fix(core): map v1 setCacheKey to compatibility

V1 provider.options.setCacheKey was passed through as an inert provider setting, so the prompt cache key was never sent for providers that opt in (and could not be disabled for providers that default it on). Lower it to compatibility.supportsPromptCacheKey on the provider, add provider-level compatibility to the config schema, and apply it to every model of the provider with model-level compatibility taking precedence.

.changeset/directory-page-heading.md

@@ -1,5 +0,0 @@
----
-"@opencode/core": patch
----
-
-Correct directory page headings when the read offset is zero.

.github/workflows/publish.yml

@@ -24,6 +24,10 @@ on:
         description: "Override version (optional)"
         required: false
         type: string
+      release_notes:
+        description: "Reviewed V2 release notes for the Discord announcement (optional)"
+        required: false
+        type: string
 
 concurrency: ${{ github.workflow }}-${{ github.ref }}-${{ (github.ref_name == 'v2' && (inputs.version || inputs.bump) && 'release') || inputs.version || inputs.bump }}
 
@@ -653,3 +657,19 @@ jobs:
           OPENCODE_DESKTOP_DIST: /tmp/desktop
           CLOUDFLARE_ACCOUNT_ID: 15d29c8639fd3733b1b5486a2acfd968
           CLOUDFLARE_API_TOKEN: ${{ secrets.CLOUDFLARE_API_TOKEN }}
+
+  notify-discord-v2:
+    needs:
+      - version
+      - publish
+    if: github.repository == 'anomalyco/opencode' && github.ref_name == 'v2' && needs.version.outputs.release && needs.publish.result == 'success'
+    runs-on: blacksmith-4vcpu-ubuntu-2404
+    steps:
+      # Unlike dev, V2 publishes a tag rather than a GitHub Release event.
+      - name: Announce V2 release in Discord
+        uses: SethCohen/github-releases-to-discord@24d166886aee4646d448c8a389ff9e1ebcab3682 # v1.20.0
+        with:
+          webhook_url: ${{ secrets.DISCORD_WEBHOOK }}
+          release_name: OpenCode V2 ${{ needs.version.outputs.tag }}
+          release_body: ${{ inputs.release_notes }}
+          release_html_url: https://github.com/${{ github.repository }}/tree/${{ needs.version.outputs.tag }}

bun.lock

@@ -194,7 +194,7 @@
         "zod": "catalog:",
       },
       "peerDependencies": {
-        "effect": "4.0.0-rc.117",
+        "effect": "4.0.0-rc.112",
         "solid-js": ">=1.9.0",
       },
       "optionalPeers": [
@@ -405,7 +405,6 @@
         "@types/node": "catalog:",
         "@types/which": "3.0.4",
         "drizzle-kit": "catalog:",
-        "fast-check": "catalog:",
       },
     },
     "packages/desktop": {
@@ -514,7 +513,7 @@
       "name": "@opencode/http-recorder",
       "version": "2.0.18",
       "dependencies": {
-        "@effect/platform-node-shared": "4.0.0-rc.117",
+        "@effect/platform-node-shared": "4.0.0-rc.112",
       },
       "devDependencies": {
         "@effect/platform-node": "catalog:",
@@ -1106,10 +1105,10 @@
   "catalog": {
     "@cloudflare/workers-types": "4.20251008.0",
     "@corvu/drawer": "0.2.4",
-    "@effect/opentelemetry": "4.0.0-rc.117",
-    "@effect/platform-node": "4.0.0-rc.117",
-    "@effect/platform-node-shared": "4.0.0-rc.117",
-    "@effect/sql-sqlite-bun": "4.0.0-rc.117",
+    "@effect/opentelemetry": "4.0.0-rc.112",
+    "@effect/platform-node": "4.0.0-rc.112",
+    "@effect/platform-node-shared": "4.0.0-rc.112",
+    "@effect/sql-sqlite-bun": "4.0.0-rc.112",
     "@hono/standard-validator": "0.2.0",
     "@hono/zod-validator": "0.4.2",
     "@kobalte/core": "0.13.13",
@@ -1149,8 +1148,7 @@
     "dompurify": "3.4.14",
     "drizzle-kit": "1.0.0-rc.5-ab785fc",
     "drizzle-orm": "1.0.0-rc.5-169397b",
-    "effect": "4.0.0-rc.117",
-    "fast-check": "4.9.0",
+    "effect": "4.0.0-rc.112",
     "fuzzysort": "3.1.0",
     "get-east-asian-width": "1.6.0",
     "hono": "4.10.7",
@@ -1682,13 +1680,13 @@
 
     "@drizzle-team/brocli": ["@drizzle-team/brocli@0.12.0", "", {}, "sha512-mlUE+rZ8CatQekLhnaiN91Iemdd+e2gFKooGlnRB3oPTL3VghLfX24dx7HrzMNeC1JrIB/0kpsfyty3f5HNfxQ=="],
 
-    "@effect/opentelemetry": ["@effect/opentelemetry@4.0.0-rc.117", "", { "peerDependencies": { "@opentelemetry/api": ">=1.9.0 <2.0.0", "@opentelemetry/api-logs": ">=0.203.0 <0.300.0", "@opentelemetry/resources": ">=2.0.0 <3.0.0", "@opentelemetry/sdk-logs": ">=0.203.0 <0.300.0", "@opentelemetry/sdk-metrics": ">=2.0.0 <3.0.0", "@opentelemetry/sdk-trace-base": ">=2.0.0 <3.0.0", "@opentelemetry/sdk-trace-node": ">=2.0.0 <3.0.0", "@opentelemetry/sdk-trace-web": ">=2.0.0 <3.0.0", "@opentelemetry/semantic-conventions": ">=1.33.0 <2.0.0", "effect": "^4.0.0-rc.117" }, "optionalPeers": ["@opentelemetry/api", "@opentelemetry/api-logs", "@opentelemetry/resources", "@opentelemetry/sdk-logs", "@opentelemetry/sdk-metrics", "@opentelemetry/sdk-trace-base", "@opentelemetry/sdk-trace-node", "@opentelemetry/sdk-trace-web"] }, "sha512-IWAn2rU/RZLStkXfcdF1nGxcKQ7kbHct7N98T/5yOmSYiXvD8ZIxsGZhuAcRPPjc0NbNU2Ay8DZLPesyhJhUgA=="],
+    "@effect/opentelemetry": ["@effect/opentelemetry@4.0.0-rc.112", "", { "peerDependencies": { "@opentelemetry/api": ">=1.9.0 <2.0.0", "@opentelemetry/api-logs": ">=0.203.0 <0.300.0", "@opentelemetry/resources": ">=2.0.0 <3.0.0", "@opentelemetry/sdk-logs": ">=0.203.0 <0.300.0", "@opentelemetry/sdk-metrics": ">=2.0.0 <3.0.0", "@opentelemetry/sdk-trace-base": ">=2.0.0 <3.0.0", "@opentelemetry/sdk-trace-node": ">=2.0.0 <3.0.0", "@opentelemetry/sdk-trace-web": ">=2.0.0 <3.0.0", "@opentelemetry/semantic-conventions": ">=1.33.0 <2.0.0", "effect": "^4.0.0-rc.112" }, "optionalPeers": ["@opentelemetry/api", "@opentelemetry/api-logs", "@opentelemetry/resources", "@opentelemetry/sdk-logs", "@opentelemetry/sdk-metrics", "@opentelemetry/sdk-trace-base", "@opentelemetry/sdk-trace-node", "@opentelemetry/sdk-trace-web"] }, "sha512-OTRv1DxTHUmnakgJ6XVM8wVgF1KgZH4UXnOemwSLUwUjXO+RCikzF8oR/rlVmOGq81KtQzj1URM4M4nchlQOuQ=="],
 
-    "@effect/platform-node": ["@effect/platform-node@4.0.0-rc.117", "", { "dependencies": { "@effect/platform-node-shared": "^4.0.0-rc.117", "undici": "^8.10.2" }, "peerDependencies": { "effect": "^4.0.0-rc.117", "redis": ">=5.0.0 <7.0.0" } }, "sha512-WbPcvQDkqXFnCeG6LohJ9eVNapCDhZbCpezhYKxm0IsZEk7swakRh7RkC1t2CXzd3hGmszTv2k9e/pXyZuL+wQ=="],
+    "@effect/platform-node": ["@effect/platform-node@4.0.0-rc.112", "", { "dependencies": { "@effect/platform-node-shared": "^4.0.0-rc.112", "mime": "^4.1.0", "undici": "^8.10.0" }, "peerDependencies": { "effect": "^4.0.0-rc.112", "redis": ">=5.0.0 <7.0.0" } }, "sha512-/BMAcdNGQQskLmI0Zoa95KfTZkr9HV9N4NSxaSrusG6GeW6Ulp9KvZ+Rlaiw8lnOt43CXjFLdfll5/k5rxL4hQ=="],
 
-    "@effect/platform-node-shared": ["@effect/platform-node-shared@4.0.0-rc.117", "", { "dependencies": { "@types/ws": "^8.18.1", "ws": "^8.21.3" }, "peerDependencies": { "effect": "^4.0.0-rc.117" } }, "sha512-GyRkEfLBG49MwJe+/XDPiXYcQ44RA9p2z0AurlsWhR1cd1PqOUMEZU1pORL+/R5hR8aH6ZuqoJYD8lAc6h+wlA=="],
+    "@effect/platform-node-shared": ["@effect/platform-node-shared@4.0.0-rc.112", "", { "dependencies": { "@types/ws": "^8.18.1", "ws": "^8.21.3" }, "peerDependencies": { "effect": "^4.0.0-rc.112" } }, "sha512-ttjz0xKamFN7vL8pNDYVwddJLjZvqKePc05djlz2VcdaKbLsnYbtMnL1rbOfHgEnIUSHGh7FkjaN4DM1Ov81sQ=="],
 
-    "@effect/sql-sqlite-bun": ["@effect/sql-sqlite-bun@4.0.0-rc.117", "", { "peerDependencies": { "effect": "^4.0.0-rc.117" } }, "sha512-UjgkEmR+s5Rc870sDsDzu/8AA5KQqcBeq5qgH6AFe5OYfv3GCMfoQTkIvnl+Q3M5KaZosYgwwEy9uij/J2HOJw=="],
+    "@effect/sql-sqlite-bun": ["@effect/sql-sqlite-bun@4.0.0-rc.112", "", { "peerDependencies": { "effect": "^4.0.0-rc.112" } }, "sha512-EqR8pWZo3VzedRvP6qo5HcfqNmFvSa+sQLWQl3oBMx2KY1FCc8NYjep79wYjNkW0qABnffrPUXCMTOncd1A+5g=="],
 
     "@electron-internal/extract-zip": ["@electron-internal/extract-zip@1.0.5", "", {}, "sha512-+bqFCP98pLI0Tt0XQo1TmlXtwjWchISndDOxCkEcIuUgXWpBnLyRI+2DU+mesvnMMX6L1XDqYNA0lXNDHd/yiA=="],
 
@@ -2022,6 +2020,18 @@
 
     "@motionone/utils": ["@motionone/utils@10.18.0", "", { "dependencies": { "@motionone/types": "^10.17.1", "hey-listen": "^1.0.8", "tslib": "^2.3.1" } }, "sha512-3XVF7sgyTSI2KWvTf6uLlBJ5iAgRgmvp3bpuOiQJvInd4nZ19ET8lX5unn30SlmRH7hXbBbH+Gxd0m0klJ3Xtw=="],
 
+    "@msgpackr-extract/msgpackr-extract-darwin-arm64": ["@msgpackr-extract/msgpackr-extract-darwin-arm64@3.0.4", "", { "os": "darwin", "cpu": "arm64" }, "sha512-LCkGo6JDfaBhgST7UpPWgNgLINpcpabaHfyz5OBx75nUYxBsaEPxjnyNjWpeb/xBup/682QnBfRBy2/LvPutZQ=="],
+
+    "@msgpackr-extract/msgpackr-extract-darwin-x64": ["@msgpackr-extract/msgpackr-extract-darwin-x64@3.0.4", "", { "os": "darwin", "cpu": "x64" }, "sha512-zExlW9zUJKZH/tOtVMttwjKa4Xm/3KcNjnE3dPN92uCktwavMxpgCA3MoJK/DOnTWsQgo224OaST27/mPNAf+w=="],
+
+    "@msgpackr-extract/msgpackr-extract-linux-arm": ["@msgpackr-extract/msgpackr-extract-linux-arm@3.0.4", "", { "os": "linux", "cpu": "arm" }, "sha512-Tg3yX65f5GbtXLkrYEHE5oibZG9epyYWas7FogTTEJeDEF9JlXJzKgXaNhT3UXlTOeA+AfZpYZYZ0uPj7Cfquw=="],
+
+    "@msgpackr-extract/msgpackr-extract-linux-arm64": ["@msgpackr-extract/msgpackr-extract-linux-arm64@3.0.4", "", { "os": "linux", "cpu": "arm64" }, "sha512-dgX0P/9wGPJeHFBG+ZmhgE6bmtMt7NP5CRBGyyktpopdk/mW4POnrpQsSLtKI1dwpc+pPLuXHDh6vvskyQE/sw=="],
+
+    "@msgpackr-extract/msgpackr-extract-linux-x64": ["@msgpackr-extract/msgpackr-extract-linux-x64@3.0.4", "", { "os": "linux", "cpu": "x64" }, "sha512-8TNXMEjJc3QEy7R/x1INhgiU+XakDAFUzBhaz7+Rbrs8NH5UQeHQxxmzsSBJGyV6I1jW79undiQm8tOI+D+8FQ=="],
+
+    "@msgpackr-extract/msgpackr-extract-win32-x64": ["@msgpackr-extract/msgpackr-extract-win32-x64@3.0.4", "", { "os": "win32", "cpu": "x64" }, "sha512-CmCXPQrkbwExx3j946/PtHWHbYJiCRBRDl4BlkRQcJB/YOwQxJRTpoo7aTsortjgoJ1x7opzTSxn7C+ASSLVjQ=="],
+
     "@napi-rs/lzma-linux-x64-gnu": ["@napi-rs/lzma-linux-x64-gnu@1.5.1", "", { "os": "linux", "cpu": "x64" }, "sha512-oTXEIha4SsuXdTA4Iyskj0kpdx2yVXdhd75c2v3xGrHFfVMsbhTPZU/nMPL4sWKo4pBHm3aucLaqGlF696dTyQ=="],
 
     "@napi-rs/wasm-runtime": ["@napi-rs/wasm-runtime@1.2.3", "", { "dependencies": { "@tybys/wasm-util": "^0.10.3" }, "peerDependencies": { "@emnapi/core": "^1.7.1 || ^2.0.0-alpha.4", "@emnapi/runtime": "^1.7.1 || ^2.0.0-alpha.4" } }, "sha512-UMduMbqO5s5zF2NkNacMT/yK5Y5QiKvWr2+50bzIIxFDwVJ2h49b+oyjaCGPhJxd2/gC2x39EHv/gHVuu36x2Q=="],
@@ -3856,7 +3866,7 @@
 
     "editorconfig": ["editorconfig@1.0.7", "", { "dependencies": { "@one-ini/wasm": "0.1.1", "commander": "^10.0.0", "minimatch": "^9.0.1", "semver": "^7.5.3" }, "bin": { "editorconfig": "bin/editorconfig" } }, "sha512-e0GOtq/aTQhVdNyDU9e02+wz9oDDM+SIOQxWME2QRjzRX5yyLAuHDE+0aE8vHb9XRC8XD37eO2u57+F09JqFhw=="],
 
-    "effect": ["effect@4.0.0-rc.117", "", {}, "sha512-UUyi9QiOW4nySFIBM3KnYbNMd9EZliOdKfBcyLD0mPMPheO2fkuXS5y0opjWc9oqzlJxPQICEGm8gGw3kh9j/w=="],
+    "effect": ["effect@4.0.0-rc.112", "", { "dependencies": { "fast-check": "^4.9.0", "msgpackr": "^2.0.5" } }, "sha512-wXxwuh1Ywnv4cPRM3Wfa0vDwuOHnZ1TsTgHJkG9XgzND6inhBH9n1vBxhg3iIXOia/OrpmvVmd3lrD4vq6bF3A=="],
 
     "ejs": ["ejs@3.1.10", "", { "dependencies": { "jake": "^10.8.5" }, "bin": { "ejs": "bin/cli.js" } }, "sha512-UeJmFfOrAQS8OJWPZ4qtgHyWExa088/MtK5UEyoJGFH67cDEXkZSviOiKRCZ4Xij0zxI3JECgYs3oKx+AizQBA=="],
 
@@ -4694,7 +4704,7 @@
 
     "micromatch": ["micromatch@4.0.8", "", { "dependencies": { "braces": "^3.0.3", "picomatch": "^2.3.1" } }, "sha512-PXwfBhYu0hBCPw8Dn0E+WDYb7af3dSLVWKi3HGv84IdF4TyFoC0ysxFd0Goxw7nSv4T/PzEJQxsYsEiFCKo2BA=="],
 
-    "mime": ["mime@3.0.0", "", { "bin": { "mime": "cli.js" } }, "sha512-jSCU7/VB1loIWBZe14aEYHU/+1UMEHoaO7qxCOVJOw9GgH72VAWppxNcjU+x9a2k3GSIBXNKxXQFqRvvZ7vr3A=="],
+    "mime": ["mime@4.1.0", "", { "bin": { "mime": "bin/cli.js" } }, "sha512-X5ju04+cAzsojXKes0B/S4tcYtFAJ6tTMuSPBEn9CPGlrWr8Fiw7qYeLT0XyH80HSoAoqWCaz+MWKh22P7G1cw=="],
 
