mirror of
https://github.com/anomalyco/opencode.git
synced 2026-08-07 17:49:53 -04:00
Compare commits
1 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 Kit Langton
|
227598c504 |
@@ -4,13 +4,6 @@
|
||||
- The default branch in this repo is `dev`.
|
||||
- Local `main` ref may not exist; use `dev` or `origin/dev` for diffs.
|
||||
|
||||
## Live V2 TUI Testing
|
||||
|
||||
- Run `bun run dev:live` from a development worktree to test its TUI against the currently elected `opencode2` background server and live sessions.
|
||||
- Pass a directory after the script when needed, for example `bun run dev:live /path/to/project`.
|
||||
- The script discovers the server with `opencode2 service status`, injects its private local credential from `opencode2 service get password`, and uses the `next` TUI storage channel so tabs and other client-local state match the installed client.
|
||||
- Prefer `dev:live` over plain `bun run dev` for this workflow. An implicit managed-service connection may replace the live server when the worktree client version differs; explicit `--server` warns and continues without replacing it.
|
||||
|
||||
## Branch Names
|
||||
|
||||
Use a short branch name of at most three words, separated by hyphens. Do not use slashes or type prefixes such as `feat/` or `fix/`.
|
||||
|
||||
@@ -285,9 +285,13 @@
|
||||
"name": "@opencode-ai/console-function",
|
||||
"version": "1.18.8",
|
||||
"dependencies": {
|
||||
"@ai-sdk/anthropic": "3.0.82",
|
||||
"@ai-sdk/openai": "3.0.48",
|
||||
"@ai-sdk/openai-compatible": "2.0.37",
|
||||
"@openauthjs/openauth": "0.0.0-20250322224806",
|
||||
"@opencode-ai/console-core": "workspace:*",
|
||||
"@opencode-ai/console-resource": "workspace:*",
|
||||
"ai": "catalog:",
|
||||
"zod": "catalog:",
|
||||
},
|
||||
"devDependencies": {
|
||||
@@ -295,6 +299,7 @@
|
||||
"@tsconfig/node22": "22.0.2",
|
||||
"@types/node": "catalog:",
|
||||
"@typescript/native-preview": "catalog:",
|
||||
"openai": "5.11.0",
|
||||
"typescript": "catalog:",
|
||||
},
|
||||
},
|
||||
@@ -357,15 +362,18 @@
|
||||
"@ai-sdk/cohere": "3.0.27",
|
||||
"@ai-sdk/deepinfra": "2.0.41",
|
||||
"@ai-sdk/gateway": "3.0.104",
|
||||
"@ai-sdk/google": "3.0.73",
|
||||
"@ai-sdk/google-vertex": "4.0.128",
|
||||
"@ai-sdk/groq": "3.0.31",
|
||||
"@ai-sdk/mistral": "3.0.51",
|
||||
"@ai-sdk/openai": "3.0.84",
|
||||
"@ai-sdk/openai-compatible": "2.0.41",
|
||||
"@ai-sdk/perplexity": "3.0.26",
|
||||
"@ai-sdk/provider": "3.0.8",
|
||||
"@ai-sdk/provider-utils": "4.0.23",
|
||||
"@ai-sdk/togetherai": "2.0.41",
|
||||
"@ai-sdk/vercel": "2.0.39",
|
||||
"@ai-sdk/xai": "3.0.102",
|
||||
"@aws-sdk/credential-providers": "3.1057.0",
|
||||
"@effect/platform-node": "catalog:",
|
||||
"@effect/sql-sqlite-bun": "catalog:",
|
||||
@@ -376,9 +384,11 @@
|
||||
"@opencode-ai/ai": "workspace:*",
|
||||
"@opencode-ai/codemode": "workspace:*",
|
||||
"@opencode-ai/effect-drizzle-sqlite": "workspace:*",
|
||||
"@opencode-ai/effect-sqlite-node": "workspace:*",
|
||||
"@opencode-ai/plugin": "workspace:*",
|
||||
"@opencode-ai/schema": "workspace:*",
|
||||
"@opencode-ai/util": "workspace:*",
|
||||
"@openrouter/ai-sdk-provider": "2.9.0",
|
||||
"@parcel/watcher": "2.5.1",
|
||||
"@silvia-odwyer/photon-node": "0.3.4",
|
||||
"@standard-schema/spec": "catalog:",
|
||||
@@ -395,6 +405,7 @@
|
||||
"ignore": "7.0.5",
|
||||
"immer": "11.1.4",
|
||||
"jsonc-parser": "3.3.1",
|
||||
"semver": "^7.6.3",
|
||||
"tree-sitter-bash": "0.25.0",
|
||||
"tree-sitter-powershell": "0.25.10",
|
||||
"turndown": "7.2.0",
|
||||
@@ -416,6 +427,7 @@
|
||||
"@tsconfig/bun": "catalog:",
|
||||
"@types/bun": "catalog:",
|
||||
"@types/node": "catalog:",
|
||||
"@types/semver": "catalog:",
|
||||
"@types/turndown": "5.0.5",
|
||||
"@types/which": "3.0.4",
|
||||
"drizzle-kit": "catalog:",
|
||||
@@ -903,6 +915,7 @@
|
||||
"@opentui/solid": "catalog:",
|
||||
"@solid-primitives/event-bus": "1.1.2",
|
||||
"clipboardy": "4.0.0",
|
||||
"diff": "catalog:",
|
||||
"effect": "catalog:",
|
||||
"fuzzysort": "catalog:",
|
||||
"get-east-asian-width": "catalog:",
|
||||
@@ -1029,6 +1042,7 @@
|
||||
"@shikijs/transformers": "3.20.0",
|
||||
"@solid-primitives/resize-observer": "2.1.5",
|
||||
"@types/luxon": "catalog:",
|
||||
"ai": "catalog:",
|
||||
"astro": "5.7.13",
|
||||
"diff": "catalog:",
|
||||
"js-base64": "3.7.7",
|
||||
@@ -1074,16 +1088,17 @@
|
||||
"tree-sitter-bash",
|
||||
],
|
||||
"patchedDependencies": {
|
||||
"solid-js@1.9.10": "patches/solid-js@1.9.10.patch",
|
||||
"@pierre/trees@1.0.0-beta.4": "patches/@pierre%2Ftrees@1.0.0-beta.4.patch",
|
||||
"effect@4.0.0-beta.101": "patches/effect@4.0.0-beta.101.patch",
|
||||
"@ai-sdk/xai@3.0.102": "patches/@ai-sdk%2Fxai@3.0.102.patch",
|
||||
"@modelcontextprotocol/sdk@1.29.0": "patches/@modelcontextprotocol%2Fsdk@1.29.0.patch",
|
||||
"@tanstack/virtual-core@3.17.3": "patches/@tanstack%2Fvirtual-core@3.17.3.patch",
|
||||
"@ai-sdk/google@3.0.73": "patches/@ai-sdk%2Fgoogle@3.0.73.patch",
|
||||
"@standard-community/standard-openapi@0.2.9": "patches/@standard-community%2Fstandard-openapi@0.2.9.patch",
|
||||
"@ai-sdk/mistral@3.0.51": "patches/@ai-sdk%2Fmistral@3.0.51.patch",
|
||||
"@npmcli/agent@4.0.2": "patches/@npmcli%2Fagent@4.0.2.patch",
|
||||
"@silvia-odwyer/photon-node@0.3.4": "patches/@silvia-odwyer%2Fphoton-node@0.3.4.patch",
|
||||
"solid-js@1.9.10": "patches/solid-js@1.9.10.patch",
|
||||
"@ai-sdk/google@3.0.73": "patches/@ai-sdk%2Fgoogle@3.0.73.patch",
|
||||
},
|
||||
"overrides": {
|
||||
"@opentui/core": "catalog:",
|
||||
@@ -1209,9 +1224,9 @@
|
||||
|
||||
"@ai-sdk/mistral": ["@ai-sdk/mistral@3.0.51", "", { "dependencies": { "@ai-sdk/provider": "3.0.14", "@ai-sdk/provider-utils": "4.0.40" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-83eXY6p0lUFhSuMvNDmTKDuMciK5XDAWDlNh5c0L80tKjmtCFRItA1MZHp4IKe1r7eK8Rb5nN7qtxqMLUFRIRw=="],
|
||||
|
||||
"@ai-sdk/openai": ["@ai-sdk/openai@3.0.67", "", { "dependencies": { "@ai-sdk/provider": "3.0.10", "@ai-sdk/provider-utils": "4.0.27" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-oAiGC9eWG7IgtdsdS74bOCnAAHarAfTJhWN9x5INwnWPekL802AvF+0I5DvLzIF1MIRmNw4N8mPSL/GUVbX9Mw=="],
|
||||
"@ai-sdk/openai": ["@ai-sdk/openai@3.0.48", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@ai-sdk/provider-utils": "4.0.21" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-ALmj/53EXpcRqMbGpPJPP4UOSWw0q4VGpnDo7YctvsynjkrKDmoneDG/1a7VQnSPYHnJp6tTRMf5ZdxZ5whulg=="],
|
||||
|
||||
"@ai-sdk/openai-compatible": ["@ai-sdk/openai-compatible@2.0.41", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@ai-sdk/provider-utils": "4.0.23" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-kNAGINk71AlOXx10Dq/PXw4t/9XjdK8uxfpVElRwtSFMdeSiLVt58p9TPx4/FJD+hxZuVhvxYj9r42osxWq79g=="],
|
||||
"@ai-sdk/openai-compatible": ["@ai-sdk/openai-compatible@2.0.37", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@ai-sdk/provider-utils": "4.0.21" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-+POSFVcgiu47BK64dhsI6OpcDC0/VAE2ZSaXdXGNNhpC/ava++uSRJYks0k2bpfY0wwCTgpAWZsXn/dG2Yppiw=="],
|
||||
|
||||
"@ai-sdk/perplexity": ["@ai-sdk/perplexity@3.0.26", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@ai-sdk/provider-utils": "4.0.21" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-dXzrVsLR5f6tr+U04jq4AXoRroGFBTvODnLgss0SWbzNjGGQg3XqtQ9j7rCLo6o8qbYGuAHvqUrIpUCuiscuFg=="],
|
||||
|
||||
@@ -4933,7 +4948,7 @@
|
||||
|
||||
"open": ["open@10.1.2", "", { "dependencies": { "default-browser": "^5.2.1", "define-lazy-prop": "^3.0.0", "is-inside-container": "^1.0.0", "is-wsl": "^3.1.0" } }, "sha512-cxN6aIDPz6rm8hbebcP7vrQNhvRcveZoJU72Y7vskh4oIm+BZwBECnx5nTmrlres1Qapvx27Qo1Auukpf8PKXw=="],
|
||||
|
||||
"openai": ["openai@6.49.0", "", { "peerDependencies": { "@aws-sdk/credential-provider-node": ">=3.972.0 <4", "@smithy/hash-node": ">=4.3.0 <5", "@smithy/signature-v4": ">=5.4.0 <6", "ws": "^8.18.0", "zod": "^3.25 || ^4.0" }, "optionalPeers": ["@aws-sdk/credential-provider-node", "@smithy/hash-node", "@smithy/signature-v4", "ws", "zod"] }, "sha512-aYCc0C6L864eR6WSYIwQGyXriw/nIyZx0ObvhzOEVuk0zoBDpynjSbrionWI7q65B5H8jJX0DXR9snEzM6bfPg=="],
|
||||
"openai": ["openai@5.11.0", "", { "peerDependencies": { "ws": "^8.18.0", "zod": "^3.23.8" }, "optionalPeers": ["ws", "zod"], "bin": { "openai": "bin/cli" } }, "sha512-+AuTc5pVjlnTuA9zvn8rA/k+1RluPIx9AD4eDcnutv6JNwHHZxIhkFy+tmMKCvmMFDQzfA/r1ujvPWB19DQkYg=="],
|
||||
|
||||
"openapi-types": ["openapi-types@12.1.3", "", {}, "sha512-N4YtSYJqghVu4iek2ZUvcN/0aqH1kRDuNqzcycDxhOUpg7GdvLa2F3DgS6yBNhInhv2r/6I0Flkn7CqL8+nIcw=="],
|
||||
|
||||
@@ -5951,8 +5966,12 @@
|
||||
|
||||
"@actions/http-client/undici": ["undici@6.28.0", "", {}, "sha512-LIY910g9TI13YS95lrMFrs8Rm/u/irgHeTWoKCoteeJ04CUJ92eEfj0rVn+7VKMPBpUPiUoBKfhNyLI23EE/KA=="],
|
||||
|
||||
"@ai-sdk/alibaba/@ai-sdk/openai-compatible": ["@ai-sdk/openai-compatible@2.0.41", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@ai-sdk/provider-utils": "4.0.23" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-kNAGINk71AlOXx10Dq/PXw4t/9XjdK8uxfpVElRwtSFMdeSiLVt58p9TPx4/FJD+hxZuVhvxYj9r42osxWq79g=="],
|
||||
|
||||
"@ai-sdk/amazon-bedrock/@ai-sdk/anthropic": ["@ai-sdk/anthropic@3.0.81", "", { "dependencies": { "@ai-sdk/provider": "3.0.10", "@ai-sdk/provider-utils": "4.0.27" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-B1JDd9Ugq9R5AgIaW3674lhGCMMYJcPUxnrZh8fzbGojgg4QvHFRv6eZahGQAUsmGHbcf74G9bdSBDLWQGY2GA=="],
|
||||
|
||||
"@ai-sdk/amazon-bedrock/@ai-sdk/openai": ["@ai-sdk/openai@3.0.67", "", { "dependencies": { "@ai-sdk/provider": "3.0.10", "@ai-sdk/provider-utils": "4.0.27" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-oAiGC9eWG7IgtdsdS74bOCnAAHarAfTJhWN9x5INwnWPekL802AvF+0I5DvLzIF1MIRmNw4N8mPSL/GUVbX9Mw=="],
|
||||
|
||||
"@ai-sdk/amazon-bedrock/@ai-sdk/provider": ["@ai-sdk/provider@3.0.10", "", { "dependencies": { "json-schema": "^0.4.0" } }, "sha512-Q3BZ27qfpYqnCYGvE3vt+Qi6LGOF9R5Nmzn+9JoM1lCRsD9mYaIhfJLkSunN48nfGXJ6n+XNV0J/XVpqGQl7Dw=="],
|
||||
|
||||
"@ai-sdk/amazon-bedrock/@ai-sdk/provider-utils": ["@ai-sdk/provider-utils@4.0.27", "", { "dependencies": { "@ai-sdk/provider": "3.0.10", "@standard-schema/spec": "^1.1.0", "eventsource-parser": "^3.0.8" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-ubkAJ+xODouwtmN1tYlvTPphH1hPOBfZaEQe8U7skGvFAnIRs9PPpsq57bC2+Ky/MB4yzhd6YOsxTAx9sGpazw=="],
|
||||
@@ -5967,8 +5986,6 @@
|
||||
|
||||
"@ai-sdk/azure/@ai-sdk/provider-utils": ["@ai-sdk/provider-utils@4.0.38", "", { "dependencies": { "@ai-sdk/provider": "3.0.14", "@standard-schema/spec": "^1.1.0", "eventsource-parser": "^3.0.8" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-/HHGmtKllqjg1OLc023v9w9kK3laW7Z6TzfZukYQWCsGBbzB9p60zTvvpXFVcs44NZBVXL3viOa1HRKUbeee8g=="],
|
||||
|
||||
"@ai-sdk/cerebras/@ai-sdk/openai-compatible": ["@ai-sdk/openai-compatible@2.0.37", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@ai-sdk/provider-utils": "4.0.21" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-+POSFVcgiu47BK64dhsI6OpcDC0/VAE2ZSaXdXGNNhpC/ava++uSRJYks0k2bpfY0wwCTgpAWZsXn/dG2Yppiw=="],
|
||||
|
||||
"@ai-sdk/cerebras/@ai-sdk/provider-utils": ["@ai-sdk/provider-utils@4.0.21", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@standard-schema/spec": "^1.1.0", "eventsource-parser": "^3.0.6" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-MtFUYI1/8mgDvRmaBDjbLJPFFrMG777AvSgyIFQtZHIMzm88R/12vYBBpnk7pfiWLFE1DSZzY4WDYzGbKAcmiw=="],
|
||||
|
||||
"@ai-sdk/cohere/@ai-sdk/provider-utils": ["@ai-sdk/provider-utils@4.0.21", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@standard-schema/spec": "^1.1.0", "eventsource-parser": "^3.0.6" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-MtFUYI1/8mgDvRmaBDjbLJPFFrMG777AvSgyIFQtZHIMzm88R/12vYBBpnk7pfiWLFE1DSZzY4WDYzGbKAcmiw=="],
|
||||
@@ -5977,8 +5994,6 @@
|
||||
|
||||
"@ai-sdk/deepgram/@ai-sdk/provider-utils": ["@ai-sdk/provider-utils@4.0.40", "", { "dependencies": { "@ai-sdk/provider": "3.0.14", "@standard-schema/spec": "^1.1.0", "eventsource-parser": "^3.0.8" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-OL5IrpUm9Y8Dwy+w/vvFwPotS6m52O9W0op2oXgXdCROMJIBalBI0oro6OIBYkPxvm5Xg02GSkoQN25RlR0bnw=="],
|
||||
|
||||
"@ai-sdk/deepinfra/@ai-sdk/openai-compatible": ["@ai-sdk/openai-compatible@2.0.37", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@ai-sdk/provider-utils": "4.0.21" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-+POSFVcgiu47BK64dhsI6OpcDC0/VAE2ZSaXdXGNNhpC/ava++uSRJYks0k2bpfY0wwCTgpAWZsXn/dG2Yppiw=="],
|
||||
|
||||
"@ai-sdk/deepinfra/@ai-sdk/provider-utils": ["@ai-sdk/provider-utils@4.0.21", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@standard-schema/spec": "^1.1.0", "eventsource-parser": "^3.0.6" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-MtFUYI1/8mgDvRmaBDjbLJPFFrMG777AvSgyIFQtZHIMzm88R/12vYBBpnk7pfiWLFE1DSZzY4WDYzGbKAcmiw=="],
|
||||
|
||||
"@ai-sdk/deepseek/@ai-sdk/provider": ["@ai-sdk/provider@3.0.14", "", { "dependencies": { "json-schema": "^0.4.0" } }, "sha512-5X1k57JBJ4H7H1QjX7CnJYAB1I19r/trVZTMcSms7/kLNZ8RaU4Nt2agcwZzv82Hfx6Q7/TOLU7agAKeFfc8cA=="],
|
||||
@@ -6013,18 +6028,14 @@
|
||||
|
||||
"@ai-sdk/mistral/@ai-sdk/provider-utils": ["@ai-sdk/provider-utils@4.0.40", "", { "dependencies": { "@ai-sdk/provider": "3.0.14", "@standard-schema/spec": "^1.1.0", "eventsource-parser": "^3.0.8" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-OL5IrpUm9Y8Dwy+w/vvFwPotS6m52O9W0op2oXgXdCROMJIBalBI0oro6OIBYkPxvm5Xg02GSkoQN25RlR0bnw=="],
|
||||
|
||||
"@ai-sdk/openai/@ai-sdk/provider": ["@ai-sdk/provider@3.0.10", "", { "dependencies": { "json-schema": "^0.4.0" } }, "sha512-Q3BZ27qfpYqnCYGvE3vt+Qi6LGOF9R5Nmzn+9JoM1lCRsD9mYaIhfJLkSunN48nfGXJ6n+XNV0J/XVpqGQl7Dw=="],
|
||||
"@ai-sdk/openai/@ai-sdk/provider-utils": ["@ai-sdk/provider-utils@4.0.21", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@standard-schema/spec": "^1.1.0", "eventsource-parser": "^3.0.6" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-MtFUYI1/8mgDvRmaBDjbLJPFFrMG777AvSgyIFQtZHIMzm88R/12vYBBpnk7pfiWLFE1DSZzY4WDYzGbKAcmiw=="],
|
||||
|
||||
"@ai-sdk/openai/@ai-sdk/provider-utils": ["@ai-sdk/provider-utils@4.0.27", "", { "dependencies": { "@ai-sdk/provider": "3.0.10", "@standard-schema/spec": "^1.1.0", "eventsource-parser": "^3.0.8" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-ubkAJ+xODouwtmN1tYlvTPphH1hPOBfZaEQe8U7skGvFAnIRs9PPpsq57bC2+Ky/MB4yzhd6YOsxTAx9sGpazw=="],
|
||||
"@ai-sdk/openai-compatible/@ai-sdk/provider-utils": ["@ai-sdk/provider-utils@4.0.21", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@standard-schema/spec": "^1.1.0", "eventsource-parser": "^3.0.6" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-MtFUYI1/8mgDvRmaBDjbLJPFFrMG777AvSgyIFQtZHIMzm88R/12vYBBpnk7pfiWLFE1DSZzY4WDYzGbKAcmiw=="],
|
||||
|
||||
"@ai-sdk/perplexity/@ai-sdk/provider-utils": ["@ai-sdk/provider-utils@4.0.21", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@standard-schema/spec": "^1.1.0", "eventsource-parser": "^3.0.6" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-MtFUYI1/8mgDvRmaBDjbLJPFFrMG777AvSgyIFQtZHIMzm88R/12vYBBpnk7pfiWLFE1DSZzY4WDYzGbKAcmiw=="],
|
||||
|
||||
"@ai-sdk/togetherai/@ai-sdk/openai-compatible": ["@ai-sdk/openai-compatible@2.0.37", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@ai-sdk/provider-utils": "4.0.21" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-+POSFVcgiu47BK64dhsI6OpcDC0/VAE2ZSaXdXGNNhpC/ava++uSRJYks0k2bpfY0wwCTgpAWZsXn/dG2Yppiw=="],
|
||||
|
||||
"@ai-sdk/togetherai/@ai-sdk/provider-utils": ["@ai-sdk/provider-utils@4.0.21", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@standard-schema/spec": "^1.1.0", "eventsource-parser": "^3.0.6" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-MtFUYI1/8mgDvRmaBDjbLJPFFrMG777AvSgyIFQtZHIMzm88R/12vYBBpnk7pfiWLFE1DSZzY4WDYzGbKAcmiw=="],
|
||||
|
||||
"@ai-sdk/vercel/@ai-sdk/openai-compatible": ["@ai-sdk/openai-compatible@2.0.37", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@ai-sdk/provider-utils": "4.0.21" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-+POSFVcgiu47BK64dhsI6OpcDC0/VAE2ZSaXdXGNNhpC/ava++uSRJYks0k2bpfY0wwCTgpAWZsXn/dG2Yppiw=="],
|
||||
|
||||
"@ai-sdk/vercel/@ai-sdk/provider-utils": ["@ai-sdk/provider-utils@4.0.21", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@standard-schema/spec": "^1.1.0", "eventsource-parser": "^3.0.6" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-MtFUYI1/8mgDvRmaBDjbLJPFFrMG777AvSgyIFQtZHIMzm88R/12vYBBpnk7pfiWLFE1DSZzY4WDYzGbKAcmiw=="],
|
||||
|
||||
"@ai-sdk/xai/@ai-sdk/openai-compatible": ["@ai-sdk/openai-compatible@2.0.56", "", { "dependencies": { "@ai-sdk/provider": "3.0.13", "@ai-sdk/provider-utils": "4.0.35" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-cQrN6OUn/jvsY3OdsU6Wn+ss7vp1iwIcakZKSlSRMnYqShBfyT7Qht+eqmgxs7w9ttrw6FAG6o11AiBs+iEsTA=="],
|
||||
@@ -6343,6 +6354,10 @@
|
||||
|
||||
"@opencode-ai/console-mail/@types/react": ["@types/react@18.0.25", "", { "dependencies": { "@types/prop-types": "*", "@types/scheduler": "*", "csstype": "^3.0.2" } }, "sha512-xD6c0KDT4m7n9uD4ZHi02lzskaiqcBxf4zi+tXZY98a04wvc0hi/TcCPC2FOESZi51Nd7tlUeOJY8RofL799/g=="],
|
||||
|
||||
"@opencode-ai/core/@ai-sdk/openai": ["@ai-sdk/openai@3.0.84", "", { "dependencies": { "@ai-sdk/provider": "3.0.14", "@ai-sdk/provider-utils": "4.0.38" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-cmgbeJL0bbY0yTJH4/AdmP5E7MjWRL9G8UdhIi0JlV/So03o82ORJofW8OzwCZPTORVQblFbpZXYGDcUd9NdUQ=="],
|
||||
|
||||
"@opencode-ai/core/@ai-sdk/openai-compatible": ["@ai-sdk/openai-compatible@2.0.41", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@ai-sdk/provider-utils": "4.0.23" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-kNAGINk71AlOXx10Dq/PXw4t/9XjdK8uxfpVElRwtSFMdeSiLVt58p9TPx4/FJD+hxZuVhvxYj9r42osxWq79g=="],
|
||||
|
||||
"@opencode-ai/desktop/@actions/artifact": ["@actions/artifact@4.0.0", "", { "dependencies": { "@actions/core": "^1.10.0", "@actions/github": "^6.0.1", "@actions/http-client": "^2.1.0", "@azure/core-http": "^3.0.5", "@azure/storage-blob": "^12.15.0", "@octokit/core": "^5.2.1", "@octokit/plugin-request-log": "^1.0.4", "@octokit/plugin-retry": "^3.0.9", "@octokit/request": "^8.4.1", "@octokit/request-error": "^5.1.1", "@protobuf-ts/plugin": "^2.2.3-alpha.1", "archiver": "^7.0.1", "jwt-decode": "^3.1.2", "unzip-stream": "^0.3.1" } }, "sha512-HCc2jMJRAfviGFAh0FsOR/jNfWhirxl7W6z8zDtttt0GltwxBLdEIjLiweOPFl9WbyJRW1VWnPUSAixJqcWUMQ=="],
|
||||
|
||||
"@opencode-ai/desktop/marked": ["marked@15.0.12", "", { "bin": { "marked": "bin/marked.js" } }, "sha512-8dD6FusOQSrpv9Z1rdNMdlSgQOIP880DHqnohobOmYLElGEqAL/JvxvuxZO16r4HtjTlfPRDC1hbvxC9dPN2nA=="],
|
||||
@@ -6567,8 +6582,6 @@
|
||||
|
||||
"babel-plugin-module-resolver/glob": ["glob@9.3.5", "", { "dependencies": { "fs.realpath": "^1.0.0", "minimatch": "^8.0.2", "minipass": "^4.2.4", "path-scurry": "^1.6.1" } }, "sha512-e1LleDykUz2Iu+MTYdkSsuWX8lvAjAcs0Xef0lNIu0S2wOAzuTxCJtcd9S3cijlwYF18EsU3rzb8jPVobxDh9Q=="],
|
||||
|
||||
"blume/@ai-sdk/openai-compatible": ["@ai-sdk/openai-compatible@2.0.37", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@ai-sdk/provider-utils": "4.0.21" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-+POSFVcgiu47BK64dhsI6OpcDC0/VAE2ZSaXdXGNNhpC/ava++uSRJYks0k2bpfY0wwCTgpAWZsXn/dG2Yppiw=="],
|
||||
|
||||
"blume/@astrojs/mdx": ["@astrojs/mdx@7.0.3", "", { "dependencies": { "@astrojs/internal-helpers": "0.10.1", "@astrojs/markdown-remark": "7.2.1", "@mdx-js/mdx": "^3.1.1", "acorn": "^8.16.0", "es-module-lexer": "^2.0.0", "estree-util-visit": "^2.0.0", "hast-util-to-html": "^9.0.5", "piccolore": "^0.1.3", "rehype-raw": "^7.0.0", "remark-gfm": "^4.0.1", "remark-smartypants": "^3.0.2", "source-map": "^0.7.6", "unist-util-visit": "^5.1.0", "vfile": "^6.0.3" }, "peerDependencies": { "@astrojs/markdown-satteri": "^0.3.1", "astro": "^7.0.0" }, "optionalPeers": ["@astrojs/markdown-satteri"] }, "sha512-RxyIwU0uFam5ftwqKOjpIdhnFxZ/kEikeimLyQy3eGXbHT8WgRGzzesOIHVU8+m9TY8ag5WVOyvV24/GyqPdPQ=="],
|
||||
|
||||
"blume/@clack/prompts": ["@clack/prompts@1.7.0", "", { "dependencies": { "@clack/core": "1.4.3", "fast-string-width": "^3.0.2", "fast-wrap-ansi": "^0.2.0", "sisteransi": "^1.0.5" } }, "sha512-y7/yvZ2TPAnR9+jnc00klvNNLkJiXFFrQA/hlLCcxA9a2A4zQIOimyFQ9XfwYKiGD1fb5GY8vbKIIgO8d5Tb2A=="],
|
||||
@@ -6705,6 +6718,8 @@
|
||||
|
||||
"gcp-metadata/google-logging-utils": ["google-logging-utils@1.1.3", "", {}, "sha512-eAmLkjDjAFCVXg7A1unxHsLf961m6y17QFqXqAXGj/gVkKFrEICfStRfwUlGNfeCEjNRa32JEWOUTlYXPyyKvA=="],
|
||||
|
||||
"gitlab-ai-provider/openai": ["openai@6.49.0", "", { "peerDependencies": { "@aws-sdk/credential-provider-node": ">=3.972.0 <4", "@smithy/hash-node": ">=4.3.0 <5", "@smithy/signature-v4": ">=5.4.0 <6", "ws": "^8.18.0", "zod": "^3.25 || ^4.0" }, "optionalPeers": ["@aws-sdk/credential-provider-node", "@smithy/hash-node", "@smithy/signature-v4", "ws", "zod"] }, "sha512-aYCc0C6L864eR6WSYIwQGyXriw/nIyZx0ObvhzOEVuk0zoBDpynjSbrionWI7q65B5H8jJX0DXR9snEzM6bfPg=="],
|
||||
|
||||
"gitlab-ai-provider/zod": ["zod@3.25.76", "", {}, "sha512-gzUt/qt81nXsFGKIFcC3YnfEAx5NkunCfnDlvuBSSFS02bcXu4Lmea0AFIUwbLWxWPx3d9p8S5QoaujKcNQxcQ=="],
|
||||
|
||||
"globby/ignore": ["ignore@5.3.2", "", {}, "sha512-hsBTNUqQTDwkWtcdYI2i06Y/nUBEsNEDJKjWdigLvegy8kDuJAS8uRlpkkcQpyEXL0Z/pjDy5HBmMjRCJ2gq+g=="],
|
||||
@@ -7369,6 +7384,10 @@
|
||||
|
||||
"@octokit/rest/@octokit/core/before-after-hook": ["before-after-hook@4.0.0", "", {}, "sha512-q6tR3RPqIB1pMiTRMFcZwuG5T8vwp+vUvEG0vuI6B+Rikh5BfPp2fQ82c925FOs+b0lcFQ8CFrL+KbilfZFhOQ=="],
|
||||
|
||||
"@opencode-ai/core/@ai-sdk/openai/@ai-sdk/provider": ["@ai-sdk/provider@3.0.14", "", { "dependencies": { "json-schema": "^0.4.0" } }, "sha512-5X1k57JBJ4H7H1QjX7CnJYAB1I19r/trVZTMcSms7/kLNZ8RaU4Nt2agcwZzv82Hfx6Q7/TOLU7agAKeFfc8cA=="],
|
||||
|
||||
"@opencode-ai/core/@ai-sdk/openai/@ai-sdk/provider-utils": ["@ai-sdk/provider-utils@4.0.38", "", { "dependencies": { "@ai-sdk/provider": "3.0.14", "@standard-schema/spec": "^1.1.0", "eventsource-parser": "^3.0.8" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-/HHGmtKllqjg1OLc023v9w9kK3laW7Z6TzfZukYQWCsGBbzB9p60zTvvpXFVcs44NZBVXL3viOa1HRKUbeee8g=="],
|
||||
|
||||
"@opencode-ai/desktop/@actions/artifact/@actions/core": ["@actions/core@1.11.1", "", { "dependencies": { "@actions/exec": "^1.1.1", "@actions/http-client": "^2.0.1" } }, "sha512-hXJCSrkwfA46Vd9Z3q4cpEpHB1rL5NG04+/rbqW9d3+CSvtB1tYe8UTpAlixa1vj0m/ULglfEK2UKxMGxCxv5A=="],
|
||||
|
||||
"@opencode-ai/desktop/@actions/artifact/@actions/http-client": ["@actions/http-client@2.2.3", "", { "dependencies": { "tunnel": "^0.0.6", "undici": "^5.25.4" } }, "sha512-mx8hyJi/hjFvbPokCg4uRd4ZX78t+YyRPtnKWwIl+RzNaVuFpQHfmlGVfsKEJN8LwTCvL+DfVgAM04XaHkm6bA=="],
|
||||
@@ -7605,8 +7624,6 @@
|
||||
|
||||
"babel-plugin-module-resolver/glob/path-scurry": ["path-scurry@1.11.1", "", { "dependencies": { "lru-cache": "^10.2.0", "minipass": "^5.0.0 || ^6.0.2 || ^7.0.0" } }, "sha512-Xa4Nw17FS9ApQFJ9umLiJS4orGjm7ZzwUrwamcGQuHSzDyth9boKDaycYdDcZDuqYATXw4HFXgaqWTctW/v1HA=="],
|
||||
|
||||
"blume/@ai-sdk/openai-compatible/@ai-sdk/provider-utils": ["@ai-sdk/provider-utils@4.0.21", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@standard-schema/spec": "^1.1.0", "eventsource-parser": "^3.0.6" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-MtFUYI1/8mgDvRmaBDjbLJPFFrMG777AvSgyIFQtZHIMzm88R/12vYBBpnk7pfiWLFE1DSZzY4WDYzGbKAcmiw=="],
|
||||
|
||||
"blume/@astrojs/mdx/@astrojs/internal-helpers": ["@astrojs/internal-helpers@0.10.1", "", { "dependencies": { "@types/hast": "^3.0.4", "@types/mdast": "^4.0.4", "js-yaml": "^4.1.1", "picomatch": "^4.0.4", "retext-smartypants": "^6.2.0", "shiki": "^4.0.2", "smol-toml": "^1.6.0", "unified": "^11.0.5" } }, "sha512-5phcroT/vmOOrYuuAxtkbPixy5hePtlz9i8K4OeDv3dNK6/UQRuXPOSRTxIOBbUY5Sonw2UaxjbuVc43Mcir6Q=="],
|
||||
|
||||
"blume/@astrojs/mdx/@astrojs/markdown-remark": ["@astrojs/markdown-remark@7.2.1", "", { "dependencies": { "@astrojs/internal-helpers": "0.10.1", "@astrojs/prism": "4.0.2", "github-slugger": "^2.0.0", "hast-util-from-html": "^2.0.3", "hast-util-to-text": "^4.0.2", "mdast-util-definitions": "^6.0.0", "rehype-raw": "^7.0.0", "rehype-stringify": "^10.0.1", "remark-gfm": "^4.0.1", "remark-parse": "^11.0.0", "remark-rehype": "^11.1.2", "remark-smartypants": "^3.0.2", "unified": "^11.0.5", "unist-util-remove-position": "^5.0.0", "unist-util-visit": "^5.1.0", "unist-util-visit-parents": "^6.0.2", "vfile": "^6.0.3" } }, "sha512-jPVNIqTvk+yKviikszv/Y1U4jGUSKpp/Nw48QZV4qjWgp70j4Lkq3lhSDRbWwCfgKvEyO9GHuVbV1dM2WYXy1w=="],
|
||||
|
||||
+1
-1
@@ -8,7 +8,6 @@
|
||||
"packageManager": "bun@1.3.14",
|
||||
"scripts": {
|
||||
"dev": "bun run --cwd packages/cli --conditions=browser src/index.ts",
|
||||
"dev:live": "OPENCODE_TUI_CHANNEL=next OPENCODE_PASSWORD=\"$(opencode2 service get password)\" bun run dev --server \"$(opencode2 service status)\"",
|
||||
"dev:desktop": "bun --cwd packages/desktop dev",
|
||||
"dev:web": "bun --cwd packages/app dev",
|
||||
"dev:console": "ulimit -n 10240 2>/dev/null; bun run --cwd packages/console/app dev",
|
||||
@@ -161,6 +160,7 @@
|
||||
"@silvia-odwyer/photon-node@0.3.4": "patches/@silvia-odwyer%2Fphoton-node@0.3.4.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",
|
||||
"@ai-sdk/xai@3.0.102": "patches/@ai-sdk%2Fxai@3.0.102.patch",
|
||||
"@ai-sdk/mistral@3.0.51": "patches/@ai-sdk%2Fmistral@3.0.51.patch",
|
||||
"gcp-metadata@8.1.2": "patches/gcp-metadata@8.1.2.patch",
|
||||
"pacote@21.5.0": "patches/pacote@21.5.0.patch",
|
||||
|
||||
+10
-10
@@ -10,7 +10,7 @@
|
||||
|
||||
## Conventions
|
||||
|
||||
Per-type constructors live on the type, not as top-level re-exports. Use `Message.system(...)`, `Message.user(...)`, `Message.assistant(...)`, `Message.tool(...)`, `LanguageModel.make(...)`, `ToolDefinition.make(...)`, `ToolCallPart.make(...)`, `ToolResultPart.make(...)`, `ToolChoice.make(...)`, `ToolChoice.named(...)`, `SystemPart.make(...)`, and `GenerationOptions.make(...)` directly. The top-level `LLM` namespace is reserved for request-shaped call APIs: `LLM.request`, `LLM.generate`, `LLM.stream`, and `LLM.generateObject`. Use `LLMRequest.update(...)` when deriving canonical request data; do not add a duplicate `LLM.updateRequest(...)` path. Two ways to construct the same thing is one too many.
|
||||
Per-type constructors live on the type, not as top-level re-exports. Use `Message.system(...)`, `Message.user(...)`, `Message.assistant(...)`, `Message.tool(...)`, `Model.make(...)`, `ToolDefinition.make(...)`, `ToolCallPart.make(...)`, `ToolResultPart.make(...)`, `ToolChoice.make(...)`, `ToolChoice.named(...)`, `SystemPart.make(...)`, and `GenerationOptions.make(...)` directly. The top-level `LLM` namespace is reserved for request-shaped call APIs: `LLM.request`, `LLM.generate`, `LLM.stream`, `LLM.updateRequest`, and `LLM.generateObject`. Two ways to construct the same thing is one too many.
|
||||
|
||||
- Keep provider-defined string enums forward-compatible. Expose known values for autocomplete while accepting future values with `Known | (string & {})`; use `Schema.String` at runtime unless rejecting unknown values is required for correctness.
|
||||
|
||||
@@ -76,11 +76,11 @@ export const route = Route.make({
|
||||
})
|
||||
```
|
||||
|
||||
Route defaults are request-shaping defaults such as `headers`, `limits`, `generation`, `providerOptions`, and `http`. Endpoint host/query belongs on the route endpoint. Selected `LanguageModel` values carry only model id, provider id, and the configured route value. Model capability/catalog metadata lives outside this package; protocol support is enforced by request lowering and typed `AIError`s.
|
||||
Route defaults are request-shaping defaults such as `headers`, `limits`, `generation`, `providerOptions`, and `http`. Endpoint host/query belongs on the route endpoint. Selected `Model` values carry only model id, provider id, and the configured route value. Model capability/catalog metadata lives outside this package; protocol support is enforced by request lowering and typed `LLMError`s.
|
||||
|
||||
The four-axis decomposition is the reason DeepSeek, TogetherAI, Cerebras, Baseten, Fireworks, and DeepInfra all reuse `OpenAIChat.protocol` verbatim — each provider deployment is a 5-15 line `Route.make(...)` call instead of a 300-400 line route clone. Bug fixes in one protocol propagate to every consumer of that protocol in a single commit.
|
||||
|
||||
When a provider supports multiple physical transports, selection remains execution policy below its semantic route. OpenAI Responses uses a purpose-built hybrid transport that prepares one final request, executes HTTP by default, and passes a generic channel exchange to a per-call `WebSocketChannelExecutor` when supplied. `Route.streamPrepared` owns decoding and acknowledges channel completion only after successful full consumption.
|
||||
When a provider ships a non-HTTP transport (OpenAI's WebSocket Responses backend, hypothetical bidirectional streaming APIs), the seam is `Transport` — `WebSocketTransport.jsonTransport.with(...)` constructs an IO template whose `prepare` receives the route endpoint/auth at compile time, builds a WebSocket URL and message, and whose `frames` yields decoded text from the socket. Same protocol and endpoint source, different transport.
|
||||
|
||||
### URL Construction
|
||||
|
||||
@@ -106,7 +106,7 @@ const proxied = gateway.model("openai/gpt-4o-mini")
|
||||
Keep provider facades small and explicit:
|
||||
|
||||
- Use branded `ProviderID.make(...)` and `ModelID.make(...)` where ids are constructed directly.
|
||||
- Use `model` for the default API path and named methods for provider-native alternatives such as OpenAI `responses` and `chat`.
|
||||
- Use `model` for the default API path and named methods for provider-native alternatives such as OpenAI `responses`, `responsesWebSocket`, and `chat`.
|
||||
- Put provider-specific setup on `.configure(...)`; do not add `model(id, overrides)` as a duplicate construction path.
|
||||
- Export lower-level `routes` arrays separately only when advanced internal wiring needs them.
|
||||
- Prefer `apiKey` as provider-specific sugar and `auth` as the explicit override; keep them mutually exclusive in provider option types with `ProviderAuthOption`.
|
||||
@@ -124,10 +124,11 @@ import { model } from "@opencode-ai/ai/providers/openai/responses"
|
||||
|
||||
const selected = model("gpt-5", {
|
||||
apiKey,
|
||||
transport: "websocket",
|
||||
})
|
||||
```
|
||||
|
||||
Keep semantic APIs as separate entrypoints, such as OpenAI `chat` and `responses`. Transport is execution policy: OpenAI Responses uses HTTP by default and may receive a per-call WebSocket channel executor through `StreamOptions` without changing model or route identity.
|
||||
Keep semantic APIs as separate entrypoints, such as OpenAI `chat` and `responses`. Keep transport choices inside the semantic entrypoint settings, so OpenAI Responses HTTP and WebSocket share one entrypoint. Provider facades may still expose named selectors such as `responsesWebSocket` for direct typed call sites; the package-like contract maps its settings to those selectors before returning an executable `Model`.
|
||||
|
||||
Do not expose `Route` in provider package settings. Route composition stays an implementation detail behind `model(...)`.
|
||||
|
||||
@@ -137,10 +138,10 @@ Do not expose `Route` in provider package settings. Route composition stays an i
|
||||
packages/ai/src/
|
||||
schema/ canonical Schema model, split by concern
|
||||
ids.ts branded IDs, literal types, ProviderMetadata
|
||||
options.ts Generation/Provider/Http options, Limits, LanguageModel, cache policy
|
||||
options.ts Generation/Provider/Http options, Limits, Model, cache policy
|
||||
messages.ts content parts, Message, ToolDefinition, LLMRequest
|
||||
events.ts Usage, individual events, LLMEvent, LLMResponse
|
||||
errors.ts error reasons, AIError, ToolFailure
|
||||
errors.ts error reasons, LLMError, ToolFailure
|
||||
index.ts barrel
|
||||
llm.ts request constructors and convenience helpers
|
||||
route/
|
||||
@@ -153,10 +154,9 @@ packages/ai/src/
|
||||
auth-options.ts ProviderAuthOption shape, AuthOptions.bearer, AtLeastOne helper
|
||||
framing.ts Framing type + Framing.sse
|
||||
transport/ transport implementations
|
||||
index.ts Transport execution types + HttpTransport / WebSocketTransport namespaces
|
||||
websocket-channel.ts generic sequential channel executor/driver contract
|
||||
index.ts Transport type + HttpTransport / WebSocketTransport namespaces
|
||||
http.ts HttpTransport.httpJson — POST + framing
|
||||
websocket.ts direct one-request channel executor + raw socket adapter
|
||||
websocket.ts WebSocketTransport.json + WebSocketExecutor service
|
||||
protocols/
|
||||
shared.ts ProviderShared toolkit used inside protocol impls
|
||||
openai-chat.ts protocol + route (compose OpenAIChat.protocol)
|
||||
|
||||
@@ -96,7 +96,7 @@ contains identity, capabilities, pricing metadata, provider-specific option
|
||||
types, reusable request-behavior defaults, and hidden execution behavior.
|
||||
|
||||
Normal users do not need to learn the current `Route` composite. Protocol,
|
||||
endpoint, auth, transport, and hooks are bound behind `LanguageModel`.
|
||||
endpoint, auth, transport, and hooks are bound behind `Model`.
|
||||
|
||||
### Request
|
||||
|
||||
@@ -539,7 +539,7 @@ Hosted tools do not pretend to have local handlers, and callers do not inspect a
|
||||
|
||||
### Run stream
|
||||
|
||||
`LLM.stream` returns an Effect `Stream<RunEvent, AIError, Requirements>`.
|
||||
`LLM.stream` returns an Effect `Stream<RunEvent, LLMError, Requirements>`.
|
||||
Run events explicitly expose orchestration boundaries:
|
||||
|
||||
```ts
|
||||
@@ -828,11 +828,11 @@ portable semantic guarantee.
|
||||
|
||||
## Error Model
|
||||
|
||||
The Effect error channel is a tagged domain union rather than one `AIError`
|
||||
The Effect error channel is a tagged domain union rather than one `LLMError`
|
||||
wrapper with nested reasons. Illustrative categories:
|
||||
|
||||
```ts
|
||||
type AIError =
|
||||
type LLMError =
|
||||
| AuthenticationError
|
||||
| InvalidRequestError
|
||||
| UnsupportedCapabilityError
|
||||
@@ -1079,7 +1079,7 @@ The redesign intentionally removes or changes these current concepts:
|
||||
| `LLM.generate` means one turn | `LLM.generate` means complete run |
|
||||
| `LLMClient.generate/stream` | `LLM.generateTurn/streamTurn` for one turn |
|
||||
| `LLMClient.layer` requirement | Standard Effect requirements exposed directly |
|
||||
| Public `Route` mental model | Hidden behind executable `LanguageModel` |
|
||||
| Public `Route` mental model | Hidden behind executable `Model` |
|
||||
| `Provider.make` structural helper | Experimental declarative `Provider.define` |
|
||||
| Schema classes as canonical values | Plain immutable values plus schema subpath |
|
||||
| `LLM.updateRequest` | Object spread |
|
||||
@@ -1089,7 +1089,7 @@ The redesign intentionally removes or changes these current concepts:
|
||||
| `generateObject` | Typed `output` option on `generate` |
|
||||
| One event union for provider output | Separate `TurnEvent` and `RunEvent` unions |
|
||||
| `providerExecuted` dispatch check | Distinct hosted-tool constructors |
|
||||
| One wrapped `AIError` | Tagged domain error union |
|
||||
| One wrapped `LLMError` | Tagged domain error union |
|
||||
|
||||
OpenCode should migrate to `generateTurn` / `streamTurn`, preserving its durable
|
||||
prompt admission, persistence, permission, tool settlement, and continuation
|
||||
|
||||
+4
-34
@@ -3,9 +3,8 @@
|
||||
Schema-first AI primitives for opencode. Provider quirks live in adapters, not in calling code.
|
||||
|
||||
```ts
|
||||
import { Effect, Layer } from "effect"
|
||||
import { Effect } from "effect"
|
||||
import { LLM, LLMClient } from "@opencode-ai/ai"
|
||||
import { RequestExecutor } from "@opencode-ai/ai/route"
|
||||
import { OpenAI } from "@opencode-ai/ai/providers"
|
||||
|
||||
const model = OpenAI.configure({ apiKey: process.env.OPENAI_API_KEY }).responses("gpt-4o-mini")
|
||||
@@ -21,10 +20,6 @@ const program = Effect.gen(function* () {
|
||||
const response = yield* LLMClient.generate(request)
|
||||
console.log(response.text)
|
||||
})
|
||||
|
||||
const llmLayer = LLMClient.layer.pipe(Layer.provide(RequestExecutor.fetchLayer))
|
||||
|
||||
await Effect.runPromise(program.pipe(Effect.provide(llmLayer)))
|
||||
```
|
||||
|
||||
Run `LLMClient.stream(request)` instead of `generate` when you want incremental `LLMEvent`s. The event stream is provider-neutral — same shape across OpenAI Chat, OpenAI Responses, Anthropic Messages, Gemini, Bedrock Converse, and any OpenAI-compatible deployment.
