can work without a model today, while reserving an upgrade path for future semantic fallback.
|
||||
|
||||
---
|
||||
|
||||
## Terminology
|
||||
|
||||
### Deterministic mode
|
||||
|
||||
A submit-task mode enabled only when the instruction ends with `。。。`.
|
||||
|
||||
### Natural-language business parameters
|
||||
|
||||
Values expressed by the user in text, such as:
|
||||
|
||||
- `兰州公司`
|
||||
- `天水公司`
|
||||
- `月累计`
|
||||
- `周累计`
|
||||
- `2026-03`
|
||||
- `2026年第12周`
|
||||
|
||||
These are intermediate semantic values, not final backend parameters.
|
||||
|
||||
### Canonical execution parameters
|
||||
|
||||
The normalized values required by the source page / source API, such as:
|
||||
|
||||
- canonical company label
|
||||
- canonical company code
|
||||
- period mode code (month/week)
|
||||
- canonical request period payload
|
||||
|
||||
---
|
||||
|
||||
## Ownership Boundary and Landing Zones
|
||||
|
||||
### Staged skill changes
|
||||
|
||||
These land in:
|
||||
|
||||
`D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging`
|
||||
|
||||
Primary landing zone:
|
||||
|
||||
- `skills/tq-lineloss-report/`
|
||||
|
||||
Target package structure:
|
||||
|
||||
- `SKILL.md`
|
||||
- `SKILL.toml`
|
||||
- `references/collection-flow.md`
|
||||
- `references/data-quality.md`
|
||||
- `assets/scene-snapshot/index.html`
|
||||
- `scripts/collect_lineloss.js`
|
||||
- `scripts/collect_lineloss.test.js`
|
||||
|
||||
Potential aligned scene metadata (if included in this slice):
|
||||
|
||||
- `scenes/tq-lineloss-report/scene.json`
|
||||
- optional scene registry updates if the current staging conventions require it
|
||||
|
||||
### Caller/runtime changes
|
||||
|
||||
These land in:
|
||||
|
||||
`D:/data/ideaSpace/rust/sgClaw/claw-new`
|
||||
|
||||
Likely ownership areas:
|
||||
|
||||
- deterministic instruction detection and deterministic skill matching
|
||||
- parameter extraction and normalization
|
||||
- deterministic skill dispatch to the existing browser-script seam
|
||||
- narrow result interpretation for the returned artifact
|
||||
- focused regression tests
|
||||
|
||||
Design rule:
|
||||
|
||||
`claw-new` owns routing, extraction, normalization, and dispatch.
|
||||
|
||||
`claw-new` must **not** absorb the line-loss business logic itself.
|
||||
|
||||
The staged skill package owns:
|
||||
|
||||
- page inspection
|
||||
- page-side state reading
|
||||
- page/API data collection
|
||||
- row normalization
|
||||
- export/report-log behavior
|
||||
- final artifact generation
|
||||
|
||||
---
|
||||
|
||||
## Target Runtime Flow
|
||||
|
||||
### Step 1: Submit-task enters deterministic mode only on `。。。`
|
||||
|
||||
When the user instruction does **not** end in `。。。`:
|
||||
|
||||
- keep the current runtime behavior unchanged
|
||||
- preserve existing Zhihu hotlist behavior exactly
|
||||
- preserve existing direct-submit and compat/LLM flows
|
||||
|
||||
When the instruction **does** end in `。。。`:
|
||||
|
||||
- enter deterministic mode
|
||||
- do not run the ordinary LLM interpretation branch for this request
|
||||
- evaluate only the deterministic skill whitelist
|
||||
|
||||
### Step 2: Deterministic whitelist match
|
||||
|
||||
The runtime should match the instruction against deterministic business scenes.
|
||||
|
||||
For this slice the new required deterministic scene is:
|
||||
|
||||
- `tq-lineloss-report.collect_lineloss`
|
||||
|
||||
The matching layer should remain narrow and explicit. It should not become a general scene-registry runtime in this slice.
|
||||
|
||||
Matching should use a deterministic combination of:
|
||||
|
||||
- instruction keywords
|
||||
- optional page URL/title constraints when available
|
||||
|
||||
The runtime must not accidentally steal instructions that should still go down the Zhihu path.
|
||||
|
||||
### Step 3: Extract semantic business parameters from natural language
|
||||
|
||||
After `tq-lineloss-report` is matched, the runtime extracts semantic business parameters from the instruction.
|
||||
|
||||
Required semantic categories:
|
||||
|
||||
- company/unit expression
|
||||
- period mode (`month` vs `week`)
|
||||
- period text/value
|
||||
|
||||
Examples of accepted user-facing expressions include:
|
||||
|
||||
- `兰州公司`
|
||||
- `天水公司`
|
||||
- `国网兰州供电公司`
|
||||
- `城关供电分公司`
|
||||
- `2026-03`
|
||||
- `2026年3月`
|
||||
- `2026年第12周`
|
||||
- `第12周`
|
||||
- `月累计`
|
||||
- `周累计`
|
||||
|
||||
### Step 4: Normalize semantic values into canonical coded values
|
||||
|
||||
This is a required separate design step.
|
||||
|
||||
The runtime must not pass raw natural-language company text directly to the business request layer.
|
||||
|
||||
Instead it must normalize semantic values into canonical execution parameters, including:
|
||||
|
||||
- `org_label` — canonical unit label
|
||||
- `org_code` — the actual code/value required by the business page/API
|
||||
- `period_mode` — canonical mode (`month` or `week`)
|
||||
- `period_mode_code` — the page/API code (for example `timeChage`-style encoded mode)
|
||||
- canonical time payload required by the source APIs/page state
|
||||
|
||||
This normalization should be derived from the actual source materials, including page-side dictionaries such as the existing unit tree data.
|
||||
|
||||
### Step 5: Missing and ambiguous parameters must stop execution
|
||||
|
||||
This slice must not silently infer missing parameters from page defaults.
|
||||
|
||||
If a required parameter is missing, execution must stop with an explicit prompt to the user.
|
||||
|
||||
If a parameter is ambiguous, execution must stop with an explicit ambiguity prompt.
|
||||
|
||||
Examples:
|
||||
|
||||
- no company matched
|
||||
- no month/week mode matched
|
||||
- no period value matched when required
|
||||
- a short company alias matches multiple canonical units
|
||||
- both monthly and weekly intent appear in the same instruction
|
||||
|
||||
This is preferable to silently using the wrong company code or the wrong query period.
|
||||
|
||||
### Step 6: Execute the staged skill through the existing pipe seam
|
||||
|
||||
If and only if parameters are present and successfully normalized:
|
||||
|
||||
- resolve `tq-lineloss-report.collect_lineloss`
|
||||
- build the args object
|
||||
- execute it through the current `browser_script` runtime
|
||||
- inject the script into the browser through the existing pipe-backed browser tool seam
|
||||
|
||||
This slice must reuse the execution pattern already proven by the current browser-script/direct-skill infrastructure and the current Zhihu hotlist path.
|
||||
|
||||
Do not introduce a second browser protocol, new browser opcode family, or parallel execution harness.
|
||||
|
||||
### Step 7: Skill JS performs page-side work and returns one artifact
|
||||
|
||||
The staged script owns the actual line-loss business behavior:
|
||||
|
||||
- reading page-side state when needed
|
||||
- validating the page context
|
||||
- using normalized codes/parameters from args
|
||||
- building source API requests
|
||||
- collecting/normalizing rows
|
||||
- export/report logging behavior if required by the final business contract
|
||||
- returning a structured artifact
|
||||
|
||||
---
|
||||
|
||||
## Deterministic Trigger Contract
|
||||
|
||||
### Trigger rule
|
||||
|
||||
Deterministic mode is activated only when the raw instruction ends with the exact three-Chinese-dot suffix:
|
||||
|
||||
- `。。。`
|
||||
|
||||
This suffix is a user-controlled explicit mode switch.
|
||||
|
||||
### Why the suffix exists
|
||||
|
||||
It lets the user force business-deterministic behavior without relying on a model, while preserving the normal LLM path for ordinary requests.
|
||||
|
||||
### Scope rule
|
||||
|
||||
The suffix is not a free pass to run arbitrary browser actions.
|
||||
|
||||
It only selects among the deterministic skill whitelist.
|
||||
|
||||
If no deterministic scene matches, the runtime should return a deterministic-mode mismatch error that explains the currently supported deterministic scenes, rather than silently dropping into another behavior.
|
||||
|
||||
---
|
||||
|
||||
## Company / Unit Matching Contract
|
||||
|
||||
### Accepted input style
|
||||
|
||||
The user does **not** need to type the exact full canonical label.
|
||||
|
||||
The runtime should support business shorthand such as:
|
||||
|
||||
- `兰州公司`
|
||||
- `天水公司`
|
||||
- `白银公司`
|
||||
- `城关供电分公司`
|
||||
- `榆中县供电公司`
|
||||
|
||||
### Matching approach
|
||||
|
||||
Do not use regex alone as the primary company-resolution mechanism.
|
||||
|
||||
Use a three-stage resolution strategy:
|
||||
|
||||
1. text normalization
|
||||
2. alias/candidate generation from canonical unit names
|
||||
3. uniqueness resolution against the real unit dictionary
|
||||
|
||||
### Normalization examples
|
||||
|
||||
Canonical names such as:
|
||||
|
||||
- `国网兰州供电公司`
|
||||
- `国网天水供电公司`
|
||||
- `国网榆中县供电公司`
|
||||
|
||||
should be matchable from business shorthand forms such as:
|
||||
|
||||
- `兰州公司`
|
||||
- `天水公司`
|
||||
- `榆中县公司`
|
||||
- `榆中供电公司`
|
||||
|
||||
### Data source for canonical mapping
|
||||
|
||||
The company/unit resolver should derive canonical mappings from the real source materials used by the business page, such as the current unit tree dictionary embedded in the source page resources.
|
||||
|
||||
Design implication:
|
||||
|
||||
- the resolver should produce the real `value`/code required downstream
|
||||
- the resolver should also keep the canonical label for display/auditability
|
||||
|
||||
### Ambiguity rule
|
||||
|
||||
If a short alias resolves to more than one valid unit, execution must stop and ask the user to be more specific.
|
||||
|
||||
Do not auto-guess.
|
||||
|
||||
### Supported granularity
|
||||
|
||||
The first implementation must support both:
|
||||
|
||||
- city-company level
|
||||
- district/county/sub-company level
|
||||
|
||||
This includes forms like:
|
||||
|
||||
- `兰州公司`
|
||||
- `天水公司`
|
||||
- `城关供电分公司`
|
||||
- `榆中县供电公司`
|
||||
|
||||
---
|
||||
|
||||
## Period Extraction and Normalization Contract
|
||||
|
||||
### Required period dimensions
|
||||
|
||||
The runtime must identify:
|
||||
|
||||
- mode: `month` or `week`
|
||||
- actual requested period value in a canonical form
|
||||
|
||||
### Accepted user-facing patterns
|
||||
|
||||
At minimum the design should account for patterns such as:
|
||||
|
||||
- `月累计`
|
||||
- `周累计`
|
||||
- `2026-03`
|
||||
- `2026年3月`
|
||||
- `2026年第12周`
|
||||
- `第12周`
|
||||
|
||||
### Normalization output
|
||||
|
||||
The resolver should produce:
|
||||
|
||||
- a canonical mode enum/string
|
||||
- a mode code required by the page/API
|
||||
- a canonical period payload consumable by the script/business request layer
|
||||
|
||||
### Ambiguity rule
|
||||
|
||||
If both month and week intent appear, stop and ask the user to clarify.
|
||||
|
||||
### Missing-period rule
|
||||
|
||||
If the selected line-loss query requires a time period and the instruction does not provide enough information to construct one, stop and ask the user to provide it.
|
||||
|
||||
Do not default to the page-selected period in this slice.
|
||||
|
||||
---
|
||||
|
||||
## Parameter Prompting Contract
|
||||
|
||||
When deterministic mode matches `tq-lineloss-report` but one or more required parameters are missing or ambiguous, the runtime should return a user-facing prompt rather than executing.
|
||||
|
||||
Expected prompting cases include:
|
||||
|
||||
- missing company/unit
|
||||
- missing month/week mode
|
||||
- missing period value
|
||||
- ambiguous company alias
|
||||
- contradictory period expressions
|
||||
|
||||
The prompt should be specific enough to let the user correct only the missing field(s).
|
||||
|
||||
Example style:
|
||||
|
||||
- `已命中台区线损报表技能，但缺少供电单位，请补充如“兰州公司”或“城关供电分公司”。`
|
||||
- `已命中台区线损报表技能，但未识别到月/周类型，请补充“月累计”或“周累计”。`
|
||||
|
||||
---
|
||||
|
||||
## Skill Package Contract
|
||||
|
||||
### SKILL.toml
|
||||
|
||||
The new skill package must declare a single deterministic collection entrypoint:
|
||||
|
||||
- tool name: `collect_lineloss`
|
||||
- kind: `browser_script`
|
||||
|
||||
The tool description must reflect the real staged behavior, not a placeholder shell.
|
||||
|
||||
### SKILL.md
|
||||
|
||||
The written contract should cover:
|
||||
|
||||
- when to use the skill
|
||||
- when not to use it
|
||||
- collection workflow
|
||||
- runtime contract
|
||||
- explicit missing/partial/error semantics
|
||||
- returned artifact contract
|
||||
|
||||
### references/collection-flow.md
|
||||
|
||||
Must explain:
|
||||
|
||||
- the source page state used by the skill
|
||||
- how company and period parameters map to business requests
|
||||
- which page/API calls are used for month vs week
|
||||
- export/report-log sequencing if retained in the business flow
|
||||
|
||||
### references/data-quality.md
|
||||
|
||||
Must define:
|
||||
|
||||
- canonical output columns
|
||||
- required field coverage
|
||||
- status semantics
|
||||
- partial/error conditions
|
||||
- company/period normalization assumptions that the script relies on
|
||||
|
||||
### scripts/collect_lineloss.js
|
||||
|
||||
This is the real browser-side entrypoint. It should:
|
||||
|
||||
- accept normalized args
|
||||
- validate page context
|
||||
- execute deterministic page/API data collection
|
||||
- normalize rows
|
||||
- perform downstream export/report-history behavior if required
|
||||
- directly return the final artifact from the browser-script runtime entrypoint shape
|
||||
|
||||
### scripts/collect_lineloss.test.js
|
||||
|
||||
Must cover the business transforms that can be tested off-browser, especially:
|
||||
|
||||
- company normalization assumptions consumed by the script
|
||||
- monthly vs weekly request-shape logic
|
||||
- status semantics
|
||||
- artifact shaping
|
||||
|
||||
---
|
||||
|
||||
## Returned Artifact Contract
|
||||
|
||||
The final line-loss skill should return one structured artifact object rather than free-form prose.
|
||||
|
||||
At minimum it should expose:
|
||||
|
||||
- artifact type
|
||||
- report name
|
||||
- canonical company label/code used for the query
|
||||
- period mode and canonical period value used for the query
|
||||
- columns
|
||||
- rows
|
||||
- status
|
||||
- counts
|
||||
- downstream export/report-log status when applicable
|
||||
- clear reasons for blocked/partial/error states
|
||||
|
||||
The exact field names may be finalized during implementation planning, but the contract must be structured enough for `claw-new` to interpret success vs partial vs blocked without re-embedding business logic.
|
||||
|
||||
---
|
||||
|
||||
## Pipe-First / Ws-Ready Execution Seam
|
||||
|
||||
### Current requirement
|
||||
|
||||
The first implementation on `main` must use the existing pipe-backed browser execution path.
|
||||
|
||||
### Future requirement
|
||||
|
||||
The design must allow later ws adoption without redesigning the skill or routing contract.
|
||||
|
||||
### Practical design rule
|
||||
|
||||
Keep these backend-neutral:
|
||||
|
||||
- deterministic trigger contract
|
||||
- skill matching contract
|
||||
- parameter extraction contract
|
||||
- parameter normalization contract
|
||||
- tool args contract
|
||||
- artifact contract
|
||||
|
||||
Keep backend-specific code isolated to the execution seam only.
|
||||
|
||||
That way the later ws migration can replace the browser backend beneath the same deterministic skill contract.
|
||||
|
||||
---
|
||||
|
||||
## Caller/Runtime Design Rules
|
||||
|
||||
### 1. Keep new business logic out of broad orchestration
|
||||
|
||||
Do not thread line-loss-specific business behavior through the general orchestration/runtime path.
|
||||
|
||||
### 2. Add a narrow deterministic-routing seam
|
||||
|
||||
This slice should add a narrow deterministic branch around submit-task routing, rather than rewriting the whole runtime decision tree.
|
||||
|
||||
### 3. Separate extraction from normalization
|
||||
|
||||
Do not mix “what the user typed” with “what the backend needs”.
|
||||
|
||||
There must be a distinct normalization step.
|
||||
|
||||
### 4. Keep the direct-skill browser seam narrow
|
||||
|
||||
Reuse the current `browser_script` execution seam instead of inventing a new browser bridge.
|
||||
|
||||
### 5. Preserve Zhihu behavior by design, not by hope
|
||||
|
||||
The design should assume new deterministic routing can accidentally steal or alter existing Zhihu behavior unless explicitly guarded against.
|
||||
|
||||
This is why focused Zhihu regression coverage is mandatory.
|
||||
|
||||
---
|
||||
|
||||
## Verification Requirements for the Future Implementation Plan
|
||||
|
||||
Implementation planning must include explicit verification for:
|
||||
|
||||
1. deterministic suffix detection
|
||||
2. deterministic lineloss scene matching
|
||||
3. company alias normalization to canonical code
|
||||
4. support for both company-level and district/county/sub-company-level units
|
||||
5. month/week extraction and normalization
|
||||
6. missing-parameter prompt behavior
|
||||
7. ambiguous-company prompt behavior
|
||||
8. pipe-backed browser-script execution for the new skill
|
||||
9. no regression to the existing Zhihu hotlist path
|
||||
10. preserved direct-skill/browser-script behavior outside the new line-loss scene
|
||||
|
||||
---
|
||||
|
||||
## Out of Scope for This Slice
|
||||
|
||||
- enabling ws execution on `main`
|
||||
- replacing the current Zhihu routing model
|
||||
- general scene-registry runtime architecture redesign
|
||||
- full free-form semantic understanding of arbitrary business language
|
||||
- typo-tolerant fuzzy NLP beyond deterministic business-safe matching
|
||||
- making page defaults the hidden source of truth when the user omitted parameters
|
||||
|
||||
---
|
||||
|
||||
## Planning Notes
|
||||
|
||||
The implementation plan should likely split into distinct work items for:
|
||||
|
||||
1. staged skill package creation and business contract definition
|
||||
2. deterministic trigger + scene match in `claw-new`
|
||||
3. company/unit normalization and ambiguity handling
|
||||
4. period extraction/normalization and ambiguity handling
|
||||
5. pipe-backed direct execution integration
|
||||
6. returned artifact interpretation
|
||||
7. Zhihu regression verification
|
||||
8. ws-readiness seam verification
|
||||
|
||||
The plan should explicitly keep the “do not break Zhihu hotlist” boundary visible in every execution and verification stage.
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"version": "1.0",
|
||||
"demo_only_domains": ["baidu.com", "www.baidu.com", "zhihu.com", "www.zhihu.com"],
|
||||
"demo_only_domains": ["baidu.com", "www.baidu.com", "zhihu.com", "www.zhihu.com", "zhuanlan.zhihu.com"],
|
||||
"domains": {
|
||||
"allowed": [
|
||||
"oa.example.com",
|
||||
@@ -9,7 +9,8 @@
|
||||
"baidu.com",
|
||||
"www.baidu.com",
|
||||
"zhihu.com",
|
||||
"www.zhihu.com"
|
||||
"www.zhihu.com",
|
||||
"zhuanlan.zhihu.com"
|
||||
]
|
||||
},
|
||||
"pipe_actions": {
|
||||
|
||||
637
resources/zhihu-hotlist-echarts.html
Normal file
637
resources/zhihu-hotlist-echarts.html
Normal file
@@ -0,0 +1,637 @@
|
||||
<!doctype html>
|
||||
<html lang="zh-CN">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1" />
|
||||
<title>知乎热榜图表驾驶舱</title>
|
||||
<script src="https://cdn.jsdelivr.net/npm/echarts@5/dist/echarts.min.js"></script>
|
||||
<style>
|
||||
:root {
|
||||
--bg: #06111f;
|
||||
--bg-2: #0a1f37;
|
||||
--panel: rgba(8, 25, 42, 0.88);
|
||||
--panel-strong: rgba(10, 32, 55, 0.95);
|
||||
--line: rgba(101, 187, 255, 0.18);
|
||||
--line-strong: rgba(236, 186, 81, 0.26);
|
||||
--text: #eef6ff;
|
||||
--muted: #8ea6c2;
|
||||
--accent: #62d0ff;
|
||||
--accent-2: #ecba51;
|
||||
--accent-3: #6df0c2;
|
||||
--danger: #ff8b7e;
|
||||
--shadow: 0 20px 48px rgba(0, 0, 0, 0.34);
|
||||
--font-heading: "DIN Alternate", "Bahnschrift", "Microsoft YaHei UI", sans-serif;
|
||||
--font-body: "Segoe UI Variable Text", "Microsoft YaHei", "PingFang SC", sans-serif;
|
||||
}
|
||||
|
||||
* {
|
||||
box-sizing: border-box;
|
||||
}
|
||||
|
||||
html,
|
||||
body {
|
||||
margin: 0;
|
||||
min-height: 100%;
|
||||
background:
|
||||
radial-gradient(circle at 16% 10%, rgba(98, 208, 255, 0.18), transparent 22%),
|
||||
radial-gradient(circle at 86% 12%, rgba(236, 186, 81, 0.14), transparent 18%),
|
||||
linear-gradient(145deg, var(--bg) 0%, var(--bg-2) 42%, #030910 100%);
|
||||
color: var(--text);
|
||||
font-family: var(--font-body);
|
||||
}
|
||||
|
||||
body::before {
|
||||
content: "";
|
||||
position: fixed;
|
||||
inset: 0;
|
||||
pointer-events: none;
|
||||
background-image:
|
||||
linear-gradient(rgba(101, 187, 255, 0.05) 1px, transparent 1px),
|
||||
linear-gradient(90deg, rgba(101, 187, 255, 0.05) 1px, transparent 1px);
|
||||
background-size: 44px 44px;
|
||||
mask-image: radial-gradient(circle at center, black 34%, rgba(0, 0, 0, 0.22) 88%, transparent 100%);
|
||||
}
|
||||
|
||||
.page {
|
||||
min-height: 100vh;
|
||||
padding: 18px;
|
||||
display: grid;
|
||||
grid-template-rows: auto auto 1fr auto;
|
||||
gap: 14px;
|
||||
}
|
||||
|
||||
.panel {
|
||||
position: relative;
|
||||
overflow: hidden;
|
||||
background:
|
||||
linear-gradient(180deg, rgba(255, 255, 255, 0.035), rgba(255, 255, 255, 0.01)),
|
||||
linear-gradient(145deg, rgba(9, 30, 51, 0.97), rgba(6, 20, 34, 0.92));
|
||||
border: 1px solid var(--line);
|
||||
border-radius: 22px;
|
||||
box-shadow: var(--shadow);
|
||||
}
|
||||
|
||||
.panel::before {
|
||||
content: "";
|
||||
position: absolute;
|
||||
left: 18px;
|
||||
right: 18px;
|
||||
top: 0;
|
||||
height: 2px;
|
||||
background: linear-gradient(90deg, transparent, var(--accent), var(--accent-2), transparent);
|
||||
opacity: 0.95;
|
||||
}
|
||||
|
||||
.hero {
|
||||
padding: 18px 24px;
|
||||
display: grid;
|
||||
grid-template-columns: minmax(0, 1fr) 360px;
|
||||
gap: 16px;
|
||||
align-items: center;
|
||||
}
|
||||
|
||||
.eyebrow {
|
||||
color: var(--accent);
|
||||
letter-spacing: 2px;
|
||||
text-transform: uppercase;
|
||||
font-size: 12px;
|
||||
margin-bottom: 8px;
|
||||
}
|
||||
|
||||
h1 {
|
||||
margin: 0;
|
||||
font-family: var(--font-heading);
|
||||
font-size: 38px;
|
||||
line-height: 1.08;
|
||||
letter-spacing: 1px;
|
||||
}
|
||||
|
||||
#snapshot-meta {
|
||||
margin: 10px 0 0;
|
||||
color: var(--muted);
|
||||
font-size: 14px;
|
||||
}
|
||||
|
||||
.hero-notes {
|
||||
display: grid;
|
||||
gap: 10px;
|
||||
}
|
||||
|
||||
.note-card {
|
||||
padding: 14px 16px;
|
||||
border-radius: 16px;
|
||||
background: linear-gradient(135deg, rgba(98, 208, 255, 0.08), rgba(236, 186, 81, 0.08));
|
||||
border: 1px solid rgba(255, 255, 255, 0.05);
|
||||
}
|
||||
|
||||
.note-card strong {
|
||||
display: block;
|
||||
margin-bottom: 6px;
|
||||
font-size: 14px;
|
||||
}
|
||||
|
||||
.note-card span {
|
||||
color: var(--muted);
|
||||
font-size: 12px;
|
||||
line-height: 1.5;
|
||||
}
|
||||
|
||||
.metrics {
|
||||
display: grid;
|
||||
grid-template-columns: repeat(4, 1fr);
|
||||
gap: 12px;
|
||||
}
|
||||
|
||||
.metric {
|
||||
padding: 18px 18px 16px;
|
||||
}
|
||||
|
||||
.metric-label {
|
||||
color: var(--muted);
|
||||
font-size: 12px;
|
||||
letter-spacing: 1px;
|
||||
text-transform: uppercase;
|
||||
}
|
||||
|
||||
.metric-value {
|
||||
margin-top: 10px;
|
||||
font-family: var(--font-heading);
|
||||
font-size: 34px;
|
||||
color: var(--text);
|
||||
}
|
||||
|
||||
.metric-sub {
|
||||
margin-top: 8px;
|
||||
color: var(--accent);
|
||||
font-size: 12px;
|
||||
}
|
||||
|
||||
.charts {
|
||||
min-height: 0;
|
||||
display: grid;
|
||||
grid-template-columns: 1.2fr 1fr 0.95fr;
|
||||
grid-template-rows: 360px 320px;
|
||||
gap: 14px;
|
||||
grid-template-areas:
|
||||
"bar top pie"
|
||||
"bubble table table";
|
||||
}
|
||||
|
||||
.chart-panel {
|
||||
padding: 14px 16px 12px;
|
||||
}
|
||||
|
||||
.bar-panel { grid-area: bar; }
|
||||
.top-panel { grid-area: top; }
|
||||
.pie-panel { grid-area: pie; }
|
||||
.bubble-panel { grid-area: bubble; }
|
||||
.table-panel { grid-area: table; padding: 14px 16px 10px; }
|
||||
|
||||
.section-head {
|
||||
display: flex;
|
||||
align-items: end;
|
||||
justify-content: space-between;
|
||||
gap: 12px;
|
||||
margin-bottom: 10px;
|
||||
}
|
||||
|
||||
.section-head h2 {
|
||||
margin: 0;
|
||||
font-size: 22px;
|
||||
font-family: var(--font-heading);
|
||||
letter-spacing: 1px;
|
||||
}
|
||||
|
||||
.section-head span {
|
||||
color: var(--muted);
|
||||
font-size: 12px;
|
||||
}
|
||||
|
||||
.chart {
|
||||
width: 100%;
|
||||
height: calc(100% - 42px);
|
||||
}
|
||||
|
||||
.table-wrap {
|
||||
height: calc(100% - 42px);
|
||||
overflow: auto;
|
||||
padding-right: 4px;
|
||||
}
|
||||
|
||||
table {
|
||||
width: 100%;
|
||||
border-collapse: collapse;
|
||||
}
|
||||
|
||||
thead th {
|
||||
position: sticky;
|
||||
top: 0;
|
||||
z-index: 1;
|
||||
background: rgba(6, 19, 32, 0.96);
|
||||
padding: 10px 8px;
|
||||
text-align: left;
|
||||
font-size: 12px;
|
||||
color: var(--muted);
|
||||
letter-spacing: 1px;
|
||||
text-transform: uppercase;
|
||||
border-bottom: 1px solid var(--line-strong);
|
||||
}
|
||||
|
||||
tbody td {
|
||||
padding: 11px 8px;
|
||||
border-bottom: 1px solid rgba(255, 255, 255, 0.05);
|
||||
font-size: 13px;
|
||||
vertical-align: top;
|
||||
}
|
||||
|
||||
tbody tr:nth-child(odd) {
|
||||
background: rgba(255, 255, 255, 0.016);
|
||||
}
|
||||
|
||||
.rank {
|
||||
font-family: var(--font-heading);
|
||||
color: var(--accent-2);
|
||||
white-space: nowrap;
|
||||
}
|
||||
|
||||
.heat {
|
||||
color: var(--accent-3);
|
||||
font-family: var(--font-heading);
|
||||
white-space: nowrap;
|
||||
}
|
||||
|
||||
.tag {
|
||||
display: inline-flex;
|
||||
align-items: center;
|
||||
padding: 4px 10px;
|
||||
border-radius: 999px;
|
||||
background: rgba(98, 208, 255, 0.12);
|
||||
color: var(--accent);
|
||||
font-size: 12px;
|
||||
}
|
||||
|
||||
.footer {
|
||||
padding: 10px 16px;
|
||||
color: var(--muted);
|
||||
font-size: 12px;
|
||||
}
|
||||
|
||||
@media (max-width: 1440px) {
|
||||
.hero {
|
||||
grid-template-columns: 1fr;
|
||||
}
|
||||
|
||||
.metrics {
|
||||
grid-template-columns: repeat(2, 1fr);
|
||||
}
|
||||
|
||||
.charts {
|
||||
grid-template-columns: 1fr;
|
||||
grid-template-rows: 320px 320px 320px 320px 420px;
|
||||
grid-template-areas:
|
||||
"bar"
|
||||
"top"
|
||||
"pie"
|
||||
"bubble"
|
||||
"table";
|
||||
}
|
||||
}
|
||||
|
||||
@media (max-width: 760px) {
|
||||
.page {
|
||||
padding: 12px;
|
||||
}
|
||||
|
||||
h1 {
|
||||
font-size: 28px;
|
||||
}
|
||||
|
||||
.metrics {
|
||||
grid-template-columns: 1fr;
|
||||
}
|
||||
}
|
||||
</style>
|
||||
</head>
|
||||
<body>
|
||||
<div class="page">
|
||||
<section class="panel hero">
|
||||
<div>
|
||||
<div class="eyebrow">Zhihu Hotlist Visual Command Center</div>
|
||||
<h1>知乎热榜图表驾驶舱</h1>
|
||||
<p id="snapshot-meta">由 sgClaw screen_html_export 生成的本地静态展示页</p>
|
||||
</div>
|
||||
<div class="hero-notes">
|
||||
<div class="note-card">
|
||||
<strong>图表表达</strong>
|
||||
<span>同一份热榜数据同时映射为分类热度、头部热点、结构占比和热度散点，适合现场讲解图表能力。</span>
|
||||
</div>
|
||||
<div class="note-card">
|
||||
<strong>演示建议</strong>
|
||||
<span id="lead-summary">优先讲解榜首热点、分类分布与热度层级，再向下展开全量榜单细节。</span>
|
||||
