forked from EduCraft/curriculum-project-hub
feat(hub): switch capability provider from MinerU to Aliyun Doc Mind (ADR-0027)
Replace the MinerU client with Alibaba Cloud Document Mind (docmind) as the backing service for pdf_to_md_bundle. Aliyun docmind covers both PDF→MD (with LaTeX formula enhancement) and audio/video→text in one provider, unlike MinerU which only does documents. Changes: - Install @alicloud/docmind-api20220711 + @alicloud/credentials + tea-util - Delete mineruClient.ts; add docmindClient.ts with AliyunDocmindClient using the official SDK (SubmitDocParserJobAdvance → poll → GetDocParserResult) - CapabilitySecretPayload: baseUrl+apiToken → accessKeyId+accessKeySecret+endpoint - pdfToMdBundle adapter: provider aliyun_docmind, DocmindClientError - Tests updated: 7/7 green, mock client matches new interface Pricing (aliyun docmind, 2025-07): - PDF 增强链路 (含公式 LaTeX): 0.04元/页 ≈ $0.0056/页 - 视频: 0.002元/秒 - 音频: 0.00035元/秒 Cost is derived from page count × unit price (COST_PER_PAGE_USD) until the service reports an actual cost field; costSource=provider_reported. The aliyun CLI is NOT used at runtime — Hub calls the SDK directly. The CLI remains available for operators to manage AccessKeys and test connectivity.
This commit is contained in:
Generated
+349
-1
@@ -8,6 +8,9 @@
|
||||
"name": "@paradigm/hub",
|
||||
"version": "0.0.31",
|
||||
"dependencies": {
|
||||
"@alicloud/credentials": "^2.4.5",
|
||||
"@alicloud/docmind-api20220711": "^1.4.15",
|
||||
"@alicloud/tea-util": "^1.4.11",
|
||||
"@anthropic-ai/claude-agent-sdk": "^0.3.202",
|
||||
"@fastify/cookie": "^11.0.2",
|
||||
"@larksuiteoapi/node-sdk": "^1.70.0",
|
||||
@@ -74,6 +77,175 @@
|
||||
"zod": "^3.25.76 || ^4.1.8"
|
||||
}
|
||||
},
|
||||
"node_modules/@alicloud/credentials": {
|
||||
"version": "2.4.5",
|
||||
"resolved": "https://registry.npmjs.org/@alicloud/credentials/-/credentials-2.4.5.tgz",
|
||||
"integrity": "sha512-od1ufCxOO7cP2R4EVFliOB0kGo9lUXCibyj/mzmI6yLhxeqhqsegTzVsx5p2NJJsceKJnYcmye7FWKyLJAFBkw==",
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"@alicloud/tea-typescript": "^1.8.0",
|
||||
"httpx": "^2.3.3",
|
||||
"ini": "^1.3.5",
|
||||
"kitx": "^2.0.0"
|
||||
}
|
||||
},
|
||||
"node_modules/@alicloud/darabonba-array": {
|
||||
"version": "0.1.2",
|
||||
"resolved": "https://registry.npmjs.org/@alicloud/darabonba-array/-/darabonba-array-0.1.2.tgz",
|
||||
"integrity": "sha512-ZPuQ+bJyjrd8XVVm55kl+ypk7OQoi1ZH/DiToaAEQaGvgEjrTcvQkg71//vUX/6cvbLIF5piQDvhrLb+lUEIPQ==",
|
||||
"license": "ISC",
|
||||
"dependencies": {
|
||||
"@alicloud/tea-typescript": "^1.7.1"
|
||||
}
|
||||
},
|
||||
"node_modules/@alicloud/darabonba-encode-util": {
|
||||
"version": "0.0.2",
|
||||
"resolved": "https://registry.npmjs.org/@alicloud/darabonba-encode-util/-/darabonba-encode-util-0.0.2.tgz",
|
||||
"integrity": "sha512-mlsNctkeqmR0RtgE1Rngyeadi5snLOAHBCWEtYf68d7tyKskosXDTNeZ6VCD/UfrUu4N51ItO8zlpfXiOgeg3A==",
|
||||
"license": "ISC",
|
||||
"dependencies": {
|
||||
"moment": "^2.29.1"
|
||||
}
|
||||
},
|
||||
"node_modules/@alicloud/darabonba-map": {
|
||||
"version": "0.0.1",
|
||||
"resolved": "https://registry.npmjs.org/@alicloud/darabonba-map/-/darabonba-map-0.0.1.tgz",
|
||||
"integrity": "sha512-2ep+G3YDvuI+dRYVlmER1LVUQDhf9kEItmVB/bbEu1pgKzelcocCwAc79XZQjTcQGFgjDycf3vH87WLDGLFMlw==",
|
||||
"license": "ISC",
|
||||
"dependencies": {
|
||||
"@alicloud/tea-typescript": "^1.7.1"
|
||||
}
|
||||
},
|
||||
"node_modules/@alicloud/darabonba-signature-util": {
|
||||
"version": "0.0.4",
|
||||
"resolved": "https://registry.npmjs.org/@alicloud/darabonba-signature-util/-/darabonba-signature-util-0.0.4.tgz",
|
||||
"integrity": "sha512-I1TtwtAnzLamgqnAaOkN0IGjwkiti//0a7/auyVThdqiC/3kyafSAn6znysWOmzub4mrzac2WiqblZKFcN5NWg==",
|
||||
"license": "ISC",
|
||||
"dependencies": {
|
||||
"@alicloud/darabonba-encode-util": "^0.0.1"
|
||||
}
|
||||
},
|
||||
"node_modules/@alicloud/darabonba-signature-util/node_modules/@alicloud/darabonba-encode-util": {
|
||||
"version": "0.0.1",
|
||||
"resolved": "https://registry.npmjs.org/@alicloud/darabonba-encode-util/-/darabonba-encode-util-0.0.1.tgz",
|
||||
"integrity": "sha512-Sl5vCRVAYMqwmvXpJLM9hYoCHOMsQlGxaWSGhGWulpKk/NaUBArtoO1B0yHruJf1C5uHhEJIaylYcM48icFHgw==",
|
||||
"license": "ISC",
|
||||
"dependencies": {
|
||||
"@alicloud/tea-typescript": "^1.7.1",
|
||||
"moment": "^2.29.1"
|
||||
}
|
||||
},
|
||||
"node_modules/@alicloud/darabonba-string": {
|
||||
"version": "1.0.3",
|
||||
"resolved": "https://registry.npmjs.org/@alicloud/darabonba-string/-/darabonba-string-1.0.3.tgz",
|
||||
"integrity": "sha512-NyWwrU8cAIesWk3uHL1Q7pTDTqLkCI/0PmJXC4/4A0MFNAZ9Ouq0iFBsRqvfyUujSSM+WhYLuTfakQXiVLkTMA==",
|
||||
"license": "Apache-2.0",
|
||||
"dependencies": {
|
||||
"@alicloud/tea-typescript": "^1.5.1"
|
||||
}
|
||||
},
|
||||
"node_modules/@alicloud/docmind-api20220711": {
|
||||
"version": "1.4.15",
|
||||
"resolved": "https://registry.npmjs.org/@alicloud/docmind-api20220711/-/docmind-api20220711-1.4.15.tgz",