     "mime-db": ["mime-db@1.54.0", "", {}, "sha512-aU5EJuIN2WDemCcAp2vFBfp/m4EAhWJnUNSSw0ixs7/kXbd6Pg64EmwJkNdFhB8aWt1sH2CTXrLxo/iAGV3oPQ=="],
 
@@ -4742,6 +4752,10 @@
 
     "ms": ["ms@2.1.3", "", {}, "sha512-6FlzubTLZG3J2a/NVCAleEhjzq5oxgHyaCU9yYXvcLsvoVaHJq/s5xXI6/XXP6tz7R9xAOtHnSO/tXtF3WRTlA=="],
 
+    "msgpackr": ["msgpackr@2.0.5", "", { "optionalDependencies": { "msgpackr-extract": "^3.0.4" } }, "sha512-cef05H/dSYpLpqp3sj/qyZh5vhUYCalnaLO7j1yOmpsR0y/XwLVtK7r5gn+U/F7CTEfMowcGhlUQJDLcLf7jcA=="],
+
+    "msgpackr-extract": ["msgpackr-extract@3.0.4", "", { "dependencies": { "node-gyp-build-optional-packages": "5.2.2" }, "optionalDependencies": { "@msgpackr-extract/msgpackr-extract-darwin-arm64": "3.0.4", "@msgpackr-extract/msgpackr-extract-darwin-x64": "3.0.4", "@msgpackr-extract/msgpackr-extract-linux-arm": "3.0.4", "@msgpackr-extract/msgpackr-extract-linux-arm64": "3.0.4", "@msgpackr-extract/msgpackr-extract-linux-x64": "3.0.4", "@msgpackr-extract/msgpackr-extract-win32-x64": "3.0.4" }, "bin": { "download-msgpackr-prebuilds": "bin/download-prebuilds.js" } }, "sha512-4kmO/MdyUIkLIvTPr8VHLil4AtoKIoniWPIEk5+CDy0xnWC84azhSFmuJ7PxZdsYtiP5kEeQsORAVIeMgxT+Hw=="],
+
     "muggle-string": ["muggle-string@0.4.1", "", {}, "sha512-VNTrAak/KhO2i8dqqnqnAHOa3cYBwXEZe9h+D5h/1ZqFSTEFHdM65lR7RoIqq3tBBYavsOXV84NoHXZ0AkPyqQ=="],
 
     "mustache": ["mustache@4.2.0", "", { "bin": { "mustache": "bin/mustache" } }, "sha512-71ippSywq5Yb7/tVYyGbkBggbU8H3u5Rz56fH60jGFgr8uHwxs+aSKeqmluIVzM0m0kB7xQjKS6qPfd0b2ZoqQ=="],
@@ -4784,6 +4798,8 @@
 
     "node-gyp-build": ["node-gyp-build@4.8.4", "", { "bin": { "node-gyp-build": "bin.js", "node-gyp-build-optional": "optional.js", "node-gyp-build-test": "build-test.js" } }, "sha512-LA4ZjwlnUblHVgq0oBF3Jl/6h/Nvs5fzBLwdEF4nuxnFdsfajde4WfxtJr3CaiH+F6ewcIB/q4jQ4UzPyid+CQ=="],
 
+    "node-gyp-build-optional-packages": ["node-gyp-build-optional-packages@5.2.2", "", { "dependencies": { "detect-libc": "^2.0.1" }, "bin": { "node-gyp-build-optional-packages": "bin.js", "node-gyp-build-optional-packages-optional": "optional.js", "node-gyp-build-optional-packages-test": "build-test.js" } }, "sha512-s+w+rBWnpTMwSFbaE0UXsRlg7hU4FjekKU4eyAih5T8nJuNZT1nNsskXpxmeqSK9UzkBl6UgRlnKc8hz8IEqOw=="],
+
     "node-html-parser": ["node-html-parser@7.1.0", "", { "dependencies": { "css-select": "^5.1.0", "he": "1.2.0" } }, "sha512-iJo8b2uYGT40Y8BTyy5ufL6IVbN8rbm/1QK2xffXU/1a/v3AAa0d1YAoqBNYqaS4R/HajkWIpIfdE6KcyFh1AQ=="],
 
     "node-int64": ["node-int64@0.4.0", "", {}, "sha512-O5lz91xSOeoXP6DulyHfllpq+Eg00MWitZIbtPfoSEvqIHdl5gfcY6hYzDWnj0qD5tz52PI08u9qUvSVeUBeHw=="],
@@ -5580,7 +5596,7 @@
 
     "uncrypto": ["uncrypto@0.1.3", "", {}, "sha512-Ql87qFHB3s/De2ClA9e0gsnS6zXG27SkTiSJwjCc9MebbfapQfuPzumMIUMi38ezPZVNFcHI9sUIepeQfw8J8Q=="],
 
-    "undici": ["undici@8.10.2", "", {}, "sha512-/y4/bH9YNU5hi9NIrpOuvGXFcxrj3CMrV+/AYpowAYTpHn8gX/XPFjNy766FPoYY0miQhdW977JFWKGNhBdwyQ=="],
+    "undici": ["undici@8.10.0", "", {}, "sha512-HvltHd7avK13QIw/oLe4qoOLyoVSoafqJ2jYOrtMRBkbYT31eiBQ8O0ehRKZiEZCMEyLFQNIADpgCWC5fALvYQ=="],
 
     "undici-types": ["undici-types@7.16.0", "", {}, "sha512-Zz+aZWSj8LE6zoxD+xrjh4VfkIG8Ya6LvYkZqtUQGJPZjYl53ypCaUwWqo7eI0x66KBGeRo+mlBEkMSeSZ38Nw=="],
 
@@ -6032,6 +6048,8 @@
 
     "@bufbuild/protoplugin/typescript": ["typescript@5.4.5", "", { "bin": { "tsc": "bin/tsc", "tsserver": "bin/tsserver" } }, "sha512-vcI4UpRgg81oIRUFwR0WSIHKt11nJ7SAVlYNIu+QpqeyXP+gpQJy/Z4+F0aGxSE4MqwjyXvW/TzgkLAx2AGHwQ=="],
 
+    "@cloudflare/kv-asset-handler/mime": ["mime@3.0.0", "", { "bin": { "mime": "cli.js" } }, "sha512-jSCU7/VB1loIWBZe14aEYHU/+1UMEHoaO7qxCOVJOw9GgH72VAWppxNcjU+x9a2k3GSIBXNKxXQFqRvvZ7vr3A=="],
+
     "@cloudflare/vite-plugin/vite": ["vite@7.3.6", "", { "dependencies": { "esbuild": "^0.27.0 || ^0.28.0", "fdir": "^6.5.0", "picomatch": "^4.0.3", "postcss": "^8.5.6", "rollup": "^4.43.0", "tinyglobby": "^0.2.15" }, "optionalDependencies": { "fsevents": "~2.3.3" }, "peerDependencies": { "@types/node": "^20.19.0 || >=22.12.0", "jiti": ">=1.21.0", "less": "^4.0.0", "lightningcss": "^1.21.0", "sass": "^1.70.0", "sass-embedded": "^1.70.0", "stylus": ">=0.54.8", "sugarss": "^5.0.0", "terser": "^5.16.0", "tsx": "^4.8.1", "yaml": "^2.4.2" }, "optionalPeers": ["@types/node", "jiti", "less", "lightningcss", "sass", "sass-embedded", "stylus", "sugarss", "terser", "tsx", "yaml"], "bin": { "vite": "bin/vite.js" } }, "sha512-4XP60spRGjSZFf1qYH+dJIkK2znL3zQfl9KkOV9MkkRR/3Dls0dxaBsQPTloEc5BLXWPL9vsOxopxyKoMmDueg=="],
 
     "@cloudflare/vite-plugin/ws": ["ws@8.18.0", "", { "peerDependencies": { "bufferutil": "^4.0.1", "utf-8-validate": ">=5.0.2" }, "optionalPeers": ["bufferutil", "utf-8-validate"] }, "sha512-8VbfWfHLbbwu3+N6OKsOMpBdT4kXPDDB9cJk2bJ6mh9ucxdlnNvH1e+roYkKmN9Nxw2yjz7VzeO9oOz2zJ04Pw=="],
@@ -6632,8 +6650,6 @@
 
     "tw-to-css/tailwindcss": ["tailwindcss@3.3.2", "", { "dependencies": { "@alloc/quick-lru": "^5.2.0", "arg": "^5.0.2", "chokidar": "^3.5.3", "didyoumean": "^1.2.2", "dlv": "^1.1.3", "fast-glob": "^3.2.12", "glob-parent": "^6.0.2", "is-glob": "^4.0.3", "jiti": "^1.18.2", "lilconfig": "^2.1.0", "micromatch": "^4.0.5", "normalize-path": "^3.0.0", "object-hash": "^3.0.0", "picocolors": "^1.0.0", "postcss": "^8.4.23", "postcss-import": "^15.1.0", "postcss-js": "^4.0.1", "postcss-load-config": "^4.0.1", "postcss-nested": "^6.0.1", "postcss-selector-parser": "^6.0.11", "postcss-value-parser": "^4.2.0", "resolve": "^1.22.2", "sucrase": "^3.32.0" }, "bin": { "tailwind": "lib/cli.js", "tailwindcss": "lib/cli.js" } }, "sha512-9jPkMiIBXvPc2KywkraqsUfbfj+dHDb+JPWtSJa9MLFdrPyazI7q6WX2sUrm7R9eVR7qqv3Pas7EvQFzxKnI6w=="],
 
-    "unifont/undici": ["undici@8.10.0", "", {}, "sha512-HvltHd7avK13QIw/oLe4qoOLyoVSoafqJ2jYOrtMRBkbYT31eiBQ8O0ehRKZiEZCMEyLFQNIADpgCWC5fALvYQ=="],
-
     "unplugin/acorn": ["acorn@8.18.0", "", { "bin": { "acorn": "bin/acorn" } }, "sha512-lGq+9yr1/GuAWaVYIHRjvvySG5/4VfKIvC8EWxStPdcDh/Ka7FG3twP6v4d5BkravUilhIAsG4Qj83t02LWUPQ=="],
 
     "unused-filename/escape-string-regexp": ["escape-string-regexp@5.0.0", "", {}, "sha512-/veY75JbMK4j1yjvuUxuVsiS/hr/4iHs9FTT6cgTexxdE0Ly/glccBAkloH/DofkjRbZU3bnoj38mOmhkZ0lHw=="],

flake.lock

@@ -2,11 +2,11 @@
   "nodes": {
     "nixpkgs": {
       "locked": {
-        "lastModified": 1776683584,
-        "narHash": "sha256-NuTLMrr10Tng72hurYG8jYQ4XKK8wnpJmOGcPiis96g=",
+        "lastModified": 1790510107,
+        "narHash": "sha256-EVMNYv7hYDDD9TGVT/hIyTYgpiXA8y3m5xIEIxuGNU0=",
         "owner": "NixOS",
         "repo": "nixpkgs",
-        "rev": "9dd5558b06dbdacbf635a3dd36dce1b1a7ee3a89",
+        "rev": "3181085bfd08663b6b9e60bc7a8395c2aaa741bd",
         "type": "github"
       },
       "original": {

package.json

@@ -42,10 +42,10 @@
       "packages/stats/*"
     ],
     "catalog": {
-      "@effect/opentelemetry": "4.0.0-rc.117",
-      "@effect/platform-node": "4.0.0-rc.117",
-      "@effect/platform-node-shared": "4.0.0-rc.117",
-      "@effect/sql-sqlite-bun": "4.0.0-rc.117",
+      "@effect/opentelemetry": "4.0.0-rc.112",
+      "@effect/platform-node": "4.0.0-rc.112",
+      "@effect/platform-node-shared": "4.0.0-rc.112",
+      "@effect/sql-sqlite-bun": "4.0.0-rc.112",
       "@npmcli/arborist": "9.4.0",
       "@types/bun": "1.4.0",
       "@types/cross-spawn": "6.0.6",
@@ -79,8 +79,7 @@
       "dompurify": "3.4.14",
       "drizzle-kit": "1.0.0-rc.5-ab785fc",
       "drizzle-orm": "1.0.0-rc.5-169397b",
-      "effect": "4.0.0-rc.117",
-      "fast-check": "4.9.0",
+      "effect": "4.0.0-rc.112",
       "ai": "6.0.168",
       "cross-spawn": "7.0.6",
       "hono": "4.10.7",

packages/ai/AGENTS.md

@@ -98,11 +98,11 @@ When a provider supports multiple physical transports, selection remains executi
 
 Media does not fit the SSE-frames-to-event-state-machine LLM route. `MediaRoute.inline(...)` / `queued(...)` / `stream(...)` (`src/route/media.ts`) compose a `MediaProtocol` kind with `Endpoint` and `Auth` and own the transport plumbing: `http` option merging, URL/query rendering, auth headers, JSON vs multipart encoding, and handing the response back to the protocol. `MediaProtocol.inline` (`src/route/media-protocol.ts`) is `body.from(request)` plus `response.decode(response, context)`; each protocol declares `const route = MediaProtocol.identity({ id, name, provider })` once and decodes through `route.decodeJson` / `route.text` / `route.decodeStarted` so decode failures retain the raw body and HTTP context, raising `route.unsupported(operation, message)` for requests it cannot lower, and passes `route` as the first argument to `MediaProtocol.inline` / `queued` / `stream`. `Generation` (`src/generation.ts`) is the provider-neutral handle for a queued generation over a `GenerationRoute` (`status`, `result`, `cancel`). Image protocol files follow the same section order as LLM protocols and declare unsupported common fields once through the protocol's `unsupported` list.
 
-`MediaProtocol.queued` is the submit-then-poll kind every video route uses: `start` (body + decode into `{ token, snapshot }`), `status`, `result`, and optional `cancel` (with `activeOnly` when the provider's cancel endpoint deletes finished work, as Runway's does: the route refreshes status first and skips terminal generations), each addressed by a route-owned `token` whose `Schema.Codec` makes it serializable. `MediaRoute.inline` and `MediaRoute.queued` compose the two kinds with `Endpoint` and `Auth`; the queued route decodes the token once at the boundary (`start` output or `resume` input) and closes over it in a token-free `GenerationRoute` (`status`/`result`/`cancel` are plain Effects), so `Generation` never sees the token's shape and only carries the encoded JSON for persistence. Polls reuse the route's auth and deployment headers plus the request's `http` overlay after `start`, and resolve relative paths against the route base URL (provider-issued absolute URLs such as fal's `status_url` pass through). `result` is always its own GET even when the provider returns output inside the status document, so `Generation.await` behaves the same after `start` and after `resume`. `PollContext.auth` carries only what `Auth` added or changed so protocols can hand download credentials to output assets as transient `Media.Asset.headers` (Veo) — never part of `source` or JSON. Status strings map through a per-protocol `STATUS` table via `MediaProtocol.status`; terminal generations without output fail through `output.ended` / `output.contentPolicy` with the provider document on `reason.body`. `GenerationAwaitOptions` (`AwaitOptions` in `src/generation.ts`, `{ poll?: Poll }`) is the one options type for `await`, `events`, `Video.generate`, and `Video.stream`.
+`MediaProtocol.queued` is the submit-then-poll kind every video route uses: `start` (body + decode into `{ token, snapshot }`), `status`, `result`, and optional `cancel` (with `activeOnly` when the provider's cancel endpoint deletes finished work, as Runway's does: the route refreshes status first and skips terminal generations), each addressed by a route-owned `token` whose `Schema.Codec` makes it serializable. `MediaRoute.inline` and `MediaRoute.queued` compose the two kinds with `Endpoint` and `Auth`; the queued route decodes the token once at the boundary (`start` output or `resume` input) and closes over it in a token-free `GenerationRoute` (`status`/`result`/`cancel` are plain Effects), so `Generation` never sees the token's shape and only carries the encoded JSON for persistence. Polls reuse the route's auth and deployment headers plus the request's `http` overlay after `start`, and resolve relative paths against the route base URL (provider-issued absolute URLs such as fal's `status_url` pass through). `result` is always its own GET even when the provider returns output inside the status document, so `Generation.await` behaves the same after `start` and after `resume`. `PollContext.auth` carries only what `Auth` added or changed so protocols can hand download credentials to output assets as transient `Media.Asset.headers` (Veo) — never part of `source` or JSON. Status strings map through a per-protocol `STATUS` table via `MediaProtocol.status`; terminal generations without output fail through `output.ended` / `output.contentPolicy` with the provider document on `reason.body`; a `failed` generation maps the provider's error code through a per-protocol `FAILURE` table via `MediaProtocol.failure` so rejected inputs are not reported as retryable `ProviderInternal`. `GenerationAwaitOptions` (`AwaitOptions` in `src/generation.ts`, `{ poll?: Poll }`) is the one options type for `await`, `events`, `Video.generate`, and `Video.stream`.
 