</div>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
<section class="metrics">
|
||||
<article class="panel metric">
|
||||
<div class="metric-label">热榜条目数</div>
|
||||
<div id="metric-total" class="metric-value">0</div>
|
||||
<div class="metric-sub">Tracked items</div>
|
||||
</article>
|
||||
<article class="panel metric">
|
||||
<div class="metric-label">主题分类数</div>
|
||||
<div id="metric-categories" class="metric-value">0</div>
|
||||
<div class="metric-sub">Topic groups</div>
|
||||
</article>
|
||||
<article class="panel metric">
|
||||
<div class="metric-label">累计热度</div>
|
||||
<div id="metric-heat" class="metric-value">0</div>
|
||||
<div class="metric-sub">Total heat</div>
|
||||
</article>
|
||||
<article class="panel metric">
|
||||
<div class="metric-label">头部峰值</div>
|
||||
<div id="metric-peak" class="metric-value">0</div>
|
||||
<div class="metric-sub">Peak topic heat</div>
|
||||
</article>
|
||||
</section>
|
||||
|
||||
<section class="charts">
|
||||
<section class="panel chart-panel bar-panel">
|
||||
<div class="section-head">
|
||||
<h2>分类总热度</h2>
|
||||
<span>横向对比</span>
|
||||
</div>
|
||||
<div id="bar-chart" class="chart"></div>
|
||||
</section>
|
||||
|
||||
<section class="panel chart-panel top-panel">
|
||||
<div class="section-head">
|
||||
<h2>Top10 热点</h2>
|
||||
<span>柱状排行</span>
|
||||
</div>
|
||||
<div id="top-chart" class="chart"></div>
|
||||
</section>
|
||||
|
||||
<section class="panel chart-panel pie-panel">
|
||||
<div class="section-head">
|
||||
<h2>分类占比</h2>
|
||||
<span>环形结构</span>
|
||||
</div>
|
||||
<div id="pie-chart" class="chart"></div>
|
||||
</section>
|
||||
|
||||
<section class="panel chart-panel bubble-panel">
|
||||
<div class="section-head">
|
||||
<h2>热度分层</h2>
|
||||
<span>散点气泡</span>
|
||||
</div>
|
||||
<div id="bubble-chart" class="chart"></div>
|
||||
</section>
|
||||
|
||||
<section class="panel table-panel">
|
||||
<div class="section-head">
|
||||
<h2>热榜明细</h2>
|
||||
<span id="table-note">按原始顺序保留</span>
|
||||
</div>
|
||||
<div class="table-wrap">
|
||||
<table>
|
||||
<thead>
|
||||
<tr>
|
||||
<th>排名</th>
|
||||
<th>标题</th>
|
||||
<th>分类</th>
|
||||
<th>热度</th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody id="table-body"></tbody>
|
||||
</table>
|
||||
</div>
|
||||
</section>
|
||||
</section>
|
||||
|
||||
<section class="panel footer">
|
||||
本页由 `screen_html_export` 生成，适合在系统浏览器中直接打开进行展示。
|
||||
</section>
|
||||
</div>
|
||||
<script>
|
||||
const defaultPayload = {
|
||||
"snapshot_id": "template-snapshot",
|
||||
"generated_at_ms": 0,
|
||||
"categories": [],
|
||||
"table": []
|
||||
}
|
||||
|
||||
const themeMeta = {
|
||||
title: "知乎热榜图表驾驶舱",
|
||||
renderer: "screen_html_export"
|
||||
};
|
||||
|
||||
const chartColors = ["#62d0ff", "#ecba51", "#6df0c2", "#7f8cff", "#ff8b7e", "#9fcbff", "#58a6ff"];
|
||||
const charts = {};
|
||||
|
||||
function formatNumber(value) {
|
||||
return new Intl.NumberFormat("zh-CN").format(Number(value || 0));
|
||||
}
|
||||
|
||||
function getTotalHeat(categories) {
|
||||
return (categories || []).reduce((sum, item) => sum + Number(item.total_heat || 0), 0);
|
||||
}
|
||||
|
||||
function getPeakHeat(table) {
|
||||
return (table || []).reduce((max, row) => Math.max(max, Number(row.heat_value || 0)), 0);
|
||||
}
|
||||
|
||||
function buildLeadSummary(table, categories) {
|
||||
const top = (table || [])[0];
|
||||
const category = (categories || []).slice().sort((a, b) => (b.total_heat || 0) - (a.total_heat || 0))[0];
|
||||
const parts = [];
|
||||
if (top) {
|
||||
parts.push(`榜首是“${top.title}”`);
|
||||
}
|
||||
if (category) {
|
||||
parts.push(`主导分类为“${category.category_label}”`);
|
||||
}
|
||||
parts.push(`共覆盖 ${(table || []).length} 条热点`);
|
||||
return parts.join("，");
|
||||
}
|
||||
|
||||
function ensureCharts() {
|
||||
if (!window.echarts) {
|
||||
return;
|
||||
}
|
||||
charts.bar = charts.bar || echarts.init(document.getElementById("bar-chart"));
|
||||
charts.top = charts.top || echarts.init(document.getElementById("top-chart"));
|
||||
charts.pie = charts.pie || echarts.init(document.getElementById("pie-chart"));
|
||||
charts.bubble = charts.bubble || echarts.init(document.getElementById("bubble-chart"));
|
||||
}
|
||||
|
||||
function renderBarChart(categories) {
|
||||
const sorted = (categories || []).slice().sort((a, b) => Number(a.total_heat || 0) - Number(b.total_heat || 0));
|
||||
charts.bar.setOption({
|
||||
animationDuration: 700,
|
||||
grid: {left: 90, right: 18, top: 10, bottom: 20},
|
||||
xAxis: {
|
||||
type: "value",
|
||||
axisLabel: {color: "#8ea6c2"},
|
||||
splitLine: {lineStyle: {color: "rgba(255,255,255,0.06)"}}
|
||||
},
|
||||
yAxis: {
|
||||
type: "category",
|
||||
data: sorted.map((item) => item.category_label),
|
||||
axisLabel: {color: "#eef6ff"},
|
||||
axisLine: {lineStyle: {color: "rgba(255,255,255,0.1)"}}
|
||||
},
|
||||
tooltip: {trigger: "axis", axisPointer: {type: "shadow"}},
|
||||
series: [{
|
||||
type: "bar",
|
||||
data: sorted.map((item, index) => ({
|
||||
value: Number(item.total_heat || 0),
|
||||
itemStyle: {color: chartColors[index % chartColors.length], borderRadius: [0, 8, 8, 0]}
|
||||
})),
|
||||
label: {show: true, position: "right", color: "#dfeeff"}
|
||||
}]
|
||||
});
|
||||
}
|
||||
|
||||
function renderTopChart(table) {
|
||||
const top = (table || []).slice(0, 10);
|
||||
charts.top.setOption({
|
||||
animationDuration: 700,
|
||||
grid: {left: 42, right: 12, top: 26, bottom: 46},
|
||||
tooltip: {trigger: "axis", axisPointer: {type: "shadow"}},
|
||||
xAxis: {
|
||||
type: "category",
|
||||
data: top.map((row) => `#${row.rank}`),
|
||||
axisLabel: {color: "#8ea6c2"},
|
||||
axisLine: {lineStyle: {color: "rgba(255,255,255,0.1)"}}
|
||||
},
|
||||
yAxis: {
|
||||
type: "value",
|
||||
axisLabel: {color: "#8ea6c2"},
|
||||
splitLine: {lineStyle: {color: "rgba(255,255,255,0.06)"}}
|
||||
},
|
||||
series: [{
|
||||
type: "bar",
|
||||
data: top.map((row, index) => ({
|
||||
value: Number(row.heat_value || 0),
|
||||
itemStyle: {color: chartColors[index % chartColors.length], borderRadius: [8, 8, 0, 0]}
|
||||
})),
|
||||
label: {show: true, position: "top", color: "#eef6ff", formatter: ({dataIndex}) => top[dataIndex].heat_text}
|
||||
}]
|
||||
});
|
||||
}
|
||||
|
||||
function renderPieChart(categories) {
|
||||
charts.pie.setOption({
|
||||
animationDuration: 700,
|
||||
color: chartColors,
|
||||
tooltip: {trigger: "item"},
|
||||
legend: {
|
||||
bottom: 2,
|
||||
textStyle: {color: "#8ea6c2", fontSize: 11},
|
||||
itemWidth: 12,
|
||||
itemHeight: 8
|
||||
},
|
||||
series: [{
|
||||
type: "pie",
|
||||
radius: ["44%", "72%"],
|
||||
center: ["50%", "44%"],
|
||||
itemStyle: {borderColor: "#081a2c", borderWidth: 2},
|
||||
label: {
|
||||
color: "#eef6ff",
|
||||
formatter: "{b}\n{d}%"
|
||||
},
|
||||
data: (categories || []).map((item) => ({
|
||||
name: item.category_label,
|
||||
value: Number(item.total_heat || 0)
|
||||
}))
|
||||
}]
|
||||
});
|
||||
}
|
||||
|
||||
function renderBubbleChart(table) {
|
||||
const top = (table || []).slice(0, 12);
|
||||
charts.bubble.setOption({
|
||||
animationDuration: 700,
|
||||
color: chartColors,
|
||||
grid: {left: 44, right: 18, top: 16, bottom: 36},
|
||||
xAxis: {
|
||||
type: "value",
|
||||
name: "排名",
|
||||
inverse: true,
|
||||
min: 0,
|
||||
max: Math.max(...top.map((row) => Number(row.rank || 0)), 10) + 1,
|
||||
nameTextStyle: {color: "#8ea6c2"},
|
||||
axisLabel: {color: "#8ea6c2"},
|
||||
splitLine: {lineStyle: {color: "rgba(255,255,255,0.06)"}}
|
||||
},
|
||||
yAxis: {
|
||||
type: "value",
|
||||
name: "热度值",
|
||||
nameTextStyle: {color: "#8ea6c2"},
|
||||
axisLabel: {color: "#8ea6c2"},
|
||||
splitLine: {lineStyle: {color: "rgba(255,255,255,0.06)"}}
|
||||
},
|
||||
tooltip: {
|
||||
formatter: (params) => {
|
||||
const row = params.data.raw;
|
||||
return `${row.title}<br/>排名 #${row.rank}<br/>热度 ${row.heat_text}<br/>分类 ${row.category_label}`;
|
||||
}
|
||||
},
|
||||
series: [{
|
||||
type: "scatter",
|
||||
symbolSize: (value) => Math.max(18, Math.min(56, value[2] / 80000)),
|
||||
data: top.map((row, index) => ({
|
||||
value: [Number(row.rank || 0), Number(row.heat_value || 0), Number(row.heat_value || 0)],
|
||||
raw: row,
|
||||
itemStyle: {color: chartColors[index % chartColors.length], opacity: 0.82}
|
||||
}))
|
||||
}]
|
||||
});
|
||||
}
|
||||
|
||||
function renderTable(table) {
|
||||
document.getElementById("table-body").innerHTML = (table || []).map((row) => `
|
||||
<tr>
|
||||
<td class="rank">#${row.rank}</td>
|
||||
<td>${row.title}</td>
|
||||
<td><span class="tag">${row.category_label}</span></td>
|
||||
<td class="heat">${row.heat_text}</td>
|
||||
</tr>
|
||||
`).join("");
|
||||
}
|
||||
|
||||
function render(payload) {
|
||||
const data = payload || defaultPayload;
|
||||
const categories = data.categories || [];
|
||||
const table = data.table || [];
|
||||
|
||||
document.title = themeMeta.title;
|
||||
document.getElementById("snapshot-meta").textContent =
|
||||
`${data.snapshot_id} | 生成时间 ${new Date(data.generated_at_ms || 0).toLocaleString()}`;
|
||||
document.getElementById("metric-total").textContent = formatNumber(table.length);
|
||||
document.getElementById("metric-categories").textContent = formatNumber(categories.length);
|
||||
document.getElementById("metric-heat").textContent = formatNumber(getTotalHeat(categories));
|
||||
document.getElementById("metric-peak").textContent = formatNumber(getPeakHeat(table));
|
||||
document.getElementById("lead-summary").textContent = buildLeadSummary(table, categories);
|
||||
document.getElementById("table-note").textContent =
|
||||
table.length > 0 ? `当前展示 ${table.length} 条热点` : "暂无热榜数据";
|
||||
|
||||
renderTable(table);
|
||||
ensureCharts();
|
||||
if (window.echarts) {
|
||||
renderBarChart(categories);
|
||||
renderTopChart(table);
|
||||
renderPieChart(categories);
|
||||
renderBubbleChart(table);
|
||||
}
|
||||
}
|
||||
|
||||
window.addEventListener("resize", () => {
|
||||
Object.values(charts).forEach((chart) => chart && chart.resize());
|
||||
});
|
||||
|
||||
render(defaultPayload);
|
||||
</script>
|
||||
</body>
|
||||
</html>
|
||||
@@ -7,9 +7,7 @@ use std::path::PathBuf;
|
||||
use crate::compat::config_adapter::resolve_skills_dir_from_sgclaw_settings;
|
||||
use crate::compat::runtime::CompatTaskContext;
|
||||
use crate::config::SgClawSettings;
|
||||
use crate::pipe::{
|
||||
AgentMessage, BrowserMessage, BrowserPipeTool, PipeError, Transport,
|
||||
};
|
||||
use crate::pipe::{AgentMessage, BrowserMessage, BrowserPipeTool, PipeError, Transport};
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq)]
|
||||
pub struct AgentRuntimeContext {
|
||||
@@ -166,8 +164,9 @@ pub fn handle_browser_message_with_context<T: Transport + 'static>(
|
||||
page_url,
|
||||
page_title,
|
||||
} => {
|
||||
let instruction = instruction.trim().to_string();
|
||||
if instruction.is_empty() {
|
||||
let raw_instruction = instruction;
|
||||
let trimmed_instruction = raw_instruction.trim().to_string();
|
||||
if trimmed_instruction.is_empty() {
|
||||
return transport.send(&AgentMessage::TaskComplete {
|
||||
success: false,
|
||||
summary: "请输入任务内容。".to_string(),
|
||||
@@ -181,6 +180,25 @@ pub fn handle_browser_message_with_context<T: Transport + 'static>(
|
||||
page_url: (!page_url.trim().is_empty()).then_some(page_url),
|
||||
page_title: (!page_title.trim().is_empty()).then_some(page_title),
|
||||
};
|
||||
let mut instruction = trimmed_instruction;
|
||||
let mut deterministic_plan = None;
|
||||
match crate::compat::deterministic_submit::decide_deterministic_submit(
|
||||
&raw_instruction,
|
||||
task_context.page_url.as_deref(),
|
||||
task_context.page_title.as_deref(),
|
||||
) {
|
||||
crate::compat::deterministic_submit::DeterministicSubmitDecision::NotDeterministic => {}
|
||||
crate::compat::deterministic_submit::DeterministicSubmitDecision::Prompt { summary } => {
|
||||
return transport.send(&AgentMessage::TaskComplete {
|
||||
success: false,
|
||||
summary,
|
||||
});
|
||||
}
|
||||
crate::compat::deterministic_submit::DeterministicSubmitDecision::Execute(plan) => {
|
||||
instruction = plan.instruction.clone();
|
||||
deterministic_plan = Some(plan);
|
||||
}
|
||||
}
|
||||
let _ = transport.send(&AgentMessage::LogEntry {
|
||||
level: "info".to_string(),
|
||||
message: runtime_version_log_message(),
|
||||
@@ -218,10 +236,28 @@ pub fn handle_browser_message_with_context<T: Transport + 'static>(
|
||||
level: "info".to_string(),
|
||||
message: format!(
|
||||
"runtime profile={:?} skills_prompt_mode={:?}",
|
||||
settings.runtime_profile,
|
||||
settings.skills_prompt_mode
|
||||
settings.runtime_profile, settings.skills_prompt_mode
|
||||
),
|
||||
});
|
||||
if let Some(plan) = deterministic_plan.as_ref() {
|
||||
let _ = send_mode_log(transport, "direct_skill_primary");
|
||||
let completion = match crate::compat::deterministic_submit::execute_deterministic_submit(
|
||||
browser_tool.clone(),
|
||||
plan,
|
||||
&context.workspace_root,
|
||||
&settings,
|
||||
) {
|
||||
Ok(outcome) => AgentMessage::TaskComplete {
|
||||
success: outcome.success,
|
||||
summary: outcome.summary,
|
||||
},
|
||||
Err(err) => AgentMessage::TaskComplete {
|
||||
success: false,
|
||||
summary: err.to_string(),
|
||||
},
|
||||
};
|
||||
return transport.send(&completion);
|
||||
}
|
||||
if crate::compat::orchestration::should_use_primary_orchestration(
|
||||
&instruction,
|
||||
task_context.page_url.as_deref(),
|
||||
@@ -250,6 +286,31 @@ pub fn handle_browser_message_with_context<T: Transport + 'static>(
|
||||
}
|
||||
}
|
||||
}
|
||||
if settings
|
||||
.direct_submit_skill
|
||||
.as_deref()
|
||||
.map(str::trim)
|
||||
.is_some_and(|value| !value.is_empty())
|
||||
{
|
||||
let _ = send_mode_log(transport, "direct_skill_primary");
|
||||
let completion = match crate::compat::direct_skill_runtime::execute_direct_submit_skill(
|
||||
browser_tool.clone(),
|
||||
&instruction,
|
||||
&task_context,
|
||||
&context.workspace_root,
|
||||
&settings,
|
||||
) {
|
||||
Ok(outcome) => AgentMessage::TaskComplete {
|
||||
success: outcome.success,
|
||||
summary: outcome.summary,
|
||||
},
|
||||
Err(err) => AgentMessage::TaskComplete {
|
||||
success: false,
|
||||
summary: err.to_string(),
|
||||
},
|
||||
};
|
||||
return transport.send(&completion);
|
||||
}
|
||||
let _ = send_mode_log(transport, "compat_llm_primary");
|
||||
match crate::compat::runtime::execute_task_with_sgclaw_settings(
|
||||
transport,
|
||||
|
||||
@@ -189,7 +189,10 @@ fn plan_zhihu_search(query: &str) -> TaskPlan {
|
||||
|
||||
fn build_zhihu_hotlist_preview(instruction: &str) -> ExecutionPreview {
|
||||
let normalized = instruction.to_ascii_lowercase();
|
||||
if normalized.contains("dashboard") || instruction.contains("大屏") || instruction.contains("新标签页") {
|
||||
if normalized.contains("dashboard")
|
||||
|| instruction.contains("大屏")
|
||||
|| instruction.contains("新标签页")
|
||||
{
|
||||
return ExecutionPreview {
|
||||
summary: "先规划再执行知乎热榜大屏生成".to_string(),
|
||||
steps: vec![
|
||||
|
||||
@@ -3,6 +3,10 @@ use serde_json::{json, Map, Value};
|
||||
use crate::llm::{ChatMessage, LlmError, LlmProvider, ToolDefinition, ToolFunctionCall};
|
||||
use crate::pipe::{Action, AgentMessage, BrowserPipeTool, PipeError, Transport};
|
||||
|
||||
/// Legacy browser-only runtime kept for dev-only validation and narrow regression coverage.
|
||||
/// Production browser submit flow uses `compat::runtime` plus `runtime::engine`.
|
||||
pub const LEGACY_DEV_ONLY: bool = true;
|
||||
|
||||
const BROWSER_ACTION_TOOL_NAME: &str = "browser_action";
|
||||
|
||||
#[derive(Debug, Clone, PartialEq)]
|
||||
@@ -21,8 +25,7 @@ pub fn execute_task_with_provider<P: LlmProvider, T: Transport>(
|
||||
let messages = vec![
|
||||
ChatMessage {
|
||||
role: "system".to_string(),
|
||||
content: "You are sgClaw. Use browser_action to complete the browser task."
|
||||
.to_string(),
|
||||
content: "You are sgClaw. Use browser_action to complete the browser task.".to_string(),
|
||||
},
|
||||
ChatMessage {
|
||||
role: "user".to_string(),
|
||||
@@ -35,8 +38,8 @@ pub fn execute_task_with_provider<P: LlmProvider, T: Transport>(
|
||||
.map_err(map_llm_error_to_pipe_error)?;
|
||||
|
||||
for call in calls {
|
||||
let browser_call = parse_browser_action_call(call)
|
||||
.map_err(|err| PipeError::Protocol(err.to_string()))?;
|
||||
let browser_call =
|
||||
parse_browser_action_call(call).map_err(|err| PipeError::Protocol(err.to_string()))?;
|
||||
|
||||
transport.send(&AgentMessage::LogEntry {
|
||||
level: "info".to_string(),
|
||||
|
||||
@@ -13,6 +13,7 @@ use crate::pipe::{Action, BrowserPipeTool, Transport};
|
||||
pub struct BrowserScriptSkillTool<T: Transport> {
|
||||
tool_name: String,
|
||||
tool_description: String,
|
||||
skill_root: PathBuf,
|
||||
script_path: PathBuf,
|
||||
args: HashMap<String, String>,
|
||||
browser_tool: BrowserPipeTool<T>,
|
||||
@@ -25,22 +26,13 @@ impl<T: Transport> BrowserScriptSkillTool<T> {
|
||||
skill_root: &Path,
|
||||
browser_tool: BrowserPipeTool<T>,
|
||||
) -> anyhow::Result<Self> {
|
||||
let script_path = skill_root.join(&tool.command);
|
||||
let canonical_skill_root = skill_root.canonicalize().unwrap_or_else(|_| skill_root.to_path_buf());
|
||||
let canonical_script_path = script_path
|
||||
.canonicalize()
|
||||
.map_err(|err| anyhow::anyhow!("failed to resolve browser script {}: {err}", script_path.display()))?;
|
||||
if !canonical_script_path.starts_with(&canonical_skill_root) {
|
||||
anyhow::bail!(
|
||||
"browser script path escapes skill root: {}",
|
||||
canonical_script_path.display()
|
||||
);
|
||||
}
|
||||
let script_path = resolve_browser_script_path(skill_root, &tool.command)?;
|
||||
|
||||
Ok(Self {
|
||||
tool_name: format!("{}.{}", skill_name, tool.name),
|
||||
tool_description: tool.description.clone(),
|
||||
script_path: canonical_script_path,
|
||||
skill_root: skill_root.to_path_buf(),
|
||||
script_path,
|
||||
args: tool.args.clone(),
|
||||
browser_tool,
|
||||
})
|
||||
@@ -92,78 +84,103 @@ impl<T: Transport + 'static> Tool for BrowserScriptSkillTool<T> {
|
||||
}
|
||||
|
||||
async fn execute(&self, args: Value) -> anyhow::Result<ToolResult> {
|
||||
let mut args = match args {
|
||||
Value::Object(args) => args,
|
||||
other => {
|
||||
return Ok(failed_tool_result(format!(
|
||||
"expected object arguments, got {other}"
|
||||
)))
|
||||
}
|
||||
let tool = SkillTool {
|
||||
name: self.tool_name.clone(),
|
||||
description: self.tool_description.clone(),
|
||||
kind: "browser_script".to_string(),
|
||||
command: self.script_path.to_string_lossy().into_owned(),
|
||||
args: self.args.clone(),
|
||||
};
|
||||
|
||||
let raw_expected_domain = match args.remove("expected_domain") {
|
||||
Some(Value::String(value)) if !value.trim().is_empty() => value,
|
||||
Some(other) => {
|
||||
return Ok(failed_tool_result(format!(
|
||||
"expected_domain must be a non-empty string, got {other}"
|
||||
)))
|
||||
}
|
||||
None => return Ok(failed_tool_result("missing required field expected_domain".to_string())),
|
||||
};
|
||||
let expected_domain = match normalize_domain_like(&raw_expected_domain) {
|
||||
Some(value) => value,
|
||||
None => {
|
||||
return Ok(failed_tool_result(format!(
|
||||
"expected_domain must resolve to a hostname, got {raw_expected_domain:?}"
|
||||
)))
|
||||
}
|
||||
};
|
||||
|
||||
for required_arg in self.args.keys() {
|
||||
if !args.contains_key(required_arg) {
|
||||
return Ok(failed_tool_result(format!(
|
||||
"missing required field {required_arg}"
|
||||
)));
|
||||
}
|
||||
}
|
||||
|
||||
let script_body = match fs::read_to_string(&self.script_path) {
|
||||
Ok(value) => value,
|
||||
Err(err) => {
|
||||
return Ok(failed_tool_result(format!(
|
||||
"failed to read browser script {}: {err}",
|
||||
self.script_path.display()
|
||||
)))
|
||||
}
|
||||
};
|
||||
|
||||
let wrapped_script = wrap_browser_script(&script_body, &Value::Object(args.clone()));
|
||||
let result = match self.browser_tool.invoke(
|
||||
Action::Eval,
|
||||
json!({ "script": wrapped_script }),
|
||||
&expected_domain,
|
||||
) {
|
||||
Ok(result) => result,
|
||||
Err(err) => return Ok(failed_tool_result(err.to_string())),
|
||||
};
|
||||
|
||||
if !result.success {
|
||||
return Ok(failed_tool_result(format_browser_script_error(&result.data)));
|
||||
}
|
||||
|
||||
let payload = result
|
||||
.data
|
||||
.get("text")
|
||||
.cloned()
|
||||
.unwrap_or_else(|| result.data.clone());
|
||||
Ok(ToolResult {
|
||||
success: true,
|
||||
output: stringify_tool_payload(&payload)?,
|
||||
error: None,
|
||||
})
|
||||
execute_browser_script_tool(&tool, &self.skill_root, self.browser_tool.clone(), args).await
|
||||
}
|
||||
}
|
||||
|
||||
pub async fn execute_browser_script_tool<T: Transport + 'static>(
|
||||
tool: &SkillTool,
|
||||
skill_root: &Path,
|
||||
browser_tool: BrowserPipeTool<T>,
|
||||
args: Value,
|
||||
) -> anyhow::Result<ToolResult> {
|
||||
if tool.kind != "browser_script" {
|
||||
return Ok(failed_tool_result(format!(
|
||||
"browser script tool kind must be browser_script, got {}",
|
||||
tool.kind
|
||||
)));
|
||||
}
|
||||
|
||||
let script_path = resolve_browser_script_path(skill_root, &tool.command)?;
|
||||
let mut args = match args {
|
||||
Value::Object(args) => args,
|
||||
other => return Ok(failed_tool_result(format!("expected object arguments, got {other}"))),
|
||||
};
|
||||
|
||||
let raw_expected_domain = match args.remove("expected_domain") {
|
||||
Some(Value::String(value)) if !value.trim().is_empty() => value,
|
||||
Some(other) => {
|
||||
return Ok(failed_tool_result(format!(
|
||||
"expected_domain must be a non-empty string, got {other}"
|
||||
)))
|
||||
}
|
||||
None => {
|
||||
return Ok(failed_tool_result(
|
||||
"missing required field expected_domain".to_string(),
|
||||
))
|
||||
}
|
||||
};
|
||||
let expected_domain = match normalize_domain_like(&raw_expected_domain) {
|
||||
Some(value) => value,
|
||||
None => {
|
||||
return Ok(failed_tool_result(format!(
|
||||
"expected_domain must resolve to a hostname, got {raw_expected_domain:?}"
|
||||
)))
|
||||
}
|
||||
};
|
||||
|
||||
for required_arg in tool.args.keys() {
|
||||
if !args.contains_key(required_arg) {
|
||||
return Ok(failed_tool_result(format!(
|
||||
"missing required field {required_arg}"
|
||||
)));
|
||||
}
|
||||
}
|
||||
|
||||
let script_body = match fs::read_to_string(&script_path) {
|
||||
Ok(value) => value,
|
||||
Err(err) => {
|
||||
return Ok(failed_tool_result(format!(
|
||||
"failed to read browser script {}: {err}",
|
||||
script_path.display()
|
||||
)))
|
||||
}
|
||||
};
|
||||
|
||||
let wrapped_script = wrap_browser_script(&script_body, &Value::Object(args.clone()));
|
||||
let result = match browser_tool.invoke(
|
||||
Action::Eval,
|
||||
json!({ "script": wrapped_script }),
|
||||
&expected_domain,
|
||||
) {
|
||||
Ok(result) => result,
|
||||
Err(err) => return Ok(failed_tool_result(err.to_string())),
|
||||
};
|
||||
|
||||
if !result.success {
|
||||
return Ok(failed_tool_result(format_browser_script_error(&result.data)));
|
||||
}
|
||||
|
||||
let payload = result
|
||||
.data
|
||||
.get("text")
|
||||
.cloned()
|
||||
.unwrap_or_else(|| result.data.clone());
|
||||
Ok(ToolResult {
|
||||
success: true,
|
||||
output: stringify_tool_payload(&payload)?,
|
||||
error: None,
|
||||
})
|
||||
}
|
||||
|
||||
pub fn build_browser_script_skill_tools<T: Transport + 'static>(
|
||||
skills: &[Skill],
|
||||
browser_tool: BrowserPipeTool<T>,
|
||||
@@ -202,6 +219,32 @@ fn wrap_browser_script(script_body: &str, args: &Value) -> String {
|
||||
)
|
||||
}
|
||||
|
||||
fn resolve_browser_script_path(skill_root: &Path, command: &str) -> anyhow::Result<PathBuf> {
|
||||
let script_path = PathBuf::from(command);
|
||||
let script_path = if script_path.is_absolute() {
|
||||
script_path
|
||||
} else {
|
||||
skill_root.join(script_path)
|
||||
};
|
||||
let canonical_skill_root = skill_root
|
||||
.canonicalize()
|
||||
.unwrap_or_else(|_| skill_root.to_path_buf());
|
||||
let canonical_script_path = script_path.canonicalize().map_err(|err| {
|
||||
anyhow::anyhow!(
|
||||
"failed to resolve browser script {}: {err}",
|
||||
script_path.display()
|
||||
)
|
||||
})?;
|
||||
if !canonical_script_path.starts_with(&canonical_skill_root) {
|
||||
anyhow::bail!(
|
||||
"browser script path escapes skill root: {}",
|
||||
canonical_script_path.display()
|
||||
);
|
||||
}
|
||||
|
||||
Ok(canonical_script_path)
|
||||
}
|
||||
|
||||
fn stringify_tool_payload(payload: &Value) -> anyhow::Result<String> {
|
||||
Ok(match payload {
|
||||
Value::String(value) => value.clone(),
|
||||
|
||||
@@ -101,14 +101,14 @@ impl<T: Transport + 'static> Tool for ZeroClawBrowserTool<T> {
|
||||
Err(err) => return Ok(failed_tool_result(err.to_string())),
|
||||
};
|
||||
|
||||
let result = match self.browser_tool.invoke(
|
||||
request.action,
|
||||
request.params,
|
||||
&request.expected_domain,
|
||||
) {
|
||||
Ok(result) => result,
|
||||
Err(err) => return Ok(failed_tool_result(err.to_string())),
|
||||
};
|
||||
let result =
|
||||
match self
|
||||
.browser_tool
|
||||
.invoke(request.action, request.params, &request.expected_domain)
|
||||
{
|
||||
Ok(result) => result,
|
||||
Err(err) => return Ok(failed_tool_result(err.to_string())),
|
||||
};
|
||||
|
||||
let output = serde_json::to_string(&json!({
|
||||
"seq": result.seq,
|
||||
@@ -122,8 +122,7 @@ impl<T: Transport + 'static> Tool for ZeroClawBrowserTool<T> {
|
||||
Ok(ToolResult {
|
||||
success: result.success,
|
||||
output,
|
||||
error: (!result.success)
|
||||
.then(|| format_browser_action_error(&result.data)),
|
||||
error: (!result.success).then(|| format_browser_action_error(&result.data)),
|
||||
})
|
||||
}
|
||||
}
|
||||
@@ -134,7 +133,9 @@ struct BrowserActionRequest {
|
||||
params: Value,
|
||||
}
|
||||
|
||||
fn parse_browser_action_request(args: Value) -> Result<BrowserActionRequest, BrowserActionAdapterError> {
|
||||
fn parse_browser_action_request(
|
||||
args: Value,
|
||||
) -> Result<BrowserActionRequest, BrowserActionAdapterError> {
|
||||
let mut args = match args {
|
||||
Value::Object(args) => args,
|
||||
other => {
|
||||
|
||||
@@ -2,8 +2,8 @@ use std::collections::HashMap;
|
||||
use std::ffi::OsStr;
|
||||
use std::path::{Path, PathBuf};
|
||||
|
||||
use zeroclaw::Config as ZeroClawConfig;
|
||||
use zeroclaw::config::schema::ModelProviderConfig;
|
||||
use zeroclaw::Config as ZeroClawConfig;
|
||||
|
||||
use crate::compat::cron_adapter::configure_embedded_cron;
|
||||
use crate::compat::memory_adapter::configure_embedded_memory;
|
||||
@@ -13,7 +13,9 @@ use crate::runtime::RuntimeProfile;
|
||||
const SGCLAW_ZEROCLAW_WORKSPACE_DIR: &str = ".sgclaw-zeroclaw-workspace";
|
||||
const SKILLS_DIR_NAME: &str = "skills";
|
||||
|
||||
pub fn build_zeroclaw_config(workspace_root: &Path) -> Result<ZeroClawConfig, crate::config::ConfigError> {
|
||||
pub fn build_zeroclaw_config(
|
||||
workspace_root: &Path,
|
||||
) -> Result<ZeroClawConfig, crate::config::ConfigError> {
|
||||
let settings = SgClawSettings::from_env()?;
|
||||
Ok(build_zeroclaw_config_from_sgclaw_settings(
|
||||
workspace_root,
|
||||
|
||||
@@ -65,7 +65,10 @@ where
|
||||
|
||||
for job in jobs {
|
||||
if !matches!(job.job_type, JobType::Agent) {
|
||||
anyhow::bail!("unsupported cron job type in sgclaw compat: {:?}", job.job_type);
|
||||
anyhow::bail!(
|
||||