|
||||
"integrity": "sha512-QmjSDPV52d2B5bd/Dk3Zeofu+cJFPKYS+MphIHqlulfYsOynLgOaDqTRMGTK/RhcmVCwG14CyZ/15GBF00GRFw==",
|
||||
"license": "Apache-2.0",
|
||||
"dependencies": {
|
||||
"@alicloud/credentials": "^2.4.2",
|
||||
"@alicloud/openapi-core": "^1.0.0",
|
||||
"@darabonba/typescript": "^1.0.0"
|
||||
}
|
||||
},
|
||||
"node_modules/@alicloud/endpoint-util": {
|
||||
"version": "0.0.1",
|
||||
"resolved": "https://registry.npmjs.org/@alicloud/endpoint-util/-/endpoint-util-0.0.1.tgz",
|
||||
"integrity": "sha512-+pH7/KEXup84cHzIL6UJAaPqETvln4yXlD9JzlrqioyCSaWxbug5FUobsiI6fuUOpw5WwoB3fWAtGbFnJ1K3Yg==",
|
||||
"license": "Apache-2.0",
|
||||
"dependencies": {
|
||||
"@alicloud/tea-typescript": "^1.5.1",
|
||||
"kitx": "^2.0.0"
|
||||
}
|
||||
},
|
||||
"node_modules/@alicloud/gateway-pop": {
|
||||
"version": "0.0.6",
|
||||
"resolved": "https://registry.npmjs.org/@alicloud/gateway-pop/-/gateway-pop-0.0.6.tgz",
|
||||
"integrity": "sha512-KF4I+JvfYuLKc3fWeWYIZ7lOVJ9jRW0sQXdXidZn1DKZ978ncfGf7i0LBfONGk4OxvNb/HD3/0yYhkgZgPbKtA==",
|
||||
"license": "ISC",
|
||||
"dependencies": {
|
||||
"@alicloud/credentials": "^2",
|
||||
"@alicloud/darabonba-array": "^0.1.0",
|
||||
"@alicloud/darabonba-encode-util": "^0.0.2",
|
||||
"@alicloud/darabonba-map": "^0.0.1",
|
||||
"@alicloud/darabonba-signature-util": "^0.0.4",
|
||||
"@alicloud/darabonba-string": "^1.0.2",
|
||||
"@alicloud/endpoint-util": "^0.0.1",
|
||||
"@alicloud/gateway-spi": "^0.0.8",
|
||||
"@alicloud/openapi-util": "^0.3.2",
|
||||
"@alicloud/tea-typescript": "^1.7.1",
|
||||
"@alicloud/tea-util": "^1.4.8"
|
||||
}
|
||||
},
|
||||
"node_modules/@alicloud/gateway-spi": {
|
||||
"version": "0.0.8",
|
||||
"resolved": "https://registry.npmjs.org/@alicloud/gateway-spi/-/gateway-spi-0.0.8.tgz",
|
||||
"integrity": "sha512-KM7fu5asjxZPmrz9sJGHJeSU+cNQNOxW+SFmgmAIrITui5hXL2LB+KNRuzWmlwPjnuA2X3/keq9h6++S9jcV5g==",
|
||||
"license": "ISC",
|
||||
"dependencies": {
|
||||
"@alicloud/credentials": "^2",
|
||||
"@alicloud/tea-typescript": "^1.7.1"
|
||||
}
|
||||
},
|
||||
"node_modules/@alicloud/openapi-core": {
|
||||
"version": "1.0.8",
|
||||
"resolved": "https://registry.npmjs.org/@alicloud/openapi-core/-/openapi-core-1.0.8.tgz",
|
||||
"integrity": "sha512-xs8LdgMDcEUqv13kZ4nl+Vd+Fc1mixTF0g1lm5QSrNWDaLUUD5vqpuMtvUZnKNnq9PITfUQ+8KunAvNQJpFo8g==",
|
||||
"hasInstallScript": true,
|
||||
"license": "ISC",
|
||||
"dependencies": {
|
||||
"@alicloud/credentials": "^2.4.2",
|
||||
"@alicloud/gateway-pop": "0.0.6",
|
||||
"@alicloud/gateway-spi": "^0.0.8",
|
||||
"@darabonba/typescript": "^1.0.5"
|
||||
}
|
||||
},
|
||||
"node_modules/@alicloud/openapi-util": {
|
||||
"version": "0.3.3",
|
||||
"resolved": "https://registry.npmjs.org/@alicloud/openapi-util/-/openapi-util-0.3.3.tgz",
|
||||
"integrity": "sha512-vf0cQ/q8R2U7ZO88X5hDiu1yV3t/WexRj+YycWxRutkH/xVXfkmpRgps8lmNEk7Ar+0xnY8+daN2T+2OyB9F4A==",
|
||||
"license": "ISC",
|
||||
"dependencies": {
|
||||
"@alicloud/tea-typescript": "^1.7.1",
|
||||
"@alicloud/tea-util": "^1.3.0",
|
||||
"kitx": "^2.1.0",
|
||||
"sm3": "^1.0.3"
|
||||
}
|
||||
},
|
||||
"node_modules/@alicloud/tea-typescript": {
|
||||
"version": "1.8.0",
|
||||
"resolved": "https://registry.npmjs.org/@alicloud/tea-typescript/-/tea-typescript-1.8.0.tgz",
|
||||
"integrity": "sha512-CWXWaquauJf0sW30mgJRVu9aaXyBth5uMBCUc+5vKTK1zlgf3hIqRUjJZbjlwHwQ5y9anwcu18r48nOZb7l2QQ==",
|
||||
"license": "ISC",
|
||||
"dependencies": {
|
||||
"@types/node": "^12.0.2",
|
||||
"httpx": "^2.2.6"
|
||||
}
|
||||
},
|
||||
"node_modules/@alicloud/tea-typescript/node_modules/@types/node": {
|
||||
"version": "12.20.55",
|
||||
"resolved": "https://registry.npmjs.org/@types/node/-/node-12.20.55.tgz",
|
||||
"integrity": "sha512-J8xLz7q2OFulZ2cyGTLE1TbbZcjpno7FaN6zdJNrgAdrJ+DZzh/uFR6YrTb4C+nXakvud8Q4+rbhoIWlYQbUFQ==",
|
||||
"license": "MIT"
|
||||
},
|
||||
"node_modules/@alicloud/tea-util": {
|
||||
"version": "1.4.11",
|
||||
"resolved": "https://registry.npmjs.org/@alicloud/tea-util/-/tea-util-1.4.11.tgz",
|
||||
"integrity": "sha512-HyPEEQ8F0WoZegiCp7sVdrdm6eBOB+GCvGl4182u69LDFktxfirGLcAx3WExUr1zFWkq2OSmBroTwKQ4w/+Yww==",
|
||||
"license": "Apache-2.0",
|
||||
"dependencies": {
|
||||
"@alicloud/tea-typescript": "^1.5.1",
|
||||
"@darabonba/typescript": "^1.0.0",
|
||||
"kitx": "^2.0.0"
|
||||
}
|
||||
},
|
||||
"node_modules/@anthropic-ai/claude-agent-sdk": {
|
||||
"version": "0.3.202",
|
||||
"resolved": "https://registry.npmjs.org/@anthropic-ai/claude-agent-sdk/-/claude-agent-sdk-0.3.202.tgz",
|
||||
@@ -234,6 +406,24 @@
|
||||
"node": ">=6.9.0"
|
||||
}
|
||||
},
|
||||
"node_modules/@darabonba/typescript": {
|
||||
"version": "1.0.5",
|
||||
"resolved": "https://registry.npmjs.org/@darabonba/typescript/-/typescript-1.0.5.tgz",
|
||||
"integrity": "sha512-pfxHFVM8I3h8K2o8skpDQLMmR5iAeQ2eNpP1HrKDEm/9ZPF8aKwDKPwwEszT1NnIo0Y3++E7x1YsVkVpGjA/xw==",
|
||||
"license": "Apache License 2.0",
|
||||
"dependencies": {
|
||||
"@alicloud/tea-typescript": "^1.5.1",
|
||||