|
||||
@@ -200,37 +195,11 @@ The hosted result is represented as a provider-executed tool call and tool resul
|
||||
- **`LLM.request({...})`** — build a provider-neutral `LLMRequest`. Accepts ergonomic inputs (`system: string`, `prompt: string`) that normalize into the canonical Schema classes.
|
||||
- **`LLM.generate` / `LLM.stream`** — re-exported from `LLMClient` for one-import use.
|
||||
- **`Message.user(...)` / `Message.assistant(...)` / `Message.tool(...)`** — message constructors from the canonical schema model.
|
||||
- **`LanguageModel.make(...)` / `ToolCallPart.make(...)` / `ToolResultPart.make(...)` / `ToolDefinition.make(...)`** — model and tool-related constructors from the canonical schema model.
|
||||
- **`Model.make(...)` / `ToolCallPart.make(...)` / `ToolResultPart.make(...)` / `ToolDefinition.make(...)`** — model and tool-related constructors from the canonical schema model.
|
||||
- **`LLMEvent.is.*`** — typed guards (`is.textDelta`, `is.toolCall`, `is.finish`, …) for filtering streams.
|
||||
- **`Image.generate({...})`** — generate images through a provider-neutral image request and response model.
|
||||
- **`ImageClient`** — Effect service and layer for image execution, parallel to `LLMClient`.
|
||||
|
||||
## Testing
|
||||
|
||||
Use the deterministic test client from `@opencode-ai/ai/testing` to script provider-neutral responses and inspect
|
||||
the requests sent by code under test:
|
||||
|
||||
```ts
|
||||
import { Effect } from "effect"
|
||||
import { TestLLM } from "@opencode-ai/ai/testing"
|
||||
|
||||
const testLLM = TestLLM.layer({
|
||||
fallback: TestLLM.text("Hello from the test model", "text-1"),
|
||||
})
|
||||
|
||||
// TestLLM.clientLayer provides LLMClient.Service and consumes TestLLM.Service.
|
||||
const programWithTestClient = Effect.gen(function* () {
|
||||
const result = yield* program
|
||||
const test = yield* TestLLM.Service
|
||||
console.log(test.requests)
|
||||
return result
|
||||
}).pipe(Effect.provide(TestLLM.clientLayer), Effect.provide(testLLM))
|
||||
```
|
||||
|
||||
`TestLLM.push(...)` scripts one-shot responses, `TestLLM.always(...)` changes the fallback, and
|
||||
`TestLLM.wait(...)` lets concurrent tests wait until a request has arrived. Every received canonical request is
|
||||
available on the yielded `TestLLM.Service`.
|
||||
|
||||
## Caching
|
||||
|
||||
Prompt caching is **on by default**. Every `LLMRequest` resolves to `cache: "auto"` unless the caller opts out with `cache: "none"`. Each protocol translates `CacheHint`s to its wire format (`cache_control` on Anthropic, `cachePoint` on Bedrock; OpenAI and Gemini do implicit caching server-side and don't need inline markers — auto is a no-op there).
|
||||
@@ -315,6 +284,7 @@ import { model } from "@opencode-ai/ai/providers/openai/responses"
|
||||
|
||||
const selected = model("gpt-5", {
|
||||
apiKey: process.env.OPENAI_API_KEY,
|
||||
transport: "websocket",
|
||||
headers: { "x-application": "opencode" },
|
||||
limits: { context: 200_000, output: 64_000 },
|
||||
})
|
||||
@@ -331,7 +301,7 @@ OpenAI Chat and OpenAI Responses are separate semantic entrypoints:
|
||||
- `@opencode-ai/ai/providers/google-vertex/responses`
|
||||
- `@opencode-ai/ai/providers/google-vertex/messages`
|
||||
|
||||
OpenAI Responses has one semantic route and uses HTTP by default. Advanced callers may supply a per-call WebSocket channel executor through `StreamOptions`; transport policy does not change provider settings, model identity, or route identity. Azure follows the same Chat/Responses split at `providers/azure/chat` and `providers/azure/responses`. Generic OpenAI-compatible Chat remains at `providers/openai-compatible`; the Responses adapter at `providers/openai-compatible/responses` uses the provider-neutral Open Responses protocol. OpenAI Responses extends that baseline with OpenAI tools, event variants, metadata, and defaults. Generic Anthropic Messages-compatible providers use `providers/anthropic-compatible`, which the named Anthropic provider composes. Google Gemini and Amazon Bedrock expose their single native API through their existing provider paths.
|
||||
Responses HTTP versus WebSocket is a scoped `transport` setting on the OpenAI Responses entrypoint, not another entrypoint. Azure follows the same Chat/Responses split at `providers/azure/chat` and `providers/azure/responses`. Generic OpenAI-compatible Chat remains at `providers/openai-compatible`; the Responses adapter at `providers/openai-compatible/responses` uses the provider-neutral Open Responses protocol. OpenAI Responses extends that baseline with OpenAI tools, event variants, metadata, defaults, and transports. Generic Anthropic Messages-compatible providers use `providers/anthropic-compatible`, which the named Anthropic provider composes. Google Gemini and Amazon Bedrock expose their single native API through their existing provider paths.
|
||||
|
||||
Vertex Gemini, Vertex Chat, Vertex Responses, and Vertex Messages are separate API entrypoints. All accept `project`, `location`, and an optional `accessToken`; when no explicit token or auth override is supplied they lazily use Google Application Default Credentials. Vertex Gemini instead selects express mode when `apiKey` or `GOOGLE_VERTEX_API_KEY` is present. Vertex Chat targets MaaS models through the OpenAI-compatible Chat Completions endpoint, while Vertex Responses targets Grok models and defaults `store` to `false` as required by Vertex. `providers/google-vertex` remains the default alias for `providers/google-vertex/gemini`.
|
||||
|
||||
|
||||
+38
-37
@@ -1,6 +1,6 @@
|
||||
# LLM Provider Parity Status
|
||||
|
||||
Last reviewed: 2026-08-07
|
||||
Last reviewed: 2026-07-24
|
||||
|
||||
This file tracks the gap between the native `@opencode-ai/ai` package and the AI SDK provider packages that opencode still depends on for many catalog/runtime paths.
|
||||
|
||||
@@ -16,7 +16,8 @@ This file tracks the gap between the native `@opencode-ai/ai` package and the AI
|
||||
| Native slice | Source | Current state | Main gaps |
|
||||
| ---------------------------------- | --------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| OpenAI Chat | `src/protocols/openai-chat.ts`, `src/providers/openai.ts` | Usable. Streams text, reasoning deltas, tool calls, usage, images, and common generation controls. | No typed structured-output / `response_format` path. Limited typed OpenAI option surface compared with SDK escape hatches. |
|
||||
| OpenAI Responses | `src/protocols/open-responses.ts`, `src/protocols/openai-responses.ts`, `src/providers/openai.ts` | Usable over HTTP by default, with optional per-call WebSocket channel execution on the same model and route identity. | No incremental `previous_response_id` path or persistent Session channel manager yet. Typed options cover only a subset of Responses fields. Structured output is still mostly synthetic-tool based. |
|
||||
| OpenAI Responses HTTP | `src/protocols/open-responses.ts`, `src/protocols/openai-responses.ts`, `src/providers/openai.ts` | Usable. Extends the Open Responses baseline with hosted-tool event surfacing, reasoning replay metadata, GPT-5 defaults, and cache usage. | No explicit `previous_response_id` path. Typed options cover only a subset of Responses fields. Structured output is still mostly synthetic-tool based. |
|
||||
| OpenAI Responses WebSocket | `src/protocols/openai-responses.ts`, `src/route/transport/websocket.ts` | Present as `OpenAI.responsesWebSocket(...)`. | Runner/catalog support explicitly must not downgrade WebSocket routes; broader runtime selection is not complete. |
|
||||
| OpenAI-compatible Chat | `src/protocols/openai-compatible-chat.ts`, `src/providers/openai-compatible.ts` | Usable for generic Chat and several profiles: Baseten, Cerebras, DeepInfra, DeepSeek, Fireworks, Groq, TogetherAI. | Family quirks are mostly endpoint defaults, not full typed behavior. |
|
||||
| Open Responses-compatible | `src/protocols/open-responses.ts`, `src/protocols/openai-compatible-responses.ts`, `src/providers/openai-compatible-responses.ts` | Usable for deployments that implement the provider-neutral Open Responses protocol. The deployment adapter does not inherit OpenAI tools, events, metadata, or defaults. | No named family profiles or recorded deployment coverage yet. |
|
||||
| Anthropic-compatible Messages | `src/protocols/anthropic-messages.ts`, `src/providers/anthropic-compatible.ts` | Usable for deployments that implement the Anthropic Messages wire protocol. Named Anthropic composes this base; MiniMax M3 has recorded text and tool-loop coverage. | No named compatible family profiles yet. |
|
||||
@@ -47,19 +48,19 @@ Other `aisdk:` packages, including Google Vertex, Azure, and Bedrock, currently
|
||||
|
||||
## AI SDK Package Parity Matrix
|
||||
|
||||
| AI SDK package | Intended native target | Status | Biggest gaps |
|
||||
| --------------------------------- | --------------------------------------------------------- | ---------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| `@ai-sdk/openai` | `OpenAI.chat`, `OpenAI.responses` | Partial / usable | Add complete typed option coverage, structured output strategy, explicit Responses continuation support, and runner execution policy for optional WebSocket channels. |
|
||||
| `@ai-sdk/openai-compatible` | Generic OpenAI-compatible Chat and Responses | Partial / usable | Decide per-family namespace/profile behavior and runner API selection for providers that support Responses versus Chat only. |
|
||||
| `@ai-sdk/anthropic` | `AnthropicMessages` | Partial / usable | Finish Messages API parity for headers/betas/metadata/newer fields and document hosted-tool continuation expectations. |
|
||||
| `@ai-sdk/google` | Gemini Developer API | Partial / usable | Add typed options for safety, response schema/modalities, cached content, grounding/search/code execution, and non-text output modes where supported. |
|
||||
| `@ai-sdk/google-vertex` | Vertex Gemini namespace/facade | Partial / usable | Add runner/catalog mapping, recorded coverage, and broader provider-option parity. |
|
||||
| `@ai-sdk/google-vertex/anthropic` | Anthropic Messages over Vertex namespace/facade | Partial / usable | Add runner/catalog mapping, recorded coverage, and Vertex-specific hosted-tool parity. |
|
||||
| `@ai-sdk/google-vertex/maas` | Vertex Chat | Partial / usable | Add runner/catalog mapping, recorded coverage, and MaaS family-specific request parity. |
|
||||
| `@ai-sdk/google-vertex/xai` | Vertex Chat / Responses | Partial / usable | Decide Chat/Responses selection for catalog models, add runner mapping and recorded coverage, and review xAI-specific request options. |
|
||||
| `@ai-sdk/azure` | Azure OpenAI Chat/Responses facade | Partial | Map runner/catalog metadata to native Azure, handle resourceName/baseURL/apiVersion variants, add AAD/token auth story, and verify Chat vs Responses deployment selection. |
|
||||
| `@ai-sdk/amazon-bedrock` | Bedrock Converse | Partial | Add default AWS credential chain/profile support, region/inference-profile model ID handling, provider option parity via `additionalModelRequestFields`, guardrails/performance config, and runner/catalog mapping. |
|
||||
| `@ai-sdk/amazon-bedrock/mantle` | Bedrock Mantle OpenAI-compatible Chat/Responses namespace | Partial / usable | Add default AWS credential chain/profile support; native catalog mapping currently requires bearer auth or explicit static credentials. |
|
||||
| AI SDK package | Intended native target | Status | Biggest gaps |
|
||||
| --------------------------------- | -------------------------------------------------------------- | ---------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| `@ai-sdk/openai` | `OpenAI.chat`, `OpenAI.responses`, `OpenAI.responsesWebSocket` | Partial / usable | Add complete typed option coverage, structured output strategy, explicit Responses continuation support, and runner route selection between Chat/Responses/WebSocket. |
|
||||
| `@ai-sdk/openai-compatible` | Generic OpenAI-compatible Chat and Responses | Partial / usable | Decide per-family namespace/profile behavior and runner API selection for providers that support Responses versus Chat only. |
|
||||
| `@ai-sdk/anthropic` | `AnthropicMessages` | Partial / usable | Finish Messages API parity for headers/betas/metadata/newer fields and document hosted-tool continuation expectations. |
|
||||
| `@ai-sdk/google` | Gemini Developer API | Partial / usable | Add typed options for safety, response schema/modalities, cached content, grounding/search/code execution, and non-text output modes where supported. |
|
||||
| `@ai-sdk/google-vertex` | Vertex Gemini namespace/facade | Partial / usable | Add runner/catalog mapping, recorded coverage, and broader provider-option parity. |
|
||||
| `@ai-sdk/google-vertex/anthropic` | Anthropic Messages over Vertex namespace/facade | Partial / usable | Add runner/catalog mapping, recorded coverage, and Vertex-specific hosted-tool parity. |
|
||||
| `@ai-sdk/google-vertex/maas` | Vertex Chat | Partial / usable | Add runner/catalog mapping, recorded coverage, and MaaS family-specific request parity. |
|
||||
| `@ai-sdk/google-vertex/xai` | Vertex Chat / Responses | Partial / usable | Decide Chat/Responses selection for catalog models, add runner mapping and recorded coverage, and review xAI-specific request options. |
|
||||
| `@ai-sdk/azure` | Azure OpenAI Chat/Responses facade | Partial | Map runner/catalog metadata to native Azure, handle resourceName/baseURL/apiVersion variants, add AAD/token auth story, and verify Chat vs Responses deployment selection. |
|
||||
| `@ai-sdk/amazon-bedrock` | Bedrock Converse | Partial | Add default AWS credential chain/profile support, region/inference-profile model ID handling, provider option parity via `additionalModelRequestFields`, guardrails/performance config, and runner/catalog mapping. |
|
||||
| `@ai-sdk/amazon-bedrock/mantle` | Bedrock Mantle OpenAI-compatible Chat/Responses namespace | Missing | Decide native Mantle shape, likely separate from Converse because it uses OpenAI-compatible Chat/Responses semantics over Bedrock. Add package mapping and tests. |
|
||||
|
||||
## Highest-Risk Gaps
|
||||
|
||||
@@ -70,31 +71,30 @@ Other `aisdk:` packages, including Google Vertex, Azure, and Bedrock, currently
|
||||
5. Azure is only a provider facade, not a full runtime replacement. Native Azure exists, but the catalog runner does not select it, and token auth/resource variants need review.
|
||||
6. Provider option typing is uneven. OpenAI, Anthropic, Gemini, Bedrock, and OpenRouter each expose a small typed subset plus raw HTTP overlays; this is useful but not equivalent to AI SDK provider option coverage.
|
||||
7. Structured output is not provider-native yet. `LLM.generateObject` still uses a synthetic tool strategy, while the future design expects native structured output where reliable and tool fallback where needed.
|
||||
8. Package/namespace boundaries for the current native loading set are explicit in docs and exports. Other exported provider facades are not catalog package entrypoints until they implement the contract. Vertex xAI still needs catalog API selection.
|
||||
9. Recorded coverage is uneven. OpenAI, Anthropic, Gemini, Bedrock Converse, Bedrock Mantle, Cloudflare, OpenRouter, and several OpenAI-compatible Chat providers have cassettes. Azure and Vertex still need first-class recorded scenarios before switching defaults.
|
||||
8. Package/namespace boundaries for the current native loading set are explicit in docs and exports. Other exported provider facades are not catalog package entrypoints until they implement the contract. Vertex xAI still needs catalog API selection; the missing native boundary is Bedrock Mantle.
|
||||
9. Recorded coverage is uneven. OpenAI, Anthropic, Gemini, Bedrock Converse, Cloudflare, OpenRouter, and several OpenAI-compatible Chat providers have cassettes. Azure, Vertex, and Mantle need first-class recorded scenarios before switching defaults.
|
||||
|
||||
## Native Namespace Shape
|
||||
|
||||
These are implementation/API slices, not separate npm packages.
|
||||
|
||||
| API slice | Package-like entrypoint | Purpose |
|
||||
| ----------------------------- | ----------------------------------------------------------- | ---------------------------------------------------------------------------- |
|
||||
| OpenAI Chat | `@opencode-ai/ai/providers/openai/chat` | OpenAI `/chat/completions` semantics. |
|
||||
| OpenAI Responses | `@opencode-ai/ai/providers/openai/responses` | OpenAI `/responses` semantics with HTTP/WebSocket selected through settings. |
|
||||
| OpenAI-compatible Chat | `@opencode-ai/ai/providers/openai-compatible` | Generic OpenAI-compatible `/chat/completions`. |
|
||||
| Open Responses-compatible | `@opencode-ai/ai/providers/openai-compatible/responses` | Generic provider-neutral `/responses`. |
|
||||
| Anthropic-compatible Messages | `@opencode-ai/ai/providers/anthropic-compatible` | Generic Anthropic-compatible `/messages`. |
|
||||
| Anthropic Messages | `@opencode-ai/ai/providers/anthropic` | Anthropic Messages API. |
|
||||
| Gemini Developer API | `@opencode-ai/ai/providers/google` | Google AI Studio Gemini API. |
|
||||
| Vertex Gemini | `@opencode-ai/ai/providers/google-vertex/gemini` | Vertex Gemini API; `providers/google-vertex` is the default alias. |
|
||||
| Vertex Chat | `@opencode-ai/ai/providers/google-vertex/chat` | Vertex OpenAI-compatible Chat Completions for MaaS models. |
|
||||
| Vertex Responses | `@opencode-ai/ai/providers/google-vertex/responses` | Vertex Open Responses for Grok models. |
|
||||
| Vertex Messages | `@opencode-ai/ai/providers/google-vertex/messages` | Vertex-hosted Anthropic Messages API. |
|
||||
| Bedrock Converse | `@opencode-ai/ai/providers/amazon-bedrock` | AWS Bedrock Converse API. |
|
||||
| Bedrock Mantle Chat | `@opencode-ai/ai/providers/amazon-bedrock/mantle/chat` | AWS Bedrock Mantle OpenAI-compatible Chat API. |
|
||||
| Bedrock Mantle Responses | `@opencode-ai/ai/providers/amazon-bedrock/mantle/responses` | AWS Bedrock Mantle OpenAI-compatible Responses API. |
|
||||
| Azure OpenAI Chat | `@opencode-ai/ai/providers/azure/chat` | Azure specialization of OpenAI Chat. |
|
||||
| Azure OpenAI Responses | `@opencode-ai/ai/providers/azure/responses` | Azure specialization of OpenAI Responses. |
|
||||
| API slice | Package-like entrypoint | Purpose |
|
||||
| ----------------------------- | ------------------------------------------------------- | ---------------------------------------------------------------------------- |
|
||||
| OpenAI Chat | `@opencode-ai/ai/providers/openai/chat` | OpenAI `/chat/completions` semantics. |
|
||||
| OpenAI Responses | `@opencode-ai/ai/providers/openai/responses` | OpenAI `/responses` semantics with HTTP/WebSocket selected through settings. |
|
||||
| OpenAI-compatible Chat | `@opencode-ai/ai/providers/openai-compatible` | Generic OpenAI-compatible `/chat/completions`. |
|
||||
| Open Responses-compatible | `@opencode-ai/ai/providers/openai-compatible/responses` | Generic provider-neutral `/responses`. |
|
||||
| Anthropic-compatible Messages | `@opencode-ai/ai/providers/anthropic-compatible` | Generic Anthropic-compatible `/messages`. |
|
||||
| Anthropic Messages | `@opencode-ai/ai/providers/anthropic` | Anthropic Messages API. |
|
||||
| Gemini Developer API | `@opencode-ai/ai/providers/google` | Google AI Studio Gemini API. |
|
||||
| Vertex Gemini | `@opencode-ai/ai/providers/google-vertex/gemini` | Vertex Gemini API; `providers/google-vertex` is the default alias. |
|
||||
| Vertex Chat | `@opencode-ai/ai/providers/google-vertex/chat` | Vertex OpenAI-compatible Chat Completions for MaaS models. |
|
||||
| Vertex Responses | `@opencode-ai/ai/providers/google-vertex/responses` | Vertex Open Responses for Grok models. |
|
||||
| Vertex Messages | `@opencode-ai/ai/providers/google-vertex/messages` | Vertex-hosted Anthropic Messages API. |
|
||||
| Bedrock Converse | `@opencode-ai/ai/providers/amazon-bedrock` | AWS Bedrock Converse API. |
|
||||
| Bedrock Mantle | Missing | AWS Bedrock Mantle OpenAI-compatible APIs. |
|
||||
| Azure OpenAI Chat | `@opencode-ai/ai/providers/azure/chat` | Azure specialization of OpenAI Chat. |
|
||||
| Azure OpenAI Responses | `@opencode-ai/ai/providers/azure/responses` | Azure specialization of OpenAI Responses. |
|
||||
|
||||
## Suggested Next Work Slices
|
||||
|
||||
@@ -103,5 +103,6 @@ These are implementation/API slices, not separate npm packages.
|
||||
3. Bring Bedrock native auth/config to AI SDK parity: region, profile, default AWS credential chain, bearer token env, endpoint override, and cross-region inference profile handling.
|
||||
4. Add runner/catalog mappings and recorded scenarios for the native Vertex Gemini, Chat, Responses, and Messages entrypoints.
|
||||
5. Decide Chat/Responses selection for `@ai-sdk/google-vertex/xai` catalog models.
|
||||
6. Expand typed provider options from the existing V1 lowerer knowledge in `packages/core/src/v1/config/provider-options.ts` before adding more raw overlay examples.
|
||||
7. Add recorded provider tests for Azure, Vertex Gemini, Vertex Chat, Vertex Responses, Vertex Messages, and Bedrock credential-chain behavior before making native runtime the default for those packages.
|
||||
6. Add Bedrock Mantle as a separate OpenAI-compatible Bedrock namespace after deciding whether it uses Chat, Responses, or both by model.
|
||||
7. Expand typed provider options from the existing V1 lowerer knowledge in `packages/core/src/v1/config/provider-options.ts` before adding more raw overlay examples.
|
||||
8. Add recorded provider tests for Azure, Vertex Gemini, Vertex Chat, Vertex Responses, Vertex Messages, Bedrock credential-chain behavior, and Mantle before making native runtime the default for those packages.
|
||||
|
||||
@@ -33,7 +33,7 @@ Keep durable identity separate from runtime capability:
|
||||
|
||||
- Durable identity is small serializable data like `{ providerID, modelID }` for
|
||||
config, sessions, logs, and catalogs.
|
||||
- Runtime capability is a `LanguageModel` with a route value, protocol, transport, auth,
|
||||
- Runtime capability is a `Model` with a route value, protocol, transport, auth,
|
||||
and defaults. It is allowed to contain functions and schemas.
|
||||
- If persisted identity needs to become executable, resolve it through an app
|
||||
boundary first. Do not make `LLMRequest` recover behavior from a global route
|
||||
@@ -67,6 +67,7 @@ Examples:
|
||||
```ts
|
||||
OpenAI.responses("gpt-4o")
|
||||
OpenAI.chat("gpt-4o")
|
||||
OpenAI.responsesWebSocket("gpt-4o")
|
||||
|
||||
Azure.configure({ resourceName, apiKey }).responses("my-deployment")
|
||||
AmazonBedrock.configure({ region, credentials }).model("anthropic.claude-3-5-sonnet-20241022-v2:0")
|
||||
@@ -136,7 +137,7 @@ starts hiding the real provider-specific config.
|
||||
- accepts model id only
|
||||
- returns executable models
|
||||
- does not accept endpoint/auth/deployment overrides
|
||||
4. **Language Model**
|
||||
4. **Model**
|
||||
- model id
|
||||
- route value
|
||||
- provider id
|
||||
@@ -163,7 +164,7 @@ execution mechanism:
|
||||
```ts
|
||||
type ProviderFacade<APIs, Config> = {
|
||||
readonly id: ProviderID
|
||||
readonly model: (id: string) => LanguageModel
|
||||
readonly model: (id: string) => Model
|
||||
readonly configure: (input?: Config) => ProviderFacade<APIs, Config>
|
||||
} & APIs
|
||||
```
|
||||
@@ -180,8 +181,8 @@ export const OpenAI = {
|
||||
configure: configureOpenAI,
|
||||
} satisfies ProviderFacade<
|
||||
{
|
||||
responses: (id: string) => LanguageModel
|
||||
chat: (id: string) => LanguageModel
|
||||
responses: (id: string) => Model
|
||||
chat: (id: string) => Model
|
||||
},
|
||||
OpenAIConfig
|
||||
>
|
||||
@@ -249,6 +250,11 @@ const openAIChat = Route.make({
|
||||
auth: Auth.envBearer("OPENAI_API_KEY"),
|
||||
})
|
||||
|
||||
const openAIResponsesWebSocket = openAIResponses.with({
|
||||
id: "openai-responses-websocket",
|
||||
transport: WebSocketTransport.json,
|
||||
})
|
||||
|
||||
const openAIConfig = (input: OpenAIConfig) => ({
|
||||
endpoint: input.endpoint,
|
||||
auth: input.auth ?? (input.apiKey ? Auth.bearer(input.apiKey) : undefined),
|
||||
@@ -260,11 +266,13 @@ const openAIConfig = (input: OpenAIConfig) => ({
|
||||
|
||||
const configureOpenAI = (input: OpenAIConfig = {}) => {
|
||||
const responses = openAIResponses.with(openAIConfig(input))
|
||||
const responsesWebSocket = openAIResponsesWebSocket.with(openAIConfig(input))
|
||||
const chat = openAIChat.with(openAIConfig(input))
|
||||
|
||||
return {
|
||||
id: openAIProvider,
|
||||
responses: responses.model,
|
||||
responsesWebSocket: responsesWebSocket.model,
|
||||
chat: chat.model,
|
||||
model: responses.model,
|
||||
configure: configureOpenAI,
|
||||
@@ -334,19 +342,22 @@ const response =
|
||||
)
|
||||
```
|
||||
|
||||
For direct provider-facade calls, Responses has one semantic model and route:
|
||||
For direct provider-facade calls, HTTP versus WebSocket is represented as named
|
||||
route selectors, not as model or request overrides. Same protocol, different
|
||||
transport, different route:
|
||||
|
||||
```ts
|
||||
OpenAI.responses("gpt-4o")
|
||||
OpenAI.responsesWebSocket("gpt-4o")
|
||||
```
|
||||
|
||||
The package-like OpenAI Responses entrypoint has the same transport-neutral
|
||||
`model(...)` contract:
|
||||
The package-like OpenAI Responses entrypoint instead keeps transport scoped to
|
||||
Responses settings while preserving the same `model(...)` contract:
|
||||
|
||||
```ts
|
||||
import { model } from "@opencode-ai/ai/providers/openai/responses"
|
||||
|
||||
model("gpt-4o", { apiKey })
|
||||
model("gpt-4o", { apiKey, transport: "websocket" })
|
||||
```
|
||||
|
||||
Vertex keeps Gemini, Chat, Responses, and Messages as separate package-like entrypoints,
|
||||
@@ -488,13 +499,16 @@ generic dynamic resolver:
|
||||
const model =
|
||||
providerID === "azure"
|
||||
? Azure.configure(resolvedAzureConfig).responses(apiModelID)
|
||||
: OpenAI.responses(apiModelID)
|
||||
: endpoint.websocket
|
||||
? OpenAI.responsesWebSocket(apiModelID)
|
||||
: OpenAI.responses(apiModelID)
|
||||
```
|
||||
|
||||
That boundary can branch on durable config/catalog metadata and call typed
|
||||
provider APIs directly. Transport selection remains execution policy: a Session
|
||||
or other caller may pass a WebSocket channel executor per call without changing
|
||||
the model constructed by this boundary.
|
||||
provider APIs directly. A direct provider-facade boundary maps metadata like
|
||||
`endpoint.websocket` to `OpenAI.responsesWebSocket(apiModelID)`. A package-loading
|
||||
boundary passes `transport: "websocket"` to the OpenAI Responses entrypoint.
|
||||
The client runtime only executes the route carried by the resulting model.
|
||||
|
||||
## Competitive Shape
|
||||
|
||||
@@ -514,7 +528,7 @@ The chosen split is:
|
||||
```txt
|
||||
Route = execution mechanics
|
||||
Provider facade = configured route group
|
||||
LanguageModel = selected executable model carrying route value
|
||||
Model = selected executable model carrying route value
|
||||
App boundary = explicit durable-config -> typed-provider call
|
||||
```
|
||||
|
||||
@@ -530,17 +544,18 @@ App boundary = explicit durable-config -> typed-provider call
|
||||
id.
|
||||
- No `model(id, overrides)` escape hatch. Model selection takes the model id;
|
||||
endpoint/auth/deployment customization happens by configuring the route first.
|
||||
- No transport setting on a provider or executable model. OpenAI Responses uses
|
||||
HTTP by default and accepts an optional per-call channel executor as execution policy.
|
||||
- No transport override on an executable model or request. Direct provider
|
||||
facades use `responses` versus `responsesWebSocket`; the package-like Responses
|
||||
entrypoint maps its scoped `transport` setting before constructing the model.
|
||||
- No separate public `LLMClient.layerWithWebSocket`. The runtime should expose one
|
||||
client layer with the available transport capabilities.
|
||||
- No executable `ModelRef`. The executable handle is `LanguageModel`; durable model
|
||||
- No executable `ModelRef`. The executable handle is `Model`; durable model
|
||||
identity stays separate and cannot execute on its own.
|
||||
|
||||
## Implementation Todo
|
||||
|
||||
- [x] Replace the current executable `ModelRef` with `LanguageModel`.
|
||||
- [x] Change `LanguageModel.route` to carry a route value, not a `RouteID` string.
|
||||
- [x] Replace the current executable `ModelRef` with `Model`.
|
||||
- [x] Change `Model.route` to carry a route value, not a `RouteID` string.
|
||||
- [ ] Keep a separate durable model identity type for persisted/session/catalog
|
||||
data, likely `{ providerID, modelID }`, and make it clear that it cannot
|
||||
execute without resolver context.
|
||||
@@ -551,7 +566,7 @@ App boundary = explicit durable-config -> typed-provider call
|
||||
- [x] Remove endpoint/auth escape hatches from route model selection; callers must
|
||||
configure endpoint/auth through `route.with(...)` or provider facades before
|
||||
calling `.model(...)`.
|
||||
- [x] Remove request-shaping defaults from `LanguageModel`; selected models now carry only
|
||||
- [x] Remove request-shaping defaults from `Model`; selected models now carry only
|
||||
id, provider, and configured route while defaults live on routes or requests.
|
||||
- [x] Rework `LLMClient.stream` / `generate` to read
|
||||
`request.model.route` directly instead of calling `registeredRoute(...)`.
|
||||
@@ -565,10 +580,12 @@ App boundary = explicit durable-config -> typed-provider call
|
||||
- [x] Make unconfigured transports reusable constants such as
|
||||
`HttpTransport.sseJson`; keep transport functions only for configured/fresh
|
||||
state construction.
|
||||
- [x] Collapse the public WebSocket runtime split so one `LLMClient.layer` accepts
|
||||
optional per-call channel execution without changing route identity.
|
||||
- [x] Collapse the public WebSocket runtime split so one `LLMClient.layer`
|
||||
exposes available transport capabilities and selected routes fail with typed
|
||||
transport config errors when a required capability is missing.
|
||||
- [x] Convert OpenAI provider APIs to provider-facade shape:
|
||||
`OpenAI.configure(config).responses(id)` and `.chat(id)`.
|
||||
`OpenAI.configure(config).responses(id)`, `.chat(id)`, and
|
||||
`.responsesWebSocket(id)`.
|
||||
- [x] Convert Azure to a configured facade where resource/base URL/api version
|
||||
setup happens before selecting deployment ids.
|
||||
- [x] Split Cloudflare products into separate facades such as
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
import { Config, Effect, Formatter, Layer, Schema, Stream } from "effect"
|
||||
import { LLM, LLMClient, LLMRequest, Message, ProviderID, Tool, ToolRuntime } from "@opencode-ai/ai"
|
||||
import { Route, Auth, Endpoint, Framing, Protocol, RequestExecutor } from "@opencode-ai/ai/route"
|
||||
import { Route, Auth, Endpoint, Framing, Protocol, RequestExecutor, WebSocketExecutor } from "@opencode-ai/ai/route"
|
||||
import { OpenAI } from "@opencode-ai/ai/providers"
|
||||
|
||||
/**
|
||||
@@ -214,7 +214,8 @@ const FakeEcho = {
|
||||
// enabled at a time so the tutorial can demonstrate generate, stream, or
|
||||
// tool-loop behavior without spending tokens on every example.
|
||||
const requestExecutorLayer = RequestExecutor.fetchLayer
|
||||
const llmClientLayer = LLMClient.layer.pipe(Layer.provide(requestExecutorLayer))
|
||||
const llmDeps = Layer.mergeAll(requestExecutorLayer, WebSocketExecutor.layer)
|
||||
const llmClientLayer = LLMClient.layer.pipe(Layer.provide(llmDeps))
|
||||
|
||||
const program = Effect.gen(function* () {
|
||||
// yield* generateOnce
|
||||
@@ -222,6 +223,6 @@ const program = Effect.gen(function* () {
|
||||
// yield* generateStructuredObject
|
||||
// yield* generateDynamicObject.pipe(Effect.andThen((response) => Effect.sync(() => console.log(response.object))))
|
||||
yield* streamWithTools
|
||||
}).pipe(Effect.provide(Layer.mergeAll(requestExecutorLayer, llmClientLayer)))
|
||||
}).pipe(Effect.provide(Layer.mergeAll(llmDeps, llmClientLayer)))
|
||||
|
||||
Effect.runPromise(program)
|
||||
|
||||
@@ -38,7 +38,7 @@ const resolve = (policy: CachePolicy | undefined): CachePolicyObject => {
|
||||
// Protocols whose wire format ignores inline cache markers (OpenAI's implicit
|
||||
// prefix caching, Gemini's implicit + out-of-band CachedContent). Skip the
|
||||
// whole policy pass for these — emitting hints would be harmless but pointless.
|
||||
const RESPECTS_INLINE_HINTS = new Set(["anthropic-messages", "bedrock-converse", "openrouter"])
|
||||
const RESPECTS_INLINE_HINTS = new Set(["anthropic-messages", "bedrock-converse"])
|
||||
|
||||
const makeHint = (ttlSeconds: number | undefined): CacheHint =>
|
||||
ttlSeconds !== undefined ? new CacheHint({ type: "ephemeral", ttlSeconds }) : new CacheHint({ type: "ephemeral" })
|
||||
@@ -133,7 +133,6 @@ const countHints = (request: LLMRequest) =>
|
||||
|
||||
export const applyCachePolicy = (request: LLMRequest): LLMRequest => {
|
||||
if (!RESPECTS_INLINE_HINTS.has(request.model.route.id)) return request
|
||||
if (request.model.route.id === "openrouter" && (request.cache === undefined || request.cache === "auto")) return request
|
||||
const policy = resolve(request.cache)
|
||||
if (!policy.tools && !policy.system && !policy.messages) return request
|
||||
|
||||
|
||||
@@ -1,25 +1,25 @@
|
||||
import { Context, Effect, Layer } from "effect"
|
||||
import { RequestExecutor } from "./route/executor"
|
||||
import type { ImageOptions, ImageRequest, ImageRequestFor, ImageResponse } from "./image"
|
||||
import type { AIError } from "./schema"
|
||||
import type { LLMError } from "./schema"
|
||||
|
||||
export type Execute = RequestExecutor.Interface["execute"]
|
||||
|
||||
export interface Interface {
|
||||
readonly generate: <Options extends ImageOptions>(
|
||||
request: ImageRequestFor<Options>,
|
||||
) => Effect.Effect<ImageResponse, AIError>
|
||||
) => Effect.Effect<ImageResponse, LLMError>
|
||||
}
|
||||
|
||||
export class Service extends Context.Service<Service, Interface>()("@opencode/ImageClient") {}
|
||||
|
||||
export const generate = <Options extends ImageOptions>(
|
||||
request: ImageRequestFor<Options>,
|
||||
): Effect.Effect<ImageResponse, AIError, Service> =>
|
||||
): Effect.Effect<ImageResponse, LLMError> =>
|
||||
Effect.gen(function* () {
|
||||
const client = yield* Service
|
||||
return yield* client.generate(request)
|
||||
})
|
||||
}) as Effect.Effect<ImageResponse, LLMError>
|
||||
|
||||
export const layer: Layer.Layer<Service, never, RequestExecutor.Service> = Layer.effect(
|
||||
Service,
|
||||
|
||||
@@ -1,10 +1,13 @@
|
||||
import { Effect, Schema } from "effect"
|
||||
import { HttpOptions, InvalidRequestReason, AIError, ModelID, ProviderID, ProviderMetadata, Usage } from "./schema"
|
||||
import { HttpOptions, InvalidRequestReason, LLMError, ModelID, ProviderID, ProviderMetadata, Usage } from "./schema"
|
||||
import { ImageClient, Service, type Execute as ImageExecute } from "./image-client"
|
||||
|
||||
export interface ImageRoute<Options extends ImageOptions = ImageOptions> {
|
||||
readonly id: string
|
||||
readonly generate: (request: ImageRequestFor<Options>, execute: ImageExecute) => Effect.Effect<ImageResponse, AIError>
|
||||
readonly generate: (
|
||||
request: ImageRequestFor<Options>,
|
||||
execute: ImageExecute,
|
||||
) => Effect.Effect<ImageResponse, LLMError>
|
||||
}
|
||||
|
||||
export type ImageOptions = Record<string, unknown>
|
||||
@@ -143,13 +146,13 @@ export function request(input: ImageRequest | ImageRequestInput) {
|
||||
|
||||
export function generate<const Model extends object>(
|
||||
input: ImageRequestInput<Model>,
|
||||
): Effect.Effect<ImageResponse, AIError, Service>
|
||||
export function generate(input: ImageRequest): Effect.Effect<ImageResponse, AIError, Service>
|
||||
): Effect.Effect<ImageResponse, LLMError, Service>
|
||||
export function generate(input: ImageRequest): Effect.Effect<ImageResponse, LLMError, Service>
|
||||
export function generate(input: ImageRequest | ImageRequestInput) {
|
||||
return Effect.try({
|
||||
try: () => (input instanceof ImageRequest ? input : request(input)),
|
||||
catch: (error) =>
|
||||
new AIError({
|
||||
new LLMError({
|
||||
module: "Image",
|
||||
method: "generate",
|
||||
reason: new InvalidRequestReason({ message: error instanceof Error ? error.message : String(error) }),
|
||||
|
||||
@@ -5,8 +5,8 @@ export { Provider } from "./provider"
|
||||
export { ProviderPackage } from "./provider-package"
|
||||
export { isContextOverflow, isContextOverflowFailure } from "./provider-error"
|
||||
export type {
|
||||
RouteLanguageModelInput,
|
||||
RouteRoutedLanguageModelInput,
|
||||
RouteModelInput,
|
||||
RouteRoutedModelInput,
|
||||
Interface as LLMClientShape,
|
||||
Service as LLMClientService,
|
||||
} from "./route/client"
|
||||
@@ -33,7 +33,7 @@ export type {
|
||||
export * as LLM from "./llm"
|
||||
export type {
|
||||
Definition as ProviderDefinition,
|
||||
LanguageModelFactory as ProviderLanguageModelFactory,
|
||||
LanguageModelOptions as ProviderLanguageModelOptions,
|
||||
ModelFactory as ProviderModelFactory,
|
||||
ModelOptions as ProviderModelOptions,
|
||||
} from "./provider"
|
||||
export type { Definition as ProviderPackageDefinition, Settings as ProviderPackageSettings } from "./provider-package"
|
||||
|
||||
+22
-29
@@ -1,36 +1,36 @@
|
||||
import { Effect, JsonSchema, Schema } from "effect"
|
||||
import { LLMClient, Service } from "./route/client"
|
||||
import { LLMClient } from "./route/client"
|
||||
import {
|
||||
GenerationOptions,
|
||||
HttpOptions,
|
||||
InvalidProviderOutputReason,
|
||||
AIError,
|
||||
LLMError,
|
||||
LLMEvent,
|
||||
LLMRequest,
|
||||
LLMResponse,
|
||||
Message,
|
||||
LanguageModel,
|
||||
Model,
|
||||
SystemPart,
|
||||
ToolChoice,
|
||||
ToolDefinition,
|
||||
type ContentPart,
|
||||
type LanguageModelProviderOptions,
|
||||
type ModelProviderOptions,
|
||||
} from "./schema"
|
||||
import { make as makeTool, toDefinitions, type ToolSchema } from "./tool"
|
||||
|
||||
/** Input accepted by `LLM.request`, normalized into the canonical `LLMRequest` class. */
|
||||
export type RequestInput<SelectedLanguageModel extends LanguageModel = LanguageModel> = Omit<
|
||||
export type RequestInput<SelectedModel extends Model = Model> = Omit<
|
||||
ConstructorParameters<typeof LLMRequest>[0],
|
||||
"model" | "system" | "messages" | "tools" | "toolChoice" | "generation" | "http" | "providerOptions"
|
||||
> & {
|
||||
readonly model: SelectedLanguageModel
|
||||
readonly model: SelectedModel
|
||||
readonly system?: string | SystemPart | ReadonlyArray<SystemPart>
|
||||
readonly prompt?: string | ContentPart | ReadonlyArray<ContentPart>
|
||||
readonly messages?: ReadonlyArray<Message | Message.Input>
|
||||
readonly tools?: ReadonlyArray<ToolDefinition.Input>
|
||||
readonly toolChoice?: ToolChoice.Input
|
||||
readonly generation?: GenerationOptions.Input
|
||||
readonly providerOptions?: NoInfer<LanguageModelProviderOptions<SelectedLanguageModel>>
|
||||
readonly providerOptions?: NoInfer<ModelProviderOptions<SelectedModel>>
|
||||
readonly http?: HttpOptions.Input
|
||||
}
|
||||
|
||||
@@ -38,9 +38,7 @@ export const generate = LLMClient.generate
|
||||
|
||||
export const stream = LLMClient.stream
|
||||
|
||||
export const request = <const SelectedLanguageModel extends LanguageModel>(
|
||||
input: RequestInput<SelectedLanguageModel>,
|
||||
) => {
|
||||
export const request = <const SelectedModel extends Model>(input: RequestInput<SelectedModel>) => {
|
||||
const {
|
||||
system: requestSystem,
|
||||
prompt,
|
||||
@@ -68,10 +66,7 @@ const GENERATE_OBJECT_TOOL_NAME = "generate_object"
|
||||
|
||||
const GENERATE_OBJECT_TOOL_DESCRIPTION = "Return the structured result by calling this tool."
|
||||
|
||||
type GenerateObjectBase<SelectedLanguageModel extends LanguageModel = LanguageModel> = Omit<
|
||||
RequestInput<SelectedLanguageModel>,
|
||||
"tools" | "toolChoice"
|
||||
>
|
||||
type GenerateObjectBase<SelectedModel extends Model = Model> = Omit<RequestInput<SelectedModel>, "tools" | "toolChoice">
|
||||
|
||||
export class GenerateObjectResponse<T> {
|
||||
constructor(
|
||||
@@ -88,15 +83,13 @@ export class GenerateObjectResponse<T> {
|
||||
}
|
||||
}
|
||||
|
||||
export interface GenerateObjectOptions<
|
||||
S extends ToolSchema<any>,
|
||||
SelectedLanguageModel extends LanguageModel = LanguageModel,
|
||||
> extends GenerateObjectBase<SelectedLanguageModel> {
|
||||
export interface GenerateObjectOptions<S extends ToolSchema<any>, SelectedModel extends Model = Model>
|
||||
extends GenerateObjectBase<SelectedModel> {
|
||||
readonly schema: S
|
||||
}
|
||||
|
||||
export interface GenerateObjectDynamicOptions<SelectedLanguageModel extends LanguageModel = LanguageModel>
|
||||
extends GenerateObjectBase<SelectedLanguageModel> {
|
||||
export interface GenerateObjectDynamicOptions<SelectedModel extends Model = Model>
|
||||
extends GenerateObjectBase<SelectedModel> {
|
||||
/** Raw JSON Schema object describing the expected output shape. */
|
||||
readonly jsonSchema: JsonSchema.JsonSchema
|
||||
}
|
||||
@@ -115,7 +108,7 @@ const runGenerateObject = Effect.fn("LLM.generateObject")(function* (
|
||||
(event) => LLMEvent.is.toolCall(event) && event.name === GENERATE_OBJECT_TOOL_NAME,
|
||||
)
|
||||
if (!call || !LLMEvent.is.toolCall(call))
|
||||
return yield* new AIError({
|
||||
return yield* new LLMError({
|
||||
module: "LLM",
|
||||
method: "generateObject",
|
||||
reason: new InvalidProviderOutputReason({
|
||||
@@ -125,7 +118,7 @@ const runGenerateObject = Effect.fn("LLM.generateObject")(function* (
|
||||
const object = yield* tool._decode(call.input).pipe(
|
||||
Effect.mapError(
|
||||
(error) =>
|
||||
new AIError({
|
||||
new LLMError({
|
||||
module: "LLM",
|
||||
method: "generateObject",
|
||||
reason: new InvalidProviderOutputReason({
|
||||
@@ -145,16 +138,16 @@ const runGenerateObject = Effect.fn("LLM.generateObject")(function* (
|
||||
* Two input modes:
|
||||
*
|
||||
* 1. `schema: EffectSchema<T>` — `.object` is decoded and typed as `T`.
|
||||
* Decode failures surface as `AIError`.
|
||||
* Decode failures surface as `LLMError`.
|
||||
* 2. `jsonSchema: JsonSchema.JsonSchema` — `.object` is `unknown`. Use when
|
||||
* the schema is only available at runtime (MCP, plugin manifests). Caller validates.