 `MediaProtocol.stream` is the incremental kind every speech route uses, with the same discipline as LLM protocols. `MediaRoute.stream` submits the caller's request as `MediaProtocol.Addressed<Request>` (`{ ...request, mode }`, `mode: "generate" | "stream"`), so one provider stays one protocol: `body.from`, the endpoint path, and `frames` read `request.mode` to pick the body, path, and framing. `frames(bytes, context)` returns frames — `Framing.sse`, `Framing.lines`, `Framing.document` (a single-document response shaped like a streamed record), or the raw `bytes` for chunked audio. `initial()` is fresh per-response parser state; `step` folds each frame into it and emits modality events; `finish(state, context)` runs once after the last frame with the request, body, and observed `http` (header-only usage lives there) and emits exactly one terminal event or fails with `route.incomplete()`. Keep parser state to real accumulators and derive anything the request or body determines in `finish`. `generate` runs the same stream and folds it with the modality's `collect`. Request-derived URL parameters go on the body's `query` (array values repeat the parameter), applied before route and caller `http.query`. Decode frames with `route.decodeFrame` and raise stream-time failures with `route.frameError` (the frame stays on `reason.body`); protocols never thread HTTP context, because the route fills `reason.http` on stream errors that lack it. Speech protocols share `protocols/utils/speech-stream.ts` for deltas, timestamps, voice ids, PCM and container descriptions, and the terminal asset.
 
-Every modality route is the inline | stream | queued union (transcription uses all three: OpenAI and Gemini stream, Deepgram is inline, AssemblyAI is queued), every client is `MediaClient.make(Service, { modality, responseEvents })` (`src/media-client.ts`), which dispatches on the route's `kind`, and every model composes through `composeRoute`. fal queue protocols come from `protocols/utils/fal-queue.ts`, bodies are `json`, `multipart`, or `binary` (a raw upload), and a queued protocol that must upload media before submitting implements `start.prepare` (`MediaProtocol.Prepare`; AssemblyAI `/v2/upload`).
+Every modality route is the inline | stream | queued union (transcription uses all three: OpenAI and Gemini stream, Deepgram and ElevenLabs are inline, AssemblyAI is queued), every client is `MediaClient.make(Service, { modality, responseEvents })` (`src/media-client.ts`), which dispatches on the route's `kind`, and every model composes through `composeRoute`. fal queue protocols come from `protocols/utils/fal-queue.ts`, bodies are `json`, `multipart`, or `binary` (a raw upload), and a queued protocol that must upload media before submitting implements `start.prepare` (`MediaProtocol.Prepare`; AssemblyAI `/v2/upload`).
 
 ### URL Construction
 

packages/ai/README.md

@@ -129,8 +129,9 @@ VercelAIGateway.configure().experimental.evaluation("typesafe-ai/jev")
 
 OpenRouter reads `OPENROUTER_API_KEY`. Vercel reads `AI_GATEWAY_API_KEY`, then `VERCEL_OIDC_TOKEN`.
 The common API uses `boolean`; System One routes lower it to native `noul`.
-Choice and score confidence plus score legends remain available in provider metadata, and the
-provider's rounded probabilities are returned unchanged.
+Choice and score answers include `confidence` when the provider returns it, such as
+`response.answers.department.confidence`. Score legends remain available in provider metadata, and
+the provider's rounded probabilities are returned unchanged.
 
 ## Alibaba Cloud Model Studio
 
@@ -752,7 +753,10 @@ const events = Video.stream({ model: Runway.configure({ apiKey }).video("gen4.5"
 
 Status polls, result fetches, cancels, and asset downloads all run through the same request executor with the route's
 auth. `Generation.await` and `Generation.events` fail with a
-`Timeout` reason when `poll.timeout` (default 10 minutes) elapses. Failed,
+`Timeout` reason when `poll.timeout` (default 10 minutes) elapses. Status polls and result fetches retry transient
+failures (rate limits, provider 5xx, network errors) with backoff that honors `retry-after`, always within
+`poll.timeout`; submits and cancels never retry. Interrupting a wait (or aborting its `signal`) does not cancel the
+provider job, which keeps running and billing: call `cancel()` to stop it. Failed,
 cancelled, and expired generations fail typed with the provider's terminal document on `reason.body`; moderation
 outcomes (Veo `raiMediaFilteredReasons`, xAI `respect_moderation`, Runway `SAFETY.*` codes) surface as `notices` when
 a video is still returned and as a `ContentPolicy` reason when nothing is.
@@ -773,7 +777,9 @@ Provider notes:
 The promise client exposes the same surface: `ai.video.start(...)` resolves to a handle with `await`, `events`,
 `result`, `refresh`, `cancel`, and `token`; `ai.video.generate`, `ai.video.resume(model, token)`, and
 `ai.video.stream` mirror the Effect API. The handle's `status` and `progress` are a snapshot from when it was
-created; `refresh()` resolves to a new handle.
+created; `refresh()` resolves to a new handle. Every promise method and stream accepts `{ signal }`: like `fetch`,
+aborting rejects the Promise or throws from the `for await` loop with `signal.reason` (an `AbortError` `DOMException`
+unless `abort(reason)` passed one), while `break` stops a stream without throwing.
 
 ```ts
 import { ai } from "@opencode/ai/promise"
@@ -871,11 +877,12 @@ for await (const event of ai.speech.stream({ model, text: "Hello from OpenCode."
 ## Transcription
 
 Transcription (speech-to-text) is the one modality whose providers use every route kind: OpenAI and Gemini stream,
-Deepgram answers inline, and AssemblyAI is queued. `Transcription.generate` and `Transcription.stream` work on all of
-them; `Transcription.start` / `resume` return a `Generation` on queued routes and fail with `UnsupportedOperation`
-elsewhere. Models come from `.transcription(...)` selectors on the `OpenAI`, `Google`, `Deepgram`, and `AssemblyAI`
-facades. Common fields (`language`, `prompt`, `timestamps: "none" | "segment" | "word"`, `diarize`, `speakers`) lower
-natively or fail with a typed `AIError` before any network call; a route may return more than asked.
+Deepgram and ElevenLabs answer inline, and AssemblyAI is queued. `Transcription.generate` and `Transcription.stream`
+work on all of them; `Transcription.start` / `resume` return a `Generation` on queued routes and fail with
+`UnsupportedOperation` elsewhere. Models come from `.transcription(...)` selectors on the `OpenAI`, `Google`,
+`Deepgram`, `ElevenLabs`, and `AssemblyAI` facades. Common fields (`language`, `prompt`,
+`timestamps: "none" | "segment" | "word"`, `diarize`, `speakers`) lower natively or fail with a typed `AIError` before
+any network call; a route may return more than asked.
 
 ```ts
 import { Console, Effect, Stream } from "effect"
@@ -887,7 +894,7 @@ const openai = OpenAI.configure({ apiKey: process.env.OPENAI_API_KEY })
 const program = Effect.gen(function* () {
   const audio = yield* Media.file("./call.mp3")
 
-  // Speaker-labelled segments; labels are provider-native strings ("A", "0", "spk:0").
+  // Speaker-labelled segments; labels are provider-native strings ("A", "0", "spk:0", "speaker_0").
   const response = yield* Transcription.generate({
     model: Deepgram.configure({ apiKey }).transcription("nova-3"),
     audio,
@@ -897,7 +904,7 @@ const program = Effect.gen(function* () {
   response.text // "Hello from OpenCode."
   response.segments // [{ text, startSeconds, endSeconds, speaker: "0" }]
   response.words // [{ text, startSeconds, endSeconds, speaker, confidence }]
-  response.language // the provider's own value, lowercased ("en", "english", "en_us")
+  response.language // the provider's own value, lowercased ("en", "eng", "english", "en_us")
 
   // Text deltas as the model transcribes, then one finish carrying the whole transcript.
   yield* Transcription.stream({ model: openai.transcription("gpt-4o-mini-transcribe"), audio }).pipe(
@@ -921,7 +928,12 @@ Provider notes:
 - **OpenAI** takes inline audio only; `diarize` needs `gpt-4o-transcribe-diarize`, timestamps need `whisper-1`, and `whisper-1` does not stream.
 - **Gemini** needs a transcribe model (`gemini-3.5-transcribe`); `prompt` and `speakers` fail typed.
 - **Deepgram** detects the language unless `language` is set; vocabulary goes in `providerOptions.keyterm`.
-- **AssemblyAI** uploads inline audio before submitting and is the only route that accepts `speakers`.
+- **ElevenLabs** (`scribe_v2`) uploads inline audio as the multipart `file` and sends a URL as `source_url`. Words
+  always carry timestamps, and segments are speaker turns, so `diarize`, `timestamps: "segment"`, or `speakers` turns
+  on diarization. `speakers` is an upper bound (`num_speakers`); `prompt` fails typed (vocabulary goes in
+  `providerOptions.keyterms`), as do webhook delivery and per-channel output (`use_multi_channel` without
+  `multichannel_output_style: "combined"`).
+- **AssemblyAI** uploads inline audio before submitting and treats `speakers` as the exact speaker count.
 
 The promise client mirrors the Effect API:
 

packages/ai/docs/media-design.md

@@ -1,7 +1,6 @@
 # Media generation in `@opencode/ai` — public API direction
 
-Status: phases 1–4 implemented (through Image queued routes and partial images; ElevenLabs Scribe transcription
-pending); phase 5 proposal.
+Status: phases 1–4 implemented (through Image queued routes and partial images); phase 5 proposal.
 
 ## Goal
 
@@ -271,8 +270,8 @@ Deferred: `Speech.session(...)` — input-streaming TTS where text arrives incre
 #### Transcription (STT)
 
 Shipped as the second half of phase 3 (`src/transcription.ts`, `src/transcription-client.ts`, protocols
-`openai-transcription`, `google-transcription`, `deepgram-transcription`, `assemblyai-transcription`; new `AssemblyAI`
-facade).
+`openai-transcription`, `google-transcription`, `deepgram-transcription`, `elevenlabs-transcription`,
+`assemblyai-transcription`; new `AssemblyAI` facade).
 
 ```ts
 const request = Transcription.request({
@@ -281,7 +280,7 @@ const request = Transcription.request({
   language: "en",                                  // provider-native passthrough
   timestamps: "segment",                           // none | segment | word
   diarize: true,
-  speakers: 2,                                     // exact speaker count (AssemblyAI only)
+  speakers: 2,                                     // speaker count (AssemblyAI exact, ElevenLabs maximum)
   providerOptions: { known_speaker_names: ["agent"] },
 })
 
@@ -309,17 +308,23 @@ upload); `packages/ai/AGENTS.md` (Media Routes) describes both.
 Settled rules:
 
 - **Timestamps.** A granularity the selected route or model cannot produce fails as `UnsupportedOperation`
-  (`media.timestamps`), following Speech; a route that returns more than asked (Deepgram and AssemblyAI always return
-  words) is not stripped. Segments always carry start and end times: Gemini times each transcription part from its
+  (`media.timestamps`), following Speech; a route that returns more than asked (Deepgram, ElevenLabs, and AssemblyAI
+  always return words) is not stripped. Segments always carry start and end times: Gemini times each transcription part from its
   word offsets, so segment timestamps and diarization also request word offsets there.
 - **Diarization.** `diarize` means segments (and words, where the provider labels them) carry `speaker`. Labels are
-  provider-native strings — OpenAI `A` or a known speaker name, Deepgram `0`, Gemini `spk:0`, AssemblyAI `A` — with no
-  cross-provider speaker model. `speakers` is the exact number of speakers to label, which AssemblyAI (`speakers_expected`, the only route that
-  accepts it) treats as a constraint rather than a hint.
+  provider-native strings — OpenAI `A` or a known speaker name, Deepgram `0`, Gemini `spk:0`, AssemblyAI `A`,
+  ElevenLabs `speaker_0` — with no cross-provider speaker model. `speakers` is the number of speakers to label:
+  AssemblyAI (`speakers_expected`) treats it as an exact constraint rather than a hint, and ElevenLabs
+  (`num_speakers`) as the maximum. Both turn on diarization for it; the other routes reject it.
+- **Segments from words.** ElevenLabs returns only a token list (`word`, `spacing`, `audio_event`), so its segments
+  are speaker turns: consecutive words and spacing with one `speaker_id`, text joined from the provider's own spacing
+  tokens. `words` drops spacing and audio events. Segments therefore need diarization, which `timestamps: "segment"`
+  turns on, as AssemblyAI's utterances need speaker labels.
 - **Language** is passed through (`language`, OpenAI `gpt-transcribe` `languages[]`, Gemini `languageCodes`,
-  AssemblyAI `language_code`). `response.language` is the provider's own value, lowercased but not normalized: an
-  ISO code on most routes (AssemblyAI's detection returns `en`), `english` from whisper-1. Deepgram and AssemblyAI
-  assume English unless asked to detect, so a missing `language` enables their detection.
+  AssemblyAI and ElevenLabs `language_code`). `response.language` is the provider's own value, lowercased but not
+  normalized: an ISO code on most routes (AssemblyAI's detection returns `en`, ElevenLabs ISO 639-3 `eng`), `english`
+  from whisper-1. Deepgram and AssemblyAI assume English unless asked to detect, so a missing `language` enables their
+  detection.
 - **Gemini** requires a transcribe model; other model ids fail with `UnsupportedOperation` before the call, because
   general models ignore `audioTranscriptionConfig` and answer conversationally. Streamed chunks carry whole speaker
   turns (one part per turn), which join with a space.
@@ -332,11 +337,12 @@ Settled rules:
 | OpenAI | stream (`stream: true` in `stream` mode; `whisper-1` ignores `stream`, so it emits only `finish`) | multipart `file` (inline only) | `whisper-1` (`verbose_json`); diarize model: `segment` | `gpt-4o-transcribe-diarize` (`diarized_json`) | `speakers`; `prompt` on the diarize model | `tokens` or `seconds` |
 | Gemini | stream (`generateContent` / `streamGenerateContent`) | `inlineData` or Gemini Files `fileData` | `audioTranscriptionConfig.wordTimestamp` | `audioTranscriptionConfig.diarization` | `prompt`, `speakers` | `tokens` |
 | Deepgram | inline | raw body, or JSON `{ url }` | words always; `segment` → `utterances` | `diarize_model=latest` + `utterances` | `prompt`, `speakers` | `seconds` (`metadata.duration`) |
+| ElevenLabs | inline | multipart `file`, or `source_url` | words always; `segment` → `diarize` (speaker turns) | `diarize` | `prompt`; `webhook`, per-channel `use_multi_channel` | `seconds` (`audio_duration_secs`) |
 | AssemblyAI | queued (upload → submit → poll) | `/v2/upload` then `audio_url`, or a URL | words always; `segment` → `speaker_labels` | `speaker_labels` | — | `seconds` (`audio_duration`) |
 
 Deferred: `Transcription.session(...)` — realtime STT over WebSocket (Deepgram live, AssemblyAI streaming, ElevenLabs
 realtime, OpenAI realtime transcription) — is the same future scoped `session` shape as input-streaming TTS and ships
-with the realtime work in phase 5. ElevenLabs Scribe is not implemented yet.
+with the realtime work in phase 5.
 
 ### `Generation` — shared async execution
 
@@ -361,6 +367,10 @@ Poll = { interval?: Duration; timeout?: Duration }
 
 `Generation` is not video-specific. Image routes on BFL, fal, Replicate, and Stability `upscale()` are queued; `Image.start` exists for them. A route declares itself `inline` or `queued`; `generate` on a queued route is `start` then `await`.
 
+Status polls and result reads retry transient failures (rate limits, provider 5xx, and transport errors, classified by the same `isRetryable` the Session runner uses) inside `MediaRoute.queued`. Only the HTTP exchange retries, never the decoded document: a terminal `failed` generation also surfaces as `ProviderInternal` and must not be re-read. Gaps grow exponentially from 1s with jitter, up to 30s each, honoring a provider `retry-after` up to that cap, for at most 8 retries. `await`, `events`, and `Video.stream` cut retries off at `poll.timeout` and fail with `Timeout`, so retries never extend the caller's deadline; a direct `result()` or `resume` read is bounded by the retry cap alone. `start` and `cancel` never retry: a repeated submit can start and bill a second job. The policy is internal; there is no option for it.
+
+Interrupting `await`, `events`, or `Video.stream` (or aborting the promise API's `signal`) stops waiting only. The provider job keeps running and billing; call `cancel()` explicitly to stop it.
+
 ### Usage
 