"http-proxy-agent": "^5.0.0",
|
||||
"https-proxy-agent": "^5.0.1",
|
||||
"httpx": "^2.3.2",
|
||||
"lodash": "^4.17.21",
|
||||
"moment": "^2.30.1",
|
||||
"moment-timezone": "^0.5.45",
|
||||
"socks-proxy-agent": "^6.2.1",
|
||||
"ws": "^8.18.0",
|
||||
"xml2js": "^0.6.2"
|
||||
}
|
||||
},
|
||||
"node_modules/@emnapi/core": {
|
||||
"version": "1.11.2",
|
||||
"resolved": "https://registry.npmjs.org/@emnapi/core/-/core-1.11.2.tgz",
|
||||
@@ -1396,6 +1586,15 @@
|
||||
"integrity": "sha512-l2aFy5jALhniG5HgqrD6jXLi/rUWrKvqN/qJx6yoJsgKhblVd+iqqU4RCXavm/jPityDo5TCvKMnpjKnOriy0w==",
|
||||
"license": "MIT"
|
||||
},
|
||||
"node_modules/@tootallnate/once": {
|
||||
"version": "2.0.1",
|
||||
"resolved": "https://registry.npmjs.org/@tootallnate/once/-/once-2.0.1.tgz",
|
||||
"integrity": "sha512-HqmEUIGRJ5fSXchkVgR5F7qn48bDBzv0kWj/Kfu5e6uci4UlEeng4331LnBkWffb++Ei3FOVLxo8JJWMFBDMeQ==",
|
||||
"license": "MIT",
|
||||
"engines": {
|
||||
"node": ">= 10"
|
||||
}
|
||||
},
|
||||
"node_modules/@tybys/wasm-util": {
|
||||
"version": "0.10.3",
|
||||
"resolved": "https://registry.npmjs.org/@tybys/wasm-util/-/wasm-util-0.10.3.tgz",
|
||||
@@ -2830,6 +3029,20 @@
|
||||
"url": "https://opencollective.com/express"
|
||||
}
|
||||
},
|
||||
"node_modules/http-proxy-agent": {
|
||||
"version": "5.0.0",
|
||||
"resolved": "https://registry.npmjs.org/http-proxy-agent/-/http-proxy-agent-5.0.0.tgz",
|
||||
"integrity": "sha512-n2hY8YdoRE1i7r6M0w9DIw5GgZN0G25P8zLCRQ8rjXtTU3vsNFBI/vWK/UIeE6g5MUUz6avwAPXmL6Fy9D/90w==",
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"@tootallnate/once": "2",
|
||||
"agent-base": "6",
|
||||
"debug": "4"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">= 6"
|
||||
}
|
||||
},
|
||||
"node_modules/https-proxy-agent": {
|
||||
"version": "5.0.1",
|
||||
"resolved": "https://registry.npmjs.org/https-proxy-agent/-/https-proxy-agent-5.0.1.tgz",
|
||||
@@ -2843,6 +3056,25 @@
|
||||
"node": ">= 6"
|
||||
}
|
||||
},
|
||||
"node_modules/httpx": {
|
||||
"version": "2.3.3",
|
||||
"resolved": "https://registry.npmjs.org/httpx/-/httpx-2.3.3.tgz",
|
||||
"integrity": "sha512-k1qv94u1b6e+XKCxVbLgYlOypVP9MPGpnN5G/vxFf6tDO4V3xpz3d6FUOY/s8NtPgaq5RBVVgSB+7IHpVxMYzw==",
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"@types/node": "^20",
|
||||
"debug": "^4.1.1"
|
||||
}
|
||||
},
|
||||
"node_modules/httpx/node_modules/@types/node": {
|
||||
"version": "20.19.43",
|
||||
"resolved": "https://registry.npmjs.org/@types/node/-/node-20.19.43.tgz",
|
||||
"integrity": "sha512-6oYBAi5ikg4Pl+kGsoYtawUMBT2zZMCvPNF7pVLnHZfd1zf38DRiWn/gT01RYCdUqkv7Fhr+C9ot4/tb+2sVvA==",
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"undici-types": "~6.21.0"
|
||||
}
|
||||
},
|
||||
"node_modules/iconv-lite": {
|
||||
"version": "0.7.3",
|
||||
"resolved": "https://registry.npmjs.org/iconv-lite/-/iconv-lite-0.7.3.tgz",
|
||||
@@ -2867,12 +3099,17 @@
|
||||
"license": "ISC",
|
||||
"peer": true
|
||||
},
|
||||
"node_modules/ini": {
|
||||
"version": "1.3.8",
|
||||
"resolved": "https://registry.npmjs.org/ini/-/ini-1.3.8.tgz",
|
||||
"integrity": "sha512-JV/yugV2uzW5iMRSiZAyDtQd+nxtUnjeLt0acNdw98kKLrvuRVyB80tsREOE7yvGVgalhZ6RNXCmEHkUKBKxew==",
|
||||
"license": "ISC"
|
||||
},
|
||||
"node_modules/ip-address": {
|
||||
"version": "10.2.0",
|
||||
"resolved": "https://registry.npmjs.org/ip-address/-/ip-address-10.2.0.tgz",
|
||||
"integrity": "sha512-/+S6j4E9AHvW9SWMSEY9Xfy66O5PWvVEJ08O0y5JGyEKQpojb0K0GKpz/v5HJ/G0vi3D2sjGK78119oXZeE0qA==",
|
||||
"license": "MIT",
|
||||
"peer": true,
|
||||
"engines": {
|
||||
"node": ">= 12"
|
||||
}
|
||||
@@ -2972,6 +3209,15 @@
|
||||
"license": "BSD-2-Clause",
|
||||
"peer": true
|
||||
},
|
||||
"node_modules/kitx": {
|
||||
"version": "2.2.0",
|
||||
"resolved": "https://registry.npmjs.org/kitx/-/kitx-2.2.0.tgz",
|
||||
"integrity": "sha512-tBMwe6AALTBQJb0woQDD40734NKzb0Kzi3k7wQj9ar3AbP9oqhoVrdXPh7rk2r00/glIgd0YbToIUJsnxWMiIg==",
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"@types/node": "^22.5.4"
|
||||
}
|
||||
},
|
||||
"node_modules/light-my-request": {
|
||||
"version": "6.6.0",
|
||||
"resolved": "https://registry.npmjs.org/light-my-request/-/light-my-request-6.6.0.tgz",
|
||||
@@ -3270,6 +3516,12 @@
|
||||
"url": "https://opencollective.com/parcel"
|
||||
}
|
||||
},
|
||||
"node_modules/lodash": {
|
||||
"version": "4.18.1",
|
||||
"resolved": "https://registry.npmjs.org/lodash/-/lodash-4.18.1.tgz",
|
||||
"integrity": "sha512-dMInicTPVE8d1e5otfwmmjlxkZoUpiVLwyeTdUsi/Caj/gfzzblBcCE5sRHV/AsjuCmxWrte2TNGSYuCeCq+0Q==",
|
||||
"license": "MIT"
|
||||
},
|
||||
"node_modules/lodash.identity": {
|
||||
"version": "3.0.0",
|
||||
"resolved": "https://registry.npmjs.org/lodash.identity/-/lodash.identity-3.0.0.tgz",
|
||||
@@ -3357,6 +3609,27 @@
|
||||
"node": ">= 0.6"
|
||||
}
|
||||
},
|
||||
"node_modules/moment": {
|
||||
"version": "2.30.1",
|
||||
"resolved": "https://registry.npmjs.org/moment/-/moment-2.30.1.tgz",
|
||||
"integrity": "sha512-uEmtNhbDOrWPFS+hdjFCBfy9f2YoyzRpwcl+DqpC6taX21FzsTLQVbMV/W7PzNSX6x/bhC1zA3c2UQ5NzH6how==",