|
||||
*/
|
||||
export function generateObject<const SelectedLanguageModel extends LanguageModel, S extends ToolSchema<any>>(
|
||||
options: GenerateObjectOptions<S, SelectedLanguageModel>,
|
||||
): Effect.Effect<GenerateObjectResponse<Schema.Schema.Type<S>>, AIError, Service>
|
||||
export function generateObject<const SelectedLanguageModel extends LanguageModel>(
|
||||
options: GenerateObjectDynamicOptions<SelectedLanguageModel>,
|
||||
): Effect.Effect<GenerateObjectResponse<unknown>, AIError, Service>
|
||||
export function generateObject<const SelectedModel extends Model, S extends ToolSchema<any>>(
|
||||
options: GenerateObjectOptions<S, SelectedModel>,
|
||||
): Effect.Effect<GenerateObjectResponse<Schema.Schema.Type<S>>, LLMError>
|
||||
export function generateObject<const SelectedModel extends Model>(
|
||||
options: GenerateObjectDynamicOptions<SelectedModel>,
|
||||
): Effect.Effect<GenerateObjectResponse<unknown>, LLMError>
|
||||
export function generateObject(options: GenerateObjectOptions<ToolSchema<any>> | GenerateObjectDynamicOptions) {
|
||||
if ("schema" in options) {
|
||||
const { schema, ...rest } = options
|
||||
|
||||
@@ -6,7 +6,7 @@ import { Endpoint } from "../route/endpoint"
|
||||
import { Framing } from "../route/framing"
|
||||
import { Protocol } from "../route/protocol"
|
||||
import {
|
||||
AIError,
|
||||
LLMError,
|
||||
LLMEvent,
|
||||
mergeJsonRecords,
|
||||
Usage,
|
||||
@@ -242,14 +242,16 @@ const AnthropicUsage = Schema.StructWithRest(
|
||||
cache_creation_input_tokens: optionalNull(Schema.Number),
|
||||
cache_read_input_tokens: optionalNull(Schema.Number),
|
||||
server_tool_use: optionalNull(
|
||||
Schema.StructWithRest(Schema.Struct({ web_search_requests: Schema.optional(Schema.Number) }), [
|
||||
Schema.Record(Schema.String, Schema.Unknown),
|
||||
]),
|
||||
Schema.StructWithRest(
|
||||
Schema.Struct({ web_search_requests: Schema.optional(Schema.Number) }),
|
||||
[Schema.Record(Schema.String, Schema.Unknown)],
|
||||
),
|
||||
),
|
||||
output_tokens_details: optionalNull(
|
||||
Schema.StructWithRest(Schema.Struct({ thinking_tokens: Schema.optional(Schema.Number) }), [
|
||||
Schema.Record(Schema.String, Schema.Unknown),
|
||||
]),
|
||||
Schema.StructWithRest(
|
||||
Schema.Struct({ thinking_tokens: Schema.optional(Schema.Number) }),
|
||||
[Schema.Record(Schema.String, Schema.Unknown)],
|
||||
),
|
||||
),
|
||||
}),
|
||||
[Schema.Record(Schema.String, Schema.Unknown)],
|
||||
@@ -723,7 +725,8 @@ const mergeUsage = (left: Usage | undefined, right: Usage | undefined) => {
|
||||
reasoningTokens,
|
||||
totalTokens: ProviderShared.totalTokens(inputTokens, outputTokens, undefined),
|
||||
providerMetadata: {
|
||||
anthropic: mergeJsonRecords(left.providerMetadata?.["anthropic"], right.providerMetadata?.["anthropic"]) ?? {},
|
||||
anthropic:
|
||||
mergeJsonRecords(left.providerMetadata?.["anthropic"], right.providerMetadata?.["anthropic"]) ?? {},
|
||||
},
|
||||
})
|
||||
}
|
||||
@@ -813,8 +816,7 @@ const onContentBlockStart = (state: ParserState, event: AnthropicEvent): StepRes
|
||||
if (block.type === "thinking" && block.thinking !== undefined) {
|
||||
const events: LLMEvent[] = []
|
||||
const id = `reasoning-${event.index ?? 0}`
|
||||
const providerMetadata =
|
||||
block.signature === undefined ? undefined : anthropicMetadata({ signature: block.signature })
|
||||
const providerMetadata = block.signature === undefined ? undefined : anthropicMetadata({ signature: block.signature })
|
||||
const lifecycle = Lifecycle.reasoningStart(state.lifecycle, events, id, providerMetadata)
|
||||
return [
|
||||
{
|
||||
@@ -978,7 +980,7 @@ const providerErrorMessage = (event: AnthropicEvent): string => {
|
||||
}
|
||||
|
||||
const onError = (event: AnthropicEvent) =>
|
||||
new AIError({
|
||||
new LLMError({
|
||||
module: ADAPTER,
|
||||
method: "stream",
|
||||
reason: classifyProviderFailure({ message: providerErrorMessage(event), code: event.error?.type }),
|
||||
|
||||
@@ -3,7 +3,7 @@ import { Route } from "../route/client"
|
||||
import { Endpoint } from "../route/endpoint"
|
||||
import { Protocol } from "../route/protocol"
|
||||
import {
|
||||
AIError,
|
||||
LLMError,
|
||||
LLMEvent,
|
||||
Usage,
|
||||
type CacheHint,
|
||||
@@ -11,7 +11,7 @@ import {
|
||||
type FinishReasonDetails,
|
||||
type JsonSchema,
|
||||
type LLMRequest,
|
||||
type LanguageModelToolSchemaCompatibility,
|
||||
type ModelToolSchemaCompatibility,
|
||||
type ProviderMetadata,
|
||||
type ReasoningPart,
|
||||
type ToolCallPart,
|
||||
@@ -232,7 +232,7 @@ const lowerToolSpec = (tool: ToolDefinition, inputSchema: JsonSchema): BedrockTo
|
||||
})
|
||||
|
||||
const lowerTools = (
|
||||
compatibility: LanguageModelToolSchemaCompatibility | undefined,
|
||||
compatibility: ModelToolSchemaCompatibility | undefined,
|
||||
breakpoints: BedrockCache.Breakpoints,
|
||||
tools: ReadonlyArray<ToolDefinition>,
|
||||
): BedrockTool[] => {
|
||||
@@ -274,7 +274,9 @@ const reasoningSignature = (part: ReasoningPart) => {
|
||||
|
||||
const reasoningRedactedData = (part: ReasoningPart) => {
|
||||
const bedrock = part.providerMetadata?.bedrock
|
||||
return ProviderShared.isRecord(bedrock) && typeof bedrock.redactedData === "string" ? bedrock.redactedData : undefined
|
||||
return ProviderShared.isRecord(bedrock) && typeof bedrock.redactedData === "string"
|
||||
? bedrock.redactedData
|
||||
: undefined
|
||||
}
|
||||
|
||||
const lowerToolCall = (part: ToolCallPart): BedrockToolUseBlock => ({
|
||||
@@ -654,7 +656,7 @@ const step = (state: ParserState, event: BedrockEvent) =>
|
||||
] as const
|
||||
).find((entry) => entry[1] !== undefined)
|
||||
if (exception) {
|
||||
return yield* new AIError({
|
||||
return yield* new LLMError({
|
||||
module: ADAPTER,
|
||||
method: "stream",
|
||||
reason: classifyProviderFailure({
|
||||
|
||||
@@ -444,7 +444,6 @@ const mapUsage = (usage: GeminiUsage | undefined) => {
|
||||
}
|
||||
|
||||
const mapFinishReason = (finishReason: string | undefined, hasToolCalls: boolean): FinishReason => {
|
||||
if (finishReason === undefined) return hasToolCalls ? "tool-calls" : "unknown"
|
||||
if (finishReason === "STOP") return hasToolCalls ? "tool-calls" : "stop"
|
||||
if (finishReason === "MAX_TOKENS") return "length"
|
||||
if (
|
||||
|
||||
@@ -11,7 +11,7 @@ import {
|
||||
import { Auth, type Definition as AuthDefinition } from "../route/auth"
|
||||
import {
|
||||
InvalidProviderOutputReason,
|
||||
AIError,
|
||||
LLMError,
|
||||
Usage,
|
||||
mergeHttpOptions,
|
||||
mergeJsonRecords,
|
||||
@@ -125,7 +125,7 @@ const nativeOptions = (options: GoogleImageOptions | undefined) => {
|
||||
}
|
||||
|
||||
const invalidOutput = (message: string, providerMetadata?: ProviderMetadata) =>
|
||||
new AIError({
|
||||
new LLMError({
|
||||
module: ADAPTER,
|
||||
method: "generate",
|
||||
reason: new InvalidProviderOutputReason({ message, route: ADAPTER, providerMetadata }),
|
||||
@@ -285,7 +285,7 @@ export const model = (input: ModelInput) => {
|
||||
return ImageModel.make<GoogleImageOptions>({ id: input.id, provider: "google", route, http: input.http })
|
||||
}
|
||||
|
||||
const googleImagePart = (image: ImageInput): Effect.Effect<Record<string, unknown>, AIError> => {
|
||||
const googleImagePart = (image: ImageInput): Effect.Effect<Record<string, unknown>, LLMError> => {
|
||||
if (image.type === "bytes")
|
||||
return Effect.succeed({ inlineData: { mimeType: image.mediaType, data: Encoding.encodeBase64(image.data) } })
|
||||
if (image.type === "file-uri") return Effect.succeed({ fileData: { mimeType: image.mediaType, fileUri: image.uri } })
|
||||
|
||||
@@ -3,7 +3,7 @@ import type { Content } from "@opencode-ai/schema/tool"
|
||||
import { HttpTransport } from "../route/transport"
|
||||
import { Protocol } from "../route/protocol"
|
||||
import {
|
||||
AIError,
|
||||
LLMError,
|
||||
LLMEvent,
|
||||
Usage,
|
||||
type FinishReason,
|
||||
@@ -211,43 +211,11 @@ export type StreamItem = Schema.Schema.Type<typeof StreamItem>
|
||||
// event-level `error` envelope, so accept all three shapes here.
|
||||
// https://www.openresponses.org/specification
|
||||
const OpenResponsesErrorPayload = Schema.Struct({
|
||||
type: optionalNull(Schema.String),
|
||||
code: optionalNull(Schema.String),
|
||||
message: optionalNull(Schema.String),
|
||||
param: optionalNull(Schema.String),
|
||||
})
|
||||
|
||||
const WebSocketErrorHeader = Schema.Union([Schema.String, Schema.Number, Schema.Boolean])
|
||||
export const WebSocketErrorEvent = Schema.StructWithRest(
|
||||
Schema.Struct({
|
||||
type: Schema.tag("error"),
|
||||
status: Schema.optional(Schema.Number),
|
||||
status_code: Schema.optional(Schema.Number),
|
||||
code: optionalNull(Schema.String),
|
||||
message: Schema.optional(Schema.String),
|
||||
param: optionalNull(Schema.String),
|
||||
error: optionalNull(OpenResponsesErrorPayload),
|
||||
headers: Schema.optional(Schema.Record(Schema.String, WebSocketErrorHeader)),
|
||||
}),
|
||||
[Schema.Record(Schema.String, Schema.Unknown)],
|
||||
)
|
||||
const decodeWebSocketErrorEvent = Schema.decodeUnknownEffect(WebSocketErrorEvent)
|
||||
|
||||
export const decodeKnownErrorEvent = (event: Event) =>
|
||||
decodeWebSocketErrorEvent({
|
||||
...event,
|
||||
status: typeof event.status === "number" ? event.status : undefined,
|
||||
status_code: typeof event.status_code === "number" ? event.status_code : undefined,
|
||||
headers: ProviderShared.isRecord(event.headers)
|
||||
? Object.fromEntries(
|
||||
Object.entries(event.headers).filter(
|
||||
(entry): entry is [string, string | number | boolean] =>
|
||||
typeof entry[1] === "string" || typeof entry[1] === "number" || typeof entry[1] === "boolean",
|
||||
),
|
||||
)
|
||||
: undefined,
|
||||
})
|
||||
|
||||
export const Event = Schema.StructWithRest(
|
||||
Schema.Struct({
|
||||
type: Schema.String,
|
||||
@@ -272,9 +240,6 @@ export const Event = Schema.StructWithRest(
|
||||
message: Schema.optional(Schema.String),
|
||||
param: optionalNull(Schema.String),
|
||||
error: optionalNull(OpenResponsesErrorPayload),
|
||||
status: Schema.optional(Schema.Unknown),
|
||||
status_code: Schema.optional(Schema.Unknown),
|
||||
headers: Schema.optional(Schema.Unknown),
|
||||
}),
|
||||
[Schema.Record(Schema.String, Schema.Unknown)],
|
||||
)
|
||||
@@ -469,7 +434,10 @@ const lowerMessages = Effect.fn("OpenResponses.lowerMessages")(function* (reques
|
||||
const groups = content.reduce<Array<{ phase: MessagePhase | null | undefined; parts: TextPart[] }>>(
|
||||
(groups, part) => {
|
||||
const metadata = part.providerMetadata?.[providerMetadataKey]
|
||||
const phase = ProviderShared.isRecord(metadata) ? messagePhase(metadata.phase, extension) : undefined
|
||||
const phase =
|
||||
ProviderShared.isRecord(metadata)
|
||||
? messagePhase(metadata.phase, extension)
|
||||
: undefined
|
||||
const group = groups.at(-1)
|
||||
if (group && group.phase === phase) group.parts.push(part)
|
||||
else groups.push({ phase, parts: [part] })
|
||||
@@ -667,9 +635,9 @@ export type StepResult = readonly [ParserState, ReadonlyArray<LLMEvent>]
|
||||
const NO_EVENTS: StepResult["1"] = []
|
||||
|
||||
// `response.completed` / `response.incomplete` are clean finishes that emit a
|
||||
// `finish` event; `response.failed` and `error` are hard failures. All four end
|
||||
// the stream, so keep this set aligned with `step` and the protocol's terminal predicate.
|
||||
const TERMINAL_TYPES = new Set(["error", "response.completed", "response.incomplete", "response.failed"])
|
||||
// `finish` event; `response.failed` is a hard failure. All three end the stream,
|
||||
// so keep this set aligned with `step` and the protocol's terminal predicate.
|
||||
const TERMINAL_TYPES = new Set(["response.completed", "response.incomplete", "response.failed"])
|
||||
export const terminal = (event: Event) => TERMINAL_TYPES.has(event.type)
|
||||
|
||||
const onOutputTextDelta = (state: ParserState, event: Event, id: string): StepResult => {
|
||||
@@ -678,7 +646,10 @@ const onOutputTextDelta = (state: ParserState, event: Event, id: string): StepRe
|
||||
const phase = state.messagePhases[id]
|
||||
const metadata = phase === undefined ? undefined : providerMetadata(state, { phase })
|
||||
const lifecycle = Lifecycle.textStart(state.lifecycle, events, id, metadata)
|
||||
return [{ ...state, lifecycle: Lifecycle.textDelta(lifecycle, events, id, event.delta) }, events]
|
||||
return [
|
||||
{ ...state, lifecycle: Lifecycle.textDelta(lifecycle, events, id, event.delta) },
|
||||
events,
|
||||
]
|
||||
}
|
||||
|
||||
const onOutputTextDone = (state: ParserState, event: Event, id: string): StepResult => {
|
||||
@@ -1001,24 +972,16 @@ const providerErrorMessage = (event: Event, fallback: string): string => {
|
||||
return message || code || fallback
|
||||
}
|
||||
|
||||
export const providerFailure = (id: string, event: Event, fallback: string) => {
|
||||
const providerError = (state: ParserState, event: Event, fallback: string) => {
|
||||
const code = event.code || event.error?.code || event.response?.error?.code || undefined
|
||||
const message = providerErrorMessage(event, fallback)
|
||||
const status =
|
||||
typeof event.status === "number"
|
||||
? event.status
|
||||
: typeof event.status_code === "number"
|
||||
? event.status_code
|
||||
: undefined
|
||||
return new AIError({
|
||||
module: id,
|
||||
return new LLMError({
|
||||
module: state.id,
|
||||
method: "stream",
|
||||
reason: classifyProviderFailure({ message, code, status }),
|
||||
reason: classifyProviderFailure({ message, code }),
|
||||
})
|
||||
}
|
||||
|
||||
const providerError = (state: ParserState, event: Event, fallback: string) => providerFailure(state.id, event, fallback)
|
||||
|
||||
export const step = (state: ParserState, event: Event) => {
|
||||
if (event.type === "response.output_text.delta" || event.type === "response.output_text.done") {
|
||||
if (!event.item_id) return ProviderShared.eventError(state.id, `${event.type} is missing item_id`)
|
||||
@@ -1058,11 +1021,7 @@ export const step = (state: ParserState, event: Event) => {
|
||||
if (event.type === "response.completed" || event.type === "response.incomplete")
|
||||
return Effect.succeed(onResponseFinish(state, event))
|
||||
if (event.type === "response.failed") return providerError(state, event, `${state.name} response failed`)
|
||||
if (event.type === "error")
|
||||
return decodeKnownErrorEvent(event).pipe(
|
||||
Effect.mapError(() => ProviderShared.eventError(state.id, `${state.name} returned a malformed error event`)),
|
||||
Effect.flatMap(() => providerError(state, event, `${state.name} stream error`)),
|
||||
)
|
||||
if (event.type === "error") return providerError(state, event, `${state.name} stream error`)
|
||||
return Effect.succeed<StepResult>([state, NO_EVENTS])
|
||||
}
|
||||
|
||||
|
||||
@@ -6,12 +6,11 @@ import { Endpoint } from "../route/endpoint"
|
||||
import { HttpTransport } from "../route/transport"
|
||||
import { Protocol } from "../route/protocol"
|
||||
import {
|
||||
AIError,
|
||||
LLMError,
|
||||
LLMEvent,
|
||||
Usage,
|
||||
type FinishReason,
|
||||
type FinishReasonDetails,
|
||||
type CacheHint,
|
||||
type JsonSchema,
|
||||
type LLMRequest,
|
||||
type MediaPart,
|
||||
@@ -39,11 +38,6 @@ export const PATH = "/chat/completions"
|
||||
// The body schema is the provider-native JSON body. `fromRequest` below builds
|
||||
// this shape from the common `LLMRequest`, then `Route.make` validates and
|
||||
// JSON-encodes it before transport.
|
||||
const OpenAIChatCacheControl = Schema.Struct({
|
||||
type: Schema.Literal("ephemeral"),
|
||||
ttl: Schema.optional(Schema.String),
|
||||
})
|
||||
|
||||
const OpenAIChatFunction = Schema.Struct({
|
||||
name: Schema.String,
|
||||
description: Schema.String,
|
||||
@@ -53,7 +47,6 @@ const OpenAIChatFunction = Schema.Struct({
|
||||
const OpenAIChatTool = Schema.Struct({
|
||||
type: Schema.tag("function"),
|
||||
function: OpenAIChatFunction,
|
||||
cache_control: Schema.optional(OpenAIChatCacheControl),
|
||||
})
|
||||
type OpenAIChatTool = Schema.Schema.Type<typeof OpenAIChatTool>
|
||||
|
||||
@@ -68,11 +61,7 @@ const OpenAIChatAssistantToolCall = Schema.Struct({
|
||||
type OpenAIChatAssistantToolCall = Schema.Schema.Type<typeof OpenAIChatAssistantToolCall>
|
||||
|
||||
const OpenAIChatUserContent = Schema.Union([
|
||||
Schema.Struct({
|
||||
type: Schema.Literal("text"),
|
||||
text: Schema.String,
|
||||
cache_control: Schema.optional(OpenAIChatCacheControl),
|
||||
}),
|
||||
Schema.Struct({ type: Schema.Literal("text"), text: Schema.String }),
|
||||
Schema.Struct({
|
||||
type: Schema.Literal("image_url"),
|
||||
image_url: Schema.Struct({ url: Schema.String }),
|
||||
@@ -80,10 +69,7 @@ const OpenAIChatUserContent = Schema.Union([
|
||||
])
|
||||
|
||||
const OpenAIChatMessage = Schema.Union([
|
||||
Schema.Struct({
|
||||
role: Schema.Literal("system"),
|
||||
content: Schema.Union([Schema.String, Schema.Array(OpenAIChatUserContent)]),
|
||||
}),
|
||||
Schema.Struct({ role: Schema.Literal("system"), content: Schema.String }),
|
||||
Schema.Struct({
|
||||
role: Schema.Literal("user"),
|
||||
content: Schema.Union([Schema.String, Schema.Array(OpenAIChatUserContent)]),
|
||||
@@ -97,16 +83,10 @@ const OpenAIChatMessage = Schema.Union([
|
||||
reasoning: Schema.optional(Schema.String),
|
||||
reasoning_text: Schema.optional(Schema.String),
|
||||
reasoning_details: Schema.optional(Schema.Unknown),
|
||||
cache_control: Schema.optional(OpenAIChatCacheControl),
|
||||
}),
|
||||
[Schema.Record(Schema.String, Schema.Unknown)],
|
||||
),
|
||||
Schema.Struct({
|
||||
role: Schema.Literal("tool"),
|
||||
tool_call_id: Schema.String,
|
||||
content: Schema.String,
|
||||
cache_control: Schema.optional(OpenAIChatCacheControl),
|
||||
}),
|
||||
Schema.Struct({ role: Schema.Literal("tool"), tool_call_id: Schema.String, content: Schema.String }),
|
||||
]).pipe(Schema.toTaggedUnion("role"))
|
||||
type OpenAIChatMessage = Schema.Schema.Type<typeof OpenAIChatMessage>
|
||||
|
||||
@@ -127,7 +107,6 @@ export const bodyFields = {
|
||||
stream_options: Schema.optional(Schema.Struct({ include_usage: Schema.Boolean })),
|
||||
store: Schema.optional(Schema.Boolean),
|
||||
reasoning_effort: Schema.optional(OpenAIOptions.OpenAIReasoningEffort),
|
||||
max_completion_tokens: Schema.optional(Schema.Number),
|
||||
max_tokens: Schema.optional(Schema.Number),
|
||||
temperature: Schema.optional(Schema.Number),
|
||||
top_p: Schema.optional(Schema.Number),
|
||||
@@ -230,20 +209,13 @@ export interface ParserState {
|
||||
// Lowering is the only place that knows how common LLM messages map onto the
|
||||
// OpenAI Chat wire format. Keep provider quirks here instead of leaking native
|
||||
// fields into `LLMRequest`.
|
||||
interface LoweringOptions {
|
||||
readonly cacheControl?: (
|
||||
cache: CacheHint | undefined,
|
||||
) => Schema.Schema.Type<typeof OpenAIChatCacheControl> | undefined
|
||||
}
|
||||
|
||||
const lowerTool = (tool: ToolDefinition, inputSchema: JsonSchema, options: LoweringOptions): OpenAIChatTool => ({
|
||||
const lowerTool = (tool: ToolDefinition, inputSchema: JsonSchema): OpenAIChatTool => ({
|
||||
type: "function",
|
||||
function: {
|
||||
name: tool.name,
|
||||
description: tool.description,
|
||||
parameters: ToolSchemaProjection.openAI(inputSchema),
|
||||
},
|
||||
cache_control: options.cacheControl?.(tool.cache),
|
||||
})
|
||||
|
||||
const lowerToolChoice = (toolChoice: NonNullable<LLMRequest["toolChoice"]>) =>
|
||||
@@ -285,14 +257,11 @@ const reasoningDetails = (parts: ReadonlyArray<ReasoningPart>, native: unknown)
|
||||
if (isRecord(native) && Array.isArray(native.reasoning_details)) return native.reasoning_details
|
||||
}
|
||||
|
||||
const lowerUserMessage = Effect.fn("OpenAIChat.lowerUserMessage")(function* (
|
||||
message: OpenAIChatRequestMessage,
|
||||
options: LoweringOptions,
|
||||
) {
|
||||
const lowerUserMessage = Effect.fn("OpenAIChat.lowerUserMessage")(function* (message: OpenAIChatRequestMessage) {
|
||||
const content: Array<Schema.Schema.Type<typeof OpenAIChatUserContent>> = []
|
||||
for (const part of message.content) {
|
||||
if (part.type === "text") {
|
||||
content.push({ type: "text", text: part.text, cache_control: options.cacheControl?.(part.cache) })
|
||||
content.push({ type: "text", text: part.text })
|
||||
continue
|
||||
}
|
||||
if (part.type === "media") {
|
||||
@@ -301,18 +270,14 @@ const lowerUserMessage = Effect.fn("OpenAIChat.lowerUserMessage")(function* (
|
||||
}
|
||||
return yield* ProviderShared.unsupportedContent("OpenAI Chat", "user", ["text", "media"])
|
||||
}
|
||||
if (content.every((part) => part.type === "text" && part.cache_control === undefined))
|
||||
return {
|
||||
role: "user" as const,
|
||||
content: content.map((part) => (part.type === "text" ? part.text : "")).join(""),
|
||||
}
|
||||
if (content.every((part) => part.type === "text"))
|
||||
return { role: "user" as const, content: content.map((part) => part.text).join("") }
|
||||
return { role: "user" as const, content }
|
||||
})
|
||||
|
||||
const lowerAssistantMessage = Effect.fn("OpenAIChat.lowerAssistantMessage")(function* (
|
||||
message: OpenAIChatRequestMessage,
|
||||
configuredField?: string,
|
||||
options: LoweringOptions = {},
|
||||
) {
|
||||
const content: TextPart[] = []
|
||||
const reasoning: ReasoningPart[] = []
|
||||
@@ -350,44 +315,29 @@ const lowerAssistantMessage = Effect.fn("OpenAIChat.lowerAssistantMessage")(func
|
||||
if (reasoning.length === 0) return nativeReasoning
|
||||
return text
|
||||
})()
|
||||
const cached = message.content.findLast((part) => "cache" in part && part.cache !== undefined)
|
||||
const result = {
|
||||
role: "assistant" as const,
|
||||
content: content.length === 0 ? null : ProviderShared.joinText(content),
|
||||
tool_calls: toolCalls.length === 0 ? undefined : toolCalls,
|
||||
reasoning_details: details,
|
||||
cache_control: options.cacheControl?.(cached && "cache" in cached ? cached.cache : undefined),
|
||||
}
|
||||
if (field === undefined || reasoningText === undefined) return result
|
||||
return { ...result, [field]: reasoningText }
|
||||
})
|
||||
|
||||
const lowerToolMessages = Effect.fn("OpenAIChat.lowerToolMessages")(function* (
|
||||
message: OpenAIChatRequestMessage,
|
||||
options: LoweringOptions,
|
||||
) {
|
||||
const lowerToolMessages = Effect.fn("OpenAIChat.lowerToolMessages")(function* (message: OpenAIChatRequestMessage) {
|
||||
const messages: OpenAIChatMessage[] = []
|
||||
const images: Array<Schema.Schema.Type<typeof OpenAIChatUserContent>> = []
|
||||
for (const part of message.content) {
|
||||
if (!ProviderShared.supportsContent(part, ["tool-result"]))
|
||||
return yield* ProviderShared.unsupportedContent("OpenAI Chat", "tool", ["tool-result"])
|
||||
if (part.result.type !== "content") {
|
||||
messages.push({
|
||||
role: "tool",
|
||||
tool_call_id: part.id,
|
||||
content: ProviderShared.toolResultText(part),
|
||||
cache_control: options.cacheControl?.(part.cache),
|
||||
})
|
||||
messages.push({ role: "tool", tool_call_id: part.id, content: ProviderShared.toolResultText(part) })
|
||||
continue
|
||||
}
|
||||
const content: ReadonlyArray<Tool.Content> = part.result.value
|
||||
const text = content.filter((item) => item.type === "text").map((item) => item.text)
|
||||
messages.push({
|
||||
role: "tool",
|
||||
tool_call_id: part.id,
|
||||
content: text.join("\n"),
|
||||
cache_control: options.cacheControl?.(part.cache),
|
||||
})
|
||||
messages.push({ role: "tool", tool_call_id: part.id, content: text.join("\n") })
|
||||
const files = content.filter((item) => item.type === "file")
|
||||
images.push(
|
||||
...(yield* Effect.forEach(files, (item) =>
|
||||
@@ -401,29 +351,15 @@ const lowerToolMessages = Effect.fn("OpenAIChat.lowerToolMessages")(function* (
|
||||
const lowerMessage = Effect.fn("OpenAIChat.lowerMessage")(function* (
|
||||
message: OpenAIChatRequestMessage,
|
||||
reasoningField?: string,
|
||||
options: LoweringOptions = {},
|
||||
) {
|
||||
if (message.role === "user") return [yield* lowerUserMessage(message, options)]
|
||||
if (message.role === "assistant") return [yield* lowerAssistantMessage(message, reasoningField, options)]
|
||||
return (yield* lowerToolMessages(message, options)).messages
|
||||
if (message.role === "user") return [yield* lowerUserMessage(message)]
|
||||
if (message.role === "assistant") return [yield* lowerAssistantMessage(message, reasoningField)]
|
||||
return (yield* lowerToolMessages(message)).messages
|
||||
})
|
||||
|
||||
const lowerMessages = Effect.fn("OpenAIChat.lowerMessages")(function* (request: LLMRequest, options: LoweringOptions) {
|
||||
const lowerMessages = Effect.fn("OpenAIChat.lowerMessages")(function* (request: LLMRequest) {
|
||||
const system: OpenAIChatMessage[] =
|
||||
request.system.length === 0
|
||||
? []
|
||||
: request.system.some((part) => part.cache !== undefined) && options.cacheControl !== undefined
|
||||
? [
|
||||
{
|
||||
role: "system",
|
||||
content: request.system.map((part) => ({
|
||||
type: "text",
|
||||
text: part.text,
|
||||
cache_control: options.cacheControl?.(part.cache),
|
||||
})),
|
||||
},
|
||||
]
|
||||
: [{ role: "system", content: ProviderShared.joinText(request.system) }]
|
||||
request.system.length === 0 ? [] : [{ role: "system", content: ProviderShared.joinText(request.system) }]
|
||||
const messages = [...system]
|
||||
const pendingImages: Array<Schema.Schema.Type<typeof OpenAIChatUserContent>> = []
|
||||
const flushImages = () => {
|
||||
@@ -434,53 +370,28 @@ const lowerMessages = Effect.fn("OpenAIChat.lowerMessages")(function* (request:
|
||||
if (message.role === "system") {
|
||||
const part = yield* ProviderShared.wrappedSystemUpdate("OpenAI Chat", message)
|
||||
if (pendingImages.length > 0) {
|
||||
messages.push({
|
||||
role: "user",
|
||||
content: [
|
||||
...pendingImages.splice(0),
|
||||
{ type: "text", text: part.text, cache_control: options.cacheControl?.(part.cache) },
|
||||
],
|
||||
})
|
||||
messages.push({ role: "user", content: [...pendingImages.splice(0), { type: "text", text: part.text }] })
|
||||
continue
|
||||
}
|
||||
const previous = messages.at(-1)
|
||||
if (previous?.role === "user" && typeof previous.content === "string")
|
||||
messages[messages.length - 1] = options.cacheControl?.(part.cache)
|
||||
? {
|
||||
role: "user",
|
||||
content: [
|
||||
{ type: "text", text: previous.content },
|
||||
{ type: "text", text: part.text, cache_control: options.cacheControl(part.cache) },
|
||||
],
|
||||
}
|
||||
: { role: "user", content: `${previous.content}\n${part.text}` }
|
||||
messages[messages.length - 1] = { role: "user", content: `${previous.content}\n${part.text}` }
|
||||
else if (previous?.role === "user" && Array.isArray(previous.content))
|
||||
messages[messages.length - 1] = {
|
||||
role: "user",
|
||||
content: [
|
||||
...previous.content,
|
||||
{ type: "text", text: part.text, cache_control: options.cacheControl?.(part.cache) },
|
||||
],
|
||||
content: [...previous.content, { type: "text", text: part.text }],
|
||||
}
|
||||
else
|
||||
messages.push(
|
||||
options.cacheControl?.(part.cache)
|
||||
? {
|
||||
role: "user",
|
||||
content: [{ type: "text", text: part.text, cache_control: options.cacheControl(part.cache) }],
|
||||
}
|
||||
: { role: "user", content: part.text },
|
||||
)
|
||||
else messages.push({ role: "user", content: part.text })
|
||||
continue
|
||||
}
|
||||
if (message.role === "tool") {
|
||||
const lowered = yield* lowerToolMessages(message, options)
|
||||
const lowered = yield* lowerToolMessages(message)
|
||||
messages.push(...lowered.messages)
|
||||
pendingImages.push(...lowered.images)
|
||||
continue
|
||||
}
|
||||
flushImages()
|
||||
messages.push(...(yield* lowerMessage(message, request.model.compatibility?.reasoningField, options)))
|
||||
messages.push(...(yield* lowerMessage(message, request.model.compatibility?.reasoningField)))
|
||||
}
|
||||
flushImages()
|
||||
return messages
|
||||
@@ -494,10 +405,7 @@ const lowerOptions = (request: LLMRequest) => {
|
||||
}
|
||||
}
|
||||
|
||||
export const fromRequest = Effect.fn("OpenAIChat.fromRequest")(function* (
|
||||
request: LLMRequest,
|
||||
options: LoweringOptions = {},
|
||||
) {
|
||||
const fromRequest = Effect.fn("OpenAIChat.fromRequest")(function* (request: LLMRequest) {
|
||||
// `fromRequest` returns the provider body only. Endpoint, auth, framing,
|
||||
// validation, and HTTP execution are composed by `Route.make`.
|
||||
const reasoningField = request.model.compatibility?.reasoningField
|
||||
@@ -507,26 +415,19 @@ export const fromRequest = Effect.fn("OpenAIChat.fromRequest")(function* (
|
||||
)
|
||||
const generation = request.generation
|
||||
const toolSchemaCompatibility = request.model.compatibility?.toolSchema
|
||||
const maxTokensField = request.model.compatibility?.maxTokensField ?? "max_tokens"
|
||||
return {
|
||||
model: request.model.id,
|
||||
messages: yield* lowerMessages(request, options),
|
||||
messages: yield* lowerMessages(request),
|
||||
tools:
|
||||
request.tools.length === 0
|
||||
? undefined
|
||||
: request.tools.map((tool) =>
|
||||
lowerTool(
|
||||
tool,
|
||||
ToolSchemaProjection.modelCompatibility(tool.inputSchema, toolSchemaCompatibility),
|
||||
options,
|
||||
),
|
||||
lowerTool(tool, ToolSchemaProjection.modelCompatibility(tool.inputSchema, toolSchemaCompatibility)),
|
||||
),
|
||||
tool_choice: request.toolChoice ? yield* lowerToolChoice(request.toolChoice) : undefined,
|
||||
stream: true as const,
|
||||
stream_options: { include_usage: true },
|
||||
...(maxTokensField === "max_completion_tokens"
|
||||
? { max_completion_tokens: generation?.maxTokens }
|
||||
: { max_tokens: generation?.maxTokens }),
|
||||
max_tokens: generation?.maxTokens,
|
||||
temperature: generation?.temperature,
|
||||
top_p: generation?.topP,
|
||||
frequency_penalty: generation?.frequencyPenalty,
|
||||
@@ -555,7 +456,7 @@ const mapFinishReason = (reason: string | null | undefined): FinishReason => {
|
||||
// OpenAI Chat reports `prompt_tokens` (inclusive total) with a
|
||||
// cached-read and cache-write subsets, and `completion_tokens` (inclusive
|
||||
// total) with a `reasoning_tokens` subset. We pass the inclusive totals
|
||||
// through and derive the non-cached breakdown so the `AI.Usage` contract is
|
||||
// through and derive the non-cached breakdown so the `LLM.Usage` contract is
|
||||
// satisfied on both sides.
|
||||
const mapUsage = (usage: OpenAIChatEvent["usage"]): Usage | undefined => {
|
||||
if (!usage) return undefined
|
||||
@@ -645,7 +546,7 @@ const reasoningMetadata = (field: ParserState["reasoningField"], details?: Reado
|
||||
const step = (state: ParserState, event: OpenAIChatEvent) =>
|
||||
Effect.gen(function* () {
|
||||
if (event.error)
|
||||
return yield* new AIError({
|
||||
return yield* new LLMError({
|
||||
module: ADAPTER,
|
||||
method: "stream",
|
||||
reason: classifyProviderFailure({
|
||||
|
||||
@@ -1,11 +1,11 @@
|
||||
import { Route, type RouteRoutedLanguageModelInput } from "../route/client"
|
||||
import { Route, type RouteRoutedModelInput } from "../route/client"
|
||||
import { Endpoint } from "../route/endpoint"
|
||||
import { Framing } from "../route/framing"
|
||||
import * as OpenAIChat from "./openai-chat"
|
||||
|
||||
const ADAPTER = "openai-compatible-chat"
|
||||
|
||||
export type OpenAICompatibleChatLanguageModelInput = RouteRoutedLanguageModelInput
|
||||
export type OpenAICompatibleChatModelInput = RouteRoutedModelInput
|
||||
|
||||
/**
|
||||
* Route for non-OpenAI providers that expose an OpenAI Chat-compatible
|
||||
|
||||
@@ -1,10 +1,10 @@
|
||||
import { Route, type RouteRoutedLanguageModelInput } from "../route/client"
|
||||
import { Route, type RouteRoutedModelInput } from "../route/client"
|
||||
import { Endpoint } from "../route/endpoint"
|
||||
import { OpenResponses } from "./open-responses"
|
||||
|
||||
const ADAPTER = "openai-compatible-responses"
|
||||
|
||||
export type OpenAICompatibleResponsesLanguageModelInput = RouteRoutedLanguageModelInput
|
||||
export type OpenAICompatibleResponsesModelInput = RouteRoutedModelInput
|
||||
|
||||
/**
|
||||
* Deployment adapter for providers that expose an Open Responses-compatible
|
||||
|
||||
@@ -11,7 +11,7 @@ import {
|
||||
import { Auth, type Definition as AuthDefinition } from "../route/auth"
|
||||
import {
|
||||
InvalidProviderOutputReason,
|
||||
AIError,
|
||||
LLMError,
|
||||
Usage,
|
||||
mergeHttpOptions,
|
||||
mergeJsonRecords,
|
||||
@@ -85,7 +85,7 @@ const nativeOptions = (options: OpenAIImageOptions | undefined) => {
|
||||
}
|
||||
|
||||
const invalidOutput = (message: string) =>
|
||||
new AIError({
|
||||
new LLMError({
|
||||
module: ADAPTER,
|
||||
method: "generate",
|
||||
reason: new InvalidProviderOutputReason({ message, route: ADAPTER }),
|
||||
|
||||
@@ -1,37 +0,0 @@
|
||||
import { Effect, Schema } from "effect"
|
||||
import type { WebSocketChannelDriver } from "../route/transport"
|
||||
import * as ProviderShared from "./shared"
|
||||
import { OpenResponses } from "./open-responses"
|
||||
|
||||
const ADAPTER = "openai-responses"
|
||||
const NAME = "OpenAI Responses"
|
||||
const decodeEvent = Schema.decodeUnknownEffect(OpenResponses.protocol.stream.event)
|
||||
|
||||
export const make = (message: string): WebSocketChannelDriver => ({
|
||||
create: () => Effect.succeed({ message, mode: "full" }),
|
||||
observe: (_create, frame) =>
|
||||
Effect.gen(function* () {
|
||||
const event = yield* decodeEvent(frame).pipe(
|
||||
Effect.mapError(() => ProviderShared.eventError(ADAPTER, "Invalid OpenAI Responses WebSocket event", frame)),
|
||||
)
|
||||
if (event.type === "response.completed") return { type: "completed", frame }
|
||||
if (event.type === "response.incomplete") return { type: "incomplete", frame }
|
||||
if (event.type === "response.failed")
|
||||
return {
|
||||
type: "provider-failure",
|
||||
error: OpenResponses.providerFailure(ADAPTER, event, `${NAME} response failed`),
|
||||
}
|
||||
if (event.type === "error") {
|
||||
yield* OpenResponses.decodeKnownErrorEvent(event).pipe(
|
||||
Effect.mapError(() => ProviderShared.eventError(ADAPTER, `${NAME} returned a malformed error event`, frame)),
|
||||
)
|
||||
return {
|
||||
type: "provider-failure",
|
||||
error: OpenResponses.providerFailure(ADAPTER, event, `${NAME} stream error`),
|
||||
}
|
||||
}
|
||||
return { type: "frame", frame }
|
||||
}),
|
||||
})
|
||||
|
||||
export const OpenAIResponsesChannel = { make } as const
|
||||
@@ -1,24 +1,15 @@
|
||||
import { Effect, Encoding, Schema, Stream } from "effect"
|
||||
import { Headers } from "effect/unstable/http"
|
||||
import { Effect, Encoding, Schema } from "effect"
|
||||
import { Route } from "../route/client"
|
||||
import { Auth } from "../route/auth"
|
||||
import { Endpoint } from "../route/endpoint"
|
||||
import { Framing } from "../route/framing"
|
||||
import { Protocol } from "../route/protocol"
|
||||
import {
|
||||
HttpTransport,
|
||||
WebSocketTransport,
|
||||
type Transport,
|
||||
type WebSocketChannelDriver,
|
||||
type WebSocketChannelExchange,
|
||||
} from "../route/transport"
|
||||
import { HttpTransport, WebSocketTransport } from "../route/transport"
|
||||
import { LLMEvent, LLMRequest, type JsonSchema, type ToolDefinition } from "../schema"
|
||||
import { OpenResponses } from "./open-responses"
|
||||
import { optionalArray, ProviderShared } from "./shared"
|
||||
import { Lifecycle } from "./utils/lifecycle"
|
||||
import { OpenAIImage } from "./utils/openai-image"
|
||||
import { ToolSchemaProjection } from "./utils/tool-schema"
|
||||
import { OpenAIResponsesChannel } from "./openai-responses-channel"
|
||||
|
||||
const ADAPTER = "openai-responses"
|
||||
const NAME = "OpenAI Responses"
|
||||
@@ -259,6 +250,17 @@ const auth = Auth.none
|
||||
|
||||
export const httpTransport = HttpTransport.sseJson.with<OpenAIResponsesBody>()
|
||||
|
||||
export const route = Route.make({
|
||||
id: ADAPTER,
|
||||
provider: "openai",
|
||||
providerMetadataKey: "openai",
|
||||
protocol,
|
||||
endpoint,
|
||||
auth,
|
||||
transport: httpTransport,
|
||||
defaults: { providerOptions: { openai: { store: false } } },
|
||||
})
|
||||
|
||||
const decodeWebSocketMessage = ProviderShared.validateWith(Schema.decodeUnknownEffect(OpenAIResponsesWebSocketMessage))
|
||||
|
||||
const webSocketMessage = (body: OpenAIResponsesBody | Record<string, unknown>) =>
|
||||
@@ -269,58 +271,22 @@ const webSocketMessage = (body: OpenAIResponsesBody | Record<string, unknown>) =
|
||||
return yield* decodeWebSocketMessage({ ...message, type: "response.create" })
|
||||
})
|
||||
|
||||
export interface OpenAIResponsesPrepared {
|
||||
readonly http: HttpTransport.HttpPrepared<string>
|
||||
readonly channel?: {
|
||||
readonly url: string
|
||||
readonly headers: Headers.Headers
|
||||
readonly driver: WebSocketChannelDriver
|
||||
}
|
||||
}
|
||||
export const webSocketTransport = WebSocketTransport.jsonTransport.with<
|
||||
OpenAIResponsesBody,
|
||||
OpenAIResponsesWebSocketMessage
|
||||
>({
|
||||
toMessage: webSocketMessage,
|
||||
encodeMessage: encodeWebSocketMessage,
|
||||
})
|
||||
|
||||
export const transport: Transport<OpenAIResponsesBody, OpenAIResponsesPrepared, string> = {
|
||||
id: httpTransport.id,
|
||||
prepare: (input) =>
|
||||
Effect.gen(function* () {
|
||||
const parts = yield* HttpTransport.jsonRequestParts(input)
|
||||
return {
|
||||
http: {
|
||||
request: ProviderShared.jsonPost({ url: parts.url, body: parts.bodyText, headers: parts.headers }),
|
||||
framing: Framing.sse,
|
||||
middleware: input.middleware,
|
||||
},
|
||||
channel: input.webSocket
|
||||
? {
|
||||
url: yield* WebSocketTransport.toWebSocketUrl(parts.url),
|
||||
headers: parts.headers,
|
||||
driver: OpenAIResponsesChannel.make(encodeWebSocketMessage(yield* webSocketMessage(parts.jsonBody))),
|
||||
}
|
||||
: undefined,
|
||||
}
|
||||
}),
|
||||
execute: (prepared, request, runtime, options) => {
|
||||
if (!options?.webSocket || !prepared.channel) return httpTransport.execute(prepared.http, request, runtime)
|
||||
const exchange: WebSocketChannelExchange = {
|
||||
id: request.id ?? "request",
|
||||
connect: { url: prepared.channel.url, headers: prepared.channel.headers },
|
||||
fallback: () =>
|
||||
Stream.unwrap(
|
||||
httpTransport.execute(prepared.http, request, runtime).pipe(Effect.map((execution) => execution.frames)),
|
||||
),
|
||||
driver: prepared.channel.driver,
|
||||
}
|
||||
return options.webSocket.execute(exchange)
|
||||
},
|
||||
}
|
||||
|
||||
export const route = Route.make({
|
||||
id: ADAPTER,
|
||||
export const webSocketRoute = Route.make({
|
||||
id: `${ADAPTER}-websocket`,
|
||||
provider: "openai",
|
||||
providerMetadataKey: "openai",
|
||||
protocol,
|
||||
endpoint,
|
||||
auth,
|
||||
transport,
|
||||
transport: webSocketTransport,
|
||||
defaults: { providerOptions: { openai: { store: false } } },
|
||||
})
|
||||
|
||||
|
||||
@@ -6,7 +6,7 @@ import { Headers, HttpClientRequest } from "effect/unstable/http"
|
||||
import {
|
||||
InvalidProviderOutputReason,
|
||||
InvalidRequestReason,
|
||||
AIError,
|
||||
LLMError,
|
||||
type ContentPart,
|
||||
type LLMRequest,
|
||||
type MediaPart,
|
||||
@@ -41,7 +41,7 @@ export interface ToolAccumulator {
|
||||
* when at least one is defined. Returns `undefined` when neither input nor
|
||||
* output is known so routes don't publish a misleading `0`.
|
||||
*
|
||||
* Under the additive `AI.Usage` contract, `inputTokens` and `outputTokens`
|
||||
* Under the additive `LLM.Usage` contract, `inputTokens` and `outputTokens`
|
||||
* are the non-cached input and visible output only. The provider-supplied
|
||||
* `total` is the source of truth when present; the computed fallback
|
||||
* under-counts cache and reasoning by design and exists mainly so
|
||||
@@ -88,7 +88,7 @@ export const sumTokens = (...values: ReadonlyArray<number | undefined>): number
|
||||
}
|
||||
|
||||
export const eventError = (route: string, message: string, raw?: string) =>
|
||||
new AIError({
|
||||
new LLMError({
|
||||
module: "ProviderShared",
|
||||
method: "stream",
|
||||
reason: new InvalidProviderOutputReason({ route, message, raw }),
|
||||
@@ -238,9 +238,9 @@ export const errorText = (error: unknown) => {
|
||||
* `decodeChunk` sees one JSON string per element. The SSE channel emits a
|
||||
* `Retry` control event on its error channel; we drop it here (we don't
|
||||
* implement client-driven retries) so the public error channel stays
|
||||
* `AIError`.
|
||||
* `LLMError`.
|
||||
*/
|
||||
export const sseFraming = (bytes: Stream.Stream<Uint8Array, AIError>): Stream.Stream<string, AIError> =>
|
||||
export const sseFraming = (bytes: Stream.Stream<Uint8Array, LLMError>): Stream.Stream<string, LLMError> =>
|
||||
bytes.pipe(
|
||||
Stream.decodeText(),
|
||||
Stream.pipeThroughChannel(Sse.decode()),
|
||||
@@ -257,7 +257,7 @@ export const sseFraming = (bytes: Stream.Stream<Uint8Array, AIError>): Stream.St
|
||||
* lands here.
|
||||
*/
|
||||
export const invalidRequest = (message: string) =>
|
||||
new AIError({
|
||||
new LLMError({
|
||||
module: "ProviderShared",
|
||||
method: "request",
|
||||
reason: new InvalidRequestReason({ message }),
|
||||
@@ -304,7 +304,7 @@ export const unsupportedContent = (
|
||||
* Build a `validate` step from a Schema decoder. Replaces the per-route
|
||||
* lambda body `(payload) => decode(payload).pipe(Effect.mapError((e) =>
|
||||
* invalid(e.message)))`. Any decode error is translated into
|
||||
* `AIError` carrying the original parse-error message.
|
||||
* `LLMError` carrying the original parse-error message.