 ```ts
@@ -402,7 +412,7 @@ for await (const event of ai.llm.stream(request)) { … }
 await ai.dispose()
 ```
 
-Streams become `AsyncIterable` via `Stream.toAsyncIterable`. `AIError` is thrown as-is. `AbortSignal` maps to interruption. Nothing in `src/*` except this entrypoint knows about promises.
+Streams become `AsyncIterable` via `Stream.toAsyncIterable`. `AIError` is thrown as-is. Aborting an `AbortSignal` interrupts the work and, like `fetch`, rejects the Promise or throws from the stream with `signal.reason` instead of ending the stream as if complete. Nothing in `src/*` except this entrypoint knows about promises.
 
 ### Providers
 
@@ -414,7 +424,7 @@ implemented):
 | `OpenAI` | responses (default), chat | Images API (stream) | *Sora skipped (decision 8)* | ✓ | ✓ | |
 | `Google` | Gemini | Gemini-native | Veo | Gemini TTS | `gemini-3.5-transcribe` | |
 | `XAI` | ✓ | ✓ | ✓ | | | |
-| `ElevenLabs` | | | | ✓ | *Scribe (pending)* | *soundEffect, music (phase 5)* |
+| `ElevenLabs` | | | | ✓ | Scribe | *soundEffect, music (phase 5)* |
 | `Cartesia` | | | | ✓ | | |
 | `Deepgram` | | | | Aura | ✓ | |
 | `Fal` | | ✓ (queued) | ✓ | | | |
@@ -467,7 +477,7 @@ Foundation + Image ship together as the reference implementation, serially. Vide
 
 1. **Foundation** — per-modality selectors, `Media`, `Generation`, `Poll`, `Usage` union, `MediaProtocol` kinds, `@opencode/ai/promise` with `llm` + `image`. Port the five existing image protocols onto it. Unify `MediaPart` and add the `media` LLM event (fixes Gemini image output being dropped).
 2. **Video** — ✅ Veo, xAI, fal, Runway shipped (`MediaProtocol.queued`, `Video.start/generate/resume/stream`, promise `ai.video`). Deferred: `Video.complete` (webhooks), Luma, Kling, MiniMax, Replicate.
-3. **Speech + Transcription** — ✅ Speech: OpenAI, Gemini TTS, ElevenLabs, Cartesia, Deepgram shipped (`MediaProtocol.stream`, `Speech.generate/stream`, promise `ai.speech`). ✅ Transcription: OpenAI, Gemini, Deepgram, AssemblyAI shipped across all three route kinds (`Transcription.generate/stream/start/resume`, promise `ai.transcription`). Pending: ElevenLabs Scribe. Deferred: `Speech.session` and `Transcription.session` (WebSocket streaming).
+3. **Speech + Transcription** — ✅ Speech: OpenAI, Gemini TTS, ElevenLabs, Cartesia, Deepgram shipped (`MediaProtocol.stream`, `Speech.generate/stream`, promise `ai.speech`). ✅ Transcription: OpenAI, Gemini, Deepgram, ElevenLabs Scribe, AssemblyAI shipped across all three route kinds (`Transcription.generate/stream/start/resume`, promise `ai.transcription`). Deferred: `Speech.session` and `Transcription.session` (WebSocket streaming).
 4. **Image queued routes and partials** — ✅ BFL, fal, Replicate, and Stability creative upscale queued; Stability generate inline; OpenAI `partial_images` streaming (`image-partial` restored). Imagen dropped: shut down on the Gemini API and discontinued on Vertex (2026-06-30). Deferred: Stability's synchronous edit and fast/conservative upscale endpoints.
 5. **Later** — ElevenLabs music/SFX, Lyria, `Speech.session` / `Transcription.session`, realtime.
 

packages/ai/example/tutorial.ts

@@ -15,7 +15,7 @@ import { OpenAI } from "@opencode/ai/providers"
  * hover imports and local values to see how the public API is typed.
  */
 
-const apiKey = Config.Redacted("OPENAI_API_KEY")
+const apiKey = Config.redacted("OPENAI_API_KEY")
 
 // 1. Configure a provider. The configured facade records provider identity,
 // deployment options, authentication, and defaults. Per-modality selectors pick

packages/ai/script/setup-recording-env.ts

@@ -383,7 +383,7 @@ const readEnvFile = Effect.fn("RecordingEnv.readFile")(function* () {
 })
 
 const readConfigString = (provider: ConfigProvider.ConfigProvider, name: string) =>
-  Config.String(name)
+  Config.string(name)
     .parse(provider)
     .pipe(
       Effect.match({

packages/ai/src/experimental/evaluation.ts

@@ -63,6 +63,7 @@ export const ChoiceAnswer = Schema.Struct({
   type: Schema.Literal("choice"),
   choice: Schema.String,
   probabilities: Schema.optional(Schema.Record(Schema.String, Probability)),
+  confidence: Schema.optional(Probability),
 })
 export type ChoiceAnswer = Schema.Schema.Type<typeof ChoiceAnswer>
 
@@ -70,6 +71,7 @@ export const ScoreAnswer = Schema.Struct({
   type: Schema.Literal("score"),
   score: Schema.Number,
   probabilities: Schema.optional(Schema.Record(Schema.String, Probability)),
+  confidence: Schema.optional(Probability),
 })
 export type ScoreAnswer = Schema.Schema.Type<typeof ScoreAnswer>
 
@@ -92,6 +94,7 @@ export type AnswerFor<Question extends EvaluationQuestion> = Question extends {
       readonly type: "choice"
       readonly choice: Extract<keyof Criteria, string>
       readonly probabilities?: Readonly<Record<Extract<keyof Criteria, string>, number>>
+      readonly confidence?: number
     }
   : Question extends { readonly type: "score" }
     ? ScoreAnswer

packages/ai/src/experimental/system-one.ts

@@ -142,32 +142,37 @@ export const model = <Options extends EvaluationOptions = EvaluationOptions>(cfg
             Effect.mapError((cause) => fail("System One returned an invalid response", cause, text)),
           )
 
-          const confidence: Record<string, number> = {}
           const legend: Record<string, Record<string, Schema.Json>> = {}
           const answers = Object.fromEntries(
             Object.entries(data.answers).map(([id, answer]): [string, EvaluationAnswer] => {
               if (answer.type === "noul") return [id, { type: "boolean", probability: answer.noul }]
               if (answer.type === "choice") {
-                if (answer.confidence !== undefined) confidence[id] = answer.confidence
                 return [
                   id,
                   {
                     type: "choice",
                     choice: answer.choice,
                     probabilities: answer.probabilities,
+                    ...(answer.confidence === undefined ? {} : { confidence: answer.confidence }),
                   },
                 ]
               }
-              if (answer.confidence !== undefined) confidence[id] = answer.confidence
               if (answer.legend !== undefined) legend[id] = answer.legend
-              return [id, { type: "score", score: answer.score, probabilities: answer.probabilities }]
+              return [
+                id,
+                {
+                  type: "score",
+                  score: answer.score,
+                  probabilities: answer.probabilities,
+                  ...(answer.confidence === undefined ? {} : { confidence: answer.confidence }),
+                },
+              ]
             }),
           )
           const meta = {
             ...(data.id === undefined ? {} : { responseId: data.id }),
             ...(data.provider === undefined ? {} : { provider: data.provider }),
             ...data.provider_metadata?.[cfg.providerMetadataKey],
-            ...(Object.keys(confidence).length === 0 ? {} : { confidence }),
             ...(Object.keys(legend).length === 0 ? {} : { legend }),
           }
           return new EvaluationResponse({

packages/ai/src/generation.ts

@@ -102,7 +102,7 @@ export class Generation<Response> {
     return settled.pipe(
       // Non-completed terminal states also go through `result` so the route can surface its provider failure body.
       Effect.flatMap((generation) => generation.result()),
-      Effect.timeoutOrElse({ duration: timeout, orElse: () => this.timeoutError(timeout) }),
+      Effect.timeoutOrElse({ duration: timeout, orElse: () => timeoutError(this.id, timeout) }),
     )
   }
 
@@ -123,20 +123,7 @@ export class Generation<Response> {
       Clock.currentTimeMillis.pipe(
         Effect.map((start) => {
           const deadline = start + Duration.toMillis(timeout)
-          // Fail before polling once the deadline has passed: a fast status request could otherwise win the zero-budget
-          // race and schedule another zero-delay poll.
-          const refresh = Clock.currentTimeMillis.pipe(
-            Effect.flatMap((now) =>
-              now >= deadline
-                ? this.timeoutError(timeout)
-                : this.refresh().pipe(
-                    Effect.timeoutOrElse({
-                      duration: Duration.millis(deadline - now),
-                      orElse: () => this.timeoutError(timeout),
-                    }),
-                  ),
-            ),
-          )
+          const refresh = within(this.refresh(), this.id, timeout, deadline)
           const schedule = this.schedule(options?.poll).pipe(
             Schedule.modifyDelay((meta) =>
               Effect.succeed(Duration.min(meta.duration, Duration.millis(Math.max(0, deadline - meta.now)))),
@@ -157,15 +144,6 @@ export class Generation<Response> {
     return { type: "generation-progress", id: this.id, progress: this.progress }
   }
 
-  private timeoutError(timeout: Duration.Duration) {
-    return new AIError({
-      reason: new TimeoutError({
-        message: `Generation ${this.id} did not finish within ${Duration.format(timeout)}`,
-        timeoutMs: Duration.toMillis(timeout),
-      }),
-    })
-  }
-
   private poll(poll: Poll | undefined) {
     return this.refresh().pipe(
       Effect.repeat({ schedule: this.schedule(poll), until: (generation) => generation.terminal }),
@@ -177,12 +155,53 @@ export class Generation<Response> {
   }
 }
 
+/** `events` followed by the expanded result, with the result fetch bounded by the same `poll.timeout` deadline. */
 export const resultEvents = <Response, A>(
   generation: Generation<Response>,
   expand: (response: Response) => ReadonlyArray<A>,
   options?: AwaitOptions,
-): Stream.Stream<Observation | A, AIError> =>
-  generation.events(options).pipe(
-    Stream.filter((event): event is Observation => event.type !== "generation-finished"),
-    Stream.concat(Stream.fromIterableEffect(Effect.map(generation.result(), expand))),
+): Stream.Stream<Observation | A, AIError> => {
+  const timeout = Duration.fromInputUnsafe(options?.poll?.timeout ?? DEFAULT_POLL_TIMEOUT)
+  return Stream.unwrap(
+    Clock.currentTimeMillis.pipe(
+      Effect.map((start) =>
+        generation.events(options).pipe(
+          Stream.filter((event): event is Observation => event.type !== "generation-finished"),
+          Stream.concat(
+            Stream.fromIterableEffect(
+              within(generation.result(), generation.id, timeout, start + Duration.toMillis(timeout)).pipe(
+                Effect.map(expand),
+              ),
+            ),
+          ),
+        ),
+      ),
+    ),
   )
+}
+
+/**
+ * Run `effect` within the time left until `deadline`. Fails before starting once the deadline has passed: a fast
+ * request could otherwise win the zero-budget race and schedule another zero-delay poll.
+ */
+const within = <A>(effect: Effect.Effect<A, AIError>, id: string, timeout: Duration.Duration, deadline: number) =>
+  Clock.currentTimeMillis.pipe(
+    Effect.flatMap((now) =>
+      now >= deadline
+        ? Effect.fail(timeoutError(id, timeout))
+        : effect.pipe(
+            Effect.timeoutOrElse({
+              duration: Duration.millis(deadline - now),
+              orElse: () => Effect.fail(timeoutError(id, timeout)),
+            }),
+          ),
+    ),
+  )
+
+const timeoutError = (id: string, timeout: Duration.Duration) =>
+  new AIError({
+    reason: new TimeoutError({
+      message: `Generation ${id} did not finish within ${Duration.format(timeout)}`,
+      timeoutMs: Duration.toMillis(timeout),
+    }),
+  })

packages/ai/src/index.ts

@@ -4,7 +4,7 @@ export { ImageClient } from "./image-client.js"
 export { Auth } from "./route/auth.js"
 export { Provider } from "./provider.js"
 export { ProviderPackage } from "./provider-package.js"
-export { isContextOverflow, isContextOverflowFailure } from "./provider-error.js"
+export { isContextOverflow, isContextOverflowFailure, isRetryable } from "./provider-error.js"
 export type {
   RouteLanguageModelInput,
   RouteRoutedLanguageModelInput,

packages/ai/src/promise.ts

@@ -42,7 +42,7 @@ export type GenerationHandle<Response> = Snapshot & {
   /** Serializable JSON; pass it back to `resume` from another process. */
   readonly token: unknown
   readonly await: (options?: AwaitOptions & RunOptions) => Promise<Response>
-  /** Status observations until the first terminal one, polling like `await`; abort ends iteration without throwing. */
+  /** Status observations until the first terminal one, polling like `await`; abort throws `signal.reason`. */
   readonly events: (options?: AwaitOptions & RunOptions) => AsyncIterable<Event>
   /** The result without polling; fails when the generation has not completed. */
   readonly result: (options?: RunOptions) => Promise<Response>
@@ -50,15 +50,16 @@ export type GenerationHandle<Response> = Snapshot & {
   readonly cancel: (options?: RunOptions) => Promise<void>
 }
 
+// Fails with `signal.reason` so aborted calls reject and aborted streams throw like `fetch`: an `AbortError` by default.
 const abortEffect = (signal: AbortSignal | undefined) =>
   signal === undefined
     ? Effect.never
-    : Effect.callback<void>((resume) => {
+    : Effect.callback<never, unknown>((resume) => {
         if (signal.aborted) {
-          resume(Effect.void)
+          resume(Effect.fail(signal.reason))
           return
         }
-        const onAbort = () => resume(Effect.void)
+        const onAbort = () => resume(Effect.fail(signal.reason))
         signal.addEventListener("abort", onAbort, { once: true })
         return Effect.sync(() => signal.removeEventListener("abort", onAbort))
       })
@@ -68,14 +69,14 @@ export const make = (options: Options = {}) => {
 
   /** Run any package Effect (for example `LLMClient.compact(...)`) inside this runtime. */
   const run = <A, E>(effect: Effect.Effect<A, E, Services>, options?: RunOptions) =>
-    runtime.runPromise(effect, { signal: options?.signal })
+    runtime.runPromise(Effect.raceFirst(effect, abortEffect(options?.signal)))
 
   const iterate = <A, E>(stream: Stream.Stream<A, E, Services>, options?: RunOptions): AsyncIterable<A> =>
     Stream.toAsyncIterable(
       Stream.unwrap(
         runtime.contextEffect.pipe(
           Effect.map(
-            (context): Stream.Stream<A, E> =>
+            (context): Stream.Stream<A, unknown> =>
               stream.pipe(Stream.interruptWhen(abortEffect(options?.signal)), Stream.provideContext(context)),
           ),
         ),

packages/ai/src/protocols/deepgram-transcription.ts

@@ -6,6 +6,7 @@ import { mergeJsonRecords, type OpenString } from "../schema/index.js"
 import { TranscriptionModel, TranscriptionResponse, type TranscriptionRequestFor } from "../transcription.js"
 import { ProviderShared } from "./shared.js"
 import { MediaInput } from "./utils/media-input.js"
+import { SpeakerTurns } from "./utils/speaker-turns.js"
 
 const route = MediaProtocol.identity({ id: "deepgram-transcription", name: "Deepgram", provider: "deepgram" })
 export const DEFAULT_BASE_URL = "https://api.deepgram.com"
@@ -115,16 +116,6 @@ const speaker = (value: number | undefined) => (value === undefined ? undefined
 
 const wordText = (word: typeof Word.Type) => word.punctuated_word ?? word.word
 
-// Utterances split on pauses, not speakers: the v2 diarizer labels a whole utterance with one speaker even when its
-// words change speaker, so segments split each utterance at speaker changes.
-const speakerTurns = (words: ReadonlyArray<typeof Word.Type>) =>
-  words.reduce<Array<Array<typeof Word.Type>>>((turns, word) => {
-    const last = turns.at(-1)
-    if (last === undefined || last[0].speaker !== word.speaker) return [...turns, [word]]
-    last.push(word)
-    return turns
-  }, [])
-
 const decodeResponse = Effect.fn("DeepgramTranscription.decodeResponse")(function* (
   response: HttpClientResponse.HttpClientResponse,
 ) {
@@ -136,6 +127,8 @@ const decodeResponse = Effect.fn("DeepgramTranscription.decodeResponse")(functio
   const requestID = output.value.metadata?.request_id
   return new TranscriptionResponse({
     text: alternative.transcript,
+    // Utterances split on pauses, not speakers: the v2 diarizer labels a whole utterance with one speaker even when
+    // its words change speaker, so segments split each utterance at speaker changes.