|
||||
"license": "MIT",
|
||||
"engines": {
|
||||
"node": "*"
|
||||
}
|
||||
},
|
||||
"node_modules/moment-timezone": {
|
||||
"version": "0.5.48",
|
||||
"resolved": "https://registry.npmjs.org/moment-timezone/-/moment-timezone-0.5.48.tgz",
|
||||
"integrity": "sha512-f22b8LV1gbTO2ms2j2z13MuPogNoh5UzxL3nzNAYKGraILnbGc9NEE6dyiiiLv46DGRb8A4kg8UKWLjPthxBHw==",
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"moment": "^2.29.4"
|
||||
},
|
||||
"engines": {
|
||||
"node": "*"
|
||||
}
|
||||
},
|
||||
"node_modules/ms": {
|
||||
"version": "2.1.3",
|
||||
"resolved": "https://registry.npmjs.org/ms/-/ms-2.1.3.tgz",
|
||||
@@ -3976,6 +4249,15 @@
|
||||
"license": "MIT",
|
||||
"peer": true
|
||||
},
|
||||
"node_modules/sax": {
|
||||
"version": "1.6.0",
|
||||
"resolved": "https://registry.npmjs.org/sax/-/sax-1.6.0.tgz",
|
||||
"integrity": "sha512-6R3J5M4AcbtLUdZmRv2SygeVaM7IhrLXu9BmnOGmmACak8fiUtOsYNWUS4uK7upbmHIBbLBeFeI//477BKLBzA==",
|
||||
"license": "BlueOak-1.0.0",
|
||||
"engines": {
|
||||
"node": ">=11.0.0"
|
||||
}
|
||||
},
|
||||
"node_modules/secure-json-parse": {
|
||||
"version": "4.1.0",
|
||||
"resolved": "https://registry.npmjs.org/secure-json-parse/-/secure-json-parse-4.1.0.tgz",
|
||||
@@ -4193,6 +4475,50 @@
|
||||
"dev": true,
|
||||
"license": "ISC"
|
||||
},
|
||||
"node_modules/sm3": {
|
||||
"version": "1.0.3",
|
||||
"resolved": "https://registry.npmjs.org/sm3/-/sm3-1.0.3.tgz",
|
||||
"integrity": "sha512-KyFkIfr8QBlFG3uc3NaljaXdYcsbRy1KrSfc4tsQV8jW68jAktGeOcifu530Vx/5LC+PULHT0Rv8LiI8Gw+c1g==",
|
||||
"license": "MIT"
|
||||
},
|
||||
"node_modules/smart-buffer": {
|
||||
"version": "4.2.0",
|
||||
"resolved": "https://registry.npmjs.org/smart-buffer/-/smart-buffer-4.2.0.tgz",
|
||||
"integrity": "sha512-94hK0Hh8rPqQl2xXc3HsaBoOXKV20MToPkcXvwbISWLEs+64sBq5kFgn2kJDHb1Pry9yrP0dxrCI9RRci7RXKg==",
|
||||
"license": "MIT",
|
||||
"engines": {
|
||||
"node": ">= 6.0.0",
|
||||
"npm": ">= 3.0.0"
|
||||
}
|
||||
},
|
||||
"node_modules/socks": {
|
||||
"version": "2.8.9",
|
||||
"resolved": "https://registry.npmjs.org/socks/-/socks-2.8.9.tgz",
|
||||
"integrity": "sha512-LJhUYUvItdQ0LkJTmPeaEObWXAqFyfmP85x0tch/ez9cahmhlBBLbIqDFnvBnUJGagb0JbIQrkBs1wJ+yRYpEw==",
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"ip-address": "^10.1.1",
|
||||
"smart-buffer": "^4.2.0"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">= 10.0.0",
|
||||
"npm": ">= 3.0.0"
|
||||
}
|
||||
},
|
||||
"node_modules/socks-proxy-agent": {
|
||||
"version": "6.2.1",
|
||||
"resolved": "https://registry.npmjs.org/socks-proxy-agent/-/socks-proxy-agent-6.2.1.tgz",
|
||||
"integrity": "sha512-a6KW9G+6B3nWZ1yB8G7pJwL3ggLy1uTzKAgCb7ttblwqdz9fMGJUuTy3uFzEP48FAs9FLILlmzDlE2JJhVQaXQ==",
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"agent-base": "^6.0.2",
|
||||
"debug": "^4.3.3",
|
||||
"socks": "^2.6.2"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">= 10"
|
||||
}
|
||||
},
|
||||
"node_modules/sonic-boom": {
|
||||
"version": "4.2.1",
|
||||
"resolved": "https://registry.npmjs.org/sonic-boom/-/sonic-boom-4.2.1.tgz",
|
||||
@@ -4700,6 +5026,28 @@
|
||||
}
|
||||
}
|
||||
},
|
||||
"node_modules/xml2js": {
|
||||
"version": "0.6.2",
|
||||
"resolved": "https://registry.npmjs.org/xml2js/-/xml2js-0.6.2.tgz",
|
||||
"integrity": "sha512-T4rieHaC1EXcES0Kxxj4JWgaUQHDk+qwHcYOCFHfiwKz7tOVPLq7Hjq9dM1WCMhylqMEfP7hMcOIChvotiZegA==",
|
||||
"license": "MIT",
|
||||
"dependencies": {
|
||||
"sax": ">=0.6.0",
|
||||
"xmlbuilder": "~11.0.0"
|
||||
},
|
||||
"engines": {
|
||||
"node": ">=4.0.0"
|
||||
}
|
||||
},
|
||||
"node_modules/xmlbuilder": {
|
||||
"version": "11.0.1",
|
||||
"resolved": "https://registry.npmjs.org/xmlbuilder/-/xmlbuilder-11.0.1.tgz",
|
||||
"integrity": "sha512-fDlsI/kFEx7gLvbecc0/ohLG50fugQp8ryHzMTuW9vSa1GJ0XYWKnhsUx7oie3G98+r56aTQIUB4kht42R3JvA==",
|
||||
"license": "MIT",
|
||||
"engines": {
|
||||
"node": ">=4.0"
|
||||
}
|
||||
},
|
||||
"node_modules/zod": {
|
||||
"version": "4.4.3",
|
||||
"resolved": "https://registry.npmjs.org/zod/-/zod-4.4.3.tgz",
|
||||
|
||||
@@ -7,6 +7,9 @@
|
||||
"node": ">=24"
|
||||
},
|
||||
"dependencies": {
|
||||
"@alicloud/credentials": "^2.4.5",
|
||||
"@alicloud/docmind-api20220711": "^1.4.15",
|
||||
"@alicloud/tea-util": "^1.4.11",
|
||||
"@anthropic-ai/claude-agent-sdk": "^0.3.202",
|
||||
"@fastify/cookie": "^11.0.2",
|
||||
"@larksuiteoapi/node-sdk": "^1.70.0",
|
||||
|
||||
@@ -63,8 +63,8 @@ export async function resolveCapabilityCredential(
|
||||
organizationId: connection.organizationId,
|
||||
capabilityId: connection.capabilityId,
|
||||
schemaVersion: 1,
|
||||
baseUrl: payload.baseUrl,
|
||||
apiToken: payload.apiToken,
|
||||
projectId: payload.projectId,
|
||||
accessKeyId: payload.accessKeyId,
|
||||
accessKeySecret: payload.accessKeySecret,
|
||||
endpoint: payload.endpoint,
|
||||
};
|
||||
}
|
||||
|
||||
@@ -0,0 +1,194 @@
|
||||
/**
|
||||
* ADR-0027: Alibaba Cloud Document Mind (docmind) client.