"unsupported cron job type in sgclaw compat: {:?}",
|
||||
job.job_type
|
||||
);
|
||||
}
|
||||
|
||||
let started_at = Utc::now();
|
||||
|
||||
272
src/compat/deterministic_submit.rs
Normal file
272
src/compat/deterministic_submit.rs
Normal file
@@ -0,0 +1,272 @@
|
||||
use std::path::Path;
|
||||
|
||||
use serde_json::{Map, Value};
|
||||
|
||||
use crate::compat::direct_skill_runtime::DirectSubmitOutcome;
|
||||
use crate::config::SgClawSettings;
|
||||
use crate::pipe::{BrowserPipeTool, PipeError, Transport};
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq)]
|
||||
pub struct DeterministicExecutionPlan {
|
||||
pub instruction: String,
|
||||
pub tool_name: String,
|
||||
pub expected_domain: String,
|
||||
pub org_label: String,
|
||||
pub org_code: String,
|
||||
pub period_mode: String,
|
||||
pub period_mode_code: String,
|
||||
pub period_value: String,
|
||||
pub period_payload: String,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq)]
|
||||
pub enum DeterministicSubmitDecision {
|
||||
NotDeterministic,
|
||||
Prompt { summary: String },
|
||||
Execute(DeterministicExecutionPlan),
|
||||
}
|
||||
|
||||
const DETERMINISTIC_SUFFIX: &str = "。。。";
|
||||
const LINELLOSS_HOST: &str = "20.76.57.61";
|
||||
const LINELLOSS_TOOL: &str = "tq-lineloss-report.collect_lineloss";
|
||||
|
||||
pub fn decide_deterministic_submit(
|
||||
raw_instruction: &str,
|
||||
page_url: Option<&str>,
|
||||
page_title: Option<&str>,
|
||||
) -> DeterministicSubmitDecision {
|
||||
let Some(instruction) = strip_exact_deterministic_suffix(raw_instruction) else {
|
||||
return DeterministicSubmitDecision::NotDeterministic;
|
||||
};
|
||||
|
||||
let normalized_instruction = instruction.trim();
|
||||
if normalized_instruction.is_empty() {
|
||||
return unsupported_scene_prompt();
|
||||
}
|
||||
|
||||
if !matches_lineloss_scene(normalized_instruction) {
|
||||
return unsupported_scene_prompt();
|
||||
}
|
||||
|
||||
let resolved_org = match crate::compat::tq_lineloss::org_resolver::resolve_org_from_instruction(
|
||||
normalized_instruction,
|
||||
) {
|
||||
Ok(Some(resolved_org)) => resolved_org,
|
||||
Ok(None) => {
|
||||
return DeterministicSubmitDecision::Prompt {
|
||||
summary: crate::compat::tq_lineloss::contracts::missing_company_prompt(),
|
||||
};
|
||||
}
|
||||
Err(summary) => {
|
||||
return DeterministicSubmitDecision::Prompt { summary };
|
||||
}
|
||||
};
|
||||
|
||||
let resolved_period = match crate::compat::tq_lineloss::period_resolver::resolve_period(
|
||||
normalized_instruction,
|
||||
) {
|
||||
Ok(resolved_period) => resolved_period,
|
||||
Err(summary) => {
|
||||
return DeterministicSubmitDecision::Prompt { summary };
|
||||
}
|
||||
};
|
||||
|
||||
if page_context_conflicts_with_lineloss(page_url, page_title) {
|
||||
return DeterministicSubmitDecision::Prompt {
|
||||
summary:
|
||||
"已命中台区线损报表技能，但当前页面与台区线损场景不匹配，请切换到线损页面后重试。"
|
||||
.to_string(),
|
||||
};
|
||||
}
|
||||
|
||||
DeterministicSubmitDecision::Execute(DeterministicExecutionPlan {
|
||||
instruction: normalized_instruction.to_string(),
|
||||
tool_name: LINELLOSS_TOOL.to_string(),
|
||||
expected_domain: LINELLOSS_HOST.to_string(),
|
||||
org_label: resolved_org.label,
|
||||
org_code: resolved_org.code,
|
||||
period_mode: period_mode_name(&resolved_period.mode).to_string(),
|
||||
period_mode_code: resolved_period.mode_code,
|
||||
period_value: resolved_period.value,
|
||||
period_payload: serde_json::to_string(&resolved_period.payload)
|
||||
.unwrap_or_else(|_| "{}".to_string()),
|
||||
})
|
||||
}
|
||||
|
||||
pub fn execute_deterministic_submit<T: Transport + 'static>(
|
||||
browser_tool: BrowserPipeTool<T>,
|
||||
plan: &DeterministicExecutionPlan,
|
||||
workspace_root: &Path,
|
||||
settings: &SgClawSettings,
|
||||
) -> Result<DirectSubmitOutcome, PipeError> {
|
||||
let mut args = Map::new();
|
||||
args.insert(
|
||||
"expected_domain".to_string(),
|
||||
Value::String(plan.expected_domain.clone()),
|
||||
);
|
||||
args.insert(
|
||||
"org_label".to_string(),
|
||||
Value::String(plan.org_label.clone()),
|
||||
);
|
||||
args.insert(
|
||||
"org_code".to_string(),
|
||||
Value::String(plan.org_code.clone()),
|
||||
);
|
||||
args.insert(
|
||||
"period_mode".to_string(),
|
||||
Value::String(plan.period_mode.clone()),
|
||||
);
|
||||
args.insert(
|
||||
"period_mode_code".to_string(),
|
||||
Value::String(plan.period_mode_code.clone()),
|
||||
);
|
||||
args.insert(
|
||||
"period_value".to_string(),
|
||||
Value::String(plan.period_value.clone()),
|
||||
);
|
||||
args.insert(
|
||||
"period_payload".to_string(),
|
||||
Value::String(plan.period_payload.clone()),
|
||||
);
|
||||
|
||||
let output = crate::compat::direct_skill_runtime::execute_browser_script_skill_raw_output(
|
||||
browser_tool,
|
||||
&plan.tool_name,
|
||||
workspace_root,
|
||||
settings,
|
||||
args,
|
||||
)?;
|
||||
|
||||
Ok(summarize_lineloss_output(&output))
|
||||
}
|
||||
|
||||
fn summarize_lineloss_output(output: &str) -> DirectSubmitOutcome {
|
||||
let Some(payload) = serde_json::from_str::<Value>(output).ok() else {
|
||||
return DirectSubmitOutcome {
|
||||
success: true,
|
||||
summary: output.to_string(),
|
||||
};
|
||||
};
|
||||
|
||||
let artifact = payload
|
||||
.as_object()
|
||||
.and_then(|object| object.get("text"))
|
||||
.unwrap_or(&payload);
|
||||
|
||||
summarize_lineloss_artifact(artifact)
|
||||
}
|
||||
|
||||
fn summarize_lineloss_artifact(artifact: &Value) -> DirectSubmitOutcome {
|
||||
let Some(artifact) = artifact.as_object() else {
|
||||
return DirectSubmitOutcome {
|
||||
success: true,
|
||||
summary: artifact.to_string(),
|
||||
};
|
||||
};
|
||||
|
||||
if artifact.get("type").and_then(Value::as_str) != Some("report-artifact") {
|
||||
return DirectSubmitOutcome {
|
||||
success: true,
|
||||
summary: Value::Object(artifact.clone()).to_string(),
|
||||
};
|
||||
}
|
||||
|
||||
let status = artifact
|
||||
.get("status")
|
||||
.and_then(Value::as_str)
|
||||
.unwrap_or("ok");
|
||||
let success = matches!(status, "ok" | "partial" | "empty");
|
||||
let report_name = artifact
|
||||
.get("report_name")
|
||||
.and_then(Value::as_str)
|
||||
.unwrap_or("tq-lineloss-report");
|
||||
let org_label = artifact
|
||||
.get("org")
|
||||
.and_then(Value::as_object)
|
||||
.and_then(|org| org.get("label"))
|
||||
.and_then(Value::as_str)
|
||||
.unwrap_or("");
|
||||
let period_value = artifact
|
||||
.get("period")
|
||||
.and_then(Value::as_object)
|
||||
.and_then(|period| period.get("value"))
|
||||
.and_then(Value::as_str)
|
||||
.unwrap_or("");
|
||||
let rows = artifact
|
||||
.get("counts")
|
||||
.and_then(Value::as_object)
|
||||
.and_then(|counts| counts.get("rows"))
|
||||
.and_then(Value::as_u64)
|
||||
.map(|value| value as usize)
|
||||
.or_else(|| artifact.get("rows").and_then(Value::as_array).map(Vec::len))
|
||||
.unwrap_or(0);
|
||||
let reasons = artifact
|
||||
.get("reasons")
|
||||
.and_then(Value::as_array)
|
||||
.map(|reasons| {
|
||||
reasons
|
||||
.iter()
|
||||
.filter_map(Value::as_str)
|
||||
.filter(|value| !value.trim().is_empty())
|
||||
.collect::<Vec<_>>()
|
||||
})
|
||||
.unwrap_or_default();
|
||||
|
||||
let mut parts = vec![report_name.to_string()];
|
||||
if !org_label.is_empty() {
|
||||
parts.push(org_label.to_string());
|
||||
}
|
||||
if !period_value.is_empty() {
|
||||
parts.push(period_value.to_string());
|
||||
}
|
||||
parts.push(format!("status={status}"));
|
||||
parts.push(format!("rows={rows}"));
|
||||
if !reasons.is_empty() {
|
||||
parts.push(format!("reasons={}", reasons.join(",")));
|
||||
}
|
||||
|
||||
DirectSubmitOutcome {
|
||||
success,
|
||||
summary: parts.join(" "),
|
||||
}
|
||||
}
|
||||
|
||||
fn strip_exact_deterministic_suffix(raw_instruction: &str) -> Option<&str> {
|
||||
let without_suffix = raw_instruction.strip_suffix(DETERMINISTIC_SUFFIX)?;
|
||||
if without_suffix.ends_with('。') {
|
||||
return None;
|
||||
}
|
||||
Some(without_suffix)
|
||||
}
|
||||
|
||||
fn matches_lineloss_scene(instruction: &str) -> bool {
|
||||
instruction.contains("线损") || instruction.contains("月累计") || instruction.contains("周累计")
|
||||
}
|
||||
|
||||
fn page_context_conflicts_with_lineloss(page_url: Option<&str>, page_title: Option<&str>) -> bool {
|
||||
let url = page_url.unwrap_or_default().to_ascii_lowercase();
|
||||
let title = page_title.unwrap_or_default();
|
||||
let has_context = !url.is_empty() || !title.is_empty();
|
||||
if !has_context {
|
||||
return false;
|
||||
}
|
||||
|
||||
let url_matches = url.contains(LINELLOSS_HOST) || url.contains("lineloss");
|
||||
let title_matches = title.contains("线损");
|
||||
|
||||
!(url_matches || title_matches)
|
||||
}
|
||||
|
||||
fn period_mode_name(mode: &crate::compat::tq_lineloss::contracts::PeriodMode) -> &'static str {
|
||||
match mode {
|
||||
crate::compat::tq_lineloss::contracts::PeriodMode::Month => "month",
|
||||
crate::compat::tq_lineloss::contracts::PeriodMode::Week => "week",
|
||||
}
|
||||
}
|
||||
|
||||
fn unsupported_scene_prompt() -> DeterministicSubmitDecision {
|
||||
DeterministicSubmitDecision::Prompt {
|
||||
summary: "确定性提交当前只支持台区线损月/周累计线损率报表场景，请补充台区线损请求。"
|
||||
.to_string(),
|
||||
}
|
||||
}
|
||||
371
src/compat/direct_skill_runtime.rs
Normal file
371
src/compat/direct_skill_runtime.rs
Normal file
@@ -0,0 +1,371 @@
|
||||
use std::path::Path;
|
||||
|
||||
use reqwest::Url;
|
||||
use serde_json::{Map, Value};
|
||||
use zeroclaw::skills::{load_skills_from_directory, SkillTool};
|
||||
|
||||
use crate::compat::browser_script_skill_tool::execute_browser_script_tool;
|
||||
use crate::compat::config_adapter::resolve_skills_dir_from_sgclaw_settings;
|
||||
use crate::compat::runtime::CompatTaskContext;
|
||||
use crate::config::SgClawSettings;
|
||||
use crate::pipe::{BrowserPipeTool, PipeError, Transport};
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq)]
|
||||
pub struct DirectSubmitOutcome {
|
||||
pub success: bool,
|
||||
pub summary: String,
|
||||
}
|
||||
|
||||
pub fn execute_direct_submit_skill<T: Transport + 'static>(
|
||||
browser_tool: BrowserPipeTool<T>,
|
||||
instruction: &str,
|
||||
task_context: &CompatTaskContext,
|
||||
workspace_root: &Path,
|
||||
settings: &SgClawSettings,
|
||||
) -> Result<DirectSubmitOutcome, PipeError> {
|
||||
let configured_tool = settings
|
||||
.direct_submit_skill
|
||||
.as_deref()
|
||||
.map(str::trim)
|
||||
.filter(|value| !value.is_empty())
|
||||
.ok_or_else(|| PipeError::Protocol("direct submit skill is not configured".to_string()))?;
|
||||
let expected_domain = derive_expected_domain(task_context)?;
|
||||
let period = derive_period(instruction)?;
|
||||
|
||||
let mut args = Map::new();
|
||||
args.insert("expected_domain".to_string(), Value::String(expected_domain));
|
||||
args.insert("period".to_string(), Value::String(period));
|
||||
|
||||
let output = execute_browser_script_skill_raw_output(
|
||||
browser_tool,
|
||||
configured_tool,
|
||||
workspace_root,
|
||||
settings,
|
||||
args,
|
||||
)?;
|
||||
|
||||
Ok(interpret_direct_submit_output(&output))
|
||||
}
|
||||
|
||||
pub fn execute_browser_script_skill_raw_output<T: Transport + 'static>(
|
||||
browser_tool: BrowserPipeTool<T>,
|
||||
configured_tool: &str,
|
||||
workspace_root: &Path,
|
||||
settings: &SgClawSettings,
|
||||
args: Map<String, Value>,
|
||||
) -> Result<String, PipeError> {
|
||||
let (skill_name, tool_name) = parse_configured_tool_name(configured_tool)?;
|
||||
let skills_dir = resolve_skills_dir_from_sgclaw_settings(workspace_root, settings);
|
||||
let skills = load_skills_from_directory(&skills_dir, true);
|
||||
let skill = skills
|
||||
.iter()
|
||||
.find(|skill| skill.name == skill_name)
|
||||
.ok_or_else(|| {
|
||||
PipeError::Protocol(format!(
|
||||
"direct submit skill {skill_name} was not found in {}",
|
||||
skills_dir.display()
|
||||
))
|
||||
})?;
|
||||
let tool = skill
|
||||
.tools
|
||||
.iter()
|
||||
.find(|tool| tool.name == tool_name)
|
||||
.ok_or_else(|| {
|
||||
PipeError::Protocol(format!(
|
||||
"direct submit tool {configured_tool} was not found"
|
||||
))
|
||||
})?;
|
||||
|
||||
let skill_root = skill
|
||||
.location
|
||||
.as_deref()
|
||||
.and_then(Path::parent)
|
||||
.ok_or_else(|| {
|
||||
PipeError::Protocol(format!(
|
||||
"direct submit skill {skill_name} is missing a resolvable location"
|
||||
))
|
||||
})?;
|
||||
|
||||
execute_browser_script_tool_output(browser_tool, configured_tool, tool, skill_root, args)
|
||||
}
|
||||
|
||||
fn execute_browser_script_tool_output<T: Transport + 'static>(
|
||||
browser_tool: BrowserPipeTool<T>,
|
||||
configured_tool: &str,
|
||||
tool: &SkillTool,
|
||||
skill_root: &Path,
|
||||
args: Map<String, Value>,
|
||||
) -> Result<String, PipeError> {
|
||||
if tool.kind != "browser_script" {
|
||||
return Err(PipeError::Protocol(format!(
|
||||
"direct submit tool {configured_tool} must be browser_script, got {}",
|
||||
tool.kind
|
||||
)));
|
||||
}
|
||||
|
||||
let mut tool = tool.clone();
|
||||
tool.args.remove("expected_domain");
|
||||
|
||||
let runtime = tokio::runtime::Runtime::new()
|
||||
.map_err(|err| PipeError::Protocol(format!("failed to create tokio runtime: {err}")))?;
|
||||
let result = runtime
|
||||
.block_on(execute_browser_script_tool(
|
||||
&tool,
|
||||
skill_root,
|
||||
browser_tool,
|
||||
Value::Object(args),
|
||||
))
|
||||
.map_err(|err| PipeError::Protocol(err.to_string()))?;
|
||||
|
||||
if result.success {
|
||||
Ok(result.output)
|
||||
} else {
|
||||
Err(PipeError::Protocol(
|
||||
result
|
||||
.error
|
||||
.unwrap_or_else(|| "direct submit skill execution failed".to_string()),
|
||||
))
|
||||
}
|
||||
}
|
||||
|
||||
fn interpret_direct_submit_output(output: &str) -> DirectSubmitOutcome {
|
||||
let Some(payload) = serde_json::from_str::<Value>(output).ok() else {
|
||||
return DirectSubmitOutcome {
|
||||
success: true,
|
||||
summary: output.to_string(),
|
||||
};
|
||||
};
|
||||
|
||||
let Some(artifact) = payload.as_object() else {
|
||||
return DirectSubmitOutcome {
|
||||
success: true,
|
||||
summary: output.to_string(),
|
||||
};
|
||||
};
|
||||
|
||||
if artifact.get("type").and_then(Value::as_str) != Some("report-artifact") {
|
||||
return DirectSubmitOutcome {
|
||||
success: true,
|
||||
summary: output.to_string(),
|
||||
};
|
||||
}
|
||||
|
||||
let status = artifact
|
||||
.get("status")
|
||||
.and_then(Value::as_str)
|
||||
.unwrap_or("ok");
|
||||
let success = matches!(status, "ok" | "partial" | "empty");
|
||||
let report_name = artifact
|
||||
.get("report_name")
|
||||
.and_then(Value::as_str)
|
||||
.unwrap_or("report-artifact");
|
||||
let period = artifact
|
||||
.get("period")
|
||||
.and_then(Value::as_str)
|
||||
.unwrap_or("");
|
||||
let detail_rows = count_rows(artifact.get("counts"), artifact.get("rows"), "detail_rows");
|
||||
let summary_rows = count_summary_rows(artifact.get("counts"), artifact.get("sections"));
|
||||
let partial_reasons = artifact
|
||||
.get("partial_reasons")
|
||||
.and_then(Value::as_array)
|
||||
.map(|reasons| {
|
||||
reasons
|
||||
.iter()
|
||||
.filter_map(Value::as_str)
|
||||
.filter(|value| !value.trim().is_empty())
|
||||
.collect::<Vec<_>>()
|
||||
})
|
||||
.unwrap_or_default();
|
||||
|
||||
let mut parts = vec![report_name.to_string()];
|
||||
if !period.trim().is_empty() {
|
||||
parts.push(period.to_string());
|
||||
}
|
||||
parts.push(format!("status={status}"));
|
||||
parts.push(format!("detail_rows={detail_rows}"));
|
||||
parts.push(format!("summary_rows={summary_rows}"));
|
||||
if !partial_reasons.is_empty() {
|
||||
parts.push(format!("partial_reasons={}", partial_reasons.join(",")));
|
||||
}
|
||||
|
||||
DirectSubmitOutcome {
|
||||
success,
|
||||
summary: parts.join(" "),
|
||||
}
|
||||
}
|
||||
|
||||
fn count_rows(counts: Option<&Value>, rows: Option<&Value>, key: &str) -> usize {
|
||||
counts
|
||||
.and_then(Value::as_object)
|
||||
.and_then(|counts| counts.get(key))
|
||||
.and_then(Value::as_u64)
|
||||
.map(|count| count as usize)
|
||||
.or_else(|| rows.and_then(Value::as_array).map(Vec::len))
|
||||
.unwrap_or(0)
|
||||
}
|
||||
|
||||
fn count_summary_rows(counts: Option<&Value>, sections: Option<&Value>) -> usize {
|
||||
counts
|
||||
.and_then(Value::as_object)
|
||||
.and_then(|counts| counts.get("summary_rows"))
|
||||
.and_then(Value::as_u64)
|
||||
.map(|count| count as usize)
|
||||
.or_else(|| {
|
||||
sections
|
||||
.and_then(Value::as_array)
|
||||
.and_then(|sections| {
|
||||
sections.iter().find_map(|section| {
|
||||
section
|
||||
.as_object()
|
||||
.and_then(|section| section.get("rows"))
|
||||
.and_then(Value::as_array)
|
||||
.map(Vec::len)
|
||||
})
|
||||
})
|
||||
})
|
||||
.unwrap_or(0)
|
||||
}
|
||||
|
||||
fn parse_configured_tool_name(configured_tool: &str) -> Result<(&str, &str), PipeError> {
|
||||
let (skill_name, tool_name) = configured_tool.split_once('.').ok_or_else(|| {
|
||||
PipeError::Protocol(format!(
|
||||
"direct submit skill must use skill.tool format, got {configured_tool}"
|
||||
))
|
||||
})?;
|
||||
let skill_name = skill_name.trim();
|
||||
let tool_name = tool_name.trim();
|
||||
if skill_name.is_empty() || tool_name.is_empty() {
|
||||
return Err(PipeError::Protocol(format!(
|
||||
"direct submit skill must use skill.tool format, got {configured_tool}"
|
||||
)));
|
||||
}
|
||||
Ok((skill_name, tool_name))
|
||||
}
|
||||
|
||||
fn derive_expected_domain(task_context: &CompatTaskContext) -> Result<String, PipeError> {
|
||||
let page_url = task_context
|
||||
.page_url
|
||||
.as_deref()
|
||||
.map(str::trim)
|
||||
.filter(|value| !value.is_empty())
|
||||
.ok_or_else(|| {
|
||||
PipeError::Protocol(
|
||||
"direct submit skill requires page_url so expected_domain can be derived"
|
||||
.to_string(),
|
||||
)
|
||||
})?;
|
||||
|
||||
Url::parse(page_url)
|
||||
.ok()
|
||||
.and_then(|url| url.host_str().map(|host| host.to_ascii_lowercase()))
|
||||
.ok_or_else(|| {
|
||||
PipeError::Protocol(format!(
|
||||
"direct submit skill could not derive expected_domain from page_url {page_url:?}"
|
||||
))
|
||||
})
|
||||
}
|
||||
|
||||
fn derive_period(instruction: &str) -> Result<String, PipeError> {
|
||||
let chars = instruction.chars().collect::<Vec<_>>();
|
||||
if chars.len() < 7 {
|
||||
return Err(PipeError::Protocol(
|
||||
"direct submit skill requires an explicit YYYY-MM period in the instruction"
|
||||
.to_string(),
|
||||
));
|
||||
}
|
||||
|
||||
for start in 0..=chars.len() - 7 {
|
||||
let candidate = chars[start..start + 7].iter().collect::<String>();
|
||||
if is_year_month(&candidate) {
|
||||
return Ok(candidate);
|
||||
}
|
||||
}
|
||||
|
||||
Err(PipeError::Protocol(
|
||||
"direct submit skill requires an explicit YYYY-MM period in the instruction"
|
||||
.to_string(),
|
||||
))
|
||||
}
|
||||
|
||||
fn is_year_month(candidate: &str) -> bool {
|
||||
let bytes = candidate.as_bytes();
|
||||
bytes.len() == 7
|
||||
&& bytes[0..4].iter().all(u8::is_ascii_digit)
|
||||
&& bytes[4] == b'-'
|
||||
&& bytes[5..7].iter().all(u8::is_ascii_digit)
|
||||
&& matches!((bytes[5] - b'0') * 10 + (bytes[6] - b'0'), 1..=12)
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::{
|
||||
count_rows, count_summary_rows, derive_period, interpret_direct_submit_output,
|
||||
is_year_month, parse_configured_tool_name,
|
||||
};
|
||||
use serde_json::json;
|
||||
|
||||
#[test]
|
||||
fn parse_configured_tool_name_requires_skill_and_tool() {
|
||||
assert_eq!(
|
||||
parse_configured_tool_name("fault-details-report.collect_fault_details")
|
||||
.unwrap(),
|
||||
("fault-details-report", "collect_fault_details")
|
||||
);
|
||||
assert!(parse_configured_tool_name("fault-details-report").is_err());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn derive_period_requires_explicit_year_month() {
|
||||
assert_eq!(derive_period("收集 2026-03 故障明细").unwrap(), "2026-03");
|
||||
assert!(derive_period("收集三月故障明细").is_err());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn year_month_validation_rejects_invalid_month() {
|
||||
assert!(is_year_month("2026-12"));
|
||||
assert!(!is_year_month("2026-00"));
|
||||
assert!(!is_year_month("2026-13"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn interpret_direct_submit_output_maps_report_artifact_statuses() {
|
||||
let partial = interpret_direct_submit_output(
|
||||
&json!({
|
||||
"type": "report-artifact",
|
||||
"report_name": "fault-details-report",
|
||||
"period": "2026-03",
|
||||
"counts": { "detail_rows": 1, "summary_rows": 1 },
|
||||
"status": "partial",
|
||||
"partial_reasons": ["report_log_failed"]
|
||||
})
|
||||
.to_string(),
|
||||
);
|
||||
assert!(partial.success);
|
||||
assert!(partial.summary.contains("status=partial"));
|
||||
assert!(partial.summary.contains("report_log_failed"));
|
||||
|
||||
let blocked = interpret_direct_submit_output(
|
||||
&json!({
|
||||
"type": "report-artifact",
|
||||
"report_name": "fault-details-report",
|
||||
"status": "blocked",
|
||||
"partial_reasons": ["selected_range_unavailable"]
|
||||
})
|
||||
.to_string(),
|
||||
);
|
||||
assert!(!blocked.success);
|
||||
assert!(blocked.summary.contains("status=blocked"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn row_count_helpers_fall_back_to_payload_shapes() {
|
||||
assert_eq!(
|
||||
count_rows(None, Some(&json!([{ "qxdbh": "QX-1" }, { "qxdbh": "QX-2" }])), "detail_rows"),
|
||||
2
|
||||
);
|
||||
assert_eq!(
|
||||
count_summary_rows(None, Some(&json!([{ "name": "summary-sheet", "rows": [{ "index": 1 }] }]))),
|
||||
1
|
||||
);
|
||||
}
|
||||
}
|
||||
@@ -14,19 +14,17 @@ pub fn log_entry_for_turn_event(
|
||||
level: "info".to_string(),
|
||||
message: format_tool_call(name, args, skill_versions),
|
||||
}),
|
||||
TurnEvent::ToolResult { output, .. } if is_tool_error(output) => Some(AgentMessage::LogEntry {
|
||||
level: "error".to_string(),
|
||||
message: output.trim_start_matches("Error: ").to_string(),
|
||||
}),
|
||||
TurnEvent::ToolResult { output, .. } if is_tool_error(output) => {
|
||||
Some(AgentMessage::LogEntry {
|
||||
level: "error".to_string(),
|
||||
message: output.trim_start_matches("Error: ").to_string(),
|
||||
})
|
||||
}
|
||||
_ => None,
|
||||
}
|
||||
}
|
||||
|
||||
fn format_tool_call(
|
||||
name: &str,
|
||||
args: &Value,
|
||||
skill_versions: &HashMap<String, String>,
|
||||
) -> String {
|
||||
fn format_tool_call(name: &str, args: &Value, skill_versions: &HashMap<String, String>) -> String {
|
||||
if name == "read_skill" {
|
||||
let skill_name = args
|
||||
.get("name")
|
||||
@@ -49,7 +47,10 @@ fn format_tool_call(
|
||||
|
||||
match action {
|
||||
"navigate" => {
|
||||
let url = args.get("url").and_then(Value::as_str).unwrap_or("<missing-url>");
|
||||
let url = args
|
||||
.get("url")
|
||||
.and_then(Value::as_str)
|
||||
.unwrap_or("<missing-url>");
|
||||
format!("navigate {url}")
|
||||
}
|
||||
"type" => {
|
||||
|
||||
@@ -2,10 +2,13 @@ pub mod browser_script_skill_tool;
|
||||
pub mod browser_tool_adapter;
|
||||
pub mod config_adapter;
|
||||
pub mod cron_adapter;
|
||||
pub mod deterministic_submit;
|
||||
pub mod direct_skill_runtime;
|
||||
pub mod event_bridge;
|
||||
pub mod memory_adapter;
|
||||
pub mod openxml_office_tool;
|
||||
pub mod orchestration;
|
||||
pub mod runtime;
|
||||
pub mod screen_html_export_tool;
|
||||
pub mod tq_lineloss;
|
||||
pub mod workflow_executor;
|
||||
|
||||
@@ -1,13 +1,16 @@
|
||||
use async_trait::async_trait;
|
||||
use serde::Deserialize;
|
||||
use serde_json::{json, Value};
|
||||
use std::collections::BTreeSet;
|
||||
use std::collections::BTreeMap;
|
||||
use std::collections::BTreeSet;
|
||||
use std::fs;
|
||||
use std::io::{Read, Write};
|
||||
use std::path::{Path, PathBuf};
|
||||
use std::process::Command;
|
||||
use std::time::{SystemTime, UNIX_EPOCH};
|
||||
use zeroclaw::tools::{Tool, ToolResult};
|
||||
use zip::write::FileOptions;
|
||||
use zip::{CompressionMethod, ZipWriter};
|
||||
|
||||
const OPENXML_OFFICE_TOOL_NAME: &str = "openxml_office";
|
||||
const DEFAULT_SHEET_NAME: &str = "知乎热榜";
|
||||
@@ -93,7 +96,11 @@ impl Tool for OpenXmlOfficeTool {
|
||||
return Ok(failed_tool_result("rows must not be empty".to_string()));
|
||||
}
|
||||
|
||||
if parsed.rows.iter().any(|row| row.len() != parsed.columns.len()) {
|
||||
if parsed
|
||||
.rows
|
||||
.iter()
|
||||
.any(|row| row.len() != parsed.columns.len())
|
||||
{
|
||||
return Ok(failed_tool_result(
|
||||
"each row must match the declared columns length".to_string(),
|
||||
));
|
||||
@@ -153,10 +160,10 @@ fn failed_tool_result(error: String) -> ToolResult {
|
||||
}
|
||||
|
||||
fn create_job_root(workspace_root: &Path) -> anyhow::Result<PathBuf> {
|
||||
let nanos = SystemTime::now()
|
||||
.duration_since(UNIX_EPOCH)?
|
||||
.as_nanos();
|
||||
let path = workspace_root.join(".sgclaw-openxml").join(format!("{nanos}"));
|
||||
let nanos = SystemTime::now().duration_since(UNIX_EPOCH)?.as_nanos();
|
||||
let path = workspace_root
|
||||
.join(".sgclaw-openxml")
|
||||
.join(format!("{nanos}"));
|
||||
fs::create_dir_all(&path)?;
|
||||
Ok(path)
|
||||
}
|
||||
@@ -188,10 +195,7 @@ fn resolve_column_order(
|
||||
.iter()
|
||||
.map(|value| value.to_string())
|
||||
.collect::<BTreeSet<_>>();
|
||||
let expected_set = expected_columns
|
||||
.iter()
|
||||
.cloned()
|
||||
.collect::<BTreeSet<_>>();
|
||||
let expected_set = expected_columns.iter().cloned().collect::<BTreeSet<_>>();
|
||||
|
||||
if provided_set != expected_set {
|
||||
return None;
|
||||
@@ -279,13 +283,8 @@ fn run_openxml_cli(request_path: &Path) -> anyhow::Result<Value> {
|
||||
.parent()
|
||||
.map(|path| path.join("openxml_cli").join("Cargo.toml"))
|
||||
.ok_or_else(|| anyhow::anyhow!("failed to resolve openxml_cli manifest path"))?;
|
||||
let binary_path = manifest_path
|
||||
.parent()
|
||||
.map(|path| path.join("target").join("debug").join("openxml-cli"))
|
||||
.ok_or_else(|| anyhow::anyhow!("failed to resolve openxml_cli binary path"))?;
|
||||
|
||||
let output = if binary_path.exists() {
|
||||
Command::new(&binary_path)
|
||||
let output = if let Some(binary_path) = resolve_openxml_cli_binary(&manifest_path) {
|
||||
Command::new(binary_path)
|
||||
.args([
|
||||
"template",
|
||||
"render",
|
||||
@@ -324,6 +323,34 @@ fn run_openxml_cli(request_path: &Path) -> anyhow::Result<Value> {
|
||||
Ok(serde_json::from_str(&stdout)?)
|
||||
}
|
||||
|
||||
fn resolve_openxml_cli_binary(manifest_path: &Path) -> Option<PathBuf> {
|
||||
let cli_dir = manifest_path.parent()?;
|
||||
openxml_cli_candidate_paths(cli_dir)
|
||||
.into_iter()
|
||||
.find(|path| path.exists())
|
||||
}
|
||||
|
||||
fn openxml_cli_candidate_paths(cli_dir: &Path) -> Vec<PathBuf> {
|
||||
let mut paths = Vec::new();
|
||||
for profile in ["release", "debug"] {
|
||||
paths.push(
|
||||
cli_dir
|
||||
.join("target")
|
||||
.join(profile)
|
||||
.join(openxml_cli_binary_name()),
|
||||
);
|
||||
}
|
||||
paths
|
||||
}
|
||||
|
||||
fn openxml_cli_binary_name() -> &'static str {
|
||||
if cfg!(windows) {
|
||||
"openxml-cli.exe"
|
||||
} else {
|
||||
"openxml-cli"
|
||||
}
|
||||
}
|
||||
|
||||
fn value_to_string(value: &Value) -> String {
|
||||
match value {
|
||||
Value::String(text) => text.clone(),
|
||||
@@ -362,22 +389,81 @@ fn write_hotlist_template(path: &Path, row_count: usize) -> anyhow::Result<()> {
|
||||
fs::remove_file(path)?;
|
||||
}
|
||||
|
||||
let zip = Command::new("zip")
|
||||
.current_dir(&build_root)
|
||||
.args(["-q", "-r", path.to_string_lossy().as_ref(), "."])