     segments: output.value.results.utterances?.flatMap((utterance) =>
       utterance.words === undefined || utterance.words.length === 0
         ? [
@@ -146,7 +139,7 @@ const decodeResponse = Effect.fn("DeepgramTranscription.decodeResponse")(functio
               speaker: speaker(utterance.speaker),
             },
           ]
-        : speakerTurns(utterance.words).map((turn) => ({
+        : SpeakerTurns.group(utterance.words, (word) => word.speaker).map((turn) => ({
             text: turn.map(wordText).join(" "),
             startSeconds: turn[0].start,
             endSeconds: turn[turn.length - 1].end,

packages/ai/src/protocols/elevenlabs-transcription.ts

@@ -0,0 +1,211 @@
+import { Effect, Schema } from "effect"
+import type { HttpClientResponse } from "effect/unstable/http"
+import { MediaProtocol } from "../route/media-protocol.js"
+import { MediaRoute } from "../route/media.js"
+import { mergeJsonRecords, type OpenString } from "../schema/index.js"
+import { TranscriptionModel, TranscriptionResponse, type TranscriptionRequestFor } from "../transcription.js"
+import { mediaTypeExtension } from "../utils/media-type.js"
+import { ProviderShared, optionalNull } from "./shared.js"
+import { MediaInput } from "./utils/media-input.js"
+import { SpeakerTurns } from "./utils/speaker-turns.js"
+
+const route = MediaProtocol.identity({
+  id: "elevenlabs-transcription",
+  name: "ElevenLabs Transcription",
+  provider: "elevenlabs",
+})
+export const DEFAULT_BASE_URL = "https://api.elevenlabs.io"
+export const PATH = "/v1/speech-to-text"
+
+// ---------------------------------------------------------------------------
+// 1. Public model input
+// ---------------------------------------------------------------------------
+
+export type ElevenLabsTranscriptionOptions = {
+  readonly tag_audio_events?: boolean
+  readonly timestamps_granularity?: OpenString<"none" | "word" | "character">
+  readonly diarization_threshold?: number
+  readonly file_format?: OpenString<"pcm_s16le_16" | "other">
+  readonly temperature?: number
+  readonly seed?: number
+  readonly keyterms?: ReadonlyArray<string>
+  readonly no_verbatim?: boolean
+  readonly detect_speaker_roles?: boolean
+  readonly use_speaker_library?: boolean
+  readonly entity_detection?: string | ReadonlyArray<string>
+  readonly entity_redaction?: string | ReadonlyArray<string>
+  readonly entity_redaction_mode?: OpenString<"redacted" | "entity_type" | "enumerated_entity_type">
+} & Record<string, unknown>
+
+export type Request = TranscriptionRequestFor<ElevenLabsTranscriptionOptions>
+
+// ---------------------------------------------------------------------------
+// 2. Response schema
+// ---------------------------------------------------------------------------
+
+/** `type` is `word`, `spacing` (the whitespace between words), or `audio_event` (`(laughter)`). */
+const Token = Schema.Struct({
+  text: Schema.String,
+  type: Schema.String,
+  start: optionalNull(Schema.Number),
+  end: optionalNull(Schema.Number),
+  speaker_id: optionalNull(Schema.String),
+  logprob: optionalNull(Schema.Number),
+})
+type Token = Schema.Schema.Type<typeof Token>
+
+const Transcript = Schema.Struct({
+  language_code: optionalNull(Schema.String),
+  text: Schema.String,
+  words: optionalNull(Schema.Array(Token)),
+  transcription_id: optionalNull(Schema.String),
+  audio_duration_secs: optionalNull(Schema.Number),
+})
+
+// ---------------------------------------------------------------------------
+// 5. Request body construction
+// ---------------------------------------------------------------------------
+
+/** Speaker turns are the only segments ElevenLabs can produce, and `num_speakers` only applies to diarization. */
+const diarizes = (request: Request) =>
+  request.diarize === true || request.timestamps === "segment" || request.speakers !== undefined
+
+const RESERVED_FORM_FIELDS = new Set([
+  "file",
+  "cloud_storage_url",
+  "source_url",
+  "model_id",
+  "language_code",
+  "diarize",
+  "num_speakers",
+])
+
+const validate = (request: Request, overlay: Record<string, unknown>) => {
+  // Webhook requests return 202 with no transcript; the result arrives at a configured webhook instead.
+  if (overlay.webhook === true)
+    return Effect.fail(route.unsupported("transcription.webhook", `${route.name} does not deliver to webhooks`))
+  // Separate multichannel output replaces the transcript with one transcript per channel.
+  if (overlay.use_multi_channel === true && overlay.multichannel_output_style !== "combined")
+    return Effect.fail(
+      route.unsupported(
+        "transcription.multichannel",
+        `${route.name} returns a single transcript; set multichannel_output_style: "combined" to merge channels`,
+      ),
+    )
+  if (overlay.timestamps_granularity === "none" && (request.timestamps === "word" || diarizes(request)))
+    return Effect.fail(
+      route.unsupported(
+        "media.timestamps",
+        `${route.name} cannot return word timestamps or speaker turns with timestamps_granularity: "none"`,
+      ),
+    )
+  return Effect.void
+}
+
+const fromRequest = Effect.fn("ElevenLabsTranscription.fromRequest")(function* (request: Request) {
+  const overlay = mergeJsonRecords(request.providerOptions, request.http?.body) ?? {}
+  yield* validate(request, overlay)
+  const form = new FormData()
+  const url = ProviderShared.mediaUrl(request.audio)
+  if (url === undefined) {
+    const extension = mediaTypeExtension(request.audio.mediaType)
+    const audio = yield* MediaInput.inlineBytes(route.id, request.audio)
+    form.append(
+      "file",
+      MediaInput.blob(audio, request.audio.mediaType),
+      extension === undefined ? "audio" : `audio.${extension}`,
+    )
+  }
+  MediaInput.appendFields(
+    form,
+    {
+      model_id: request.model.id,
+      // `cloud_storage_url` is deprecated in favor of `source_url`, which accepts any hosted audio or video URL.
+      source_url: url,
+      language_code: request.language,
+      diarize: diarizes(request) ? true : undefined,
+      num_speakers: request.speakers,
+    },
+    { overlay, reserved: RESERVED_FORM_FIELDS, repeatArrays: "key" },
+  )
+  return MediaProtocol.multipart(form)
+})
+
+// ---------------------------------------------------------------------------
+// 6. Response decoding
+// ---------------------------------------------------------------------------
+
+const decodeTranscript = route.decodeJson(Transcript)
+
+type TimedWord = Token & { readonly start: number; readonly end: number }
+
+const isTimedWord = (token: Token): token is TimedWord =>
+  token.type === "word" && typeof token.start === "number" && typeof token.end === "number"
+
+/** Turn text keeps the provider's own spacing tokens, so languages written without spaces are not re-spaced. */
+const speakerTurns = (tokens: ReadonlyArray<Token>) =>
+  SpeakerTurns.group(
+    tokens.filter((token) => token.type === "word" || token.type === "spacing"),
+    (token) => token.speaker_id,
+  ).flatMap((turn) => {
+    const words = turn.filter(isTimedWord)
+    if (words.length === 0) return []
+    return [
+      {
+        text: turn
+          .map((token) => token.text)
+          .join("")
+          .trim(),
+        startSeconds: words[0].start,
+        endSeconds: words[words.length - 1].end,
+        speaker: turn[0].speaker_id ?? undefined,
+      },
+    ]
+  })
+
+const decodeResponse = Effect.fn("ElevenLabsTranscription.decodeResponse")(function* (
+  response: HttpClientResponse.HttpClientResponse,
+  context: MediaProtocol.DecodeContext<Request>,
+) {
+  const output = yield* decodeTranscript(response)
+  const transcript = output.value
+  const tokens = transcript.words ?? []
+  const duration = transcript.audio_duration_secs ?? undefined
+  const transcriptionID = transcript.transcription_id ?? undefined
+  return new TranscriptionResponse({
+    text: transcript.text,
+    segments: diarizes(context.request) ? speakerTurns(tokens) : undefined,
+    words: tokens.filter(isTimedWord).map((word) => ({
+      text: word.text,
+      startSeconds: word.start,
+      endSeconds: word.end,
+      speaker: word.speaker_id ?? undefined,
+      confidence: typeof word.logprob === "number" ? Math.exp(word.logprob) : undefined,
+    })),
+    language: transcript.language_code?.toLowerCase(),
+    durationSeconds: duration,
+    usage: duration === undefined ? undefined : { type: "seconds", seconds: duration },
+    providerMetadata: transcriptionID === undefined ? undefined : { elevenlabs: { transcriptionId: transcriptionID } },
+  })
+})
+
+// ---------------------------------------------------------------------------
+// 7. Protocol and route
+// ---------------------------------------------------------------------------
+
+export const protocol = MediaProtocol.inline<Request, TranscriptionResponse>(route, {
+  unsupported: ["prompt"],
+  body: { from: fromRequest },
+  response: { decode: decodeResponse },
+})
+
+export const model = (input: MediaRoute.ModelInput) =>
+  TranscriptionModel.fromRoute<ElevenLabsTranscriptionOptions>(
+    { protocol, baseURL: DEFAULT_BASE_URL, path: PATH },
+    input,
+  )
+
+export const ElevenLabsTranscription = {
+  protocol,
+  model,
+} as const

packages/ai/src/protocols/google-video.ts

@@ -36,7 +36,9 @@ const StartResponse = Schema.Struct({ name: Schema.String })
 
 const Operation = Schema.Struct({
   done: Schema.optional(Schema.Boolean),
-  error: Schema.optional(Schema.Struct({ message: Schema.optional(Schema.String) })),
+  error: Schema.optional(
+    Schema.Struct({ code: Schema.optional(Schema.Number), message: Schema.optional(Schema.String) }),
+  ),
   response: Schema.optional(
     Schema.Struct({
       generateVideoResponse: Schema.optional(
@@ -60,6 +62,16 @@ const Operation = Schema.Struct({
   metadata: Schema.optional(Schema.Unknown),
 })
 
+// Operation errors are `google.rpc.Status`; unlisted codes (INTERNAL, UNAVAILABLE, ...) are provider-side.
+const FAILURE = {
+  3: "InvalidRequest", // INVALID_ARGUMENT
+  7: "Authentication", // PERMISSION_DENIED
+  8: "RateLimit", // RESOURCE_EXHAUSTED
+  9: "InvalidRequest", // FAILED_PRECONDITION
+  11: "InvalidRequest", // OUT_OF_RANGE
+  16: "Authentication", // UNAUTHENTICATED
+} as const satisfies Record<number, MediaProtocol.Failure>
+
 // ---------------------------------------------------------------------------
 // 5. Request body construction
 // ---------------------------------------------------------------------------
@@ -154,6 +166,7 @@ const decodeResult = Effect.fn("GoogleVideo.decodeResult")(function* (
     return yield* output.ended(
       "failed",
       `${route.name} operation failed${operation.error?.message === undefined ? "" : `: ${operation.error.message}`}`,
+      MediaProtocol.failure(FAILURE, operation.error?.code),
     )
   const generated = operation.response?.generateVideoResponse
   // Downloads require the same API key as the poll; the asset carries it transiently and follows the redirect.

packages/ai/src/protocols/openai-chat.ts

@@ -64,6 +64,14 @@ const OpenAIChatTool = Schema.Struct({
 })
 type OpenAIChatTool = Schema.Schema.Type<typeof OpenAIChatTool>
 
+// Gemini's OpenAI-compatible surface carries thought signatures in tool call
+// `extra_content` and rejects replayed parallel calls without them:
+// https://ai.google.dev/gemini-api/docs/thinking#signatures
+const ExtraContent = Schema.Struct({
+  google: Schema.Struct({ thought_signature: Schema.String }),
+})
+const decodeExtraContent = (value: unknown) => Option.getOrUndefined(Schema.decodeUnknownOption(ExtraContent)(value))
+
 const OpenAIChatAssistantToolCall = Schema.Struct({
   id: Schema.String,
   type: Schema.tag("function"),
@@ -71,6 +79,7 @@ const OpenAIChatAssistantToolCall = Schema.Struct({
     name: Schema.String,
     arguments: Schema.String,
   }),
+  extra_content: Schema.optional(ExtraContent),
 })
 type OpenAIChatAssistantToolCall = Schema.Schema.Type<typeof OpenAIChatAssistantToolCall>
 
@@ -112,12 +121,6 @@ const decodeReasoningDetail = Schema.decodeUnknownOption(ReasoningDetail)
 const knownReasoningDetails = (details: ReadonlyArray<unknown>) =>
   details.flatMap((detail) => Option.toArray(decodeReasoningDetail(detail)))
 
-// Intentionally omit Gemini's provider-specific `extra_content.google.thought_signature`
-// extension until direct Google OpenAI-compatible routing is supported here:
-// https://github.com/vercel/ai/issues/11590
-// https://github.com/vercel/ai/pull/11745
-// https://ai.google.dev/gemini-api/docs/thought-signatures#openai
-
 const OpenAIChatUserContent = Schema.Union([
   Schema.Struct({
     type: Schema.Literal("text"),
@@ -242,6 +245,7 @@ const OpenAIChatToolCallDelta = Schema.Struct({
   index: optionalNull(Schema.Number),
   id: optionalNull(Schema.String),
   function: optionalNull(OpenAIChatToolCallDeltaFunction),
+  extra_content: optionalNull(Schema.Unknown),
 })
 type OpenAIChatToolCallDelta = Schema.Schema.Type<typeof OpenAIChatToolCallDelta>
 
@@ -294,6 +298,7 @@ interface PendingToolDelta {
   readonly id?: string
   readonly name?: string
   readonly input: string
+  readonly extraContent?: Schema.Schema.Type<typeof ExtraContent>
 }
 
 export interface ParserState {
@@ -347,13 +352,17 @@ const lowerToolChoice = (toolChoice: NonNullable<LLMRequest["toolChoice"]>) =>
     tool: (name) => ({ type: "function" as const, function: { name } }),
   })
 
-const lowerToolCall = (part: ToolCallPart, options: LoweringOptions): OpenAIChatAssistantToolCall => ({
+const lowerToolCall = (
+  part: ToolCallPart,
+  options: LoweringOptions & { readonly providerMetadataKey: string },
+): OpenAIChatAssistantToolCall => ({
   id: options.toolCallID?.(part.id) ?? part.id,
   type: "function",
   function: {
     name: part.name,
     arguments: ProviderShared.encodeJson(part.input === undefined ? {} : part.input),
   },
+  extra_content: decodeExtraContent(part.providerMetadata?.[options.providerMetadataKey]?.extraContent),
 })
 
 const lowerMedia = Effect.fn("OpenAIChat.lowerMedia")(function* (part: MediaPart) {
@@ -721,7 +730,9 @@ const detectSupportsStore = (provider: string, baseURL: string | undefined): boo
     p === "vercel-ai-gateway" || url.includes("ai-gateway.vercel.sh") || url.includes("vercel.sh")
   const isAntLing = p === "ant-ling" || url.includes("api.ant-ling.com")
   const isOpencode = p === "opencode" || url.includes("opencode.ai")
+  const isGemini = url.includes("generativelanguage.googleapis.com")
   const isNonStandard =
+    isGemini ||
     isNvidia ||
     isCerebras ||
     isXai ||
@@ -1114,12 +1125,13 @@ const step = (state: ParserState, event: OpenAIChatEvent) =>
       const id = current?.id ?? pending?.id ?? (tool.id || undefined)
       const name = current?.name ?? pending?.name ?? (tool.function?.name || undefined)
       const text = `${pending?.input ?? ""}${tool.function?.arguments ?? ""}`
+      const extraContent = pending?.extraContent ?? decodeExtraContent(tool.extra_content)
       latestToolIndex = index
       nextToolIndex = Math.max(nextToolIndex, index + 1)
       if (!current && (!id || !name)) {
         pendingTools = {
           ...pendingTools,
-          [index]: { id: id || undefined, name: name || undefined, input: text },
+          [index]: { id: id || undefined, name: name || undefined, input: text, extraContent },
         }
         continue
       }
@@ -1131,7 +1143,12 @@ const step = (state: ParserState, event: OpenAIChatEvent) =>
         ADAPTER,
         tools,
         index,
-        { id: id || undefined, name: name || undefined, text },
+        {
+          id: id || undefined,
+          name: name || undefined,
+          text,
+          providerMetadata: extraContent && { [state.providerMetadataKey]: { extraContent } },
+        },
         "OpenAI Chat tool call delta is missing id or name",
       )
       if (ToolStream.isError(result))

packages/ai/src/protocols/openai-transcription.ts

@@ -193,7 +193,7 @@ const fromRequest = Effect.fn("OpenAITranscription.fromRequest")(function* (requ
     {
       overlay: mergeJsonRecords(request.providerOptions, request.http?.body),
       reserved: RESERVED_FORM_FIELDS,
-      repeatArrays: true,
+      repeatArrays: "key[]",
     },
   )
   return MediaProtocol.multipart(form)

packages/ai/src/protocols/runway-video.ts