|
||||
*/
|
||||
export const validateWith =
|
||||
<A, I, E extends { readonly message: string }>(decode: (input: I) => Effect.Effect<A, E>) =>
|
||||
|
||||
@@ -22,8 +22,6 @@ const signRequest = (input: {
|
||||
readonly body: string
|
||||
readonly headers: Headers.Headers
|
||||
readonly credentials: Credentials
|
||||
readonly service: string
|
||||
readonly name: string
|
||||
}) =>
|
||||
Effect.tryPromise({
|
||||
try: async () => {
|
||||
@@ -36,26 +34,23 @@ const signRequest = (input: {
|
||||
accessKeyId: input.credentials.accessKeyId,
|
||||
secretAccessKey: input.credentials.secretAccessKey,
|
||||
sessionToken: input.credentials.sessionToken,
|
||||
service: input.service,
|
||||
service: "bedrock",
|
||||
}).sign()
|
||||
return Object.fromEntries(signed.headers.entries())
|
||||
},
|
||||
catch: (error) =>
|
||||
ProviderShared.invalidRequest(
|
||||
`${input.name} SigV4 signing failed: ${error instanceof Error ? error.message : String(error)}`,
|
||||
`Bedrock Converse SigV4 signing failed: ${error instanceof Error ? error.message : String(error)}`,
|
||||
),
|
||||
})
|
||||
|
||||
/** Sign the exact JSON bytes with SigV4 using credentials configured on the route. */
|
||||
export const sigV4 = (
|
||||
credentials: Credentials | undefined,
|
||||
options: { readonly service?: string; readonly name?: string } = {},
|
||||
) =>
|
||||
export const sigV4 = (credentials: Credentials | undefined) =>
|
||||
Auth.custom((input: AuthInput) => {
|
||||
return Effect.gen(function* () {
|
||||
if (!credentials) {
|
||||
return yield* ProviderShared.invalidRequest(
|
||||
`${options.name ?? "Bedrock Converse"} requires either route bearer auth or AWS credentials configured on the route`,
|
||||
"Bedrock Converse requires either route bearer auth or AWS credentials configured on the route",
|
||||
)
|
||||
}
|
||||
const headersForSigning = Headers.set(input.headers, "content-type", "application/json")
|
||||
@@ -64,8 +59,6 @@ export const sigV4 = (
|
||||
body: input.body,
|
||||
headers: headersForSigning,
|
||||
credentials,
|
||||
service: options.service ?? "bedrock",
|
||||
name: options.name ?? "Bedrock Converse",
|
||||
})
|
||||
return Headers.setAll(headersForSigning, signed)
|
||||
})
|
||||
|
||||
@@ -1,9 +1,9 @@
|
||||
import { Effect, Encoding } from "effect"
|
||||
import type { ImageInput } from "../../image"
|
||||
import { InvalidRequestReason, AIError } from "../../schema"
|
||||
import { InvalidRequestReason, LLMError } from "../../schema"
|
||||
|
||||
const invalid = (module: string, message: string) =>
|
||||
new AIError({
|
||||
new LLMError({
|
||||
module,
|
||||
method: "generate",
|
||||
reason: new InvalidRequestReason({ message }),
|
||||
@@ -15,7 +15,7 @@ export const dataUrl = (input: Extract<ImageInput, { readonly type: "bytes" }>)
|
||||
export const decodeDataUrl = (
|
||||
url: string,
|
||||
module: string,
|
||||
): Effect.Effect<{ readonly mediaType: string; readonly data: Uint8Array } | undefined, AIError> => {
|
||||
): Effect.Effect<{ readonly mediaType: string; readonly data: Uint8Array } | undefined, LLMError> => {
|
||||
if (!url.startsWith("data:")) return Effect.succeed(undefined)
|
||||
const match = /^data:([^;,]+);base64,(.*)$/s.exec(url)
|
||||
if (!match) return Effect.fail(invalid(module, "Image data URLs must contain a MIME type and base64 data"))
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
import type { JsonSchema, LanguageModelToolSchemaCompatibility } from "../../schema"
|
||||
import type { JsonSchema, ModelToolSchemaCompatibility } from "../../schema"
|
||||
import { isRecord } from "../../utils/record"
|
||||
import { GeminiToolSchema } from "./gemini-tool-schema"
|
||||
|
||||
@@ -69,7 +69,7 @@ const gemini = (schema: JsonSchema): JsonSchema => GeminiToolSchema.convert(sche
|
||||
|
||||
const modelCompatibility = (
|
||||
schema: JsonSchema,
|
||||
compatibility: LanguageModelToolSchemaCompatibility | undefined,
|
||||
compatibility: ModelToolSchemaCompatibility | undefined,
|
||||
): JsonSchema => {
|
||||
if (compatibility === undefined) return schema
|
||||
switch (compatibility) {
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
import { Effect } from "effect"
|
||||
import { AIError, LLMEvent, type ProviderMetadata, type ToolCall, type ToolInputError } from "../../schema"
|
||||
import { LLMError, LLMEvent, type ProviderMetadata, type ToolCall, type ToolInputError } from "../../schema"
|
||||
import { eventError, parseToolInput, type ToolAccumulator } from "../shared"
|
||||
|
||||
type StreamKey = string | number
|
||||
@@ -112,8 +112,8 @@ const appendTool = <K extends StreamKey>(
|
||||
}
|
||||
}
|
||||
|
||||
export const isError = <K extends StreamKey>(result: AppendOutcome<K> | AIError): result is AIError =>
|
||||
result instanceof AIError
|
||||
export const isError = <K extends StreamKey>(result: AppendOutcome<K> | LLMError): result is LLMError =>
|
||||
result instanceof LLMError
|
||||
|
||||
/**
|
||||
* Register a tool call whose start event arrived before any argument deltas.
|
||||
@@ -138,7 +138,7 @@ export const appendOrStart = <K extends StreamKey>(
|
||||
key: K,
|
||||
delta: { readonly id?: string; readonly name?: string; readonly text: string },
|
||||
missingToolMessage: string,
|
||||
): AppendOutcome<K> | AIError => {
|
||||
): AppendOutcome<K> | LLMError => {
|
||||
const current = tools[key]
|
||||
const id = current?.id ?? delta.id
|
||||
const name = current?.name ?? delta.name
|
||||
@@ -167,7 +167,7 @@ export const appendExisting = <K extends StreamKey>(
|
||||
key: K,
|
||||
text: string,
|
||||
missingToolMessage: string,
|
||||
): AppendOutcome<K> | AIError => {
|
||||
): AppendOutcome<K> | LLMError => {
|
||||
const current = tools[key]
|
||||
if (!current) return eventError(route, missingToolMessage)
|
||||
if (text.length === 0) return { tools, tool: current, events: [] }
|
||||
|
||||
@@ -4,7 +4,7 @@ import { GeneratedImage, ImageModel, ImageResponse, type ImageRequestFor, type I
|
||||
import { Auth, type Definition as AuthDefinition } from "../route/auth"
|
||||
import {
|
||||
InvalidProviderOutputReason,
|
||||
AIError,
|
||||
LLMError,
|
||||
Usage,
|
||||
mergeHttpOptions,
|
||||
mergeJsonRecords,
|
||||
@@ -95,7 +95,7 @@ const nativeOptions = (options: XAIImageOptions | undefined) => {
|
||||
}
|
||||
|
||||
const invalidOutput = (message: string) =>
|
||||
new AIError({
|
||||
new LLMError({
|
||||
module: ADAPTER,
|
||||
method: "generate",
|
||||
reason: new InvalidProviderOutputReason({ message, route: ADAPTER }),
|
||||
|
||||
@@ -2,7 +2,7 @@ import { Effect, Schema } from "effect"
|
||||
import { Headers, HttpClientRequest } from "effect/unstable/http"
|
||||
import { GeneratedImage, ImageModel, ImageResponse, type ImageRequestFor, type ImageRoute } from "../image"
|
||||
import { Auth, type Definition as AuthDefinition } from "../route/auth"
|
||||
import { InvalidProviderOutputReason, AIError, mergeHttpOptions, mergeJsonRecords, type HttpOptions } from "../schema"
|
||||
import { InvalidProviderOutputReason, LLMError, mergeHttpOptions, mergeJsonRecords, type HttpOptions } from "../schema"
|
||||
import { ProviderShared } from "./shared"
|
||||
import { ImageInputs } from "./utils/image-input"
|
||||
|
||||
@@ -58,7 +58,7 @@ const nativeOptions = (options: ZAIImageOptions | undefined) => {
|
||||
}
|
||||
|
||||
const invalidOutput = (message: string) =>
|
||||
new AIError({
|
||||
new LLMError({
|
||||
module: ADAPTER,
|
||||
method: "generate",
|
||||
reason: new InvalidProviderOutputReason({ message, route: ADAPTER }),
|
||||
|
||||
@@ -3,7 +3,7 @@ import {
|
||||
AuthenticationReason,
|
||||
ContentPolicyReason,
|
||||
InvalidRequestReason,
|
||||
AIError,
|
||||
LLMError,
|
||||
ProviderErrorEvent,
|
||||
ProviderInternalReason,
|
||||
QuotaExceededReason,
|
||||
@@ -16,6 +16,7 @@ import {
|
||||
|
||||
const patterns = [
|
||||
/prompt is too long/i,
|
||||
/request_too_large/i,
|
||||
/input is too long for requested model/i,
|
||||
/exceeds the context window/i,
|
||||
/exceeds (?:the )?(?:model'?s )?maximum context length(?: of [\d,]+ tokens?|\s*\([\d,]+\))/i,
|
||||
@@ -32,6 +33,7 @@ const patterns = [
|
||||
/context window exceeds limit/i,
|
||||
/exceeded model token limit/i,
|
||||
/context[_ ]length[_ ]exceeded/i,
|
||||
/request entity too large/i,
|
||||
/context length is only \d+ tokens/i,
|
||||
/input length.*exceeds.*context length/i,
|
||||
/prompt too long; exceeded (?:max )?context length/i,
|
||||
@@ -42,18 +44,14 @@ const patterns = [
|
||||
/token limit exceeded/i,
|
||||
]
|
||||
|
||||
const payloadPatterns = [/request_too_large/i, /request entity too large/i, /payload too large/i, /request too large/i]
|
||||
|
||||
const exclusions = [/^(throttling error|service unavailable):/i, /rate limit/i, /too many requests/i]
|
||||
|
||||
export const isContextOverflow = (message: string) =>
|
||||
!exclusions.some((pattern) => pattern.test(message)) &&
|
||||
(patterns.some((pattern) => pattern.test(message)) || /^400\s*(status code)?\s*\(no body\)/i.test(message))
|
||||
|
||||
export const isPayloadTooLarge = (message: string) => payloadPatterns.some((pattern) => pattern.test(message))
|
||||
(patterns.some((pattern) => pattern.test(message)) || /^4(00|13)\s*(status code)?\s*\(no body\)/i.test(message))
|
||||
|
||||
export const isContextOverflowFailure = (failure: unknown) =>
|
||||
failure instanceof AIError
|
||||
failure instanceof LLMError
|
||||
? failure.reason._tag === "InvalidRequest" && failure.reason.classification === "context-overflow"
|
||||
: Schema.is(ProviderErrorEvent)(failure) && failure.classification === "context-overflow"
|
||||
|
||||
@@ -67,7 +65,6 @@ const SERVER_CODES = new Set([
|
||||
"overloaded_error",
|
||||
"server_error",
|
||||
"server_is_overloaded",
|
||||
"slow_down",
|
||||
"serviceunavailableexception",
|
||||
])
|
||||
const INVALID_REQUEST_CODES = new Set(["invalid_prompt", "invalid_request_error", "validationexception"])
|
||||
@@ -87,7 +84,7 @@ export interface ProviderFailure {
|
||||
|
||||
// Keep HTTP failures and provider-reported stream failures on one typed path so
|
||||
// session retry policy never needs provider-specific string matching.
|
||||
export function classifyProviderFailure(input: ProviderFailure): AIError["reason"] {
|
||||
export function classifyProviderFailure(input: ProviderFailure): LLMError["reason"] {
|
||||
const body = input.http?.body ?? ""
|
||||
const codes = [input.code, ...providerCodes(body), ...providerCodes(input.message)]
|
||||
.filter((code): code is string => code !== undefined)
|
||||
@@ -103,8 +100,6 @@ export function classifyProviderFailure(input: ProviderFailure): AIError["reason
|
||||
isContextOverflow(text))
|
||||
)
|
||||
return new InvalidRequestReason({ ...common, classification: "context-overflow" })
|
||||
if (input.status === 413 || isPayloadTooLarge(text))
|
||||
return new InvalidRequestReason({ ...common, classification: "payload-too-large" })
|
||||
if (CONTENT_POLICY_TEXT.test(text)) return new ContentPolicyReason(common)
|
||||
if (codes.some((code) => QUOTA_CODES.has(code)) || (input.status === 429 && QUOTA_TEXT.test(text)))
|
||||
return new QuotaExceededReason(common)
|
||||
@@ -147,7 +142,12 @@ export function classifyProviderFailure(input: ProviderFailure): AIError["reason
|
||||
retryAfterMs: input.retryAfterMs,
|
||||
})
|
||||
if (codes.some((code) => INVALID_REQUEST_CODES.has(code))) return new InvalidRequestReason(common)
|
||||
if (input.status === 400 || input.status === 404 || input.status === 413 || input.status === 422)
|
||||
if (
|
||||
input.status === 400 ||
|
||||
input.status === 404 ||
|
||||
input.status === 413 ||
|
||||
input.status === 422
|
||||
)
|
||||
return new InvalidRequestReason(common)
|
||||
return new UnknownProviderReason({ ...common, status: input.status })
|
||||
}
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
import type { LanguageModel, ProviderOptions } from "./schema"
|
||||
import type { Model, ProviderOptions } from "./schema"
|
||||
|
||||
export interface Settings extends Readonly<Record<string, unknown>> {
|
||||
readonly baseURL?: string
|
||||
@@ -6,7 +6,6 @@ export interface Settings extends Readonly<Record<string, unknown>> {
|
||||
readonly body?: Readonly<Record<string, unknown>>
|
||||
readonly limits?: {
|
||||
readonly context: number
|
||||
readonly input?: number
|
||||
readonly output: number
|
||||
}
|
||||
}
|
||||
@@ -15,7 +14,7 @@ export interface Definition<
|
||||
ProviderSettings extends Settings = Settings,
|
||||
Options extends ProviderOptions = ProviderOptions,
|
||||
> {
|
||||
readonly model: (modelID: string, settings: ProviderSettings) => LanguageModel<Options>
|
||||
readonly model: (modelID: string, settings: ProviderSettings) => Model<Options>
|
||||
}
|
||||
|
||||
export * as ProviderPackage from "./provider-package"
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
import type { LanguageModel, ModelID, ProviderID } from "./schema"
|
||||
import type { Model, ModelID, ProviderID } from "./schema"
|
||||
|
||||
export type LanguageModelOptions = Pick<LanguageModel.Input, "defaults" | "compatibility">
|
||||
export type ModelOptions = Pick<Model.Input, "defaults" | "compatibility">
|
||||
|
||||
/**
|
||||
* Advanced structural provider definition helper. Built-in providers should
|
||||
@@ -8,23 +8,23 @@ export type LanguageModelOptions = Pick<LanguageModel.Input, "defaults" | "compa
|
||||
* chosen before model selection. The optional `apis` map remains for external
|
||||
* structural providers that expose multiple route selectors behind one provider.
|
||||
*/
|
||||
export type LanguageModelFactory<Options extends LanguageModelOptions = LanguageModelOptions> = (
|
||||
export type ModelFactory<Options extends ModelOptions = ModelOptions> = (
|
||||
id: string | ModelID,
|
||||
options?: Options,
|
||||
) => LanguageModel
|
||||
) => Model
|
||||
|
||||
type AnyLanguageModelFactory = (...args: never[]) => LanguageModel
|
||||
type AnyModelFactory = (...args: never[]) => Model
|
||||
|
||||
export interface Definition<Factory extends AnyLanguageModelFactory = LanguageModelFactory> {
|
||||
export interface Definition<Factory extends AnyModelFactory = ModelFactory> {
|
||||
readonly id: ProviderID
|
||||
readonly model: Factory
|
||||
readonly apis?: Record<string, AnyLanguageModelFactory>
|
||||
readonly apis?: Record<string, AnyModelFactory>
|
||||
}
|
||||
|
||||
type DefinitionShape = {
|
||||
readonly id: ProviderID
|
||||
readonly model: (...args: never[]) => LanguageModel
|
||||
readonly apis?: Record<string, (...args: never[]) => LanguageModel>
|
||||
readonly model: (...args: never[]) => Model
|
||||
readonly apis?: Record<string, (...args: never[]) => Model>
|
||||
}
|
||||
|
||||
type NoExtraFields<Input, Shape> = Input & Record<Exclude<keyof Input, keyof Shape>, never>
|
||||
|
||||
@@ -1,107 +0,0 @@
|
||||
import { Auth } from "../route/auth"
|
||||
import type { Route as RouteDef, RouteDefaultsInput } from "../route/client"
|
||||
import type { ProviderPackage } from "../provider-package"
|
||||
import { OpenAIChat } from "../protocols/openai-chat"
|
||||
import { OpenAIResponses } from "../protocols/openai-responses"
|
||||
import { BedrockAuth, type Credentials } from "../protocols/utils/bedrock-auth"
|
||||
import { ProviderID, type ModelID } from "../schema"
|
||||
import { withOpenAIOptions, type OpenAIProviderOptionsInput } from "./openai-options"
|
||||
|
||||
export const id = ProviderID.make("amazon-bedrock")
|
||||
|
||||
export type Config = RouteDefaultsInput & {
|
||||
readonly apiKey?: string
|
||||
readonly baseURL?: string
|
||||
readonly credentials?: Credentials
|
||||
readonly region?: string
|
||||
readonly providerOptions?: OpenAIProviderOptionsInput
|
||||
}
|
||||
|
||||
export interface Settings extends ProviderPackage.Settings {
|
||||
readonly apiKey?: string
|
||||
readonly auth?: "bearer" | "sigv4"
|
||||
readonly baseURL?: string
|
||||
readonly credentials?: Credentials
|
||||
readonly region?: string
|
||||
readonly providerOptions?: OpenAIProviderOptionsInput
|
||||
}
|
||||
|
||||
const responsesRoute = OpenAIResponses.route.with({
|
||||
id: "bedrock-mantle-responses",
|
||||
provider: id,
|
||||
})
|
||||
|
||||
const chatRoute = OpenAIChat.route.with({
|
||||
id: "bedrock-mantle-chat",
|
||||
provider: id,
|
||||
})
|
||||
|
||||
export const routes = [responsesRoute, chatRoute]
|
||||
|
||||
const configuredRoute = <Body, Prepared>(route: RouteDef<Body, Prepared>, input: Config) => {
|
||||
const region = input.region ?? input.credentials?.region ?? "us-east-1"
|
||||
const credentials = input.credentials === undefined ? undefined : { ...input.credentials, region }
|
||||
return route.with({
|
||||
endpoint: { baseURL: input.baseURL ?? `https://bedrock-mantle.${region}.api.aws/v1` },
|
||||
auth:
|
||||
input.apiKey === undefined
|
||||
? BedrockAuth.sigV4(credentials, { service: "bedrock-mantle", name: "Bedrock Mantle" })
|
||||
: Auth.bearer(input.apiKey),
|
||||
})
|
||||
}
|
||||
|
||||
const defaults = (input: Config) => {
|
||||
const { apiKey: _, baseURL: _baseURL, credentials: _credentials, region: _region, ...rest } = input
|
||||
return rest
|
||||
}
|
||||
|
||||
export const configure = (input: Config = {}) => {
|
||||
const configuredResponsesRoute = configuredRoute(responsesRoute, input)
|
||||
const configuredChatRoute = configuredRoute(chatRoute, input)
|
||||
const modelDefaults = defaults(input)
|
||||
const responses = (modelID: string | ModelID) =>
|
||||
configuredResponsesRoute
|
||||
.with(withOpenAIOptions(modelID, modelDefaults))
|
||||
.model<OpenAIProviderOptionsInput>({ id: modelID })
|
||||
const chat = (modelID: string | ModelID) =>
|
||||
configuredChatRoute
|
||||
.with(withOpenAIOptions(modelID, modelDefaults))
|
||||
.model<OpenAIProviderOptionsInput>({ id: modelID })
|
||||
|
||||
return {
|
||||
id,
|
||||
model: chat,
|
||||
chat,
|
||||
responses,
|
||||
configure,
|
||||
}
|
||||
}
|
||||
|
||||
export const provider = configure()
|
||||
|
||||
const config = (settings: Settings): Config => {
|
||||
if (settings.auth === "bearer" && settings.apiKey === undefined)
|
||||
throw new Error("Amazon Bedrock Mantle bearer auth requires apiKey")
|
||||
if (settings.auth === "sigv4" && settings.apiKey !== undefined)
|
||||
throw new Error("Amazon Bedrock Mantle SigV4 auth does not accept apiKey")
|
||||
return {
|
||||
apiKey: settings.auth === "sigv4" ? undefined : settings.apiKey,
|
||||
baseURL: settings.baseURL,
|
||||
credentials: settings.credentials,
|
||||
headers: settings.headers === undefined ? undefined : { ...settings.headers },
|
||||
http: settings.body === undefined ? undefined : { body: { ...settings.body } },
|
||||
limits: settings.limits,
|
||||
providerOptions: settings.providerOptions,
|
||||
region: settings.region,
|
||||
}
|
||||
}
|
||||
|
||||
export const chatModel: ProviderPackage.Definition<Settings, OpenAIProviderOptionsInput>["model"] = (
|
||||
modelID,
|
||||
settings,
|
||||
) => configure(config(settings)).chat(modelID)
|
||||
export const responsesModel: ProviderPackage.Definition<Settings, OpenAIProviderOptionsInput>["model"] = (
|
||||
modelID,
|
||||
settings,
|
||||
) => configure(config(settings)).responses(modelID)
|
||||
export const model = chatModel
|
||||
@@ -1,2 +0,0 @@
|
||||
export { chatModel as model } from "../amazon-bedrock-mantle"
|
||||
export type { Settings } from "../amazon-bedrock-mantle"
|
||||
@@ -1,2 +0,0 @@
|
||||
export { chatModel as model } from "../../amazon-bedrock-mantle"
|
||||
export type { Settings } from "../../amazon-bedrock-mantle"
|
||||
@@ -1,2 +0,0 @@
|
||||
export { responsesModel as model } from "../../amazon-bedrock-mantle"
|
||||
export type { Settings } from "../../amazon-bedrock-mantle"
|
||||
@@ -14,7 +14,7 @@ const routeAuth = Auth.remove("authorization")
|
||||
// (helper builds the URL) or `baseURL` directly.
|
||||
type AzureURL = AtLeastOne<{ readonly resourceName: string; readonly baseURL: string }>
|
||||
|
||||
export type LanguageModelOptions = AzureURL &
|
||||
export type ModelOptions = AzureURL &
|
||||
RouteDefaultsInput &
|
||||
ProviderAuthOption<"optional"> & {
|
||||
readonly apiVersion?: string
|
||||
@@ -22,7 +22,7 @@ export type LanguageModelOptions = AzureURL &
|
||||
readonly useCompletionUrls?: boolean
|
||||
readonly providerOptions?: OpenAIProviderOptionsInput
|
||||
}
|
||||
export type Config = LanguageModelOptions
|
||||
export type Config = ModelOptions
|
||||
|
||||
export type Settings = ProviderPackage.Settings &
|
||||
AzureURL & {
|
||||
|
||||
@@ -9,14 +9,14 @@ export const id = ProviderID.make("github-copilot")
|
||||
|
||||
// GitHub Copilot has no canonical public URL — callers (opencode, etc.) must
|
||||
// supply `baseURL` explicitly.
|
||||
export type LanguageModelOptions = Omit<RouteDefaultsInput, "providerOptions"> &
|
||||
export type ModelOptions = Omit<RouteDefaultsInput, "providerOptions"> &
|
||||
ProviderAuthOption<"optional"> & {
|
||||
readonly baseURL: string
|
||||
readonly endpoint?: "chat" | "responses"
|
||||
readonly providerOptions?: OpenAIProviderOptionsInput
|
||||
}
|
||||
|
||||
export const shouldUseResponsesApi = (modelID: string | ModelID, endpoint?: LanguageModelOptions["endpoint"]) => {
|
||||
export const shouldUseResponsesApi = (modelID: string | ModelID, endpoint?: ModelOptions["endpoint"]) => {
|
||||
if (endpoint) return endpoint === "responses"
|
||||
const model = String(modelID)
|
||||
const match = /^gpt-(\d+)/.exec(model)
|
||||
@@ -29,24 +29,24 @@ export const routes = [OpenAIResponses.route, OpenAIChat.route]
|
||||
const chatRoute = OpenAIChat.route.with({ provider: id })
|
||||
const responsesRoute = OpenAIResponses.route.with({ provider: id })
|
||||
|
||||
const defaults = (options: LanguageModelOptions) => {
|
||||
const defaults = (options: ModelOptions) => {
|
||||
const { apiKey: _, auth: _auth, baseURL: _baseURL, endpoint: _endpoint, ...rest } = options
|
||||
return rest
|
||||
}
|
||||
|
||||
const configuredResponsesRoute = (options: LanguageModelOptions) =>
|
||||
const configuredResponsesRoute = (options: ModelOptions) =>
|
||||
responsesRoute.with({
|
||||
endpoint: { baseURL: options.baseURL },
|
||||
auth: AuthOptions.bearer(options, []),
|
||||
})
|
||||
|
||||
const configuredChatRoute = (options: LanguageModelOptions) =>
|
||||
const configuredChatRoute = (options: ModelOptions) =>
|
||||
chatRoute.with({
|
||||
endpoint: { baseURL: options.baseURL },
|
||||
auth: AuthOptions.bearer(options, []),
|
||||
})
|
||||
|
||||
export const configure = (options: LanguageModelOptions) => {
|
||||
export const configure = (options: ModelOptions) => {
|
||||
const responsesRoute = configuredResponsesRoute(options)
|
||||
const chatRoute = configuredChatRoute(options)
|
||||
const responses = (modelID: string | ModelID) =>
|
||||
|
||||
@@ -1,7 +1,6 @@
|
||||
export * as Anthropic from "./anthropic"
|
||||
export * as AnthropicCompatible from "./anthropic-compatible"
|
||||
export * as AmazonBedrock from "./amazon-bedrock"
|
||||
export * as AmazonBedrockMantle from "./amazon-bedrock-mantle"
|
||||
export * as Azure from "./azure"
|
||||
export * as Cloudflare from "./cloudflare"
|
||||
export { CloudflareAIGateway, CloudflareWorkersAI } from "./cloudflare"
|
||||
|
||||
@@ -12,7 +12,7 @@ export type { OpenAIImageOptions } from "../protocols/openai-images"
|
||||
|
||||
export const id = ProviderID.make("openai")
|
||||
|
||||
export const routes = [OpenAIResponses.route, OpenAIChat.route]
|
||||
export const routes = [OpenAIResponses.route, OpenAIResponses.webSocketRoute, OpenAIChat.route]
|
||||
|
||||
// This provider facade wraps the lower-level Responses and Chat model factories
|
||||
// with OpenAI-specific conveniences: typed options, API-key sugar, env fallback,
|
||||
@@ -63,6 +63,7 @@ export interface Settings extends ProviderPackage.Settings {
|
||||
readonly organization?: string
|
||||
readonly project?: string
|
||||
readonly queryParams?: Readonly<Record<string, string>>
|
||||
readonly transport?: "http" | "websocket"
|
||||
readonly providerOptions?: OpenAIProviderOptionsInput
|
||||
}
|
||||
|
||||
@@ -81,12 +82,17 @@ const configuredRoute = <Body, Prepared>(route: Route<Body, Prepared>, input: Co
|
||||
|
||||
export const configure = (input: Config = {}) => {
|
||||
const responsesRoute = configuredRoute(OpenAIResponses.route, input)
|
||||
const responsesWebSocketRoute = configuredRoute(OpenAIResponses.webSocketRoute, input)
|
||||
const chatRoute = configuredRoute(OpenAIChat.route, input)
|
||||
const modelDefaults = defaults(input)
|
||||
const responses = (id: string | ModelID) =>
|
||||
responsesRoute
|
||||
.with(withOpenAIOptions(id, modelDefaults, { textVerbosity: true }))
|
||||
.model<OpenAIProviderOptionsInput>({ id })
|
||||
const responsesWebSocket = (id: string | ModelID) =>
|
||||
responsesWebSocketRoute
|
||||
.with(withOpenAIOptions(id, modelDefaults, { textVerbosity: true }))
|
||||
.model<OpenAIProviderOptionsInput>({ id })
|
||||
const chat = (id: string | ModelID) =>
|
||||
chatRoute.with(withOpenAIOptions(id, modelDefaults)).model<OpenAIProviderOptionsInput>({ id })
|
||||
const image = (modelID: string | ModelID) =>
|
||||
@@ -105,6 +111,7 @@ export const configure = (input: Config = {}) => {
|
||||
id,
|
||||
model: responses,
|
||||
responses,
|
||||
responsesWebSocket,
|
||||
chat,
|
||||
image,
|
||||
configure,
|
||||
@@ -131,7 +138,10 @@ const config = (settings: Settings): Config => {
|
||||
}
|
||||
|
||||
export const model: ProviderPackage.Definition<Settings, OpenAIProviderOptionsInput>["model"] = (modelID, settings) => {
|
||||
return configure(config(settings)).responses(modelID)
|
||||
const configured = configure(config(settings))
|
||||
if (settings.transport === undefined || settings.transport === "http") return configured.responses(modelID)
|
||||
if (settings.transport === "websocket") return configured.responsesWebSocket(modelID)
|
||||
throw new Error(`Unsupported OpenAI Responses transport: ${String(settings.transport)}`)
|
||||
}
|
||||
|
||||
export const chatModel: ProviderPackage.Definition<Settings, OpenAIProviderOptionsInput>["model"] = (
|
||||
@@ -139,5 +149,6 @@ export const chatModel: ProviderPackage.Definition<Settings, OpenAIProviderOptio
|
||||
settings,
|
||||
) => configure(config(settings)).chat(modelID)
|
||||
export const responses = provider.responses
|
||||
export const responsesWebSocket = provider.responsesWebSocket
|
||||
export const chat = provider.chat
|
||||
export const image = provider.image
|
||||
|
||||
@@ -4,79 +4,28 @@ import { Endpoint } from "../route/endpoint"
|
||||
import { Framing } from "../route/framing"
|
||||
import { Protocol } from "../route/protocol"
|
||||
import { AuthOptions, type ProviderAuthOption } from "../route/auth-options"
|
||||
import { ProviderID, type CacheHint, type ModelID, type ProviderOptions } from "../schema"
|
||||
import { ProviderID, type ModelID, type ProviderOptions } from "../schema"
|
||||
import type { ProviderPackage } from "../provider-package"
|
||||
import * as OpenAICompatibleProfiles from "./openai-compatible-profile"
|
||||
import * as OpenAIChat from "../protocols/openai-chat"
|
||||
import { newBreakpoints, ttlBucket } from "../protocols/utils/cache"
|
||||
import { isRecord } from "../protocols/shared"
|
||||
|
||||
export const profile = OpenAICompatibleProfiles.profiles.openrouter
|
||||
export const id = ProviderID.make(profile.provider)
|
||||
const ADAPTER = "openrouter"
|
||||
|
||||
type OpenRouterString<Known extends string> = Known | (string & {})
|
||||
|
||||
export interface OpenRouterProviderRouting {
|
||||
readonly [key: string]: unknown
|
||||
readonly order?: ReadonlyArray<string>
|
||||
readonly allow_fallbacks?: boolean
|
||||
readonly require_parameters?: boolean
|
||||
readonly data_collection?: OpenRouterString<"allow" | "deny">
|
||||
readonly only?: ReadonlyArray<string>
|
||||
readonly ignore?: ReadonlyArray<string>
|
||||
readonly quantizations?: ReadonlyArray<string>
|
||||
readonly sort?: OpenRouterString<"price" | "throughput" | "latency">
|
||||
readonly max_price?: Readonly<{
|
||||
prompt?: number | string
|
||||
completion?: number | string
|
||||
image?: number | string
|
||||
audio?: number | string
|
||||
request?: number | string
|
||||
}>
|
||||
readonly zdr?: boolean
|
||||
}
|
||||
|
||||
export type OpenRouterPlugin =
|
||||
| Readonly<{
|
||||
id: "web"
|
||||
max_results?: number
|
||||
search_prompt?: string
|
||||
engine?: OpenRouterString<"native" | "exa">
|
||||
}>
|
||||
| Readonly<{ id: "file-parser"; max_files?: number; pdf?: { engine?: string } }>
|
||||
| Readonly<{ id: "moderation" }>
|
||||
| Readonly<{ id: "response-healing" }>
|
||||
| Readonly<{ id: "auto-router"; allowed_models?: ReadonlyArray<string> }>
|
||||
| Readonly<{ id: string & {}; [key: string]: unknown }>
|
||||
|
||||
export interface OpenRouterOptions {
|
||||
readonly [key: string]: unknown
|
||||
readonly debug?: Readonly<{ echo_upstream_body?: boolean }>
|
||||
readonly models?: ReadonlyArray<string>
|
||||
readonly plugins?: ReadonlyArray<OpenRouterPlugin>
|
||||
readonly usage?: boolean | Record<string, unknown>
|
||||
readonly reasoning?: Record<string, unknown>
|
||||
readonly promptCacheKey?: string
|
||||
readonly provider?: OpenRouterProviderRouting
|
||||
readonly reasoning?: Readonly<{
|
||||
enabled?: boolean
|
||||
exclude?: boolean
|
||||
effort?: OpenRouterString<"none" | "minimal" | "low" | "medium" | "high" | "xhigh" | "max">
|
||||
max_tokens?: number
|
||||
}>
|
||||
readonly usage?: boolean | Readonly<{ include: boolean }>
|
||||
readonly user?: string
|
||||
readonly web_search_options?: Readonly<{
|
||||
max_results?: number
|
||||
search_prompt?: string
|
||||
engine?: OpenRouterString<"native" | "exa">
|
||||
}>
|
||||
}
|
||||
|
||||
export type OpenRouterProviderOptionsInput = ProviderOptions & {
|
||||
readonly openrouter?: OpenRouterOptions
|
||||
}
|
||||
|
||||
export type LanguageModelOptions = Omit<RouteDefaultsInput, "providerOptions"> &
|
||||
export type ModelOptions = Omit<RouteDefaultsInput, "providerOptions"> &
|
||||
ProviderAuthOption<"optional"> & {
|
||||
readonly baseURL?: string
|
||||
readonly providerOptions?: OpenRouterProviderOptionsInput
|
||||
@@ -98,7 +47,7 @@ export const protocol = Protocol.make({
|
||||
body: {
|
||||
schema: OpenRouterBody,
|
||||
from: (request) =>
|
||||
OpenAIChat.fromRequest(request, { cacheControl: cacheControl() }).pipe(
|
||||
OpenAIChat.protocol.body.from(request).pipe(
|
||||
Effect.map((body) => {
|
||||
const sourceAssistants = request.messages.filter((message) => message.role === "assistant")
|
||||
let assistantIndex = 0
|
||||
@@ -129,39 +78,16 @@ export const protocol = Protocol.make({
|
||||
stream: OpenAIChat.protocol.stream,
|
||||
})
|
||||
|
||||
const cacheControl = () => {
|
||||
const breakpoints = newBreakpoints(4)
|
||||
return (cache: CacheHint | undefined) => {
|
||||
if (cache === undefined || breakpoints.remaining === 0) return undefined
|
||||
breakpoints.remaining -= 1
|
||||
return {
|
||||
type: "ephemeral" as const,
|
||||
...(ttlBucket(cache.ttlSeconds) === "1h" ? { ttl: "1h" } : {}),
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
const bodyOptions = (input: unknown) => {
|
||||
const openrouter = isRecord(input) ? input : {}
|
||||
const { usage, models, provider, plugins, web_search_options, debug, user, reasoning, promptCacheKey, ...options } =
|
||||
openrouter
|
||||
return {
|
||||
...options,
|
||||
...(usage === undefined || usage === true
|
||||
...(openrouter.usage === true
|
||||
? { usage: { include: true } }
|
||||
: usage === false
|
||||
? { usage: { include: false } }
|
||||
: isRecord(usage)
|
||||
? { usage }
|
||||
: {}),
|
||||
...(Array.isArray(models) ? { models } : {}),
|
||||
...(isRecord(provider) ? { provider } : {}),
|
||||
...(Array.isArray(plugins) ? { plugins } : {}),
|
||||
...(isRecord(web_search_options) ? { web_search_options } : {}),
|
||||
...(isRecord(debug) ? { debug } : {}),
|
||||
...(typeof user === "string" ? { user } : {}),
|
||||
...(isRecord(reasoning) ? { reasoning } : {}),
|
||||
...(typeof promptCacheKey === "string" ? { prompt_cache_key: promptCacheKey } : {}),
|
||||
: isRecord(openrouter.usage)
|
||||
? { usage: openrouter.usage }
|
||||
: {}),
|
||||
...(isRecord(openrouter.reasoning) ? { reasoning: openrouter.reasoning } : {}),
|
||||
...(typeof openrouter.promptCacheKey === "string" ? { prompt_cache_key: openrouter.promptCacheKey } : {}),
|
||||
}
|
||||
}
|
||||
|
||||
@@ -175,7 +101,7 @@ export const route = Route.make({
|
||||
|
||||
export const routes = [route]
|
||||
|
||||
const configuredRoute = (input: LanguageModelOptions) => {
|
||||
const configuredRoute = (input: ModelOptions) => {
|
||||
const { apiKey: _, auth: _auth, baseURL, ...rest } = input
|
||||
return route.with({
|
||||
...rest,
|
||||
@@ -184,7 +110,7 @@ const configuredRoute = (input: LanguageModelOptions) => {
|
||||
})
|
||||
}
|
||||
|
||||
export const configure = (input: LanguageModelOptions = {}) => {
|
||||
export const configure = (input: ModelOptions = {}) => {
|
||||
const route = configuredRoute(input)
|
||||
return {
|
||||
id,
|
||||
|
||||
@@ -16,7 +16,7 @@ export type XAIProviderOptionsInput = ProviderOptions & {
|
||||
readonly xai?: OpenAIOptionsInput
|
||||
}
|
||||
|
||||
export type LanguageModelOptions = Omit<RouteDefaultsInput, "providerOptions"> &
|
||||
export type ModelOptions = Omit<RouteDefaultsInput, "providerOptions"> &
|
||||
ProviderAuthOption<"optional"> & {
|
||||
readonly baseURL?: string
|
||||
readonly providerOptions?: XAIProviderOptionsInput
|
||||
@@ -53,7 +53,7 @@ export const routes = [responsesRoute, chatRoute]
|
||||
|
||||
const auth = (options: ProviderAuthOption<"optional">) => AuthOptions.bearer(options, "XAI_API_KEY")
|
||||
|
||||
const configuredResponsesRoute = (input: LanguageModelOptions) => {
|
||||
const configuredResponsesRoute = (input: ModelOptions) => {
|
||||
const { apiKey: _, auth: _auth, baseURL, ...rest } = input
|
||||
return responsesRoute.with({
|
||||
...rest,
|
||||
@@ -62,7 +62,7 @@ const configuredResponsesRoute = (input: LanguageModelOptions) => {
|
||||
})
|
||||
}
|
||||
|
||||
const configuredChatRoute = (input: LanguageModelOptions) => {
|
||||
const configuredChatRoute = (input: ModelOptions) => {
|
||||
const { apiKey: _, auth: _auth, baseURL, ...rest } = input
|
||||
return chatRoute.with({
|
||||
...rest,
|
||||
@@ -71,7 +71,7 @@ const configuredChatRoute = (input: LanguageModelOptions) => {
|
||||
})
|
||||
}
|
||||
|
||||
export const configure = (input: LanguageModelOptions = {}) => {
|
||||
export const configure = (input: ModelOptions = {}) => {
|
||||
const responsesRoute = configuredResponsesRoute(input)
|
||||
const chatRoute = configuredChatRoute(input)
|
||||
const responses = (modelID: string | ModelID) => responsesRoute.model<XAIProviderOptionsInput>({ id: modelID })
|
||||
|
||||
@@ -22,17 +22,13 @@ export type ProviderAuthOption<Mode extends ApiKeyMode> =
|
||||
| AuthOverride
|
||||
| (Mode extends "optional" ? OptionalApiKeyAuth : RequiredApiKeyAuth)
|
||||
|
||||
export type LanguageModelOptions<Base, Mode extends ApiKeyMode> = Omit<Base, "apiKey" | "auth"> &
|
||||
ProviderAuthOption<Mode>
|
||||
export type ModelOptions<Base, Mode extends ApiKeyMode> = Omit<Base, "apiKey" | "auth"> & ProviderAuthOption<Mode>
|
||||
|
||||
export type LanguageModelArgs<Base, Mode extends ApiKeyMode> = Mode extends "optional"
|
||||
? readonly [options?: LanguageModelOptions<Base, Mode>]
|
||||
: readonly [options: LanguageModelOptions<Base, Mode>]
|
||||
export type ModelArgs<Base, Mode extends ApiKeyMode> = Mode extends "optional"
|
||||
? readonly [options?: ModelOptions<Base, Mode>]
|
||||
: readonly [options: ModelOptions<Base, Mode>]
|
||||
|
||||
export type LanguageModelFactory<Base, Mode extends ApiKeyMode, LanguageModel> = (
|
||||
id: string,
|
||||
...args: LanguageModelArgs<Base, Mode>
|
||||
) => LanguageModel
|
||||
export type ModelFactory<Base, Mode extends ApiKeyMode, Model> = (id: string, ...args: ModelArgs<Base, Mode>) => Model
|
||||
|
||||
/**
|
||||
* Require at least one of the keys in `T`. Use for option shapes where any
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
import { Config, Effect, Redacted } from "effect"
|
||||
import { Headers } from "effect/unstable/http"
|
||||
import { AuthenticationReason, InvalidRequestReason, AIError, type HttpOptions } from "../schema"
|
||||
import { AuthenticationReason, InvalidRequestReason, LLMError, type HttpOptions } from "../schema"
|
||||
|
||||
export class MissingCredentialError extends Error {
|
||||
readonly _tag = "MissingCredentialError"
|
||||
@@ -11,7 +11,7 @@ export class MissingCredentialError extends Error {
|
||||
}
|
||||
|
||||
export type CredentialError = MissingCredentialError | Config.ConfigError
|
||||
export type AuthError = CredentialError | AIError
|
||||
export type AuthError = CredentialError | LLMError
|
||||
type Secret = string | Redacted.Redacted | Config.Config<string | Redacted.Redacted>
|
||||
|
||||
export interface AuthInput {
|
||||
@@ -100,7 +100,7 @@ export const headers = (input: Headers.Input) =>
|
||||
|
||||
export const remove = (name: string) => auth((input) => Effect.succeed(Headers.remove(input.headers, name)))
|
||||
|
||||
export const custom = (apply: (input: AuthInput) => Effect.Effect<Headers.Headers, AIError>) => auth(apply)
|
||||
export const custom = (apply: (input: AuthInput) => Effect.Effect<Headers.Headers, LLMError>) => auth(apply)
|
||||
|
||||
export const passthrough = none
|
||||
|
||||
@@ -134,9 +134,9 @@ export function bearerHeader(name: string, source?: Secret | Credential) {
|
||||
return render(source)
|
||||
}
|
||||
|
||||
const toAIError = (error: AuthError): AIError => {
|
||||
const toLLMError = (error: AuthError): LLMError => {
|
||||
if (error instanceof MissingCredentialError || error instanceof Config.ConfigError) {
|
||||
return new AIError({
|
||||
return new LLMError({
|
||||
module: "Auth",
|
||||
method: "apply",
|
||||
reason:
|
||||
@@ -150,7 +150,7 @@ const toAIError = (error: AuthError): AIError => {
|
||||
|
||||
export const toEffect =
|
||||
(input: Definition) =>
|
||||
(authInput: AuthInput): Effect.Effect<Headers.Headers, AIError> =>
|
||||
input.apply(authInput).pipe(Effect.mapError(toAIError))
|
||||
(authInput: AuthInput): Effect.Effect<Headers.Headers, LLMError> =>
|
||||
input.apply(authInput).pipe(Effect.mapError(toLLMError))
|
||||
|
||||
export * as Auth from "./auth"
|
||||
|
||||
@@ -1,24 +1,25 @@
|
||||
import { Cause, Context, Effect, Layer, Schema, Stream } from "effect"
|
||||
import * as Option from "effect/Option"
|
||||
import { Auth } from "./auth"
|
||||
import { Endpoint, type EndpointPatch } from "./endpoint"
|
||||
import { RequestExecutor } from "./executor"
|
||||
import { Framing } from "./framing"
|
||||
import { HttpTransport } from "./transport"
|
||||
import type { HttpMiddleware, Transport, TransportRuntime, WebSocketChannelExecutor } from "./transport"
|
||||
import type { HttpRequestTransform, Transport, TransportRuntime } from "./transport"
|
||||
import { WebSocketExecutor } from "./transport"
|
||||
import type { Protocol } from "./protocol"
|
||||
import { applyCachePolicy } from "../cache-policy"
|
||||
import * as ProviderShared from "../protocols/shared"
|
||||
import type { ProtocolID, ProviderOptions } from "../schema"
|
||||
import type { LLMError, ProtocolID, ProviderOptions } from "../schema"
|
||||
import {
|
||||
AIError,
|
||||
GenerationOptions,
|
||||
HttpOptions,
|
||||
LLMRequest,
|
||||
LLMResponse,
|
||||
LanguageModel,
|
||||
LanguageModelLimits,
|
||||
Model,
|
||||
ModelLimits,
|
||||
LLMError as LLMErrorClass,
|
||||
LLMEvent,
|
||||
InvalidProviderOutputReason,
|
||||
ProviderID,
|
||||
mergeGenerationOptions,
|
||||
mergeHttpOptions,
|
||||
@@ -29,7 +30,7 @@ export interface RouteBody<Body> {
|
||||
/** Schema for the validated provider-native body sent as the JSON request. */
|
||||
readonly schema: Schema.Codec<Body, unknown>
|
||||
/** Build the provider-native body from a common `LLMRequest`. */
|
||||
readonly from: (request: LLMRequest) => Effect.Effect<Body, AIError>
|
||||
readonly from: (request: LLMRequest) => Effect.Effect<Body, LLMError>
|
||||
}
|
||||
|
||||
export interface Route<Body, Prepared = unknown> {
|
||||
@@ -44,20 +45,17 @@ export interface Route<Body, Prepared = unknown> {
|
||||
readonly defaults: RouteDefaults
|
||||
readonly body: RouteBody<Body>
|
||||
readonly with: (patch: RoutePatch<Body, Prepared>) => Route<Body, Prepared>
|
||||
readonly model: <Options extends ProviderOptions = ProviderOptions>(
|
||||
input: RouteMappedLanguageModelInput,
|
||||
) => LanguageModel<Options>
|
||||
readonly model: <Options extends ProviderOptions = ProviderOptions>(input: RouteMappedModelInput) => Model<Options>
|
||||
readonly prepareTransport: (
|
||||
body: Body,
|
||||
request: LLMRequest,
|
||||
options?: StreamOptions,
|
||||
) => Effect.Effect<Prepared, AIError>
|
||||
) => Effect.Effect<Prepared, LLMError>
|
||||
readonly streamPrepared: (
|
||||
prepared: Prepared,
|
||||
request: LLMRequest,
|
||||
runtime: TransportRuntime,
|
||||
options?: StreamOptions,
|
||||
) => Stream.Stream<LLMEvent, AIError>
|
||||
) => Stream.Stream<LLMEvent, LLMError>
|
||||
}
|
||||
|
||||
// Route registries intentionally erase body generics after construction.
