From f5742940ccd06bafd2708e32af30023eef241241 Mon Sep 17 00:00:00 2001 From: marius-kilocode Date: Fri, 29 May 2026 16:24:48 +0200 Subject: [PATCH] feat(cli): support DOCX text extraction in read tool --- .changeset/read-docx-text.md | 5 + bun.lock | 46 +++-- package.json | 3 +- packages/opencode/package.json | 1 + .../opencode/src/kilocode/tool/read-docx.ts | 15 ++ packages/opencode/src/tool/read.ts | 6 +- .../opencode/test/kilocode/read-docx.test.ts | 185 ++++++++++++++++++ patches/mammoth@1.12.0.patch | 33 ++++ 8 files changed, 277 insertions(+), 17 deletions(-) create mode 100644 .changeset/read-docx-text.md create mode 100644 packages/opencode/src/kilocode/tool/read-docx.ts create mode 100644 packages/opencode/test/kilocode/read-docx.test.ts create mode 100644 patches/mammoth@1.12.0.patch diff --git a/.changeset/read-docx-text.md b/.changeset/read-docx-text.md new file mode 100644 index 00000000000..91d44d72f84 --- /dev/null +++ b/.changeset/read-docx-text.md @@ -0,0 +1,5 @@ +--- +"@kilocode/cli": patch +--- + +Support reading text from DOCX files through the read tool. diff --git a/bun.lock b/bun.lock index 1abda6e1a39..30d072506e5 100644 --- a/bun.lock +++ b/bun.lock @@ -387,6 +387,7 @@ "ignore": "7.0.5", "immer": "11.1.4", "jsonc-parser": "3.3.1", + "mammoth": "1.12.0", "mime-types": "3.0.2", "minimatch": "10.2.5", "npm-package-arg": "13.0.2", @@ -588,6 +589,7 @@ "patchedDependencies": { "@standard-community/standard-openapi@0.2.9": "patches/@standard-community%2Fstandard-openapi@0.2.9.patch", "@npmcli/agent@4.0.0": "patches/@npmcli%2Fagent@4.0.0.patch", + "mammoth@1.12.0": "patches/mammoth@1.12.0.patch", }, "overrides": { "@effect/platform-node-shared": "4.0.0-beta.46", @@ -2258,6 +2260,8 @@ "@webcontainer/env": ["@webcontainer/env@1.1.1", "", {}, "sha512-6aN99yL695Hi9SuIk1oC88l9o0gmxL1nGWWQ/kNy81HigJ0FoaoTXpytCj6ItzgyCEwA9kF1wixsTuv5cjsgng=="], + "@xmldom/xmldom": ["@xmldom/xmldom@0.9.10", "", {}, "sha512-A9gOqLdi6cV4ibazAjcQufGj0B1y/vDqYrcuP6d/6x8P27gRS8643Dj9o1dEKtB6O7fwxb2FgBmJS2mX7gpvdw=="], + "@xterm/addon-clipboard": ["@xterm/addon-clipboard@0.2.0", "", { "dependencies": { "js-base64": "^3.7.5" } }, "sha512-Dl31BCtBhLaUEECUbEiVcCLvLBbaeGYdT7NofB8OJkGTD3MWgBsaLjXvfGAD4tQNHhm6mbKyYkR7XD8kiZsdNg=="], "@xterm/addon-fit": ["@xterm/addon-fit@0.11.0", "", {}, "sha512-jYcgT6xtVYhnhgxh3QgYDnnNMYTcf8ElbxxFzX0IZo+vabQqSPAjC3c1wJrKB5E19VwQei89QCiZZP86DCPF7g=="], @@ -2320,7 +2324,7 @@ "arctic": ["arctic@2.3.4", "", { "dependencies": { "@oslojs/crypto": "1.0.1", "@oslojs/encoding": "1.1.0", "@oslojs/jwt": "0.2.0" } }, "sha512-+p30BOWsctZp+CVYCt7oAean/hWGW42sH5LAcRQX56ttEkFJWbzXBhmSpibbzwSJkRrotmsA+oAoJoVsU0f5xA=="], - "argparse": ["argparse@2.0.1", "", {}, "sha512-8+9WqebbFzpX9OR+Wa6O29asIogeRMzcGtAINdpMHHyAg10f05aSFVBbcEqGf/PXw1EjAZ+q2/bEBg3DvurK3Q=="], + "argparse": ["argparse@1.0.10", "", { "dependencies": { "sprintf-js": "~1.0.2" } }, "sha512-o5Roy6tNG4SL/FOkCAN6RzjiakZS25RLYFrcMttJqbdd8BWrnA+fGz57iN5Pb06pvBGvl5gQ0B48dJlslXvoTg=="], "aria-query": ["aria-query@5.3.2", "", {}, "sha512-COROpnaoap1E2F000S62r6A60uHZnmlvomhfyT2DlTcrY1OrBKn2UhH7qn5wTC9zMvD0AY7csdPSNwKP+7WiQw=="], @@ -2412,6 +2416,8 @@ "bl": ["bl@6.1.6", "", { "dependencies": { "@types/readable-stream": "^4.0.0", "buffer": "^6.0.3", "inherits": "^2.0.4", "readable-stream": "^4.2.0" } }, "sha512-jLsPgN/YSvPUg9UX0Kd73CXpm2Psg9FxMeCSXnk3WBO3CMT10JMwijubhGfHCnFu6TPn1ei3b975dxv7K2pWVg=="], + "bluebird": ["bluebird@3.4.7", "", {}, "sha512-iD3898SR7sWVRHbiQv+sHUtHnMvC1o3nW5rAcqnq3uOn07DSAppZYUkIGslDz6gXC7HfunPe7YVBgoEJASPcHA=="], + "blueimp-md5": ["blueimp-md5@2.19.0", "", {}, "sha512-DRQrD6gJyy8FbiE4s+bDoXS9hiW3Vbx5uCdwvcCf3zLHL+Iv7LtGHLpr+GZV8rHG8tK766FGYBwRbu8pELTt+w=="], "body-parser": ["body-parser@2.2.2", "", { "dependencies": { "bytes": "^3.1.2", "content-type": "^1.0.5", "debug": "^4.4.3", "http-errors": "^2.0.0", "iconv-lite": "^0.7.0", "on-finished": "^2.4.1", "qs": "^6.14.1", "raw-body": "^3.0.1", "type-is": "^2.0.1" } }, "sha512-oP5VkATKlNwcgvxi0vM0p/D3n2C3EReYVX+DNYs5TjZFn/oQt2j+4sVJtSMr18pdRr8wjTcBl6LoV+FUwzPmNA=="], @@ -2742,6 +2748,8 @@ "dijkstrajs": ["dijkstrajs@1.0.3", "", {}, "sha512-qiSlmBq9+BCdCA/L46dw8Uy93mloxsPSbwnm5yrKn2vMPiy8KyAskTF6zuV/j5BMsmOGZDPs7KjU+mjb670kfA=="], + "dingbat-to-unicode": ["dingbat-to-unicode@1.0.1", "", {}, "sha512-98l0sW87ZT58pU4i61wa2OHwxbiYSbuxsCBozaVnYX2iCnr3bLM3fIes1/ej7h1YdOKuKt/MLs706TVnALA65w=="], + "dir-glob": ["dir-glob@3.0.1", "", { "dependencies": { "path-type": "^4.0.0" } }, "sha512-WkrWp9GR4KXfKGYzOLmTuGVi1UWFfws377n9cc55/tb6DuqyF6pcQ5AbiHEshaDpY9v6oaSr2XCDidGmMwdzIA=="], "dns-packet": ["dns-packet@5.6.1", "", { "dependencies": { "@leichtgewicht/ip-codec": "^2.0.1" } }, "sha512-l4gcSouhcgIKRvyy99RNVOgxXiicE+2jZoNmaNmZ6JXiGajBOJAesk1OBlJuM5k2c+eudGdLxDqXuPCKIj6kpw=="], @@ -2764,6 +2772,8 @@ "drizzle-orm": ["drizzle-orm@1.0.0-beta.19-d95b7a4", "", { "peerDependencies": { "@aws-sdk/client-rds-data": ">=3", "@cloudflare/workers-types": ">=4", "@effect/sql": "^0.48.5", "@effect/sql-pg": "^0.49.7", "@electric-sql/pglite": ">=0.2.0", "@libsql/client": ">=0.10.0", "@libsql/client-wasm": ">=0.10.0", "@neondatabase/serverless": ">=0.10.0", "@op-engineering/op-sqlite": ">=2", "@opentelemetry/api": "^1.4.1", "@planetscale/database": ">=1.13", "@sinclair/typebox": ">=0.34.8", "@sqlitecloud/drivers": ">=1.0.653", "@tidbcloud/serverless": "*", "@tursodatabase/database": ">=0.2.1", "@tursodatabase/database-common": ">=0.2.1", "@tursodatabase/database-wasm": ">=0.2.1", "@types/better-sqlite3": "*", "@types/mssql": "^9.1.4", "@types/pg": "*", "@types/sql.js": "*", "@upstash/redis": ">=1.34.7", "@vercel/postgres": ">=0.8.0", "@xata.io/client": "*", "arktype": ">=2.0.0", "better-sqlite3": ">=9.3.0", "bun-types": "*", "expo-sqlite": ">=14.0.0", "gel": ">=2", "mssql": "^11.0.1", "mysql2": ">=2", "pg": ">=8", "postgres": ">=3", "sql.js": ">=1", "sqlite3": ">=5", "typebox": ">=1.0.0", "valibot": ">=1.0.0-beta.7", "zod": "^3.25.0 || ^4.0.0" }, "optionalPeers": ["@aws-sdk/client-rds-data", "@cloudflare/workers-types", "@effect/sql", "@effect/sql-pg", "@electric-sql/pglite", "@libsql/client", "@libsql/client-wasm", "@neondatabase/serverless", "@op-engineering/op-sqlite", "@opentelemetry/api", "@planetscale/database", "@sinclair/typebox", "@sqlitecloud/drivers", "@tidbcloud/serverless", "@tursodatabase/database", "@tursodatabase/database-common", "@tursodatabase/database-wasm", "@types/better-sqlite3", "@types/pg", "@types/sql.js", "@upstash/redis", "@vercel/postgres", "@xata.io/client", "arktype", "better-sqlite3", "bun-types", "expo-sqlite", "gel", "mysql2", "pg", "postgres", "sql.js", "sqlite3", "typebox", "valibot", "zod"] }, "sha512-bZZKKeoRKrMVU6zKTscjrSH0+WNb1WEi3N0Jl4wEyQ7aQpTgHzdYY6IJQ1P0M74HuSJVeX4UpkFB/S6dtqLEJg=="], + "duck": ["duck@0.1.12", "", { "dependencies": { "underscore": "^1.13.1" } }, "sha512-wkctla1O6VfP89gQ+J/yDesM0S7B7XLXjKGzXxMDVFg7uEn706niAtyYovKbyq1oT9YwDcly721/iUWoc8MVRg=="], + "dunder-proto": ["dunder-proto@1.0.1", "", { "dependencies": { "call-bind-apply-helpers": "^1.0.1", "es-errors": "^1.3.0", "gopd": "^1.2.0" } }, "sha512-KIN/nDJBQRcXw0MLVhZE9iQHmG68qAVIBg9CqmUYjmQIhgij9U5MFvrqkUL5FbtyyzZuOeOt0zdeRe4UY7ct+A=="], "eastasianwidth": ["eastasianwidth@0.2.0", "", {}, "sha512-I88TYZWc9XiYHRQ4/3c5rjjfgkjhLyW2luGIheGERbNQ6OY7yTybanSpDXZa8y7VUP9YmDcYa+eyq4ca7iLqWA=="], @@ -3368,6 +3378,8 @@ "loose-envify": ["loose-envify@1.4.0", "", { "dependencies": { "js-tokens": "^3.0.0 || ^4.0.0" }, "bin": { "loose-envify": "cli.js" } }, "sha512-lyuxPGr/Wfhrlem2CL/UcnUc1zcqKAImBDzukY7Y5F/yQiNdko6+fRLevlw1HgMySw7f611UIY408EtxRSoK3Q=="], + "lop": ["lop@0.4.2", "", { "dependencies": { "duck": "^0.1.12", "option": "~0.2.1", "underscore": "^1.13.1" } }, "sha512-RefILVDQ4DKoRZsJ4Pj22TxE3omDO47yFpkIBoDKzkqPRISs5U1cnAdg/5583YPkWPaLIYHOKRMQSvjFsO26cw=="], + "loupe": ["loupe@3.2.1", "", {}, "sha512-CdzqowRJCeLU72bHvWqwRBBlLcMEtIvGrlvef74kMnV2AolS9Y8xUv1I0U/MNAWMhBlKIoyuEgoJ0t/bbwHbLQ=="], "lru-cache": ["lru-cache@11.3.5", "", {}, "sha512-NxVFwLAnrd9i7KUBxC4DrUhmgjzOs+1Qm50D3oF1/oL+r1NpZ4gA7xvG0/zJ8evR7zIKn4vLf7qTNduWFtCrRw=="], @@ -3386,6 +3398,8 @@ "make-fetch-happen": ["make-fetch-happen@15.0.5", "", { "dependencies": { "@gar/promise-retry": "^1.0.0", "@npmcli/agent": "^4.0.0", "@npmcli/redact": "^4.0.0", "cacache": "^20.0.1", "http-cache-semantics": "^4.1.1", "minipass": "^7.0.2", "minipass-fetch": "^5.0.0", "minipass-flush": "^1.0.5", "minipass-pipeline": "^1.2.4", "negotiator": "^1.0.0", "proc-log": "^6.0.0", "ssri": "^13.0.0" } }, "sha512-uCbIa8jWWmQZt4dSnEStkVC6gdakiinAm4PiGsywIkguF0eWMdcjDz0ECYhUolFU3pFLOev9VNPCEygydXnddg=="], + "mammoth": ["mammoth@1.12.0", "", { "dependencies": { "@xmldom/xmldom": "^0.8.6", "argparse": "~1.0.3", "base64-js": "^1.5.1", "bluebird": "~3.4.0", "dingbat-to-unicode": "^1.0.1", "jszip": "^3.7.1", "lop": "^0.4.2", "path-is-absolute": "^1.0.0", "underscore": "^1.13.1", "xmlbuilder": "^10.0.0" }, "bin": { "mammoth": "bin/mammoth" } }, "sha512-cwnK1RIcRdDMi2HRx2EXGYlxqIEh0Oo3bLhorgnsVJi2UkbX1+jKxuBNR9PC5+JaX7EkmJxFPmo6mjLpqShI2w=="], + "map-age-cleaner": ["map-age-cleaner@0.1.3", "", { "dependencies": { "p-defer": "^1.0.0" } }, "sha512-bJzx6nMoP6PDLPBFmg7+xRKeFZvFboMrGlxmNj9ClvX53KrmvM5bXFXEWjbz4cz1AFn+jWJ9z/DJSz7hrs0w3w=="], "markdown-it": ["markdown-it@14.1.1", "", { "dependencies": { "argparse": "^2.0.1", "entities": "^4.4.0", "linkify-it": "^5.0.0", "mdurl": "^2.0.0", "punycode.js": "^2.3.1", "uc.micro": "^2.1.0" }, "bin": { "markdown-it": "bin/markdown-it.mjs" } }, "sha512-BuU2qnTti9YKgK5N+IeMubp14ZUKUUw7yeJbkjtosvHiP0AZ5c8IAgEMk79D0eC8F23r4Ac/q8cAIFdm2FtyoA=="], @@ -3602,6 +3616,8 @@ "opentui-spinner": ["opentui-spinner@0.0.6", "", { "dependencies": { "cli-spinners": "^3.3.0" }, "peerDependencies": { "@opentui/core": "^0.1.49", "@opentui/react": "^0.1.49", "@opentui/solid": "^0.1.49", "typescript": "^5" }, "optionalPeers": ["@opentui/react", "@opentui/solid"] }, "sha512-xupLOeVQEAXEvVJCvHkfX6fChDWmJIPHe5jyUrVb8+n4XVTX8mBNhitFfB9v2ZbkC1H2UwPab/ElePHoW37NcA=="], + "option": ["option@0.2.4", "", {}, "sha512-pkEqbDyl8ou5cpq+VsnQbe/WlEy5qS7xPzMS1U55OCG9KPvwFD46zDbxQIj3egJSFc3D+XhYOPUzz49zQAVy7A=="], + "optionator": ["optionator@0.9.4", "", { "dependencies": { "deep-is": "^0.1.3", "fast-levenshtein": "^2.0.6", "levn": "^0.4.1", "prelude-ls": "^1.2.1", "type-check": "^0.4.0", "word-wrap": "^1.2.5" } }, "sha512-6IpQ7mKUxRcZNLIObR0hz7lxsapSSIYNZJwXPGeF0mTVqGKFIXj1DQcMoT22S3ROcLyY/rz0PWaWZ9ayWmad9g=="], "ora": ["ora@8.2.0", "", { "dependencies": { "chalk": "^5.3.0", "cli-cursor": "^5.0.0", "cli-spinners": "^2.9.2", "is-interactive": "^2.0.0", "is-unicode-supported": "^2.0.0", "log-symbols": "^6.0.0", "stdin-discarder": "^0.2.2", "string-width": "^7.2.0", "strip-ansi": "^7.1.0" } }, "sha512-weP+BZ8MVNnlCm8c0Qdc1WSWq4Qn7I+9CJGm7Qali6g44e/PUzbjNqJX5NJ9ljlNMosfJvg1fKEGILklK9cwnw=="], @@ -3666,6 +3682,8 @@ "path-expression-matcher": ["path-expression-matcher@1.5.0", "", {}, "sha512-cbrerZV+6rvdQrrD+iGMcZFEiiSrbv9Tfdkvnusy6y0x0GKBXREFg/Y65GhIfm0tnLntThhzCnfKwp1WRjeCyQ=="], + "path-is-absolute": ["path-is-absolute@1.0.1", "", {}, "sha512-AVbw3UJ2e9bq64vSaS9Am0fje1Pa8pbGqTTsmXfaIiMpnr5DlDhfJOuLj9Sf95ZPVDAUerDfEk88MPmPe7UCQg=="], + "path-key": ["path-key@3.1.1", "", {}, "sha512-ojmeN0qd+y0jszEtoY48r0Peq5dwMEkIlCOu6Q5f41lfkswXuKtYrhgoTpLnyIcHm24Uhqx+5Tqm2InSwLhE6Q=="], "path-parse": ["path-parse@1.0.7", "", {}, "sha512-LDJzPVEEEPR+y48z93A0Ed0yXb8pAByGWo/k5YYdYgpY2/2EsOsksJrq7lOHxryrVOn1ejG6oAp8ahvOIQD8sw=="], @@ -4018,7 +4036,7 @@ "split2": ["split2@4.2.0", "", {}, "sha512-UcjcJOWknrNkF6PLX83qcHM6KHgVKNkV62Y8a5uYDVv9ydGQVwAHMKqHdJje1VTWpljG0WYpCDhrCdAOYH4TWg=="], - "sprintf-js": ["sprintf-js@1.1.3", "", {}, "sha512-Oo+0REFV59/rz3gfJNKQiBlwfHaSESl1pcGyABQsnnIfWOFt6JNj5gCog2U6MLZ//IGYD+nA8nI+mTShREReaA=="], + "sprintf-js": ["sprintf-js@1.0.3", "", {}, "sha512-D9cPgkvLlV3t3IzL0D0YLvGA9Ahk4PcvVwUbN0dSGr1aP0Nrt4AEnTUbuGvquEC0mA64Gqt1fzirlRs5ibXx8g=="], "ssri": ["ssri@13.0.1", "", { "dependencies": { "minipass": "^7.0.3" } }, "sha512-QUiRf1+u9wPTL/76GTYlKttDEBWV1ga9ZXW8BG6kfdeyyM8LGPix9gROyg9V2+P0xNyF3X2Go526xKFdMZrHSQ=="], @@ -4356,7 +4374,7 @@ "xml2js": ["xml2js@0.5.0", "", { "dependencies": { "sax": ">=0.6.0", "xmlbuilder": "~11.0.0" } }, "sha512-drPFnkQJik/O+uPKpqSgr22mpuFHqKdbS835iAQrUC73L2F5WkboIRd63ai/2Yg6I1jzifPFKH2NTK+cfglkIA=="], - "xmlbuilder": ["xmlbuilder@11.0.1", "", {}, "sha512-fDlsI/kFEx7gLvbecc0/ohLG50fugQp8ryHzMTuW9vSa1GJ0XYWKnhsUx7oie3G98+r56aTQIUB4kht42R3JvA=="], + "xmlbuilder": ["xmlbuilder@10.1.1", "", {}, "sha512-OyzrcFLL/nb6fMGHbiRDuPup9ljBycsdCypwuyg5AAHvyWzGfChJpCXMG88AGTIMFhGZ9RccFN1e6lhg3hkwKg=="], "xmlhttprequest-ssl": ["xmlhttprequest-ssl@2.1.2", "", {}, "sha512-TEU+nJVUUnA4CYJFLvK5X9AOeH4KvDvhIfm0vV1GaQRtchnG0hgK5p8hw/xjv8cunWYCsiPCSDzObPyhEwq3KQ=="], @@ -4814,6 +4832,8 @@ "istanbul-lib-report/supports-color": ["supports-color@7.2.0", "", { "dependencies": { "has-flag": "^4.0.0" } }, "sha512-qpCAvRl9stuOHveKsn7HncJRvv501qIacKzQlO/+Lwxc9+0q2wLyv4Dfvt80/DPn2pqOBsJdDiogXGR9+OvwRw=="], + "js-yaml/argparse": ["argparse@2.0.1", "", {}, "sha512-8+9WqebbFzpX9OR+Wa6O29asIogeRMzcGtAINdpMHHyAg10f05aSFVBbcEqGf/PXw1EjAZ+q2/bEBg3DvurK3Q=="], + "jszip/readable-stream": ["readable-stream@2.3.8", "", { "dependencies": { "core-util-is": "~1.0.0", "inherits": "~2.0.3", "isarray": "~1.0.0", "process-nextick-args": "~2.0.0", "safe-buffer": "~5.1.1", "string_decoder": "~1.1.1", "util-deprecate": "~1.0.1" } }, "sha512-8p0AUk4XODgIewSi0l8Epjs+EVnWiK7NoDIEGU0HhE7+ZyY8D1IMY7odu5lRrFXGg71L15KG8QrPmum45RTtdA=="], "katex/commander": ["commander@8.3.0", "", {}, "sha512-OkTL9umf+He2DZkUq8f8J9of7yL6RJKI24dVITBmNfZBmri9zYZQrKkuXiKhyfPSu8tUhnVBB1iKXevvnlR4Ww=="], @@ -4842,6 +4862,8 @@ "log-symbols/is-unicode-supported": ["is-unicode-supported@0.1.0", "", {}, "sha512-knxG2q4UC3u8stRGyAVJCOdxFmv5DZiRcdlIaAQXAbSfJya+OhopNotLQrstBhququ4ZpuKbDc/8S6mgXgPFPw=="], + "markdown-it/argparse": ["argparse@2.0.1", "", {}, "sha512-8+9WqebbFzpX9OR+Wa6O29asIogeRMzcGtAINdpMHHyAg10f05aSFVBbcEqGf/PXw1EjAZ+q2/bEBg3DvurK3Q=="], + "markdown-it/entities": ["entities@4.5.0", "", {}, "sha512-V0hjH4dGPh9Ao5p0MoRY6BVqtwCjhz6vI5LT8AJ55H+4g9/4vbHx1I54fS0XuclLhDHArPQCiMjDxjaL8fPxhw=="], "matcher/escape-string-regexp": ["escape-string-regexp@5.0.0", "", {}, "sha512-/veY75JbMK4j1yjvuUxuVsiS/hr/4iHs9FTT6cgTexxdE0Ly/glccBAkloH/DofkjRbZU3bnoj38mOmhkZ0lHw=="], @@ -4992,6 +5014,8 @@ "tedious/iconv-lite": ["iconv-lite@0.6.3", "", { "dependencies": { "safer-buffer": ">= 2.1.2 < 3.0.0" } }, "sha512-4fCk79wshMdzMp2rH06qWrJE4iolqLhCUH+OiuIgU++RB0+94NlDL81atO7GX55uUKueo0txHNtvEyI6D7WdMw=="], + "tedious/sprintf-js": ["sprintf-js@1.1.3", "", {}, "sha512-Oo+0REFV59/rz3gfJNKQiBlwfHaSESl1pcGyABQsnnIfWOFt6JNj5gCog2U6MLZ//IGYD+nA8nI+mTShREReaA=="], + "test-exclude/glob": ["glob@10.5.0", "", { "dependencies": { "foreground-child": "^3.1.0", "jackspeak": "^3.1.2", "minimatch": "^9.0.4", "minipass": "^7.1.2", "package-json-from-dist": "^1.0.0", "path-scurry": "^1.11.1" }, "bin": { "glob": "dist/esm/bin.mjs" } }, "sha512-DfXN8DfhJ7NH3Oe7cFmu3NCu1wKbkReJ8TorzSAFbSKrlNaQSKfIzqYqVY8zlbs2NLBbWpRiU52GX2PbaBVNkg=="], "to-buffer/isarray": ["isarray@2.0.5", "", {}, "sha512-xHjhDr3cNBK0BzdUJSPXZntQUx/mwMS5Rw4A7lPJ90XGAO6ISP/ePDNuo0vhqOZU+UD5JoodwCAAoZQd3FeAKw=="], @@ -5018,6 +5042,8 @@ "xml2js/sax": ["sax@1.6.0", "", {}, "sha512-6R3J5M4AcbtLUdZmRv2SygeVaM7IhrLXu9BmnOGmmACak8fiUtOsYNWUS4uK7upbmHIBbLBeFeI//477BKLBzA=="], + "xml2js/xmlbuilder": ["xmlbuilder@11.0.1", "", {}, "sha512-fDlsI/kFEx7gLvbecc0/ohLG50fugQp8ryHzMTuW9vSa1GJ0XYWKnhsUx7oie3G98+r56aTQIUB4kht42R3JvA=="], + "yargs-unparser/decamelize": ["decamelize@4.0.0", "", {}, "sha512-9iE1PgSik9HeIIw2JO94IidnE3eBoQrFJ3w7sFuzSX4DpmZ3v5sZpUiV5Swcf6mQEF+Y0ru8Neo+p+nyh2J+hQ=="], "yauzl/buffer-crc32": ["buffer-crc32@0.2.13", "", {}, "sha512-VO9Ht/+p3SN7SKWqcrgEzjGbRSJYTx+Q1pTQC0wrWqHx0vpJraQ6GtHx8tvcg1rlK1byhU5gccxgOgj7B0TDkQ=="], @@ -5228,6 +5254,8 @@ "aws-sdk/xml2js/sax": ["sax@1.6.0", "", {}, "sha512-6R3J5M4AcbtLUdZmRv2SygeVaM7IhrLXu9BmnOGmmACak8fiUtOsYNWUS4uK7upbmHIBbLBeFeI//477BKLBzA=="], + "aws-sdk/xml2js/xmlbuilder": ["xmlbuilder@11.0.1", "", {}, "sha512-fDlsI/kFEx7gLvbecc0/ohLG50fugQp8ryHzMTuW9vSa1GJ0XYWKnhsUx7oie3G98+r56aTQIUB4kht42R3JvA=="], + "babel-plugin-module-resolver/glob/minimatch": ["minimatch@8.0.7", "", { "dependencies": { "brace-expansion": "^2.0.1" } }, "sha512-V+1uQNdzybxa14e/p00HZnQNNcTjnRJjDxg2V8wtkjFctq4M7hXFws4oekyTP0Jebeq7QYtpFyOeBAjc88zvYg=="], "babel-plugin-module-resolver/glob/minipass": ["minipass@4.2.8", "", {}, "sha512-fNzuVyifolSLFL4NzpF+wEF4qrgqaaKX0haXPQEdQ7NKAN+WecoKMHV09YcuL/DHxrUsYQOK3MiuDf7Ip2OXfQ=="], @@ -5338,8 +5366,6 @@ "friendly-words/express/type-is": ["type-is@1.6.18", "", { "dependencies": { "media-typer": "0.3.0", "mime-types": "~2.1.24" } }, "sha512-TkRKr9sUTxEH8MdfuCSP7VizJyzRNMjj2J2do2Jr3Kym598JVdEksuzPQCnlFPW4ky9Q+iA+ma9BGm06XQBy8g=="], - "gray-matter/js-yaml/argparse": ["argparse@1.0.10", "", { "dependencies": { "sprintf-js": "~1.0.2" } }, "sha512-o5Roy6tNG4SL/FOkCAN6RzjiakZS25RLYFrcMttJqbdd8BWrnA+fGz57iN5Pb06pvBGvl5gQ0B48dJlslXvoTg=="], - "jszip/readable-stream/safe-buffer": ["safe-buffer@5.1.2", "", {}, "sha512-Gd2UZBJDkXlY7GbJxfsE8/nvKkUEU1G38c1siN6QP6a9PT9MmHB8GnpscSmMJSoF8LOIrt8ud/wPtojys4G6+g=="], "jszip/readable-stream/string_decoder": ["string_decoder@1.1.1", "", { "dependencies": { "safe-buffer": "~5.1.0" } }, "sha512-n/ShnvDi6FHbbVfviro+WojiFzv+s8MPMHBczVePfUpDJLwoLT0ht1l4YwBCbi8pJAveEEdnkHyPyTP/mzRfwg=="], @@ -5396,8 +5422,6 @@ "qrcode/yargs/yargs-parser": ["yargs-parser@18.1.3", "", { "dependencies": { "camelcase": "^5.0.0", "decamelize": "^1.2.0" } }, "sha512-o50j0JeToy/4K6OZcaQmW6lyXXKhq7csREXcDwk2omFPJEwUNOVtJKvmDr9EI1fAJZUyZcRF7kxGBWmRXudrCQ=="], - "read-yaml-file/js-yaml/argparse": ["argparse@1.0.10", "", { "dependencies": { "sprintf-js": "~1.0.2" } }, "sha512-o5Roy6tNG4SL/FOkCAN6RzjiakZS25RLYFrcMttJqbdd8BWrnA+fGz57iN5Pb06pvBGvl5gQ0B48dJlslXvoTg=="], - "readable-stream/buffer/ieee754": ["ieee754@1.2.1", "", {}, "sha512-dcyqhDvX1C46lXZcVqCpK+FtMRQVdIMN6/Df5js2zouUsqG7I6sFxitIC+7KYK29KdXOLHdu9zL4sFnoVQnqaA=="], "readdir-glob/minimatch/brace-expansion": ["brace-expansion@2.1.0", "", { "dependencies": { "balanced-match": "^1.0.0" } }, "sha512-TN1kCZAgdgweJhWWpgKYrQaMNHcDULHkWwQIspdtjV4Y5aurRdZpjAqn6yX3FPqTA9ngHCc4hJxMAMgGfve85w=="], @@ -5406,8 +5430,6 @@ "string-width-cjs/strip-ansi/ansi-regex": ["ansi-regex@5.0.1", "", {}, "sha512-quJQXlTSUGL2LH9SUXo8VwsY4soanhgo6LNSm84E1LBcE8s3O0wpdiRzyR9z/ZZJMlMWv37qOOb9pdJlMUEKFQ=="], - "supertap/js-yaml/argparse": ["argparse@1.0.10", "", { "dependencies": { "sprintf-js": "~1.0.2" } }, "sha512-o5Roy6tNG4SL/FOkCAN6RzjiakZS25RLYFrcMttJqbdd8BWrnA+fGz57iN5Pb06pvBGvl5gQ0B48dJlslXvoTg=="], - "table/string-width/emoji-regex": ["emoji-regex@8.0.0", "", {}, "sha512-MSjYzcWNOA0ewAHpz0MxpYFvwg6yjy1NG3xteoqz644VCo/RPgnr1/GGt+ic3iJTzQ8Eu3TdM14SawnVUmGE6A=="], "table/strip-ansi/ansi-regex": ["ansi-regex@5.0.1", "", {}, "sha512-quJQXlTSUGL2LH9SUXo8VwsY4soanhgo6LNSm84E1LBcE8s3O0wpdiRzyR9z/ZZJMlMWv37qOOb9pdJlMUEKFQ=="], @@ -5556,8 +5578,6 @@ "friendly-words/express/type-is/mime-types": ["mime-types@2.1.35", "", { "dependencies": { "mime-db": "1.52.0" } }, "sha512-ZDY+bPm5zTTF+YpCrAU9nK0UgICYPT0QtT1NZWFv4s++TNkcgVaT0g6+4R2uI4MjQjzysHB1zxuWL50hzaeXiw=="], - "gray-matter/js-yaml/argparse/sprintf-js": ["sprintf-js@1.0.3", "", {}, "sha512-D9cPgkvLlV3t3IzL0D0YLvGA9Ahk4PcvVwUbN0dSGr1aP0Nrt4AEnTUbuGvquEC0mA64Gqt1fzirlRs5ibXx8g=="], - "mocha/glob/jackspeak/@isaacs/cliui": ["@isaacs/cliui@8.0.2", "", { "dependencies": { "string-width": "^5.1.2", "string-width-cjs": "npm:string-width@^4.2.0", "strip-ansi": "^7.0.1", "strip-ansi-cjs": "npm:strip-ansi@^6.0.1", "wrap-ansi": "^8.1.0", "wrap-ansi-cjs": "npm:wrap-ansi@^7.0.0" } }, "sha512-O8jcjabXaleOG9DQ0+ARXWZBTfnP4WNAqzuiJK7ll44AmxGKv/J2M4TPjxjY3znBCfvBXFzucm1twdyFybFqEA=="], "mocha/glob/path-scurry/lru-cache": ["lru-cache@10.4.3", "", {}, "sha512-JNAzZcXrCt42VGLuYz0zfAzDfAvJWW6AfYlDBQyDV5DClI2m5sAmK+OIO7s59XfsRsWHp02jAJrRadPRGTt6SQ=="], @@ -5590,12 +5610,8 @@ "qrcode/yargs/yargs-parser/camelcase": ["camelcase@5.3.1", "", {}, "sha512-L28STB170nwWS63UjtlEOE3dldQApaJXZkOI1uMFfzf3rRuPegHaHesyee+YxQ+W6SvRDQV6UrdOdRiR153wJg=="], - "read-yaml-file/js-yaml/argparse/sprintf-js": ["sprintf-js@1.0.3", "", {}, "sha512-D9cPgkvLlV3t3IzL0D0YLvGA9Ahk4PcvVwUbN0dSGr1aP0Nrt4AEnTUbuGvquEC0mA64Gqt1fzirlRs5ibXx8g=="], - "readdir-glob/minimatch/brace-expansion/balanced-match": ["balanced-match@1.0.2", "", {}, "sha512-3oSeUO0TMV67hN1AmbXsK4yaqU7tjiHlbxRDZOpH0KW9+CeX4bRAaX0Anxt0tx2MrpRpWwQaPwIlISEJhYU5Pw=="], - "supertap/js-yaml/argparse/sprintf-js": ["sprintf-js@1.0.3", "", {}, "sha512-D9cPgkvLlV3t3IzL0D0YLvGA9Ahk4PcvVwUbN0dSGr1aP0Nrt4AEnTUbuGvquEC0mA64Gqt1fzirlRs5ibXx8g=="], - "tar-fs/tar-stream/bl/buffer": ["buffer@5.7.1", "", { "dependencies": { "base64-js": "^1.3.1", "ieee754": "^1.1.13" } }, "sha512-EHcyIPBQ4BSGlvjB16k5KgAJ27CIsHY/2JBmCRReo48y9rQ3MaUzWX3KVlBa4U7MyX02HdVj0K7C3WaB3ju7FQ=="], "test-exclude/glob/jackspeak/@isaacs/cliui": ["@isaacs/cliui@8.0.2", "", { "dependencies": { "string-width": "^5.1.2", "string-width-cjs": "npm:string-width@^4.2.0", "strip-ansi": "^7.0.1", "strip-ansi-cjs": "npm:strip-ansi@^6.0.1", "wrap-ansi": "^8.1.0", "wrap-ansi-cjs": "npm:wrap-ansi@^7.0.0" } }, "sha512-O8jcjabXaleOG9DQ0+ARXWZBTfnP4WNAqzuiJK7ll44AmxGKv/J2M4TPjxjY3znBCfvBXFzucm1twdyFybFqEA=="], diff --git a/package.json b/package.json index 4f205b19d71..8c158e35a51 100644 --- a/package.json +++ b/package.json @@ -147,7 +147,8 @@ "patchedDependencies": { "@npmcli/agent@4.0.0": "patches/@npmcli%2Fagent@4.0.0.patch", "@standard-community/standard-openapi@0.2.9": "patches/@standard-community%2Fstandard-openapi@0.2.9.patch", - "solid-js@1.9.10": "patches/solid-js@1.9.10.patch" + "solid-js@1.9.10": "patches/solid-js@1.9.10.patch", + "mammoth@1.12.0": "patches/mammoth@1.12.0.patch" }, "version": "7.3.16", "peerDependencies": {} diff --git a/packages/opencode/package.json b/packages/opencode/package.json index 89e79ca78b5..2c67e59e704 100644 --- a/packages/opencode/package.json +++ b/packages/opencode/package.json @@ -166,6 +166,7 @@ "ignore": "7.0.5", "immer": "11.1.4", "jsonc-parser": "3.3.1", + "mammoth": "1.12.0", "mime-types": "3.0.2", "minimatch": "10.2.5", "npm-package-arg": "13.0.2", diff --git a/packages/opencode/src/kilocode/tool/read-docx.ts b/packages/opencode/src/kilocode/tool/read-docx.ts new file mode 100644 index 00000000000..544ef3317d2 --- /dev/null +++ b/packages/opencode/src/kilocode/tool/read-docx.ts @@ -0,0 +1,15 @@ +import mammoth from "mammoth" +import * as path from "path" +import { Readable } from "stream" + +export function accepts(filepath: string) { + return path.extname(filepath).toLowerCase() === ".docx" +} + +export async function open(filepath: string) { + const result = await mammoth.extractRawText({ path: filepath }).catch((err: unknown) => { + const message = err instanceof Error ? err.message : String(err) + throw new Error(`Failed to extract text from DOCX file: ${filepath}\n${message}`, { cause: err }) + }) + return Readable.from([result.value]) +} diff --git a/packages/opencode/src/tool/read.ts b/packages/opencode/src/tool/read.ts index 551e3744553..67ad87e2bc9 100644 --- a/packages/opencode/src/tool/read.ts +++ b/packages/opencode/src/tool/read.ts @@ -15,6 +15,7 @@ import { isPdfAttachment, sniffAttachmentMime } from "@/util/media" // kilocode_change start import * as Encoding from "../kilocode/encoding" import * as TextStream from "../kilocode/text-stream" +import * as Docx from "../kilocode/tool/read-docx" // kilocode_change end const DEFAULT_READ_LIMIT = 2000 @@ -300,9 +301,11 @@ export const ReadTool = Tool.define( } } - if (isBinaryFile(filepath, sample)) { + // kilocode_change start - extract DOCX as text + if (!Docx.accepts(filepath) && isBinaryFile(filepath, sample)) { return yield* Effect.fail(new Error(`Cannot read binary file: ${filepath}`)) } + // kilocode_change end const file = yield* Effect.promise(() => lines(filepath, { limit: params.limit ?? DEFAULT_READ_LIMIT, offset: params.offset || 1 }), @@ -358,6 +361,7 @@ export const ReadTool = Tool.define( // routed through TextStream.withFallback so non-UTF-8 files are decoded via // iconv. The body otherwise matches upstream. export async function lines(filepath: string, opts: { limit: number; offset: number }) { + if (Docx.accepts(filepath)) return readLines(await Docx.open(filepath), opts) // kilocode_change return TextStream.withFallback(filepath, (stream) => readLines(stream, opts)) } diff --git a/packages/opencode/test/kilocode/read-docx.test.ts b/packages/opencode/test/kilocode/read-docx.test.ts new file mode 100644 index 00000000000..e932df83f39 --- /dev/null +++ b/packages/opencode/test/kilocode/read-docx.test.ts @@ -0,0 +1,185 @@ +import { describe, expect } from "bun:test" +import { Cause, Effect, Exit, Layer } from "effect" +import path from "path" +import { TextReader, Uint8ArrayWriter, ZipWriter } from "@zip.js/zip.js" +import { Agent } from "../../src/agent/agent" +import * as CrossSpawnSpawner from "@opencode-ai/core/cross-spawn-spawner" +import { AppFileSystem } from "@opencode-ai/core/filesystem" +import { LSP } from "../../src/lsp/lsp" +import { Instruction } from "../../src/session/instruction" +import { MessageID, SessionID } from "../../src/session/schema" +import { ReadTool } from "../../src/tool/read" +import { Tool } from "../../src/tool/tool" +import { Truncate } from "../../src/tool/truncate" +import { provideInstance, tmpdirScoped } from "../fixture/fixture" +import { testEffect } from "../lib/effect" + +const ctx: Tool.Context = { + sessionID: SessionID.make("ses_test-docx"), + messageID: MessageID.make(""), + callID: "", + agent: "code", + abort: AbortSignal.any([]), + messages: [], + metadata: () => Effect.void, + ask: () => Effect.void, +} + +const expanded: Tool.Context = { ...ctx, extra: { includeDirectoryFiles: true } } + +const it = testEffect( + Layer.mergeAll( + Agent.defaultLayer, + AppFileSystem.defaultLayer, + CrossSpawnSpawner.defaultLayer, + Instruction.defaultLayer, + LSP.defaultLayer, + Truncate.defaultLayer, + ), +) + +const init = Effect.fn("ReadDocxTest.init")(function* () { + const info = yield* ReadTool + return yield* Tool.init(info) +}) + +const run = Effect.fn("ReadDocxTest.run")(function* ( + args: Tool.InferParameters, + next: Tool.Context = ctx, +) { + const tool = yield* init() + return yield* tool.execute(args, next) +}) + +const exec = Effect.fn("ReadDocxTest.exec")(function* ( + dir: string, + args: Tool.InferParameters, + next: Tool.Context = ctx, +) { + return yield* provideInstance(dir)(run(args, next)) +}) + +const fail = Effect.fn("ReadDocxTest.fail")(function* (dir: string, args: Tool.InferParameters) { + const exit = yield* exec(dir, args).pipe(Effect.exit) + if (Exit.isFailure(exit)) { + const err = Cause.squash(exit.cause) + return err instanceof Error ? err : new Error(String(err)) + } + throw new Error("expected read to fail") +}) + +const put = Effect.fn("ReadDocxTest.put")(function* (filepath: string, content: string | Uint8Array) { + const fs = yield* AppFileSystem.Service + yield* fs.writeWithDirs(filepath, content) +}) + +const document = async (paragraphs: string[]) => { + const writer = new ZipWriter(new Uint8ArrayWriter()) + await writer.add( + "[Content_Types].xml", + new TextReader( + '' + + '' + + '' + + '' + + '' + + "", + ), + ) + await writer.add( + "_rels/.rels", + new TextReader( + '' + + '' + + '' + + "", + ), + ) + await writer.add( + "word/document.xml", + new TextReader( + '' + + '' + + paragraphs.map((text) => `${text}`).join("") + + "", + ), + ) + return writer.close() +} + +describe("kilocode DOCX reads", () => { + it.live("extracts paragraph text from .docx and .DOCX files", () => + Effect.gen(function* () { + const dir = yield* tmpdirScoped() + const bytes = yield* Effect.promise(() => document(["First paragraph", "Second paragraph"])) + + for (const ext of ["docx", "DOCX"]) { + const filepath = path.join(dir, `sample.