|
||||
*
|
||||
* Uses the official @alicloud/docmind-api20220711 SDK to call the document
|
||||
* parsing (large model version) API. The API is asynchronous:
|
||||
* 1. SubmitDocParserJobAdvance — upload local file, get job id
|
||||
* 2. QueryDocParserStatus — poll until completed
|
||||
* 3. GetDocParserResult — fetch markdown + page images
|
||||
*
|
||||
* Pricing (2025-07, aliyun docmind):
|
||||
* - 图文文档基础链路: 0.02元/页
|
||||
* - 图文文档增强链路 (含公式 LaTeX): 0.04元/页
|
||||
* - 视频: 0.002元/秒
|
||||
* - 音频: 0.00035元/秒
|
||||
*
|
||||
* The adapter requests OutputFormat=markdown and FormulaEnhancement=true for
|
||||
* PDF inputs. Page images are returned as URLs and downloaded into the
|
||||
* workspace by the adapter.
|
||||
*/
|
||||
import $DocmindClient, {
|
||||
SubmitDocParserJobAdvanceRequest,
|
||||
QueryDocParserStatusRequest,
|
||||
GetDocParserResultRequest,
|
||||
} from "@alicloud/docmind-api20220711";
|
||||
import { RuntimeOptions } from "@alicloud/tea-util";
|
||||
import { readFile } from "node:fs/promises";
|
||||
import { basename } from "node:path";
|
||||
import type { CapabilitySecretPayload } from "./types.js";
|
||||
|
||||
/** A single extracted image (page render) from the parsed document. */
|
||||
export interface DocmindExtractedImage {
|
||||
/** Suggested relative filename (e.g. "page_1.jpg"). */
|
||||
readonly filename: string;
|
||||
/** Raw image bytes (downloaded from the docmind URL). */
|
||||
readonly data: Uint8Array;
|
||||
}
|
||||
|
||||
/** The structured result of parsing one document. */
|
||||
export interface DocmindParseResult {
|
||||
/** Markdown text with image references (relative to output dir). */
|
||||
readonly markdown: string;
|
||||
/** Page images extracted from the document, downloaded as bytes. */
|
||||
readonly images: readonly DocmindExtractedImage[];
|
||||
/** Number of pages processed (for UsageFact quantity, unit "pages"). */
|
||||
readonly pageCount: number;
|
||||
/** USD cost if the service reported one; null if unknown (ADR-0022).
|
||||
* docmind bills in CNY per page; cost is derived from page count × unit price. */
|
||||
readonly costUsd: number | null;
|
||||
/** External job id for the UsageFact correlationId. */
|
||||
readonly requestId: string | null;
|
||||
}
|
||||
|
||||
/** Options passed to the client. */
|
||||
export interface DocmindParseOptions {
|
||||
/** Absolute path to the input file on the Hub's filesystem. */
|
||||
readonly inputFilePath: string;
|
||||
}
|
||||
|
||||
/**
|
||||
* Client interface for the Alibaba Cloud Document Mind parsing service.
|
||||
* The real implementation uses the official SDK; tests inject a mock.
|
||||
*/
|
||||
export interface CapabilityProviderClient {
|
||||
parse(credential: CapabilitySecretPayload, options: DocmindParseOptions): Promise<DocmindParseResult>;
|
||||
}
|
||||
|
||||
/** Errors raised by the docmind client. */
|
||||
export class DocmindClientError extends Error {
|
||||
constructor(
|
||||
message: string,
|
||||
readonly code: "docmind_unreachable" | "docmind_rejected" | "docmind_invalid_response" | "docmind_no_output" | "docmind_timeout",
|
||||
readonly upstreamStatus?: number,
|
||||
) {
|
||||
super(message);
|
||||
this.name = "DocmindClientError";
|
||||
}
|
||||
}
|
||||
|
||||
/** Cost per page in USD (0.04 CNY/page ≈ 0.0056 USD, rate ~7.15). Updated when pricing confirmed. */
|
||||
const COST_PER_PAGE_USD = 0.0056;
|
||||
|
||||
/** Poll interval for QueryDocParserStatus (ms). Aliyun recommends 10s. */
|
||||
const POLL_INTERVAL_MS = 10_000;
|
||||
/** Max poll duration (ms). Aliyun allows 120 minutes; we cap at 5 minutes for a single page bundle. */
|
||||
const POLL_TIMEOUT_MS = 5 * 60_000;
|
||||
|
||||
/** Type alias for the SDK client constructor's config parameter. */
|
||||
type DocmindConfig = ConstructorParameters<typeof $DocmindClient.default>[0];
|
||||
|
||||
/**
|
||||
* Real Alibaba Cloud Document Mind client using the official SDK.
|
||||
* Submits a local file, polls for completion, fetches the markdown result,
|
||||
* and downloads page images.
|
||||
*/
|
||||
export class AliyunDocmindClient implements CapabilityProviderClient {
|
||||
async parse(credential: CapabilitySecretPayload, options: DocmindParseOptions): Promise<DocmindParseResult> {
|
||||
const config: DocmindConfig = {
|
||||
endpoint: credential.endpoint,
|
||||
accessKeyId: credential.accessKeyId,
|
||||
accessKeySecret: credential.accessKeySecret,
|
||||
type: "access_key",
|
||||
regionId: "cn-hangzhou",
|
||||
} as DocmindConfig;
|
||||
const client = new $DocmindClient.default(config);
|
||||
|
||||
// 1. Submit job with local file upload.