|
||||
@@ -68,13 +66,13 @@ export type AnyRoute = Route<any, any>
|
||||
|
||||
export type HttpOptionsInput = HttpOptions.Input
|
||||
|
||||
export type RouteLanguageModelInput = Omit<LanguageModel.Input, "provider" | "route">
|
||||
export type RouteModelInput = Omit<Model.Input, "provider" | "route">
|
||||
|
||||
export type RouteRoutedLanguageModelInput = Omit<LanguageModel.Input, "route">
|
||||
export type RouteRoutedModelInput = Omit<Model.Input, "route">
|
||||
|
||||
export interface RouteDefaults {
|
||||
readonly headers?: Record<string, string>
|
||||
readonly limits?: LanguageModelLimits
|
||||
readonly limits?: ModelLimits
|
||||
readonly generation?: GenerationOptions
|
||||
readonly providerOptions?: ProviderOptions
|
||||
readonly http?: HttpOptions
|
||||
@@ -82,7 +80,7 @@ export interface RouteDefaults {
|
||||
|
||||
export interface RouteDefaultsInput {
|
||||
readonly headers?: Record<string, string>
|
||||
readonly limits?: LanguageModelLimits.Input
|
||||
readonly limits?: ModelLimits.Input
|
||||
readonly generation?: GenerationOptions.Input
|
||||
readonly providerOptions?: ProviderOptions
|
||||
readonly http?: HttpOptions.Input
|
||||
@@ -96,17 +94,14 @@ export interface RoutePatch<Body, Prepared> extends RouteDefaultsInput {
|
||||
readonly endpoint?: EndpointPatch<Body>
|
||||
}
|
||||
|
||||
type RouteMappedLanguageModelInput = RouteLanguageModelInput | RouteRoutedLanguageModelInput
|
||||
type RouteMappedModelInput = RouteModelInput | RouteRoutedModelInput
|
||||
|
||||
const makeRouteLanguageModel = <Options extends ProviderOptions = ProviderOptions>(
|
||||
route: AnyRoute,
|
||||
mapped: RouteMappedLanguageModelInput,
|
||||
) => {
|
||||
const makeRouteModel = <Options extends ProviderOptions = ProviderOptions>(route: AnyRoute, mapped: RouteMappedModelInput) => {
|
||||
const provider = route.provider ?? ("provider" in mapped ? mapped.provider : undefined)
|
||||
if (!provider) throw new Error(`Route.model(${route.id}) requires a provider`)
|
||||
if (!endpointBaseURL(route.endpoint))
|
||||
throw new Error(`Route.model(${route.id}) requires an endpoint baseURL — configure it on the route first`)
|
||||
return LanguageModel.make<Options>({
|
||||
return Model.make<Options>({
|
||||
...mapped,
|
||||
provider,
|
||||
route,
|
||||
@@ -119,7 +114,7 @@ const mergeRouteDefaults = (base: RouteDefaults | undefined, patch: RouteDefault
|
||||
...base,
|
||||
...patch,
|
||||
headers,
|
||||
limits: patch.limits === undefined ? base?.limits : LanguageModelLimits.make(patch.limits),
|
||||
limits: patch.limits === undefined ? base?.limits : ModelLimits.make(patch.limits),
|
||||
generation: mergeGenerationOptions(generationOptions(base?.generation), generationOptions(patch.generation)),
|
||||
providerOptions: mergeProviderOptions(base?.providerOptions, patch.providerOptions),
|
||||
http: mergeHttpOptions(
|
||||
@@ -155,16 +150,15 @@ export interface Interface {
|
||||
}
|
||||
|
||||
export interface StreamOptions {
|
||||
readonly http?: HttpMiddleware
|
||||
readonly webSocket?: WebSocketChannelExecutor
|
||||
readonly transform?: HttpRequestTransform
|
||||
}
|
||||
|
||||
export interface StreamMethod {
|
||||
(request: LLMRequest, options?: StreamOptions): Stream.Stream<LLMEvent, AIError>
|
||||
(request: LLMRequest, options?: StreamOptions): Stream.Stream<LLMEvent, LLMError>
|
||||
}
|
||||
|
||||
export interface GenerateMethod {
|
||||
(request: LLMRequest, options?: StreamOptions): Effect.Effect<LLMResponse, AIError>
|
||||
(request: LLMRequest, options?: StreamOptions): Effect.Effect<LLMResponse, LLMError>
|
||||
}
|
||||
|
||||
export class Service extends Context.Service<Service, Interface>()("@opencode/LLMClient") {}
|
||||
@@ -228,22 +222,11 @@ export interface MakeTransportInput<Body, Prepared, Frame, Event, State> {
|
||||
|
||||
const streamError = (route: string, message: string, cause: Cause.Cause<unknown>) => {
|
||||
const failed = cause.reasons.find(Cause.isFailReason)?.error
|
||||
if (failed instanceof AIError) return failed
|
||||
if (failed instanceof LLMErrorClass) return failed
|
||||
return ProviderShared.eventError(route, message, Cause.pretty(cause))
|
||||
}
|
||||
|
||||
const incompleteStreamError = (route: string) =>
|
||||
new AIError({
|
||||
module: "LLMClient",
|
||||
method: "stream",
|
||||
reason: new InvalidProviderOutputReason({
|
||||
classification: "incomplete-stream",
|
||||
message: "The provider response ended unexpectedly.",
|
||||
route,
|
||||
}),
|
||||
})
|
||||
|
||||
const requireTerminalEvent = (route: string) => (events: Stream.Stream<LLMEvent, AIError>) =>
|
||||
const requireTerminalEvent = (route: string) => (events: Stream.Stream<LLMEvent, LLMError>) =>
|
||||
Stream.suspend(() => {
|
||||
let terminal = false
|
||||
return events.pipe(
|
||||
@@ -255,7 +238,13 @@ const requireTerminalEvent = (route: string) => (events: Stream.Stream<LLMEvent,
|
||||
if (LLMEvent.is.finish(event) || LLMEvent.is.providerError(event)) terminal = true
|
||||
return Effect.succeed(event)
|
||||
}),
|
||||
Stream.onEnd(Effect.suspend(() => (terminal ? Effect.void : Effect.fail(incompleteStreamError(route))))),
|
||||
Stream.onEnd(
|
||||
Effect.suspend(() =>
|
||||
terminal
|
||||
? Effect.void
|
||||
: Effect.fail(ProviderShared.eventError(route, "Provider stream ended without a terminal finish event")),
|
||||
),
|
||||
),
|
||||
)
|
||||
})
|
||||
|
||||
@@ -303,8 +292,8 @@ function makeFromTransport<Body, Prepared, Frame, Event, State>(
|
||||
defaults: mergeRouteDefaults(route.defaults, defaults),
|
||||
})
|
||||
},
|
||||
model: <Options extends ProviderOptions = ProviderOptions>(input: RouteMappedLanguageModelInput) =>
|
||||
makeRouteLanguageModel<Options>(route, input),
|
||||
model: <Options extends ProviderOptions = ProviderOptions>(input: RouteMappedModelInput) =>
|
||||
makeRouteModel<Options>(route, input),
|
||||
prepareTransport: (body, request, options) =>
|
||||
routeInput.transport.prepare({
|
||||
body,
|
||||
@@ -313,30 +302,24 @@ function makeFromTransport<Body, Prepared, Frame, Event, State>(
|
||||
auth: routeInput.auth ?? Auth.none,
|
||||
encodeBody,
|
||||
headers: routeInput.headers,
|
||||
middleware: options?.http,
|
||||
webSocket: options?.webSocket,
|
||||
transform: options?.transform,
|
||||
}),
|
||||
streamPrepared: (prepared: Prepared, request: LLMRequest, runtime: TransportRuntime, options?: StreamOptions) => {
|
||||
streamPrepared: (prepared: Prepared, request: LLMRequest, runtime: TransportRuntime) => {
|
||||
const route = `${request.model.provider}/${request.model.route.id}`
|
||||
return Stream.unwrap(
|
||||
routeInput.transport.execute(prepared, request, runtime, options).pipe(
|
||||
Effect.map((execution) => {
|
||||
const events = execution.frames.pipe(
|
||||
Stream.mapEffect(decodeEvent(route)),
|
||||
protocol.stream.terminal ? Stream.takeUntil(protocol.stream.terminal) : (stream) => stream,
|
||||
)
|
||||
const stream = events.pipe(
|
||||
Stream.mapAccumEffect(
|
||||
() => protocol.stream.initial(request),
|
||||
protocol.stream.step,
|
||||
protocol.stream.onHalt ? { onHalt: protocol.stream.onHalt } : undefined,
|
||||
),
|
||||
Stream.catchCause((cause) => Stream.fail(streamError(route, `Failed to read ${route} stream`, cause))),
|
||||
requireTerminalEvent(route),
|
||||
)
|
||||
return execution.complete ? stream.pipe(Stream.onEnd(execution.complete)) : stream
|
||||
}),
|
||||
const events = routeInput.transport
|
||||
.frames(prepared, request, runtime)
|
||||
.pipe(
|
||||
Stream.mapEffect(decodeEvent(route)),
|
||||
protocol.stream.terminal ? Stream.takeUntil(protocol.stream.terminal) : (stream) => stream,
|
||||
)
|
||||
return events.pipe(
|
||||
Stream.mapAccumEffect(
|
||||
() => protocol.stream.initial(request),
|
||||
protocol.stream.step,
|
||||
protocol.stream.onHalt ? { onHalt: protocol.stream.onHalt } : undefined,
|
||||
),
|
||||
Stream.catchCause((cause) => Stream.fail(streamError(route, `Failed to read ${route} stream`, cause))),
|
||||
requireTerminalEvent(route),
|
||||
)
|
||||
},
|
||||
} satisfies Route<Body, Prepared>
|
||||
@@ -419,7 +402,7 @@ const streamRequestWith = (runtime: TransportRuntime) => (request: LLMRequest, o
|
||||
Stream.unwrap(
|
||||
Effect.gen(function* () {
|
||||
const compiled = yield* compile(request, options)
|
||||
return compiled.route.streamPrepared(compiled.prepared, compiled.request, runtime, options)
|
||||
return compiled.route.streamPrepared(compiled.prepared, compiled.request, runtime)
|
||||
}),
|
||||
)
|
||||
|
||||
@@ -428,21 +411,24 @@ const generateWith = (stream: Interface["stream"]) =>
|
||||
const state = yield* stream(request, options).pipe(Stream.runFold(LLMResponse.empty, LLMResponse.reduce))
|
||||
const response = LLMResponse.complete(state)
|
||||
if (response) return response
|
||||
return yield* incompleteStreamError(`${request.model.provider}/${request.model.route.id}`)
|
||||
return yield* ProviderShared.eventError(
|
||||
`${request.model.provider}/${request.model.route.id}`,
|
||||
"Provider stream ended without a terminal finish event",
|
||||
)
|
||||
})
|
||||
|
||||
export function stream(request: LLMRequest, options?: StreamOptions): Stream.Stream<LLMEvent, AIError, Service> {
|
||||
export function stream(request: LLMRequest, options?: StreamOptions): Stream.Stream<LLMEvent, LLMError> {
|
||||
return Stream.unwrap(
|
||||
Effect.gen(function* () {
|
||||
return (yield* Service).stream(request, options)
|
||||
}),
|
||||
)
|
||||
) as Stream.Stream<LLMEvent, LLMError>
|
||||
}
|
||||
|
||||
export function generate(request: LLMRequest, options?: StreamOptions): Effect.Effect<LLMResponse, AIError, Service> {
|
||||
export function generate(request: LLMRequest, options?: StreamOptions): Effect.Effect<LLMResponse, LLMError> {
|
||||
return Effect.gen(function* () {
|
||||
return yield* (yield* Service).generate(request, options)
|
||||
})
|
||||
}) as Effect.Effect<LLMResponse, LLMError>
|
||||
}
|
||||
|
||||
export const streamRequest = (request: LLMRequest, options?: StreamOptions) =>
|
||||
@@ -457,6 +443,7 @@ export const layer: Layer.Layer<Service, never, RequestExecutor.Service> = Layer
|
||||
Effect.gen(function* () {
|
||||
const stream = streamRequestWith({
|
||||
http: yield* RequestExecutor.Service,
|
||||
webSocket: Option.getOrUndefined(yield* Effect.serviceOption(WebSocketExecutor.Service)),
|
||||
})
|
||||
return Service.of({ stream, generate: generateWith(stream) })
|
||||
}),
|
||||
|
||||
@@ -12,7 +12,7 @@ import {
|
||||
HttpRateLimitDetails,
|
||||
HttpRequestDetails,
|
||||
HttpResponseDetails,
|
||||
AIError,
|
||||
LLMError,
|
||||
TransportReason,
|
||||
} from "../schema"
|
||||
import { classifyProviderFailure } from "../provider-error"
|
||||
@@ -20,19 +20,10 @@ import { classifyProviderFailure } from "../provider-error"
|
||||
export interface Interface {
|
||||
readonly execute: (
|
||||
request: HttpClientRequest.HttpClientRequest,
|
||||
middleware?: HttpMiddleware,
|
||||
) => Effect.Effect<HttpClientResponse.HttpClientResponse, AIError>
|
||||
) => Effect.Effect<HttpClientResponse.HttpClientResponse, LLMError>
|
||||
}
|
||||
|
||||
export type HttpHandler = (
|
||||
request: HttpClientRequest.HttpClientRequest,
|
||||
) => Effect.Effect<HttpClientResponse.HttpClientResponse, Error>
|
||||
export type HttpMiddleware = (
|
||||
request: HttpClientRequest.HttpClientRequest,
|
||||
handler: HttpHandler,
|
||||
) => Effect.Effect<HttpClientResponse.HttpClientResponse, Error>
|
||||
|
||||
export class Service extends Context.Service<Service, Interface>()("@opencode/AI/RequestExecutor") {}
|
||||
export class Service extends Context.Service<Service, Interface>()("@opencode/LLM/RequestExecutor") {}
|
||||
|
||||
const BODY_LIMIT = 16_384
|
||||
const REDACTED = "<redacted>"
|
||||
@@ -229,7 +220,7 @@ const statusError =
|
||||
const retryAfter = retryAfterMs(headers)
|
||||
const rateLimit = rateLimitDetails(headers, retryAfter)
|
||||
const details = responseBody(body, request)
|
||||
return yield* new AIError({
|
||||
return yield* new LLMError({
|
||||
module: "RequestExecutor",
|
||||
method: "execute",
|
||||
reason: classifyProviderFailure({
|
||||
@@ -255,7 +246,7 @@ const toHttpError = (redactedNames: ReadonlyArray<string | RegExp>) => (error: u
|
||||
readonly kind?: string | undefined
|
||||
readonly request?: HttpClientRequest.HttpClientRequest | undefined
|
||||
}) =>
|
||||
new AIError({
|
||||
new LLMError({
|
||||
module: "RequestExecutor",
|
||||
method: "execute",
|
||||
reason: new TransportReason({
|
||||
@@ -270,7 +261,7 @@ const toHttpError = (redactedNames: ReadonlyArray<string | RegExp>) => (error: u
|
||||
return transportError({ message: error.message, kind: "Timeout" })
|
||||
}
|
||||
if (!HttpClientError.isHttpClientError(error)) {
|
||||
return transportError({ message: error instanceof Error ? error.message : "HTTP transport failed" })
|
||||
return transportError({ message: "HTTP transport failed" })
|
||||
}
|
||||
const request = "request" in error ? error.request : undefined
|
||||
if (error.reason._tag === "TransportError") {
|
||||
@@ -291,20 +282,12 @@ export const layer: Layer.Layer<Service, never, HttpClient.HttpClient> = Layer.e
|
||||
Service,
|
||||
Effect.gen(function* () {
|
||||
const http = yield* HttpClient.HttpClient
|
||||
const executeOnce = (request: HttpClientRequest.HttpClientRequest, middleware?: HttpMiddleware) =>
|
||||
const executeOnce = (request: HttpClientRequest.HttpClientRequest) =>
|
||||
Effect.gen(function* () {
|
||||
const redactedNames = yield* Headers.CurrentRedactedNames
|
||||
if (!middleware)
|
||||
return yield* http
|
||||
.execute(request)
|
||||
.pipe(Effect.mapError(toHttpError(redactedNames)), Effect.flatMap(statusError(request, redactedNames)))
|
||||
|
||||
const response = yield* middleware(request, (input) =>
|
||||
http
|
||||
.execute(input)
|
||||
.pipe(Effect.mapError((cause) => (cause instanceof Error ? cause : new Error(String(cause))))),
|
||||
).pipe(Effect.mapError(toHttpError(redactedNames)))
|
||||
return yield* statusError(response.request, redactedNames)(response)
|
||||
return yield* http
|
||||
.execute(request)
|
||||
.pipe(Effect.mapError(toHttpError(redactedNames)), Effect.flatMap(statusError(request, redactedNames)))
|
||||
})
|
||||
return Service.of({
|
||||
execute: executeOnce,
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
import type { Stream } from "effect"
|
||||
import * as ProviderShared from "../protocols/shared"
|
||||
import type { AIError } from "../schema"
|
||||
import type { LLMError } from "../schema"
|
||||
|
||||
/**
|
||||
* Decode a streaming HTTP response body into provider-protocol frames.
|
||||
@@ -18,7 +18,7 @@ import type { AIError } from "../schema"
|
||||
*/
|
||||
export interface Definition<Frame> {
|
||||
readonly id: string
|
||||
readonly frame: (bytes: Stream.Stream<Uint8Array, AIError>) => Stream.Stream<Frame, AIError>
|
||||
readonly frame: (bytes: Stream.Stream<Uint8Array, LLMError>) => Stream.Stream<Frame, LLMError>
|
||||
}
|
||||
|
||||
/** Server-Sent Events framing. Used by every JSON-streaming HTTP provider. */
|
||||
|
||||
@@ -1,8 +1,8 @@
|
||||
export { Route, LLMClient } from "./client"
|
||||
export type {
|
||||
Route as RouteShape,
|
||||
RouteLanguageModelInput,
|
||||
RouteRoutedLanguageModelInput,
|
||||
RouteModelInput,
|
||||
RouteRoutedModelInput,
|
||||
RouteDefaults,
|
||||
RouteDefaultsInput,
|
||||
AnyRoute,
|
||||
@@ -16,28 +16,11 @@ export { AuthOptions } from "./auth-options"
|
||||
export { Endpoint } from "./endpoint"
|
||||
export { Framing } from "./framing"
|
||||
export { Protocol } from "./protocol"
|
||||
export { HttpTransport, WebSocketTransport } from "./transport"
|
||||
export { HttpTransport, WebSocketExecutor, WebSocketTransport } from "./transport"
|
||||
export * as Transport from "./transport"
|
||||
export type { Definition as AuthShape, AuthInput, Credential, CredentialError } from "./auth"
|
||||
export type { ApiKeyMode, AuthOverride, ProviderAuthOption } from "./auth-options"
|
||||
export type { Definition as EndpointFn, EndpointInput } from "./endpoint"
|
||||
export type { Definition as FramingDef } from "./framing"
|
||||
export type { Protocol as ProtocolDef } from "./protocol"
|
||||
export type {
|
||||
ChannelCheckpoint,
|
||||
ChannelCreate,
|
||||
ChannelObservation,
|
||||
HttpHandler,
|
||||
HttpMiddleware,
|
||||
Transport as TransportDef,
|
||||
TransportExecuteOptions,
|
||||
TransportExecution,
|
||||
TransportRuntime,
|
||||
WebSocketConnection,
|
||||
WebSocketChannelDriver,
|
||||
WebSocketChannelExchange,
|
||||
WebSocketChannelExecution,
|
||||
WebSocketChannelExecutor,
|
||||
WebSocketConnector,
|
||||
WebSocketRequest,
|
||||
} from "./transport"
|
||||
export type { HttpRequest, HttpRequestTransform, Transport as TransportDef, TransportRuntime } from "./transport"
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
import { Schema, type Effect } from "effect"
|
||||
import type { AIError, LLMEvent, LLMRequest, ProtocolID } from "../schema"
|
||||
import type { LLMError, LLMEvent, LLMRequest, ProtocolID } from "../schema"
|
||||
|
||||
/**
|
||||
* The semantic API contract of one model server family.
|
||||
@@ -47,7 +47,7 @@ export interface ProtocolBody<Body> {
|
||||
/** Schema for the validated provider-native body sent as the JSON request. */
|
||||
readonly schema: Schema.Codec<Body, unknown>
|
||||
/** Build the provider-native body from a common `LLMRequest`. */
|
||||
readonly from: (request: LLMRequest) => Effect.Effect<Body, AIError>
|
||||
readonly from: (request: LLMRequest) => Effect.Effect<Body, LLMError>
|
||||
}
|
||||
|
||||
export interface ProtocolStream<Frame, Event, State> {
|
||||
@@ -56,7 +56,7 @@ export interface ProtocolStream<Frame, Event, State> {
|
||||
/** Initial parser state. Called once per response with the resolved request. */
|
||||
readonly initial: (request: LLMRequest) => State
|
||||
/** Translate one event into emitted `LLMEvent`s plus the next state. */
|
||||
readonly step: (state: State, event: Event) => Effect.Effect<readonly [State, ReadonlyArray<LLMEvent>], AIError>
|
||||
readonly step: (state: State, event: Event) => Effect.Effect<readonly [State, ReadonlyArray<LLMEvent>], LLMError>
|
||||
/** Optional request-completion signal for transports that do not end naturally. */
|
||||
readonly terminal?: (event: Event) => boolean
|
||||
/** Optional flush emitted when the framed stream ends. */
|
||||
|
||||
@@ -3,7 +3,7 @@ import { Headers, HttpClientRequest } from "effect/unstable/http"
|
||||
import { Auth } from "../auth"
|
||||
import { render as renderEndpoint } from "../endpoint"
|
||||
import { Framing } from "../framing"
|
||||
import type { HttpMiddleware, Transport, TransportPrepareInput } from "./index"
|
||||
import type { Transport, TransportPrepareInput } from "./index"
|
||||
import * as ProviderShared from "../../protocols/shared"
|
||||
import { mergeJsonRecords, type LLMRequest } from "../../schema"
|
||||
|
||||
@@ -19,7 +19,6 @@ export interface JsonRequestParts<Body = unknown> {
|
||||
export interface HttpPrepared<Frame> {
|
||||
readonly request: HttpClientRequest.HttpClientRequest
|
||||
readonly framing: Framing.Definition<Frame>
|
||||
readonly middleware?: HttpMiddleware
|
||||
}
|
||||
|
||||
const applyQuery = (url: string, query: Record<string, string> | undefined) => {
|
||||
@@ -29,9 +28,57 @@ const applyQuery = (url: string, query: Record<string, string> | undefined) => {
|
||||
return next.toString()
|
||||
}
|
||||
|
||||
const PROTOCOL_BODY_OVERLAY_DENYLIST = new Set([
|
||||
"anthropic_version",
|
||||
"content",
|
||||
"contents",
|
||||
"frequencyPenalty",
|
||||
"frequency_penalty",
|
||||
"generationConfig",
|
||||
"inferenceConfig",
|
||||
"input",
|
||||
"maxTokens",
|
||||
"max_tokens",
|
||||
"messages",
|
||||
"model",
|
||||
"presencePenalty",
|
||||
"presence_penalty",
|
||||
"responseFormat",
|
||||
"response_format",
|
||||
"seed",
|
||||
"stop",
|
||||
"stopSequences",
|
||||
"stop_sequences",
|
||||
"stream",
|
||||
"streamOptions",
|
||||
"stream_options",
|
||||
"system",
|
||||
"systemInstruction",
|
||||
"system_instruction",
|
||||
"temperature",
|
||||
"thinking",
|
||||
"toolChoice",
|
||||
"toolConfig",
|
||||
"tool_choice",
|
||||
"tool_config",
|
||||
"tools",
|
||||
"topK",
|
||||
"topP",
|
||||
"top_k",
|
||||
"top_p",
|
||||
])
|
||||
|
||||
const forbiddenBodyOverlayKeys = (body: Record<string, unknown>) =>
|
||||
Object.keys(body).filter((key) => PROTOCOL_BODY_OVERLAY_DENYLIST.has(key))
|
||||
|
||||
const bodyWithOverlay = <Body>(body: Body, request: LLMRequest, encodeBody: (body: Body) => string) =>
|
||||
Effect.gen(function* () {
|
||||
if (request.http?.body === undefined) return { jsonBody: body, bodyText: encodeBody(body) }
|
||||
const forbiddenKeys = forbiddenBodyOverlayKeys(request.http.body)
|
||||
if (forbiddenKeys.length > 0)
|
||||
return yield* ProviderShared.invalidRequest(
|
||||
`http.body cannot overlay protocol-owned field(s): ${forbiddenKeys.join(", ")}`,
|
||||
)
|
||||
if (ProviderShared.isRecord(body)) {
|
||||
const overlaid = mergeJsonRecords(body, request.http.body) ?? {}
|
||||
return { jsonBody: overlaid, bodyText: ProviderShared.encodeJson(overlaid) }
|
||||
@@ -75,39 +122,37 @@ export const httpJson = <Body, Frame>(input: HttpJsonInput<Body, Frame>): HttpJs
|
||||
prepare: (prepareInput) =>
|
||||
Effect.gen(function* () {
|
||||
const parts = yield* jsonRequestParts({ ...prepareInput })
|
||||
const request = ProviderShared.jsonPost({
|
||||
url: parts.url,
|
||||
body: parts.bodyText,
|
||||
headers: parts.headers,
|
||||
})
|
||||
const request = { url: parts.url, method: "POST", headers: { ...parts.headers }, body: parts.bodyText }
|
||||
yield* (prepareInput.transform?.(request) ?? Effect.void)
|
||||
return {
|
||||
request,
|
||||
request: ProviderShared.jsonPost({
|
||||
url: request.url,
|
||||
body: request.body ?? "",
|
||||
headers: Headers.fromInput(request.headers),
|
||||
}),
|
||||
framing: input.framing,
|
||||
middleware: prepareInput.middleware,
|
||||
}
|
||||
}),
|
||||
execute: (prepared, request, runtime) =>
|
||||
Effect.succeed({
|
||||
frames: Stream.unwrap(
|
||||
runtime.http
|
||||
.execute(prepared.request, prepared.middleware)
|
||||
.pipe(
|
||||
Effect.map((response) =>
|
||||
prepared.framing.frame(
|
||||
response.stream.pipe(
|
||||
Stream.mapError((error) =>
|
||||
ProviderShared.eventError(
|
||||
`${request.model.provider}/${request.model.route.id}`,
|
||||
`Failed to read ${request.model.provider}/${request.model.route.id} stream`,
|
||||
ProviderShared.errorText(error),
|
||||
),
|
||||
frames: (prepared, request, runtime) =>
|
||||
Stream.unwrap(
|
||||
runtime.http
|
||||
.execute(prepared.request)
|
||||
.pipe(
|
||||
Effect.map((response) =>
|
||||
prepared.framing.frame(
|
||||
response.stream.pipe(
|
||||
Stream.mapError((error) =>
|
||||
ProviderShared.eventError(
|
||||
`${request.model.provider}/${request.model.route.id}`,
|
||||
`Failed to read ${request.model.provider}/${request.model.route.id} stream`,
|
||||
ProviderShared.errorText(error),
|
||||
),
|
||||
),
|
||||
),
|
||||
),
|
||||
),
|
||||
),
|
||||
}),
|
||||
),
|
||||
),
|
||||
})
|
||||
|
||||
export const sseJson = {
|
||||
|
||||
@@ -1,33 +1,32 @@
|
||||
import type { Effect, Scope, Stream } from "effect"
|
||||
import type { Effect, Stream } from "effect"
|
||||
import { Endpoint } from "../endpoint"
|
||||
import { Auth } from "../auth"
|
||||
import type { HttpMiddleware, Interface as RequestExecutorInterface } from "../executor"
|
||||
import type { WebSocketChannelExecutor } from "./websocket-channel"
|
||||
import type { AIError, LLMRequest } from "../../schema"
|
||||
import type { Interface as RequestExecutorInterface } from "../executor"
|
||||
import type { Interface as WebSocketExecutorInterface } from "./websocket"
|
||||
import type { LLMError, LLMRequest } from "../../schema"
|
||||
|
||||
export interface TransportRuntime {
|
||||
readonly http: RequestExecutorInterface
|
||||
readonly webSocket?: WebSocketExecutorInterface
|
||||
}
|
||||
|
||||
export interface TransportExecution<Frame> {
|
||||
readonly frames: Stream.Stream<Frame, AIError>
|
||||
/** Optional successful-consumption acknowledgement. HTTP leaves this absent. */
|
||||
readonly complete?: Effect.Effect<void>
|
||||
export interface HttpRequest {
|
||||
url: string
|
||||
readonly method: string
|
||||
headers: Record<string, string>
|
||||
body: string | undefined
|
||||
}
|
||||
|
||||
export interface TransportExecuteOptions {
|
||||
readonly webSocket?: WebSocketChannelExecutor
|
||||
}
|
||||
export type HttpRequestTransform = (request: HttpRequest) => Effect.Effect<void>
|
||||
|
||||
export interface Transport<Body, Prepared, Frame> {
|
||||
readonly id: string
|
||||
readonly prepare: (input: TransportPrepareInput<Body>) => Effect.Effect<Prepared, AIError>
|
||||
readonly execute: (
|
||||
readonly prepare: (input: TransportPrepareInput<Body>) => Effect.Effect<Prepared, LLMError>
|
||||
readonly frames: (
|
||||
prepared: Prepared,
|
||||
request: LLMRequest,
|
||||
runtime: TransportRuntime,
|
||||
options?: TransportExecuteOptions,
|
||||
) => Effect.Effect<TransportExecution<Frame>, AIError, Scope.Scope>
|
||||
) => Stream.Stream<Frame, LLMError>
|
||||
}
|
||||
|
||||
export interface TransportPrepareInput<Body> {
|
||||
@@ -37,20 +36,8 @@ export interface TransportPrepareInput<Body> {
|
||||
readonly auth: Auth.Definition
|
||||
readonly encodeBody: (body: Body) => string
|
||||
readonly headers?: (input: { readonly request: LLMRequest }) => Record<string, string>
|
||||
readonly middleware?: HttpMiddleware
|
||||
readonly webSocket?: WebSocketChannelExecutor
|
||||
readonly transform?: HttpRequestTransform
|
||||
}
|
||||
|
||||
export * as HttpTransport from "./http"
|
||||
export type { HttpHandler, HttpMiddleware } from "../executor"
|
||||
export type {
|
||||
ChannelCheckpoint,
|
||||
ChannelCreate,
|
||||
ChannelObservation,
|
||||
WebSocketChannelDriver,
|
||||
WebSocketChannelExchange,
|
||||
WebSocketChannelExecution,
|
||||
WebSocketChannelExecutor,
|
||||
} from "./websocket-channel"
|
||||
export type { WebSocketConnection, WebSocketConnector, WebSocketRequest } from "./websocket"
|
||||
export { WebSocketTransport } from "./websocket"
|
||||
export { WebSocketExecutor, WebSocketTransport } from "./websocket"
|
||||
|
||||
@@ -1,48 +0,0 @@
|
||||
import type { Effect, Scope, Stream } from "effect"
|
||||
import type { Headers } from "effect/unstable/http"
|
||||
import type { AIError } from "../../schema"
|
||||
|
||||
export interface WebSocketChannelExecutor {
|
||||
readonly execute: (
|
||||
exchange: WebSocketChannelExchange,
|
||||
) => Effect.Effect<WebSocketChannelExecution, AIError, Scope.Scope>
|
||||
}
|
||||
|
||||
export interface WebSocketChannelExecution {
|
||||
readonly frames: Stream.Stream<string, AIError>
|
||||
/** Commits staged state after the decoded Route stream ends successfully. */
|
||||
readonly complete: Effect.Effect<void>
|
||||
}
|
||||
|
||||
export interface WebSocketChannelExchange {
|
||||
readonly id: string
|
||||
readonly connect: {
|
||||
readonly url: string
|
||||
readonly headers: Headers.Headers
|
||||
}
|
||||
readonly fallback: () => Stream.Stream<string, AIError>
|
||||
readonly driver: WebSocketChannelDriver
|
||||
}
|
||||
|
||||
export interface WebSocketChannelDriver {
|
||||
readonly create: (checkpoint: ChannelCheckpoint | undefined) => Effect.Effect<ChannelCreate, AIError>
|
||||
readonly observe: (create: ChannelCreate, frame: string) => Effect.Effect<ChannelObservation, AIError>
|
||||
}
|
||||
|
||||
export interface ChannelCreate {
|
||||
readonly message: string
|
||||
readonly mode: "full" | "incremental"
|
||||
}
|
||||
|
||||
export type ChannelObservation =
|
||||
| { readonly type: "frame"; readonly frame: string }
|
||||
| { readonly type: "completed"; readonly frame: string; readonly checkpoint?: ChannelCheckpoint }
|
||||
| { readonly type: "incomplete"; readonly frame: string }
|
||||
| { readonly type: "provider-failure"; readonly error: AIError }
|
||||
| { readonly type: "rejected"; readonly error: AIError; readonly recovery: "retry-full" }
|
||||
| { readonly type: "rejected"; readonly error: AIError; readonly recovery: "rotate-and-retry-full" }
|
||||
|
||||
export interface ChannelCheckpoint {
|
||||
readonly protocol: string
|
||||
readonly value: unknown
|
||||
}
|
||||
@@ -1,15 +1,8 @@
|
||||
import { Cause, Effect, Queue, Stream } from "effect"
|
||||
import { Cause, Context, Effect, Layer, Queue, Stream } from "effect"
|
||||
import { Headers } from "effect/unstable/http"
|
||||
import { Socket } from "effect/unstable/socket"
|
||||
import { AIError, TransportReason } from "../../schema"
|
||||
import { LLMError, TransportReason } from "../../schema"
|
||||
import * as HttpTransport from "./http"
|
||||
import type { Transport } from "./index"
|
||||
import type {
|
||||
ChannelObservation,
|
||||
WebSocketChannelDriver,
|
||||
WebSocketChannelExchange,
|
||||
WebSocketChannelExecutor,
|
||||
} from "./websocket-channel"
|
||||
|
||||
export interface WebSocketRequest {
|
||||
readonly url: string
|
||||
@@ -17,62 +10,33 @@ export interface WebSocketRequest {
|
||||
}
|
||||
|
||||
export interface WebSocketConnection {
|
||||
readonly sendText: (message: string) => Effect.Effect<void, AIError>
|
||||
readonly messages: Stream.Stream<string | Uint8Array, AIError>
|
||||
readonly sendText: (message: string) => Effect.Effect<void, LLMError>
|
||||
readonly messages: Stream.Stream<string | Uint8Array, LLMError>
|
||||
readonly close: Effect.Effect<void, never>
|
||||
}
|
||||
|
||||
export interface WebSocketConnector {
|
||||
readonly open: (input: WebSocketRequest) => Effect.Effect<WebSocketConnection, AIError>
|
||||
export interface Interface {
|
||||
readonly open: (input: WebSocketRequest) => Effect.Effect<WebSocketConnection, LLMError>
|
||||
}
|
||||
|
||||
type WebSocketConstructorWithHeaders = (
|
||||
type WebSocketConstructorWithHeaders = new (
|
||||
url: string,
|
||||
options?: { readonly headers?: Headers.Headers },
|
||||
) => globalThis.WebSocket
|
||||
|
||||
export class Service extends Context.Service<Service, Interface>()("@opencode/LLM/WebSocketExecutor") {}
|
||||
|
||||
const transportError = (
|
||||
method: string,
|
||||
message: string,
|
||||
input: {
|
||||
readonly url?: string
|
||||
readonly kind?: string
|
||||
readonly phase?: TransportReason["phase"]
|
||||
readonly delivery?: TransportReason["delivery"]
|
||||
} = {},
|
||||
input: { readonly url?: string; readonly kind?: string } = {},
|
||||
) =>
|
||||
new AIError({
|
||||
module: "WebSocketConnector",
|
||||
new LLMError({
|
||||
module: "WebSocketExecutor",
|
||||
method,
|
||||
reason: new TransportReason({
|
||||
message,
|
||||
url: input.url,
|
||||
kind: input.kind,
|
||||
phase: input.phase,
|
||||
delivery: input.delivery,
|
||||
}),
|
||||
reason: new TransportReason({ message, url: input.url, kind: input.kind }),
|
||||
})
|
||||
|
||||
const annotateTransportError = (
|
||||
error: AIError,
|
||||
input: { readonly phase: TransportReason["phase"]; readonly delivery: TransportReason["delivery"] },
|
||||
) =>
|
||||
error.reason._tag === "Transport"
|
||||
? new AIError({
|
||||
module: error.module,
|
||||
method: error.method,
|
||||
reason: new TransportReason({
|
||||
message: error.reason.message,
|
||||
kind: error.reason.kind,
|
||||
url: error.reason.url,
|
||||
http: error.reason.http,
|
||||
phase: input.phase,
|
||||
delivery: input.delivery,
|
||||
recovery: error.reason.recovery,
|
||||
}),
|
||||
})
|
||||
: error
|
||||
|
||||
const eventMessage = (event: Event) => {
|
||||
if ("message" in event && typeof event.message === "string") return event.message
|
||||
return event.type
|
||||
@@ -92,12 +56,10 @@ const waitOpen = (ws: globalThis.WebSocket, input: WebSocketRequest) => {
|
||||
transportError("open", `WebSocket closed before opening (state ${ws.readyState})`, {
|
||||
url: input.url,
|
||||
kind: "open",
|
||||
phase: "connect",
|
||||
delivery: "not-sent",
|
||||
}),
|
||||
)
|
||||
}
|
||||
return Effect.callback<void, AIError>((resume, signal) => {
|
||||
return Effect.callback<void, LLMError>((resume, signal) => {
|
||||
const cleanup = () => {
|
||||
ws.removeEventListener("open", onOpen)
|
||||
ws.removeEventListener("error", onError)
|
||||
@@ -117,12 +79,7 @@ const waitOpen = (ws: globalThis.WebSocket, input: WebSocketRequest) => {
|
||||
cleanup()
|
||||
resume(
|
||||
Effect.fail(
|
||||
transportError("open", `Failed to open WebSocket: ${eventMessage(event)}`, {
|
||||
url: input.url,
|
||||
kind: "open",
|
||||
phase: "connect",
|
||||
delivery: "not-sent",
|
||||
}),
|
||||
transportError("open", `Failed to open WebSocket: ${eventMessage(event)}`, { url: input.url, kind: "open" }),
|
||||
),
|
||||
)
|
||||
}
|
||||
@@ -133,8 +90,6 @@ const waitOpen = (ws: globalThis.WebSocket, input: WebSocketRequest) => {
|
||||
transportError("open", `WebSocket closed before opening with code ${event.code}`, {
|
||||
url: input.url,
|
||||
kind: "open",
|
||||
phase: "connect",
|
||||
delivery: "not-sent",
|
||||
}),
|
||||
),
|
||||
)
|
||||
@@ -146,7 +101,7 @@ const waitOpen = (ws: globalThis.WebSocket, input: WebSocketRequest) => {
|
||||
})
|
||||
}
|
||||
|
||||
export const toWebSocketUrl = (value: string) =>
|
||||
const webSocketUrl = (value: string) =>
|
||||
Effect.try({
|
||||
try: () => {
|
||||
const url = new URL(value)
|
||||
@@ -164,39 +119,29 @@ export const toWebSocketUrl = (value: string) =>
|
||||
transportError("prepare", error instanceof Error ? error.message : "Invalid WebSocket URL", {
|
||||
url: value,
|
||||
kind: "websocket",
|
||||
phase: "prepare",
|
||||
delivery: "not-sent",
|
||||
}),
|
||||
})
|
||||
|
||||
export const open = (input: WebSocketRequest) =>
|
||||
Effect.gen(function* () {
|
||||
const constructor = yield* Socket.WebSocketConstructor
|
||||
const ws = yield* Effect.try({
|
||||
try: () =>
|
||||
// Platform implementations may extend Effect's browser-compatible constructor with handshake options.