@@ -137,7 +137,12 @@ const decodeResult = Effect.fn("RunwayVideo.decodeResult")(function* (
     const message = `${route.name} task failed${code === undefined ? "" : ` (${code})`}${task.failure ? `: ${task.failure}` : ""}`
     // Runway failure codes are dotted paths; every moderation outcome carries a SAFETY segment.
     if (code !== undefined && /(^|\.)SAFETY(\.|$)/.test(code)) return yield* output.contentPolicy(message)
-    return yield* output.ended("failed", message)
+    // ASSET.INVALID rejects the caller's input media; Runway documents it as not retryable.
+    return yield* output.ended(
+      "failed",
+      message,
+      code !== undefined && /^ASSET\.INVALID(\.|$)/.test(code) ? "InvalidRequest" : "ProviderInternal",
+    )
   }
   if (status === "cancelled")
     return yield* output.ended("cancelled", `${route.name} task ${context.token.taskID} was cancelled`)

packages/ai/src/protocols/utils/media-input.ts

@@ -71,8 +71,9 @@ export const imageOutput = (
 }
 
 /**
- * Append multipart text fields: strings as-is, other values as JSON, or arrays as repeated `key[]` parts with
- * `repeatArrays`. `overlay` keys in `reserved` are dropped so `http.body` cannot replace route-owned fields.
+ * Append multipart text fields: strings as-is, other values as JSON, or scalar arrays as one part per item with
+ * `repeatArrays`, named `key[]` or `key`. `overlay` keys in `reserved` are dropped so `http.body` cannot replace
+ * route-owned fields.
  */
 export const appendFields = (
   form: FormData,
@@ -80,13 +81,13 @@ export const appendFields = (
   options: {
     readonly overlay?: Record<string, unknown>
     readonly reserved: ReadonlySet<string>
-    readonly repeatArrays?: true
+    readonly repeatArrays?: "key[]" | "key"
   },
 ) => {
   const overlay = Object.entries(options.overlay ?? {}).filter(([key]) => !options.reserved.has(key))
   Object.entries(mergeJsonRecords(fields, Object.fromEntries(overlay)) ?? {}).forEach(([key, value]) => {
-    if (Array.isArray(value) && options.repeatArrays)
-      return value.forEach((item) => form.append(`${key}[]`, String(item)))
+    if (Array.isArray(value) && value.every(isScalar) && options.repeatArrays !== undefined)
+      return value.forEach((item) => form.append(options.repeatArrays === "key[]" ? `${key}[]` : key, String(item)))
     form.append(key, typeof value === "string" ? value : encodeJson(value))
   })
 }

packages/ai/src/protocols/utils/speaker-turns.ts

@@ -0,0 +1,10 @@
+/** Split an ordered token list into runs of consecutive tokens with the same speaker. */
+export const group = <Item>(items: ReadonlyArray<Item>, speaker: (item: Item) => unknown) =>
+  items.reduce<Array<Array<Item>>>((turns, item) => {
+    const last = turns.at(-1)
+    if (last === undefined || speaker(last[0]) !== speaker(item)) return [...turns, [item]]
+    last.push(item)
+    return turns
+  }, [])
+
+export * as SpeakerTurns from "./speaker-turns.js"

packages/ai/src/protocols/utils/tool-stream.ts

@@ -147,7 +147,12 @@ export const appendOrStart = <K extends StreamKey>(
   route: string,
   tools: State<K>,
   key: K,
-  delta: { readonly id?: string; readonly name?: string; readonly text: string },
+  delta: {
+    readonly id?: string
+    readonly name?: string
+    readonly text: string
+    readonly providerMetadata?: ProviderMetadata
+  },
   missingToolMessage: string,
 ): AppendOutcome<K> | AIError => {
   const current = tools[key]
@@ -161,7 +166,7 @@ export const appendOrStart = <K extends StreamKey>(
     namespace: current?.namespace,
     input: `${current?.input ?? ""}${delta.text}`,
     providerExecuted: current?.providerExecuted,
-    providerMetadata: current?.providerMetadata,
+    providerMetadata: current?.providerMetadata ?? delta.providerMetadata,
   }
   if (current && delta.text.length === 0 && current.id === id && current.name === name)
     return { tools, tool: current, events: [] }

packages/ai/src/protocols/xai-video.ts

@@ -65,6 +65,13 @@ const STATUS = {
   expired: "expired",
 } as const satisfies Record<string, Status>
 
+// Documented video error codes; `service_unavailable`, `internal_error`, and unknown codes are provider-side.
+const FAILURE = {
+  invalid_argument: "InvalidRequest",
+  failed_precondition: "InvalidRequest",
+  permission_denied: "Authentication",
+} as const satisfies Record<string, MediaProtocol.Failure>
+
 // ---------------------------------------------------------------------------
 // 5. Request body construction
 // ---------------------------------------------------------------------------
@@ -143,6 +150,7 @@ const decodeResult = Effect.fn("XAIVideo.decodeResult")(function* (
     return yield* output.ended(
       "failed",
       `${route.name} generation failed${code === undefined ? "" : ` (${code})`}${message === undefined ? "" : `: ${message}`}`,
+      MediaProtocol.failure(FAILURE, code),
     )
   }
   if (status !== "completed")

packages/ai/src/provider-error.ts

@@ -58,6 +58,47 @@ export const isContextOverflowFailure = (failure: unknown) =>
     ? failure.reason._tag === "InvalidRequest" && failure.reason.classification === "context-overflow"
     : Schema.is(ProviderErrorEvent)(failure) && failure.classification === "context-overflow"
 
+/**
+ * Whether a failed call may succeed when sent again: rate limits, provider-side failures, transport failures that did
+ * not deliver an accepted write, and unrecognized failures. Callers decide which calls are safe to repeat.
+ */
+export const isRetryable = (error: AIError) => {
+  const override = error.reason.http?.headers["x-should-retry"]
+  if (override === "true") return true
+  if (override === "false") return false
+  switch (error.reason._tag) {
+    case "RateLimit":
+    case "ProviderInternal":
+      return true
+    // A WebSocket acknowledgment marks delivery accepted before model output may exist.
+    // Read failures can still recover; the caller chooses retry versus continuation from durable output.
+    case "Transport":
+      return (
+        error.reason.delivery !== "rejected" &&
+        (error.reason.delivery !== "accepted" || error.reason.operation === "read")
+      )
+    case "InvalidProviderOutput":
+      return error.reason.classification === "incomplete-stream"
+    // Unrecognized failures retry: classification records affirmative
+    // deterministic evidence, and transient failures are exactly the ones
+    // that arrive in shapes no classifier anticipates.
+    case "UnknownProvider":
+      return true
+    case "Authentication":
+    case "QuotaExceeded":
+    case "ContentPolicy":
+    case "InvalidRequest":
+    case "UnsupportedOperation":
+    case "NoRoute":
+    case "Timeout":
+      return false
+    default: {
+      const exhaustive: never = error.reason
+      return exhaustive
+    }
+  }
+}
+
 const decodeJson = Schema.decodeUnknownOption(Schema.fromJsonString(Schema.Unknown))
 // OpenCode Zen reports account caps as typed 429/402 errors that are not throttles.
 const QUOTA_CODES = new Set([

packages/ai/src/providers/elevenlabs.ts

@@ -3,8 +3,10 @@ import type { ProviderAuthOption } from "../route/auth-options.js"
 import { MediaRoute } from "../route/media.js"
 import { type HttpOptions, ProviderID, type ModelID } from "../schema/index.js"
 import { ElevenLabsSpeech } from "../protocols/elevenlabs-speech.js"
+import { ElevenLabsTranscription } from "../protocols/elevenlabs-transcription.js"
 
 export type { ElevenLabsOutputFormat, ElevenLabsSpeechOptions } from "../protocols/elevenlabs-speech.js"
+export type { ElevenLabsTranscriptionOptions } from "../protocols/elevenlabs-transcription.js"
 
 export const id = ProviderID.make("elevenlabs")
 
@@ -24,12 +26,15 @@ const auth = (options: ProviderAuthOption<"optional">) => {
 export const configure = (input: Config = {}) => {
   const media = MediaRoute.deployment(input, auth(input))
   const speech = (modelID: string | ModelID) => ElevenLabsSpeech.model({ ...media, id: modelID })
+  const transcription = (modelID: string | ModelID) => ElevenLabsTranscription.model({ ...media, id: modelID })
   return {
     id,
     speech,
+    transcription,
     configure,
   }
 }
 
 export const provider = configure()
 export const speech = provider.speech
+export const transcription = provider.transcription

packages/ai/src/route/auth.ts

@@ -95,7 +95,7 @@ export const optional = (secret: Secret | undefined, source = "optional value")
 export const config = (name: string) =>
   credential(
     Effect.gen(function* () {
-      const secret = yield* Config.option(Config.Redacted(name))
+      const secret = yield* Config.option(Config.redacted(name))
       if (Option.isSome(secret) && Redacted.value(secret.value) !== "") return secret.value
       return yield* Effect.fail(new MissingCredentialError(name, `${name} is not set`))
     }),

packages/ai/src/route/media-protocol.ts

@@ -5,12 +5,14 @@ import { Media } from "../media.js"
 import type { AuthInput } from "./auth.js"
 import {
   AIError,
+  AuthenticationError,
   ContentPolicyError,
   HttpContext,
   InvalidProviderOutputError,
   InvalidRequestError,
   ProviderID,
   ProviderInternalError,
+  RateLimitError,
   UnsupportedOperationError,
 } from "../schema/index.js"
 
@@ -188,6 +190,16 @@ export const stream = <Request, Event, Frame, State>(
 // Response helpers
 // ---------------------------------------------------------------------------
 
+/** Reasons a provider can report for a `failed` generation; anything it does not classify is `ProviderInternal`. */
+const FAILURES = {
+  InvalidRequest: InvalidRequestError,
+  Authentication: AuthenticationError,
+  RateLimit: RateLimitError,
+  ProviderInternal: ProviderInternalError,
+}
+
+export type Failure = keyof typeof FAILURES
+
 const context = (response: HttpClientResponse.HttpClientResponse) =>
   new HttpContext({ url: response.request.url, status: response.status, headers: response.headers })
 
@@ -199,9 +211,10 @@ export const identity = (input: { readonly id: string; readonly name: string; re
 
   /**
    * Read a text body while retaining the original payload and HTTP context on every downstream error. `invalid` is a
-   * malformed provider document; `ended` is a generation that reached a terminal status without output (`failed` is
-   * provider-side, `cancelled`/`expired` mean the result will never exist); `pending` is a `result()` read before the
-   * generation finished, which is caller misuse; `contentPolicy` is a moderated result.
+   * malformed provider document; `ended` is a generation that reached a terminal status without output (`failed`
+   * carries the provider's classification, defaulting to `ProviderInternal`; `cancelled`/`expired` mean the result
+   * will never exist); `pending` is a `result()` read before the generation finished, which is caller misuse;
+   * `contentPolicy` is a moderated result.
    */
   const text = Effect.fn("MediaProtocol.text")(function* (response: HttpClientResponse.HttpClientResponse) {
     const http = context(response)
@@ -223,11 +236,15 @@ export const identity = (input: { readonly id: string; readonly name: string; re
       http,
       invalid: (message: string, cause?: unknown) =>
         new AIError({ reason: new InvalidProviderOutputError({ route: input.id, message, body, http, cause }) }),
-      ended: (status: Exclude<Status, "queued" | "running" | "completed">, message: string) =>
+      ended: (
+        status: Exclude<Status, "queued" | "running" | "completed">,
+        message: string,
+        failure: Failure = "ProviderInternal",
+      ) =>
         new AIError({
           reason:
             status === "failed"
-              ? new ProviderInternalError({ message, body, http })
+              ? new FAILURES[failure]({ message, body, http })
               : new InvalidRequestError({ message, body, http }),
         }),
       pending: (id: string) =>
@@ -303,6 +320,10 @@ export const status = <Table extends Record<string, Status>>(
   return Effect.succeed(table[raw])
 }
 
+/** Map a provider error code through the protocol's table; missing or unmapped codes are `ProviderInternal`. */
+export const failure = (table: Readonly<Record<string, Failure>>, code: string | number | undefined): Failure =>
+  code !== undefined && Object.hasOwn(table, code) ? table[code] : "ProviderInternal"
+
 /** A `url` asset whose provider-declared retention window starts now. */
 export const expiringUrl = (url: string, retention: Duration.Duration, options?: Parameters<typeof Media.url>[1]) =>
   Clock.currentTimeMillis.pipe(

packages/ai/src/route/media.ts

@@ -1,4 +1,4 @@
-import { Effect, Schema, Stream } from "effect"
+import { Duration, Effect, Schedule, Schema, Stream } from "effect"
 import { Headers, HttpClientRequest, type HttpClientResponse } from "effect/unstable/http"
 import { Auth, type AuthInput } from "./auth.js"
 import { Endpoint } from "./endpoint.js"
@@ -7,6 +7,7 @@ import { RequestExecutor } from "./executor.js"
 import { MediaProtocol } from "./media-protocol.js"
 import { Generation, isTerminal } from "../generation.js"
 import type { Media } from "../media.js"
+import { isRetryable } from "../provider-error.js"
 import {
   AIError,
   AIErrorReason,
@@ -137,6 +138,32 @@ export const inline = <Request extends MediaRequest, Response>(
   }
 }
 
+const READ_RETRY_MAX_DELAY = Duration.seconds(30)
+
+/**
+ * Status and result reads retry transient failures; `start` and `cancel` never do. Gaps grow exponentially from 1s,
+ * jittered, up to 30s each, for at most 8 retries (about two minutes when every attempt fails), so a direct
+ * `Generation.result()` stays bounded; `await` and `events` also cut retries off at `poll.timeout`. A provider
+ * `retryAfterMs` raises the gap, still capped at 30s.
+ */
+const READ_RETRY = Schedule.max([
+  Schedule.min([Schedule.exponential("1 second"), Schedule.spaced(READ_RETRY_MAX_DELAY)]),
+  Schedule.recurs(8),
+]).pipe(
+  Schedule.jittered,
+  Schedule.setInputType<AIError>(),
+  Schedule.modifyDelay(({ input, duration }) =>
+    Effect.succeed(
+      Duration.min(
+        input.reason._tag === "RateLimit" || input.reason._tag === "ProviderInternal"
+          ? Duration.max(duration, Duration.millis(input.reason.retryAfterMs ?? 0))
+          : duration,
+        READ_RETRY_MAX_DELAY,
+      ),
+    ),
+  ),
+)
+
 /**
  * Compose a queued media protocol the same way, adding `start`/`resume` handles whose polls reuse the route's auth,
  * deployment headers, and (for `start`) the request's `http` overlay. The token is decoded once at the boundary and
@@ -154,6 +181,8 @@ export const queued = <Request extends MediaRequest, Response, Token>(
   const generationRoute = (token: Token, http: HttpOptions | undefined, execute: Execute) => {
     const materialize = (asset: Media.Asset) =>
       asset.materialize().pipe(Effect.provideService(RequestExecutorService, { execute }))
+    // Only the GET exchange retries: a decoded terminal failure (`output.ended`) can be a `ProviderInternal` too, and
+    // re-reading it would spin until the caller's deadline.
     const poll = <A>(operation: {
       readonly path: (token: Token) => string
       readonly decode: (
@@ -161,9 +190,10 @@ export const queued = <Request extends MediaRequest, Response, Token>(
         context: MediaProtocol.PollContext<Token>,
       ) => Effect.Effect<A, AIError>
     }) =>
-      transport
-        .call("GET", operation.path(token), http, execute)
-        .pipe(Effect.flatMap((sent) => operation.decode(sent.response, { token, auth: sent.auth, materialize })))
+      transport.call("GET", operation.path(token), http, execute).pipe(
+        Effect.retry({ schedule: READ_RETRY, while: isRetryable }),
+        Effect.flatMap((sent) => operation.decode(sent.response, { token, auth: sent.auth, materialize })),
+      )
     const status = poll(protocol.status)
     const cancel = protocol.cancel
     const send =

packages/ai/src/tool.ts

@@ -6,7 +6,6 @@ import type {
   ToolOutput as ToolOutputType,
 } from "./schema/index.js"
 import { ToolDefinition, ToolFailure, ToolOutput } from "./schema/index.js"
-import { isRecord } from "./utils/record.js"
 
 /**
  * Schema constraint for tool parameters / success values: no decoding or
@@ -201,7 +200,7 @@ export function make(config: TypedToolConfig | DynamicToolConfig): AnyTool {