|
||||
.output()?;
|
||||
if !zip.status.success() {
|
||||
let stderr = String::from_utf8_lossy(&zip.stderr);
|
||||
return Err(anyhow::anyhow!(format!(
|
||||
"failed to create xlsx template: {}",
|
||||
stderr.trim()
|
||||
)));
|
||||
}
|
||||
zip_directory(&build_root, path)?;
|
||||
|
||||
let _ = fs::remove_dir_all(&build_root);
|
||||
Ok(())
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::{openxml_cli_binary_name, openxml_cli_candidate_paths, zip_entry_name};
|
||||
use std::path::Path;
|
||||
|
||||
#[test]
|
||||
fn openxml_cli_candidates_prefer_release_before_debug() {
|
||||
let paths = openxml_cli_candidate_paths(Path::new("E:\\coding\\codex\\openxml_cli"));
|
||||
assert_eq!(paths.len(), 2);
|
||||
assert_eq!(
|
||||
paths[0],
|
||||
Path::new("E:\\coding\\codex\\openxml_cli")
|
||||
.join("target")
|
||||
.join("release")
|
||||
.join(openxml_cli_binary_name())
|
||||
);
|
||||
assert_eq!(
|
||||
paths[1],
|
||||
Path::new("E:\\coding\\codex\\openxml_cli")
|
||||
.join("target")
|
||||
.join("debug")
|
||||
.join(openxml_cli_binary_name())
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn zip_entry_name_normalizes_windows_separators() {
|
||||
let rel = Path::new("xl\\worksheets\\sheet1.xml");
|
||||
assert_eq!(zip_entry_name(rel), "xl/worksheets/sheet1.xml");
|
||||
}
|
||||
}
|
||||
|
||||
fn zip_directory(source_root: &Path, zip_path: &Path) -> anyhow::Result<()> {
|
||||
let file = fs::File::create(zip_path)?;
|
||||
let mut writer = ZipWriter::new(file);
|
||||
let options = FileOptions::default().compression_method(CompressionMethod::Stored);
|
||||
add_directory_to_zip(&mut writer, source_root, source_root, options)?;
|
||||
writer.finish()?;
|
||||
Ok(())
|
||||
}
|
||||
|
||||
fn add_directory_to_zip<W: Write + std::io::Seek>(
|
||||
writer: &mut ZipWriter<W>,
|
||||
source_root: &Path,
|
||||
current_dir: &Path,
|
||||
options: FileOptions,
|
||||
) -> anyhow::Result<()> {
|
||||
for entry in fs::read_dir(current_dir)? {
|
||||
let entry = entry?;
|
||||
let path = entry.path();
|
||||
if path.is_dir() {
|
||||
add_directory_to_zip(writer, source_root, &path, options)?;
|
||||
continue;
|
||||
}
|
||||
|
||||
let relative_path = path.strip_prefix(source_root)?;
|
||||
writer.start_file(zip_entry_name(relative_path), options)?;
|
||||
let mut input = fs::File::open(&path)?;
|
||||
let mut buffer = Vec::new();
|
||||
input.read_to_end(&mut buffer)?;
|
||||
writer.write_all(&buffer)?;
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
fn zip_entry_name(path: &Path) -> String {
|
||||
path.to_string_lossy().replace('\\', "/")
|
||||
}
|
||||
|
||||
fn worksheet_xml(row_count: usize) -> String {
|
||||
let mut rows = Vec::new();
|
||||
rows.push(
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
use std::path::Path;
|
||||
|
||||
use crate::compat::config_adapter::resolve_skills_dir_from_sgclaw_settings;
|
||||
use crate::compat::runtime::CompatTaskContext;
|
||||
use crate::config::SgClawSettings;
|
||||
use crate::pipe::{BrowserPipeTool, PipeError, Transport};
|
||||
@@ -9,6 +10,12 @@ pub fn should_use_primary_orchestration(
|
||||
page_url: Option<&str>,
|
||||
page_title: Option<&str>,
|
||||
) -> bool {
|
||||
if crate::compat::workflow_executor::detect_route(instruction, page_url, page_title)
|
||||
.is_some_and(|route| crate::compat::workflow_executor::prefers_direct_execution(&route))
|
||||
{
|
||||
return true;
|
||||
}
|
||||
|
||||
let normalized = instruction.to_ascii_lowercase();
|
||||
let needs_export = normalized.contains("excel")
|
||||
|| normalized.contains("xlsx")
|
||||
@@ -28,11 +35,25 @@ pub fn execute_task_with_sgclaw_settings<T: Transport + 'static>(
|
||||
workspace_root: &Path,
|
||||
settings: &SgClawSettings,
|
||||
) -> Result<String, PipeError> {
|
||||
let skills_dir = resolve_skills_dir_from_sgclaw_settings(workspace_root, settings);
|
||||
let route = crate::compat::workflow_executor::detect_route(
|
||||
instruction,
|
||||
task_context.page_url.as_deref(),
|
||||
task_context.page_title.as_deref(),
|
||||
);
|
||||
if let Some(route) = route.clone() {
|
||||
if crate::compat::workflow_executor::prefers_direct_execution(&route) {
|
||||
return crate::compat::workflow_executor::execute_route(
|
||||
transport,
|
||||
&browser_tool,
|
||||
workspace_root,
|
||||
&skills_dir,
|
||||
instruction,
|
||||
task_context,
|
||||
route,
|
||||
);
|
||||
}
|
||||
}
|
||||
let primary_result = crate::compat::runtime::execute_task_with_sgclaw_settings(
|
||||
transport,
|
||||
browser_tool.clone(),
|
||||
@@ -44,13 +65,17 @@ pub fn execute_task_with_sgclaw_settings<T: Transport + 'static>(
|
||||
|
||||
match (route, primary_result) {
|
||||
(Some(route), Ok(summary))
|
||||
if crate::compat::workflow_executor::should_fallback_after_summary(&summary, &route) =>
|
||||
if crate::compat::workflow_executor::should_fallback_after_summary(
|
||||
&summary, &route,
|
||||
) =>
|
||||
{
|
||||
crate::compat::workflow_executor::execute_route(
|
||||
transport,
|
||||
&browser_tool,
|
||||
workspace_root,
|
||||
&skills_dir,
|
||||
instruction,
|
||||
task_context,
|
||||
route,
|
||||
)
|
||||
}
|
||||
@@ -59,7 +84,9 @@ pub fn execute_task_with_sgclaw_settings<T: Transport + 'static>(
|
||||
transport,
|
||||
&browser_tool,
|
||||
workspace_root,
|
||||
&skills_dir,
|
||||
instruction,
|
||||
task_context,
|
||||
route,
|
||||
),
|
||||
(None, Err(err)) => Err(err),
|
||||
|
||||
@@ -5,23 +5,18 @@ use async_trait::async_trait;
|
||||
use futures_util::{stream, StreamExt};
|
||||
use zeroclaw::agent::TurnEvent;
|
||||
use zeroclaw::config::Config as ZeroClawConfig;
|
||||
use zeroclaw::providers::{
|
||||
self, ChatMessage, ChatRequest, ChatResponse, Provider,
|
||||
};
|
||||
use zeroclaw::providers::traits::{
|
||||
ProviderCapabilities, StreamEvent, StreamOptions, StreamResult,
|
||||
};
|
||||
use zeroclaw::providers::traits::{ProviderCapabilities, StreamEvent, StreamOptions, StreamResult};
|
||||
use zeroclaw::providers::{self, ChatMessage, ChatRequest, ChatResponse, Provider};
|
||||
|
||||
use crate::compat::browser_script_skill_tool::build_browser_script_skill_tools;
|
||||
use crate::compat::browser_tool_adapter::ZeroClawBrowserTool;
|
||||
use crate::compat::config_adapter::{
|
||||
build_zeroclaw_config_from_sgclaw_settings,
|
||||
resolve_skills_dir_from_sgclaw_settings,
|
||||
build_zeroclaw_config_from_sgclaw_settings, resolve_skills_dir_from_sgclaw_settings,
|
||||
};
|
||||
use crate::compat::event_bridge::log_entry_for_turn_event;
|
||||
use crate::compat::openxml_office_tool::OpenXmlOfficeTool;
|
||||
use crate::compat::screen_html_export_tool::ScreenHtmlExportTool;
|
||||
use crate::config::{DeepSeekSettings, OfficeBackend, SgClawSettings};
|
||||
use crate::compat::event_bridge::log_entry_for_turn_event;
|
||||
use crate::pipe::{BrowserPipeTool, ConversationMessage, PipeError, Transport};
|
||||
use crate::runtime::RuntimeEngine;
|
||||
|
||||
@@ -136,13 +131,17 @@ pub async fn execute_task_with_provider<T: Transport + 'static>(
|
||||
.map_err(map_anyhow_to_pipe_error)?,
|
||||
);
|
||||
}
|
||||
if matches!(settings.office_backend, OfficeBackend::OpenXml) &&
|
||||
engine.should_attach_openxml_office_tool(instruction)
|
||||
if matches!(settings.office_backend, OfficeBackend::OpenXml)
|
||||
&& engine.should_attach_openxml_office_tool(instruction)
|
||||
{
|
||||
tools.push(Box::new(OpenXmlOfficeTool::new(config.workspace_dir.clone())));
|
||||
tools.push(Box::new(OpenXmlOfficeTool::new(
|
||||
config.workspace_dir.clone(),
|
||||
)));
|
||||
}
|
||||
if engine.should_attach_screen_html_export_tool(instruction) {
|
||||
tools.push(Box::new(ScreenHtmlExportTool::new(config.workspace_dir.clone())));
|
||||
tools.push(Box::new(ScreenHtmlExportTool::new(
|
||||
config.workspace_dir.clone(),
|
||||
)));
|
||||
}
|
||||
let mut agent = engine.build_agent(
|
||||
provider,
|
||||
@@ -190,10 +189,7 @@ pub async fn execute_task_with_provider<T: Transport + 'static>(
|
||||
|
||||
fn build_provider(config: &ZeroClawConfig) -> Result<Box<dyn Provider>, PipeError> {
|
||||
let provider_name = config.default_provider.as_deref().unwrap_or("deepseek");
|
||||
let model_name = config
|
||||
.default_model
|
||||
.as_deref()
|
||||
.unwrap_or("deepseek-chat");
|
||||
let model_name = config.default_model.as_deref().unwrap_or("deepseek-chat");
|
||||
let runtime_options = providers::provider_runtime_options_from_config(config);
|
||||
let resolved_provider_name = if provider_name == "deepseek" {
|
||||
config
|
||||
@@ -258,7 +254,9 @@ impl Provider for NonStreamingProvider {
|
||||
model: &str,
|
||||
temperature: f64,
|
||||
) -> anyhow::Result<String> {
|
||||
self.inner.chat_with_history(messages, model, temperature).await
|
||||
self.inner
|
||||
.chat_with_history(messages, model, temperature)
|
||||
.await
|
||||
}
|
||||
|
||||
async fn chat(
|
||||
|
||||
@@ -12,7 +12,7 @@ const SCREEN_HTML_EXPORT_TOOL_NAME: &str = "screen_html_export";
|
||||
const DEFAULT_SCREEN_TITLE: &str = "知乎热榜主题分类分析大屏";
|
||||
const TEMPLATE: &str = include_str!(concat!(
|
||||
env!("CARGO_MANIFEST_DIR"),
|
||||
"/../skill_lib/skills/zhihu-hotlist-screen/assets/zhihu-hotlist-echarts.html"
|
||||
"/resources/zhihu-hotlist-echarts.html"
|
||||
));
|
||||
const PAYLOAD_START_MARKER: &str = " const defaultPayload = ";
|
||||
const PAYLOAD_END_MARKER: &str = "\n\n const themeMeta = {";
|
||||
@@ -238,29 +238,40 @@ fn derive_categories(table: &[ScreenTableRow]) -> Vec<ScreenCategory> {
|
||||
|
||||
grouped
|
||||
.into_iter()
|
||||
.map(|((category_code, category_label), (item_count, total_heat))| ScreenCategory {
|
||||
category_code,
|
||||
category_label,
|
||||
item_count,
|
||||
total_heat,
|
||||
avg_heat: if item_count == 0 {
|
||||
0
|
||||
} else {
|
||||
total_heat / item_count
|
||||
.map(
|
||||
|((category_code, category_label), (item_count, total_heat))| ScreenCategory {
|
||||
category_code,
|
||||
category_label,
|
||||
item_count,
|
||||
total_heat,
|
||||
avg_heat: if item_count == 0 {
|
||||
0
|
||||
} else {
|
||||
total_heat / item_count
|
||||
},
|
||||
},
|
||||
})
|
||||
)
|
||||
.collect()
|
||||
}
|
||||
|
||||
fn classify_title(title: &str) -> (&'static str, &'static str) {
|
||||
let normalized = title.to_ascii_lowercase();
|
||||
if contains_any(&normalized, &["ai", "芯片", "科技", "算法", "机器人", "无人机"]) {
|
||||
if contains_any(
|
||||
&normalized,
|
||||
&["ai", "芯片", "科技", "算法", "机器人", "无人机"],
|
||||
) {
|
||||
return ("technology", "科技");
|
||||
}
|
||||
if contains_any(&normalized, &["电影", "综艺", "明星", "周杰伦", "短剧", "娱乐"]) {
|
||||
if contains_any(
|
||||
&normalized,
|
||||
&["电影", "综艺", "明星", "周杰伦", "短剧", "娱乐"],
|
||||
) {
|
||||
return ("entertainment", "娱乐");
|
||||
}
|
||||
if contains_any(&normalized, &["足球", "比赛", "联赛", "国足", "体育", "冠军"]) {
|
||||
if contains_any(
|
||||
&normalized,
|
||||
&["足球", "比赛", "联赛", "国足", "体育", "冠军"],
|
||||
) {
|
||||
return ("sports", "体育");
|
||||
}
|
||||
if contains_any(&normalized, &["航母", "作战", "军", "军事", "演训"]) {
|
||||
|
||||
50
src/compat/tq_lineloss/contracts.rs
Normal file
50
src/compat/tq_lineloss/contracts.rs
Normal file
@@ -0,0 +1,50 @@
|
||||
use serde_json::Value;
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq)]
|
||||
pub struct ResolvedOrg {
|
||||
pub label: String,
|
||||
pub code: String,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq)]
|
||||
pub enum PeriodMode {
|
||||
Month,
|
||||
Week,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, PartialEq)]
|
||||
pub struct ResolvedPeriod {
|
||||
pub mode: PeriodMode,
|
||||
pub mode_code: String,
|
||||
pub value: String,
|
||||
pub payload: Value,
|
||||
}
|
||||
|
||||
pub fn missing_company_prompt() -> String {
|
||||
"已命中台区线损报表技能，但缺少供电单位，请补充如“兰州公司”或“城关供电分公司”。"
|
||||
.to_string()
|
||||
}
|
||||
|
||||
pub fn ambiguous_company_prompt() -> String {
|
||||
"已命中台区线损报表技能，但供电单位存在歧义，请补充更完整名称。".to_string()
|
||||
}
|
||||
|
||||
pub fn missing_period_mode_prompt() -> String {
|
||||
"已命中台区线损报表技能，但未识别到月/周类型，请补充“月累计”或“周累计”。"
|
||||
.to_string()
|
||||
}
|
||||
|
||||
pub fn missing_period_prompt() -> String {
|
||||
"已命中台区线损报表技能，但缺少统计周期，请补充如“2026-03”或“2026年第12周”。"
|
||||
.to_string()
|
||||
}
|
||||
|
||||
pub fn contradictory_period_mode_prompt() -> String {
|
||||
"已命中台区线损报表技能，但月/周类型存在冲突，请只保留“月累计”或“周累计”之一。"
|
||||
.to_string()
|
||||
}
|
||||
|
||||
pub fn missing_week_year_prompt() -> String {
|
||||
"已命中台区线损报表技能，但周累计缺少年份，请补充如“2026年第12周”。"
|
||||
.to_string()
|
||||
}
|
||||
4
src/compat/tq_lineloss/mod.rs
Normal file
4
src/compat/tq_lineloss/mod.rs
Normal file
@@ -0,0 +1,4 @@
|
||||
pub mod contracts;
|
||||
pub mod org_resolver;
|
||||
pub mod org_units;
|
||||
pub mod period_resolver;
|
||||
71
src/compat/tq_lineloss/org_resolver.rs
Normal file
71
src/compat/tq_lineloss/org_resolver.rs
Normal file
@@ -0,0 +1,71 @@
|
||||
use super::contracts::{ambiguous_company_prompt, ResolvedOrg};
|
||||
use super::org_units::{OrgUnit, ORG_UNITS};
|
||||
|
||||
fn normalize(value: &str) -> String {
|
||||
value.chars().filter(|ch| !ch.is_whitespace()).collect()
|
||||
}
|
||||
|
||||
fn candidate_names(unit: &'static OrgUnit) -> impl Iterator<Item = &'static str> {
|
||||
std::iter::once(unit.label).chain(unit.aliases.iter().copied())
|
||||
}
|
||||
|
||||
fn to_resolved_org(unit: &OrgUnit) -> ResolvedOrg {
|
||||
ResolvedOrg {
|
||||
label: unit.label.to_string(),
|
||||
code: unit.code.to_string(),
|
||||
}
|
||||
}
|
||||
|
||||
pub fn resolve_org(input: &str) -> Result<ResolvedOrg, String> {
|
||||
let normalized = normalize(input);
|
||||
if normalized.is_empty() {
|
||||
return Err(super::contracts::missing_company_prompt());
|
||||
}
|
||||
|
||||
let exact_matches: Vec<&OrgUnit> = ORG_UNITS
|
||||
.iter()
|
||||
.filter(|unit| candidate_names(unit).any(|name| normalize(name) == normalized))
|
||||
.collect();
|
||||
if exact_matches.len() == 1 {
|
||||
return Ok(to_resolved_org(exact_matches[0]));
|
||||
}
|
||||
if exact_matches.len() > 1 {
|
||||
return Err(ambiguous_company_prompt());
|
||||
}
|
||||
|
||||
let fuzzy_matches: Vec<&OrgUnit> = ORG_UNITS
|
||||
.iter()
|
||||
.filter(|unit| {
|
||||
candidate_names(unit).any(|name| {
|
||||
let normalized_name = normalize(name);
|
||||
normalized_name.contains(&normalized) || normalized.contains(&normalized_name)
|
||||
})
|
||||
})
|
||||
.collect();
|
||||
if fuzzy_matches.len() == 1 {
|
||||
return Ok(to_resolved_org(fuzzy_matches[0]));
|
||||
}
|
||||
if fuzzy_matches.len() > 1 {
|
||||
return Err(ambiguous_company_prompt());
|
||||
}
|
||||
|
||||
Err(super::contracts::missing_company_prompt())
|
||||
}
|
||||
|
||||
pub fn resolve_org_from_instruction(instruction: &str) -> Result<Option<ResolvedOrg>, String> {
|
||||
let normalized_instruction = normalize(instruction);
|
||||
let direct_matches: Vec<&OrgUnit> = ORG_UNITS
|
||||
.iter()
|
||||
.filter(|unit| {
|
||||
candidate_names(unit).any(|name| normalized_instruction.contains(&normalize(name)))
|
||||
})
|
||||
.collect();
|
||||
if direct_matches.len() == 1 {
|
||||
return Ok(Some(to_resolved_org(direct_matches[0])));
|
||||
}
|
||||
if direct_matches.len() > 1 {
|
||||
return Err(ambiguous_company_prompt());
|
||||
}
|
||||
|
||||
Ok(None)
|
||||
}
|
||||
33
src/compat/tq_lineloss/org_units.rs
Normal file
33
src/compat/tq_lineloss/org_units.rs
Normal file
@@ -0,0 +1,33 @@
|
||||
pub(crate) struct OrgUnit {
|
||||
pub(crate) label: &'static str,
|
||||
pub(crate) code: &'static str,
|
||||
pub(crate) aliases: &'static [&'static str],
|
||||
}
|
||||
|
||||
pub(crate) const ORG_UNITS: &[OrgUnit] = &[
|
||||
OrgUnit {
|
||||
label: "国网兰州供电公司",
|
||||
code: "62401",
|
||||
aliases: &["国网兰州供电公司", "兰州供电公司", "兰州公司"],
|
||||
},
|
||||
OrgUnit {
|
||||
label: "国网天水供电公司",
|
||||
code: "62403",
|
||||
aliases: &["国网天水供电公司", "天水供电公司", "天水公司"],
|
||||
},
|
||||
OrgUnit {
|
||||
label: "城关供电分公司",
|
||||
code: "6240108",
|
||||
aliases: &["城关供电分公司", "城关分公司"],
|
||||
},
|
||||
OrgUnit {
|
||||
label: "国网榆中县供电公司",
|
||||
code: "6240121",
|
||||
aliases: &["国网榆中县供电公司", "榆中县供电公司", "榆中县公司"],
|
||||
},
|
||||
OrgUnit {
|
||||
label: "榆中城关供电所",
|
||||
code: "624012108",
|
||||
aliases: &["榆中城关供电所"],
|
||||
},
|
||||
];
|
||||
244
src/compat/tq_lineloss/period_resolver.rs
Normal file
244
src/compat/tq_lineloss/period_resolver.rs
Normal file
@@ -0,0 +1,244 @@
|
||||
use chrono::{Datelike, Duration, Local, NaiveDate};
|
||||
use serde_json::json;
|
||||
|
||||
use super::contracts::{
|
||||
contradictory_period_mode_prompt, missing_period_mode_prompt, missing_period_prompt,
|
||||
missing_week_year_prompt, PeriodMode, ResolvedPeriod,
|
||||
};
|
||||
|
||||
pub fn resolve_period(input: &str) -> Result<ResolvedPeriod, String> {
|
||||
let has_month = input.contains("月累计");
|
||||
let has_week = input.contains("周累计");
|
||||
|
||||
match (has_month, has_week) {
|
||||
(true, true) => return Err(contradictory_period_mode_prompt()),
|
||||
(false, false) => return Err(missing_period_mode_prompt()),
|
||||
(true, false) => resolve_month_period(input),
|
||||
(false, true) => resolve_week_period(input),
|
||||
}
|
||||
}
|
||||
|
||||
fn resolve_month_period(input: &str) -> Result<ResolvedPeriod, String> {
|
||||
if let Some(value) = extract_year_month_dash(input) {
|
||||
return Ok(ResolvedPeriod {
|
||||
mode: PeriodMode::Month,
|
||||
mode_code: "1".to_string(),
|
||||
value: value.clone(),
|
||||
payload: json!({ "fdate": value }),
|
||||
});
|
||||
}
|
||||
|
||||
if let Some(value) = extract_year_month_cn(input) {
|
||||
return Ok(ResolvedPeriod {
|
||||
mode: PeriodMode::Month,
|
||||
mode_code: "1".to_string(),
|
||||
value: value.clone(),
|
||||
payload: json!({ "fdate": value }),
|
||||
});
|
||||
}
|
||||
|
||||
if contains_explicit_month_period_hint(input) {
|
||||
return Err(missing_period_prompt());
|
||||
}
|
||||
|
||||
Ok(default_month_period())
|
||||
}
|
||||
|
||||
fn resolve_week_period(input: &str) -> Result<ResolvedPeriod, String> {
|
||||
if input.contains('第') && input.contains('周') && !input.contains('年') {
|
||||
return Err(missing_week_year_prompt());
|
||||
}
|
||||
|
||||
if let Some((year, week)) = extract_year_week(input) {
|
||||
let Some(week_start) = week_start_date(year, week) else {
|
||||
return Err(missing_period_prompt());
|
||||
};
|
||||
let week_end = week_start + Duration::days(6);
|
||||
|
||||
return Ok(ResolvedPeriod {
|
||||
mode: PeriodMode::Week,
|
||||
mode_code: "2".to_string(),
|
||||
value: format!("{year}-W{week:02}"),
|
||||
payload: json!({
|
||||
"tjzq": "week",
|
||||
"level": "00",
|
||||
"weekSfdate": week_start.format("%Y-%m-%d").to_string(),
|
||||
"weekEfdate": week_end.format("%Y-%m-%d").to_string(),
|
||||
}),
|
||||
});
|
||||
}
|
||||
|
||||
if contains_explicit_week_period_hint(input) {
|
||||
return Err(missing_period_prompt());
|
||||
}
|
||||
|
||||
Ok(default_week_period())
|
||||
}
|
||||
|
||||
fn default_month_period() -> ResolvedPeriod {
|
||||
let today = Local::now().date_naive();
|
||||
let (year, month) = if today.month() == 1 {
|
||||
(today.year() - 1, 12)
|
||||
} else {
|
||||
(today.year(), today.month() - 1)
|
||||
};
|
||||
let value = format!("{year}-{month:02}");
|
||||
|
||||
ResolvedPeriod {
|
||||
mode: PeriodMode::Month,
|
||||
mode_code: "1".to_string(),
|
||||
value: value.clone(),
|
||||
payload: json!({ "fdate": value }),
|
||||
}
|
||||
}
|
||||
|
||||
fn default_week_period() -> ResolvedPeriod {
|
||||
let today = Local::now().date_naive();
|
||||
let month_start = today.with_day(1).expect("current month should have day 1");
|
||||
let start = month_start.format("%Y-%m-%d").to_string();
|
||||
let end = today.format("%Y-%m-%d").to_string();
|
||||
|
||||
ResolvedPeriod {
|
||||
mode: PeriodMode::Week,
|
||||
mode_code: "2".to_string(),
|
||||
value: format!("{start}至{end}"),
|
||||
payload: json!({
|
||||
"tjzq": "week",
|
||||
"level": "00",
|
||||
"weekSfdate": start,
|
||||
"weekEfdate": end,
|
||||
}),
|
||||
}
|
||||
}
|
||||
|
||||
fn contains_explicit_month_period_hint(input: &str) -> bool {
|
||||
let trimmed = input.replace("月累计", "");
|
||||
trimmed.contains('年')
|
||||
|| trimmed.contains('月')
|
||||
|| trimmed.contains('-')
|
||||
|| trimmed.chars().any(|ch| ch.is_ascii_digit())
|
||||
}
|
||||
|
||||
fn contains_explicit_week_period_hint(input: &str) -> bool {
|
||||
let trimmed = input.replace("周累计", "");
|
||||
trimmed.contains('年')
|
||||
|| trimmed.contains('第')
|
||||
|| trimmed.contains('周')
|
||||
|| trimmed.contains('-')
|
||||
|| trimmed.chars().any(|ch| ch.is_ascii_digit())
|
||||
}
|
||||
|
||||
fn extract_year_month_dash(input: &str) -> Option<String> {
|
||||
let chars: Vec<char> = input.chars().collect();
|
||||
for window in chars.windows(7) {
|
||||
let candidate: String = window.iter().collect();
|
||||
if is_year_month_dash(&candidate) {
|
||||
return Some(candidate);
|
||||
}
|
||||
}
|
||||
None
|
||||
}
|
||||
|
||||
fn is_year_month_dash(candidate: &str) -> bool {
|
||||
let bytes = candidate.as_bytes();
|
||||
bytes.len() == 7
|
||||
&& bytes[0..4].iter().all(u8::is_ascii_digit)
|
||||
&& bytes[4] == b'-'
|
||||
&& bytes[5..7].iter().all(u8::is_ascii_digit)
|
||||
&& matches!((bytes[5] - b'0') * 10 + (bytes[6] - b'0'), 1..=12)
|
||||
}
|
||||
|
||||
fn extract_year_month_cn(input: &str) -> Option<String> {
|
||||
let chars: Vec<char> = input.chars().collect();
|
||||
for index in 0..chars.len() {
|
||||
if index + 6 >= chars.len() {
|
||||
break;
|
||||
}
|
||||
if !chars[index..index + 4].iter().all(|ch| ch.is_ascii_digit()) {
|
||||
continue;
|
||||
}
|
||||
if chars[index + 4] != '年' {
|
||||
continue;
|
||||
}
|
||||
|
||||
let mut month_digits = String::new();
|
||||
let mut cursor = index + 5;
|
||||
while cursor < chars.len() && chars[cursor].is_ascii_digit() && month_digits.len() < 2 {
|
||||
month_digits.push(chars[cursor]);
|
||||
cursor += 1;
|
||||
}
|
||||
if month_digits.is_empty() || cursor >= chars.len() || chars[cursor] != '月' {
|
||||
continue;
|
||||
}
|
||||
|
||||
let month: u32 = month_digits.parse().ok()?;
|
||||
if !(1..=12).contains(&month) {
|
||||
continue;
|
||||
}
|
||||
let year: String = chars[index..index + 4].iter().collect();
|
||||
return Some(format!("{year}-{month:02}"));
|
||||
}
|
||||
None
|
||||
}
|
||||
|
||||
fn extract_year_week(input: &str) -> Option<(i32, u32)> {
|
||||
let chars: Vec<char> = input.chars().collect();
|
||||
for index in 0..chars.len() {
|
||||
if index + 7 >= chars.len() {
|
||||
break;
|
||||
}
|
||||
if !chars[index..index + 4].iter().all(|ch| ch.is_ascii_digit()) {
|
||||
continue;
|
||||
}
|
||||
if chars[index + 4] != '年' || chars[index + 5] != '第' {
|
||||
continue;
|
||||
}
|
||||
|
||||
let mut week_digits = String::new();
|
||||
let mut cursor = index + 6;
|
||||
while cursor < chars.len() && chars[cursor].is_ascii_digit() && week_digits.len() < 2 {
|
||||
week_digits.push(chars[cursor]);
|
||||
cursor += 1;
|
||||
}
|
||||
if week_digits.is_empty() || cursor >= chars.len() || chars[cursor] != '周' {
|
||||
continue;
|
||||
}
|
||||
|
||||
let year: i32 = chars[index..index + 4].iter().collect::<String>().parse().ok()?;
|
||||
let week: u32 = week_digits.parse().ok()?;
|
||||
if !(1..=53).contains(&week) {
|
||||
continue;
|
||||
}
|
||||
return Some((year, week));
|
||||
}
|
||||
None
|
||||
}
|
||||
|
||||
fn week_start_date(year: i32, week: u32) -> Option<NaiveDate> {
|
||||
let jan4 = NaiveDate::from_ymd_opt(year, 1, 4)?;
|
||||
let iso_week1_monday = jan4 - Duration::days(jan4.weekday().num_days_from_monday() as i64);
|
||||
let candidate = iso_week1_monday + Duration::weeks((week - 1) as i64);
|
||||
let iso = candidate.iso_week();
|
||||
(iso.year() == year && iso.week() == week).then_some(candidate)
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::resolve_period;
|
||||
use crate::compat::tq_lineloss::contracts::PeriodMode;
|
||||
|
||||
#[test]
|
||||
fn resolves_dash_month() {
|
||||
let resolved = resolve_period("月累计 2026-03").unwrap();
|
||||
assert_eq!(resolved.mode, PeriodMode::Month);
|
||||
assert_eq!(resolved.payload["fdate"], "2026-03");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn resolves_week_range() {
|
||||
let resolved = resolve_period("周累计 2026年第12周").unwrap();
|
||||
assert_eq!(resolved.mode, PeriodMode::Week);
|
||||
assert_eq!(resolved.payload["weekSfdate"], "2026-03-16");
|
||||
assert_eq!(resolved.payload["weekEfdate"], "2026-03-22");
|
||||
}
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,12 +1,6 @@
|
||||
mod settings;
|
||||
|
||||
pub use settings::{
|
||||
BrowserBackend,
|
||||
ConfigError,
|
||||
DeepSeekSettings,
|
||||
OfficeBackend,
|
||||
PlannerMode,
|
||||
ProviderSettings,
|
||||
SgClawSettings,
|
||||
SkillsPromptMode,
|
||||
BrowserBackend, ConfigError, DeepSeekSettings, OfficeBackend, PlannerMode, ProviderSettings,
|
||||
SgClawSettings, SkillsPromptMode,
|
||||
};
|
||||
|
||||
@@ -10,6 +10,10 @@ pub use zeroclaw::config::SkillsPromptInjectionMode as SkillsPromptMode;
|
||||
const DEFAULT_DEEPSEEK_BASE_URL: &str = "https://api.deepseek.com";
|
||||
const DEFAULT_DEEPSEEK_MODEL: &str = "deepseek-chat";
|
||||
const DEFAULT_PROVIDER_ID: &str = "deepseek";
|
||||
const DIRECT_SUBMIT_PROVIDER_ID: &str = "direct-submit";
|
||||
const DIRECT_SUBMIT_BASE_URL: &str = "http://127.0.0.1/direct-submit";
|
||||
const DIRECT_SUBMIT_MODEL: &str = "direct-submit-placeholder-model";
|
||||
const DIRECT_SUBMIT_API_KEY: &str = "direct-submit-placeholder-key";
|
||||
|
||||
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
|
||||
pub enum PlannerMode {
|
||||
@@ -66,6 +70,19 @@ impl ProviderSettings {
|
||||
})
|
||||
}
|
||||
|
||||
fn direct_submit_placeholder() -> Self {
|
||||
Self {
|
||||
id: DIRECT_SUBMIT_PROVIDER_ID.to_string(),
|
||||
provider: DIRECT_SUBMIT_PROVIDER_ID.to_string(),
|
||||
api_key: DIRECT_SUBMIT_API_KEY.to_string(),
|
||||
base_url: Some(DIRECT_SUBMIT_BASE_URL.to_string()),
|
||||
model: DIRECT_SUBMIT_MODEL.to_string(),
|
||||
api_path: None,
|
||||
wire_api: None,
|
||||
requires_openai_auth: false,
|
||||
}
|
||||
}
|
||||
|
||||
fn from_raw(raw: RawProviderSettings) -> Result<Self, ConfigError> {
|
||||
let id = raw.id.trim().to_string();
|
||||
if id.is_empty() {
|
||||
@@ -114,7 +131,8 @@ impl DeepSeekSettings {
|
||||
}
|
||||
|
||||
pub fn load(config_path: Option<&Path>) -> Result<Option<Self>, ConfigError> {
|
||||
SgClawSettings::load(config_path).map(|settings| settings.map(|settings| Self::from(&settings)))
|
||||
SgClawSettings::load(config_path)
|
||||
.map(|settings| settings.map(|settings| Self::from(&settings)))
|
||||
}
|
||||
}
|
||||
|
||||
@@ -124,6 +142,7 @@ pub struct SgClawSettings {
|
||||
pub provider_base_url: String,
|
||||
pub provider_model: String,
|
||||
pub skills_dir: Option<PathBuf>,
|
||||
pub direct_submit_skill: Option<String>,
|
||||
pub skills_prompt_mode: SkillsPromptMode,
|
||||
pub runtime_profile: RuntimeProfile,
|
||||
pub planner_mode: PlannerMode,
|
||||
@@ -162,6 +181,7 @@ impl SgClawSettings {
|
||||
None,
|
||||
None,
|
||||
None,
|
||||
None,
|
||||
Vec::new(),
|
||||
None,
|
||||
None,
|
||||
@@ -197,6 +217,7 @@ impl SgClawSettings {
|
||||
None,
|
||||
None,
|
||||
None,
|
||||
None,
|
||||
Vec::new(),
|
||||
None,
|
||||
None,
|
||||
@@ -216,7 +237,10 @@ impl SgClawSettings {
|
||||
.map(parse_runtime_profile)
|
||||
.transpose()
|
||||
.map_err(|value| {
|
||||
ConfigError::ConfigParse(path.to_path_buf(), format!("invalid runtimeProfile: {value}"))
|
||||
ConfigError::ConfigParse(
|
||||
path.to_path_buf(),
|
||||
format!("invalid runtimeProfile: {value}"),
|
||||
)
|
||||
})?;
|
||||
let skills_prompt_mode = config
|
||||
.skills_prompt_mode
|
||||
@@ -235,7 +259,10 @@ impl SgClawSettings {
|
||||
.map(parse_planner_mode)
|
||||
.transpose()
|
||||
.map_err(|value| {
|
||||
ConfigError::ConfigParse(path.to_path_buf(), format!("invalid plannerMode: {value}"))
|
||||
ConfigError::ConfigParse(
|
||||
path.to_path_buf(),
|
||||
format!("invalid plannerMode: {value}"),
|
||||
)
|
||||
})?;
|
||||
let browser_backend = config
|
||||
.browser_backend
|
||||
@@ -243,7 +270,10 @@ impl SgClawSettings {
|
||||
.map(parse_browser_backend)
|
||||
.transpose()
|
||||
.map_err(|value| {
|
||||
ConfigError::ConfigParse(path.to_path_buf(), format!("invalid browserBackend: {value}"))
|
||||
ConfigError::ConfigParse(
|
||||
path.to_path_buf(),
|
||||
format!("invalid browserBackend: {value}"),
|
||||
)
|
||||
})?;
|
||||
let office_backend = config
|
||||
.office_backend
|
||||
@@ -251,7 +281,10 @@ impl SgClawSettings {
|
||||
.map(parse_office_backend)
|
||||
.transpose()
|
||||
.map_err(|value| {
|
||||
ConfigError::ConfigParse(path.to_path_buf(), format!("invalid officeBackend: {value}"))
|
||||
ConfigError::ConfigParse(
|
||||
path.to_path_buf(),
|
||||
format!("invalid officeBackend: {value}"),
|
||||
)
|
||||
})?;
|
||||
let providers = config
|
||||
.providers
|
||||
@@ -265,6 +298,7 @@ impl SgClawSettings {
|
||||
config.base_url,
|
||||
config.model,
|
||||
resolve_configured_skills_dir(config.skills_dir, config_dir),
|
||||
config.direct_submit_skill,
|
||||
skills_prompt_mode,
|
||||
runtime_profile,
|
||||
planner_mode,
|
||||
@@ -281,6 +315,7 @@ impl SgClawSettings {
|
||||
base_url: String,
|
||||
model: String,
|
||||
skills_dir: Option<PathBuf>,
|
||||
direct_submit_skill: Option<String>,
|
||||
skills_prompt_mode: Option<SkillsPromptMode>,
|
||||
runtime_profile: Option<RuntimeProfile>,
|
||||
planner_mode: Option<PlannerMode>,
|
||||
@@ -289,13 +324,20 @@ impl SgClawSettings {
|
||||
browser_backend: Option<BrowserBackend>,
|
||||
office_backend: Option<OfficeBackend>,
|
||||
) -> Result<Self, ConfigError> {
|
||||
let direct_submit_skill = normalize_direct_submit_skill(direct_submit_skill)?;
|
||||
let providers = if providers.is_empty() {
|
||||
vec![ProviderSettings::from_legacy_deepseek(api_key, base_url, model)?]