|
||||
// oxlint-disable-next-line typescript-eslint/no-unsafe-type-assertion
|
||||
(constructor as unknown as WebSocketConstructorWithHeaders)(input.url, {
|
||||
headers: input.headers,
|
||||
}),
|
||||
catch: (error) =>
|
||||
transportError("open", error instanceof Error ? error.message : "Failed to construct WebSocket", {
|
||||
url: input.url,
|
||||
kind: "open",
|
||||
phase: "connect",
|
||||
delivery: "not-sent",
|
||||
}),
|
||||
})
|
||||
return yield* fromWebSocket(ws, input)
|
||||
})
|
||||
Effect.try({
|
||||
try: () =>
|
||||
new (globalThis.WebSocket as unknown as WebSocketConstructorWithHeaders)(input.url, { headers: input.headers }),
|
||||
catch: (error) =>
|
||||
transportError("open", error instanceof Error ? error.message : "Failed to construct WebSocket", {
|
||||
url: input.url,
|
||||
kind: "open",
|
||||
}),
|
||||
}).pipe(Effect.flatMap((ws) => fromWebSocket(ws, input)))
|
||||
|
||||
export const layer: Layer.Layer<Service> = Layer.succeed(Service, Service.of({ open }))
|
||||
|
||||
export const fromWebSocket = (
|
||||
ws: globalThis.WebSocket,
|
||||
input: WebSocketRequest,
|
||||
): Effect.Effect<WebSocketConnection, AIError> =>
|
||||
): Effect.Effect<WebSocketConnection, LLMError> =>
|
||||
Effect.gen(function* () {
|
||||
yield* waitOpen(ws, input)
|
||||
const messages = yield* Queue.bounded<string | Uint8Array, AIError | Cause.Done<void>>(128)
|
||||
const messages = yield* Queue.bounded<string | Uint8Array, LLMError | Cause.Done<void>>(128)
|
||||
|
||||
const onMessage = (event: MessageEvent) => {
|
||||
if (typeof event.data === "string") return Queue.offerUnsafe(messages, event.data)
|
||||
@@ -205,11 +150,7 @@ export const fromWebSocket = (
|
||||
Queue.failCauseUnsafe(
|
||||
messages,
|
||||
Cause.fail(
|
||||
transportError("message", "Unsupported WebSocket message payload", {
|
||||
url: input.url,
|
||||
kind: "message",
|
||||
phase: "receive",
|
||||
}),
|
||||
transportError("message", "Unsupported WebSocket message payload", { url: input.url, kind: "message" }),
|
||||
),
|
||||
)
|
||||
}
|
||||
@@ -217,23 +158,16 @@ export const fromWebSocket = (
|
||||
Queue.failCauseUnsafe(
|
||||
messages,
|
||||
Cause.fail(
|
||||
transportError("message", `WebSocket error: ${eventMessage(event)}`, {
|
||||
url: input.url,
|
||||
kind: "message",
|
||||
phase: "receive",
|
||||
}),
|
||||
transportError("message", `WebSocket error: ${eventMessage(event)}`, { url: input.url, kind: "message" }),
|
||||
),
|
||||
)
|
||||
}
|
||||
const onClose = (event: CloseEvent) => {
|
||||
if (event.code === 1000 || event.code === 1005) return Queue.endUnsafe(messages)
|
||||
Queue.failCauseUnsafe(
|
||||
messages,
|
||||
Cause.fail(
|
||||
transportError("message", `WebSocket closed with code ${event.code}`, {
|
||||
url: input.url,
|
||||
kind: "close",
|
||||
phase: "close",
|
||||
}),
|
||||
transportError("message", `WebSocket closed with code ${event.code}`, { url: input.url, kind: "close" }),
|
||||
),
|
||||
)
|
||||
}
|
||||
@@ -255,8 +189,6 @@ export const fromWebSocket = (
|
||||
transportError("sendText", error instanceof Error ? error.message : "Failed to send WebSocket message", {
|
||||
url: input.url,
|
||||
kind: "write",
|
||||
phase: "send",
|
||||
delivery: "not-sent",
|
||||
}),
|
||||
}),
|
||||
messages: Stream.fromQueue(messages),
|
||||
@@ -274,57 +206,6 @@ export const fromWebSocket = (
|
||||
export const messageText = (message: string | Uint8Array, decoder: TextDecoder) =>
|
||||
typeof message === "string" ? message : decoder.decode(message)
|
||||
|
||||
const observationFrame = (observation: ChannelObservation) => {
|
||||
if (observation.type === "frame" || observation.type === "completed" || observation.type === "incomplete")
|
||||
return Effect.succeed(observation.frame)
|
||||
return Effect.fail(observation.error)
|
||||
}
|
||||
|
||||
const observationTerminal = (observation: ChannelObservation) => observation.type !== "frame"
|
||||
|
||||
export const makeDirect = (connector: WebSocketConnector): WebSocketChannelExecutor => ({
|
||||
execute: (exchange) =>
|
||||
Effect.gen(function* () {
|
||||
const connection = yield* Effect.acquireRelease(
|
||||
connector
|
||||
.open(exchange.connect)
|
||||
.pipe(Effect.mapError((error) => annotateTransportError(error, { phase: "connect", delivery: "not-sent" }))),
|
||||
(connection) => connection.close,
|
||||
)
|
||||
const create = yield* exchange.driver.create(undefined)
|
||||
yield* connection.sendText(create.message)
|
||||
const decoder = new TextDecoder()
|
||||
let observed = false
|
||||
return {
|
||||
frames: connection.messages.pipe(
|
||||
Stream.map((message) => {
|
||||
observed = true
|
||||
return messageText(message, decoder)
|
||||
}),
|
||||
Stream.mapError((error) =>
|
||||
annotateTransportError(error, {
|
||||
phase: error.reason._tag === "Transport" && error.reason.phase === "close" ? "close" : "receive",
|
||||
delivery: observed ? "accepted" : "ambiguous",
|
||||
}),
|
||||
),
|
||||
Stream.mapEffect((frame) => exchange.driver.observe(create, frame)),
|
||||
Stream.takeUntil(observationTerminal),
|
||||
Stream.mapEffect(observationFrame),
|
||||
),
|
||||
complete: Effect.void,
|
||||
}
|
||||
}),
|
||||
})
|
||||
|
||||
export const direct: Effect.Effect<WebSocketChannelExecutor, never, Socket.WebSocketConstructor> = Effect.gen(
|
||||
function* () {
|
||||
const constructor = yield* Socket.WebSocketConstructor
|
||||
return makeDirect({
|
||||
open: (input) => open(input).pipe(Effect.provideService(Socket.WebSocketConstructor, constructor)),
|
||||
})
|
||||
},
|
||||
)
|
||||
|
||||
export interface JsonPrepared {
|
||||
readonly url: string
|
||||
readonly headers: Headers.Headers
|
||||
@@ -332,7 +213,7 @@ export interface JsonPrepared {
|
||||
}
|
||||
|
||||
export interface JsonInput<Body, Message> {
|
||||
readonly toMessage: (body: Body | Record<string, unknown>) => Effect.Effect<Message, AIError>
|
||||
readonly toMessage: (body: Body | Record<string, unknown>) => Effect.Effect<Message, LLMError>
|
||||
readonly encodeMessage: (message: Message) => string
|
||||
}
|
||||
|
||||
@@ -351,42 +232,32 @@ export const json = <Body, Message>(input: JsonInput<Body, Message>): JsonTransp
|
||||
...prepareInput,
|
||||
})
|
||||
return {
|
||||
url: yield* toWebSocketUrl(parts.url),
|
||||
url: yield* webSocketUrl(parts.url),
|
||||
headers: parts.headers,
|
||||
message: input.encodeMessage(yield* input.toMessage(parts.jsonBody)),
|
||||
}
|
||||
}),
|
||||
execute: (prepared, request, _runtime, options) => {
|
||||
const webSocket = options?.webSocket
|
||||
frames: (prepared, _request, runtime) => {
|
||||
const webSocket = runtime.webSocket
|
||||
if (!webSocket) {
|
||||
return Effect.fail(
|
||||
transportError("json", "WebSocket JSON transport requires StreamOptions.webSocket", {
|
||||
return Stream.fail(
|
||||
transportError("json", "WebSocket JSON transport requires WebSocketExecutor.Service", {
|
||||
url: prepared.url,
|
||||
kind: "websocket",
|
||||
phase: "prepare",
|
||||
delivery: "not-sent",
|
||||
}),
|
||||
)
|
||||
}
|
||||
const driver: WebSocketChannelDriver = {
|
||||
create: () => Effect.succeed({ message: prepared.message, mode: "full" }),
|
||||
observe: (_create, frame) => Effect.succeed({ type: "frame", frame }),
|
||||
}
|
||||
const exchange: WebSocketChannelExchange = {
|
||||
id: request.id ?? "request",
|
||||
connect: { url: prepared.url, headers: prepared.headers },
|
||||
fallback: () =>
|
||||
Stream.fail(
|
||||
transportError("fallback", "WebSocket JSON transport does not provide HTTP fallback", {
|
||||
url: prepared.url,
|
||||
kind: "websocket",
|
||||
phase: "fallback",
|
||||
delivery: "not-sent",
|
||||
}),
|
||||
),
|
||||
driver,
|
||||
}
|
||||
return webSocket.execute(exchange)
|
||||
const decoder = new TextDecoder()
|
||||
return Stream.unwrap(
|
||||
Effect.gen(function* () {
|
||||
const connection = yield* Effect.acquireRelease(
|
||||
webSocket.open({ url: prepared.url, headers: prepared.headers }),
|
||||
(connection) => connection.close,
|
||||
)
|
||||
yield* connection.sendText(prepared.message)
|
||||
return connection.messages.pipe(Stream.map((message) => messageText(message, decoder)))
|
||||
}),
|
||||
)
|
||||
},
|
||||
})
|
||||
|
||||
@@ -395,13 +266,15 @@ export const jsonTransport = {
|
||||
with: json,
|
||||
} as const
|
||||
|
||||
export const WebSocketTransport = {
|
||||
json,
|
||||
jsonTransport,
|
||||
direct,
|
||||
makeDirect,
|
||||
export const WebSocketExecutor = {
|
||||
Service,
|
||||
layer,
|
||||
open,
|
||||
fromWebSocket,
|
||||
messageText,
|
||||
toWebSocketUrl,
|
||||
} as const
|
||||
|
||||
export const WebSocketTransport = {
|
||||
json,
|
||||
jsonTransport,
|
||||
} as const
|
||||
|
||||
@@ -2,28 +2,28 @@ import { Schema } from "effect"
|
||||
import { Tool } from "@opencode-ai/schema/tool"
|
||||
import { ModelID, ProviderID, ProviderMetadata, RouteID } from "./ids"
|
||||
|
||||
export const ProviderFailureClassification = Schema.Literals(["context-overflow", "payload-too-large"])
|
||||
export const ProviderFailureClassification = Schema.Literal("context-overflow")
|
||||
export type ProviderFailureClassification = typeof ProviderFailureClassification.Type
|
||||
|
||||
export class HttpRequestDetails extends Schema.Class<HttpRequestDetails>("AI.HttpRequestDetails")({
|
||||
export class HttpRequestDetails extends Schema.Class<HttpRequestDetails>("LLM.HttpRequestDetails")({
|
||||
method: Schema.String,
|
||||
url: Schema.String,
|
||||
headers: Schema.Record(Schema.String, Schema.String),
|
||||
}) {}
|
||||
|
||||
export class HttpResponseDetails extends Schema.Class<HttpResponseDetails>("AI.HttpResponseDetails")({
|
||||
export class HttpResponseDetails extends Schema.Class<HttpResponseDetails>("LLM.HttpResponseDetails")({
|
||||
status: Schema.Number,
|
||||
headers: Schema.Record(Schema.String, Schema.String),
|
||||
}) {}
|
||||
|
||||
export class HttpRateLimitDetails extends Schema.Class<HttpRateLimitDetails>("AI.HttpRateLimitDetails")({
|
||||
export class HttpRateLimitDetails extends Schema.Class<HttpRateLimitDetails>("LLM.HttpRateLimitDetails")({
|
||||
retryAfterMs: Schema.optional(Schema.Number),
|
||||
limit: Schema.optional(Schema.Record(Schema.String, Schema.String)),
|
||||
remaining: Schema.optional(Schema.Record(Schema.String, Schema.String)),
|
||||
reset: Schema.optional(Schema.Record(Schema.String, Schema.String)),
|
||||
}) {}
|
||||
|
||||
export class HttpContext extends Schema.Class<HttpContext>("AI.HttpContext")({
|
||||
export class HttpContext extends Schema.Class<HttpContext>("LLM.HttpContext")({
|
||||
request: HttpRequestDetails,
|
||||
response: Schema.optional(HttpResponseDetails),
|
||||
body: Schema.optional(Schema.String),
|
||||
@@ -32,7 +32,7 @@ export class HttpContext extends Schema.Class<HttpContext>("AI.HttpContext")({
|
||||
rateLimit: Schema.optional(HttpRateLimitDetails),
|
||||
}) {}
|
||||
|
||||
export class InvalidRequestReason extends Schema.Class<InvalidRequestReason>("AI.Error.InvalidRequest")({
|
||||
export class InvalidRequestReason extends Schema.Class<InvalidRequestReason>("LLM.Error.InvalidRequest")({
|
||||
_tag: Schema.tag("InvalidRequest"),
|
||||
message: Schema.String,
|
||||
parameter: Schema.optional(Schema.String),
|
||||
@@ -41,18 +41,18 @@ export class InvalidRequestReason extends Schema.Class<InvalidRequestReason>("AI
|
||||
http: Schema.optional(HttpContext),
|
||||
}) {}
|
||||
|
||||
export class NoRouteReason extends Schema.Class<NoRouteReason>("AI.Error.NoRoute")({
|
||||
export class NoRouteReason extends Schema.Class<NoRouteReason>("LLM.Error.NoRoute")({
|
||||
_tag: Schema.tag("NoRoute"),
|
||||
route: RouteID,
|
||||
provider: ProviderID,
|
||||
model: ModelID,
|
||||
}) {
|
||||
get message() {
|
||||
return `No AI route for ${this.provider}/${this.model} using ${this.route}`
|
||||
return `No LLM route for ${this.provider}/${this.model} using ${this.route}`
|
||||
}
|
||||
}
|
||||
|
||||
export class AuthenticationReason extends Schema.Class<AuthenticationReason>("AI.Error.Authentication")({
|
||||
export class AuthenticationReason extends Schema.Class<AuthenticationReason>("LLM.Error.Authentication")({
|
||||
_tag: Schema.tag("Authentication"),
|
||||
message: Schema.String,
|
||||
kind: Schema.Literals(["missing", "invalid", "expired", "insufficient-permissions", "unknown"]),
|
||||
@@ -60,7 +60,7 @@ export class AuthenticationReason extends Schema.Class<AuthenticationReason>("AI
|
||||
http: Schema.optional(HttpContext),
|
||||
}) {}
|
||||
|
||||
export class RateLimitReason extends Schema.Class<RateLimitReason>("AI.Error.RateLimit")({
|
||||
export class RateLimitReason extends Schema.Class<RateLimitReason>("LLM.Error.RateLimit")({
|
||||
_tag: Schema.tag("RateLimit"),
|
||||
message: Schema.String,
|
||||
retryAfterMs: Schema.optional(Schema.Number),
|
||||
@@ -69,21 +69,21 @@ export class RateLimitReason extends Schema.Class<RateLimitReason>("AI.Error.Rat
|
||||
http: Schema.optional(HttpContext),
|
||||
}) {}
|
||||
|
||||
export class QuotaExceededReason extends Schema.Class<QuotaExceededReason>("AI.Error.QuotaExceeded")({
|
||||
export class QuotaExceededReason extends Schema.Class<QuotaExceededReason>("LLM.Error.QuotaExceeded")({
|
||||
_tag: Schema.tag("QuotaExceeded"),
|
||||
message: Schema.String,
|
||||
providerMetadata: Schema.optional(ProviderMetadata),
|
||||
http: Schema.optional(HttpContext),
|
||||
}) {}
|
||||
|
||||
export class ContentPolicyReason extends Schema.Class<ContentPolicyReason>("AI.Error.ContentPolicy")({
|
||||
export class ContentPolicyReason extends Schema.Class<ContentPolicyReason>("LLM.Error.ContentPolicy")({
|
||||
_tag: Schema.tag("ContentPolicy"),
|
||||
message: Schema.String,
|
||||
providerMetadata: Schema.optional(ProviderMetadata),
|
||||
http: Schema.optional(HttpContext),
|
||||
}) {}
|
||||
|
||||
export class ProviderInternalReason extends Schema.Class<ProviderInternalReason>("AI.Error.ProviderInternal")({
|
||||
export class ProviderInternalReason extends Schema.Class<ProviderInternalReason>("LLM.Error.ProviderInternal")({
|
||||
_tag: Schema.tag("ProviderInternal"),
|
||||
message: Schema.String,
|
||||
status: Schema.optional(Schema.Number),
|
||||
@@ -92,33 +92,25 @@ export class ProviderInternalReason extends Schema.Class<ProviderInternalReason>
|
||||
http: Schema.optional(HttpContext),
|
||||
}) {}
|
||||
|
||||
export class TransportReason extends Schema.Class<TransportReason>("AI.Error.Transport")({
|
||||
export class TransportReason extends Schema.Class<TransportReason>("LLM.Error.Transport")({
|
||||
_tag: Schema.tag("Transport"),
|
||||
message: Schema.String,
|
||||
kind: Schema.optional(Schema.String),
|
||||
url: Schema.optional(Schema.String),
|
||||
http: Schema.optional(HttpContext),
|
||||
phase: Schema.optional(
|
||||
Schema.Literals(["prepare", "queue", "connect", "send", "receive", "decode", "complete", "fallback", "close"]),
|
||||
),
|
||||
delivery: Schema.optional(Schema.Literals(["not-sent", "rejected", "ambiguous", "accepted"])),
|
||||
recovery: Schema.optional(
|
||||
Schema.Literals(["retry-connect", "retry-full", "rotate-and-retry-full", "fallback-http", "fail"]),
|
||||
),
|
||||
}) {}
|
||||
|
||||
export class InvalidProviderOutputReason extends Schema.Class<InvalidProviderOutputReason>(
|
||||
"AI.Error.InvalidProviderOutput",
|
||||
"LLM.Error.InvalidProviderOutput",
|
||||
)({
|
||||
_tag: Schema.tag("InvalidProviderOutput"),
|
||||
message: Schema.String,
|
||||
classification: Schema.optional(Schema.Literals(["incomplete-stream"])),
|
||||
route: Schema.optional(Schema.String),
|
||||
raw: Schema.optional(Schema.String),
|
||||
providerMetadata: Schema.optional(ProviderMetadata),
|
||||
}) {}
|
||||
|
||||
export class UnknownProviderReason extends Schema.Class<UnknownProviderReason>("AI.Error.UnknownProvider")({
|
||||
export class UnknownProviderReason extends Schema.Class<UnknownProviderReason>("LLM.Error.UnknownProvider")({
|
||||
_tag: Schema.tag("UnknownProvider"),
|
||||
message: Schema.String,
|
||||
status: Schema.optional(Schema.Number),
|
||||
@@ -126,7 +118,7 @@ export class UnknownProviderReason extends Schema.Class<UnknownProviderReason>("
|
||||
http: Schema.optional(HttpContext),
|
||||
}) {}
|
||||
|
||||
export const AIErrorReason = Schema.Union([
|
||||
export const LLMErrorReason = Schema.Union([
|
||||
InvalidRequestReason,
|
||||
NoRouteReason,
|
||||
AuthenticationReason,
|
||||
@@ -138,12 +130,12 @@ export const AIErrorReason = Schema.Union([
|
||||
InvalidProviderOutputReason,
|
||||
UnknownProviderReason,
|
||||
]).pipe(Schema.toTaggedUnion("_tag"))
|
||||
export type AIErrorReason = Schema.Schema.Type<typeof AIErrorReason>
|
||||
export type LLMErrorReason = Schema.Schema.Type<typeof LLMErrorReason>
|
||||
|
||||
export class AIError extends Schema.TaggedErrorClass<AIError>()("AI.Error", {
|
||||
export class LLMError extends Schema.TaggedErrorClass<LLMError>()("LLM.Error", {
|
||||
module: Schema.String,
|
||||
method: Schema.String,
|
||||
reason: AIErrorReason,
|
||||
reason: LLMErrorReason,
|
||||
}) {
|
||||
override readonly cause = this.reason
|
||||
|
||||
|
||||
@@ -48,7 +48,7 @@ import { ProviderFailureClassification } from "./errors"
|
||||
* — for fields we don't normalize and for billing-level audit trails.
|
||||
* Matches the same escape-hatch field on `LLMEvent`.
|
||||
*/
|
||||
export class Usage extends Schema.Class<Usage>("AI.Usage")({
|
||||
export class Usage extends Schema.Class<Usage>("LLM.Usage")({
|
||||
inputTokens: Schema.optional(Schema.Number),
|
||||
outputTokens: Schema.optional(Schema.Number),
|
||||
nonCachedInputTokens: Schema.optional(Schema.Number),
|
||||
|
||||
@@ -1,6 +1,5 @@
|
||||
import { Schema } from "effect"
|
||||
import { ProviderMetadata } from "@opencode-ai/schema/ai"
|
||||
import { LLM } from "@opencode-ai/schema/llm"
|
||||
import { LLM, ProviderMetadata } from "@opencode-ai/schema/llm"
|
||||
|
||||
export { ProviderMetadata }
|
||||
|
||||
@@ -12,10 +11,10 @@ export type ProtocolID = Schema.Schema.Type<typeof ProtocolID>
|
||||
export const RouteID = Schema.String
|
||||
export type RouteID = Schema.Schema.Type<typeof RouteID>
|
||||
|
||||
export const ModelID = Schema.String.pipe(Schema.brand("AI.ModelID"))
|
||||
export const ModelID = Schema.String.pipe(Schema.brand("LLM.ModelID"))
|
||||
export type ModelID = typeof ModelID.Type
|
||||
|
||||
export const ProviderID = Schema.String.pipe(Schema.brand("AI.ProviderID"))
|
||||
export const ProviderID = Schema.String.pipe(Schema.brand("LLM.ProviderID"))
|
||||
export type ProviderID = typeof ProviderID.Type
|
||||
|
||||
export const ResponseID = Schema.String
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
import { Schema } from "effect"
|
||||
import { Tool } from "@opencode-ai/schema/tool"
|
||||
import { JsonSchema, MessageRole, ProviderMetadata } from "./ids"
|
||||
import { CacheHint, CachePolicy, GenerationOptions, HttpOptions, LanguageModelSchema, ProviderOptions } from "./options"
|
||||
import { CacheHint, CachePolicy, GenerationOptions, HttpOptions, ModelSchema, ProviderOptions } from "./options"
|
||||
import { isRecord } from "../utils/record"
|
||||
|
||||
const systemPartSchema = Schema.Struct({
|
||||
@@ -124,7 +124,6 @@ export const ToolCallPart = Object.assign(
|
||||
name: Schema.String,
|
||||
input: Schema.Unknown,
|
||||
providerExecuted: Schema.optional(Schema.Boolean),
|
||||
cache: Schema.optional(CacheHint),
|
||||
metadata: Schema.optional(Schema.Record(Schema.String, Schema.Unknown)),
|
||||
providerMetadata: Schema.optional(ProviderMetadata),
|
||||
}).annotate({ identifier: "LLM.Content.ToolCall" }),
|
||||
@@ -169,7 +168,6 @@ export const ReasoningPart = Schema.Struct({
|
||||
type: Schema.Literal("reasoning"),
|
||||
text: Schema.String,
|
||||
encrypted: Schema.optional(Schema.String),
|
||||
cache: Schema.optional(CacheHint),
|
||||
metadata: Schema.optional(Schema.Record(Schema.String, Schema.Unknown)),
|
||||
providerMetadata: Schema.optional(ProviderMetadata),
|
||||
}).annotate({ identifier: "LLM.Content.Reasoning" })
|
||||
@@ -263,7 +261,7 @@ export namespace ToolChoice {
|
||||
|
||||
export class LLMRequest extends Schema.Class<LLMRequest>("LLM.Request")({
|
||||
id: Schema.optional(Schema.String),
|
||||
model: LanguageModelSchema,
|
||||
model: ModelSchema,
|
||||
system: Schema.Array(SystemPart),
|
||||
messages: Schema.Array(Message),
|
||||
tools: Schema.Array(ToolDefinition),
|
||||
|
||||
@@ -50,7 +50,7 @@ export const mergeProviderOptions = (
|
||||
return Object.keys(result).length === 0 ? undefined : result
|
||||
}
|
||||
|
||||
export class HttpOptions extends Schema.Class<HttpOptions>("AI.HttpOptions")({
|
||||
export class HttpOptions extends Schema.Class<HttpOptions>("LLM.HttpOptions")({
|
||||
body: Schema.optional(JsonSchema),
|
||||
headers: Schema.optional(Schema.Record(Schema.String, Schema.String)),
|
||||
query: Schema.optional(Schema.Record(Schema.String, Schema.String)),
|
||||
@@ -121,32 +121,31 @@ export const mergeGenerationOptions = (...items: ReadonlyArray<GenerationOptions
|
||||
return Object.values(result).some((value) => value !== undefined) ? result : undefined
|
||||
}
|
||||
|
||||
export class LanguageModelLimits extends Schema.Class<LanguageModelLimits>("LLM.LanguageModelLimits")({
|
||||
export class ModelLimits extends Schema.Class<ModelLimits>("LLM.ModelLimits")({
|
||||
context: Schema.optional(Schema.Number),
|
||||
input: Schema.optional(Schema.Number),
|
||||
output: Schema.optional(Schema.Number),
|
||||
}) {}
|
||||
|
||||
export namespace LanguageModelLimits {
|
||||
export type Input = LanguageModelLimits | ConstructorParameters<typeof LanguageModelLimits>[0]
|
||||
export namespace ModelLimits {
|
||||
export type Input = ModelLimits | ConstructorParameters<typeof ModelLimits>[0]
|
||||
|
||||
/** Normalize model limit input into the canonical `LanguageModelLimits` class. */
|
||||
/** Normalize model limit input into the canonical `ModelLimits` class. */
|
||||
export const make = (input: Input | undefined) =>
|
||||
input instanceof LanguageModelLimits ? input : new LanguageModelLimits(input ?? {})
|
||||
input instanceof ModelLimits ? input : new ModelLimits(input ?? {})
|
||||
}
|
||||
|
||||
export class LanguageModelDefaults extends Schema.Class<LanguageModelDefaults>("LLM.LanguageModelDefaults")({
|
||||
limits: Schema.optional(LanguageModelLimits),
|
||||
export class ModelDefaults extends Schema.Class<ModelDefaults>("LLM.ModelDefaults")({
|
||||
limits: Schema.optional(ModelLimits),
|
||||
generation: Schema.optional(GenerationOptions),
|
||||
providerOptions: Schema.optional(ProviderOptions),
|
||||
http: Schema.optional(HttpOptions),
|
||||
}) {}
|
||||
|
||||
export namespace LanguageModelDefaults {
|
||||
export namespace ModelDefaults {
|
||||
export type Input =
|
||||
| LanguageModelDefaults
|
||||
| ModelDefaults
|
||||
| {
|
||||
readonly limits?: LanguageModelLimits.Input
|
||||
readonly limits?: ModelLimits.Input
|
||||
readonly generation?: GenerationOptions.Input
|
||||
readonly providerOptions?: ProviderOptions
|
||||
readonly http?: HttpOptions.Input
|
||||
@@ -154,9 +153,9 @@ export namespace LanguageModelDefaults {
|
||||
|
||||
/** Normalize selected-model request defaults without applying precedence. */
|
||||
export const make = (input: Input) => {
|
||||
if (input instanceof LanguageModelDefaults) return input
|
||||
return new LanguageModelDefaults({
|
||||
limits: input.limits === undefined ? undefined : LanguageModelLimits.make(input.limits),
|
||||
if (input instanceof ModelDefaults) return input
|
||||
return new ModelDefaults({
|
||||
limits: input.limits === undefined ? undefined : ModelLimits.make(input.limits),
|
||||
generation: input.generation === undefined ? undefined : GenerationOptions.make(input.generation),
|
||||
providerOptions: input.providerOptions,
|
||||
http: input.http === undefined ? undefined : HttpOptions.make(input.http),
|
||||
@@ -164,39 +163,30 @@ export namespace LanguageModelDefaults {
|
||||
}
|
||||
}
|
||||
|
||||
export const LanguageModelToolSchemaCompatibility = Schema.Literals(["gemini", "moonshot"])
|
||||
export type LanguageModelToolSchemaCompatibility = Schema.Schema.Type<typeof LanguageModelToolSchemaCompatibility>
|
||||
export const ModelToolSchemaCompatibility = Schema.Literals(["gemini", "moonshot"])
|
||||
export type ModelToolSchemaCompatibility = Schema.Schema.Type<typeof ModelToolSchemaCompatibility>
|
||||
|
||||
export const LanguageModelMaxTokensFieldCompatibility = Schema.Literals(["max_completion_tokens", "max_tokens"])
|
||||
export type LanguageModelMaxTokensFieldCompatibility = Schema.Schema.Type<
|
||||
typeof LanguageModelMaxTokensFieldCompatibility
|
||||
>
|
||||
|
||||
export class LanguageModelCompatibility extends Schema.Class<LanguageModelCompatibility>(
|
||||
"LLM.LanguageModelCompatibility",
|
||||
)({
|
||||
toolSchema: Schema.optional(LanguageModelToolSchemaCompatibility),
|
||||
export class ModelCompatibility extends Schema.Class<ModelCompatibility>("LLM.ModelCompatibility")({
|
||||
toolSchema: Schema.optional(ModelToolSchemaCompatibility),
|
||||
reasoningField: Schema.optional(Schema.String),
|
||||
maxTokensField: Schema.optional(LanguageModelMaxTokensFieldCompatibility),
|
||||
}) {}
|
||||
|
||||
export namespace LanguageModelCompatibility {
|
||||
export type Input = LanguageModelCompatibility | ConstructorParameters<typeof LanguageModelCompatibility>[0]
|
||||
export namespace ModelCompatibility {
|
||||
export type Input = ModelCompatibility | ConstructorParameters<typeof ModelCompatibility>[0]
|
||||
|
||||
/** Normalize model/upstream compatibility metadata without projecting requests. */
|
||||
export const make = (input: Input) =>
|
||||
input instanceof LanguageModelCompatibility ? input : new LanguageModelCompatibility(input)
|
||||
export const make = (input: Input) => (input instanceof ModelCompatibility ? input : new ModelCompatibility(input))
|
||||
}
|
||||
|
||||
export class LanguageModel<Options extends ProviderOptions = ProviderOptions> {
|
||||
export class Model<Options extends ProviderOptions = ProviderOptions> {
|
||||
declare protected readonly _ProviderOptions: Options
|
||||
readonly id: ModelID
|
||||
readonly provider: ProviderID
|
||||
readonly route: AnyRoute
|
||||
readonly defaults?: LanguageModelDefaults
|
||||
readonly compatibility?: LanguageModelCompatibility
|
||||
readonly defaults?: ModelDefaults
|
||||
readonly compatibility?: ModelCompatibility
|
||||
|
||||
constructor(input: LanguageModel.ConstructorInput) {
|
||||
constructor(input: Model.ConstructorInput) {
|
||||
this.id = input.id
|
||||
this.provider = input.provider
|
||||
this.route = input.route
|
||||
@@ -204,18 +194,17 @@ export class LanguageModel<Options extends ProviderOptions = ProviderOptions> {
|
||||
this.compatibility = input.compatibility
|
||||
}
|
||||
|
||||
static make<Options extends ProviderOptions = ProviderOptions>(input: LanguageModel.Input) {
|
||||
return new LanguageModel<Options>({
|
||||
static make<Options extends ProviderOptions = ProviderOptions>(input: Model.Input) {
|
||||
return new Model<Options>({
|
||||
id: ModelID.make(input.id),
|
||||
provider: ProviderID.make(input.provider),
|
||||
route: input.route,
|
||||
defaults: input.defaults === undefined ? undefined : LanguageModelDefaults.make(input.defaults),
|
||||
compatibility:
|
||||
input.compatibility === undefined ? undefined : LanguageModelCompatibility.make(input.compatibility),
|
||||
defaults: input.defaults === undefined ? undefined : ModelDefaults.make(input.defaults),
|
||||
compatibility: input.compatibility === undefined ? undefined : ModelCompatibility.make(input.compatibility),
|
||||
})
|
||||
}
|
||||
|
||||
static input<Options extends ProviderOptions>(model: LanguageModel<Options>): LanguageModel.ConstructorInput {
|
||||
static input<Options extends ProviderOptions>(model: Model<Options>): Model.ConstructorInput {
|
||||
return {
|
||||
id: model.id,
|
||||
provider: model.provider,
|
||||
@@ -225,40 +214,37 @@ export class LanguageModel<Options extends ProviderOptions = ProviderOptions> {
|
||||
}
|
||||
}
|
||||
|
||||
static update<Options extends ProviderOptions>(model: LanguageModel<Options>, patch: Partial<LanguageModel.Input>) {
|
||||
static update<Options extends ProviderOptions>(model: Model<Options>, patch: Partial<Model.Input>) {
|
||||
if (Object.keys(patch).length === 0) return model
|
||||
return LanguageModel.make<Options>({
|
||||
...LanguageModel.input(model),
|
||||
return Model.make<Options>({
|
||||
...Model.input(model),
|
||||
...patch,
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
export namespace LanguageModel {
|
||||
export namespace Model {
|
||||
export type ConstructorInput = {
|
||||
readonly id: ModelID
|
||||
readonly provider: ProviderID
|
||||
readonly route: AnyRoute
|
||||
readonly defaults?: LanguageModelDefaults
|
||||
readonly compatibility?: LanguageModelCompatibility
|
||||
readonly defaults?: ModelDefaults
|
||||
readonly compatibility?: ModelCompatibility
|
||||
}
|
||||
|
||||
export type Input = Omit<ConstructorInput, "id" | "provider" | "defaults" | "compatibility"> & {
|
||||
readonly id: string | ModelID
|
||||
readonly provider: string | ProviderID
|
||||
readonly defaults?: LanguageModelDefaults.Input
|
||||
readonly compatibility?: LanguageModelCompatibility.Input
|
||||
readonly defaults?: ModelDefaults.Input
|
||||
readonly compatibility?: ModelCompatibility.Input
|
||||
}
|
||||
}
|
||||
|
||||
export type LanguageModelInput = LanguageModel.Input
|
||||
export type ModelInput = Model.Input
|
||||
|
||||
export type LanguageModelProviderOptions<SelectedModel> =
|
||||
SelectedModel extends LanguageModel<infer Options> ? Options : never
|
||||
export type ModelProviderOptions<SelectedModel> = SelectedModel extends Model<infer Options> ? Options : never
|
||||
|
||||
export const LanguageModelSchema = Schema.declare((value): value is LanguageModel => value instanceof LanguageModel, {
|
||||
expected: "LLM.LanguageModel",
|
||||
})
|
||||
export const ModelSchema = Schema.declare((value): value is Model => value instanceof Model, { expected: "LLM.Model" })
|
||||
|
||||
export class CacheHint extends Schema.Class<CacheHint>("LLM.CacheHint")({
|
||||
type: Schema.Literals(["ephemeral", "persistent"]),
|
||||
|
||||
@@ -5,13 +5,13 @@ import {
|
||||
LLMEvent,
|
||||
LLMResponse,
|
||||
type FinishReasonDetails,
|
||||
type AIError,
|
||||
type LLMError,
|
||||
type LLMRequest,
|
||||
type UsageInput,
|
||||
} from "./schema"
|
||||
import { Context, Deferred, Effect, Latch, Layer, Queue, Scope, Stream } from "effect"
|
||||
|
||||
export type Response = readonly LLMEvent[] | Stream.Stream<LLMEvent, AIError>
|
||||
export type Response = readonly LLMEvent[] | Stream.Stream<LLMEvent, LLMError>
|
||||
|
||||
export type Gate = Readonly<{ started: Effect.Effect<void>; release: Effect.Effect<void> }>
|
||||
|
||||
@@ -63,7 +63,7 @@ export const textWithUsage = (value: string, id: string, inputTokens: number) =>
|
||||
|
||||
export const tool = (id: string, name: string, input: unknown) => toolCalls(LLMEvent.toolCall({ id, name, input }))
|
||||
|
||||
export const failAfter = (error: AIError, ...events: readonly LLMEvent[]) =>
|
||||
export const failAfter = (error: LLMError, ...events: readonly LLMEvent[]) =>
|
||||
Stream.fromIterable(events).pipe(Stream.concat(Stream.fail(error)))
|
||||
|
||||
export const hangAfter = (...events: readonly LLMEvent[]) => Stream.concat(Stream.fromIterable(events), Stream.never)
|
||||
|
||||
@@ -24,7 +24,7 @@ export type ToolExecute<Parameters extends ToolSchema<any>, Success extends Tool
|
||||
) => Effect.Effect<Schema.Schema.Type<Success>, ToolFailure>
|
||||
|
||||
export interface ToolModelOutputInput<Parameters, Output> {
|
||||
readonly id: ToolCallPart["id"]
|
||||
readonly callID: ToolCallPart["id"]
|
||||
readonly parameters: Parameters
|
||||
readonly output: Output
|
||||
}
|
||||
@@ -59,7 +59,7 @@ export interface Definition<Parameters extends ToolSchema<any>, Success extends
|
||||
/** @internal */
|
||||
readonly _project: (
|
||||
parameters: Schema.Schema.Type<Parameters>,
|
||||
id: ToolCallPart["id"],
|
||||
callID: ToolCallPart["id"],
|
||||
output: unknown,
|
||||
) => ToolOutputType
|
||||
/** @internal */
|
||||
@@ -173,8 +173,8 @@ export function make(config: TypedToolConfig | DynamicToolConfig): AnyTool {
|
||||
toStructuredOutput: config.toStructuredOutput,
|
||||
_decode: Effect.succeed,
|
||||
_encode: Effect.succeed,
|
||||
_project: (parameters, id, output) =>
|
||||
project(config.toModelOutput, config.toStructuredOutput, parameters, id, output),
|
||||
_project: (parameters, callID, output) =>
|
||||
project(config.toModelOutput, config.toStructuredOutput, parameters, callID, output),
|
||||
_legacyResult: config.toModelOutput === undefined && config.toStructuredOutput === undefined,
|
||||
_definition: new ToolDefinition({
|
||||
name: "",
|
||||
@@ -193,8 +193,8 @@ export function make(config: TypedToolConfig | DynamicToolConfig): AnyTool {
|
||||
toStructuredOutput: config.toStructuredOutput,
|
||||
_decode: Schema.decodeUnknownEffect(config.parameters),
|
||||
_encode: Schema.encodeEffect(config.success),
|
||||
_project: (parameters, id, output) =>
|
||||
project(config.toModelOutput, config.toStructuredOutput, parameters, id, output),
|
||||
_project: (parameters, callID, output) =>
|
||||
project(config.toModelOutput, config.toStructuredOutput, parameters, callID, output),
|
||||
_legacyResult: false,
|
||||
_definition: new ToolDefinition({
|
||||
name: "",
|
||||
@@ -239,12 +239,12 @@ const project = (
|
||||
toModelOutput: ((input: ToolModelOutputInput<any, any>) => ReadonlyArray<Tool.Content>) | undefined,
|
||||
toStructuredOutput: ((output: unknown) => unknown) | undefined,
|
||||
parameters: unknown,
|
||||
id: ToolCallPart["id"],
|
||||
callID: ToolCallPart["id"],
|
||||
output: unknown,
|
||||
): ToolOutputType =>
|
||||
ToolOutput.make(
|
||||
toStructuredOutput?.(output) ?? output,
|
||||
toModelOutput?.({ id, parameters, output }) ??
|
||||
toModelOutput?.({ callID, parameters, output }) ??
|
||||
(typeof output === "string" ? [{ type: "text", text: output }] : []),
|
||||
)
|
||||
|
||||
|
||||
@@ -3,11 +3,11 @@ import { Effect, Schema, Stream } from "effect"
|
||||
import { LLM, LLMRequest, LLMResponse } from "../src"
|
||||
import { Route, Endpoint, LLMClient, Protocol, type FramingDef } from "../src/route"
|
||||
import { compileRequest } from "../src/route/client"
|
||||
import { LanguageModel } from "../src/schema"
|
||||
import { Model } from "../src/schema"
|
||||
import { testEffect } from "./lib/effect"
|
||||
import { dynamicResponse } from "./lib/http"
|
||||
|
||||
const updateModel = (model: LanguageModel, patch: Partial<LanguageModel.Input>) => LanguageModel.update(model, patch)
|
||||
const updateModel = (model: Model, patch: Partial<Model.Input>) => Model.update(model, patch)
|
||||
|
||||
const Json = Schema.fromJsonString(Schema.Unknown)
|
||||
const encodeJson = Schema.encodeSync(Json)
|
||||
@@ -86,7 +86,7 @@ const configuredGemini = gemini.with({ endpoint: { baseURL: "https://fake.local"
|
||||
|
||||
const request = LLM.request({
|
||||
id: "req_1",
|
||||
model: LanguageModel.make({
|
||||
model: Model.make({
|
||||
id: "fake-model",
|
||||
provider: "fake-provider",
|
||||
route: configuredFake,
|
||||
@@ -133,8 +133,8 @@ describe("llm route", () => {
|
||||
Effect.gen(function* () {
|
||||
const error = yield* (yield* LLMClient.Service).stream(request).pipe(Stream.runDrain, Effect.flip)
|
||||
|
||||
expect(error.reason).toMatchObject({ _tag: "InvalidProviderOutput", classification: "incomplete-stream" })
|
||||
expect(error.message).toContain("The provider response ended unexpectedly.")
|
||||
expect(error.reason).toMatchObject({ _tag: "InvalidProviderOutput" })
|
||||
expect(error.message).toContain("Provider stream ended without a terminal finish event")
|
||||
}),
|
||||
)
|
||||
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
import { Config } from "effect"
|
||||
import { Auth } from "../src/route"
|
||||
import type { LanguageModelFactory } from "../src/route/auth-options"
|
||||
import type { ModelFactory } from "../src/route/auth-options"
|
||||
import * as OpenAIChat from "../src/protocols/openai-chat"
|
||||
import * as AmazonBedrock from "../src/providers/amazon-bedrock"
|
||||
import * as Anthropic from "../src/providers/anthropic"
|
||||
@@ -23,13 +23,13 @@ type BaseOptions = {
|
||||
readonly headers?: Record<string, string>
|
||||
}
|
||||
|
||||
type LanguageModel = {
|
||||
type Model = {
|
||||
readonly id: string
|
||||
}
|
||||
|
||||
declare const auth: Auth.Definition
|
||||
declare const optionalAuthModel: LanguageModelFactory<BaseOptions, "optional", LanguageModel>
|
||||
declare const requiredAuthModel: LanguageModelFactory<BaseOptions, "required", LanguageModel>
|
||||
declare const optionalAuthModel: ModelFactory<BaseOptions, "optional", Model>
|
||||
declare const requiredAuthModel: ModelFactory<BaseOptions, "required", Model>
|
||||
const configApiKey = Config.redacted("OPENAI_API_KEY")
|
||||
|
||||
OpenAIChat.route.model({ id: "gpt-4.1-mini" })
|
||||
|
||||
@@ -4,12 +4,12 @@ import { Headers } from "effect/unstable/http"
|
||||
import { LLM } from "../src"
|
||||
import { Auth } from "../src/route/auth"
|
||||
import * as OpenAIChat from "../src/protocols/openai-chat"
|
||||
import { LanguageModel } from "../src/schema"
|
||||
import { Model } from "../src/schema"
|
||||
import { it } from "./lib/effect"
|
||||
|
||||
const request = LLM.request({
|
||||
id: "req_auth",
|
||||
model: LanguageModel.make({ id: "fake-model", provider: "fake", route: OpenAIChat.route }),
|
||||
model: Model.make({ id: "fake-model", provider: "fake", route: OpenAIChat.route }),
|
||||
prompt: "hello",
|
||||
})
|
||||
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
import { describe, expect, test } from "bun:test"
|
||||
import { Effect, Ref, Schema } from "effect"
|
||||
import { HttpClientRequest, HttpClientResponse } from "effect/unstable/http"
|
||||
import { Effect, Schema } from "effect"
|
||||
import { HttpClientRequest } from "effect/unstable/http"
|
||||
import { LLM, mergeProviderOptions } from "../src"
|
||||
import { AnthropicMessages, OpenAIChat } from "../src/protocols"
|
||||
import { Auth, LLMClient } from "../src/route"
|
||||
@@ -146,16 +146,12 @@ describe("request option precedence", () => {
|
||||
prompt: "Say hello.",
|
||||
}),
|
||||
{
|
||||
http: (request, handler) =>
|
||||
Effect.gen(function* () {
|
||||
return yield* handler(
|
||||
request.pipe(
|
||||
HttpClientRequest.setUrl("https://proxy.test/v1/chat/completions"),
|
||||
HttpClientRequest.setMethod("PUT"),
|
||||
HttpClientRequest.setHeader("x-plugin", "transformed"),
|
||||
HttpClientRequest.bodyText(JSON.stringify({ transformed: true }), "application/custom+json"),
|
||||
),
|
||||
)
|
||||
transform: (request) =>
|
||||
Effect.sync(() => {
|
||||
expect(request.headers.authorization).toBe("Bearer fresh-key")
|
||||
request.url = "https://proxy.test/v1/chat/completions"
|
||||
request.headers["x-plugin"] = "transformed"
|
||||
request.body = JSON.stringify({ transformed: true })
|
||||
}),
|
||||
},
|
||||
).pipe(
|
||||
@@ -164,9 +160,7 @@ describe("request option precedence", () => {
|
||||
Effect.gen(function* () {
|
||||
const web = yield* HttpClientRequest.toWeb(input.request).pipe(Effect.orDie)
|
||||
expect(web.url).toBe("https://proxy.test/v1/chat/completions")
|
||||
expect(web.method).toBe("PUT")
|
||||
expect(web.headers.get("x-plugin")).toBe("transformed")
|
||||
expect(web.headers.get("content-type")).toBe("application/custom+json")
|
||||
expect(decodeJson(input.text)).toEqual({ transformed: true })
|
||||
return input.respond(sseEvents(deltaChunk({}, "stop")), {
|
||||
headers: { "content-type": "text/event-stream" },
|
||||
@@ -177,105 +171,26 @@ describe("request option precedence", () => {
|
||||
),
|
||||
)
|
||||
|
||||
it.effect("transforms the HTTP response before protocol decoding", () =>
|
||||
it.effect("rejects raw body overlays for protocol-owned roots", () =>
|
||||
Effect.gen(function* () {
|
||||
const response = yield* LLMClient.generate(
|
||||
const model = OpenAIChat.route
|
||||
.with({ endpoint: { baseURL: "https://api.openai.test/v1/" }, auth: Auth.bearer("test") })
|
||||
.model({ id: "gpt-4o-mini" })
|
||||
const error = yield* compileRequest(
|
||||
LLM.request({
|
||||
model: OpenAIChat.route
|
||||
.with({ endpoint: { baseURL: "https://api.openai.test/v1/" }, auth: Auth.bearer("test") })
|
||||
.model({ id: "gpt-4o-mini" }),
|
||||
model,
|
||||
prompt: "Say hello.",
|
||||
http: { body: { model: "gpt-5", messages: [], tools: [] } },
|
||||
}),
|
||||
{
|
||||
http: (request, handler) =>
|
||||
Effect.gen(function* () {
|
||||
const response = yield* handler(request)
|
||||
return HttpClientResponse.fromWeb(
|
||||
response.request,
|
||||
new Response((yield* response.text).replace("network", "hooked"), {
|
||||
status: response.status,
|
||||
headers: response.headers,
|
||||
}),
|
||||
)
|
||||
}),
|
||||
},
|
||||
).pipe(
|
||||
Effect.provide(
|
||||
dynamicResponse((input) =>
|
||||
Effect.succeed(
|
||||
input.respond(sseEvents(deltaChunk({ content: "network" }, "stop")), {
|
||||
headers: { "content-type": "text/event-stream" },
|
||||
}),
|
||||
),
|
||||
),
|
||||
),
|
||||
)
|
||||
).pipe(Effect.flip)
|
||||
|
||||
expect(response.text).toBe("hooked")
|
||||
expect(error.reason).toMatchObject({
|
||||
_tag: "InvalidRequest",
|
||||
message: "http.body cannot overlay protocol-owned field(s): model, messages, tools",
|
||||
})
|
||||
}),
|
||||
)
|
||||
|
||||
it.effect("can inspect an error response and retry the native request", () =>
|
||||
Effect.gen(function* () {
|
||||
const attempts = yield* Ref.make(0)
|
||||
const response = yield* LLMClient.generate(
|
||||
LLM.request({
|
||||
model: OpenAIChat.route
|
||||
.with({ endpoint: { baseURL: "https://api.openai.test/v1/" }, auth: Auth.bearer("stale") })
|
||||
.model({ id: "gpt-4o-mini" }),
|
||||
prompt: "Say hello.",
|
||||
}),
|
||||
{
|
||||
http: (request, handler) =>
|
||||
Effect.gen(function* () {
|
||||
const response = yield* handler(request)
|
||||
expect(response.status).toBe(401)
|
||||
return yield* handler(HttpClientRequest.setHeader(request, "authorization", "Bearer refreshed"))
|
||||
}),
|
||||
},
|
||||
).pipe(
|
||||
Effect.provide(
|
||||
dynamicResponse((input) =>
|
||||
Effect.gen(function* () {
|
||||
yield* Ref.update(attempts, (value) => value + 1)
|
||||
if (input.request.headers.authorization !== "Bearer refreshed")
|
||||
return input.respond("unauthorized", { status: 401 })
|
||||
return input.respond(sseEvents(deltaChunk({ content: "retried" }, "stop")), {
|
||||
headers: { "content-type": "text/event-stream" },
|
||||
})
|
||||
}),
|
||||
),
|
||||
),
|
||||
)
|
||||
|
||||
expect(response.text).toBe("retried")
|
||||
expect(yield* Ref.get(attempts)).toBe(2)
|
||||
}),
|
||||
)
|
||||
|
||||
it.effect("applies raw body overlays after protocol lowering", () =>
|
||||
LLMClient.generate(
|
||||
LLM.request({
|
||||
model: OpenAIChat.route
|
||||
.with({ endpoint: { baseURL: "https://api.openai.test/v1/" }, auth: Auth.bearer("test") })
|
||||
.model({ id: "gpt-4o-mini" }),
|
||||
prompt: "Say hello.",
|
||||
http: { body: { model: "gpt-5", messages: [], tools: [] } },
|
||||
}),
|
||||
).pipe(
|
||||
Effect.provide(
|
||||
dynamicResponse((input) =>
|
||||
Effect.gen(function* () {
|
||||
expect(decodeJson(input.text)).toMatchObject({ model: "gpt-5", messages: [], tools: [] })
|
||||
return input.respond(sseEvents(deltaChunk({}, "stop")), {
|
||||
headers: { "content-type": "text/event-stream" },
|
||||
})
|
||||
}),
|
||||
),
|
||||
),
|
||||
),
|
||||
)
|
||||
|
||||
it.effect("uses model output limits after route limits and before call maxTokens", () =>
|
||||
Effect.gen(function* () {
|
||||
const route = AnthropicMessages.route.with({
|
||||
|
||||
@@ -1,12 +1,4 @@
|
||||
import {
|
||||
LLM,
|
||||
Message,
|
||||
ToolCallPart,
|
||||
ToolDefinition,
|
||||
ToolResultPart,
|
||||
type ContentPart,
|
||||
type LanguageModel,
|
||||
} from "../src"
|
||||
import { LLM, Message, ToolCallPart, ToolDefinition, ToolResultPart, type ContentPart, type Model } from "../src"
|
||||
|
||||
export const basicContinuation = ["system", "user-text", "assistant-text", "user-follow-up"] as const
|
||||
export const toolContinuation = ["tool-call", "tool-result"] as const
|
||||
@@ -48,7 +40,7 @@ export const continuationTool = ToolDefinition.make({
|
||||
|
||||
export function continuationRequest(input: {
|
||||
readonly id: string
|
||||
readonly model: LanguageModel
|
||||
readonly model: Model
|
||||
readonly features: ReadonlyArray<ContinuationFeature>
|
||||
readonly image?: string
|
||||
}) {
|
||||
|
||||
@@ -2,11 +2,11 @@ import { describe, expect, test } from "bun:test"
|
||||
import { LLM } from "../src"
|
||||
import * as OpenAIChat from "../src/protocols/openai-chat"
|
||||
import { Endpoint } from "../src/route"
|
||||
import { LanguageModel } from "../src/schema"
|
||||
import { Model } from "../src/schema"
|
||||
|
||||
const request = () =>
|
||||
LLM.request({
|
||||
model: LanguageModel.make({
|
||||
model: Model.make({
|
||||
id: "model-1",
|
||||
provider: "test",
|
||||
route: OpenAIChat.route,
|
||||
|
||||
@@ -1,11 +1,10 @@
|
||||
import { describe, expect } from "bun:test"
|
||||
import { Deferred, Effect, Fiber, Layer, Ref, Stream } from "effect"
|
||||
import { Effect, Layer, Ref } from "effect"
|
||||
import { Headers, HttpClient, HttpClientRequest, HttpClientResponse } from "effect/unstable/http"
|
||||
import { LLM, AIError } from "../src"
|
||||
import { LLMClient, RequestExecutor, WebSocketTransport, type WebSocketChannelExecutor } from "../src/route"
|
||||
import { LLM, LLMError } from "../src"
|
||||
import { LLMClient, RequestExecutor } from "../src/route"
|
||||
import * as OpenAIChat from "../src/protocols/openai-chat"
|
||||
import * as OpenAI from "../src/providers/openai"
|
||||
import { dynamicResponse, fixedResponse } from "./lib/http"
|
||||
import { dynamicResponse } from "./lib/http"
|
||||
import { deltaChunk } from "./lib/openai-chunks"
|
||||
import { sseRaw } from "./lib/sse"
|
||||
import { it } from "./lib/effect"
|
||||