     _definition: new ToolDefinition({
       name: "",
       description: config.description,
-      inputSchema: toInputJsonSchema(config.parameters),
+      inputSchema: toJsonSchema(config.parameters),
       outputSchema: toJsonSchema(config.success),
     }),
   }
@@ -231,33 +230,8 @@ export const toDefinitions = (tools: Tools): ReadonlyArray<ToolDefinitionClass>
       }),
   )
 
-const toInputJsonSchema = (schema: Schema.Top): JsonSchema.JsonSchema => {
-  // Effect represents Struct({}) as any non-null value; tool parameters must
-  // instead describe an object. Inline named empty inputs so providers such as
-  // Gemini can recognize a no-argument tool, while retaining schema annotations.
-  if (
-    schema.ast._tag !== "Objects" ||
-    schema.ast.propertySignatures.length !== 0 ||
-    schema.ast.indexSignatures.length !== 0 ||
-    schema.ast.encoding !== undefined ||
-    schema.ast.checks !== undefined
-  )
-    return toJsonSchema(schema)
-
-  const json = Schema.toJsonSchemaDocument(schema, {
-    onExcessProperty: "error",
-    referencePolicy: () => undefined,
-  }).schema
-  if (isRecord(json.not) && json.not.type === "null" && Object.keys(json.not).length === 1) {
-    const normalized: JsonSchema.JsonSchema = { type: "object", properties: {}, additionalProperties: false, ...json }
-    delete normalized.not
-    return normalized
-  }
-  return toJsonSchema(schema)
-}
-
 const toJsonSchema = (schema: Schema.Top): JsonSchema.JsonSchema => {
-  const document = Schema.toJsonSchemaDocument(schema, { onExcessProperty: "error" })
+  const document = Schema.toJsonSchemaDocument(schema)
   if (Object.keys(document.definitions).length === 0) return document.schema
   return { ...document.schema, $defs: document.definitions }
 }

packages/ai/src/transcription.ts

@@ -103,7 +103,7 @@ export type TranscriptionRequestInput<Model extends TranscriptionModel = Transcr
 // Response and events
 // ---------------------------------------------------------------------------
 
-/** Speaker labels are provider-native (`A`, `0`, `spk:0`, or a known speaker name). */
+/** Speaker labels are provider-native (`A`, `0`, `spk:0`, `speaker_0`, or a known speaker name). */
 export const TranscriptionSegment = Schema.Struct({
   text: Schema.String,
   startSeconds: Schema.Number,

packages/ai/test/auth-options.types.ts

@@ -30,7 +30,7 @@ type LanguageModel = {
 declare const auth: Auth.Definition
 declare const optionalAuthModel: LanguageModelFactory<BaseOptions, "optional", LanguageModel>
 declare const requiredAuthModel: LanguageModelFactory<BaseOptions, "required", LanguageModel>
-const configApiKey = Config.Redacted("OPENAI_API_KEY")
+const configApiKey = Config.redacted("OPENAI_API_KEY")
 
 OpenAIChat.route.model({ id: "gpt-4.1-mini" })
 

packages/ai/test/evaluation.test.ts

@@ -39,17 +39,18 @@ describe("experimental Evaluation", () => {
         type: "choice",
         choice: "billing",
         probabilities: { billing: 0.9, technical: 0.1 },
+        confidence: 0.8,
       })
       expect(response.answers.urgency).toEqual({
         type: "score",
         score: 1.2,
         probabilities: { "0": 0, "1": 0.8, "2": 0.2 },
+        confidence: 0.6,
       })
       expect(response.answers.refund).toEqual({ type: "boolean", probability: 0.97 })
       expect(response.usage?.totalTokens).toBe(36)
       expect(response.providerMetadata).toEqual({
         typesafe: {
-          confidence: { department: 0.8, urgency: 0.6 },
           legend: { urgency: { "0": "Can wait", "1": "Needs attention", "2": "Blocking" } },
         },
       })

packages/ai/test/evaluation.types.ts

@@ -26,8 +26,10 @@ const request = Evaluation.request({
 const result = EvaluationClient.evaluate(request)
 type Result = Success<typeof result>
 type Choice = Assert<Equal<Result["answers"]["topic"]["choice"], "billing" | "support">>
+type Confidence = Assert<Equal<Result["answers"]["topic"]["confidence"], number | undefined>>
 type ClientRequirements = Assert<Equal<Requirements<typeof result>, Service>>
 void (true satisfies Choice)
+void (true satisfies Confidence)
 void (true satisfies ClientRequirements)
 
 Effect.gen(function* () {

packages/ai/test/exports.test.ts

@@ -197,6 +197,11 @@ describe("public exports", () => {
     expect(Google.configure({ apiKey: "fixture" }).transcription("gemini-3.5-transcribe").route.kind).toBe("stream")
     expect(Deepgram.configure({ apiKey: "fixture" }).transcription("nova-3").route.kind).toBe("inline")
     expect(AssemblyAI.configure({ apiKey: "fixture" }).transcription("universal-3-5-pro").route.kind).toBe("queued")
+    expect(ElevenLabs.configure({ apiKey: "fixture" }).transcription("scribe_v2").route.id).toBe(
+      "elevenlabs-transcription",
+    )
+    expect(ElevenLabs.configure({ apiKey: "fixture" }).transcription("scribe_v2").route.kind).toBe("inline")
+    expect(ElevenLabs.provider.transcription).toBe(ElevenLabs.transcription)
   })
 
   test("protocol barrels expose supported low-level routes", () => {

packages/ai/test/fixtures/recordings/elevenlabs-transcription/groups-diarized-words-into-speaker-turns.json

@@ -0,0 +1,32 @@
+{
+  "version": 1,
+  "metadata": {
+    "tags": [
+      "prefix:elevenlabs-transcription",
+      "provider:elevenlabs",
+      "protocol:elevenlabs-transcription"
+    ],
+    "name": "elevenlabs-transcription/groups-diarized-words-into-speaker-turns",
+    "recordedAt": "2026-09-27T09:35:28.265Z"
+  },
+  "interactions": [
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://api.elevenlabs.io/v1/speech-to-text",
+        "headers": {
+          "content-type": "multipart/form-data; boundary=----WebKitFormBoundary356bdc14864a477dbacbfcf60d1ecceb"
+        },
+        "body": "--BOUNDARY\r\nContent-Disposition: form-data; name=\"file\"; filename=\"audio.mp3\"\r\nContent-Type: audio/mpeg\r\n\r\n[audio]\r\n--BOUNDARY\r\nContent-Disposition: form-data; name=\"model_id\"\r\n\r\nscribe_v2\r\n--BOUNDARY\r\nContent-Disposition: form-data; name=\"diarize\"\r\n\r\ntrue\r\n--BOUNDARY--\r\n"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "application/json"
+        },
+        "body": "{\"language_code\":\"eng\",\"language_probability\":0.9495430588722229,\"text\":\"Did the release ship? Yes, it shipped this morning\",\"words\":[{\"text\":\"Did\",\"start\":0.34,\"end\":0.44,\"type\":\"word\",\"speaker_id\":\"speaker_0\",\"logprob\":-1.7881377516459906e-6},{\"text\":\" \",\"start\":0.44,\"end\":0.48,\"type\":\"spacing\",\"speaker_id\":\"speaker_0\",\"logprob\":-1.1920928244535389e-7},{\"text\":\"the\",\"start\":0.48,\"end\":0.56,\"type\":\"word\",\"speaker_id\":\"speaker_0\",\"logprob\":-1.1920928244535389e-7},{\"text\":\" \",\"start\":0.56,\"end\":0.6,\"type\":\"spacing\",\"speaker_id\":\"speaker_0\",\"logprob\":-7.152531907195225e-6},{\"text\":\"release\",\"start\":0.6,\"end\":0.92,\"type\":\"word\",\"speaker_id\":\"speaker_0\",\"logprob\":-7.152531907195225e-6},{\"text\":\" \",\"start\":0.92,\"end\":0.94,\"type\":\"spacing\",\"speaker_id\":\"speaker_0\",\"logprob\":-8.344646857949556e-7},{\"text\":\"ship?\",\"start\":0.94,\"end\":1.26,\"type\":\"word\",\"speaker_id\":\"speaker_0\",\"logprob\":-7.414704032271402e-6},{\"text\":\" \",\"start\":1.26,\"end\":1.26,\"type\":\"spacing\",\"speaker_id\":\"speaker_0\",\"logprob\":-0.0009363081189803779},{\"text\":\"Yes,\",\"start\":1.68,\"end\":2.02,\"type\":\"word\",\"speaker_id\":\"speaker_1\",\"logprob\":-0.003542040009030245},{\"text\":\" \",\"start\":2.02,\"end\":2.48,\"type\":\"spacing\",\"speaker_id\":\"speaker_1\",\"logprob\":-3.933898824470816e-6},{\"text\":\"it\",\"start\":2.48,\"end\":2.62,\"type\":\"word\",\"speaker_id\":\"speaker_1\",\"logprob\":-3.933898824470816e-6},{\"text\":\" \",\"start\":2.62,\"end\":2.64,\"type\":\"spacing\",\"speaker_id\":\"speaker_1\",\"logprob\":-0.000013589766240329482},{\"text\":\"shipped\",\"start\":2.66,\"end\":2.9,\"type\":\"word\",\"speaker_id\":\"speaker_1\",\"logprob\":-0.000013589766240329482},{\"text\":\" \",\"start\":2.9,\"end\":2.94,\"type\":\"spacing\",\"speaker_id\":\"speaker_1\",\"logprob\":0.0},{\"text\":\"this\",\"start\":2.94,\"end\":3.12,\"type\":\"word\",\"speaker_id\":\"speaker_1\",\"logprob\":0.0},{\"text\":\" \",\"start\":3.12,\"end\":3.18,\"type\":\"spacing\",\"speaker_id\":\"speaker_1\",\"logprob\":-3.576278118089249e-7},{\"text\":\"morning\",\"start\":3.18,\"end\":3.5,\"type\":\"word\",\"speaker_id\":\"speaker_1\",\"logprob\":-3.576278118089249e-7}],\"transcription_id\":\"cs3I2282TH8hjw12brNg\",\"audio_duration_secs\":3.5526875}"
+      }
+    }
+  ]
+}

packages/ai/test/fixtures/recordings/elevenlabs-transcription/transcribes-audio-with-word-timestamps.json

@@ -0,0 +1,50 @@
+{
+  "version": 1,
+  "metadata": {
+    "tags": [
+      "prefix:elevenlabs-transcription",
+      "provider:elevenlabs",
+      "protocol:elevenlabs-transcription"
+    ],
+    "name": "elevenlabs-transcription/transcribes-audio-with-word-timestamps",
+    "recordedAt": "2026-09-27T09:35:27.686Z"
+  },
+  "interactions": [
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://api.elevenlabs.io/v1/speech-to-text",
+        "headers": {
+          "content-type": "multipart/form-data; boundary=----WebKitFormBoundarye2be7b31e94441bbbeb35a9c890a9d74"
+        },
+        "body": "--BOUNDARY\r\nContent-Disposition: form-data; name=\"file\"; filename=\"audio.mp3\"\r\nContent-Type: audio/mpeg\r\n\r\n[audio]\r\n--BOUNDARY\r\nContent-Disposition: form-data; name=\"model_id\"\r\n\r\nscribe_v2\r\n--BOUNDARY--\r\n"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "application/json"
+        },
+        "body": "{\"language_code\":\"eng\",\"language_probability\":0.6618340611457825,\"text\":\"Hello from OpenCode\",\"words\":[{\"text\":\"Hello\",\"start\":0.4,\"end\":0.66,\"type\":\"word\",\"logprob\":-0.000014781842764932662},{\"text\":\" \",\"start\":0.66,\"end\":0.74,\"type\":\"spacing\",\"logprob\":-3.814689989667386e-6},{\"text\":\"from\",\"start\":0.74,\"end\":0.84,\"type\":\"word\",\"logprob\":-3.814689989667386e-6},{\"text\":\" \",\"start\":0.84,\"end\":0.9,\"type\":\"spacing\",\"logprob\":-0.018268775194883347},{\"text\":\"OpenCode\",\"start\":0.9,\"end\":1.44,\"type\":\"word\",\"logprob\":-0.1251817401498556}],\"transcription_id\":\"D4VfnANM2ArCHTujIb9q\",\"audio_duration_secs\":1.54125}"
+      }
+    },
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://api.elevenlabs.io/v1/speech-to-text",
+        "headers": {
+          "content-type": "multipart/form-data; boundary=----WebKitFormBoundaryfb80d0e44d9e44d299416ed546a04056"
+        },
+        "body": "--BOUNDARY\r\nContent-Disposition: form-data; name=\"file\"; filename=\"audio.mp3\"\r\nContent-Type: audio/mpeg\r\n\r\n[audio]\r\n--BOUNDARY\r\nContent-Disposition: form-data; name=\"model_id\"\r\n\r\nscribe_v2\r\n--BOUNDARY--\r\n"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "application/json"
+        },
+        "body": "{\"language_code\":\"eng\",\"language_probability\":0.6618340611457825,\"text\":\"Hello from OpenCode\",\"words\":[{\"text\":\"Hello\",\"start\":0.4,\"end\":0.66,\"type\":\"word\",\"logprob\":-0.000023007127310847864},{\"text\":\" \",\"start\":0.66,\"end\":0.74,\"type\":\"spacing\",\"logprob\":-2.3841830625315197e-6},{\"text\":\"from\",\"start\":0.74,\"end\":0.84,\"type\":\"word\",\"logprob\":-2.3841830625315197e-6},{\"text\":\" \",\"start\":0.84,\"end\":0.9,\"type\":\"spacing\",\"logprob\":-0.008306833915412426},{\"text\":\"OpenCode\",\"start\":0.9,\"end\":1.44,\"type\":\"word\",\"logprob\":-0.1075385226868093}],\"transcription_id\":\"SkYplzfq1DW8Ae3bWnoy\",\"audio_duration_secs\":1.54125}"
+      }
+    }
+  ]
+}

packages/ai/test/fixtures/recordings/openai-compatible-chat/gemini-parallel-tool-signatures.json

@@ -0,0 +1,54 @@
+{
+  "version": 1,
+  "metadata": {
+    "model": "gemini-3.8-flash",
+    "tags": [
+      "prefix:openai-compatible-chat",
+      "provider:google",
+      "protocol:openai-chat",
+      "tool",
+      "tool-loop",
+      "continuation"
+    ],
+    "name": "gemini-parallel-tool-signatures",
+    "recordedAt": "2026-09-28T03:12:05.083Z"
+  },
+  "interactions": [
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://generativelanguage.googleapis.com/v1beta/openai/chat/completions",
+        "headers": {
+          "content-type": "application/json"
+        },
+        "body": "{\"model\":\"gemini-3.8-flash\",\"messages\":[{\"role\":\"system\",\"content\":\"Call get_weather for every requested city in parallel, then answer in one short sentence.\"},{\"role\":\"user\",\"content\":\"What is the weather in Paris and in Tokyo?\"}],\"tools\":[{\"type\":\"function\",\"function\":{\"name\":\"get_weather\",\"description\":\"Get current weather for a city.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false},\"strict\":false}}],\"stream\":true,\"stream_options\":{\"include_usage\":true}}"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "text/event-stream"
+        },
+        "body": "data: {\"choices\":[{\"delta\":{\"role\":\"assistant\",\"tool_calls\":[{\"extra_content\":{\"google\":{\"thought_signature\":\"ErYCCrMCAWkUfRNGh+/Zbc8YUSzk1yfWAfROcjA4HyF1x69jz6167w8zd4n6kZQQ5FDeBZ5HZMEbEkQ4ENOpzsQL8roCR6wONkhXpiduWrTD6XwbP8KGNkf6D1tX/JlBh7G5Cl+0rdjiSOl/mdY1lcjbkfyCRFs5T8odNWMG7WD3rCrXJDFQ/5QfOl+tqVTceKGz2yyXBhOhvsQDU33ulR9tHQJo/Fmx3HNyDdwvmyKUXm+kgqHsYZnkdv6y6xZwy9zBXGUO4QwxelMw3Rrc24Mp2rNbEDZS3YEeP72Jn/hIP5a8XWOx6+zop/4/CjYxxSfN/tJRY5d48NAKRNFzUN1Az8SvAs/N5X2I3/5ZMaDnQWW/BVdS9fm2KFYJ2baqtBiRRnJxMq4ELArkKjGZzHpd97XG8YjV6g==\"}},\"function\":{\"arguments\":\"{\\\"city\\\":\\\"Paris\\\"}\",\"name\":\"get_weather\"},\"id\":\"call_723181\",\"type\":\"function\"}]},\"index\":0}],\"created\":1790565123,\"id\":\"A9u5aoufBp3rz7IPke_3oAo\",\"model\":\"gemini-3.8-flash\",\"object\":\"chat.completion.chunk\",\"usage\":{\"completion_tokens\":16,\"prompt_tokens\":74,\"total_tokens\":132}}\n\ndata: {\"choices\":[{\"delta\":{\"role\":\"assistant\",\"tool_calls\":[{\"function\":{\"arguments\":\"{\\\"city\\\":\\\"Tokyo\\\"}\",\"name\":\"get_weather\"},\"id\":\"call_723184\",\"type\":\"function\"}]},\"index\":0}],\"created\":1790565123,\"id\":\"A9u5aoufBp3rz7IPke_3oAo\",\"model\":\"gemini-3.8-flash\",\"object\":\"chat.completion.chunk\",\"usage\":{\"completion_tokens\":32,\"prompt_tokens\":74,\"total_tokens\":148}}\n\ndata: {\"choices\":[{\"delta\":{\"role\":\"assistant\"},\"finish_reason\":\"stop\",\"index\":0}],\"created\":1790565124,\"id\":\"A9u5aoufBp3rz7IPke_3oAo\",\"model\":\"gemini-3.8-flash\",\"object\":\"chat.completion.chunk\",\"usage\":{\"completion_tokens\":32,\"prompt_tokens\":74,\"total_tokens\":148}}\n\ndata: [DONE]\n\n"
+      }
+    },
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://generativelanguage.googleapis.com/v1beta/openai/chat/completions",
+        "headers": {
+          "content-type": "application/json"
+        },
+        "body": "{\"model\":\"gemini-3.8-flash\",\"messages\":[{\"role\":\"system\",\"content\":\"Call get_weather for every requested city in parallel, then answer in one short sentence.\"},{\"role\":\"user\",\"content\":\"What is the weather in Paris and in Tokyo?\"},{\"role\":\"assistant\",\"content\":null,\"tool_calls\":[{\"id\":\"call_723181\",\"type\":\"function\",\"function\":{\"name\":\"get_weather\",\"arguments\":\"{\\\"city\\\":\\\"Paris\\\"}\"},\"extra_content\":{\"google\":{\"thought_signature\":\"ErYCCrMCAWkUfRNGh+/Zbc8YUSzk1yfWAfROcjA4HyF1x69jz6167w8zd4n6kZQQ5FDeBZ5HZMEbEkQ4ENOpzsQL8roCR6wONkhXpiduWrTD6XwbP8KGNkf6D1tX/JlBh7G5Cl+0rdjiSOl/mdY1lcjbkfyCRFs5T8odNWMG7WD3rCrXJDFQ/5QfOl+tqVTceKGz2yyXBhOhvsQDU33ulR9tHQJo/Fmx3HNyDdwvmyKUXm+kgqHsYZnkdv6y6xZwy9zBXGUO4QwxelMw3Rrc24Mp2rNbEDZS3YEeP72Jn/hIP5a8XWOx6+zop/4/CjYxxSfN/tJRY5d48NAKRNFzUN1Az8SvAs/N5X2I3/5ZMaDnQWW/BVdS9fm2KFYJ2baqtBiRRnJxMq4ELArkKjGZzHpd97XG8YjV6g==\"}}},{\"id\":\"call_723184\",\"type\":\"function\",\"function\":{\"name\":\"get_weather\",\"arguments\":\"{\\\"city\\\":\\\"Tokyo\\\"}\"}}]},{\"role\":\"tool\",\"tool_call_id\":\"call_723181\",\"content\":\"{\\\"temperature\\\":22,\\\"condition\\\":\\\"sunny\\\"}\"},{\"role\":\"tool\",\"tool_call_id\":\"call_723184\",\"content\":\"{\\\"temperature\\\":0,\\\"condition\\\":\\\"unknown\\\"}\"}],\"tools\":[{\"type\":\"function\",\"function\":{\"name\":\"get_weather\",\"description\":\"Get current weather for a city.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false},\"strict\":false}}],\"stream\":true,\"stream_options\":{\"include_usage\":true}}"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "text/event-stream"