|
||||
if direct_submit_skill.is_some() {
|
||||
vec![ProviderSettings::direct_submit_placeholder()]
|
||||
} else {
|
||||
vec![ProviderSettings::from_legacy_deepseek(
|
||||
api_key, base_url, model,
|
||||
)?]
|
||||
}
|
||||
} else {
|
||||
providers
|
||||
};
|
||||
let active_provider = normalize_optional_value(active_provider)
|
||||
.unwrap_or_else(|| providers[0].id.clone());
|
||||
let active_provider =
|
||||
normalize_optional_value(active_provider).unwrap_or_else(|| providers[0].id.clone());
|
||||
let active_provider_settings = providers
|
||||
.iter()
|
||||
.find(|provider| provider.id == active_provider)
|
||||
@@ -308,9 +350,13 @@ impl SgClawSettings {
|
||||
|
||||
Ok(Self {
|
||||
provider_api_key: active_provider_settings.api_key.clone(),
|
||||
provider_base_url: active_provider_settings.base_url.clone().unwrap_or_default(),
|
||||
provider_base_url: active_provider_settings
|
||||
.base_url
|
||||
.clone()
|
||||
.unwrap_or_default(),
|
||||
provider_model: active_provider_settings.model.clone(),
|
||||
skills_dir,
|
||||
direct_submit_skill,
|
||||
skills_prompt_mode: skills_prompt_mode.unwrap_or(SkillsPromptMode::Compact),
|
||||
runtime_profile: runtime_profile.unwrap_or(RuntimeProfile::BrowserAttached),
|
||||
planner_mode: planner_mode.unwrap_or(PlannerMode::ZeroclawPlanFirst),
|
||||
@@ -429,6 +475,29 @@ fn normalize_optional_value(raw: Option<String>) -> Option<String> {
|
||||
.filter(|value| !value.is_empty())
|
||||
}
|
||||
|
||||
fn normalize_direct_submit_skill(raw: Option<String>) -> Result<Option<String>, ConfigError> {
|
||||
let value = normalize_optional_value(raw);
|
||||
let Some(value) = value.as_deref() else {
|
||||
return Ok(None);
|
||||
};
|
||||
|
||||
let Some((skill_name, tool_name)) = value.split_once('.') else {
|
||||
return Err(ConfigError::InvalidValue(
|
||||
"directSubmitSkill",
|
||||
format!("must use skill.tool format, got {value}"),
|
||||
));
|
||||
};
|
||||
|
||||
if skill_name.trim().is_empty() || tool_name.trim().is_empty() {
|
||||
return Err(ConfigError::InvalidValue(
|
||||
"directSubmitSkill",
|
||||
format!("must use skill.tool format, got {value}"),
|
||||
));
|
||||
}
|
||||
|
||||
Ok(Some(value.to_string()))
|
||||
}
|
||||
|
||||
fn normalize_base_url(raw: String) -> String {
|
||||
let trimmed = raw.trim();
|
||||
if trimmed.is_empty() {
|
||||
@@ -465,6 +534,8 @@ struct RawSgClawSettings {
|
||||
model: String,
|
||||
#[serde(rename = "skillsDir", alias = "skills_dir", default)]
|
||||
skills_dir: Option<String>,
|
||||
#[serde(rename = "directSubmitSkill", alias = "direct_submit_skill", default)]
|
||||
direct_submit_skill: Option<String>,
|
||||
#[serde(rename = "skillsPromptMode", alias = "skills_prompt_mode", default)]
|
||||
skills_prompt_mode: Option<String>,
|
||||
#[serde(rename = "runtimeProfile", alias = "runtime_profile", default)]
|
||||
@@ -497,11 +568,7 @@ struct RawProviderSettings {
|
||||
api_path: Option<String>,
|
||||
#[serde(rename = "wireApi", alias = "wire_api", default)]
|
||||
wire_api: Option<String>,
|
||||
#[serde(
|
||||
rename = "requiresOpenaiAuth",
|
||||
alias = "requires_openai_auth",
|
||||
default
|
||||
)]
|
||||
#[serde(rename = "requiresOpenaiAuth", alias = "requires_openai_auth", default)]
|
||||
requires_openai_auth: bool,
|
||||
}
|
||||
|
||||
|
||||
@@ -3,6 +3,7 @@ pub mod compat;
|
||||
pub mod config;
|
||||
pub mod llm;
|
||||
pub mod pipe;
|
||||
pub mod runtime;
|
||||
pub mod security;
|
||||
|
||||
use std::path::PathBuf;
|
||||
|
||||
@@ -21,9 +21,7 @@ impl HandshakeResult {
|
||||
.iter()
|
||||
.any(|capability| capability == "browser_action")
|
||||
.then(|| {
|
||||
ExecutionSurfaceMetadata::privileged_browser_pipe(
|
||||
"browser_host_and_mac_policy",
|
||||
)
|
||||
ExecutionSurfaceMetadata::privileged_browser_pipe("browser_host_and_mac_policy")
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
@@ -5,8 +5,8 @@ pub mod protocol;
|
||||
pub use browser_tool::{BrowserPipeTool, CommandOutput};
|
||||
pub use handshake::{perform_handshake, HandshakeResult};
|
||||
pub use protocol::{
|
||||
supported_actions, Action, AgentMessage, BrowserContext, BrowserMessage,
|
||||
ConversationMessage, ExecutionSurfaceKind, ExecutionSurfaceMetadata, SecurityFields, Timing,
|
||||
supported_actions, Action, AgentMessage, BrowserContext, BrowserMessage, ConversationMessage,
|
||||
ExecutionSurfaceKind, ExecutionSurfaceMetadata, SecurityFields, Timing,
|
||||
};
|
||||
|
||||
use std::io::{BufRead, BufReader, Read, Write};
|
||||
|
||||
@@ -24,6 +24,7 @@ const BROWSER_TOOL_CONTRACT_PROMPT: &str = "SuperRPA browser interface contract:
|
||||
const ZHIHU_HOTLIST_EXECUTION_PROMPT: &str = "Zhihu hotlist execution contract:\n- Treat Zhihu hotlist export/presentation requests as a real browser workflow, not as a text-only summarization task.\n- You must attempt the browser workflow before concluding failure; a prose-only answer is invalid for this workflow.\n- If the current page is not already `https://www.zhihu.com/hot`, navigate there first.\n- If the `zhihu-hotlist.extract_hotlist` skill tool is available, call it before any generic browser probing.\n- Use generic `getText` only as a last-resort fallback when the packaged extractor fails.\n- Extract ordered rows containing `rank`, `title`, and `heat` as structured data.\n- Do not use shell, web_fetch, web_search_tool, or fabricated sample data for this workflow.\n- Do not repeat the same sentence or section in your final answer.";
|
||||
const OFFICE_EXPORT_COMPLETION_PROMPT: &str = "Export completion contract:\n- This task requires a real Excel export.\n- After the Zhihu rows are available, you must call openxml_office before finishing.\n- Never fabricate, simulate, or invent substitute hotlist data when a live collection/export task fails.\n- If live collection fails, report the failure concisely instead of producing fake rows.\n- Do not stop after describing how you will parse or export the data.\n- Do not repeat the same sentence or section in your final answer.\n- Your final answer must include the generated local .xlsx path.";
|
||||
const SCREEN_EXPORT_COMPLETION_PROMPT: &str = "Presentation completion contract:\n- This task requires a real dashboard artifact.\n- After the Zhihu rows are available, you must call screen_html_export before finishing.\n- Do not stop after describing how you will render or present the data.\n- Do not repeat the same sentence or section in your final answer.\n- Your final answer must include the local .html path and the presentation object.";
|
||||
const ZHIHU_WRITE_PUBLISH_PROMPT: &str = "Zhihu article publish contract:\n- This task may publish a Zhihu article.\n- You must not click publish without explicit human confirmation in the current session.\n- If the user asked to publish but no explicit confirmation phrase is present yet, ask for confirmation concisely and stop after the confirmation request.\n- Do not keep exploring tools after you have determined that publish confirmation is missing.\n- If the user only asked to write or draft, stay in draft mode and do not treat it as publish mode.\n- Do not repeat the same sentence or section in your final answer.";
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq)]
|
||||
pub struct RuntimeEngine {
|
||||
@@ -51,9 +52,7 @@ impl RuntimeEngine {
|
||||
self.tool_policy
|
||||
.allowed_tools
|
||||
.iter()
|
||||
.any(|tool| {
|
||||
tool == BROWSER_ACTION_TOOL_NAME || tool == SUPERRPA_BROWSER_TOOL_NAME
|
||||
})
|
||||
.any(|tool| tool == BROWSER_ACTION_TOOL_NAME || tool == SUPERRPA_BROWSER_TOOL_NAME)
|
||||
}
|
||||
|
||||
pub fn build_agent(
|
||||
@@ -155,6 +154,9 @@ impl RuntimeEngine {
|
||||
if task_needs_screen_export(trimmed_instruction) {
|
||||
sections.push(SCREEN_EXPORT_COMPLETION_PROMPT.to_string());
|
||||
}
|
||||
if task_requests_zhihu_article_publish(trimmed_instruction, page_url, page_title) {
|
||||
sections.push(ZHIHU_WRITE_PUBLISH_PROMPT.to_string());
|
||||
}
|
||||
if let Some(page_context) = build_page_context_message(page_url, page_title) {
|
||||
sections.push(page_context);
|
||||
}
|
||||
@@ -173,17 +175,11 @@ impl RuntimeEngine {
|
||||
.cmp(&right.name)
|
||||
.then(left.version.cmp(&right.version))
|
||||
});
|
||||
skills.dedup_by(|left, right| {
|
||||
left.name == right.name && left.version == right.version
|
||||
});
|
||||
skills.dedup_by(|left, right| left.name == right.name && left.version == right.version);
|
||||
skills
|
||||
}
|
||||
|
||||
pub fn loaded_skill_names(
|
||||
&self,
|
||||
config: &ZeroClawConfig,
|
||||
skills_dir: &Path,
|
||||
) -> Vec<String> {
|
||||
pub fn loaded_skill_names(&self, config: &ZeroClawConfig, skills_dir: &Path) -> Vec<String> {
|
||||
let mut names = self
|
||||
.loaded_skills(config, skills_dir)
|
||||
.into_iter()
|
||||
@@ -237,8 +233,8 @@ impl RuntimeEngine {
|
||||
}
|
||||
allowed_tools.dedup();
|
||||
|
||||
if matches!(self.profile, RuntimeProfile::GeneralAssistant) &&
|
||||
self.tool_policy.may_use_non_browser_tools
|
||||
if matches!(self.profile, RuntimeProfile::GeneralAssistant)
|
||||
&& self.tool_policy.may_use_non_browser_tools
|
||||
{
|
||||
None
|
||||
} else {
|
||||
@@ -263,9 +259,7 @@ fn browser_script_tool_names(skills: &[zeroclaw::skills::Skill]) -> Vec<String>
|
||||
|
||||
fn task_needs_local_file_read(instruction: &str) -> bool {
|
||||
let normalized = instruction.trim();
|
||||
normalized.contains("/home/") ||
|
||||
normalized.contains("./") ||
|
||||
normalized.contains("../")
|
||||
normalized.contains("/home/") || normalized.contains("./") || normalized.contains("../")
|
||||
}
|
||||
|
||||
pub fn is_zhihu_hotlist_task(
|
||||
@@ -277,16 +271,16 @@ pub fn is_zhihu_hotlist_task(
|
||||
let normalized_url = page_url.unwrap_or_default().to_ascii_lowercase();
|
||||
let normalized_title = page_title.unwrap_or_default().to_ascii_lowercase();
|
||||
|
||||
let is_zhihu = normalized_instruction.contains("zhihu") ||
|
||||
instruction.contains("知乎") ||
|
||||
normalized_url.contains("zhihu.com") ||
|
||||
normalized_title.contains("zhihu") ||
|
||||
page_title.unwrap_or_default().contains("知乎");
|
||||
let is_hotlist = normalized_instruction.contains("hotlist") ||
|
||||
instruction.contains("热榜") ||
|
||||
normalized_url.contains("/hot") ||
|
||||
normalized_title.contains("hotlist") ||
|
||||
page_title.unwrap_or_default().contains("热榜");
|
||||
let is_zhihu = normalized_instruction.contains("zhihu")
|
||||
|| instruction.contains("知乎")
|
||||
|| normalized_url.contains("zhihu.com")
|
||||
|| normalized_title.contains("zhihu")
|
||||
|| page_title.unwrap_or_default().contains("知乎");
|
||||
let is_hotlist = normalized_instruction.contains("hotlist")
|
||||
|| instruction.contains("热榜")
|
||||
|| normalized_url.contains("/hot")
|
||||
|| normalized_title.contains("hotlist")
|
||||
|| page_title.unwrap_or_default().contains("热榜");
|
||||
|
||||
is_zhihu && is_hotlist
|
||||
}
|
||||
@@ -310,6 +304,48 @@ fn task_needs_screen_export(instruction: &str) -> bool {
|
||||
|| normalized.contains("汇报")
|
||||
}
|
||||
|
||||
pub fn task_requests_zhihu_article_publish(
|
||||
instruction: &str,
|
||||
page_url: Option<&str>,
|
||||
page_title: Option<&str>,
|
||||
) -> bool {
|
||||
if !is_zhihu_write_task(instruction, page_url, page_title) {
|
||||
return false;
|
||||
}
|
||||
|
||||
let normalized = instruction.to_ascii_lowercase();
|
||||
normalized.contains("publish") || instruction.contains("发布") || instruction.contains("发表")
|
||||
}
|
||||
|
||||
pub fn is_zhihu_write_task(
|
||||
instruction: &str,
|
||||
page_url: Option<&str>,
|
||||
page_title: Option<&str>,
|
||||
) -> bool {
|
||||
let normalized_instruction = instruction.to_ascii_lowercase();
|
||||
let normalized_url = page_url.unwrap_or_default().to_ascii_lowercase();
|
||||
let normalized_title = page_title.unwrap_or_default().to_ascii_lowercase();
|
||||
|
||||
let is_zhihu = normalized_instruction.contains("zhihu")
|
||||
|| instruction.contains("知乎")
|
||||
|| normalized_url.contains("zhihu.com")
|
||||
|| normalized_title.contains("zhihu")
|
||||
|| page_title.unwrap_or_default().contains("知乎");
|
||||
let is_write = normalized_instruction.contains("article")
|
||||
|| normalized_instruction.contains("write")
|
||||
|| normalized_instruction.contains("publish")
|
||||
|| instruction.contains("文章")
|
||||
|| instruction.contains("写")
|
||||
|| instruction.contains("发布")
|
||||
|| instruction.contains("发表")
|
||||
|| normalized_url.contains("creator")
|
||||
|| normalized_url.contains("write")
|
||||
|| page_title.unwrap_or_default().contains("创作")
|
||||
|| page_title.unwrap_or_default().contains("写文章");
|
||||
|
||||
is_zhihu && is_write
|
||||
}
|
||||
|
||||
fn load_runtime_skills(config: &ZeroClawConfig, skills_dir: &Path) -> Vec<zeroclaw::skills::Skill> {
|
||||
let default_skills_dir = config.workspace_dir.join("skills");
|
||||
if skills_dir == default_skills_dir {
|
||||
@@ -344,10 +380,7 @@ fn build_page_context_message(page_url: Option<&str>, page_title: Option<&str>)
|
||||
return None;
|
||||
}
|
||||
|
||||
Some(format!(
|
||||
"Current browser context:\n{}",
|
||||
parts.join("\n")
|
||||
))
|
||||
Some(format!("Current browser context:\n{}", parts.join("\n")))
|
||||
}
|
||||
|
||||
fn map_anyhow_to_pipe_error(err: anyhow::Error) -> PipeError {
|
||||
|
||||
@@ -2,6 +2,8 @@ mod engine;
|
||||
mod profile;
|
||||
mod tool_policy;
|
||||
|
||||
pub use engine::{is_zhihu_hotlist_task, RuntimeEngine};
|
||||
pub use engine::{
|
||||
is_zhihu_hotlist_task, is_zhihu_write_task, task_requests_zhihu_article_publish, RuntimeEngine,
|
||||
};
|
||||
pub use profile::RuntimeProfile;
|
||||
pub use tool_policy::ToolPolicy;
|
||||
|
||||
6
src/runtime/profile.rs
Normal file
6
src/runtime/profile.rs
Normal file
@@ -0,0 +1,6 @@
|
||||
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
|
||||
pub enum RuntimeProfile {
|
||||
BrowserAttached,
|
||||
BrowserHeavy,
|
||||
GeneralAssistant,
|
||||
}
|
||||
@@ -13,18 +13,12 @@ impl ToolPolicy {
|
||||
RuntimeProfile::BrowserAttached => Self {
|
||||
requires_browser_surface: false,
|
||||
may_use_non_browser_tools: true,
|
||||
allowed_tools: vec![
|
||||
"superrpa_browser".to_string(),
|
||||
"browser_action".to_string(),
|
||||
],
|
||||
allowed_tools: vec!["superrpa_browser".to_string(), "browser_action".to_string()],
|
||||
},
|
||||
RuntimeProfile::BrowserHeavy => Self {
|
||||
requires_browser_surface: true,
|
||||
may_use_non_browser_tools: true,
|
||||
allowed_tools: vec![
|
||||
"superrpa_browser".to_string(),
|
||||
"browser_action".to_string(),
|
||||
],
|
||||
allowed_tools: vec!["superrpa_browser".to_string(), "browser_action".to_string()],
|
||||
},
|
||||
RuntimeProfile::GeneralAssistant => Self {
|
||||
requires_browser_surface: false,
|
||||
|
||||
@@ -1,10 +1,19 @@
|
||||
mod common;
|
||||
|
||||
use std::fs;
|
||||
use std::path::PathBuf;
|
||||
use std::sync::Arc;
|
||||
use std::time::Duration;
|
||||
|
||||
use uuid::Uuid;
|
||||
|
||||
use common::MockTransport;
|
||||
use sgclaw::agent::{
|
||||
handle_browser_message, handle_browser_message_with_context, AgentRuntimeContext,
|
||||
};
|
||||
use sgclaw::agent::runtime::{browser_action_tool_definition, execute_task_with_provider};
|
||||
use sgclaw::compat::runtime::CompatTaskContext;
|
||||
use sgclaw::config::SgClawSettings;
|
||||
use sgclaw::llm::{ChatMessage, LlmError, LlmProvider, ToolDefinition, ToolFunctionCall};
|
||||
use sgclaw::pipe::{Action, AgentMessage, BrowserMessage, BrowserPipeTool, Timing};
|
||||
use sgclaw::security::MacPolicy;
|
||||
@@ -23,20 +32,605 @@ impl LlmProvider for FakeProvider {
|
||||
}
|
||||
}
|
||||
|
||||
fn test_policy() -> MacPolicy {
|
||||
fn provider_path_test_policy() -> MacPolicy {
|
||||
policy_for_domains(&["www.baidu.com"])
|
||||
}
|
||||
|
||||
fn direct_runtime_test_policy() -> MacPolicy {
|
||||
policy_for_domains(&["95598.sgcc.com.cn"])
|
||||
}
|
||||
|
||||
fn policy_for_domains(domains: &[&str]) -> MacPolicy {
|
||||
MacPolicy::from_json_str(
|
||||
r#"{
|
||||
&serde_json::json!({
|
||||
"version": "1.0",
|
||||
"domains": { "allowed": ["www.baidu.com"] },
|
||||
"domains": { "allowed": domains },
|
||||
"pipe_actions": {
|
||||
"allowed": ["click", "type", "navigate", "getText"],
|
||||
"allowed": ["click", "type", "navigate", "getText", "eval"],
|
||||
"blocked": []
|
||||
}
|
||||
}"#,
|
||||
})
|
||||
.to_string(),
|
||||
)
|
||||
.unwrap()
|
||||
}
|
||||
|
||||
fn build_direct_runtime_skill_root() -> PathBuf {
|
||||
let root = std::env::temp_dir().join(format!(
|
||||
"sgclaw-agent-runtime-skill-root-{}",
|
||||
Uuid::new_v4()
|
||||
));
|
||||
let skill_dir = root.join("fault-details-report");
|
||||
let script_dir = skill_dir.join("scripts");
|
||||
|
||||
fs::create_dir_all(&script_dir).unwrap();
|
||||
fs::write(
|
||||
skill_dir.join("SKILL.toml"),
|
||||
r#"
|
||||
[skill]
|
||||
name = "fault-details-report"
|
||||
description = "Collect 95598 fault detail data via browser eval."
|
||||
version = "0.1.0"
|
||||
|
||||
[[tools]]
|
||||
name = "collect_fault_details"
|
||||
description = "Collect structured fault detail rows for a specific period."
|
||||
kind = "browser_script"
|
||||
command = "scripts/collect_fault_details.js"
|
||||
|
||||
[tools.args]
|
||||
period = "YYYY-MM period to collect."