@@ -59,33 +58,21 @@ const countedResponsesLayer = (attempts: Ref.Ref<number>, responses: ReadonlyArr
|
||||
),
|
||||
)
|
||||
|
||||
const expectAIError = (error: unknown) => {
|
||||
expect(error).toBeInstanceOf(AIError)
|
||||
if (!(error instanceof AIError)) throw new Error("expected AIError")
|
||||
const expectLLMError = (error: unknown) => {
|
||||
expect(error).toBeInstanceOf(LLMError)
|
||||
if (!(error instanceof LLMError)) throw new Error("expected LLMError")
|
||||
return error
|
||||
}
|
||||
|
||||
const errorHttp = (error: AIError) => ("http" in error.reason ? error.reason.http : undefined)
|
||||
const errorHttp = (error: LLMError) => ("http" in error.reason ? error.reason.http : undefined)
|
||||
|
||||
describe("RequestExecutor", () => {
|
||||
it.effect("preserves middleware error messages", () =>
|
||||
Effect.gen(function* () {
|
||||
const executor = yield* RequestExecutor.Service
|
||||
const error = yield* executor
|
||||
.execute(request, () => Effect.fail(new Error("plugin rejected request")))
|
||||
.pipe(Effect.flip)
|
||||
|
||||
expectAIError(error)
|
||||
expect(error.reason.message).toBe("plugin rejected request")
|
||||
}).pipe(Effect.provide(responsesLayer([]))),
|
||||
)
|
||||
|
||||
it.effect("classifies context overflow responses", () =>
|
||||
Effect.gen(function* () {
|
||||
const executor = yield* RequestExecutor.Service
|
||||
const error = yield* executor.execute(request).pipe(Effect.flip)
|
||||
|
||||
expectAIError(error)
|
||||
expectLLMError(error)
|
||||
expect(error.reason).toMatchObject({ _tag: "InvalidRequest", classification: "context-overflow" })
|
||||
}).pipe(
|
||||
Effect.provide(
|
||||
@@ -98,17 +85,14 @@ describe("RequestExecutor", () => {
|
||||
),
|
||||
)
|
||||
|
||||
it.effect("classifies generic HTTP 413 payload errors", () =>
|
||||
it.effect("does not classify generic HTTP 413 payload errors as context overflow", () =>
|
||||
Effect.gen(function* () {
|
||||
const executor = yield* RequestExecutor.Service
|
||||
const error = yield* executor.execute(request).pipe(Effect.flip)
|
||||
|
||||
expectAIError(error)
|
||||
expect(error.reason).toMatchObject({
|
||||
_tag: "InvalidRequest",
|
||||
classification: "payload-too-large",
|
||||
http: { response: { status: 413 } },
|
||||
})
|
||||
expectLLMError(error)
|
||||
expect(error.reason).toMatchObject({ _tag: "InvalidRequest" })
|
||||
expect("classification" in error.reason ? error.reason.classification : undefined).toBeUndefined()
|
||||
}).pipe(Effect.provide(responsesLayer([new Response("request too large", { status: 413 })]))),
|
||||
)
|
||||
|
||||
@@ -117,7 +101,7 @@ describe("RequestExecutor", () => {
|
||||
const executor = yield* RequestExecutor.Service
|
||||
const error = yield* executor.execute(request).pipe(Effect.flip)
|
||||
|
||||
expectAIError(error)
|
||||
expectLLMError(error)
|
||||
expect(error.reason).toMatchObject({ _tag: "InvalidRequest" })
|
||||
expect("classification" in error.reason ? error.reason.classification : undefined).toBeUndefined()
|
||||
}).pipe(Effect.provide(responsesLayer([new Response("invalid parameter", { status: 400 })]))),
|
||||
@@ -130,7 +114,7 @@ describe("RequestExecutor", () => {
|
||||
const executor = yield* RequestExecutor.Service
|
||||
const error = yield* executor.execute(request).pipe(Effect.flip)
|
||||
|
||||
expectAIError(error)
|
||||
expectLLMError(error)
|
||||
expect(error.reason).toMatchObject({ _tag: "RateLimit" })
|
||||
}).pipe(Effect.provide(responsesLayer([new Response(body, { status: 400 })])))
|
||||
|
||||
@@ -147,7 +131,7 @@ describe("RequestExecutor", () => {
|
||||
const executor = yield* RequestExecutor.Service
|
||||
const error = yield* executor.execute(request).pipe(Effect.flip)
|
||||
|
||||
expectAIError(error)
|
||||
expectLLMError(error)
|
||||
expect(error.reason).toMatchObject({ _tag: "ProviderInternal" })
|
||||
}).pipe(Effect.provide(responsesLayer([new Response(body, { status: 400 })])))
|
||||
|
||||
@@ -161,7 +145,7 @@ describe("RequestExecutor", () => {
|
||||
const executor = yield* RequestExecutor.Service
|
||||
const error = yield* executor.execute(request).pipe(Effect.flip)
|
||||
|
||||
expectAIError(error)
|
||||
expectLLMError(error)
|
||||
expect(error).toMatchObject({
|
||||
reason: {
|
||||
_tag: "RateLimit",
|
||||
@@ -203,7 +187,7 @@ describe("RequestExecutor", () => {
|
||||
const executor = yield* RequestExecutor.Service
|
||||
const error = yield* executor.execute(request).pipe(Effect.flip)
|
||||
|
||||
expectAIError(error)
|
||||
expectLLMError(error)
|
||||
expect(errorHttp(error)?.request.headers["x-safe"]).toBe("<redacted>")
|
||||
expect(errorHttp(error)?.response?.headers["x-safe"]).toBe("<redacted>")
|
||||
}).pipe(
|
||||
@@ -217,7 +201,7 @@ describe("RequestExecutor", () => {
|
||||
const executor = yield* RequestExecutor.Service
|
||||
const error = yield* executor.execute(request).pipe(Effect.flip)
|
||||
|
||||
expectAIError(error)
|
||||
expectLLMError(error)
|
||||
expect(error.reason).toMatchObject({ _tag: "RateLimit" })
|
||||
expect(error.reason._tag === "RateLimit" ? error.reason.rateLimit : undefined).toEqual({
|
||||
retryAfterMs: 0,
|
||||
@@ -250,7 +234,7 @@ describe("RequestExecutor", () => {
|
||||
const executor = yield* RequestExecutor.Service
|
||||
const error = yield* executor.execute(request).pipe(Effect.flip)
|
||||
|
||||
expectAIError(error)
|
||||
expectLLMError(error)
|
||||
expect(error.reason).toMatchObject({ _tag: "ProviderInternal" })
|
||||
expect(errorHttp(error)?.rateLimit).toEqual({
|
||||
retryAfterMs: 0,
|
||||
@@ -293,7 +277,7 @@ describe("RequestExecutor", () => {
|
||||
),
|
||||
)
|
||||
|
||||
expectAIError(error)
|
||||
expectLLMError(error)
|
||||
expect(error.reason).toMatchObject({ _tag: "ProviderInternal", status: 503 })
|
||||
expect(yield* Ref.get(attempts)).toBe(1)
|
||||
}),
|
||||
@@ -306,7 +290,7 @@ describe("RequestExecutor", () => {
|
||||
const executor = yield* RequestExecutor.Service
|
||||
const error = yield* executor.execute(request).pipe(Effect.flip)
|
||||
|
||||
expectAIError(error)
|
||||
expectLLMError(error)
|
||||
expect(error.reason).toMatchObject({ _tag: "ProviderInternal", status })
|
||||
}).pipe(
|
||||
Effect.provide(
|
||||
@@ -329,7 +313,7 @@ describe("RequestExecutor", () => {
|
||||
const executor = yield* RequestExecutor.Service
|
||||
const error = yield* executor.execute(request).pipe(Effect.flip)
|
||||
|
||||
expectAIError(error)
|
||||
expectLLMError(error)
|
||||
expect(error.reason).toMatchObject({ _tag: "Authentication" })
|
||||
expect(errorHttp(error)?.bodyTruncated).toBe(true)
|
||||
expect(errorHttp(error)?.body).toHaveLength(16_384)
|
||||
@@ -348,7 +332,7 @@ describe("RequestExecutor", () => {
|
||||
const executor = yield* RequestExecutor.Service
|
||||
const error = yield* executor.execute(request).pipe(Effect.flip)
|
||||
|
||||
expectAIError(error)
|
||||
expectLLMError(error)
|
||||
expect(errorHttp(error)?.body).toContain('"key":"<redacted>"')
|
||||
expect(errorHttp(error)?.body).toContain("api_key=<redacted>")
|
||||
expect(errorHttp(error)?.body).not.toContain("body-secret")
|
||||
@@ -369,7 +353,7 @@ describe("RequestExecutor", () => {
|
||||
const executor = yield* RequestExecutor.Service
|
||||
const error = yield* executor.execute(secretRequest).pipe(Effect.flip)
|
||||
|
||||
expectAIError(error)
|
||||
expectLLMError(error)
|
||||
expect(errorHttp(error)?.body).toContain("provider echoed <redacted>")
|
||||
expect(errorHttp(error)?.body).toContain("authorization <redacted>")
|
||||
expect(errorHttp(error)?.body).not.toContain("query-secret-123")
|
||||
@@ -408,131 +392,9 @@ describe("RequestExecutor", () => {
|
||||
Effect.flip,
|
||||
)
|
||||
|
||||
expectAIError(error)
|
||||
expectLLMError(error)
|
||||
expect(error.reason).toMatchObject({ _tag: "InvalidProviderOutput" })
|
||||
expect(yield* Ref.get(attempts)).toBe(1)
|
||||
}),
|
||||
)
|
||||
})
|
||||
|
||||
describe("WebSocket channel execution", () => {
|
||||
const model = OpenAI.configure({ baseURL: "https://api.openai.test/v1/", apiKey: "test" }).responses("gpt-4.1-mini")
|
||||
const request = LLM.request({ model, prompt: "Say hello." })
|
||||
const frames = [
|
||||
JSON.stringify({ type: "response.output_text.delta", item_id: "msg_1", delta: "Hi" }),
|
||||
JSON.stringify({ type: "response.completed", response: { id: "resp_1" } }),
|
||||
]
|
||||
|
||||
it.effect("runs a channel driver through the direct executor", () =>
|
||||
Effect.gen(function* () {
|
||||
const sent = yield* Ref.make("")
|
||||
const closed = yield* Ref.make(false)
|
||||
const observed = yield* Ref.make(0)
|
||||
const webSocket = WebSocketTransport.makeDirect({
|
||||
open: () =>
|
||||
Effect.succeed({
|
||||
sendText: (message) => Ref.set(sent, message),
|
||||
messages: Stream.make("one", "done", "late"),
|
||||
close: Ref.set(closed, true),
|
||||
}),
|
||||
})
|
||||
const received = yield* Effect.scoped(
|
||||
Effect.gen(function* () {
|
||||
const execution = yield* webSocket.execute({
|
||||
id: "exchange_1",
|
||||
connect: { url: "wss://api.openai.test/v1/responses", headers: Headers.empty },
|
||||
fallback: () => Stream.empty,
|
||||
driver: {
|
||||
create: () => Effect.succeed({ message: "create", mode: "full" }),
|
||||
observe: (_create, frame) =>
|
||||
Ref.update(observed, (value) => value + 1).pipe(
|
||||
Effect.as(
|
||||
frame === "done" ? { type: "completed" as const, frame } : { type: "frame" as const, frame },
|
||||
),
|
||||
),
|
||||
},
|
||||
})
|
||||
return yield* Stream.runCollect(execution.frames)
|
||||
}),
|
||||
)
|
||||
|
||||
expect(Array.from(received)).toEqual(["one", "done"])
|
||||
expect(yield* Ref.get(sent)).toBe("create")
|
||||
expect(yield* Ref.get(observed)).toBe(2)
|
||||
expect(yield* Ref.get(closed)).toBe(true)
|
||||
}),
|
||||
)
|
||||
|
||||
it.effect("requires a per-call WebSocket executor", () =>
|
||||
Effect.gen(function* () {
|
||||
const error = yield* LLMClient.generate(request).pipe(Effect.provide(fixedResponse("")), Effect.flip)
|
||||
|
||||
expect(error.reason).toMatchObject({
|
||||
_tag: "Transport",
|
||||
phase: "prepare",
|
||||
delivery: "not-sent",
|
||||
})
|
||||
expect(error.message).toContain("StreamOptions.webSocket")
|
||||
}),
|
||||
)
|
||||
|
||||
it.effect("commits channel execution only after complete consumption", () =>
|
||||
Effect.gen(function* () {
|
||||
const commits = yield* Ref.make(0)
|
||||
const executor = (input: Stream.Stream<string, AIError>): WebSocketChannelExecutor => ({
|
||||
execute: () =>
|
||||
Effect.succeed({
|
||||
frames: input,
|
||||
complete: Ref.update(commits, (value) => value + 1),
|
||||
}),
|
||||
})
|
||||
|
||||
const response = yield* LLMClient.generate(request, {
|
||||
webSocket: executor(Stream.fromArray(frames)),
|
||||
}).pipe(Effect.provide(fixedResponse("")))
|
||||
expect(response.text).toBe("Hi")
|
||||
expect(yield* Ref.get(commits)).toBe(1)
|
||||
|
||||
yield* LLMClient.generate(request, { webSocket: executor(Stream.make("not-json")) }).pipe(
|
||||
Effect.provide(fixedResponse("")),
|
||||
Effect.flip,
|
||||
)
|
||||
expect(yield* Ref.get(commits)).toBe(1)
|
||||
|
||||
yield* LLMClient.stream(request, { webSocket: executor(Stream.fromArray(frames)) }).pipe(
|
||||
Stream.take(1),
|
||||
Stream.runDrain,
|
||||
Effect.provide(fixedResponse("")),
|
||||
)
|
||||
expect(yield* Ref.get(commits)).toBe(1)
|
||||
}),
|
||||
)
|
||||
|
||||
it.effect("does not commit interrupted channel execution", () =>
|
||||
Effect.gen(function* () {
|
||||
const commits = yield* Ref.make(0)
|
||||
const started = yield* Deferred.make<void>()
|
||||
const executor: WebSocketChannelExecutor = {
|
||||
execute: () =>
|
||||
Effect.succeed({
|
||||
frames: Stream.fromEffect(
|
||||
Deferred.succeed(started, undefined).pipe(
|
||||
Effect.as(JSON.stringify({ type: "response.created", response: { id: "resp_1" } })),
|
||||
),
|
||||
).pipe(Stream.concat(Stream.never)),
|
||||
complete: Ref.update(commits, (value) => value + 1),
|
||||
}),
|
||||
}
|
||||
const fiber = yield* LLMClient.stream(request, { webSocket: executor }).pipe(
|
||||
Stream.runDrain,
|
||||
Effect.provide(fixedResponse("")),
|
||||
Effect.forkChild({ startImmediately: true }),
|
||||
)
|
||||
|
||||
yield* Deferred.await(started)
|
||||
yield* Fiber.interrupt(fiber)
|
||||
|
||||
expect(yield* Ref.get(commits)).toBe(0)
|
||||
}),
|
||||
)
|
||||
})
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
import { describe, expect, test } from "bun:test"
|
||||
import { AIError, ImageInput, LanguageModel, LLM, LLMClient, Provider } from "@opencode-ai/ai"
|
||||
import { Route, Protocol, WebSocketTransport } from "@opencode-ai/ai/route"
|
||||
import { ImageInput, LLM, LLMClient, Provider } from "@opencode-ai/ai"
|
||||
import { Route, Protocol } from "@opencode-ai/ai/route"
|
||||
import { Provider as ProviderSubpath } from "@opencode-ai/ai/provider"
|
||||
import {
|
||||
CloudflareAIGateway,
|
||||
@@ -26,8 +26,6 @@ describe("public exports", () => {
|
||||
expect(LLM.request).toBeFunction()
|
||||
expect(LLMClient.Service).toBeFunction()
|
||||
expect(LLMClient.layer).toBeDefined()
|
||||
expect(AIError).toBeFunction()
|
||||
expect(LanguageModel.make).toBeFunction()
|
||||
expect(ImageInput.bytes).toBeFunction()
|
||||
expect(Provider.make).toBeFunction()
|
||||
expect(ProviderSubpath.make).toBe(Provider.make)
|
||||
@@ -37,7 +35,6 @@ describe("public exports", () => {
|
||||
test("route barrel exposes route-authoring APIs", () => {
|
||||
expect(Route.make).toBeFunction()
|
||||
expect(Protocol.make).toBeFunction()
|
||||
expect(WebSocketTransport.makeDirect).toBeFunction()
|
||||
})
|
||||
|
||||
test("provider barrels expose user-facing facades", async () => {
|
||||
@@ -45,6 +42,7 @@ describe("public exports", () => {
|
||||
|
||||
expect(OpenAI.model).toBeFunction()
|
||||
expect(OpenAI.provider.responses).toBe(OpenAI.responses)
|
||||
expect(OpenAI.provider.responsesWebSocket).toBe(OpenAI.responsesWebSocket)
|
||||
expect(OpenAI.configure({ apiKey: "fixture" }).responses).toBeFunction()
|
||||
expect(OpenAICompatible.deepseek.model).toBeFunction()
|
||||
expect(
|
||||
@@ -86,6 +84,7 @@ describe("public exports", () => {
|
||||
expect(OpenAICompatibleResponses.route.id).toBe("openai-compatible-responses")
|
||||
expect(OpenAICompatibleResponses.route.protocol).toBe("open-responses")
|
||||
expect(OpenAIResponses.route.id).toBe("openai-responses")
|
||||
expect(OpenAIResponses.webSocketRoute.id).toBe("openai-responses-websocket")
|
||||
expect(AnthropicMessages.route.id).toBe("anthropic-messages")
|
||||
})
|
||||
})
|
||||
|
||||
File diff suppressed because one or more lines are too long
@@ -1,7 +1,5 @@
|
||||
import { Effect } from "effect"
|
||||
import {
|
||||
Image,
|
||||
ImageClient,
|
||||
ImageInput,
|
||||
ImageModel,
|
||||
type ImageModelOptions,
|
||||
@@ -9,13 +7,8 @@ import {
|
||||
type ImageRequestFor,
|
||||
type ImageRoute,
|
||||
} from "../src"
|
||||
import type { Service } from "../src/image-client"
|
||||
import { Google, OpenAI, XAI, ZAI } from "../src/providers"
|
||||
|
||||
type Requirements<T> = T extends Effect.Effect<infer _A, infer _E, infer R> ? R : never
|
||||
type Equal<A, B> = [A, B] extends [B, A] ? true : false
|
||||
type Assert<T extends true> = T
|
||||
|
||||
type GoogleLikeOptions = {
|
||||
readonly aspectRatio?: "1:1" | "16:9"
|
||||
readonly imageSize?: "1K" | "2K"
|
||||
@@ -153,9 +146,6 @@ const request = Image.request({
|
||||
})
|
||||
const typedRequest: ImageRequestFor<GoogleLikeOptions> = request
|
||||
void typedRequest
|
||||
const generated = ImageClient.generate(request)
|
||||
type GenerateRequirements = Assert<Equal<Requirements<typeof generated>, Service>>
|
||||
void (true satisfies GenerateRequirements)
|
||||
|
||||
// @ts-expect-error Image requests no longer expose a common count option.
|
||||
Image.generate({ model: openai, prompt: "A lighthouse", count: 2 })
|
||||
|
||||
@@ -1,8 +1,9 @@
|
||||
import { Effect, Layer, Ref } from "effect"
|
||||
import { HttpClient, HttpClientRequest, HttpClientResponse } from "effect/unstable/http"
|
||||
import { LLMClient, RequestExecutor } from "../../src/route"
|
||||
import { LLMClient, RequestExecutor, WebSocketExecutor } from "../../src/route"
|
||||
import type { Service as LLMClientService } from "../../src/route/client"
|
||||
import type { Service as RequestExecutorService } from "../../src/route/executor"
|
||||
import type { Service as WebSocketExecutorService } from "../../src/route/transport/websocket"
|
||||
|
||||
export type HandlerInput = {
|
||||
readonly request: HttpClientRequest.HttpClientRequest
|
||||
@@ -31,12 +32,13 @@ const handlerLayer = (handler: Handler): Layer.Layer<HttpClient.HttpClient> =>
|
||||
),
|
||||
)
|
||||
|
||||
export type RuntimeEnv = RequestExecutorService | LLMClientService
|
||||
export type RuntimeEnv = RequestExecutorService | WebSocketExecutorService | LLMClientService
|
||||
|
||||
export const runtimeLayer = (layer: Layer.Layer<HttpClient.HttpClient>): Layer.Layer<RuntimeEnv> => {
|
||||
const requestExecutorLayer = RequestExecutor.layer.pipe(Layer.provide(layer))
|
||||
const llmClientLayer = LLMClient.layer.pipe(Layer.provide(requestExecutorLayer))
|
||||
return Layer.mergeAll(requestExecutorLayer, llmClientLayer)
|
||||
const deps = Layer.mergeAll(requestExecutorLayer, WebSocketExecutor.layer)
|
||||
const llmClientLayer = LLMClient.layer.pipe(Layer.provide(deps))
|
||||
return Layer.mergeAll(deps, llmClientLayer)
|
||||
}
|
||||
|
||||
const SSE_HEADERS = { "content-type": "text/event-stream" } as const
|
||||
|
||||
@@ -1,11 +1,5 @@
|
||||
import { Effect, Schema, Stream } from "effect"
|
||||
import {
|
||||
LLM,
|
||||
type LLMClientService,
|
||||
type LanguageModel,
|
||||
type LanguageModelProviderOptions,
|
||||
type ProviderOptions,
|
||||
} from "../src"
|
||||
import { Schema } from "effect"
|
||||
import { LLM, type Model, type ModelProviderOptions, type ProviderOptions } from "../src"
|
||||
import { OpenAIChat } from "../src/protocols"
|
||||
|
||||
interface ExampleOptions {
|
||||
@@ -21,19 +15,9 @@ const model = OpenAIChat.route
|
||||
.with({ endpoint: { baseURL: "https://example.com/v1" } })
|
||||
.model<ExampleProviderOptions>({ id: "example" })
|
||||
|
||||
type Requirements<T> = T extends Effect.Effect<infer _A, infer _E, infer R> ? R : never
|
||||
type StreamRequirements<T> = T extends Stream.Stream<infer _A, infer _E, infer R> ? R : never
|
||||
type Equal<A, B> = [A, B] extends [B, A] ? true : false
|
||||
type Assert<T extends true> = T
|
||||
|
||||
LLM.request({ model, prompt: "Hello", providerOptions: { example: { mode: "fast" } } })
|
||||
LLM.request({ model, prompt: "Hello", providerOptions: { future: { option: true } } })
|
||||
|
||||
const generated = LLM.generate(LLM.request({ model, prompt: "Hello" }))
|
||||
type GenerateRequirements = Assert<Equal<Requirements<typeof generated>, LLMClientService>>
|
||||
const streamed = LLM.stream(LLM.request({ model, prompt: "Hello" }))
|
||||
type StreamClientRequirements = Assert<Equal<StreamRequirements<typeof streamed>, LLMClientService>>
|
||||
|
||||
LLM.request({
|
||||
model,
|
||||
prompt: "Hello",
|
||||
@@ -41,20 +25,12 @@ LLM.request({
|
||||
providerOptions: { example: { mode: "slow" } },
|
||||
})
|
||||
|
||||
const generatedObject = LLM.generateObject({
|
||||
LLM.generateObject({
|
||||
model,
|
||||
prompt: "Hello",
|
||||
schema: Schema.Struct({ answer: Schema.String }),
|
||||
providerOptions: { example: { mode: "thorough" } },
|
||||
})
|
||||
type GenerateObjectRequirements = Assert<Equal<Requirements<typeof generatedObject>, LLMClientService>>
|
||||
|
||||
const generatedDynamicObject = LLM.generateObject({
|
||||
model,
|
||||
prompt: "Hello",
|
||||
jsonSchema: { type: "object" },
|
||||
})
|
||||
type GenerateDynamicObjectRequirements = Assert<Equal<Requirements<typeof generatedDynamicObject>, LLMClientService>>
|
||||
|
||||
LLM.generateObject({
|
||||
model,
|
||||
@@ -64,12 +40,8 @@ LLM.generateObject({
|
||||
providerOptions: { example: { mode: false } },
|
||||
})
|
||||
|
||||
declare const generic: LanguageModel
|
||||
declare const generic: Model
|
||||
LLM.request({ model: generic, prompt: "Hello", providerOptions: { arbitrary: { option: true } } })
|
||||
|
||||
const options: LanguageModelProviderOptions<typeof model> = { example: { mode: "fast" } }
|
||||
void (options satisfies LanguageModelProviderOptions<typeof model>)
|
||||
void (true satisfies GenerateRequirements)
|
||||
void (true satisfies StreamClientRequirements)
|
||||
void (true satisfies GenerateObjectRequirements)
|
||||
void (true satisfies GenerateDynamicObjectRequirements)
|
||||
const options: ModelProviderOptions<typeof model> = { example: { mode: "fast" } }
|
||||
void options
|
||||
|
||||
@@ -6,7 +6,7 @@ import {
|
||||
GenerationOptions,
|
||||
LLMRequest,
|
||||
Message,
|
||||
LanguageModel,
|
||||
Model,
|
||||
ToolCallPart,
|
||||
ToolChoice,
|
||||
ToolDefinition,
|
||||
@@ -20,13 +20,13 @@ describe("llm constructors", () => {
|
||||
test("builds canonical schema classes from ergonomic input", () => {
|
||||
const request = LLM.request({
|
||||
id: "req_1",
|
||||
model: LanguageModel.make({ id: "fake-model", provider: "fake", route: chatRoute }),
|
||||
model: Model.make({ id: "fake-model", provider: "fake", route: chatRoute }),
|
||||
system: "You are concise.",
|
||||
prompt: "Say hello.",
|
||||
})
|
||||
|
||||
expect(request).toBeInstanceOf(LLMRequest)
|
||||
expect(request.model).toBeInstanceOf(LanguageModel)
|
||||
expect(request.model).toBeInstanceOf(Model)
|
||||
expect(request.messages[0]).toBeInstanceOf(Message)
|
||||
expect(request.system).toEqual([{ type: "text", text: "You are concise." }])
|
||||
expect(request.messages[0]?.content).toEqual([{ type: "text", text: "Say hello." }])
|
||||
@@ -37,7 +37,7 @@ describe("llm constructors", () => {
|
||||
test("updates requests without spreading schema class instances", () => {
|
||||
const base = LLM.request({
|
||||
id: "req_1",
|
||||
model: LanguageModel.make({ id: "fake-model", provider: "fake", route: chatRoute }),
|
||||
model: Model.make({ id: "fake-model", provider: "fake", route: chatRoute }),
|
||||
prompt: "Say hello.",
|
||||
})
|
||||
const updated = LLMRequest.update(base, {
|
||||
@@ -54,7 +54,7 @@ describe("llm constructors", () => {
|
||||
|
||||
test("keeps request options separate from route defaults", () => {
|
||||
const request = LLM.request({
|
||||
model: LanguageModel.make({
|
||||
model: Model.make({
|
||||
id: "fake-model",
|
||||
provider: "fake",
|
||||
route: chatRoute.with({
|
||||
@@ -81,7 +81,7 @@ describe("llm constructors", () => {
|
||||
test("updates canonical requests from the request datatype", () => {
|
||||
const base = LLM.request({
|
||||
id: "req_1",
|
||||
model: LanguageModel.make({ id: "fake-model", provider: "fake", route: chatRoute }),
|
||||
model: Model.make({ id: "fake-model", provider: "fake", route: chatRoute }),
|
||||
prompt: "Say hello.",
|
||||
})
|
||||
const updated = LLMRequest.update(base, { messages: [...base.messages, Message.assistant("Hi.")] })
|
||||
@@ -94,19 +94,19 @@ describe("llm constructors", () => {
|
||||
})
|
||||
|
||||
test("updates canonical models from the model datatype", () => {
|
||||
const base = LanguageModel.make({
|
||||
const base = Model.make({
|
||||
id: "fake-model",
|
||||
provider: "fake",
|
||||
route: chatRoute,
|
||||
})
|
||||
const updated = LanguageModel.update(base, {
|
||||
const updated = Model.update(base, {
|
||||
route: responsesRoute,
|
||||
defaults: { generation: { maxTokens: 20 } },
|
||||
compatibility: { toolSchema: "gemini" },
|
||||
})
|
||||
const updatedInput = LanguageModel.input(updated)
|
||||
const updatedInput = Model.input(updated)
|
||||
|
||||
expect(updated).toBeInstanceOf(LanguageModel)
|
||||
expect(updated).toBeInstanceOf(Model)
|
||||
expect(String(updated.id)).toBe("fake-model")
|
||||
expect(updated.route).toBe(responsesRoute)
|
||||
expect(updated.defaults?.generation).toEqual({ maxTokens: 20 })
|
||||
@@ -114,7 +114,7 @@ describe("llm constructors", () => {
|
||||
expect(updatedInput.defaults).toBe(updated.defaults)
|
||||
expect(updatedInput.compatibility).toBe(updated.compatibility)
|
||||
expect(String(updatedInput.provider)).toBe("fake")
|
||||
expect(LanguageModel.update(updated, {})).toBe(updated)
|
||||
expect(Model.update(updated, {})).toBe(updated)
|
||||
})
|
||||
|
||||
test("carries model defaults and compatibility through route model selection", () => {
|
||||
@@ -155,7 +155,7 @@ describe("llm constructors", () => {
|
||||
expect(ToolChoice.make("required")).toEqual(new ToolChoice({ type: "required" }))
|
||||
expect(
|
||||
LLM.request({
|
||||
model: LanguageModel.make({
|
||||
model: Model.make({
|
||||
id: "fake-model",
|
||||
provider: "fake",
|
||||
route: chatRoute,
|
||||
@@ -181,7 +181,7 @@ describe("llm constructors", () => {
|
||||
{ type: "text", text: "Use parameterized SQL.", cache: new CacheHint({ type: "ephemeral" }) },
|
||||
])
|
||||
const request = LLM.request({
|
||||
model: LanguageModel.make({ id: "fake-model", provider: "fake", route: chatRoute }),
|
||||
model: Model.make({ id: "fake-model", provider: "fake", route: chatRoute }),
|
||||
system: "Initial operator prompt.",
|
||||
messages: [Message.user("Review this."), update],
|
||||
})
|
||||
|
||||
@@ -6,6 +6,7 @@ describe("provider error classification", () => {
|
||||
test("classifies provider token limit messages as context overflow", () => {
|
||||
const messages = [
|
||||
"tokens in request more than max tokens allowed",
|
||||
'{"error":{"type":"request_too_large","message":"Request exceeds the maximum size"}}',
|
||||
"Requested token count exceeds the model's maximum context length of 131072 tokens.",
|
||||
"Input length (265330) exceeds model's maximum context length (262144).",
|
||||
"Input length 131393 exceeds the maximum allowed input length of 131040 tokens.",
|
||||
@@ -18,24 +19,6 @@ describe("provider error classification", () => {
|
||||
expect(messages.every(isContextOverflow)).toBe(true)
|
||||
})
|
||||
|
||||
test("classifies request size failures separately from context overflow", () => {
|
||||
const failures = [
|
||||
classifyProviderFailure({ message: "request too large", status: 413 }),
|
||||
classifyProviderFailure({
|
||||
message: '{"error":{"type":"request_too_large","message":"Request exceeds the maximum size"}}',
|
||||
status: 400,
|
||||
}),
|
||||
classifyProviderFailure({ message: "upstream request entity too large", status: 502 }),
|
||||
]
|
||||
|
||||
expect(failures).toEqual(
|
||||
failures.map((failure) =>
|
||||
expect.objectContaining({ _tag: "InvalidRequest", classification: "payload-too-large" }),
|
||||
),
|
||||
)
|
||||
expect(isContextOverflow("413 status code (no body)")).toBe(false)
|
||||
})
|
||||
|
||||
test("does not classify rate limits as context overflow", () => {
|
||||
const messages = [
|
||||
"Throttling error: Too many tokens, please wait before trying again.",
|
||||
@@ -69,17 +52,16 @@ describe("provider error classification", () => {
|
||||
|
||||
test("classifies V1 overloaded provider codes", () => {
|
||||
expect(
|
||||
['{"code":"resource_exhausted"}', '{"code":"service_unavailable"}', '{"code":"slow_down"}'].map(
|
||||
['{"code":"resource_exhausted"}', '{"code":"service_unavailable"}'].map(
|
||||
(message) => classifyProviderFailure({ message })._tag,
|
||||
),
|
||||
).toEqual(["ProviderInternal", "ProviderInternal", "ProviderInternal"])
|
||||
).toEqual(["ProviderInternal", "ProviderInternal"])
|
||||
})
|
||||
|
||||
test("classifies transient client statuses as provider internal", () => {
|
||||
expect([408, 409].map((status) => classifyProviderFailure({ message: `HTTP ${status}`, status })._tag)).toEqual([
|
||||
"ProviderInternal",
|
||||
"ProviderInternal",
|
||||
])
|
||||
expect(
|
||||
[408, 409].map((status) => classifyProviderFailure({ message: `HTTP ${status}`, status })._tag),
|
||||
).toEqual(["ProviderInternal", "ProviderInternal"])
|
||||
})
|
||||
|
||||
test("classifies nested provider codes when a top-level code is also present", () => {
|
||||
|
||||
@@ -1,18 +1,13 @@
|
||||
import { LLM } from "../../src"
|
||||
import { OpenAI } from "../../src/providers"
|
||||
|
||||
const selected = OpenAI.responses("gpt-5")
|
||||
const model = OpenAI.responses("gpt-5")
|
||||
|
||||
LLM.request({ model: selected, prompt: "Hello", providerOptions: { openai: { reasoningEffort: "high" } } })
|
||||
LLM.request({ model, prompt: "Hello", providerOptions: { openai: { reasoningEffort: "high" } } })
|
||||
|
||||
LLM.request({
|
||||
model: selected,
|
||||
model,
|
||||
prompt: "Hello",
|
||||
// @ts-expect-error OpenAI reasoning effort must be a string.
|
||||
providerOptions: { openai: { reasoningEffort: 1 } },
|
||||
})
|
||||
|
||||
OpenAI.configure({
|
||||
// @ts-expect-error Transport is execution policy, not provider configuration.
|
||||
transport: "websocket",
|
||||
})
|
||||
|
||||
@@ -5,28 +5,6 @@ const model = OpenRouter.provider.model("anthropic/claude-sonnet-4.5")
|
||||
|
||||
LLM.request({ model, prompt: "Hello", providerOptions: { openrouter: { usage: true } } })
|
||||
|
||||
LLM.request({
|
||||
model,
|
||||
prompt: "Hello",
|
||||
providerOptions: {
|
||||
openrouter: {
|
||||
models: ["google/gemini-3.1-pro"],
|
||||
provider: {
|
||||
order: ["anthropic"],
|
||||
require_parameters: true,
|
||||
data_collection: "future-policy",
|
||||
sort: "future-sort",
|
||||
max_price: { prompt: "0.50" },
|
||||
},
|
||||
reasoning: { effort: "future-effort", exclude: false },
|
||||
plugins: [{ id: "future-plugin", enabled: true }],
|
||||
web_search_options: { engine: "future-engine" },
|
||||
debug: { echo_upstream_body: true },
|
||||
user: "user_123",
|
||||
},
|
||||
},
|
||||
})
|
||||
|
||||
LLM.request({
|
||||
model,
|
||||
prompt: "Hello",
|
||||
|
||||
@@ -23,16 +23,12 @@ describe("provider package entrypoints", () => {
|
||||
import("@opencode-ai/ai/providers/google-vertex/messages"),
|
||||
import("@opencode-ai/ai/providers/openrouter"),
|
||||
import("@opencode-ai/ai/providers/xai"),
|
||||
import("@opencode-ai/ai/providers/amazon-bedrock/mantle"),
|
||||
import("@opencode-ai/ai/providers/amazon-bedrock/mantle/chat"),
|
||||
import("@opencode-ai/ai/providers/amazon-bedrock/mantle/responses"),
|
||||
])
|
||||
|
||||
for (const module of modules) expect(module.model).toBeFunction()
|
||||
expect(modules[0].model).toBe(modules[1].model)
|
||||
expect(modules[8].model).toBe(modules[9].model)
|
||||
expect(modules[12].model).toBe(modules[13].model)
|
||||
expect(modules[19].model).toBe(modules[20].model)
|
||||
})
|
||||
|
||||
test("maps OpenRouter and xAI package settings onto executable models", async () => {
|
||||
@@ -80,6 +76,11 @@ describe("provider package entrypoints", () => {
|
||||
expect(selected.route.defaults.limits).toEqual({ context: 200_000, output: 64_000 })
|
||||
})
|
||||
|
||||
test("selects transport without changing the semantic API", () => {
|
||||
expect(model("gpt-5", { apiKey: "fixture" }).route.id).toBe("openai-responses")
|
||||
expect(model("gpt-5", { apiKey: "fixture", transport: "websocket" }).route.id).toBe("openai-responses-websocket")
|
||||
})
|
||||
|
||||
test("maps OpenAI-compatible Responses settings onto the executable model", async () => {
|
||||
const OpenAICompatibleResponses = await import("@opencode-ai/ai/providers/openai-compatible/responses")
|
||||
const selected = OpenAICompatibleResponses.model("custom-model", {
|
||||
|
||||
@@ -1,9 +1,9 @@
|
||||
import { Provider } from "../src/provider"
|
||||
import { ProviderID, type LanguageModel } from "../src/schema"
|
||||
import { ProviderID, type Model } from "../src/schema"
|
||||
|
||||
declare const model: (id: string) => LanguageModel
|
||||
declare const requiredModel: (id: string, options: { readonly baseURL: string }) => LanguageModel
|
||||
declare const chat: (id: string, options: { readonly apiKey: string }) => LanguageModel
|
||||
declare const model: (id: string) => Model
|
||||
declare const requiredModel: (id: string, options: { readonly baseURL: string }) => Model
|
||||
declare const chat: (id: string, options: { readonly apiKey: string }) => Model
|
||||
|
||||
Provider.make({
|
||||
id: ProviderID.make("example"),
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
import { describe, expect } from "bun:test"
|
||||
import { Effect } from "effect"
|
||||
import { LLM, AIError, Message, ToolCallPart } from "../../src"
|
||||
import { LLM, LLMError, Message, ToolCallPart } from "../../src"
|
||||
import { LLMClient } from "../../src/route"
|
||||
import * as Anthropic from "../../src/providers/anthropic"
|
||||
import { weatherToolName } from "../recorded-scenarios"
|
||||
@@ -37,7 +37,7 @@ describe("Anthropic Messages sad-path recorded", () => {
|
||||
Effect.gen(function* () {
|
||||
const error = yield* LLMClient.generate(malformedToolOrderRequest).pipe(Effect.flip)
|
||||
|
||||
expect(error).toBeInstanceOf(AIError)
|
||||
expect(error).toBeInstanceOf(LLMError)
|
||||
expect(error.reason).toMatchObject({ _tag: "InvalidRequest" })
|
||||
expect(error.message).toContain("HTTP 400")
|
||||
}),
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
import { describe, expect } from "bun:test"
|
||||
import { Effect } from "effect"
|
||||
import { HttpClientRequest } from "effect/unstable/http"
|
||||
import { CacheHint, LLM, AIError, LLMRequest, Message, ToolCallPart, ToolDefinition, Usage } from "../../src"
|
||||
import { CacheHint, LLM, LLMError, LLMRequest, Message, ToolCallPart, ToolDefinition, Usage } from "../../src"
|
||||
import { Auth, LLMClient } from "../../src/route"
|
||||
import { compileRequest } from "../../src/route/client"
|
||||
import * as AnthropicMessages from "../../src/protocols/anthropic-messages"
|
||||
@@ -538,8 +538,7 @@ describe("Anthropic Messages route", () => {
|
||||
|
||||
expect(error.reason).toMatchObject({
|
||||
_tag: "InvalidProviderOutput",
|
||||
classification: "incomplete-stream",
|
||||
message: "The provider response ended unexpectedly.",
|
||||
message: "Provider stream ended without a terminal finish event",
|
||||
})
|
||||
}),
|
||||
)
|
||||
@@ -685,7 +684,9 @@ describe("Anthropic Messages route", () => {
|
||||
),
|
||||
)
|
||||
|
||||
expect(response.toolCalls).toMatchObject([{ id: "call_1", name: "lookup", input: { query: "weather" } }])
|
||||
expect(response.toolCalls).toMatchObject([
|
||||
{ id: "call_1", name: "lookup", input: { query: "weather" } },
|
||||
])
|
||||
}),
|
||||
)
|
||||
|
||||
@@ -934,7 +935,7 @@ describe("Anthropic Messages route", () => {
|
||||
|
||||
const error = yield* LLMClient.generate(request).pipe(Effect.provide(fixedResponse(body)), Effect.flip)
|
||||
|
||||
expect(error).toBeInstanceOf(AIError)
|
||||
expect(error).toBeInstanceOf(LLMError)
|
||||
expect(error.message).toContain("Invalid JSON input for anthropic-messages tool call web_search")
|
||||
}),
|
||||
)
|
||||
@@ -1008,7 +1009,7 @@ describe("Anthropic Messages route", () => {
|
||||
Effect.flip,
|
||||
)
|
||||
|
||||
expect(error).toBeInstanceOf(AIError)
|
||||
expect(error).toBeInstanceOf(LLMError)
|
||||
expect(error.reason).toMatchObject({ _tag: "InvalidRequest" })
|
||||
expect(error.message).toContain("HTTP 400")
|
||||
}),
|
||||
|
||||
@@ -1,111 +0,0 @@
|
||||
import { describe, expect } from "bun:test"
|
||||
import { Effect } from "effect"
|
||||
import { HttpClientRequest } from "effect/unstable/http"
|
||||
import { LLM } from "../../src"
|
||||
import { AmazonBedrockMantle } from "../../src/providers"
|
||||
import { compileRequest, LLMClient } from "../../src/route/client"
|
||||
import { it } from "../lib/effect"
|
||||
import { dynamicResponse } from "../lib/http"
|
||||
import { recordedTests } from "../recorded-test"
|
||||
|
||||
const credentials = {
|
||||
region: "us-east-2",
|
||||
accessKeyId: "AKIAIOSFODNN7EXAMPLE",
|
||||
secretAccessKey: "wJalrXUtnFEMI/K7MDENG/bPxRfiCYEXAMPLEKEY",
|
||||
}
|
||||
|
||||
describe("Amazon Bedrock Mantle provider", () => {
|
||||
it.effect("uses Chat by default and exposes Responses", () =>
|
||||
Effect.gen(function* () {
|
||||
const provider = AmazonBedrockMantle.configure({ credentials })
|
||||
const chat = yield* compileRequest(LLM.request({ model: provider.model("openai.gpt-oss-120b"), prompt: "Hi" }))
|
||||
const responses = yield* compileRequest(
|
||||
LLM.request({ model: provider.responses("openai.gpt-oss-120b"), prompt: "Hi" }),
|
||||
)
|
||||
|
||||
expect(chat).toMatchObject({
|
||||
route: "bedrock-mantle-chat",
|
||||
protocol: "openai-chat",
|
||||
body: { model: "openai.gpt-oss-120b" },
|
||||
})
|
||||
expect(responses).toMatchObject({
|
||||
route: "bedrock-mantle-responses",
|
||||
protocol: "openai-responses",
|
||||
body: { model: "openai.gpt-oss-120b", store: false },
|
||||
})
|
||||
}),
|
||||
)
|
||||
|
||||
it.effect("uses the Mantle endpoint and signing service", () =>
|
||||
Effect.gen(function* () {
|
||||
const seen: Array<{ readonly url: string; readonly authorization: string | undefined }> = []
|
||||
const model = AmazonBedrockMantle.configure({ credentials, region: "us-west-1" }).responses("openai.gpt-oss-120b")
|
||||
yield* LLMClient.generate(LLM.request({ model, prompt: "Hi" })).pipe(
|
||||
Effect.provide(
|
||||
dynamicResponse((input) =>
|
||||
Effect.gen(function* () {
|
||||
const request = yield* HttpClientRequest.toWeb(input.request)
|
||||
seen.push({ url: request.url, authorization: request.headers.get("authorization") ?? undefined })
|
||||
return input.respond("", { headers: { "content-type": "text/event-stream" } })
|
||||
}),
|
||||
),
|
||||
),
|
||||
Effect.flip,
|
||||
)
|
||||
|
||||
expect(seen[0]?.url).toBe("https://bedrock-mantle.us-west-1.api.aws/v1/responses")
|
||||
expect(seen[0]?.authorization).toContain("/us-west-1/bedrock-mantle/aws4_request")
|
||||
}),
|
||||
)
|
||||
|
||||
it.effect("supports bearer authentication and custom base URLs", () =>
|
||||
Effect.gen(function* () {
|
||||
const seen: Array<{ readonly url: string; readonly authorization: string | undefined }> = []
|
||||
const model = AmazonBedrockMantle.configure({
|
||||
apiKey: "test-key",
|
||||
baseURL: "https://mantle.test/v1",
|
||||
}).chat("openai.gpt-oss-safeguard-20b")
|
||||
yield* LLMClient.generate(LLM.request({ model, prompt: "Hi" })).pipe(
|
||||
Effect.provide(
|
||||
dynamicResponse((input) =>
|
||||
Effect.gen(function* () {
|
||||
const request = yield* HttpClientRequest.toWeb(input.request)
|
||||
seen.push({ url: request.url, authorization: request.headers.get("authorization") ?? undefined })
|
||||
return input.respond("", { headers: { "content-type": "text/event-stream" } })
|
||||
}),
|
||||
),
|
||||
),
|
||||
Effect.flip,
|
||||
)
|
||||
|
||||
expect(seen).toEqual([{ url: "https://mantle.test/v1/chat/completions", authorization: "Bearer test-key" }])
|
||||
}),
|
||||
)
|
||||
})
|
||||
|
||||
const recorded = recordedTests({
|
||||
prefix: "bedrock-mantle",
|
||||
provider: "amazon-bedrock",
|
||||
protocol: "openai-responses",
|
||||
requires: ["AWS_BEARER_TOKEN_BEDROCK"],
|
||||
metadata: { model: "openai.gpt-oss-120b" },
|
||||
})
|
||||
|
||||
describe("Amazon Bedrock Mantle recorded", () => {
|
||||
recorded.effect("streams text", () =>
|
||||
Effect.gen(function* () {
|
||||
const response = yield* LLMClient.generate(
|
||||
LLM.request({
|
||||
model: AmazonBedrockMantle.configure({
|
||||
apiKey: process.env.AWS_BEARER_TOKEN_BEDROCK ?? "fixture",
|
||||
region: "us-east-1",
|
||||
}).responses("openai.gpt-oss-120b"),
|
||||
prompt: "Reply with exactly: hello",
|
||||
generation: { maxTokens: 256, temperature: 0 },
|
||||
}),
|
||||
)
|
||||
|
||||
expect(response.text.trim().toLowerCase()).toBe("hello")
|
||||
}),
|
||||
)
|
||||
})
|
||||
@@ -1,6 +1,6 @@
|
||||
import { describe, expect } from "bun:test"
|
||||
import { Effect } from "effect"
|
||||
import { LLM, AIError, LLMRequest, Message, ToolCallPart, ToolDefinition, Usage } from "../../src"
|
||||
import { LLM, LLMError, LLMRequest, Message, ToolCallPart, ToolDefinition, Usage } from "../../src"
|
||||
import { Auth, LLMClient } from "../../src/route"
|
||||
import { compileRequest } from "../../src/route/client"
|
||||
import * as Gemini from "../../src/protocols/gemini"
|
||||
@@ -601,34 +601,6 @@ describe("Gemini route", () => {
|
||||
}),
|
||||
)
|
||||
|
||||
it.effect("maps tool calls without a finish reason", () =>
|
||||
Effect.gen(function* () {
|
||||
const response = yield* LLMClient.generate(
|
||||
LLMRequest.update(request, {
|
||||
tools: [ToolDefinition.make({ name: "lookup", description: "Lookup data", inputSchema: { type: "object" } })],
|
||||
}),
|
||||
).pipe(
|
||||
Effect.provide(
|
||||
fixedResponse(
|
||||
sseEvents({
|
||||
candidates: [
|
||||
{
|
||||
content: {
|
||||
role: "model",
|
||||
parts: [{ functionCall: { name: "lookup", args: { query: "weather" } } }],
|
||||
},
|
||||
},
|
||||
],
|
||||
usageMetadata: { promptTokenCount: 5, candidatesTokenCount: 1 },
|
||||
}),
|
||||
),
|
||||
),
|
||||
)
|
||||
|
||||
expect(response.finishReason).toEqual({ normalized: "tool-calls", raw: undefined })
|
||||
}),
|
||||
)
|
||||
|
||||
it.effect("assigns unique ids to multiple streamed tool calls", () =>
|
||||
Effect.gen(function* () {
|
||||
const body = sseEvents({
|
||||
@@ -740,7 +712,7 @@ describe("Gemini route", () => {
|
||||
Effect.flip,
|
||||
)
|
||||
|
||||
expect(error).toBeInstanceOf(AIError)
|
||||
expect(error).toBeInstanceOf(LLMError)
|
||||
expect(error.reason).toMatchObject({ _tag: "InvalidProviderOutput" })
|
||||
expect(error.message).toContain("Invalid google/gemini stream event")
|
||||
}),
|
||||
|
||||
@@ -181,6 +181,23 @@ describe("Google Vertex providers", () => {
|
||||
}),
|
||||
)
|
||||
|
||||
it.effect("protects the Vertex Messages API version from body overlays", () =>
|
||||
Effect.gen(function* () {
|
||||
const error = yield* compileRequest(
|
||||
LLM.request({
|
||||
model: GoogleVertexMessages.configure({
|
||||
accessToken: "vertex-token",
|
||||
http: { body: { anthropic_version: "wrong" } },
|
||||
project: "vertex-project",
|
||||
}).model("claude-sonnet-4-6"),
|
||||
prompt: "Say hello.",
|
||||
}),
|
||||
).pipe(Effect.flip)
|
||||
|
||||
expect(error.message).toContain("http.body cannot overlay protocol-owned field(s): anthropic_version")
|
||||
}),
|
||||
)
|
||||
|
||||
it.effect("routes tuned Gemini models through their deployed endpoint", () =>
|
||||
Effect.gen(function* () {
|
||||
const response = yield* LLMClient.generate(
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
import { describe, expect } from "bun:test"
|
||||
import { Effect } from "effect"
|
||||
import { LLM, LLMEvent, LLMResponse, LanguageModel } from "../../src"
|
||||
import { LLM, LLMEvent, LLMResponse, Model } from "../../src"
|
||||
import { OpenAIChat } from "../../src/protocols/openai-chat"
|
||||
import * as OpenAICompatible from "../../src/providers/openai-compatible"
|
||||
import * as OpenRouter from "../../src/providers/openrouter"
|
||||
@@ -12,7 +12,7 @@ import { expectWeatherToolLoop, goldenWeatherToolLoopRequest, runWeatherToolLoop
|
||||
const cases = [
|
||||
{
|
||||
name: "OpenRouter",
|
||||
model: LanguageModel.update(
|
||||
model: Model.update(
|
||||
OpenRouter.configure({
|
||||
apiKey: process.env.OPENROUTER_API_KEY ?? "fixture",
|
||||
providerOptions: { openrouter: { reasoning: { max_tokens: 1024 } } },
|
||||
@@ -25,7 +25,7 @@ const cases = [
|
||||
},
|
||||
{
|
||||
name: "Vercel AI Gateway",
|
||||
model: LanguageModel.update(
|
||||
model: Model.update(
|
||||
OpenAICompatible.configure({
|
||||
provider: "vercel-ai-gateway",
|
||||
baseURL: "https://ai-gateway.vercel.sh/v1",
|
||||
|
||||
@@ -4,11 +4,11 @@ import { HttpClientRequest } from "effect/unstable/http"
|
||||
import {
|
||||
HttpOptions,
|
||||
LLM,
|
||||
AIError,
|
||||
LLMError,
|
||||
LLMEvent,
|
||||
LLMRequest,
|
||||
Message,
|
||||
LanguageModel,
|
||||
Model,
|
||||
ToolCallPart,
|
||||
ToolDefinition,
|
||||
Usage,
|
||||
@@ -104,7 +104,7 @@ describe("OpenAI Chat route", () => {
|
||||
Effect.gen(function* () {
|
||||
const prepared = yield* compileRequest(
|
||||
LLM.request({
|
||||
model: LanguageModel.update(model, { compatibility: { reasoningField: "vendor_reasoning" } }),
|
||||
model: Model.update(model, { compatibility: { reasoningField: "vendor_reasoning" } }),
|
||||
messages: [
|
||||
Message.assistant([
|
||||
{
|
||||
@@ -130,7 +130,7 @@ describe("OpenAI Chat route", () => {
|
||||
Effect.gen(function* () {
|
||||
const error = yield* compileRequest(
|
||||
LLM.request({
|
||||
model: LanguageModel.update(model, { compatibility: { reasoningField: "content" } }),
|
||||
model: Model.update(model, { compatibility: { reasoningField: "content" } }),
|
||||
messages: [Message.assistant([{ type: "reasoning", text: "thinking" }])],
|
||||
}),
|
||||
).pipe(Effect.flip)
|
||||
@@ -171,9 +171,7 @@ describe("OpenAI Chat route", () => {
|
||||
it.effect("adds native query params to the Chat Completions URL", () =>
|
||||
LLMClient.generate(
|
||||
LLMRequest.update(request, {
|
||||
model: LanguageModel.update(model, {
|
||||
route: model.route.with({ endpoint: { query: { "api-version": "v1" } } }),
|
||||
}),
|
||||
model: Model.update(model, { route: model.route.with({ endpoint: { query: { "api-version": "v1" } } }) }),
|
||||
}),
|
||||
).pipe(
|
||||
Effect.provide(
|
||||
@@ -626,7 +624,7 @@ describe("OpenAI Chat route", () => {
|
||||
|
||||
it.effect("parses and replays a configured custom reasoning field", () =>
|
||||
Effect.gen(function* () {
|
||||
const custom = LanguageModel.update(model, { compatibility: { reasoningField: "vendor_reasoning" } })
|
||||
const custom = Model.update(model, { compatibility: { reasoningField: "vendor_reasoning" } })
|
||||
const response = yield* LLMClient.generate(LLMRequest.update(request, { model: custom })).pipe(
|
||||
Effect.provide(
|
||||
fixedResponse(
|
||||
@@ -1136,12 +1134,9 @@ describe("OpenAI Chat route", () => {
|
||||
{ type: "tool-input-delta", id: "call_1", name: "lookup", text: ':"weather"}' },
|
||||
])
|
||||
expect(events.filter(LLMEvent.is.toolCall)).toEqual([])
|
||||
expect(streamError.reason).toMatchObject({
|
||||
_tag: "InvalidProviderOutput",
|
||||
classification: "incomplete-stream",
|
||||
})
|
||||
expect(streamError.message).toContain("The provider response ended unexpectedly.")