${ext}`) + yield* put(filepath, bytes) + const result = yield* exec(dir, { filePath: filepath }) + + expect(result.output).toContain("1: First paragraph") + expect(result.output).toContain("Second paragraph") + expect(result.attachments).toBeUndefined() + } + }), + ) + + it.live("applies normal read pagination to extracted text", () => + Effect.gen(function* () { + const dir = yield* tmpdirScoped() + const filepath = path.join(dir, "paged.docx") + yield* put(filepath, yield* Effect.promise(() => document(["First paragraph", "Second paragraph"]))) + + const result = yield* exec(dir, { filePath: filepath, limit: 1 }) + + expect(result.output).toContain("1: First paragraph") + expect(result.output).not.toContain("Second paragraph") + expect(result.output).toContain("Use offset=2") + expect(result.metadata.truncated).toBe(true) + }), + ) + + it.live("fails clearly for malformed DOCX files", () => + Effect.gen(function* () { + const dir = yield* tmpdirScoped() + const filepath = path.join(dir, "invalid.docx") + yield* put(filepath, new Uint8Array([0x50, 0x4b, 0x03, 0x04])) + + const err = yield* fail(dir, { filePath: filepath }) + + expect(err.message).toContain("Failed to extract text from DOCX file") + expect(err.message).toContain(filepath) + }), + ) + + it.live("does not expand DOCX content in directory reads", () => + Effect.gen(function* () { + const dir = yield* tmpdirScoped() + const folder = path.join(dir, "folder") + yield* put(path.join(folder, "sample.docx"), yield* Effect.promise(() => document(["Hidden paragraph"]))) + + const result = yield* exec(dir, { filePath: folder }, expanded) + + expect(result.output).toContain("sample.docx") + expect(result.output).not.toContain("Hidden paragraph") + }), + ) + + it.live("preserves PDF attachments and rejects unsupported binary files", () => + Effect.gen(function* () { + const dir = yield* tmpdirScoped() + const pdf = path.join(dir, "sample.pdf") + const doc = path.join(dir, "sample.doc") + yield* put(pdf, "%PDF-1.7\nfixture") + yield* put(doc, new Uint8Array([0x00, 0x01, 0x02])) + + const result = yield* exec(dir, { filePath: pdf }) + const err = yield* fail(dir, { filePath: doc }) + + expect(result.output).toBe("PDF read successfully") + expect(result.attachments?.[0].mime).toBe("application/pdf") + expect(err.message).toContain("Cannot read binary file") + }), + ) +}) diff --git a/patches/mammoth@1.12.0.patch b/patches/mammoth@1.12.0.patch new file mode 100644 index 00000000000..351cff886c2 --- /dev/null +++ b/patches/mammoth@1.12.0.patch @@ -0,0 +1,33 @@ +diff --git a/lib/xml/xmldom.js b/lib/xml/xmldom.js +index 752c353f0c97f86280c96984fe963c8b6f6d0c6c..b75bd10746eb035276cfded6d624e2cbda3c3c6e 100644 +--- a/lib/xml/xmldom.js ++++ b/lib/xml/xmldom.js +@@ -2,20 +2,22 @@ var xmldom = require("@xmldom/xmldom"); + var dom = require("@xmldom/xmldom/lib/dom"); + + function parseFromString(string) { +- var error = null; ++ var fatalError = null; + + var domParser = new xmldom.DOMParser({ +- errorHandler: function(level, message) { +- error = {level: level, message: message}; ++ onError: function(level, message) { ++ if (level === "fatalError") { ++ fatalError = message; ++ } + } + }); + +- var document = domParser.parseFromString(string); ++ var document = domParser.parseFromString(string, "text/xml"); + +- if (error === null) { ++ if (fatalError === null) { + return document; + } else { +- throw new Error(error.level + ": " + error.message); ++ throw new Error("fatalError: " + fatalError); + } + } +