|
||||
const fileName = basename(options.inputFilePath);
|
||||
const fileBuffer = await readFile(options.inputFilePath);
|
||||
const advanceRequest = new SubmitDocParserJobAdvanceRequest({
|
||||
fileUrlObject: fileBuffer,
|
||||
fileName,
|
||||
outputFormat: ["markdown"],
|
||||
formulaEnhancement: true,
|
||||
});
|
||||
const runtime = new RuntimeOptions({});
|
||||
let submitResponse;
|
||||
try {
|
||||
submitResponse = await client.submitDocParserJobAdvance(advanceRequest, runtime);
|
||||
} catch (e) {
|
||||
throw new DocmindClientError(
|
||||
e instanceof Error ? e.message : String(e),
|
||||
"docmind_unreachable",
|
||||
);
|
||||
}
|
||||
const jobId = submitResponse.body?.data?.id;
|
||||
if (jobId === undefined || jobId === null || jobId === "") {
|
||||
throw new DocmindClientError("docmind submit returned no job id", "docmind_invalid_response");
|
||||
}
|
||||
|
||||
// 2. Poll until completed.
|
||||
const deadline = Date.now() + POLL_TIMEOUT_MS;
|
||||
let completed = false;
|
||||
let status = "";
|
||||
while (Date.now() < deadline) {
|
||||
await sleep(POLL_INTERVAL_MS);
|
||||
const statusReq = new QueryDocParserStatusRequest({ id: jobId });
|
||||
const statusResponse = await client.queryDocParserStatus(statusReq);
|
||||
const body = statusResponse.body as { completed?: boolean; status?: string };
|
||||
completed = body.completed === true;
|
||||
status = body.status ?? "";
|
||||
if (completed) break;
|
||||
}
|
||||
if (!completed) {
|
||||
throw new DocmindClientError(`docmind job ${jobId} timed out (status: ${status})`, "docmind_timeout");
|
||||
}
|
||||
if (status === "Fail") {
|
||||
throw new DocmindClientError(`docmind job ${jobId} failed`, "docmind_rejected");
|
||||
}
|
||||
|
||||
// 3. Fetch result.
|
||||
const resultReq = new GetDocParserResultRequest({ id: jobId });
|
||||
const resultResponse = await client.getDocParserResult(resultReq);
|
||||
const resultBody = resultResponse.body as {
|
||||
data?: { markdown?: string; docInfo?: { pages?: Array<{ imageUrl?: string; pageIdCurDoc?: number }> } };
|
||||
};
|
||||
const markdown = resultBody.data?.markdown ?? "";
|
||||
if (markdown === "") {
|
||||
throw new DocmindClientError("docmind returned empty markdown", "docmind_no_output");
|
||||
}
|
||||
|
||||
// 4. Download page images.
|
||||
const pages = resultBody.data?.docInfo?.pages ?? [];
|
||||
const images: DocmindExtractedImage[] = [];
|
||||
for (const page of pages) {
|
||||
if (page.imageUrl === undefined || page.imageUrl === null || page.imageUrl === "") continue;
|
||||
try {
|
||||
const resp = await fetch(page.imageUrl);
|
||||
if (!resp.ok) continue;
|
||||
const data = new Uint8Array(await resp.arrayBuffer());
|
||||
const pageNum = page.pageIdCurDoc ?? images.length + 1;
|
||||
images.push({ filename: `page_${pageNum}.jpg`, data });
|
||||
} catch {
|
||||
// Best-effort: skip images that fail to download.
|
||||
}
|
||||
}
|
||||
|
||||
const pageCount = pages.length > 0 ? pages.length : countMarkdownPages(markdown);
|
||||
const costUsd = pageCount * COST_PER_PAGE_USD;
|
||||
|
||||
return { markdown, images, pageCount, costUsd, requestId: jobId };
|
||||
}
|
||||
}
|
||||
|
||||
function sleep(ms: number): Promise<void> {
|
||||
return new Promise((resolve) => {
|
||||
setTimeout(resolve, ms);
|
||||
});
|
||||
}
|
||||
|
||||
/** Fallback page count: count markdown page separators if docInfo is absent. */
|
||||
function countMarkdownPages(markdown: string): number {
|
||||
const matches = markdown.match(/\n---\n/g);
|
||||
return matches !== null ? matches.length + 1 : 1;
|
||||
}
|
||||
@@ -1,66 +0,0 @@
|
||||
/**
|
||||
* ADR-0027: MinerU client interface. Isolates the real HTTP client so the
|
||||
* adapter is testable without network access. The real implementation (filling
|
||||
* in actual MinerU API calls) is deferred until credentials and pricing are
|
||||
* confirmed; the interface and a mock implementation land now so the adapter
|
||||
* wiring, UsageFact attribution, and workspace containment are provable.
|
||||
*
|
||||
* MinerU cloud API shape (from mineru.net docs / GitHub README):
|
||||
* - REST API, async task endpoint POST /tasks (v3.0+) + sync POST /file_parse
|
||||
* - Auth: Bearer token (apiToken)
|
||||
* - Output: Markdown + extracted images, returned as a zip or structured JSON
|
||||
* - Cost: reported per-page (pricing requires account confirmation)
|
||||
*
|
||||
* The interface models the synchronous parse path for simplicity; the real
|
||||
* client may poll the async endpoint internally and is free to do so behind
|
||||
* this signature.
|
||||
*/
|
||||
import type { CapabilitySecretPayload } from "./types.js";
|
||||
|
||||
/** A single extracted image from the parsed document. */
|
||||
export interface MineruExtractedImage {
|
||||
/** Suggested relative filename (e.g. "page_1_fig_0.jpg"). */
|
||||
readonly filename: string;
|
||||
/** Raw image bytes. */
|
||||
readonly data: Uint8Array;
|
||||
}
|
||||
|
||||
/** The structured result of parsing one document. */
|
||||
export interface MineruParseResult {
|
||||
/** Markdown text with image references (relative to output dir). */
|
||||
readonly markdown: string;
|
||||
/** Images extracted from the document, to be written alongside the md. */
|
||||
readonly images: readonly MineruExtractedImage[];
|
||||
/** Number of pages processed (for UsageFact quantity, unit "pages"). */
|
||||
readonly pageCount: number;
|
||||
/** USD cost if the API reported it; null if unknown (ADR-0022). */
|
||||
readonly costUsd: number | null;
|
||||
/** External task/request id for the UsageFact correlationId. */
|
||||
readonly requestId: string | null;
|
||||
}
|
||||
|
||||
/** Options passed to the client. */
|
||||
export interface MineruParseOptions {
|
||||
/** Absolute path to the input PDF on the Hub's filesystem. */
|
||||
readonly inputFilePath: string;
|
||||
}
|
||||
|
||||
/**
|
||||
* Client interface for the MinerU document parsing service. The real
|
||||
* implementation makes authenticated HTTP calls; tests inject a mock.