|
||||
"#,
|
||||
)
|
||||
.unwrap();
|
||||
fs::write(
|
||||
script_dir.join("collect_fault_details.js"),
|
||||
r#"
|
||||
return {
|
||||
fault_type: "outage",
|
||||
observed_at: `${args.period}-15 09:00`,
|
||||
affected_scope: "line-7",
|
||||
expected_domain: args.expected_domain,
|
||||
artifact_payload: "report artifact payload"
|
||||
};
|
||||
"#,
|
||||
)
|
||||
.unwrap();
|
||||
|
||||
root
|
||||
}
|
||||
|
||||
fn write_direct_submit_config(workspace_root: &std::path::Path, skill_root: &std::path::Path) -> PathBuf {
|
||||
let config_path = workspace_root.join("sgclaw_config.json");
|
||||
fs::write(
|
||||
&config_path,
|
||||
serde_json::json!({
|
||||
"providers": [],
|
||||
"skillsDir": skill_root,
|
||||
"directSubmitSkill": "fault-details-report.collect_fault_details"
|
||||
})
|
||||
.to_string(),
|
||||
)
|
||||
.unwrap();
|
||||
config_path
|
||||
}
|
||||
|
||||
fn direct_submit_runtime_context(skill_root: &std::path::Path) -> AgentRuntimeContext {
|
||||
let workspace_root = std::env::temp_dir().join(format!(
|
||||
"sgclaw-agent-runtime-workspace-{}",
|
||||
Uuid::new_v4()
|
||||
));
|
||||
fs::create_dir_all(&workspace_root).unwrap();
|
||||
let config_path = write_direct_submit_config(&workspace_root, skill_root);
|
||||
AgentRuntimeContext::new(Some(config_path), workspace_root)
|
||||
}
|
||||
|
||||
fn submit_fault_details_message() -> BrowserMessage {
|
||||
BrowserMessage::SubmitTask {
|
||||
instruction: "请采集 2026-03 的故障明细并返回结果".to_string(),
|
||||
conversation_id: String::new(),
|
||||
messages: vec![],
|
||||
page_url: "https://95598.sgcc.com.cn/".to_string(),
|
||||
page_title: "网上国网".to_string(),
|
||||
}
|
||||
}
|
||||
|
||||
fn submit_zhihu_hotlist_export_message() -> BrowserMessage {
|
||||
BrowserMessage::SubmitTask {
|
||||
instruction: "打开知乎热榜，获取前10条数据，并导出 Excel".to_string(),
|
||||
conversation_id: String::new(),
|
||||
messages: vec![],
|
||||
page_url: String::new(),
|
||||
page_title: String::new(),
|
||||
}
|
||||
}
|
||||
|
||||
fn direct_submit_mode_logs(sent: &[AgentMessage]) -> Vec<String> {
|
||||
sent.iter()
|
||||
.filter_map(|message| match message {
|
||||
AgentMessage::LogEntry { level, message } if level == "mode" => Some(message.clone()),
|
||||
_ => None,
|
||||
})
|
||||
.collect()
|
||||
}
|
||||
|
||||
fn direct_submit_completion(sent: &[AgentMessage]) -> Option<(bool, String)> {
|
||||
sent.iter().find_map(|message| match message {
|
||||
AgentMessage::TaskComplete { success, summary } => Some((*success, summary.clone())),
|
||||
_ => None,
|
||||
})
|
||||
}
|
||||
|
||||
fn success_browser_response(seq: u64, data: serde_json::Value) -> BrowserMessage {
|
||||
BrowserMessage::Response {
|
||||
seq,
|
||||
success: true,
|
||||
data,
|
||||
aom_snapshot: vec![],
|
||||
timing: Timing {
|
||||
queue_ms: 1,
|
||||
exec_ms: 10,
|
||||
},
|
||||
}
|
||||
}
|
||||
|
||||
fn report_artifact_browser_response(
|
||||
seq: u64,
|
||||
status: &str,
|
||||
partial_reasons: &[&str],
|
||||
detail_rows: Vec<serde_json::Value>,
|
||||
summary_rows: Vec<serde_json::Value>,
|
||||
) -> BrowserMessage {
|
||||
success_browser_response(
|
||||
seq,
|
||||
serde_json::json!({
|
||||
"text": {
|
||||
"type": "report-artifact",
|
||||
"report_name": "fault-details-report",
|
||||
"period": "2026-03",
|
||||
"selected_range": {
|
||||
"start": "2026-03-08 16:00:00",
|
||||
"end": "2026-03-09 16:00:00"
|
||||
},
|
||||
"columns": ["qxdbh"],
|
||||
"rows": detail_rows,
|
||||
"sections": [{
|
||||
"name": "summary-sheet",
|
||||
"columns": ["index"],
|
||||
"rows": summary_rows
|
||||
}],
|
||||
"counts": {
|
||||
"detail_rows": detail_rows.len(),
|
||||
"summary_rows": summary_rows.len()
|
||||
},
|
||||
"status": status,
|
||||
"partial_reasons": partial_reasons,
|
||||
"downstream": {
|
||||
"export": {
|
||||
"attempted": true,
|
||||
"success": status != "blocked" && status != "error",
|
||||
"path": "http://localhost/export.xlsx"
|
||||
},
|
||||
"report_log": {
|
||||
"attempted": true,
|
||||
"success": partial_reasons.is_empty(),
|
||||
"error": partial_reasons
|
||||
.first()
|
||||
.copied()
|
||||
.unwrap_or("")
|
||||
}
|
||||
}
|
||||
}
|
||||
}),
|
||||
)
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn direct_submit_runtime_executes_fault_details_skill_without_provider_path() {
|
||||
let skill_root = build_direct_runtime_skill_root();
|
||||
let transport = Arc::new(MockTransport::new(vec![success_browser_response(
|
||||
1,
|
||||
serde_json::json!({
|
||||
"text": {
|
||||
"fault_type": "outage",
|
||||
"observed_at": "2026-03-15 09:00",
|
||||
"affected_scope": "line-7"
|
||||
}
|
||||
}),
|
||||
)]));
|
||||
let browser_tool = BrowserPipeTool::new(
|
||||
transport.clone(),
|
||||
direct_runtime_test_policy(),
|
||||
vec![1, 2, 3, 4, 5, 6, 7, 8],
|
||||
)
|
||||
.with_response_timeout(Duration::from_secs(1));
|
||||
let mut settings = SgClawSettings::from_legacy_deepseek_fields(
|
||||
"unused-key".to_string(),
|
||||
"http://127.0.0.1:9".to_string(),
|
||||
"unused-model".to_string(),
|
||||
Some(skill_root.clone()),
|
||||
)
|
||||
.unwrap();
|
||||
settings.direct_submit_skill = Some("fault-details-report.collect_fault_details".to_string());
|
||||
|
||||
let summary = sgclaw::compat::direct_skill_runtime::execute_direct_submit_skill(
|
||||
browser_tool,
|
||||
"请采集 2026-03 的故障明细并返回结果",
|
||||
&CompatTaskContext {
|
||||
page_url: Some("https://95598.sgcc.com.cn/".to_string()),
|
||||
..CompatTaskContext::default()
|
||||
},
|
||||
PathBuf::from(env!("CARGO_MANIFEST_DIR")).as_path(),
|
||||
&settings,
|
||||
)
|
||||
.unwrap();
|
||||
|
||||
assert!(summary.success);
|
||||
assert!(summary.summary.contains("fault_type"));
|
||||
let sent = transport.sent_messages();
|
||||
assert!(sent.iter().all(|message| !matches!(message, AgentMessage::LogEntry { level, message } if level == "info" && message.contains("DeepSeek config loaded"))));
|
||||
assert!(matches!(
|
||||
&sent[0],
|
||||
AgentMessage::Command {
|
||||
seq,
|
||||
action,
|
||||
params,
|
||||
security,
|
||||
} if *seq == 1
|
||||
&& action == &Action::Eval
|
||||
&& security.expected_domain == "95598.sgcc.com.cn"
|
||||
&& params["script"].as_str().is_some_and(|script| script.contains("2026-03"))
|
||||
));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn submit_task_uses_direct_skill_mode_without_llm_configuration() {
|
||||
std::env::remove_var("DEEPSEEK_API_KEY");
|
||||
std::env::remove_var("DEEPSEEK_BASE_URL");
|
||||
std::env::remove_var("DEEPSEEK_MODEL");
|
||||
|
||||
let skill_root = build_direct_runtime_skill_root();
|
||||
let runtime_context = direct_submit_runtime_context(&skill_root);
|
||||
let transport = Arc::new(MockTransport::new(vec![success_browser_response(
|
||||
1,
|
||||
serde_json::json!({
|
||||
"text": {
|
||||
"fault_type": "outage",
|
||||
"observed_at": "2026-03-15 09:00",
|
||||
"affected_scope": "line-7",
|
||||
"artifact_payload": "report artifact payload"
|
||||
}
|
||||
}),
|
||||
)]));
|
||||
let browser_tool = BrowserPipeTool::new(
|
||||
transport.clone(),
|
||||
direct_runtime_test_policy(),
|
||||
vec![1, 2, 3, 4, 5, 6, 7, 8],
|
||||
)
|
||||
.with_response_timeout(Duration::from_secs(1));
|
||||
|
||||
handle_browser_message_with_context(
|
||||
transport.as_ref(),
|
||||
&browser_tool,
|
||||
&runtime_context,
|
||||
submit_fault_details_message(),
|
||||
)
|
||||
.unwrap();
|
||||
|
||||
let sent = transport.sent_messages();
|
||||
let completion = direct_submit_completion(&sent).expect("task completion");
|
||||
|
||||
assert!(completion.0, "expected direct submit task to succeed: {sent:?}");
|
||||
assert!(
|
||||
completion.1.contains("report artifact payload"),
|
||||
"expected report artifact payload in summary: {}",
|
||||
completion.1
|
||||
);
|
||||
assert!(
|
||||
!completion.1.contains("未配置大语言模型"),
|
||||
"did not expect missing-llm summary: {}",
|
||||
completion.1
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn submit_task_rejects_invalid_direct_submit_skill_config_before_routing() {
|
||||
std::env::remove_var("DEEPSEEK_API_KEY");
|
||||
std::env::remove_var("DEEPSEEK_BASE_URL");
|
||||
std::env::remove_var("DEEPSEEK_MODEL");
|
||||
|
||||
let skill_root = build_direct_runtime_skill_root();
|
||||
let workspace_root = std::env::temp_dir().join(format!(
|
||||
"sgclaw-invalid-direct-submit-workspace-{}",
|
||||
Uuid::new_v4()
|
||||
));
|
||||
fs::create_dir_all(&workspace_root).unwrap();
|
||||
let config_path = workspace_root.join("sgclaw_config.json");
|
||||
fs::write(
|
||||
&config_path,
|
||||
serde_json::json!({
|
||||
"providers": [],
|
||||
"skillsDir": skill_root,
|
||||
"directSubmitSkill": "fault-details-report"
|
||||
})
|
||||
.to_string(),
|
||||
)
|
||||
.unwrap();
|
||||
|
||||
let runtime_context = AgentRuntimeContext::new(Some(config_path), workspace_root);
|
||||
let transport = Arc::new(MockTransport::new(vec![]));
|
||||
let browser_tool = BrowserPipeTool::new(
|
||||
transport.clone(),
|
||||
direct_runtime_test_policy(),
|
||||
vec![1, 2, 3, 4, 5, 6, 7, 8],
|
||||
)
|
||||
.with_response_timeout(Duration::from_secs(1));
|
||||
|
||||
handle_browser_message_with_context(
|
||||
transport.as_ref(),
|
||||
&browser_tool,
|
||||
&runtime_context,
|
||||
submit_fault_details_message(),
|
||||
)
|
||||
.unwrap();
|
||||
|
||||
let sent = transport.sent_messages();
|
||||
assert!(matches!(
|
||||
sent.last(),
|
||||
Some(AgentMessage::TaskComplete { success, summary })
|
||||
if !success && summary.contains("skill.tool")
|
||||
));
|
||||
assert!(direct_submit_mode_logs(&sent).is_empty());
|
||||
assert!(!sent.iter().any(|message| matches!(message, AgentMessage::Command { .. })));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn submit_task_treats_partial_report_artifact_as_success_with_warning_summary() {
|
||||
std::env::remove_var("DEEPSEEK_API_KEY");
|
||||
std::env::remove_var("DEEPSEEK_BASE_URL");
|
||||
std::env::remove_var("DEEPSEEK_MODEL");
|
||||
|
||||
let skill_root = build_direct_runtime_skill_root();
|
||||
let runtime_context = direct_submit_runtime_context(&skill_root);
|
||||
let transport = Arc::new(MockTransport::new(vec![report_artifact_browser_response(
|
||||
1,
|
||||
"partial",
|
||||
&["report_log_failed"],
|
||||
vec![serde_json::json!({ "qxdbh": "QX-1" })],
|
||||
vec![serde_json::json!({ "index": 1 })],
|
||||
)]));
|
||||
let browser_tool = BrowserPipeTool::new(
|
||||
transport.clone(),
|
||||
direct_runtime_test_policy(),
|
||||
vec![1, 2, 3, 4, 5, 6, 7, 8],
|
||||
)
|
||||
.with_response_timeout(Duration::from_secs(1));
|
||||
|
||||
handle_browser_message_with_context(
|
||||
transport.as_ref(),
|
||||
&browser_tool,
|
||||
&runtime_context,
|
||||
submit_fault_details_message(),
|
||||
)
|
||||
.unwrap();
|
||||
|
||||
let sent = transport.sent_messages();
|
||||
let completion = direct_submit_completion(&sent).expect("task completion");
|
||||
|
||||
assert!(completion.0, "expected partial artifact to succeed: {sent:?}");
|
||||
assert!(completion.1.contains("fault-details-report"));
|
||||
assert!(completion.1.contains("2026-03"));
|
||||
assert!(completion.1.contains("status=partial"));
|
||||
assert!(completion.1.contains("detail_rows=1"));
|
||||
assert!(completion.1.contains("summary_rows=1"));
|
||||
assert!(completion.1.contains("report_log_failed"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn submit_task_treats_empty_report_artifact_as_success() {
|
||||
std::env::remove_var("DEEPSEEK_API_KEY");
|
||||
std::env::remove_var("DEEPSEEK_BASE_URL");
|
||||
std::env::remove_var("DEEPSEEK_MODEL");
|
||||
|
||||
let skill_root = build_direct_runtime_skill_root();
|
||||
let runtime_context = direct_submit_runtime_context(&skill_root);
|
||||
let transport = Arc::new(MockTransport::new(vec![report_artifact_browser_response(
|
||||
1,
|
||||
"empty",
|
||||
&[],
|
||||
vec![],
|
||||
vec![],
|
||||
)]));
|
||||
let browser_tool = BrowserPipeTool::new(
|
||||
transport.clone(),
|
||||
direct_runtime_test_policy(),
|
||||
vec![1, 2, 3, 4, 5, 6, 7, 8],
|
||||
)
|
||||
.with_response_timeout(Duration::from_secs(1));
|
||||
|
||||
handle_browser_message_with_context(
|
||||
transport.as_ref(),
|
||||
&browser_tool,
|
||||
&runtime_context,
|
||||
submit_fault_details_message(),
|
||||
)
|
||||
.unwrap();
|
||||
|
||||
let sent = transport.sent_messages();
|
||||
let completion = direct_submit_completion(&sent).expect("task completion");
|
||||
|
||||
assert!(completion.0, "expected empty artifact to succeed: {sent:?}");
|
||||
assert!(completion.1.contains("status=empty"));
|
||||
assert!(completion.1.contains("detail_rows=0"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn submit_task_treats_blocked_report_artifact_as_failure() {
|
||||
std::env::remove_var("DEEPSEEK_API_KEY");
|
||||
std::env::remove_var("DEEPSEEK_BASE_URL");
|
||||
std::env::remove_var("DEEPSEEK_MODEL");
|
||||
|
||||
let skill_root = build_direct_runtime_skill_root();
|
||||
let runtime_context = direct_submit_runtime_context(&skill_root);
|
||||
let transport = Arc::new(MockTransport::new(vec![report_artifact_browser_response(
|
||||
1,
|
||||
"blocked",
|
||||
&["selected_range_unavailable"],
|
||||
vec![],
|
||||
vec![],
|
||||
)]));
|
||||
let browser_tool = BrowserPipeTool::new(
|
||||
transport.clone(),
|
||||
direct_runtime_test_policy(),
|
||||
vec![1, 2, 3, 4, 5, 6, 7, 8],
|
||||
)
|
||||
.with_response_timeout(Duration::from_secs(1));
|
||||
|
||||
handle_browser_message_with_context(
|
||||
transport.as_ref(),
|
||||
&browser_tool,
|
||||
&runtime_context,
|
||||
submit_fault_details_message(),
|
||||
)
|
||||
.unwrap();
|
||||
|
||||
let sent = transport.sent_messages();
|
||||
let completion = direct_submit_completion(&sent).expect("task completion");
|
||||
|
||||
assert!(!completion.0, "expected blocked artifact to fail: {sent:?}");
|
||||
assert!(completion.1.contains("status=blocked"));
|
||||
assert!(completion.1.contains("selected_range_unavailable"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn submit_task_treats_error_report_artifact_as_failure() {
|
||||
std::env::remove_var("DEEPSEEK_API_KEY");
|
||||
std::env::remove_var("DEEPSEEK_BASE_URL");
|
||||
std::env::remove_var("DEEPSEEK_MODEL");
|
||||
|
||||
let skill_root = build_direct_runtime_skill_root();
|
||||
let runtime_context = direct_submit_runtime_context(&skill_root);
|
||||
let transport = Arc::new(MockTransport::new(vec![report_artifact_browser_response(
|
||||
1,
|
||||
"error",
|
||||
&["detail_normalization_failed"],
|
||||
vec![],
|
||||
vec![],
|
||||
)]));
|
||||
let browser_tool = BrowserPipeTool::new(
|
||||
transport.clone(),
|
||||
direct_runtime_test_policy(),
|
||||
vec![1, 2, 3, 4, 5, 6, 7, 8],
|
||||
)
|
||||
.with_response_timeout(Duration::from_secs(1));
|
||||
|
||||
handle_browser_message_with_context(
|
||||
transport.as_ref(),
|
||||
&browser_tool,
|
||||
&runtime_context,
|
||||
submit_fault_details_message(),
|
||||
)
|
||||
.unwrap();
|
||||
|
||||
let sent = transport.sent_messages();
|
||||
let completion = direct_submit_completion(&sent).expect("task completion");
|
||||
|
||||
assert!(!completion.0, "expected error artifact to fail: {sent:?}");
|
||||
assert!(completion.1.contains("status=error"));
|
||||
assert!(completion.1.contains("detail_normalization_failed"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn submit_task_routes_zhihu_hotlist_export_before_direct_submit() {
|
||||
std::env::remove_var("DEEPSEEK_API_KEY");
|
||||
std::env::remove_var("DEEPSEEK_BASE_URL");
|
||||
std::env::remove_var("DEEPSEEK_MODEL");
|
||||
|
||||
let skill_root = build_direct_runtime_skill_root();
|
||||
let runtime_context = direct_submit_runtime_context(&skill_root);
|
||||
let transport = Arc::new(MockTransport::new(vec![]));
|
||||
let browser_tool = BrowserPipeTool::new(
|
||||
transport.clone(),
|
||||
policy_for_domains(&["www.zhihu.com"]),
|
||||
vec![1, 2, 3, 4, 5, 6, 7, 8],
|
||||
)
|
||||
.with_response_timeout(Duration::from_secs(1));
|
||||
|
||||
handle_browser_message_with_context(
|
||||
transport.as_ref(),
|
||||
&browser_tool,
|
||||
&runtime_context,
|
||||
submit_zhihu_hotlist_export_message(),
|
||||
)
|
||||
.unwrap();
|
||||
|
||||
let sent = transport.sent_messages();
|
||||
let mode_logs = direct_submit_mode_logs(&sent);
|
||||
let completion = direct_submit_completion(&sent).expect("task completion");
|
||||
|
||||
assert_eq!(mode_logs, vec!["zeroclaw_process_message_primary".to_string()]);
|
||||
assert!(
|
||||
!completion.0,
|
||||
"expected zhihu export without page context to fail before browser actions: {sent:?}"
|
||||
);
|
||||
assert!(
|
||||
!completion
|
||||
.1
|
||||
.contains("direct submit skill requires page_url so expected_domain can be derived"),
|
||||
"unexpected direct submit fallback: {sent:?}"
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn direct_skill_mode_logs_direct_skill_primary() {
|
||||
std::env::remove_var("DEEPSEEK_API_KEY");
|
||||
std::env::remove_var("DEEPSEEK_BASE_URL");
|
||||
std::env::remove_var("DEEPSEEK_MODEL");
|
||||
|
||||
let skill_root = build_direct_runtime_skill_root();
|
||||
let runtime_context = direct_submit_runtime_context(&skill_root);
|
||||
let transport = Arc::new(MockTransport::new(vec![success_browser_response(
|
||||
1,
|
||||
serde_json::json!({
|
||||
"text": {
|
||||
"fault_type": "outage",
|
||||
"observed_at": "2026-03-15 09:00",
|
||||
"affected_scope": "line-7",
|
||||
"artifact_payload": "report artifact payload"
|
||||
}
|
||||
}),
|
||||
)]));
|
||||
let browser_tool = BrowserPipeTool::new(
|
||||
transport.clone(),
|
||||
direct_runtime_test_policy(),
|
||||
vec![1, 2, 3, 4, 5, 6, 7, 8],
|
||||
)
|
||||
.with_response_timeout(Duration::from_secs(1));
|
||||
|
||||
handle_browser_message_with_context(
|
||||
transport.as_ref(),
|
||||
&browser_tool,
|
||||
&runtime_context,
|
||||
submit_fault_details_message(),
|
||||
)
|
||||
.unwrap();
|
||||
|
||||
let sent = transport.sent_messages();
|
||||
let mode_logs = direct_submit_mode_logs(&sent);
|
||||
|
||||
assert_eq!(mode_logs, vec!["direct_skill_primary".to_string()]);
|
||||
assert!(
|
||||
!mode_logs.iter().any(|mode| mode == "compat_llm_primary"),
|
||||
"unexpected compat mode logs: {mode_logs:?}"
|
||||
);
|
||||
assert!(
|
||||
!mode_logs
|
||||
.iter()
|
||||
.any(|mode| mode == "zeroclaw_process_message_primary"),
|
||||
"unexpected zeroclaw mode logs: {mode_logs:?}"
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn browser_action_tool_definition_uses_expected_name() {
|
||||
let tool = browser_action_tool_definition();
|
||||
@@ -72,7 +666,7 @@ fn runtime_executes_provider_tool_calls_and_returns_summary() {
|
||||
]));
|
||||
let browser_tool = BrowserPipeTool::new(
|
||||
transport.clone(),
|
||||
test_policy(),
|
||||
provider_path_test_policy(),
|
||||
vec![1, 2, 3, 4, 5, 6, 7, 8],
|
||||
)
|
||||
.with_response_timeout(Duration::from_secs(1));
|
||||
@@ -132,3 +726,46 @@ fn runtime_executes_provider_tool_calls_and_returns_summary() {
|
||||
if *seq == 2 && action == &Action::Type
|
||||
));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn legacy_agent_runtime_is_explicitly_dev_only() {
|
||||
assert!(sgclaw::agent::runtime::LEGACY_DEV_ONLY);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn production_submit_task_does_not_route_into_legacy_runtime_without_llm_config() {
|
||||
std::env::remove_var("DEEPSEEK_API_KEY");
|
||||
std::env::remove_var("DEEPSEEK_BASE_URL");
|
||||
std::env::remove_var("DEEPSEEK_MODEL");
|
||||
|
||||
let transport = Arc::new(MockTransport::new(vec![]));
|
||||
let browser_tool = BrowserPipeTool::new(
|
||||
transport.clone(),
|
||||
provider_path_test_policy(),
|
||||
vec![1, 2, 3, 4, 5, 6, 7, 8],
|
||||
)
|
||||
.with_response_timeout(Duration::from_secs(1));
|
||||
|
||||
handle_browser_message(
|
||||
transport.as_ref(),
|
||||
&browser_tool,
|
||||
BrowserMessage::SubmitTask {
|
||||
instruction: "打开百度".to_string(),
|
||||
conversation_id: String::new(),
|
||||
messages: vec![],
|
||||
page_url: String::new(),
|
||||
page_title: String::new(),
|
||||
},
|
||||
)
|
||||
.unwrap();
|
||||
|
||||
let sent = transport.sent_messages();
|
||||
assert!(matches!(
|
||||
sent.last(),
|
||||
Some(AgentMessage::TaskComplete { success, summary })
|
||||
if !success && summary.contains("未配置大语言模型")
|
||||
));
|
||||
assert!(!sent
|
||||
.iter()
|
||||
.any(|message| { matches!(message, AgentMessage::Command { .. }) }));
|
||||
}
|
||||
|
||||
@@ -1,15 +1,17 @@
|
||||
mod common;
|
||||
|
||||
use std::collections::HashMap;
|
||||
use std::fs;
|
||||
use std::path::PathBuf;
|
||||
use std::sync::Arc;
|
||||
use std::time::Duration;
|
||||
use std::time::{SystemTime, UNIX_EPOCH};
|
||||
use std::fs;
|
||||
|
||||
use common::MockTransport;
|
||||
use serde_json::json;
|
||||
use sgclaw::compat::browser_script_skill_tool::BrowserScriptSkillTool;
|
||||
use sgclaw::compat::browser_script_skill_tool::{
|
||||
execute_browser_script_tool, BrowserScriptSkillTool,
|
||||
};
|
||||
use sgclaw::pipe::{Action, AgentMessage, BrowserMessage, BrowserPipeTool, Timing};
|
||||
use sgclaw::security::MacPolicy;
|
||||
use zeroclaw::skills::SkillTool;
|
||||
@@ -29,6 +31,174 @@ fn test_policy() -> MacPolicy {
|
||||
.unwrap()
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn execute_browser_script_tool_runs_packaged_script_with_expected_domain() {
|
||||
let skill_dir = unique_temp_dir("sgclaw-browser-script-helper");
|
||||
let scripts_dir = skill_dir.join("scripts");
|
||||
fs::create_dir_all(&scripts_dir).unwrap();
|
||||
fs::write(
|
||||
scripts_dir.join("extract_hotlist.js"),
|
||||
"return { wrapped_args: args, source: \"packaged script\" };\n",
|
||||
)
|
||||
.unwrap();
|
||||
|
||||
let transport = Arc::new(MockTransport::new(vec![BrowserMessage::Response {
|
||||
seq: 1,
|
||||
success: true,
|
||||
data: json!({
|
||||
"text": {
|
||||
"sheet_name": "知乎热榜",
|
||||
"rows": [[1, "标题", "10条"]]
|
||||
}
|
||||
}),
|
||||
aom_snapshot: vec![],
|
||||
timing: Timing {
|
||||
queue_ms: 1,
|
||||
exec_ms: 5,
|
||||
},
|
||||
}]));
|
||||
let browser_tool = BrowserPipeTool::new(
|
||||
transport.clone(),
|
||||
test_policy(),
|
||||
vec![1, 2, 3, 4, 5, 6, 7, 8],
|
||||
)
|
||||
.with_response_timeout(Duration::from_secs(1));
|
||||
|
||||
let mut tool_args = HashMap::new();
|
||||
tool_args.insert("top_n".to_string(), "How many rows to extract".to_string());
|
||||
let skill_tool = SkillTool {
|
||||
name: "extract_hotlist".to_string(),
|
||||
description: "Extract structured hotlist rows".to_string(),
|
||||
kind: "browser_script".to_string(),
|
||||
command: "scripts/extract_hotlist.js".to_string(),
|
||||
args: tool_args,
|
||||
};
|
||||
|
||||
let result = execute_browser_script_tool(
|
||||
&skill_tool,
|
||||
&skill_dir,
|
||||
browser_tool,
|
||||
json!({
|
||||
"expected_domain": "https://WWW.ZHIHU.COM/hot?foo=bar",
|
||||
"top_n": "10"
|
||||
}),
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
let sent = transport.sent_messages();
|
||||
assert!(result.success);
|
||||
assert_eq!(
|
||||
serde_json::from_str::<serde_json::Value>(&result.output).unwrap(),
|
||||
json!({
|
||||
"sheet_name": "知乎热榜",
|
||||
"rows": [[1, "标题", "10条"]]
|
||||
})
|
||||
);
|
||||
assert!(matches!(
|
||||
&sent[0],
|
||||
AgentMessage::Command {
|
||||
action,
|
||||
params,
|
||||
security,
|
||||
..
|
||||
} if action == &Action::Eval
|
||||
&& security.expected_domain == "www.zhihu.com"
|
||||
&& params["script"].as_str().unwrap().contains("const args = {\"top_n\":\"10\"};")
|
||||
&& params["script"].as_str().unwrap().contains("source: \"packaged script\"")
|
||||
));
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn execute_browser_script_tool_rejects_non_browser_script_tool_kind() {
|
||||
let skill_dir = unique_temp_dir("sgclaw-browser-script-helper-invalid-kind");
|
||||
let scripts_dir = skill_dir.join("scripts");
|
||||
fs::create_dir_all(&scripts_dir).unwrap();
|
||||
fs::write(scripts_dir.join("extract_hotlist.js"), "return 'unused';\n").unwrap();
|
||||
|
||||
let transport = Arc::new(MockTransport::new(vec![]));
|
||||
let browser_tool = BrowserPipeTool::new(
|
||||
transport.clone(),
|
||||
test_policy(),
|
||||
vec![1, 2, 3, 4, 5, 6, 7, 8],
|
||||
)
|
||||
.with_response_timeout(Duration::from_secs(1));
|
||||
|
||||
let mut tool_args = HashMap::new();
|
||||
tool_args.insert("top_n".to_string(), "How many rows to extract".to_string());
|
||||
let skill_tool = SkillTool {
|
||||
name: "extract_hotlist".to_string(),
|
||||
description: "Extract structured hotlist rows".to_string(),
|
||||
kind: "shell".to_string(),
|
||||
command: "scripts/extract_hotlist.js".to_string(),
|
||||
args: tool_args,
|
||||
};
|
||||
|
||||
let result = execute_browser_script_tool(
|
||||
&skill_tool,
|
||||
&skill_dir,
|
||||
browser_tool,
|
||||
json!({
|
||||
"expected_domain": "www.zhihu.com",
|
||||
"top_n": "10"
|
||||
}),
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
assert!(!result.success);
|
||||
assert_eq!(
|
||||
result.error.as_deref(),
|
||||
Some("browser script tool kind must be browser_script, got shell")
|
||||
);
|
||||
assert!(transport.sent_messages().is_empty());
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn execute_browser_script_tool_rejects_missing_expected_domain() {
|
||||
let skill_dir = unique_temp_dir("sgclaw-browser-script-helper-invalid-domain");
|
||||
let scripts_dir = skill_dir.join("scripts");
|
||||
fs::create_dir_all(&scripts_dir).unwrap();
|
||||
fs::write(scripts_dir.join("extract_hotlist.js"), "return 'unused';\n").unwrap();
|
||||
|
||||
let transport = Arc::new(MockTransport::new(vec![]));
|
||||
let browser_tool = BrowserPipeTool::new(
|
||||
transport.clone(),
|
||||
test_policy(),
|
||||
vec![1, 2, 3, 4, 5, 6, 7, 8],
|
||||
)
|
||||
.with_response_timeout(Duration::from_secs(1));
|
||||
|
||||
let mut tool_args = HashMap::new();
|
||||
tool_args.insert("top_n".to_string(), "How many rows to extract".to_string());
|
||||
let skill_tool = SkillTool {
|
||||
name: "extract_hotlist".to_string(),
|
||||
description: "Extract structured hotlist rows".to_string(),
|
||||
kind: "browser_script".to_string(),
|
||||
command: "scripts/extract_hotlist.js".to_string(),
|
||||
args: tool_args,
|
||||
};
|
||||
|
||||
let result = execute_browser_script_tool(
|
||||
&skill_tool,
|
||||
&skill_dir,
|
||||
browser_tool,
|
||||
json!({
|
||||
"expected_domain": " ",
|
||||
"top_n": "10"
|
||||
}),
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
assert!(!result.success);
|
||||
assert_eq!(
|
||||
result.error.as_deref(),
|
||||
Some("expected_domain must be a non-empty string, got \" \"")
|
||||
);
|
||||
assert!(transport.sent_messages().is_empty());
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn browser_script_skill_tool_executes_packaged_script_via_eval() {
|
||||
let skill_dir = unique_temp_dir("sgclaw-browser-script-skill");
|
||||
@@ -77,13 +247,8 @@ return {
|
||||
command: "scripts/extract_hotlist.js".to_string(),
|
||||
args,
|
||||
};
|
||||
let tool = BrowserScriptSkillTool::new(
|
||||
"zhihu-hotlist",
|
||||
&skill_tool,
|
||||
&skill_dir,
|
||||
browser_tool,
|
||||
)
|
||||
.unwrap();
|
||||
let tool = BrowserScriptSkillTool::new("zhihu-hotlist", &skill_tool, &skill_dir, browser_tool)
|
||||
.unwrap();
|
||||
|
||||
let result = tool
|
||||
.execute(json!({
|
||||
@@ -116,6 +281,202 @@ return {
|
||||
));
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn browser_script_skill_tool_executes_script_directly_under_skill_root() {
|
||||
let skill_root = unique_temp_dir("sgclaw-browser-script-direct-root");
|
||||
let script_name = "extract_hotlist_direct.js";
|
||||
let script_path = skill_root.join(script_name);
|
||||
fs::write(
|
||||
&script_path,
|
||||
r#"
|
||||
return {
|
||||
sheet_name: "知乎热榜",
|
||||
rows: [[1, "标题", args.top_n]]
|
||||
};
|
||||
"#,
|
||||
)
|
||||
.unwrap();
|
||||
|
||||
let transport = Arc::new(MockTransport::new(vec![BrowserMessage::Response {
|
||||
seq: 1,
|
||||
success: true,
|
||||
data: json!({
|
||||
"text": {
|
||||
"sheet_name": "知乎热榜",
|
||||
"rows": [[1, "标题", "10条"]]
|
||||
}
|
||||
}),
|
||||
aom_snapshot: vec![],
|
||||
timing: Timing {
|
||||
queue_ms: 1,
|
||||
exec_ms: 5,
|
||||
},
|
||||
}]));
|
||||
let browser_tool = BrowserPipeTool::new(
|
||||
transport.clone(),
|
||||
test_policy(),
|
||||
vec![1, 2, 3, 4, 5, 6, 7, 8],
|
||||
)
|
||||
.with_response_timeout(Duration::from_secs(1));
|
||||
|
||||
let mut args = HashMap::new();
|
||||
args.insert("top_n".to_string(), "How many rows to extract".to_string());
|
||||
let skill_tool = SkillTool {
|
||||
name: "extract_hotlist".to_string(),
|
||||
description: "Extract structured hotlist rows".to_string(),
|
||||
kind: "browser_script".to_string(),
|
||||
command: script_name.to_string(),
|
||||
args,
|
||||
};
|
||||
let tool = BrowserScriptSkillTool::new("zhihu-hotlist", &skill_tool, &skill_root, browser_tool)
|
||||
.unwrap();
|
||||
|
||||
let result = tool
|
||||
.execute(json!({
|
||||
"expected_domain": "https://www.zhihu.com/hot",
|
||||
"top_n": "10条"
|
||||
}))
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
let sent = transport.sent_messages();
|
||||
assert!(result.success);
|
||||
assert_eq!(
|
||||
serde_json::from_str::<serde_json::Value>(&result.output).unwrap(),
|
||||
json!({
|
||||
"sheet_name": "知乎热榜",
|
||||
"rows": [[1, "标题", "10条"]]
|
||||
})
|
||||
);
|
||||
assert!(matches!(
|
||||
&sent[0],
|
||||
AgentMessage::Command {
|
||||
action,
|
||||
params,
|
||||
security,
|
||||
..