|
||||
expect(error.message).toContain("The provider response ended unexpectedly.")
|
||||
expect(streamError.reason).toMatchObject({ _tag: "InvalidProviderOutput" })
|
||||
expect(streamError.message).toContain("Provider stream ended without a terminal finish event")
|
||||
expect(error.message).toContain("Provider stream ended without a terminal finish event")
|
||||
}),
|
||||
)
|
||||
|
||||
@@ -1177,7 +1172,7 @@ describe("OpenAI Chat route", () => {
|
||||
Effect.flip,
|
||||
)
|
||||
|
||||
expect(error).toBeInstanceOf(AIError)
|
||||
expect(error).toBeInstanceOf(LLMError)
|
||||
expect(error.reason).toMatchObject({ _tag: "InvalidRequest" })
|
||||
expect(error.message).toContain("HTTP 400")
|
||||
}),
|
||||
|
||||
@@ -144,20 +144,6 @@ describe("OpenAI-compatible Chat route", () => {
|
||||
}),
|
||||
)
|
||||
|
||||
it.effect("configures the max tokens request field", () =>
|
||||
Effect.gen(function* () {
|
||||
const compatible = OpenAICompatibleChat.route
|
||||
.with({ provider: "custom", endpoint: { baseURL: "https://api.custom.test/v1" } })
|
||||
.model({ id: "custom-model", compatibility: { maxTokensField: "max_completion_tokens" } })
|
||||
const prepared = yield* compileRequest(
|
||||
LLM.request({ model: compatible, prompt: "Say hello.", generation: { maxTokens: 20 } }),
|
||||
)
|
||||
|
||||
expect(prepared.body).toMatchObject({ max_completion_tokens: 20 })
|
||||
expect(prepared.body).not.toHaveProperty("max_tokens")
|
||||
}),
|
||||
)
|
||||
|
||||
it.effect("matches AI SDK compatible tool request body fixture", () =>
|
||||
Effect.gen(function* () {
|
||||
const prepared = yield* compileRequest(
|
||||
|
||||
@@ -1,21 +1,19 @@
|
||||
import { describe, expect } from "bun:test"
|
||||
import { ConfigProvider, Effect, Layer, Ref, Stream } from "effect"
|
||||
import { ConfigProvider, Effect, Layer, Stream } from "effect"
|
||||
import { Headers, HttpClientRequest } from "effect/unstable/http"
|
||||
import {
|
||||
LLM,
|
||||
AIError,
|
||||
HttpOptions,
|
||||
LLMError,
|
||||
LLMEvent,
|
||||
LLMRequest,
|
||||
Message,
|
||||
LanguageModel,
|
||||
Model,
|
||||
ToolCallPart,
|
||||
ToolDefinition,
|
||||
ToolResultPart,
|
||||
TransportReason,
|
||||
Usage,
|
||||
} from "../../src"
|
||||
import { Auth, LLMClient, RequestExecutor, WebSocketTransport } from "../../src/route"
|
||||
import { Auth, LLMClient, RequestExecutor, WebSocketExecutor } from "../../src/route"
|
||||
import { compileRequest } from "../../src/route/client"
|
||||
import * as Azure from "../../src/providers/azure"
|
||||
import * as OpenAI from "../../src/providers/openai"
|
||||
@@ -218,19 +216,19 @@ describe("OpenAI Responses route", () => {
|
||||
}),
|
||||
)
|
||||
|
||||
it.effect("prepares one OpenAI Responses route for either transport", () =>
|
||||
it.effect("prepares OpenAI Responses WebSocket target", () =>
|
||||
Effect.gen(function* () {
|
||||
const prepared = yield* compileRequest(
|
||||
LLMRequest.update(request, {
|
||||
model: OpenAIResponses.route
|
||||
model: OpenAIResponses.webSocketRoute
|
||||
.with({ endpoint: { baseURL: "https://api.openai.test/v1/" }, auth: Auth.bearer("test") })
|
||||
.model({ id: "gpt-4.1-mini" }),
|
||||
}),
|
||||
)
|
||||
|
||||
expect(prepared.route).toBe("openai-responses")
|
||||
expect(prepared.route).toBe("openai-responses-websocket")
|
||||
expect(prepared.protocol).toBe("openai-responses")
|
||||
expect(prepared.metadata).toEqual({ transport: "http-json" })
|
||||
expect(prepared.metadata).toEqual({ transport: "websocket-json" })
|
||||
expect(prepared.body).toMatchObject({ model: "gpt-4.1-mini", store: false, stream: true })
|
||||
}),
|
||||
)
|
||||
@@ -240,35 +238,41 @@ describe("OpenAI Responses route", () => {
|
||||
const sent: string[] = []
|
||||
const opened: Array<{ readonly url: string; readonly authorization: string | undefined }> = []
|
||||
let closed = false
|
||||
const deps = Layer.succeed(
|
||||
RequestExecutor.Service,
|
||||
RequestExecutor.Service.of({
|
||||
execute: () => Effect.die("unexpected HTTP request"),
|
||||
}),
|
||||
)
|
||||
const webSocket = WebSocketTransport.makeDirect({
|
||||
open: (input) =>
|
||||
Effect.succeed({
|
||||
sendText: (message) =>
|
||||
Effect.sync(() => {
|
||||
opened.push({ url: input.url, authorization: input.headers.authorization })
|
||||
sent.push(message)
|
||||
}),
|
||||
messages: Stream.fromArray([
|
||||
ProviderShared.encodeJson({ type: "response.output_text.delta", item_id: "msg_1", delta: "Hi" }),
|
||||
ProviderShared.encodeJson({ type: "response.completed", response: { id: "resp_ws" } }),
|
||||
]),
|
||||
close: Effect.sync(() => {
|
||||
closed = true
|
||||
}),
|
||||
const deps = Layer.mergeAll(
|
||||
Layer.succeed(
|
||||
RequestExecutor.Service,
|
||||
RequestExecutor.Service.of({
|
||||
execute: () => Effect.die("unexpected HTTP request"),
|
||||
}),
|
||||
})
|
||||
),
|
||||
Layer.succeed(
|
||||
WebSocketExecutor.Service,
|
||||
WebSocketExecutor.Service.of({
|
||||
open: (input) =>
|
||||
Effect.succeed({
|
||||
sendText: (message) =>
|
||||
Effect.sync(() => {
|
||||
opened.push({ url: input.url, authorization: input.headers.authorization })
|
||||
sent.push(message)
|
||||
}),
|
||||
messages: Stream.fromArray([
|
||||
ProviderShared.encodeJson({ type: "response.output_text.delta", item_id: "msg_1", delta: "Hi" }),
|
||||
ProviderShared.encodeJson({ type: "response.completed", response: { id: "resp_ws" } }),
|
||||
]),
|
||||
close: Effect.sync(() => {
|
||||
closed = true
|
||||
}),
|
||||
}),
|
||||
}),
|
||||
),
|
||||
)
|
||||
const response = yield* LLMClient.generate(
|
||||
LLM.request({
|
||||
model: OpenAI.configure({ baseURL: "https://api.openai.test/v1/", apiKey: "test" }).responses("gpt-4.1-mini"),
|
||||
model: OpenAI.configure({ baseURL: "https://api.openai.test/v1/", apiKey: "test" }).responsesWebSocket(
|
||||
"gpt-4.1-mini",
|
||||
),
|
||||
prompt: "Say hello.",
|
||||
}),
|
||||
{ webSocket },
|
||||
).pipe(Effect.provide(LLMClient.layer.pipe(Layer.provide(deps))))
|
||||
|
||||
expect(response.text).toBe("Hi")
|
||||
@@ -284,235 +288,15 @@ describe("OpenAI Responses route", () => {
|
||||
}),
|
||||
)
|
||||
|
||||
it.effect("builds WebSocket and HTTP fallback from the same final request", () =>
|
||||
Effect.gen(function* () {
|
||||
const attempts = yield* Ref.make(0)
|
||||
const message = yield* Ref.make("")
|
||||
const body = yield* Ref.make("")
|
||||
const response = yield* LLMClient.generate(
|
||||
LLM.request({
|
||||
model: OpenAI.configure({ baseURL: "https://api.openai.test/v1/", apiKey: "test" }).responses("gpt-4.1-mini"),
|
||||
prompt: "Say hello.",
|
||||
http: {
|
||||
body: { model: "overlaid-model", metadata: { source: "overlay" } },
|
||||
headers: { "x-request": "request" },
|
||||
query: { mode: "test" },
|
||||
},
|
||||
}),
|
||||
{
|
||||
webSocket: {
|
||||
execute: (exchange) =>
|
||||
Effect.gen(function* () {
|
||||
yield* exchange.driver
|
||||
.create(undefined)
|
||||
.pipe(Effect.flatMap((create) => Ref.set(message, create.message)))
|
||||
return { frames: exchange.fallback(), complete: Effect.void }
|
||||
}),
|
||||
},
|
||||
},
|
||||
).pipe(
|
||||
Effect.provide(
|
||||
dynamicResponse((input) =>
|
||||
Effect.gen(function* () {
|
||||
yield* Ref.update(attempts, (value) => value + 1)
|
||||
yield* Ref.set(body, input.text)
|
||||
expect(input.request.url).toBe("https://api.openai.test/v1/responses?mode=test")
|
||||
expect(input.request.headers.authorization).toBe("Bearer test")
|
||||
expect(input.request.headers["x-request"]).toBe("request")
|
||||
return input.respond(sseEvents({ type: "response.completed", response: {} }), {
|
||||
headers: { "content-type": "text/event-stream" },
|
||||
})
|
||||
}),
|
||||
),
|
||||
),
|
||||
)
|
||||
|
||||
const httpBody = JSON.parse(yield* Ref.get(body))
|
||||
const { stream: _stream, ...shared } = httpBody
|
||||
expect(response.finishReason?.normalized).toBe("stop")
|
||||
expect(yield* Ref.get(attempts)).toBe(1)
|
||||
expect(JSON.parse(yield* Ref.get(message))).toEqual({ type: "response.create", ...shared })
|
||||
expect(httpBody).toMatchObject({
|
||||
model: "overlaid-model",
|
||||
metadata: { source: "overlay" },
|
||||
stream: true,
|
||||
})
|
||||
}),
|
||||
)
|
||||
|
||||
it.effect("uses exactly one HTTP request when no WebSocket executor is supplied", () =>
|
||||
Effect.gen(function* () {
|
||||
const attempts = yield* Ref.make(0)
|
||||
yield* LLMClient.generate(
|
||||
LLMRequest.update(request, { http: new HttpOptions({ body: { input: "raw-http-input" } }) }),
|
||||
).pipe(
|
||||
Effect.provide(
|
||||
dynamicResponse((input) =>
|
||||
Effect.gen(function* () {
|
||||
yield* Ref.update(attempts, (value) => value + 1)
|
||||
expect(JSON.parse(input.text).input).toBe("raw-http-input")
|
||||
return input.respond(sseEvents({ type: "response.completed", response: {} }), {
|
||||
headers: { "content-type": "text/event-stream" },
|
||||
})
|
||||
}),
|
||||
),
|
||||
),
|
||||
)
|
||||
|
||||
expect(yield* Ref.get(attempts)).toBe(1)
|
||||
}),
|
||||
)
|
||||
|
||||
it.effect("closes a direct WebSocket execution after partial consumption", () =>
|
||||
Effect.gen(function* () {
|
||||
const closed = yield* Ref.make(false)
|
||||
const webSocket = WebSocketTransport.makeDirect({
|
||||
open: () =>
|
||||
Effect.succeed({
|
||||
sendText: () => Effect.void,
|
||||
messages: Stream.fromArray([
|
||||
ProviderShared.encodeJson({ type: "response.output_text.delta", item_id: "msg_1", delta: "Hi" }),
|
||||
ProviderShared.encodeJson({ type: "response.completed", response: { id: "resp_ws" } }),
|
||||
]),
|
||||
close: Ref.set(closed, true),
|
||||
}),
|
||||
})
|
||||
|
||||
yield* LLMClient.stream(
|
||||
LLM.request({
|
||||
model: OpenAI.configure({ baseURL: "https://api.openai.test/v1/", apiKey: "test" }).responses("gpt-4.1-mini"),
|
||||
prompt: "Say hello.",
|
||||
}),
|
||||
{ webSocket },
|
||||
).pipe(
|
||||
Stream.take(1),
|
||||
Stream.runDrain,
|
||||
Effect.provide(
|
||||
LLMClient.layer.pipe(
|
||||
Layer.provide(
|
||||
Layer.succeed(
|
||||
RequestExecutor.Service,
|
||||
RequestExecutor.Service.of({ execute: () => Effect.die("unexpected HTTP request") }),
|
||||
),
|
||||
),
|
||||
),
|
||||
),
|
||||
)
|
||||
|
||||
expect(yield* Ref.get(closed)).toBe(true)
|
||||
}),
|
||||
)
|
||||
|
||||
it.effect("terminates WebSocket control events without waiting for the socket to close", () =>
|
||||
Effect.gen(function* () {
|
||||
const events = [
|
||||
{ type: "error", error: { code: "slow_down", message: "Try later" } },
|
||||
{
|
||||
type: "error",
|
||||
status_code: 429,
|
||||
message: "Rate limited",
|
||||
headers: { "retry-after": 1, "x-request-id": "request", cached: false, invalid: [] },
|
||||
},
|
||||
{
|
||||
type: "response.failed",
|
||||
response: { error: { code: "server_error", message: "Unavailable" } },
|
||||
},
|
||||
{ type: "error", status: "not-a-status", message: "Malformed status" },
|
||||
]
|
||||
|
||||
const errors = yield* Effect.forEach(events, (event) =>
|
||||
LLMClient.generate(
|
||||
LLM.request({
|
||||
model: OpenAI.configure({ baseURL: "https://api.openai.test/v1/", apiKey: "test" }).responses(
|
||||
"gpt-4.1-mini",
|
||||
),
|
||||
prompt: "Say hello.",
|
||||
}),
|
||||
{
|
||||
webSocket: WebSocketTransport.makeDirect({
|
||||
open: () =>
|
||||
Effect.succeed({
|
||||
sendText: () => Effect.void,
|
||||
messages: Stream.make(ProviderShared.encodeJson(event)).pipe(Stream.concat(Stream.never)),
|
||||
close: Effect.void,
|
||||
}),
|
||||
}),
|
||||
},
|
||||
).pipe(
|
||||
Effect.provide(
|
||||
LLMClient.layer.pipe(
|
||||
Layer.provide(
|
||||
Layer.succeed(
|
||||
RequestExecutor.Service,
|
||||
RequestExecutor.Service.of({ execute: () => Effect.die("unexpected HTTP request") }),
|
||||
),
|
||||
),
|
||||
),
|
||||
),
|
||||
Effect.flip,
|
||||
),
|
||||
)
|
||||
|
||||
expect(errors.map((error) => error.reason._tag)).toEqual([
|
||||
"ProviderInternal",
|
||||
"RateLimit",
|
||||
"ProviderInternal",
|
||||
"UnknownProvider",
|
||||
])
|
||||
}),
|
||||
)
|
||||
|
||||
it.effect("marks post-send WebSocket failures with delivery state", () =>
|
||||
Effect.gen(function* () {
|
||||
const failure = new AIError({
|
||||
module: "test",
|
||||
method: "receive",
|
||||
reason: new TransportReason({ message: "socket closed", phase: "close" }),
|
||||
})
|
||||
const streams = [
|
||||
Stream.fail(failure),
|
||||
Stream.make(ProviderShared.encodeJson({ type: "response.created" })).pipe(Stream.concat(Stream.fail(failure))),
|
||||
]
|
||||
const deps = Layer.succeed(
|
||||
RequestExecutor.Service,
|
||||
RequestExecutor.Service.of({ execute: () => Effect.die("unexpected HTTP request") }),
|
||||
)
|
||||
const webSocket = WebSocketTransport.makeDirect({
|
||||
open: () =>
|
||||
Effect.succeed({
|
||||
sendText: () => Effect.void,
|
||||
messages: streams.shift() ?? Stream.die("unexpected WebSocket open"),
|
||||
close: Effect.void,
|
||||
}),
|
||||
})
|
||||
const model = OpenAI.configure({ baseURL: "https://api.openai.test/v1/", apiKey: "test" }).responses(
|
||||
"gpt-4.1-mini",
|
||||
)
|
||||
|
||||
const errors = yield* Effect.forEach(["first", "second"], (prompt) =>
|
||||
LLMClient.generate(LLM.request({ model, prompt }), { webSocket }).pipe(
|
||||
Effect.provide(LLMClient.layer.pipe(Layer.provide(deps))),
|
||||
Effect.flip,
|
||||
),
|
||||
)
|
||||
|
||||
expect(errors.map((error) => error.reason)).toEqual([
|
||||
expect.objectContaining({ _tag: "Transport", phase: "close", delivery: "ambiguous" }),
|
||||
expect.objectContaining({ _tag: "Transport", phase: "close", delivery: "accepted" }),
|
||||
])
|
||||
}),
|
||||
)
|
||||
|
||||
it.effect("fails immediately when WebSocket is already closed", () =>
|
||||
Effect.gen(function* () {
|
||||
const error = yield* WebSocketTransport.fromWebSocket(
|
||||
const error = yield* WebSocketExecutor.fromWebSocket(
|
||||
// oxlint-disable-next-line typescript-eslint/no-unsafe-type-assertion -- fromWebSocket reads readyState before touching WebSocket methods on this branch.
|
||||
{ readyState: globalThis.WebSocket.CLOSED } as globalThis.WebSocket,
|
||||
{ url: "wss://api.openai.test/v1/responses", headers: Headers.empty },
|
||||
).pipe(Effect.flip)
|
||||
|
||||
expect(error.message).toContain("closed before opening")
|
||||
expect(error.reason).toMatchObject({ _tag: "Transport", phase: "connect", delivery: "not-sent" })
|
||||
}),
|
||||
)
|
||||
|
||||
@@ -520,9 +304,7 @@ describe("OpenAI Responses route", () => {
|
||||
Effect.gen(function* () {
|
||||
yield* LLMClient.generate(
|
||||
LLMRequest.update(request, {
|
||||
model: LanguageModel.update(model, {
|
||||
route: model.route.with({ endpoint: { query: { "api-version": "v1" } } }),
|
||||
}),
|
||||
model: Model.update(model, { route: model.route.with({ endpoint: { query: { "api-version": "v1" } } }) }),
|
||||
}),
|
||||
).pipe(
|
||||
Effect.provide(
|
||||
@@ -1203,7 +985,9 @@ describe("OpenAI Responses route", () => {
|
||||
|
||||
for (const event of events) {
|
||||
const error = yield* LLMClient.generate(request).pipe(
|
||||
Effect.provide(fixedResponse(sseEvents(event, { type: "response.completed", response: { id: "resp_1" } }))),
|
||||
Effect.provide(
|
||||
fixedResponse(sseEvents(event, { type: "response.completed", response: { id: "resp_1" } })),
|
||||
),
|
||||
Effect.flip,
|
||||
)
|
||||
expect(error.reason._tag).toBe("InvalidProviderOutput")
|
||||
@@ -2059,7 +1843,7 @@ describe("OpenAI Responses route", () => {
|
||||
Effect.flip,
|
||||
)
|
||||
|
||||
expect(error).toBeInstanceOf(AIError)
|
||||
expect(error).toBeInstanceOf(LLMError)
|
||||
expect(error.reason).toMatchObject({ _tag: "RateLimit", message: "rate_limit_exceeded: Slow down" })
|
||||
}),
|
||||
)
|
||||
@@ -2253,7 +2037,7 @@ describe("OpenAI Responses route", () => {
|
||||
Effect.flip,
|
||||
)
|
||||
|
||||
expect(error).toBeInstanceOf(AIError)
|
||||
expect(error).toBeInstanceOf(LLMError)
|
||||
expect(error.reason).toMatchObject({ _tag: "InvalidRequest" })
|
||||
expect(error.message).toContain("HTTP 400")
|
||||
}),
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
import { describe, expect } from "bun:test"
|
||||
import { Effect } from "effect"
|
||||
import { CacheHint, LLM, Message } from "../../src"
|
||||
import { LLM, Message } from "../../src"
|
||||
import { LLMClient } from "../../src/route"
|
||||
import { compileRequest } from "../../src/route/client"
|
||||
import * as OpenRouter from "../../src/providers/openrouter"
|
||||
@@ -27,131 +27,10 @@ describe("OpenRouter", () => {
|
||||
model: "openai/gpt-4o-mini",
|
||||
messages: [{ role: "user", content: "Say hello." }],
|
||||
stream: true,
|
||||
usage: { include: true },
|
||||
})
|
||||
}),
|
||||
)
|
||||
|
||||
it.effect("lowers the native cache policy to OpenRouter cache controls", () =>
|
||||
Effect.gen(function* () {
|
||||
const prepared = yield* compileRequest(
|
||||
LLM.request({
|
||||
model: OpenRouter.configure({ apiKey: "test-key" }).model("anthropic/claude-sonnet-4.6"),
|
||||
system: [
|
||||
{ type: "text", text: "Base agent", cache: new CacheHint({ type: "ephemeral", ttlSeconds: 3_600 }) },
|
||||
{ type: "text", text: "Project instructions" },
|
||||
],
|
||||
tools: [{ name: "lookup", description: "Lookup", inputSchema: { type: "object", properties: {} } }],
|
||||
prompt: "Hello",
|
||||
cache: { tools: true, system: true, messages: { tail: 1 } },
|
||||
}),
|
||||
)
|
||||
|
||||
expect(prepared.body).toMatchObject({
|
||||
tools: [{ cache_control: { type: "ephemeral" } }],
|
||||
messages: [
|
||||
{
|
||||
role: "system",
|
||||
content: [
|
||||
{ text: "Base agent", cache_control: { type: "ephemeral", ttl: "1h" } },
|
||||
{ text: "Project instructions", cache_control: { type: "ephemeral" } },
|
||||
],
|
||||
},
|
||||
{
|
||||
role: "user",
|
||||
content: [{ text: "Hello", cache_control: { type: "ephemeral" } }],
|
||||
},
|
||||
],
|
||||
})
|
||||
}),
|
||||
)
|
||||
|
||||
it.effect("lowers manual assistant and tool-result cache hints", () =>
|
||||
Effect.gen(function* () {
|
||||
const prepared = yield* compileRequest(
|
||||
LLM.request({
|
||||
model: OpenRouter.configure({ apiKey: "test-key" }).model("anthropic/claude-sonnet-4.6"),
|
||||
cache: "none",
|
||||
messages: [
|
||||
Message.user("Call the tool"),
|
||||
Message.assistant([
|
||||
{ type: "text", text: "Calling", cache: new CacheHint({ type: "ephemeral" }) },
|
||||
{ type: "tool-call", id: "call_1", name: "lookup", input: {} },
|
||||
]),
|
||||
Message.tool({
|
||||
id: "call_1",
|
||||
name: "lookup",
|
||||
result: "Done",
|
||||
cache: new CacheHint({ type: "ephemeral", ttlSeconds: 3_600 }),
|
||||
}),
|
||||
],
|
||||
}),
|
||||
)
|
||||
|
||||
expect(prepared.body.messages).toMatchObject([
|
||||
{ role: "user", content: "Call the tool" },
|
||||
{ role: "assistant", content: "Calling", cache_control: { type: "ephemeral" } },
|
||||
{ role: "tool", content: '"Done"', cache_control: { type: "ephemeral", ttl: "1h" } },
|
||||
])
|
||||
}),
|
||||
)
|
||||
|
||||
it.effect("caps manual cache controls at four breakpoints", () =>
|
||||
Effect.gen(function* () {
|
||||
const cache = new CacheHint({ type: "ephemeral" })
|
||||
const prepared = yield* compileRequest(
|
||||
LLM.request({
|
||||
model: OpenRouter.configure({ apiKey: "test-key" }).model("anthropic/claude-sonnet-4.6"),
|
||||
cache: "none",
|
||||
system: [1, 2, 3, 4, 5].map((index) => ({ type: "text" as const, text: `System ${index}`, cache })),
|
||||
prompt: "Hello",
|
||||
}),
|
||||
)
|
||||
|
||||
const system = prepared.body.messages[0]
|
||||
expect(system?.role).toBe("system")
|
||||
expect(
|
||||
system && Array.isArray(system.content)
|
||||
? system.content.filter((part) => "cache_control" in part && part.cache_control !== undefined)
|
||||
: [],
|
||||
).toHaveLength(4)
|
||||
}),
|
||||
)
|
||||
|
||||
it.effect("preserves cache policy hints on reasoning-only assistant messages", () =>
|
||||
Effect.gen(function* () {
|
||||
const prepared = yield* compileRequest(
|
||||
LLM.request({
|
||||
model: OpenRouter.configure({ apiKey: "test-key" }).model("anthropic/claude-sonnet-4.6"),
|
||||
cache: { messages: "latest-assistant" },
|
||||
messages: [Message.user("Think"), Message.assistant([{ type: "reasoning", text: "Reasoning" }])],
|
||||
}),
|
||||
)
|
||||
|
||||
expect(prepared.body.messages).toMatchObject([
|
||||
{ role: "user", content: "Think" },
|
||||
{ role: "assistant", cache_control: { type: "ephemeral" } },
|
||||
])
|
||||
}),
|
||||
)
|
||||
|
||||
it.effect("allows usage accounting to be disabled explicitly", () =>
|
||||
Effect.gen(function* () {
|
||||
const prepared = yield* compileRequest(
|
||||
LLM.request({
|
||||
model: OpenRouter.configure({
|
||||
apiKey: "test-key",
|
||||
providerOptions: { openrouter: { usage: false } },
|
||||
}).model("openai/gpt-4o-mini"),
|
||||
cache: "none",
|
||||
prompt: "Hello",
|
||||
}),
|
||||
)
|
||||
|
||||
expect(prepared.body.usage).toEqual({ include: false })
|
||||
}),
|
||||
)
|
||||
|
||||
it.effect("applies OpenRouter payload options from the model helper", () =>
|
||||
Effect.gen(function* () {
|
||||
const prepared = yield* compileRequest(
|
||||
@@ -163,13 +42,6 @@ describe("OpenRouter", () => {
|
||||
usage: true,
|
||||
reasoning: { effort: "high" },
|
||||
promptCacheKey: "session_123",
|
||||
models: ["anthropic/claude-sonnet-4.6", "google/gemini-3.1-pro"],
|
||||
provider: { order: ["anthropic", "google"], require_parameters: true },
|
||||
plugins: [{ id: "response-healing" }],
|
||||
web_search_options: { engine: "native", max_results: 3 },
|
||||
debug: { echo_upstream_body: true },
|
||||
user: "user_123",
|
||||
future_option: { enabled: true },
|
||||
},
|
||||
},
|
||||
}).model("anthropic/claude-3.7-sonnet:thinking"),
|
||||
@@ -181,54 +53,10 @@ describe("OpenRouter", () => {
|
||||
usage: { include: true },
|
||||
reasoning: { effort: "high" },
|
||||
prompt_cache_key: "session_123",
|
||||
models: ["anthropic/claude-sonnet-4.6", "google/gemini-3.1-pro"],
|
||||
provider: { order: ["anthropic", "google"], require_parameters: true },
|
||||
plugins: [{ id: "response-healing" }],
|
||||
web_search_options: { engine: "native", max_results: 3 },
|
||||
debug: { echo_upstream_body: true },
|
||||
user: "user_123",
|
||||
future_option: { enabled: true },
|
||||
})
|
||||
}),
|
||||
)
|
||||
|
||||
it.effect("filters invalid known OpenRouter options while preserving extensions", () =>
|
||||
Effect.gen(function* () {
|
||||
const invalid: Record<string, unknown> = {
|
||||
usage: "yes",
|
||||
models: "anthropic/claude-sonnet-4.6",
|
||||
provider: [],
|
||||
plugins: {},
|
||||
web_search_options: [],
|
||||
debug: [],
|
||||
user: 123,
|
||||
reasoning: [],
|
||||
promptCacheKey: 123,
|
||||
future_option: { enabled: true },
|
||||
}
|
||||
const prepared = yield* compileRequest(
|
||||
LLM.request({
|
||||
model: OpenRouter.configure({
|
||||
apiKey: "test-key",
|
||||
providerOptions: { openrouter: invalid },
|
||||
}).model("openai/gpt-4o-mini"),
|
||||
prompt: "Hello",
|
||||
}),
|
||||
)
|
||||
|
||||
expect(prepared.body).toMatchObject({ future_option: { enabled: true } })
|
||||
expect(prepared.body).not.toHaveProperty("usage")
|
||||
expect(prepared.body).not.toHaveProperty("models")
|
||||
expect(prepared.body).not.toHaveProperty("provider")
|
||||
expect(prepared.body).not.toHaveProperty("plugins")
|
||||
expect(prepared.body).not.toHaveProperty("web_search_options")
|
||||
expect(prepared.body).not.toHaveProperty("debug")
|
||||
expect(prepared.body).not.toHaveProperty("user")
|
||||
expect(prepared.body).not.toHaveProperty("reasoning")
|
||||
expect(prepared.body).not.toHaveProperty("prompt_cache_key")
|
||||
}),
|
||||
)
|
||||
|
||||
it.effect("preserves the upstream provider finish reason", () =>
|
||||
Effect.gen(function* () {
|
||||
const model = OpenRouter.configure({ apiKey: "test-key" }).model("anthropic/claude-sonnet-4.6")
|
||||
@@ -276,7 +104,6 @@ describe("OpenRouter", () => {
|
||||
const prepared = yield* compileRequest(
|
||||
LLM.request({
|
||||
model: OpenRouter.configure({ apiKey: "test-key" }).model("anthropic/claude-sonnet-4.6"),
|
||||
cache: "none",
|
||||
messages: [
|
||||
Message.assistant([
|
||||
{
|
||||
@@ -310,7 +137,6 @@ describe("OpenRouter", () => {
|
||||
const prepared = yield* compileRequest(
|
||||
LLM.request({
|
||||
model: OpenRouter.configure({ apiKey: "test-key" }).model("anthropic/claude-sonnet-4.6"),
|
||||
cache: "none",
|
||||
messages: [
|
||||
Message.assistant({
|
||||
type: "reasoning",
|
||||
@@ -336,7 +162,6 @@ describe("OpenRouter", () => {
|
||||
const prepared = yield* compileRequest(
|
||||
LLM.request({
|
||||
model: OpenRouter.configure({ apiKey: "test-key" }).model("anthropic/claude-sonnet-4.6"),
|
||||
cache: "none",
|
||||
messages: [
|
||||
Message.assistant({
|
||||
type: "reasoning",
|
||||
@@ -358,7 +183,6 @@ describe("OpenRouter", () => {
|
||||
const prepared = yield* compileRequest(
|
||||
LLM.request({
|
||||
model: OpenRouter.configure({ apiKey: "test-key" }).model("anthropic/claude-sonnet-4.6"),
|
||||
cache: "none",
|
||||
messages: [Message.assistant({ type: "reasoning", text: "Thinking" })],
|
||||
}),
|
||||
)
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
import { describe, expect } from "bun:test"
|
||||
import { Effect, Schema, Stream } from "effect"
|
||||
import { LLM, LLMResponse, Message, ToolDefinition, type LanguageModel } from "../../src"
|
||||
import { LLM, LLMResponse, Message, ToolDefinition, type Model } from "../../src"
|
||||
import { AmazonBedrock, Anthropic, Google, OpenAI, XAI } from "../../src/providers"
|
||||
import { LLMClient } from "../../src/route"
|
||||
import { Tool } from "../../src/tool"
|
||||
@@ -28,7 +28,7 @@ const targets: ReadonlyArray<{
|
||||
readonly requires: string
|
||||
readonly filename: string
|
||||
readonly maxTokens: number
|
||||
readonly model: LanguageModel
|
||||
readonly model: Model
|
||||
}> = [
|
||||
{
|
||||
id: "openai",
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
import type { HttpRecorder } from "@opencode-ai/http-recorder"
|
||||
import { describe } from "bun:test"
|
||||
import { Effect } from "effect"
|
||||
import type { LanguageModel } from "../src"
|
||||
import type { Model } from "../src"
|
||||
import { goldenScenarioTags, goldenScenarioTitle, runGoldenScenario, type GoldenScenarioID } from "./recorded-scenarios"
|
||||
import { recordedTests } from "./recorded-test"
|
||||
import { kebab } from "./recorded-utils"
|
||||
@@ -22,7 +22,7 @@ type ScenarioInput =
|
||||
|
||||
type TargetInput = {
|
||||
readonly name: string
|
||||
readonly model: LanguageModel
|
||||
readonly model: Model
|
||||
readonly protocol?: string
|
||||
readonly requires?: ReadonlyArray<string>
|
||||
readonly transport?: Transport
|
||||
|
||||
@@ -12,7 +12,7 @@ import {
|
||||
toDefinitions,
|
||||
type ContentPart,
|
||||
type FinishReason,
|
||||
type LanguageModel,
|
||||
type Model,
|
||||
} from "../src"
|
||||
import { LLMClient } from "../src/route"
|
||||
import { Tool } from "../src/tool"
|
||||
@@ -54,7 +54,7 @@ export const weatherRuntimeTool = Tool.make({
|
||||
|
||||
export const weatherToolLoopRequest = (input: {
|
||||
readonly id: string
|
||||
readonly model: LanguageModel
|
||||
readonly model: Model
|
||||
readonly system?: string
|
||||
readonly maxTokens?: number
|
||||
readonly temperature?: number | false
|
||||
@@ -73,7 +73,7 @@ export const weatherToolLoopRequest = (input: {
|
||||
|
||||
export const goldenWeatherToolLoopRequest = (input: {
|
||||
readonly id: string
|
||||
readonly model: LanguageModel
|
||||
readonly model: Model
|
||||
readonly maxTokens?: number
|
||||
readonly temperature?: number | false
|
||||
}) =>
|
||||
@@ -163,7 +163,7 @@ export const expectGoldenWeatherToolLoop = (events: ReadonlyArray<LLMEvent>) =>
|
||||
|
||||
export interface GoldenScenarioContext {
|
||||
readonly id: string
|
||||
readonly model: LanguageModel
|
||||
readonly model: Model
|
||||
readonly maxTokens?: number
|
||||
readonly temperature?: number | false
|
||||
}
|
||||
|
||||
@@ -2,11 +2,12 @@ import { HttpRecorder } from "@opencode-ai/http-recorder"
|
||||
import { Layer } from "effect"
|
||||
import * as path from "node:path"
|
||||
import { fileURLToPath } from "node:url"
|
||||
import { LLMClient, RequestExecutor } from "../src/route"
|
||||
import { LLMClient, RequestExecutor, WebSocketExecutor } from "../src/route"
|
||||
import { ImageClient } from "../src/image-client"
|
||||
import type { Service as ImageClientService } from "../src/image-client"
|
||||
import type { Service as LLMClientService } from "../src/route/client"
|
||||
import type { Service as RequestExecutorService } from "../src/route/executor"
|
||||
import type { Service as WebSocketExecutorService } from "../src/route/transport/websocket"
|
||||
import {
|
||||
recordedEffectGroup,
|
||||
type RecordedCaseOptions as RunnerCaseOptions,
|
||||
@@ -16,7 +17,7 @@ import {
|
||||
const __dirname = path.dirname(fileURLToPath(import.meta.url))
|
||||
const FIXTURES_DIR = path.resolve(__dirname, "fixtures", "recordings")
|
||||
|
||||
type RecordedEnv = RequestExecutorService | LLMClientService | ImageClientService
|
||||
type RecordedEnv = RequestExecutorService | WebSocketExecutorService | LLMClientService | ImageClientService
|
||||
|
||||
type RecordedTestsOptions = RecordedGroupOptions & {
|
||||
readonly options?: HttpRecorder.RecorderOptions
|
||||
@@ -81,10 +82,11 @@ export const recordedTests = (options: RecordedTestsOptions) =>
|
||||
}),
|
||||
),
|
||||
)
|
||||
const deps = Layer.mergeAll(requestExecutor, WebSocketExecutor.layer)
|
||||
return Layer.mergeAll(
|
||||
requestExecutor,
|
||||
LLMClient.layer.pipe(Layer.provide(requestExecutor)),
|
||||
ImageClient.layer.pipe(Layer.provide(requestExecutor)),
|
||||
deps,
|
||||
LLMClient.layer.pipe(Layer.provide(deps)),
|
||||
ImageClient.layer.pipe(Layer.provide(deps)),
|
||||
)
|
||||
},
|
||||
})
|
||||
|
||||
@@ -1,22 +1,11 @@
|
||||
import { describe, expect, test } from "bun:test"
|
||||
import { Effect, Schema } from "effect"
|
||||
import { Schema } from "effect"
|
||||
import * as OpenAIChat from "../src/protocols/openai-chat"
|
||||
import * as OpenAIResponses from "../src/protocols/openai-responses"
|
||||
import {
|
||||
AIError,
|
||||
ContentPart,
|
||||
InvalidRequestReason,
|
||||
LLMEvent,
|
||||
LLMRequest,
|
||||
LanguageModel,
|
||||
ModelID,
|
||||
ProviderID,
|
||||
TransportReason,
|
||||
Usage,
|
||||
} from "../src/schema"
|
||||
import { ContentPart, LLMEvent, LLMRequest, Model, ModelID, ProviderID, Usage } from "../src/schema"
|
||||
import { ProviderShared } from "../src/protocols/shared"
|
||||
|
||||
const model = new LanguageModel({
|
||||
const model = new Model({
|
||||
id: ModelID.make("fake-model"),
|
||||
provider: ProviderID.make("fake-provider"),
|
||||
route: OpenAIChat.route,
|
||||
@@ -44,7 +33,7 @@ describe("llm schema", () => {
|
||||
|
||||
test("accepts custom route ids", () => {
|
||||
const decoded = decodeLLMRequest({
|
||||
model: LanguageModel.update(model, { route: OpenAIResponses.route }),
|
||||
model: Model.update(model, { route: OpenAIResponses.route }),
|
||||
system: [],
|
||||
messages: [],
|
||||
tools: [],
|
||||
@@ -62,7 +51,9 @@ describe("llm schema", () => {
|
||||
expect(
|
||||
LLMEvent.stepFinish({ index: 0, reason: { normalized: "stop" }, usage: { inputTokens: 1 } }).usage,
|
||||
).toBeInstanceOf(Usage)
|
||||
expect(LLMEvent.finish({ reason: { normalized: "stop" }, usage: { outputTokens: 2 } }).usage).toBeInstanceOf(Usage)
|
||||
expect(LLMEvent.finish({ reason: { normalized: "stop" }, usage: { outputTokens: 2 } }).usage).toBeInstanceOf(
|
||||
Usage,
|
||||
)
|
||||
})
|
||||
|
||||
test("content part tagged union exposes guards", () => {
|
||||
@@ -71,7 +62,7 @@ describe("llm schema", () => {
|
||||
})
|
||||
})
|
||||
|
||||
describe("AI.Usage", () => {
|
||||
describe("LLM.Usage", () => {
|
||||
test("subtractTokens clamps non-sensical breakdowns to zero", () => {
|
||||
// Defense against a provider reporting cached_tokens > prompt_tokens or
|
||||
// reasoning_tokens > completion_tokens — the negative would otherwise
|
||||
@@ -97,33 +88,3 @@ describe("AI.Usage", () => {
|
||||
expect(new Usage({}).visibleOutputTokens).toBe(0)
|
||||
})
|
||||
})
|
||||
|
||||
test("AI errors expose the shared runtime tag", async () => {
|
||||
const error = new AIError({
|
||||
module: "test",
|
||||
method: "call",
|
||||
reason: new InvalidRequestReason({ message: "invalid" }),
|
||||
})
|
||||
expect(error._tag).toBe("AI.Error")
|
||||
expect(
|
||||
await Effect.runPromise(Effect.fail(error).pipe(Effect.catchTag("AI.Error", () => Effect.succeed("caught")))),
|
||||
).toBe("caught")
|
||||
})
|
||||
|
||||
test("transport errors serialize execution facts", () => {
|
||||
const reason = new TransportReason({
|
||||
message: "connection closed",
|
||||
phase: "receive",
|
||||
delivery: "ambiguous",
|
||||
recovery: "fail",
|
||||
})
|
||||
|
||||
expect(Schema.encodeSync(TransportReason)(reason)).toEqual({
|
||||
_tag: "Transport",
|
||||
message: "connection closed",
|
||||
phase: "receive",
|
||||
delivery: "ambiguous",
|
||||
recovery: "fail",
|
||||
})
|
||||
expect(Schema.decodeUnknownSync(TransportReason)(Schema.encodeSync(TransportReason)(reason))).toEqual(reason)
|
||||
})
|
||||
|
||||
@@ -169,7 +169,7 @@ describe("LLMClient tools", () => {
|
||||
LLMEvent.toolCall({ id: "call_projected", name: "projected", input: { prefix: "count" } }),
|
||||
)
|
||||
|
||||
expect(calls).toEqual([{ id: "call_projected", parameters: { prefix: "count" }, output: { count: "2" } }])
|
||||
expect(calls).toEqual([{ callID: "call_projected", parameters: { prefix: "count" }, output: { count: "2" } }])
|
||||
expect(dispatched.result).toEqual({ type: "text", value: "count:2" })
|
||||
expect(dispatched.output).toEqual({ structured: { count: "2" }, content: [{ type: "text", text: "count:2" }] })
|
||||
expect(dispatched.events).toEqual([
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
import { describe, expect } from "bun:test"
|
||||
import { Effect } from "effect"
|
||||
import { AIError } from "../src/schema"
|
||||
import { LLMError } from "../src/schema"
|
||||
import { ToolStream } from "../src/protocols/utils/tool-stream"
|
||||
import { it } from "./lib/effect"
|
||||
|
||||
@@ -67,7 +67,7 @@ describe("ToolStream", () => {
|
||||
Effect.gen(function* () {
|
||||
const error = ToolStream.appendExisting(ADAPTER, ToolStream.empty<number>(), 0, "{}", "missing tool")
|
||||
|
||||
expect(error).toBeInstanceOf(AIError)
|
||||
expect(error).toBeInstanceOf(LLMError)
|
||||
if (ToolStream.isError(error)) expect(error.reason.message).toBe("missing tool")
|
||||
}),
|
||||
)
|
||||
|
||||
@@ -27,8 +27,8 @@ Tool.make({
|
||||
parameters: Schema.Struct({ city: Schema.String }),
|
||||
success: Schema.Struct({ forecast: Schema.NumberFromString }),
|
||||
execute: () => Effect.succeed({ forecast: 1 }),
|
||||
toModelOutput: ({ id, parameters, output }) => [
|
||||
{ type: "text", text: `${id}:${parameters.city}:${output.forecast}` },
|
||||
toModelOutput: ({ callID, parameters, output }) => [
|
||||
{ type: "text", text: `${callID}:${parameters.city}:${output.forecast}` },
|
||||
],
|
||||
})
|
||||
|
||||
|
||||
@@ -45,10 +45,6 @@ describe("timeline fixture validation", () => {
|
||||
expect(first.payload.id).toMatch(/^evt_timeline_\d{4}$/)
|
||||
expect(Number(second.payload.id.slice(-4))).toBe(Number(first.payload.id.slice(-4)) + 1)
|
||||
})
|
||||
|
||||
test("uses the projected tool ID as its call ID", () => {
|
||||
expect(toolPart("call_1", "read", "running", {})).toMatchObject({ id: "call_1", callID: "call_1" })
|
||||
})
|
||||
})
|
||||
|
||||
if (false) {
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user