|
||||
*/
|
||||
export interface MineruClient {
|
||||
parse(credential: CapabilitySecretPayload, options: MineruParseOptions): Promise<MineruParseResult>;
|
||||
}
|
||||
|
||||
/** Errors raised by the MinerU client. */
|
||||
export class MineruClientError extends Error {
|
||||
constructor(
|
||||
message: string,
|
||||
readonly code: "mineru_unreachable" | "mineru_rejected" | "mineru_invalid_response" | "mineru_no_output",
|
||||
readonly upstreamStatus?: number,
|
||||
) {
|
||||
super(message);
|
||||
this.name = "MineruClientError";
|
||||
}
|
||||
}
|
||||
@@ -20,7 +20,7 @@ import { join, resolve, relative, isAbsolute } from "node:path";
|
||||
import type { PrismaClient } from "@prisma/client";
|
||||
import { LocalSecretEnvelope } from "../security/secretEnvelope.js";
|
||||
import { resolveCapabilityCredential } from "./capabilityConnections.js";
|
||||
import { MineruClientError, type MineruClient } from "./mineruClient.js";
|
||||
import { DocmindClientError, type CapabilityProviderClient } from "./docmindClient.js";
|
||||
import {
|
||||
CAPABILITIES,
|
||||
type CapabilityAdapter,
|
||||
@@ -30,7 +30,7 @@ import {
|
||||
} from "./types.js";
|
||||
|
||||
const CAPABILITY_ID = "pdf_to_md_bundle" as const;
|
||||
const PROVIDER_ID = "mineru";
|
||||
const PROVIDER_ID = "aliyun_docmind";
|
||||
|
||||
/** Thrown when a requested path escapes the workspace root (ADR-0018). */
|
||||
export class CapabilityPathEscape extends Error {
|
||||
@@ -59,11 +59,11 @@ function confineToWorkspace(requestedPath: string, workspaceDir: string): string
|
||||
|
||||
export interface PdfToMdBundleDeps {
|
||||
readonly secrets: LocalSecretEnvelope;
|
||||
readonly client: MineruClient;
|
||||
readonly client: CapabilityProviderClient;
|
||||
readonly prisma: PrismaClient;
|
||||
}
|
||||
|
||||
/** Build the pdf_to_md_bundle adapter. The MineruClient is injectable for testing. */
|
||||
/** Build the pdf_to_md_bundle adapter. The client is injectable for testing. */
|
||||
export function createPdfToMdBundleAdapter(deps: PdfToMdBundleDeps): CapabilityAdapter {
|
||||
return {
|
||||
capabilityId: CAPABILITY_ID,
|
||||
@@ -85,14 +85,14 @@ export function createPdfToMdBundleAdapter(deps: PdfToMdBundleDeps): CapabilityA
|
||||
try {
|
||||
result = await deps.client.parse(credential, { inputFilePath: absoluteInput });
|
||||
} catch (e) {
|
||||
if (e instanceof MineruClientError) throw e;
|
||||
throw new MineruClientError(
|
||||
if (e instanceof DocmindClientError) throw e;
|
||||
throw new DocmindClientError(
|
||||
e instanceof Error ? e.message : String(e),
|
||||
"mineru_unreachable",
|
||||
"docmind_unreachable",
|
||||
);
|
||||
}
|
||||
if (result.markdown === "") {
|
||||
throw new MineruClientError("MinerU returned empty markdown", "mineru_no_output");
|
||||
throw new DocmindClientError("docmind returned empty markdown", "docmind_no_output");
|
||||
}
|
||||
|
||||
// 4. Write outputs into the workspace.
|
||||
|
||||
@@ -80,12 +80,13 @@ export interface CapabilityAdapter {
|
||||
invoke(input: CapabilityInvocationInput): Promise<CapabilityInvocationResult>;
|
||||
}
|
||||
|
||||
/** Decrypted capability credential (CapabilitySecretPayloadV1, ADR-0027). */
|
||||
/** Decrypted capability credential (CapabilitySecretPayloadV1, ADR-0027).
|
||||
* Alibaba Cloud Document Mind (docmind) uses AccessKey ID + Secret + endpoint. */
|
||||
export interface CapabilitySecretPayload {
|
||||
readonly schemaVersion: 1;
|
||||
readonly baseUrl: string;
|
||||
readonly apiToken: string;
|
||||
readonly projectId: string | null;
|
||||
readonly accessKeyId: string;
|
||||
readonly accessKeySecret: string;
|
||||
readonly endpoint: string;
|
||||
}
|
||||
|
||||
/** Thrown when an org has no ACTIVE capability connection (fail-closed, ADR-0024). */
|
||||
|
||||
@@ -4,11 +4,11 @@ import { join } from "node:path";
|
||||
import { afterEach, beforeEach, describe, expect, it, vi } from "vitest";
|
||||
import { prisma, resetDb, seedTestOrganization, testSecretEnvelope, DEFAULT_ORG_ID } from "./helpers.js";
|
||||
import { createPdfToMdBundleAdapter, CapabilityPathEscape } from "../../src/capability/pdfToMdBundle.js";
|
||||
import { MineruClientError, type MineruClient, type MineruParseResult } from "../../src/capability/mineruClient.js";
|
||||
import { DocmindClientError, type CapabilityProviderClient, type DocmindParseResult } from "../../src/capability/docmindClient.js";
|
||||
import type { CapabilitySecretPayload } from "../../src/capability/types.js";
|
||||
|
||||
const CAPABILITY_ID = "pdf_to_md_bundle";
|
||||
const PROVIDER_ID = "mineru";
|
||||
const PROVIDER_ID = "aliyun_docmind";
|
||||
|
||||
/**
|
||||
* ADR-0027: pdf_to_md_bundle adapter contract tests. Proves:
|
||||
@@ -16,8 +16,8 @@ const PROVIDER_ID = "mineru";
|
||||
* - fail-closed credential resolution (no ACTIVE connection → error)
|
||||
* - UsageFact attribution with non-token meter (pages), costSource rules
|
||||
* - outputs (md + images) written into workspace
|
||||
* - MinerU client errors propagate
|
||||
* The MineruClient is mocked; the prisma + envelope + filesystem are real.
|
||||
* - docmind client errors propagate
|
||||
* The client is mocked; the prisma + envelope + filesystem are real.