|
||||
} if action == &Action::Eval
|
||||
&& security.expected_domain == "www.zhihu.com"
|
||||
&& params["script"].as_str().unwrap().contains("const args = {\"top_n\":\"10条\"};")
|
||||
&& params["script"].as_str().unwrap().contains("rows: [[1, \"标题\", args.top_n]]")
|
||||
));
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn execute_browser_script_tool_preserves_structured_report_artifact_payload() {
|
||||
let skill_dir = unique_temp_dir("sgclaw-browser-script-helper-report-artifact");
|
||||
let scripts_dir = skill_dir.join("scripts");
|
||||
fs::create_dir_all(&scripts_dir).unwrap();
|
||||
fs::write(
|
||||
scripts_dir.join("collect_fault_details.js"),
|
||||
r#"
|
||||
return {
|
||||
type: "report-artifact",
|
||||
report_name: "fault-details-report",
|
||||
period: args.period,
|
||||
selected_range: {
|
||||
start: "2026-03-08 16:00:00",
|
||||
end: "2026-03-09 16:00:00"
|
||||
},
|
||||
columns: ["qxdbh"],
|
||||
rows: [{ qxdbh: "QX-1" }],
|
||||
sections: [{ name: "summary-sheet", columns: ["index"], rows: [{ index: 1 }] }],
|
||||
counts: { detail_rows: 1, summary_rows: 1 },
|
||||
status: "partial",
|
||||
partial_reasons: ["report_log_failed"],
|
||||
downstream: {
|
||||
export: { attempted: true, success: true, path: "http://localhost/export.xlsx" },
|
||||
report_log: { attempted: true, success: false, error: "500" }
|
||||
}
|
||||
};
|
||||
"#,
|
||||
)
|
||||
.unwrap();
|
||||
|
||||
let transport = Arc::new(MockTransport::new(vec![BrowserMessage::Response {
|
||||
seq: 1,
|
||||
success: true,
|
||||
data: json!({
|
||||
"text": {
|
||||
"type": "report-artifact",
|
||||
"report_name": "fault-details-report",
|
||||
"period": "2026-03",
|
||||
"selected_range": {
|
||||
"start": "2026-03-08 16:00:00",
|
||||
"end": "2026-03-09 16:00:00"
|
||||
},
|
||||
"columns": ["qxdbh"],
|
||||
"rows": [{ "qxdbh": "QX-1" }],
|
||||
"sections": [{ "name": "summary-sheet", "columns": ["index"], "rows": [{ "index": 1 }] }],
|
||||
"counts": { "detail_rows": 1, "summary_rows": 1 },
|
||||
"status": "partial",
|
||||
"partial_reasons": ["report_log_failed"],
|
||||
"downstream": {
|
||||
"export": { "attempted": true, "success": true, "path": "http://localhost/export.xlsx" },
|
||||
"report_log": { "attempted": true, "success": false, "error": "500" }
|
||||
}
|
||||
}
|
||||
}),
|
||||
aom_snapshot: vec![],
|
||||
timing: Timing {
|
||||
queue_ms: 1,
|
||||
exec_ms: 5,
|
||||
},
|
||||
}]));
|
||||
let browser_tool = BrowserPipeTool::new(
|
||||
transport.clone(),
|
||||
test_policy(),
|
||||
vec![1, 2, 3, 4, 5, 6, 7, 8],
|
||||
)
|
||||
.with_response_timeout(Duration::from_secs(1));
|
||||
|
||||
let mut tool_args = HashMap::new();
|
||||
tool_args.insert("period".to_string(), "YYYY-MM period to collect".to_string());
|
||||
let skill_tool = SkillTool {
|
||||
name: "collect_fault_details".to_string(),
|
||||
description: "Collect structured fault details".to_string(),
|
||||
kind: "browser_script".to_string(),
|
||||
command: "scripts/collect_fault_details.js".to_string(),
|
||||
args: tool_args,
|
||||
};
|
||||
|
||||
let result = execute_browser_script_tool(
|
||||
&skill_tool,
|
||||
&skill_dir,
|
||||
browser_tool,
|
||||
json!({
|
||||
"expected_domain": "https://www.zhihu.com/",
|
||||
"period": "2026-03"
|
||||
}),
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
assert!(result.success);
|
||||
assert_eq!(
|
||||
serde_json::from_str::<serde_json::Value>(&result.output).unwrap(),
|
||||
json!({
|
||||
"type": "report-artifact",
|
||||
"report_name": "fault-details-report",
|
||||
"period": "2026-03",
|
||||
"selected_range": {
|
||||
"start": "2026-03-08 16:00:00",
|
||||
"end": "2026-03-09 16:00:00"
|
||||
},
|
||||
"columns": ["qxdbh"],
|
||||
"rows": [{ "qxdbh": "QX-1" }],
|
||||
"sections": [{ "name": "summary-sheet", "columns": ["index"], "rows": [{ "index": 1 }] }],
|
||||
"counts": { "detail_rows": 1, "summary_rows": 1 },
|
||||
"status": "partial",
|
||||
"partial_reasons": ["report_log_failed"],
|
||||
"downstream": {
|
||||
"export": { "attempted": true, "success": true, "path": "http://localhost/export.xlsx" },
|
||||
"report_log": { "attempted": true, "success": false, "error": "500" }
|
||||
}
|
||||
})
|
||||
);
|
||||
}
|
||||
|
||||
fn unique_temp_dir(prefix: &str) -> PathBuf {
|
||||
let nanos = SystemTime::now()
|
||||
.duration_since(UNIX_EPOCH)
|
||||
|
||||
@@ -96,8 +96,14 @@ fn browser_tool_exposes_privileged_surface_metadata_backed_by_mac_policy() {
|
||||
assert!(metadata.privileged);
|
||||
assert!(!metadata.defines_runtime_identity);
|
||||
assert_eq!(metadata.guard, "mac_policy");
|
||||
assert_eq!(metadata.allowed_domains, vec!["oa.example.com", "erp.example.com"]);
|
||||
assert_eq!(metadata.allowed_actions, vec!["click", "type", "navigate", "getText"]);
|
||||
assert_eq!(
|
||||
metadata.allowed_domains,
|
||||
vec!["oa.example.com", "erp.example.com"]
|
||||
);
|
||||
assert_eq!(
|
||||
metadata.allowed_actions,
|
||||
vec!["click", "type", "navigate", "getText"]
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
|
||||
@@ -26,7 +26,9 @@ fn test_policy() -> MacPolicy {
|
||||
.unwrap()
|
||||
}
|
||||
|
||||
fn build_adapter(messages: Vec<BrowserMessage>) -> (Arc<MockTransport>, ZeroClawBrowserTool<MockTransport>) {
|
||||
fn build_adapter(
|
||||
messages: Vec<BrowserMessage>,
|
||||
) -> (Arc<MockTransport>, ZeroClawBrowserTool<MockTransport>) {
|
||||
let transport = Arc::new(MockTransport::new(messages));
|
||||
let browser_tool = BrowserPipeTool::new(
|
||||
transport.clone(),
|
||||
@@ -204,13 +206,11 @@ async fn zeroclaw_browser_tool_keeps_domain_validation_in_mac_policy() {
|
||||
assert!(!result.success);
|
||||
assert!(result.output.is_empty());
|
||||
assert_eq!(transport.sent_messages().len(), 0);
|
||||
assert!(
|
||||
result
|
||||
.error
|
||||
.as_deref()
|
||||
.unwrap()
|
||||
.contains("domain is not allowed")
|
||||
);
|
||||
assert!(result
|
||||
.error
|
||||
.as_deref()
|
||||
.unwrap()
|
||||
.contains("domain is not allowed"));
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
@@ -300,25 +300,19 @@ async fn zeroclaw_browser_tool_rejects_missing_required_action_parameters() {
|
||||
assert!(!missing_text_selector.success);
|
||||
assert!(!missing_navigate_url.success);
|
||||
assert_eq!(transport.sent_messages().len(), 0);
|
||||
assert!(
|
||||
missing_click_selector
|
||||
.error
|
||||
.as_deref()
|
||||
.unwrap()
|
||||
.contains("click requires selector")
|
||||
);
|
||||
assert!(
|
||||
missing_text_selector
|
||||
.error
|
||||
.as_deref()
|
||||
.unwrap()
|
||||
.contains("getText requires selector")
|
||||
);
|
||||
assert!(
|
||||
missing_navigate_url
|
||||
.error
|
||||
.as_deref()
|
||||
.unwrap()
|
||||
.contains("navigate requires url")
|
||||
);
|
||||
assert!(missing_click_selector
|
||||
.error
|
||||
.as_deref()
|
||||
.unwrap()
|
||||
.contains("click requires selector"));
|
||||
assert!(missing_text_selector
|
||||
.error
|
||||
.as_deref()
|
||||
.unwrap()
|
||||
.contains("getText requires selector"));
|
||||
assert!(missing_navigate_url
|
||||
.error
|
||||
.as_deref()
|
||||
.unwrap()
|
||||
.contains("navigate requires url"));
|
||||
}
|
||||
|
||||
@@ -3,20 +3,12 @@ use std::path::Path;
|
||||
use std::sync::{Mutex, OnceLock};
|
||||
|
||||
use sgclaw::compat::config_adapter::{
|
||||
build_zeroclaw_config,
|
||||
build_zeroclaw_config_from_sgclaw_settings,
|
||||
build_zeroclaw_config_from_settings,
|
||||
resolve_skills_dir,
|
||||
zeroclaw_default_skills_dir,
|
||||
build_zeroclaw_config, build_zeroclaw_config_from_settings,
|
||||
build_zeroclaw_config_from_sgclaw_settings, resolve_skills_dir, zeroclaw_default_skills_dir,
|
||||
zeroclaw_workspace_dir,
|
||||
};
|
||||
use sgclaw::config::{
|
||||
BrowserBackend,
|
||||
DeepSeekSettings,
|
||||
OfficeBackend,
|
||||
PlannerMode,
|
||||
SgClawSettings,
|
||||
SkillsPromptMode,
|
||||
BrowserBackend, DeepSeekSettings, OfficeBackend, PlannerMode, SgClawSettings, SkillsPromptMode,
|
||||
};
|
||||
use sgclaw::runtime::RuntimeProfile;
|
||||
use uuid::Uuid;
|
||||
@@ -61,11 +53,17 @@ fn zeroclaw_config_adapter_uses_deterministic_workspace_dir() {
|
||||
let workspace_dir = zeroclaw_workspace_dir(Path::new("/var/lib/sgclaw"));
|
||||
let config = build_zeroclaw_config_from_settings(Path::new("/var/lib/sgclaw"), &settings);
|
||||
|
||||
assert_eq!(workspace_dir, Path::new("/var/lib/sgclaw/.sgclaw-zeroclaw-workspace"));
|
||||
assert_eq!(
|
||||
workspace_dir,
|
||||
Path::new("/var/lib/sgclaw/.sgclaw-zeroclaw-workspace")
|
||||
);
|
||||
assert_eq!(config.workspace_dir, workspace_dir);
|
||||
assert_eq!(config.default_provider.as_deref(), Some("deepseek"));
|
||||
assert_eq!(config.default_model.as_deref(), Some("deepseek-reasoner"));
|
||||
assert_eq!(config.api_url.as_deref(), Some("https://proxy.example.com/v1"));
|
||||
assert_eq!(
|
||||
config.api_url.as_deref(),
|
||||
Some("https://proxy.example.com/v1")
|
||||
);
|
||||
assert_eq!(
|
||||
resolve_skills_dir(Path::new("/var/lib/sgclaw"), &settings),
|
||||
zeroclaw_default_skills_dir(Path::new("/var/lib/sgclaw"))
|
||||
@@ -163,6 +161,60 @@ fn sgclaw_settings_default_to_compact_skills_and_browser_attached_profile() {
|
||||
assert_eq!(settings.skills_prompt_mode, SkillsPromptMode::Compact);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn sgclaw_settings_load_direct_submit_only_config_and_resolve_relative_skills_dir() {
|
||||
let root = std::env::temp_dir().join(format!("sgclaw-direct-submit-only-config-{}", Uuid::new_v4()));
|
||||
fs::create_dir_all(&root).unwrap();
|
||||
let config_path = root.join("sgclaw_config.json");
|
||||
|
||||
fs::write(
|
||||
&config_path,
|
||||
r#"{
|
||||
"providers": [],
|
||||
"skillsDir": "skill_lib",
|
||||
"directSubmitSkill": "fault-details-report.collect_fault_details"
|
||||
}"#,
|
||||
)
|
||||
.unwrap();
|
||||
|
||||
let settings = SgClawSettings::load(Some(config_path.as_path()))
|
||||
.unwrap()
|
||||
.expect("expected sgclaw settings from config file");
|
||||
|
||||
assert_eq!(
|
||||
settings.direct_submit_skill.as_deref(),
|
||||
Some("fault-details-report.collect_fault_details")
|
||||
);
|
||||
assert_eq!(settings.skills_dir, Some(root.join("skill_lib")));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn sgclaw_settings_reject_invalid_direct_submit_skill_format() {
|
||||
let root = std::env::temp_dir().join(format!(
|
||||
"sgclaw-invalid-direct-submit-skill-{}",
|
||||
Uuid::new_v4()
|
||||
));
|
||||
fs::create_dir_all(&root).unwrap();
|
||||
let config_path = root.join("sgclaw_config.json");
|
||||
|
||||
fs::write(
|
||||
&config_path,
|
||||
r#"{
|
||||
"providers": [],
|
||||
"skillsDir": "skill_lib",
|
||||
"directSubmitSkill": "fault-details-report"
|
||||
}"#,
|
||||
)
|
||||
.unwrap();
|
||||
|
||||
let err = SgClawSettings::load(Some(config_path.as_path()))
|
||||
.expect_err("expected invalid directSubmitSkill format");
|
||||
let message = err.to_string();
|
||||
|
||||
assert!(message.contains("directSubmitSkill"));
|
||||
assert!(message.contains("skill.tool"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn sgclaw_settings_load_new_runtime_fields_from_browser_config() {
|
||||
let root = std::env::temp_dir().join(format!("sgclaw-runtime-config-{}", Uuid::new_v4()));
|
||||
@@ -252,7 +304,10 @@ fn sgclaw_settings_load_provider_switching_and_backend_policy_from_browser_confi
|
||||
assert_eq!(settings.planner_mode, PlannerMode::ZeroclawPlanFirst);
|
||||
assert_eq!(settings.active_provider, "glm-prod");
|
||||
assert_eq!(settings.providers.len(), 2);
|
||||
assert_eq!(settings.provider_base_url, "https://open.bigmodel.cn/api/paas/v4");
|
||||
assert_eq!(
|
||||
settings.provider_base_url,
|
||||
"https://open.bigmodel.cn/api/paas/v4"
|
||||
);
|
||||
assert_eq!(settings.provider_model, "glm-4.5");
|
||||
assert_eq!(settings.browser_backend, BrowserBackend::SuperRpa);
|
||||
assert_eq!(settings.office_backend, OfficeBackend::OpenXml);
|
||||
|
||||
@@ -17,6 +17,7 @@ async fn compat_cron_adapter_creates_lists_and_runs_due_agent_jobs() {
|
||||
api_key: "key".to_string(),
|
||||
base_url: "https://api.deepseek.com".to_string(),
|
||||
model: "deepseek-chat".to_string(),
|
||||
skills_dir: None,
|
||||
};
|
||||
let workspace_root = workspace_root("sgclaw-cron");
|
||||
let config = build_zeroclaw_config_from_settings(Path::new(&workspace_root), &settings);
|
||||
|
||||
@@ -16,6 +16,7 @@ async fn compat_memory_adapter_uses_workspace_local_sqlite_backend() {
|
||||
api_key: "key".to_string(),
|
||||
base_url: "https://api.deepseek.com".to_string(),
|
||||
model: "deepseek-chat".to_string(),
|
||||
skills_dir: None,
|
||||
};
|
||||
let workspace_root = workspace_root("sgclaw-memory");
|
||||
let config = build_zeroclaw_config_from_settings(Path::new(&workspace_root), &settings);
|
||||
|
||||
@@ -1,10 +1,11 @@
|
||||
use std::path::PathBuf;
|
||||
use std::process::Command as ProcessCommand;
|
||||
use std::{fs::File, io::Read};
|
||||
|
||||
use serde_json::json;
|
||||
use sgclaw::compat::openxml_office_tool::OpenXmlOfficeTool;
|
||||
use uuid::Uuid;
|
||||
use zeroclaw::tools::Tool;
|
||||
use zip::ZipArchive;
|
||||
|
||||
fn temp_workspace_root() -> PathBuf {
|
||||
let root = std::env::temp_dir().join(format!("sgclaw-openxml-office-{}", Uuid::new_v4()));
|
||||
@@ -12,6 +13,15 @@ fn temp_workspace_root() -> PathBuf {
|
||||
root
|
||||
}
|
||||
|
||||
fn read_sheet_xml(output_path: &std::path::Path) -> String {
|
||||
let file = File::open(output_path).unwrap();
|
||||
let mut archive = ZipArchive::new(file).unwrap();
|
||||
let mut entry = archive.by_name("xl/worksheets/sheet1.xml").unwrap();
|
||||
let mut xml = String::new();
|
||||
entry.read_to_string(&mut xml).unwrap();
|
||||
xml
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn openxml_office_tool_renders_hotlist_xlsx_from_rows() {
|
||||
let workspace_root = temp_workspace_root();
|
||||
@@ -33,19 +43,12 @@ async fn openxml_office_tool_renders_hotlist_xlsx_from_rows() {
|
||||
|
||||
assert!(result.success, "{result:?}");
|
||||
assert!(output_path.exists());
|
||||
assert!(result.output.contains(output_path.to_str().unwrap()));
|
||||
let output_json: serde_json::Value = serde_json::from_str(&result.output).unwrap();
|
||||
assert_eq!(output_json["row_count"], 2);
|
||||
assert_eq!(output_json["renderer"], "openxml_office");
|
||||
assert!(!output_json["output_path"].as_str().unwrap().is_empty());
|
||||
|
||||
let unzip = ProcessCommand::new("unzip")
|
||||
.args([
|
||||
"-p",
|
||||
output_path.to_str().unwrap(),
|
||||
"xl/worksheets/sheet1.xml",
|
||||
])
|
||||
.output()
|
||||
.unwrap();
|
||||
assert!(unzip.status.success());
|
||||
|
||||
let xml = String::from_utf8(unzip.stdout).unwrap();
|
||||
let xml = read_sheet_xml(&output_path);
|
||||
assert!(xml.contains("问题一"));
|
||||
assert!(xml.contains("344万"));
|
||||
assert!(xml.contains("问题二"));
|
||||
@@ -74,17 +77,7 @@ async fn openxml_office_tool_accepts_reordered_columns_when_rows_are_structured(
|
||||
assert!(result.success, "{result:?}");
|
||||
assert!(output_path.exists());
|
||||
|
||||
let unzip = ProcessCommand::new("unzip")
|
||||
.args([
|
||||
"-p",
|
||||
output_path.to_str().unwrap(),
|
||||
"xl/worksheets/sheet1.xml",
|
||||
])
|
||||
.output()
|
||||
.unwrap();
|
||||
assert!(unzip.status.success());
|
||||
|
||||
let xml = String::from_utf8(unzip.stdout).unwrap();
|
||||
let xml = read_sheet_xml(&output_path);
|
||||
assert!(xml.contains("问题一"));
|
||||
assert!(xml.contains("344万"));
|
||||
assert!(xml.contains(">1<"));
|
||||
@@ -112,17 +105,7 @@ async fn openxml_office_tool_accepts_localized_hotlist_column_aliases() {
|
||||
assert!(result.success, "{result:?}");
|
||||
assert!(output_path.exists());
|
||||
|
||||
let unzip = ProcessCommand::new("unzip")
|
||||
.args([
|
||||
"-p",
|
||||
output_path.to_str().unwrap(),
|
||||
"xl/worksheets/sheet1.xml",
|
||||
])
|
||||
.output()
|
||||
.unwrap();
|
||||
assert!(unzip.status.success());
|
||||
|
||||
let xml = String::from_utf8(unzip.stdout).unwrap();
|
||||
let xml = read_sheet_xml(&output_path);
|
||||
assert!(xml.contains("问题一"));
|
||||
assert!(xml.contains("344万"));
|
||||
assert!(xml.contains(">1<"));
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -43,6 +43,7 @@ async fn screen_html_export_tool_renders_dashboard_html_with_presentation_contra
|
||||
.as_str()
|
||||
.unwrap()
|
||||
.starts_with("file://"));
|
||||
assert!(html.contains("知乎热榜态势驾驶舱"));
|
||||
assert!(html.contains("snapshot-20260329"));
|
||||
assert!(html.contains("问题一"));
|
||||
assert!(html.contains("344万"));
|
||||
|
||||
@@ -21,6 +21,7 @@ fn deepseek_settings_load_defaults_from_env() {
|
||||
assert_eq!(settings.api_key, "test-key");
|
||||
assert_eq!(settings.base_url, "https://api.deepseek.com");
|
||||
assert_eq!(settings.model, "deepseek-chat");
|
||||
assert_eq!(settings.skills_dir, None);
|
||||
}
|
||||
|
||||
#[test]
|
||||
@@ -29,6 +30,7 @@ fn deepseek_request_shape_matches_openai_compatible_chat_format() {
|
||||
api_key: "test-key".to_string(),
|
||||
base_url: "https://api.deepseek.com".to_string(),
|
||||
model: "deepseek-chat".to_string(),
|
||||
skills_dir: None,
|
||||
});
|
||||
let messages = vec![
|
||||
ChatMessage {
|
||||
@@ -60,8 +62,5 @@ fn deepseek_request_shape_matches_openai_compatible_chat_format() {
|
||||
assert_eq!(serialized["messages"][0]["role"], "system");
|
||||
assert_eq!(serialized["messages"][1]["content"], "打开百度搜索天气");
|
||||
assert_eq!(serialized["tools"][0]["type"], "function");
|
||||
assert_eq!(
|
||||
serialized["tools"][0]["function"]["name"],
|
||||
"browser_action"
|
||||
);
|
||||
assert_eq!(serialized["tools"][0]["function"]["name"], "browser_action");
|
||||
}
|
||||
|
||||
452
tests/deterministic_submit_test.rs
Normal file
452
tests/deterministic_submit_test.rs
Normal file
@@ -0,0 +1,452 @@
|
||||
mod common;
|
||||
|
||||
use std::path::PathBuf;
|
||||
|
||||
use chrono::{Datelike, Local};
|
||||
use zeroclaw::skills::load_skills_from_directory;
|
||||
|
||||
use sgclaw::compat::deterministic_submit::{
|
||||
decide_deterministic_submit, DeterministicSubmitDecision,
|
||||
};
|
||||
use sgclaw::compat::tq_lineloss::{
|
||||
contracts::{PeriodMode, ResolvedOrg, ResolvedPeriod},
|
||||
org_resolver::resolve_org,
|
||||
period_resolver::resolve_period,
|
||||
};
|
||||
use sgclaw::runtime::is_zhihu_hotlist_task;
|
||||
|
||||
fn expected_default_month() -> String {
|
||||
let today = Local::now().date_naive();
|
||||
let (year, month) = if today.month() == 1 {
|
||||
(today.year() - 1, 12)
|
||||
} else {
|
||||
(today.year(), today.month() - 1)
|
||||
};
|
||||
format!("{year}-{month:02}")
|
||||
}
|
||||
|
||||
fn expected_default_week_range() -> (String, String, String) {
|
||||
let today = Local::now().date_naive();
|
||||
let month_start = today.with_day(1).expect("current month should have day 1");
|
||||
let start = month_start.format("%Y-%m-%d").to_string();
|
||||
let end = today.format("%Y-%m-%d").to_string();
|
||||
(format!("{start}至{end}"), start, end)
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn deterministic_submit_discovers_tq_lineloss_skill_contract() {
|
||||
let skills_root = PathBuf::from("D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/skills");
|
||||
let skills = load_skills_from_directory(&skills_root, true);
|
||||
|
||||
let skill = skills
|
||||
.iter()
|
||||
.find(|skill| skill.name == "tq-lineloss-report")
|
||||
.expect("tq-lineloss-report should be discoverable from staged skills root");
|
||||
|
||||
let tool = skill
|
||||
.tools
|
||||
.iter()
|
||||
.find(|tool| tool.name == "collect_lineloss")
|
||||
.expect("collect_lineloss tool should be discoverable");
|
||||
|
||||
assert_eq!(tool.kind, "browser_script");
|
||||
assert_eq!(tool.command, "scripts/collect_lineloss.js");
|
||||
|
||||
let required_args = [
|
||||
"expected_domain",
|
||||
"org_label",
|
||||
"org_code",
|
||||
"period_mode",
|
||||
"period_mode_code",
|
||||
"period_value",
|
||||
"period_payload",
|
||||
];
|
||||
|
||||
for arg in required_args {
|
||||
assert!(
|
||||
tool.args.contains_key(arg),
|
||||
"expected required arg {arg} in tq-lineloss-report.collect_lineloss"
|
||||
);
|
||||
}
|
||||
|
||||
assert_eq!(tool.args.len(), required_args.len());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn deterministic_submit_requires_exact_suffix() {
|
||||
assert!(matches!(
|
||||
decide_deterministic_submit("兰州公司 月累计 2026-03。。。", None, None),
|
||||
DeterministicSubmitDecision::Execute(_)
|
||||
));
|
||||
|
||||
assert!(matches!(
|
||||
decide_deterministic_submit("兰州公司 月累计 2026-03", None, None),
|
||||
DeterministicSubmitDecision::NotDeterministic
|
||||
));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn deterministic_submit_nonmatch_returns_supported_scene_message() {
|
||||
let decision = decide_deterministic_submit("帮我打开百度。。。", None, None);
|
||||
|
||||
match decision {
|
||||
DeterministicSubmitDecision::Prompt { summary } => {
|
||||
assert!(summary.contains("台区线损") || summary.contains("支持场景"));
|
||||
}
|
||||
other => panic!("expected deterministic prompt for unsupported scene, got {other:?}"),
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn deterministic_submit_rejects_page_context_mismatch() {
|
||||
let decision = decide_deterministic_submit(
|
||||
"兰州公司 月累计 2026-03。。。",
|
||||
Some("https://www.zhihu.com/hot"),
|
||||
Some("知乎热榜"),
|
||||
);
|
||||
|
||||
match decision {
|
||||
DeterministicSubmitDecision::Prompt { summary } => {
|
||||
assert!(summary.contains("台区线损") || summary.contains("页面") || summary.contains("不匹配"));
|
||||
}
|
||||
other => panic!("expected deterministic mismatch prompt, got {other:?}"),
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn zhihu_hotlist_request_without_suffix_keeps_existing_route() {
|
||||
assert!(is_zhihu_hotlist_task(
|
||||
"打开知乎热榜",
|
||||
Some("https://www.zhihu.com/hot"),
|
||||
Some("知乎热榜")
|
||||
));
|
||||
|
||||
assert!(matches!(
|
||||
decide_deterministic_submit(
|
||||
"打开知乎热榜",
|
||||
Some("https://www.zhihu.com/hot"),
|
||||
Some("知乎热榜")
|
||||
),
|
||||
DeterministicSubmitDecision::NotDeterministic
|
||||
));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn deterministic_submit_rejects_non_exact_suffix_variants() {
|
||||
for instruction in [
|
||||
"兰州公司 月累计 2026-03...",
|
||||
"兰州公司 月累计 2026-03。。。。",
|
||||
"兰州公司。。。月累计 2026-03",
|
||||
"兰州公司 月累计 2026-03。。。 ",
|
||||
] {
|
||||
assert!(matches!(
|
||||
decide_deterministic_submit(instruction, None, None),
|
||||
DeterministicSubmitDecision::NotDeterministic
|
||||
));
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn lineloss_org_resolver_matches_city_alias() {
|
||||
assert_eq!(
|
||||
resolve_org("兰州公司").unwrap(),
|
||||
ResolvedOrg {
|
||||
label: "国网兰州供电公司".to_string(),
|
||||
code: "62401".to_string(),
|
||||
}
|
||||
);
|
||||
|
||||
assert_eq!(
|
||||
resolve_org("天水公司").unwrap(),
|
||||
ResolvedOrg {
|
||||
label: "国网天水供电公司".to_string(),
|
||||
code: "62403".to_string(),
|
||||
}
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn lineloss_org_resolver_matches_county_alias() {
|
||||
assert_eq!(
|
||||
resolve_org("榆中县公司").unwrap(),
|
||||
ResolvedOrg {
|
||||
label: "国网榆中县供电公司".to_string(),
|
||||
code: "6240121".to_string(),
|
||||
}
|
||||
);
|
||||
|
||||
assert_eq!(
|
||||
resolve_org("城关供电分公司").unwrap(),
|
||||
ResolvedOrg {
|
||||
label: "城关供电分公司".to_string(),
|
||||
code: "6240108".to_string(),
|
||||
}
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn lineloss_org_resolver_prompts_on_ambiguity() {
|
||||
let summary = resolve_org("城关")
|
||||
.expect_err("ambiguous alias should prompt instead of guessing");
|
||||
|
||||
assert!(summary.contains("供电单位存在歧义") || summary.contains("更完整名称"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn deterministic_submit_lineloss_missing_company_prompts() {
|
||||
let decision = decide_deterministic_submit("月累计 2026-03。。。", None, None);
|
||||
|
||||
match decision {
|
||||
DeterministicSubmitDecision::Prompt { summary } => {
|
||||
assert!(summary.contains("缺少供电单位") || summary.contains("兰州公司"));
|
||||
}
|
||||
other => panic!("expected missing-company prompt, got {other:?}"),
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn lineloss_period_resolver_parses_month_text() {
|
||||
assert_eq!(
|
||||
resolve_period("月累计 2026-03").unwrap(),
|
||||
ResolvedPeriod {
|
||||
mode: PeriodMode::Month,
|
||||
mode_code: "1".to_string(),
|
||||
value: "2026-03".to_string(),
|
||||
payload: serde_json::json!({
|
||||
"fdate": "2026-03",
|
||||
}),
|
||||
}
|
||||
);
|
||||
|
||||
assert_eq!(
|
||||
resolve_period("月累计 2026年3月").unwrap(),
|
||||
ResolvedPeriod {
|
||||
mode: PeriodMode::Month,
|
||||
mode_code: "1".to_string(),
|
||||
value: "2026-03".to_string(),
|
||||
payload: serde_json::json!({
|
||||
"fdate": "2026-03",
|
||||
}),
|
||||
}
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn lineloss_period_resolver_parses_week_text() {
|
||||
let resolved = resolve_period("周累计 2026年第12周").unwrap();
|
||||
|
||||
assert_eq!(resolved.mode, PeriodMode::Week);
|
||||
assert_eq!(resolved.mode_code, "2");
|
||||
assert_eq!(resolved.value, "2026-W12");
|
||||
assert_eq!(resolved.payload["tjzq"], "week");
|
||||
assert_eq!(resolved.payload["level"], "00");
|
||||
assert_eq!(resolved.payload["weekSfdate"], "2026-03-16");
|
||||
assert_eq!(resolved.payload["weekEfdate"], "2026-03-22");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn lineloss_period_resolver_defaults_month_period_from_page_semantics() {
|
||||
let expected_month = expected_default_month();
|
||||
|
||||
assert_eq!(
|
||||
resolve_period("兰州公司 月累计").unwrap(),
|
||||
ResolvedPeriod {
|
||||
mode: PeriodMode::Month,
|
||||
mode_code: "1".to_string(),
|
||||
value: expected_month.clone(),
|
||||
payload: serde_json::json!({
|
||||
"fdate": expected_month,
|
||||
}),
|
||||
}
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn lineloss_period_resolver_defaults_week_period_from_page_semantics() {
|
||||
let (expected_value, expected_start, expected_end) = expected_default_week_range();
|
||||
|
||||
assert_eq!(
|
||||
resolve_period("兰州公司 周累计").unwrap(),
|
||||
ResolvedPeriod {
|
||||
mode: PeriodMode::Week,
|
||||
mode_code: "2".to_string(),
|
||||
value: expected_value,
|
||||
payload: serde_json::json!({
|
||||
"tjzq": "week",
|
||||
"level": "00",
|
||||
"weekSfdate": expected_start,
|
||||
"weekEfdate": expected_end,
|
||||
}),
|
||||
}
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn lineloss_period_resolver_prompts_for_missing_year_on_week() {
|
||||
let summary = resolve_period("周累计 第12周")
|
||||
.expect_err("bare week should prompt for year instead of guessing");
|
||||
|
||||
assert!(summary.contains("年份") || summary.contains("第12周"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn lineloss_period_resolver_rejects_contradictory_mode() {
|
||||
let summary = resolve_period("月累计 周累计 2026-03")
|
||||
.expect_err("contradictory month/week intent should not execute");
|
||||
|
||||
assert!(summary.contains("月/周") || summary.contains("冲突") || summary.contains("歧义"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn lineloss_period_resolver_prompts_for_missing_mode() {
|
||||
let summary = resolve_period("兰州公司 2026-03")
|
||||
.expect_err("missing mode should prompt instead of guessing");
|
||||
|
||||
assert!(summary.contains("月/周类型") || summary.contains("月累计") || summary.contains("周累计"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn lineloss_period_resolver_prompts_for_missing_period() {
|
||||
let summary = resolve_period("兰州公司 月累计")
|
||||
.expect_err("missing period should prompt instead of guessing");
|
||||
|
||||
assert!(summary.contains("周期") || summary.contains("时间") || summary.contains("2026-03"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn deterministic_lineloss_execution_plan_contains_canonical_args() {
|
||||
let decision = decide_deterministic_submit(
|
||||
"兰州公司 月累计 2026-03。。。",
|
||||
Some("http://20.76.57.61:8080/#/lineloss"),
|
||||
Some("台区线损报表"),
|
||||
);
|
||||
|
||||
match decision {
|
||||
DeterministicSubmitDecision::Execute(plan) => {
|
||||
let debug = format!("{plan:?}");
|
||||
assert!(debug.contains("国网兰州供电公司"), "missing canonical org label: {debug}");
|
||||
assert!(debug.contains("62401"), "missing canonical org code: {debug}");
|
||||
assert!(debug.contains("2026-03"), "missing canonical period value: {debug}");
|
||||
assert!(debug.contains("month") || debug.contains("Month"), "missing canonical month mode: {debug}");
|
||||
assert!(debug.contains("fdate"), "missing canonical month payload: {debug}");
|
||||
}
|
||||
other => panic!("expected deterministic execute plan, got {other:?}"),
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn deterministic_lineloss_missing_period_uses_default_month_execution_plan() {
|
||||
let expected_month = expected_default_month();
|
||||
let decision = decide_deterministic_submit("兰州公司 月累计。。。", None, None);
|
||||
|
||||
match decision {
|
||||
DeterministicSubmitDecision::Execute(plan) => {
|
||||
assert_eq!(plan.period_mode, "month");
|
||||
assert_eq!(plan.period_mode_code, "1");
|
||||
assert_eq!(plan.period_value, expected_month);
|
||||
assert!(plan.period_payload.contains("fdate"));
|
||||
}
|
||||
other => panic!("expected missing month period to default into execution, got {other:?}"),
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn deterministic_lineloss_missing_period_uses_default_week_execution_plan() {
|
||||
let (expected_value, expected_start, expected_end) = expected_default_week_range();
|
||||
let decision = decide_deterministic_submit("兰州公司 周累计。。。", None, None);
|
||||
|
||||
match decision {
|
||||
DeterministicSubmitDecision::Execute(plan) => {
|
||||
assert_eq!(plan.period_mode, "week");
|
||||
assert_eq!(plan.period_mode_code, "2");
|
||||
assert_eq!(plan.period_value, expected_value);
|
||||
assert!(plan.period_payload.contains(&expected_start));
|
||||