|
||||
*/
|
||||
describe("pdf_to_md_bundle capability adapter (ADR-0027)", () => {
|
||||
let workspaceRoot: string;
|
||||
@@ -58,9 +58,9 @@ describe("pdf_to_md_bundle capability adapter (ADR-0027)", () => {
|
||||
async function seedActiveCapabilityConnection(): Promise<void> {
|
||||
const payload: CapabilitySecretPayload = {
|
||||
schemaVersion: 1,
|
||||
baseUrl: "https://mineru.test/api",
|
||||
apiToken: "mineru-secret-token",
|
||||
projectId: null,
|
||||
accessKeyId: "LTAI-test-key-id",
|
||||
accessKeySecret: "test-secret-never-log",
|
||||
endpoint: "docmind-api.cn-hangzhou.aliyuncs.com",
|
||||
};
|
||||
const connection = await prisma.organizationCapabilityConnection.create({
|
||||
data: {
|
||||
@@ -95,23 +95,23 @@ describe("pdf_to_md_bundle capability adapter (ADR-0027)", () => {
|
||||
});
|
||||
}
|
||||
|
||||
function mockMineruClient(result: Partial<MineruParseResult> = {}): MineruClient {
|
||||
const full: MineruParseResult = {
|
||||
markdown: "# Parsed Document\n\nHello world.\n\n\n",
|
||||
function mockDocmindClient(result: Partial<DocmindParseResult> = {}): CapabilityProviderClient {
|
||||
const full: DocmindParseResult = {
|
||||
markdown: "# Parsed Document\n\nHello world.\n\n\n",
|
||||
images: [
|
||||
{ filename: "page_1_fig_0.jpg", data: new Uint8Array([0xff, 0xd8, 0xff, 0xe0]) },
|
||||
{ filename: "page_1.jpg", data: new Uint8Array([0xff, 0xd8, 0xff, 0xe0]) },
|
||||
],
|
||||
pageCount: 3,
|
||||
costUsd: 0.015,
|
||||
requestId: "mineru-task-abc",
|
||||
costUsd: 0.0168,
|
||||
requestId: "docmind-job-abc",
|
||||
...result,
|
||||
};
|
||||
return {
|
||||
parse: vi.fn(async (): Promise<MineruParseResult> => full),
|
||||
parse: vi.fn(async (): Promise<DocmindParseResult> => full),
|
||||
};
|
||||
}
|
||||
|
||||
function makeAdapter(client: MineruClient) {
|
||||
function makeAdapter(client: CapabilityProviderClient) {
|
||||
return createPdfToMdBundleAdapter({
|
||||
secrets: testSecretEnvelope,
|
||||
client,
|
||||
@@ -130,7 +130,7 @@ describe("pdf_to_md_bundle capability adapter (ADR-0027)", () => {
|
||||
it("writes md + images into the workspace and records a UsageFact", async () => {
|
||||
await seedActiveCapabilityConnection();
|
||||
const inputPath = await seedInputPdf();
|
||||
const client = mockMineruClient();
|
||||
const client = mockDocmindClient();
|
||||
const adapter = makeAdapter(client);
|
||||
|
||||
const result = await adapter.invoke({
|
||||
@@ -147,12 +147,12 @@ describe("pdf_to_md_bundle capability adapter (ADR-0027)", () => {
|
||||
const md = await readFile(join(workspaceRoot, "output", "document.md"), "utf8");
|
||||
expect(md).toContain("# Parsed Document");
|
||||
expect(result.artifacts.some((a) => a.kind === "markdown" && a.path === "output/document.md")).toBe(true);
|
||||
expect(result.artifacts.some((a) => a.kind === "image" && a.path === "output/page_1_fig_0.jpg")).toBe(true);
|
||||
expect(result.artifacts.some((a) => a.kind === "image" && a.path === "output/page_1.jpg")).toBe(true);
|
||||
|
||||
// Client received the decrypted credential, not the env.
|
||||
const call = (client.parse as ReturnType<typeof vi.fn>).mock.calls[0]?.[0] as CapabilitySecretPayload;
|
||||
expect(call.apiToken).toBe("mineru-secret-token");
|
||||
expect(call.baseUrl).toBe("https://mineru.test/api");
|
||||
expect(call.accessKeyId).toBe("LTAI-test-key-id");
|
||||
expect(call.endpoint).toBe("docmind-api.cn-hangzhou.aliyuncs.com");
|
||||
|
||||
// UsageFact written with non-token meter and provider_reported cost.
|
||||
const facts = await prisma.usageFact.findMany({ where: { runId } });
|
||||
@@ -163,15 +163,15 @@ describe("pdf_to_md_bundle capability adapter (ADR-0027)", () => {
|
||||
expect(fact.capabilityId).toBe(CAPABILITY_ID);
|
||||
expect(Number(fact.quantity)).toBe(3);
|
||||
expect(fact.unit).toBe("pages");
|
||||
expect(Number(fact.costUsd!)).toBeCloseTo(0.015, 8);
|
||||
expect(Number(fact.costUsd!)).toBeCloseTo(0.0168, 8);
|
||||
expect(fact.costSource).toBe("provider_reported");
|
||||
expect(fact.correlationId).toBe("mineru-task-abc");
|
||||
expect(fact.correlationId).toBe("docmind-job-abc");
|
||||
});
|
||||
|
||||
it("writes UsageFact with costSource=unknown when MinerU reports no cost", async () => {
|
||||
it("writes UsageFact with costSource=unknown when docmind reports no cost", async () => {
|
||||
await seedActiveCapabilityConnection();
|
||||
const inputPath = await seedInputPdf();
|
||||
const client = mockMineruClient({ costUsd: null, requestId: null });
|
||||
const client = mockDocmindClient({ costUsd: null, requestId: null });
|
||||
const adapter = makeAdapter(client);
|
||||
|
||||
await adapter.invoke({
|
||||
@@ -194,7 +194,7 @@ describe("pdf_to_md_bundle capability adapter (ADR-0027)", () => {
|
||||
it("fails closed when the org has no ACTIVE capability connection", async () => {
|
||||
// No connection seeded.
|
||||
const inputPath = await seedInputPdf();
|
||||
const adapter = makeAdapter(mockMineruClient());
|
||||
const adapter = makeAdapter(mockDocmindClient());
|
||||
|
||||
await expect(adapter.invoke({
|
||||
runId,
|
||||
@@ -213,7 +213,7 @@ describe("pdf_to_md_bundle capability adapter (ADR-0027)", () => {
|
||||
|
||||
it("rejects an input path that escapes the workspace", async () => {
|
||||
await seedActiveCapabilityConnection();
|
||||
const adapter = makeAdapter(mockMineruClient());
|
||||
const adapter = makeAdapter(mockDocmindClient());
|
||||
|
||||
await expect(adapter.invoke({
|
||||
runId,
|
||||
@@ -229,7 +229,7 @@ describe("pdf_to_md_bundle capability adapter (ADR-0027)", () => {
|
||||
it("rejects an output path that escapes the workspace", async () => {
|
||||
await seedActiveCapabilityConnection();
|
||||
const inputPath = await seedInputPdf();
|
||||
const adapter = makeAdapter(mockMineruClient());
|
||||
const adapter = makeAdapter(mockDocmindClient());
|
||||
|
||||
await expect(adapter.invoke({
|
||||
runId,
|
||||
@@ -242,12 +242,12 @@ describe("pdf_to_md_bundle capability adapter (ADR-0027)", () => {
|
||||
})).rejects.toBeInstanceOf(CapabilityPathEscape);
|
||||
});
|
||||
|
||||
it("propagates MinerU client errors without writing a UsageFact", async () => {
|
||||
it("propagates docmind client errors without writing a UsageFact", async () => {
|
||||
await seedActiveCapabilityConnection();
|
||||
const inputPath = await seedInputPdf();
|
||||
const client: MineruClient = {
|
||||
parse: vi.fn(async (): Promise<MineruParseResult> => {
|
||||
throw new MineruClientError("upstream 502", "mineru_rejected", 502);
|
||||
const client: CapabilityProviderClient = {
|
||||
parse: vi.fn(async (): Promise<DocmindParseResult> => {
|
||||
throw new DocmindClientError("upstream 502", "docmind_rejected", 502);
|
||||
}),
|
||||
};
|
||||
const adapter = makeAdapter(client);
|
||||
@@ -269,7 +269,7 @@ describe("pdf_to_md_bundle capability adapter (ADR-0027)", () => {
|
||||
it("rejects empty markdown output as a parse failure", async () => {
|
||||
await seedActiveCapabilityConnection();
|
||||
const inputPath = await seedInputPdf();
|
||||
const client = mockMineruClient({ markdown: "" });
|
||||
const client = mockDocmindClient({ markdown: "" });
|
||||
const adapter = makeAdapter(client);
|
||||
|
||||
await expect(adapter.invoke({
|
||||
|
||||
Reference in New Issue
Block a user