assert!(plan.period_payload.contains(&expected_end));
|
||||
}
|
||||
other => panic!("expected missing week period to default into execution, got {other:?}"),
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn deterministic_lineloss_partial_artifact_summary_contract_is_locked() {
|
||||
let artifact = serde_json::json!({
|
||||
"type": "report-artifact",
|
||||
"report_name": "tq-lineloss-report",
|
||||
"status": "partial",
|
||||
"org": {
|
||||
"label": "国网兰州供电公司",
|
||||
"code": "62401"
|
||||
},
|
||||
"period": {
|
||||
"mode": "month",
|
||||
"mode_code": "1",
|
||||
"value": "2026-03",
|
||||
"payload": {
|
||||
"fdate": "2026-03"
|
||||
}
|
||||
},
|
||||
"columns": ["ORG_NAME", "LINE_LOSS_RATE"],
|
||||
"rows": [
|
||||
{ "ORG_NAME": "国网兰州供电公司", "LINE_LOSS_RATE": "3.21" }
|
||||
],
|
||||
"counts": {
|
||||
"rows": 1
|
||||
},
|
||||
"export": {
|
||||
"attempted": true,
|
||||
"status": "failed",
|
||||
"message": "report_log_failed"
|
||||
},
|
||||
"reasons": ["report_log_failed"]
|
||||
});
|
||||
|
||||
assert_eq!(artifact["type"], "report-artifact");
|
||||
assert_eq!(artifact["report_name"], "tq-lineloss-report");
|
||||
assert_eq!(artifact["status"], "partial");
|
||||
assert_eq!(artifact["org"]["label"], "国网兰州供电公司");
|
||||
assert_eq!(artifact["period"]["value"], "2026-03");
|
||||
assert_eq!(artifact["counts"]["rows"], 1);
|
||||
assert_eq!(artifact["reasons"][0], "report_log_failed");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn deterministic_lineloss_blocked_and_error_artifact_statuses_are_failure_contracts() {
|
||||
for status in ["blocked", "error"] {
|
||||
let artifact = serde_json::json!({
|
||||
"type": "report-artifact",
|
||||
"report_name": "tq-lineloss-report",
|
||||
"status": status,
|
||||
"org": {
|
||||
"label": "国网兰州供电公司",
|
||||
"code": "62401"
|
||||
},
|
||||
"period": {
|
||||
"mode": "week",
|
||||
"mode_code": "2",
|
||||
"value": "2026-W12",
|
||||
"payload": {
|
||||
"tjzq": "week",
|
||||
"level": "00",
|
||||
"weekSfdate": "2026-03-16",
|
||||
"weekEfdate": "2026-03-22"
|
||||
}
|
||||
},
|
||||
"columns": [],
|
||||
"rows": [],
|
||||
"counts": {
|
||||
"rows": 0
|
||||
},
|
||||
"export": {
|
||||
"attempted": false,
|
||||
"status": "skipped",
|
||||
"message": null
|
||||
},
|
||||
"reasons": ["selected_range_unavailable"]
|
||||
});
|
||||
|
||||
assert_eq!(artifact["status"], status);
|
||||
assert_eq!(artifact["type"], "report-artifact");
|
||||
assert_eq!(artifact["period"]["mode"], "week");
|
||||
assert_eq!(artifact["reasons"][0], "selected_range_unavailable");
|
||||
}
|
||||
}
|
||||
@@ -109,7 +109,10 @@ fn plan_first_mode_builds_visible_preview_for_zhihu_excel_flow() {
|
||||
.steps
|
||||
.iter()
|
||||
.any(|step| step.contains("navigate https://www.zhihu.com/hot")));
|
||||
assert!(preview.steps.iter().any(|step| step.contains("getText main")));
|
||||
assert!(preview
|
||||
.steps
|
||||
.iter()
|
||||
.any(|step| step.contains("getText main")));
|
||||
assert!(preview
|
||||
.steps
|
||||
.iter()
|
||||
|
||||
@@ -30,13 +30,22 @@ async fn read_skill_inlines_referenced_markdown_files() {
|
||||
.unwrap();
|
||||
|
||||
let tool = ReadSkillTool::new(workspace_dir, false, None);
|
||||
let result = tool.execute(json!({ "name": "zhihu-hotlist" })).await.unwrap();
|
||||
let result = tool
|
||||
.execute(json!({ "name": "zhihu-hotlist" }))
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
assert!(result.success);
|
||||
assert!(result.output.contains("# Zhihu Hotlist"));
|
||||
assert!(result.output.contains("## Referenced File: references/collection-flow.md"));
|
||||
assert!(result.output.contains("Collect rows from the hotlist first."));
|
||||
assert!(result.output.contains("## Referenced File: references/data-quality.md"));
|
||||
assert!(result
|
||||
.output
|
||||
.contains("## Referenced File: references/collection-flow.md"));
|
||||
assert!(result
|
||||
.output
|
||||
.contains("Collect rows from the hotlist first."));
|
||||
assert!(result
|
||||
.output
|
||||
.contains("## Referenced File: references/data-quality.md"));
|
||||
assert!(result.output.contains("Mark partial metrics explicitly."));
|
||||
}
|
||||
|
||||
@@ -65,12 +74,21 @@ async fn read_skill_recursively_inlines_relative_asset_references() {
|
||||
.unwrap();
|
||||
|
||||
let tool = ReadSkillTool::new(workspace_dir, false, None);
|
||||
let result = tool.execute(json!({ "name": "zhihu-hotlist" })).await.unwrap();
|
||||
let result = tool
|
||||
.execute(json!({ "name": "zhihu-hotlist" }))
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
assert!(result.success);
|
||||
assert!(result.output.contains("## Referenced File: references/collection-flow.md"));
|
||||
assert!(result.output.contains("## Referenced File: assets/zhihu_hotlist_flow.source.json"));
|
||||
assert!(result.output.contains("\"selectors\": [\".HotList-list\", \".HotItem\"]"));
|
||||
assert!(result
|
||||
.output
|
||||
.contains("## Referenced File: references/collection-flow.md"));
|
||||
assert!(result
|
||||
.output
|
||||
.contains("## Referenced File: assets/zhihu_hotlist_flow.source.json"));
|
||||
assert!(result
|
||||
.output
|
||||
.contains("\"selectors\": [\".HotList-list\", \".HotItem\"]"));
|
||||
}
|
||||
|
||||
fn temp_workspace_dir() -> PathBuf {
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
use sgclaw::runtime::{RuntimeEngine, RuntimeProfile, ToolPolicy};
|
||||
use sgclaw::config::{BrowserBackend, OfficeBackend, PlannerMode, SgClawSettings};
|
||||
use sgclaw::runtime::{RuntimeEngine, RuntimeProfile, ToolPolicy};
|
||||
|
||||
#[test]
|
||||
fn browser_attached_profile_exposes_browser_surface_without_becoming_browser_only() {
|
||||
@@ -39,6 +39,23 @@ fn browser_attached_export_prompt_requires_openxml_completion() {
|
||||
assert!(instruction.contains("final answer must include the generated local .xlsx path"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn browser_attached_publish_prompt_requires_explicit_confirmation_before_clicking_publish() {
|
||||
let engine = RuntimeEngine::new(RuntimeProfile::BrowserAttached);
|
||||
|
||||
let instruction = engine.build_instruction(
|
||||
"请直接发表这篇知乎文章，标题是测试标题，正文是第一段内容",
|
||||
Some("https://www.zhihu.com/creator"),
|
||||
Some("知乎创作中心"),
|
||||
true,
|
||||
);
|
||||
|
||||
assert!(instruction.contains("publish a Zhihu article"));
|
||||
assert!(instruction.contains("must not click publish without explicit human confirmation"));
|
||||
assert!(instruction.contains("ask for confirmation concisely"));
|
||||
assert!(instruction.contains("stop after the confirmation request"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn legacy_settings_default_to_plan_first_superrpa_and_openxml_backends() {
|
||||
let settings = SgClawSettings::from_legacy_deepseek_fields(
|
||||
|
||||
@@ -51,7 +51,9 @@ fn submit_task_without_llm_configuration_returns_clear_error() {
|
||||
assert!(matches!(
|
||||
&sent[0],
|
||||
AgentMessage::LogEntry { level, message }
|
||||
if level == "info" && message == "sgclaw runtime version=0.1.0 protocol=1.0"
|
||||
if level == "info"
|
||||
&& message.starts_with("sgclaw runtime version=")
|
||||
&& message.ends_with(" protocol=1.0")
|
||||
));
|
||||
assert!(matches!(
|
||||
&sent[1],
|
||||
|
||||
@@ -55,7 +55,7 @@ class SkillLibValidationTest(unittest.TestCase):
|
||||
self.assertIn("xlsx", record.tags)
|
||||
expected_location = (
|
||||
SKILLS_DIR / name / "SKILL.toml"
|
||||
if name == "zhihu-hotlist"
|
||||
if name in {"zhihu-hotlist", "zhihu-navigate", "zhihu-write"}
|
||||
else SKILLS_DIR / name / "SKILL.md"
|
||||
)
|
||||
self.assertEqual(record.location, expected_location)
|
||||
@@ -83,6 +83,17 @@ class SkillLibValidationTest(unittest.TestCase):
|
||||
self.assertTrue(
|
||||
(SKILLS_DIR / "zhihu-hotlist" / "scripts" / "extract_hotlist.js").is_file()
|
||||
)
|
||||
self.assertTrue((SKILLS_DIR / "zhihu-navigate" / "SKILL.toml").is_file())
|
||||
self.assertTrue(
|
||||
(SKILLS_DIR / "zhihu-navigate" / "scripts" / "open_creator_entry.js").is_file()
|
||||
)
|
||||
self.assertTrue((SKILLS_DIR / "zhihu-write" / "SKILL.toml").is_file())
|
||||
self.assertTrue(
|
||||
(SKILLS_DIR / "zhihu-write" / "scripts" / "prepare_article_editor.js").is_file()
|
||||
)
|
||||
self.assertTrue(
|
||||
(SKILLS_DIR / "zhihu-write" / "scripts" / "fill_article_draft.js").is_file()
|
||||
)
|
||||
|
||||
def test_each_skill_declares_superrpa_browser_contract(self):
|
||||
for name in [name for name in EXPECTED_SKILL_NAMES if name.startswith("zhihu-")]:
|
||||
|
||||
243
tests/skill_script_zhihu_navigate_test.py
Normal file
243
tests/skill_script_zhihu_navigate_test.py
Normal file
@@ -0,0 +1,243 @@
|
||||
import json
|
||||
import subprocess
|
||||
import textwrap
|
||||
import unittest
|
||||
from pathlib import Path
|
||||
|
||||
|
||||
REPO_ROOT = Path(__file__).resolve().parents[1]
|
||||
SCRIPT_PATH = (
|
||||
REPO_ROOT.parent / "skill_lib" / "skills" / "zhihu-navigate" / "scripts" /
|
||||
"open_creator_entry.js"
|
||||
)
|
||||
|
||||
|
||||
def run_open_creator_entry(*, body_text: str, selectors: dict[str, list[dict]]) -> dict:
|
||||
node_script = textwrap.dedent(
|
||||
f"""
|
||||
import fs from 'node:fs';
|
||||
import vm from 'node:vm';
|
||||
|
||||
const scriptPath = {json.dumps(str(SCRIPT_PATH))};
|
||||
const selectorMap = {json.dumps(selectors, ensure_ascii=False)};
|
||||
const bodyText = {json.dumps(body_text, ensure_ascii=False)};
|
||||
const source = fs.readFileSync(scriptPath, 'utf8');
|
||||
|
||||
function createNode(spec) {{
|
||||
const node = {{
|
||||
id: String(spec?.id ?? ''),
|
||||
tagName: String(spec?.tagName || 'DIV').toUpperCase(),
|
||||
textContent: String(spec?.textContent ?? ''),
|
||||
innerText: String(spec?.innerText ?? spec?.textContent ?? ''),
|
||||
href: String(spec?.href ?? ''),
|
||||
className: String(spec?.className ?? ''),
|
||||
role: String(spec?.role ?? ''),
|
||||
tabIndex: Number.isFinite(spec?.tabIndex) ? Number(spec.tabIndex) : -1,
|
||||
clicked: false,
|
||||
click() {{
|
||||
this.clicked = true;
|
||||
}},
|
||||
getAttribute(name) {{
|
||||
if (name === 'class') {{
|
||||
return this.className;
|
||||
}}
|
||||
if (name === 'role') {{
|
||||
return this.role;
|
||||
}}
|
||||
if (name === 'href') {{
|
||||
return this.href;
|
||||
}}
|
||||
if (name === 'tabindex' && this.tabIndex >= 0) {{
|
||||
return String(this.tabIndex);
|
||||
}}
|
||||
return '';
|
||||
}},
|
||||
getBoundingClientRect() {{
|
||||
return {{
|
||||
width: spec?.visible === false ? 0 : 120,
|
||||
height: spec?.visible === false ? 0 : 32,
|
||||
}};
|
||||
}},
|
||||
parentElement: null,
|
||||
closest(selector) {{
|
||||
let current = this;
|
||||
while (current) {{
|
||||
if (matchesSelector(current, selector)) {{
|
||||
return current;
|
||||
}}
|
||||
current = current.parentElement;
|
||||
}}
|
||||
return null;
|
||||
}},
|
||||
}};
|
||||
return node;
|
||||
}}
|
||||
|
||||
const created = new Map();
|
||||
const nodesById = new Map();
|
||||
function matchesSelector(node, selector) {{
|
||||
const parts = selector.split(',').map((part) => part.trim()).filter(Boolean);
|
||||
return parts.some((part) => {{
|
||||
if (part === 'a[href]') {{
|
||||
return node.tagName === 'A' && Boolean(node.href);
|
||||
}}
|
||||
if (part === 'button') {{
|
||||
return node.tagName === 'BUTTON';
|
||||
}}
|
||||
if (part === '[role=\"button\"]' || part === "[role='button']") {{
|
||||
return node.role === 'button';
|
||||
}}
|
||||
if (part === '[tabindex]') {{
|
||||
return node.tabIndex >= 0;
|
||||
}}
|
||||
if (part === 'div') {{
|
||||
return node.tagName === 'DIV';
|
||||
}}
|
||||
if (part === 'span') {{
|
||||
return node.tagName === 'SPAN';
|
||||
}}
|
||||
return false;
|
||||
}});
|
||||
}}
|
||||
function createNodeList(selector) {{
|
||||
const specs = selectorMap[selector] || [];
|
||||
return specs.map((spec, index) => {{
|
||||
const key = `${{selector}}#${{index}}`;
|
||||
if (!created.has(key)) {{
|
||||
const node = createNode(spec);
|
||||
created.set(key, node);
|
||||
if (node.id) {{
|
||||
nodesById.set(node.id, node);
|
||||
}}
|
||||
}}
|
||||
return created.get(key);
|
||||
}});
|
||||
}}
|
||||
|
||||
for (const selector of Object.keys(selectorMap)) {{
|
||||
createNodeList(selector);
|
||||
}}
|
||||
for (const node of created.values()) {{
|
||||
const parentId = selectorMap && Object.values(selectorMap)
|
||||
.flat()
|
||||
.find((spec) => String(spec?.id ?? '') === node.id)?.parentId;
|
||||
if (parentId && nodesById.has(parentId)) {{
|
||||
node.parentElement = nodesById.get(parentId);
|
||||
}}
|
||||
}}
|
||||
|
||||
const bodyNode = createNode({{ tagName: 'BODY', textContent: bodyText, innerText: bodyText }});
|
||||
const context = {{
|
||||
args: {{ desired_target: 'article_editor' }},
|
||||
location: {{ href: 'https://www.zhihu.com/creator' }},
|
||||
document: {{
|
||||
body: bodyNode,
|
||||
querySelector(selector) {{
|
||||
if (selector === 'body') {{
|
||||
return bodyNode;
|
||||
}}
|
||||
return createNodeList(selector)[0] || null;
|
||||
}},
|
||||
querySelectorAll(selector) {{
|
||||
return createNodeList(selector);
|
||||
}},
|
||||
}},
|
||||
console,
|
||||
JSON,
|
||||
Math,
|
||||
Number,
|
||||
Object,
|
||||
RegExp,
|
||||
Set,
|
||||
String,
|
||||
Array,
|
||||
Error,
|
||||
}};
|
||||
|
||||
try {{
|
||||
const result = vm.runInNewContext(`(function(){{\\n${{source}}\\n}})()`, context);
|
||||
process.stdout.write(JSON.stringify({{ ok: true, result, created: Object.fromEntries(created) }}));
|
||||
}} catch (error) {{
|
||||
process.stdout.write(JSON.stringify({{
|
||||
ok: false,
|
||||
error: String(error && error.message ? error.message : error),
|
||||
}}));
|
||||
process.exitCode = 1;
|
||||
}}
|
||||
"""
|
||||
)
|
||||
completed = subprocess.run(
|
||||
["node", "--input-type=module", "-e", node_script],
|
||||
check=False,
|
||||
capture_output=True,
|
||||
text=True,
|
||||
)
|
||||
payload = json.loads(completed.stdout)
|
||||
if completed.returncode != 0:
|
||||
raise AssertionError(payload["error"])
|
||||
return payload
|
||||
|
||||
|
||||
class SkillScriptZhihuNavigateTest(unittest.TestCase):
|
||||
def test_open_creator_entry_clicks_anchor_write_entry(self):
|
||||
payload = run_open_creator_entry(
|
||||
body_text="创作者中心 写文章",
|
||||
selectors={
|
||||
"a[href], button, [role='button']": [
|
||||
{
|
||||
"tagName": "a",
|
||||
"textContent": "写文章",
|
||||
"href": "https://zhuanlan.zhihu.com/write",
|
||||
}
|
||||
]
|
||||
},
|
||||
)
|
||||
|
||||
self.assertEqual(payload["result"]["status"], "creator_entry_clicked")
|
||||
self.assertTrue(payload["created"]["a[href], button, [role='button']#0"]["clicked"])
|
||||
|
||||
def test_open_creator_entry_clicks_button_write_entry(self):
|
||||
payload = run_open_creator_entry(
|
||||
body_text="创作者中心 发布内容",
|
||||
selectors={
|
||||
"a[href], button, [role='button']": [
|
||||
{
|
||||
"tagName": "button",
|
||||
"textContent": "写文章",
|
||||
}
|
||||
]
|
||||
},
|
||||
)
|
||||
|
||||
self.assertEqual(payload["result"]["status"], "creator_entry_clicked")
|
||||
self.assertTrue(payload["created"]["a[href], button, [role='button']#0"]["clicked"])
|
||||
|
||||
def test_open_creator_entry_clicks_clickable_ancestor_for_nested_write_text(self):
|
||||
payload = run_open_creator_entry(
|
||||
body_text="创作者中心 写文章",
|
||||
selectors={
|
||||
"a[href], button, [role='button']": [],
|
||||
"div, span, [tabindex]": [
|
||||
{
|
||||
"id": "ancestor",
|
||||
"tagName": "div",
|
||||
"className": "creator-entry",
|
||||
"tabIndex": 0,
|
||||
"textContent": "",
|
||||
},
|
||||
{
|
||||
"id": "label",
|
||||
"parentId": "ancestor",
|
||||
"tagName": "span",
|
||||
"textContent": "写文章",
|
||||
},
|
||||
],
|
||||
},
|
||||
)
|
||||
|
||||
self.assertEqual(payload["result"]["status"], "creator_entry_clicked")
|
||||
self.assertTrue(payload["created"]["div, span, [tabindex]#0"]["clicked"])
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
219
tests/skill_script_zhihu_write_test.py
Normal file
219
tests/skill_script_zhihu_write_test.py
Normal file
@@ -0,0 +1,219 @@
|
||||
import json
|
||||
import subprocess
|
||||
import textwrap
|
||||
import unittest
|
||||
from pathlib import Path
|
||||
|
||||
|
||||
REPO_ROOT = Path(__file__).resolve().parents[1]
|
||||
PREPARE_SCRIPT_PATH = (
|
||||
REPO_ROOT.parent / "skill_lib" / "skills" / "zhihu-write" / "scripts" /
|
||||
"prepare_article_editor.js"
|
||||
)
|
||||
FILL_SCRIPT_PATH = (
|
||||
REPO_ROOT.parent / "skill_lib" / "skills" / "zhihu-write" / "scripts" /
|
||||
"fill_article_draft.js"
|
||||
)
|
||||
|
||||
|
||||
def run_browser_script(script_path: Path, *, args: dict, body_text: str, selectors: dict[str, list[dict]]) -> dict:
|
||||
node_script = textwrap.dedent(
|
||||
f"""
|
||||
import fs from 'node:fs';
|
||||
import vm from 'node:vm';
|
||||
|
||||
const scriptPath = {json.dumps(str(script_path))};
|
||||
const args = {json.dumps(args, ensure_ascii=False)};
|
||||
const selectorMap = {json.dumps(selectors, ensure_ascii=False)};
|
||||
const bodyText = {json.dumps(body_text, ensure_ascii=False)};
|
||||
const source = fs.readFileSync(scriptPath, 'utf8');
|
||||
|
||||
function createNode(spec) {{
|
||||
const attrs = spec?.attrs || {{}};
|
||||
const node = {{
|
||||
tagName: String(spec?.tagName || 'DIV').toUpperCase(),
|
||||
textContent: String(spec?.textContent ?? ''),
|
||||
innerText: String(spec?.innerText ?? spec?.textContent ?? ''),
|
||||
innerHTML: String(spec?.innerHTML ?? spec?.textContent ?? ''),
|
||||
value: String(spec?.value ?? ''),
|
||||
children: [],
|
||||
focused: false,
|
||||
clicked: false,
|
||||
appendChild(child) {{
|
||||
this.children.push(child);
|
||||
return child;
|
||||
}},
|
||||
focus() {{
|
||||
this.focused = true;
|
||||
}},
|
||||
click() {{
|
||||
this.clicked = true;
|
||||
}},
|
||||
dispatchEvent() {{
|
||||
return true;
|
||||
}},
|
||||
getAttribute(name) {{
|
||||
return Object.prototype.hasOwnProperty.call(attrs, name) ? attrs[name] : null;
|
||||
}},
|
||||
querySelector() {{
|
||||
return null;
|
||||
}},
|
||||
querySelectorAll() {{
|
||||
return [];
|
||||
}},
|
||||
getBoundingClientRect() {{
|
||||
return {{
|
||||
width: spec?.visible === false ? 0 : 100,
|
||||
height: spec?.visible === false ? 0 : 20,
|
||||
}};
|
||||
}},
|
||||
}};
|
||||
return node;
|
||||
}}
|
||||
|
||||
const created = new Map();
|
||||
|
||||
function createNodeList(selector) {{
|
||||
const specs = selectorMap[selector] || [];
|
||||
return specs.map((spec, index) => {{
|
||||
const key = `${{selector}}#${{index}}`;
|
||||
if (!created.has(key)) {{
|
||||
created.set(key, createNode(spec));
|
||||
}}
|
||||
return created.get(key);
|
||||
}});
|
||||
}}
|
||||
|
||||
const bodyNode = createNode({{ tagName: 'body', textContent: bodyText, innerText: bodyText }});
|
||||
const context = {{
|
||||
args,
|
||||
location: {{ href: 'https://zhuanlan.zhihu.com/write' }},
|
||||
document: {{
|
||||
body: bodyNode,
|
||||
createElement(tagName) {{
|
||||
return createNode({{ tagName }});
|
||||
}},
|
||||
createTextNode(text) {{
|
||||
return createNode({{ tagName: '#text', textContent: text, innerText: text }});
|
||||
}},
|
||||
querySelector(selector) {{
|
||||
if (selector === 'body') {{
|
||||
return bodyNode;
|
||||
}}
|
||||
return createNodeList(selector)[0] || null;
|
||||
}},
|
||||
querySelectorAll(selector) {{
|
||||
return createNodeList(selector);
|
||||
}},
|
||||
}},
|
||||
Event: class Event {{
|
||||
constructor(type, init = {{}}) {{
|
||||
this.type = type;
|
||||
this.bubbles = !!init.bubbles;
|
||||
this.composed = !!init.composed;
|
||||
}}
|
||||
}},
|
||||
console,
|
||||
JSON,
|
||||
Math,
|
||||
Number,
|
||||
Object,
|
||||
RegExp,
|
||||
Set,
|
||||
String,
|
||||
Array,
|
||||
Error,
|
||||
}};
|
||||
|
||||
try {{
|
||||
const result = vm.runInNewContext(`(function(){{\\n${{source}}\\n}})()`, context);
|
||||
process.stdout.write(JSON.stringify({{ ok: true, result, created: Object.fromEntries(created) }}));
|
||||
}} catch (error) {{
|
||||
process.stdout.write(JSON.stringify({{
|
||||
ok: false,
|
||||
error: String(error && error.message ? error.message : error),
|
||||
}}));
|
||||
process.exitCode = 1;
|
||||
}}
|
||||
"""
|
||||
)
|
||||
completed = subprocess.run(
|
||||
["node", "--input-type=module", "-e", node_script],
|
||||
check=False,
|
||||
capture_output=True,
|
||||
text=True,
|
||||
)
|
||||
payload = json.loads(completed.stdout)
|
||||
if completed.returncode != 0:
|
||||
raise AssertionError(payload["error"])
|
||||
return payload
|
||||
|
||||
|
||||
class SkillScriptZhihuWriteTest(unittest.TestCase):
|
||||
def test_prepare_article_editor_accepts_role_textbox_title_and_generic_body_editor(self):
|
||||
payload = run_browser_script(
|
||||
PREPARE_SCRIPT_PATH,
|
||||
args={"desired_mode": "draft"},
|
||||
body_text="写文章 发布",
|
||||
selectors={
|
||||
"[role='textbox'][aria-label*='标题']": [
|
||||
{
|
||||
"tagName": "div",
|
||||
"attrs": {
|
||||
"role": "textbox",
|
||||
"aria-label": "标题",
|
||||
"contenteditable": "true",
|
||||
},
|
||||
}
|
||||
],
|
||||
"div[contenteditable='true']": [
|
||||
{
|
||||
"tagName": "div",
|
||||
"attrs": {
|
||||
"contenteditable": "true",
|
||||
"data-placeholder": "在这里输入正文",
|
||||
},
|
||||
}
|
||||
],
|
||||
},
|
||||
)
|
||||
|
||||
self.assertEqual(payload["result"]["status"], "editor_ready")
|
||||
|
||||
def test_fill_article_draft_accepts_role_textbox_title_and_generic_body_editor(self):
|
||||
payload = run_browser_script(
|
||||
FILL_SCRIPT_PATH,
|
||||
args={
|
||||
"title": "测试标题",
|
||||
"body": "第一段\n第二段",
|
||||
"publish_mode": "false",
|
||||
},
|
||||
body_text="写文章 发布",
|
||||
selectors={
|
||||
"[role='textbox'][aria-label*='标题']": [
|
||||
{
|
||||
"tagName": "div",
|
||||
"attrs": {
|
||||
"role": "textbox",
|
||||
"aria-label": "标题",
|
||||
"contenteditable": "true",
|
||||
},
|
||||
}
|
||||
],
|
||||
"div[contenteditable='true']": [
|
||||
{
|
||||
"tagName": "div",
|
||||
"attrs": {
|
||||
"contenteditable": "true",
|
||||
"data-placeholder": "在这里输入正文",
|
||||
},
|
||||
}
|
||||
],
|
||||
},
|
||||
)
|
||||
|
||||
self.assertEqual(payload["result"]["status"], "draft_ready")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
20
third_party/zeroclaw/src/agent/agent.rs
vendored
20
third_party/zeroclaw/src/agent/agent.rs
vendored
@@ -796,7 +796,8 @@ impl Agent {
|
||||
|
||||
let (text, calls) = self.tool_dispatcher.parse_response(&response);
|
||||
let calls = canonicalize_parsed_tool_calls(&self.tools, calls);
|
||||
response.tool_calls = canonicalize_provider_tool_calls(&self.tools, response.tool_calls);
|
||||
response.tool_calls =
|
||||
canonicalize_provider_tool_calls(&self.tools, response.tool_calls);
|
||||
if calls.is_empty() {
|
||||
let final_text = if text.is_empty() {
|
||||
response.text.unwrap_or_default()
|
||||
@@ -1065,7 +1066,8 @@ impl Agent {
|
||||
|
||||
let (text, calls) = self.tool_dispatcher.parse_response(&response);
|
||||
let calls = canonicalize_parsed_tool_calls(&self.tools, calls);
|
||||
response.tool_calls = canonicalize_provider_tool_calls(&self.tools, response.tool_calls);
|
||||
response.tool_calls =
|
||||
canonicalize_provider_tool_calls(&self.tools, response.tool_calls);
|
||||
if calls.is_empty() {
|
||||
let final_text = if text.is_empty() {
|
||||
response.text.unwrap_or_default()
|
||||
@@ -1207,7 +1209,8 @@ fn sanitize_final_text(text: &str) -> String {
|
||||
}
|
||||
|
||||
fn resolve_registered_tool_name(tools: &[Box<dyn Tool>], raw: &str) -> Option<String> {
|
||||
tools.iter()
|
||||
tools
|
||||
.iter()
|
||||
.find(|tool| {
|
||||
tool.name() == raw || crate::tools::provider_safe_tool_name(tool.name()) == raw
|
||||
})
|
||||
@@ -1218,7 +1221,8 @@ fn canonicalize_parsed_tool_calls(
|
||||
tools: &[Box<dyn Tool>],
|
||||
calls: Vec<ParsedToolCall>,
|
||||
) -> Vec<ParsedToolCall> {
|
||||
calls.into_iter()
|
||||
calls
|
||||
.into_iter()
|
||||
.map(|mut call| {
|
||||
if let Some(canonical_name) = resolve_registered_tool_name(tools, &call.name) {
|
||||
call.name = canonical_name;
|
||||
@@ -1232,7 +1236,8 @@ fn canonicalize_provider_tool_calls(
|
||||
tools: &[Box<dyn Tool>],
|
||||
calls: Vec<crate::providers::ToolCall>,
|
||||
) -> Vec<crate::providers::ToolCall> {
|
||||
calls.into_iter()
|
||||
calls
|
||||
.into_iter()
|
||||
.map(|mut call| {
|
||||
if let Some(canonical_name) = resolve_registered_tool_name(tools, &call.name) {
|
||||
call.name = canonical_name;
|
||||
@@ -1656,7 +1661,10 @@ mod tests {
|
||||
.expect("agent builder should succeed with valid config");
|
||||
|
||||
let (event_tx, _event_rx) = tokio::sync::mpsc::channel(8);
|
||||
let response = agent.turn_streamed("读取知乎热榜前10，并导出 excel 文件", event_tx).await.unwrap();
|
||||
let response = agent
|
||||
.turn_streamed("读取知乎热榜前10，并导出 excel 文件", event_tx)
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
assert_eq!(
|
||||
response,
|
||||
|
||||
3
third_party/zeroclaw/src/lib.rs
vendored
3
third_party/zeroclaw/src/lib.rs
vendored
@@ -71,7 +71,7 @@ pub mod routines;
|
||||
pub mod runtime;
|
||||
pub(crate) mod security;
|
||||
pub(crate) mod service;
|
||||
pub(crate) mod skills;
|
||||
pub mod skills;
|
||||
pub mod sop;
|
||||
pub mod tools;
|
||||
pub(crate) mod trust;
|
||||
@@ -83,6 +83,7 @@ pub mod verifiable_intent;
|
||||
pub mod plugins;
|
||||
|
||||
pub use config::Config;
|
||||
pub use security::{AutonomyLevel, SecurityPolicy};
|
||||
|
||||
/// Gateway management subcommands
|
||||
#[derive(Subcommand, Debug, Clone, Serialize, Deserialize, PartialEq, Eq)]
|
||||
|
||||
10
third_party/zeroclaw/src/providers/compatible.rs
vendored
10
third_party/zeroclaw/src/providers/compatible.rs
vendored
@@ -1943,9 +1943,8 @@ impl Provider for OpenAiCompatibleProvider {
|
||||
reasoning_effort: self.reasoning_effort_for_model(model),
|
||||
tool_stream: self
|
||||
.tool_stream_for_tools(tools.as_ref().is_some_and(|tools| !tools.is_empty())),
|
||||
tool_choice: self.tool_choice_for_tools(
|
||||
tools.as_ref().is_some_and(|tools| !tools.is_empty()),
|
||||
),
|
||||
tool_choice: self
|
||||
.tool_choice_for_tools(tools.as_ref().is_some_and(|tools| !tools.is_empty())),
|
||||
tools,
|
||||
max_tokens: self.max_tokens,
|
||||
};
|
||||
@@ -2099,9 +2098,8 @@ impl Provider for OpenAiCompatibleProvider {
|
||||
tool_stream: if options.enabled { Some(true) } else { None },
|
||||
stream: Some(options.enabled),
|
||||
tools: tools.clone(),
|
||||
tool_choice: self.tool_choice_for_tools(
|
||||
tools.as_ref().is_some_and(|tools| !tools.is_empty()),
|
||||
),
|
||||
tool_choice: self
|
||||
.tool_choice_for_tools(tools.as_ref().is_some_and(|tools| !tools.is_empty())),
|
||||
max_tokens: self.max_tokens,
|
||||
})
|
||||
} else {
|
||||
|
||||
14
third_party/zeroclaw/src/skills/mod.rs
vendored
14
third_party/zeroclaw/src/skills/mod.rs
vendored
@@ -816,12 +816,22 @@ pub fn skills_to_prompt_with_mode(
|
||||
let registered: Vec<_> = skill
|
||||
.tools
|
||||
.iter()
|
||||
.filter(|t| matches!(t.kind.as_str(), "shell" | "script" | "http" | "browser_script"))
|
||||
.filter(|t| {
|
||||
matches!(
|
||||
t.kind.as_str(),
|
||||
"shell" | "script" | "http" | "browser_script"
|
||||
)
|
||||
})
|
||||
.collect();
|
||||
let unregistered: Vec<_> = skill
|
||||
.tools
|
||||
.iter()
|
||||
.filter(|t| !matches!(t.kind.as_str(), "shell" | "script" | "http" | "browser_script"))
|
||||
.filter(|t| {
|
||||
!matches!(
|
||||
t.kind.as_str(),
|
||||
"shell" | "script" | "http" | "browser_script"
|
||||
)
|
||||
})
|
||||
.collect();
|
||||
|
||||
if !registered.is_empty() {
|
||||
|
||||
34
third_party/zeroclaw/src/tools/read_skill.rs
vendored
34
third_party/zeroclaw/src/tools/read_skill.rs
vendored
@@ -154,7 +154,9 @@ pub async fn read_skill_bundle(location: &Path) -> std::io::Result<String> {
|
||||
let Some(skill_root) = location.parent() else {
|
||||
return Ok(primary);
|
||||
};
|
||||
let skill_root = skill_root.canonicalize().unwrap_or_else(|_| skill_root.to_path_buf());
|
||||
let skill_root = skill_root
|
||||
.canonicalize()
|
||||
.unwrap_or_else(|_| skill_root.to_path_buf());
|
||||
let mut output = primary.clone();
|
||||
let mut appended = BTreeSet::new();
|
||||
let mut queued = BTreeSet::new();
|
||||
@@ -275,16 +277,22 @@ fn extract_reference_paths(content: &str) -> Vec<String> {
|
||||
}
|
||||
|
||||
fn looks_like_relative_reference_path(raw: &str) -> bool {
|
||||
if raw.is_empty() ||
|
||||
raw.starts_with('/') ||
|
||||
raw.starts_with("http://") ||
|
||||
raw.starts_with("https://") ||
|
||||
raw.starts_with('#')
|
||||
if raw.is_empty()
|
||||
|| raw.starts_with('/')
|
||||
|| raw.starts_with("http://")
|
||||
|| raw.starts_with("https://")
|
||||
|| raw.starts_with('#')
|
||||
{
|
||||
return false;
|
||||
}
|
||||
|
||||
let candidate = raw.split('#').next().unwrap_or(raw).split('?').next().unwrap_or(raw);
|
||||
let candidate = raw
|
||||
.split('#')
|
||||
.next()
|
||||
.unwrap_or(raw)
|
||||
.split('?')
|
||||
.next()
|
||||
.unwrap_or(raw);
|
||||
let path = Path::new(candidate);
|
||||
if path
|
||||
.components()
|
||||
@@ -418,9 +426,15 @@ description = "Ship safely"
|
||||
|
||||
assert!(result.success);
|
||||
assert!(result.output.contains("# Zhihu Hotlist"));
|
||||
assert!(result.output.contains("## Referenced File: references/collection-flow.md"));
|
||||
assert!(result.output.contains("Collect rows from the hotlist first."));
|
||||
assert!(result.output.contains("## Referenced File: references/data-quality.md"));
|
||||
assert!(result
|
||||
.output
|
||||
.contains("## Referenced File: references/collection-flow.md"));
|
||||
assert!(result
|
||||
.output
|
||||
.contains("Collect rows from the hotlist first."));
|
||||
assert!(result
|
||||
.output
|
||||
.contains("## Referenced File: references/data-quality.md"));
|
||||
assert!(result.output.contains("Mark partial metrics explicitly."));
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user