+        },
+        "body": "data: {\"choices\":[{\"delta\":{\"content\":\"It is currently sunny and 22°C in Paris,\",\"role\":\"assistant\"},\"index\":0}],\"created\":1790565125,\"id\":\"BNu5auWeB-2fz7IPxY6l4QY\",\"model\":\"gemini-3.8-flash\",\"object\":\"chat.completion.chunk\",\"usage\":{\"completion_tokens\":13,\"prompt_tokens\":150,\"total_tokens\":226}}\n\ndata: {\"choices\":[{\"delta\":{\"content\":\" while Tokyo is 0°C.\",\"role\":\"assistant\"},\"index\":0}],\"created\":1790565125,\"id\":\"BNu5auWeB-2fz7IPxY6l4QY\",\"model\":\"gemini-3.8-flash\",\"object\":\"chat.completion.chunk\",\"usage\":{\"completion_tokens\":21,\"prompt_tokens\":150,\"total_tokens\":234}}\n\ndata: {\"choices\":[{\"delta\":{\"extra_content\":{\"google\":{\"thought_signature\":\"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\"}},\"role\":\"assistant\"},\"finish_reason\":\"stop\",\"index\":0}],\"created\":1790565125,\"id\":\"BNu5auWeB-2fz7IPxY6l4QY\",\"model\":\"gemini-3.8-flash\",\"object\":\"chat.completion.chunk\",\"usage\":{\"completion_tokens\":21,\"prompt_tokens\":192,\"total_tokens\":276}}\n\ndata: [DONE]\n\n"
+      }
+    }
+  ]
+}

packages/ai/test/promise.test.ts

@@ -22,7 +22,8 @@ const chatBody = sseEvents(
 /**
  * Executor layer that answers chat completions with SSE text, image generations with one base64 PNG, Runway video
  * tasks with a queued submission that succeeds on the second poll, speech with raw audio or SSE audio deltas, OpenAI
- * transcription with JSON or SSE text deltas, and AssemblyAI transcripts that complete on the first poll.
+ * transcription with JSON or SSE text deltas, AssemblyAI transcripts that complete on the first poll, and `slow.test`
+ * chat completions that send one text delta and never finish.
  */
 const executor = (seen: Array<string>) =>
   RequestExecutor.layer.pipe(
@@ -55,6 +56,18 @@ const executor = (seen: Array<string>) =>
               output: "https://replicate.test/a.webp",
               urls: { get: "https://replicate.test/p_1", cancel: "https://replicate.test/p_1/cancel" },
             })
+          if (web.url.startsWith("https://slow.test"))
+            return input.respond(
+              new ReadableStream({
+                start: (controller) =>
+                  controller.enqueue(
+                    new TextEncoder().encode(
+                      `data: ${JSON.stringify({ choices: [{ delta: { content: "Hello" } }] })}\n\n`,
+                    ),
+                  ),
+              }),
+              { headers: { "content-type": "text/event-stream" } },
+            )
           if (web.url.endsWith("/chat/completions"))
             return input.respond(chatBody, { headers: { "content-type": "text/event-stream" } })
           if (web.url.endsWith("/audio/speech"))
@@ -304,6 +317,77 @@ describe("AI promise client", () => {
     await ai.dispose()
   })
 
+  test("aborted calls reject and aborted streams throw with the signal's reason", async () => {
+    const ai = AI.make({ layer: executor([]) })
+    const slow = OpenAI.configure({ apiKey: "test", baseURL: "https://slow.test/v1" }).chat("gpt-4o-mini")
+    const aborted = new AbortController()
+    aborted.abort()
+    const reason = new Error("mine")
+
+    const rejected = await ai.run(Effect.never, { signal: aborted.signal }).catch((error: unknown) => error)
+    expect(rejected).toBe(aborted.signal.reason)
+    expect(rejected).toMatchObject({ name: "AbortError" })
+
+    const inFlight = new AbortController()
+    setTimeout(() => inFlight.abort(reason), 10)
+    expect(
+      await ai.llm
+        .generate({ model: slow, prompt: "Hello" }, { signal: inFlight.signal })
+        .catch((error: unknown) => error),
+    ).toBe(reason)
+
+    const preAborted = await Array.fromAsync(
+      ai.speech.stream({ model: openai.speech("gpt-4o-mini-tts"), text: "Hello" }, { signal: aborted.signal }),
+    ).catch((error: unknown) => error)
+    expect(preAborted).toBe(aborted.signal.reason)
+    expect(preAborted).toMatchObject({ name: "AbortError" })
+
+    const midStream = new AbortController()
+    const deltas: Array<string> = []
+    const midStreamFailure = await Array.fromAsync(
+      ai.llm.stream({ model: slow, prompt: "Hello" }, { signal: midStream.signal }),
+      (event) => {
+        if (!LLMEvent.is.textDelta(event)) return
+        deltas.push(event.text)
+        midStream.abort()
+      },
+    ).catch((error: unknown) => error)
+    expect(deltas).toEqual(["Hello"])
+    expect(midStreamFailure).toBe(midStream.signal.reason)
+    expect(midStreamFailure).toMatchObject({ name: "AbortError" })
+
+    const model = Runway.configure({ apiKey: "test", baseURL: "https://runway.test/v1" }).video("gen4.5")
+    const generation = await ai.video.start({ model, prompt: "A kite" })
+    const polling = new AbortController()
+    const events: Array<string> = []
+    const eventsFailure = await Array.fromAsync(
+      generation.events({ poll: { interval: 60_000 }, signal: polling.signal }),
+      (event) => {
+        events.push(event.type)
+        polling.abort(reason)
+      },
+    ).catch((error: unknown) => error)
+    expect(events).toEqual(["generation-progress"])
+    expect(eventsFailure).toBe(reason)
+
+    await ai.dispose()
+  })
+
+  test("breaking out of an abortable stream cleans up without throwing", async () => {
+    const ai = AI.make({ layer: executor([]) })
+    const slow = OpenAI.configure({ apiKey: "test", baseURL: "https://slow.test/v1" }).chat("gpt-4o-mini")
+    const controller = new AbortController()
+    const deltas: Array<string> = []
+    for await (const event of ai.llm.stream({ model: slow, prompt: "Hello" }, { signal: controller.signal })) {
+      if (!LLMEvent.is.textDelta(event)) continue
+      deltas.push(event.text)
+      break
+    }
+    controller.abort()
+    expect(deltas).toEqual(["Hello"])
+    await ai.dispose()
+  })
+
   test("the default client is created lazily and can be disposed", async () => {
     expect(typeof AI.ai.llm.generate).toBe("function")
     expect(typeof AI.ai.image.generate).toBe("function")

packages/ai/test/provider/elevenlabs-transcription.recorded.test.ts

@@ -0,0 +1,50 @@
+import { describe, expect } from "bun:test"
+import { Effect, Stream } from "effect"
+import { Transcription } from "../../src/index.js"
+import { ElevenLabs } from "../../src/providers.js"
+import { recordedTests } from "../recorded-test.js"
+import { TRANSCRIPT, audio, audioRecording, dialog } from "./transcription-recording.js"
+
+const model = ElevenLabs.configure({ apiKey: process.env.ELEVENLABS_API_KEY ?? "fixture" }).transcription("scribe_v2")
+
+const recorded = recordedTests({
+  prefix: "elevenlabs-transcription",
+  provider: "elevenlabs",
+  protocol: "elevenlabs-transcription",
+  requires: ["ELEVENLABS_API_KEY"],
+  options: audioRecording,
+})
+
+describe("ElevenLabs Transcription recorded", () => {
+  recorded.effect("transcribes audio with word timestamps", () =>
+    Effect.gen(function* () {
+      const request = Transcription.request({ model, audio: yield* audio, timestamps: "word" })
+      const response = yield* Transcription.generate(request)
+
+      expect(response.text).toMatch(TRANSCRIPT)
+      expect(response.words?.map((word) => word.text)).toEqual(["Hello", "from", "OpenCode"])
+      expect(response.words?.every((word) => word.speaker === undefined && (word.confidence ?? 0) > 0)).toBe(true)
+      expect(response.segments).toBeUndefined()
+      expect(response.language).toBe("eng")
+      expect(response.durationSeconds).toBeGreaterThan(0)
+      expect(response.usage).toEqual({ type: "seconds", seconds: response.durationSeconds })
+      expect(response.providerMetadata?.elevenlabs?.transcriptionId).toEqual(expect.any(String))
+
+      const events = Array.from(yield* Stream.runCollect(Transcription.stream(request)))
+      expect(events.map((event) => event.type)).toEqual(["finish"])
+    }),
+  )
+
+  recorded.effect("groups diarized words into speaker turns", () =>
+    Effect.gen(function* () {
+      const response = yield* Transcription.generate({ model, audio: yield* dialog, diarize: true })
+
+      expect(response.segments?.map((segment) => segment.speaker)).toEqual(["speaker_0", "speaker_1"])
+      expect(response.segments?.[0].text).toMatch(/^Did the release ship\?$/)
+      expect(response.segments?.[1].text).toMatch(/^Yes, it shipped this morning\.?$/)
+      expect(response.segments?.map((segment) => segment.text).join(" ")).toBe(response.text)
+      expect(response.words?.some((word) => word.text.trim() === "")).toBe(false)
+      expect(new Set(response.words?.map((word) => word.speaker))).toEqual(new Set(["speaker_0", "speaker_1"]))
+    }),
+  )
+})

packages/ai/test/provider/evaluation.recorded.test.ts

@@ -92,5 +92,6 @@ const assertEvaluation = <Options extends EvaluationOptions>(
     expect(response.answers.refund.probability).toBeGreaterThan(0.5)
     expect(response.usage?.inputTokens).toBeGreaterThan(0)
     expect(response.usage?.outputTokens).toBeGreaterThan(0)
-    expect(response.providerMetadata?.[metadataKey]?.confidence).toBeDefined()
+    expect(response.answers.department.confidence).toBeGreaterThan(0)
+    expect(response.answers.urgency.confidence).toBeGreaterThan(0)
   })

packages/ai/test/provider/gemini-openai-chat.recorded.test.ts

@@ -0,0 +1,68 @@
+import { describe, expect } from "bun:test"
+import { Effect } from "effect"
+import { LLM, LLMEvent, LLMRequest, Message, ToolRuntime, toDefinitions } from "../../src/index.js"
+import * as OpenAICompatible from "../../src/providers/openai-compatible.js"
+import { LLMClient } from "../../src/route.js"
+import { compileRequest } from "../../src/route/client.js"
+import { recordedTests } from "../recorded-test.js"
+import { weatherRuntimeTool, weatherToolName } from "../recorded-scenarios.js"
+
+const model = OpenAICompatible.configure({
+  provider: "google",
+  baseURL: "https://generativelanguage.googleapis.com/v1beta/openai",
+  apiKey: process.env.GOOGLE_GENERATIVE_AI_API_KEY ?? "fixture",
+}).model("gemini-3.8-flash")
+
+const recorded = recordedTests({
+  prefix: "openai-compatible-chat",
+  provider: "google",
+  protocol: "openai-chat",
+  requires: ["GOOGLE_GENERATIVE_AI_API_KEY"],
+  tags: ["tool", "tool-loop", "continuation"],
+  metadata: { model: model.id },
+})
+
+describe("Gemini OpenAI-compatible Chat recorded", () => {
+  recorded.effect.with(
+    "replays thought signatures through a parallel tool loop",
+    { cassette: "openai-compatible-chat/gemini-parallel-tool-signatures" },
+    () =>
+      Effect.gen(function* () {
+        const tools = { [weatherToolName]: weatherRuntimeTool }
+        const request = LLM.request({
+          model,
+          system: "Call get_weather for every requested city in parallel, then answer in one short sentence.",
+          prompt: "What is the weather in Paris and in Tokyo?",
+          tools: toDefinitions(tools),
+          cache: "none",
+        })
+        const first = yield* LLMClient.generate(request)
+        const calls = first.events.filter(LLMEvent.is.toolCall)
+        expect(calls.map((call) => call.input)).toEqual([{ city: "Paris" }, { city: "Tokyo" }])
+        const extraContent = calls[0]?.providerMetadata?.google?.extraContent
+        expect(extraContent).toEqual({ google: { thought_signature: expect.any(String) } })
+
+        const results = yield* Effect.forEach(calls, (call) => ToolRuntime.dispatch(tools, call))
+        const continuation = LLMRequest.update(request, {
+          messages: [
+            ...request.messages,
+            first.message,
+            ...calls.map((call, index) =>
+              Message.tool({ id: call.id, name: call.name, result: results[index]!.result }),
+            ),
+          ],
+        })
+        const prepared = yield* compileRequest(continuation)
+        const assistant = prepared.body.messages.find((message) => message.role === "assistant")
+        expect(assistant?.role === "assistant" ? assistant.tool_calls?.[0]?.extra_content : undefined).toEqual(
+          extraContent,
+        )
+
+        const second = yield* LLMClient.generate(continuation)
+        expect(second.events.filter(LLMEvent.is.toolCall)).toHaveLength(0)
+        expect(second.text).toMatch(/Paris/)
+        expect(second.text).toMatch(/Tokyo/)
+      }),
+    60_000,
+  )
+})

packages/ai/test/provider/openai-chat.test.ts

@@ -472,6 +472,45 @@ describe("OpenAI Chat route", () => {
     }),
   )
 
+  it.effect("replays Gemini thought signatures as tool call extra content", () =>
+    Effect.gen(function* () {
+      const prepared = yield* compileRequest(
+        LLM.request({
+          model,
+          messages: [
+            Message.user("Weather in Paris and Tokyo?"),
+            Message.assistant([
+              ToolCallPart.make({
+                id: "call_1",
+                name: "lookup",
+                input: { city: "Paris" },
+                providerMetadata: { openai: { extraContent: { google: { thought_signature: "sig_1" } } } },
+              }),
+              ToolCallPart.make({ id: "call_2", name: "lookup", input: { city: "Tokyo" } }),
+            ]),
+            Message.tool({ id: "call_1", name: "lookup", result: "Sunny" }),
+            Message.tool({ id: "call_2", name: "lookup", result: "Rainy" }),
+          ],
+        }),
+      )
+
+      const assistant = prepared.body.messages[1]
+      expect(assistant?.role === "assistant" ? assistant.tool_calls : undefined).toEqual([
+        {
+          id: "call_1",
+          type: "function",
+          function: { name: "lookup", arguments: encodeJson({ city: "Paris" }) },
+          extra_content: { google: { thought_signature: "sig_1" } },
+        },
+        {
+          id: "call_2",
+          type: "function",
+          function: { name: "lookup", arguments: encodeJson({ city: "Tokyo" }) },
+        },
+      ])
+    }),
+  )
+
   it.effect("limits OpenAI and Azure Chat tool call IDs to 40 characters", () =>
     Effect.gen(function* () {
       const id = `call_${"a".repeat(48)}`
@@ -1805,6 +1844,78 @@ describe("OpenAI Chat route", () => {
     }),
   )
 
+  it.effect("preserves Gemini thought signatures on streamed parallel tool calls", () =>
+    Effect.gen(function* () {
+      // Gemini's OpenAI-compatible endpoint omits `index`, streams each call whole,
+      // and signs only the first call of a parallel batch.
+      const body = sseEvents(
+        deltaChunk({
+          role: "assistant",
+          tool_calls: [
+            {
+              extra_content: { google: { thought_signature: "sig_1" } },
+              id: "call_1",
+              type: "function",
+              function: { name: "lookup", arguments: '{"city":"Paris"}' },
+            },
+          ],
+        }),
+        deltaChunk({
+          role: "assistant",
+          tool_calls: [{ id: "call_2", type: "function", function: { name: "lookup", arguments: '{"city":"Tokyo"}' } }],
+        }),
+        deltaChunk({}, "stop"),
+      )
+      const response = yield* LLMClient.generate(
+        LLMRequest.update(request, {
+          tools: [ToolDefinition.make({ name: "lookup", description: "Lookup data", inputSchema: { type: "object" } })],
+        }),
+      ).pipe(Effect.provide(fixedResponse(body)))
+
+      expect(response.events.filter(LLMEvent.is.toolCall)).toEqual([
+        {
+          type: "tool-call",
+          id: "call_1",
+          name: "lookup",
+          input: { city: "Paris" },
+          providerExecuted: undefined,
+          providerMetadata: { openai: { extraContent: { google: { thought_signature: "sig_1" } } } },
+        },
+        {
+          type: "tool-call",
+          id: "call_2",
+          name: "lookup",
+          input: { city: "Tokyo" },
+          providerExecuted: undefined,
+          providerMetadata: undefined,
+        },
+      ])
+    }),
+  )
+
+  it.effect("keeps extra content that arrives before the tool identity", () =>
+    Effect.gen(function* () {
+      const body = sseEvents(
+        deltaChunk({
+          tool_calls: [
+            { index: 0, extra_content: { google: { thought_signature: "sig_1" } }, function: { arguments: "{" } },
+          ],
+        }),
+        deltaChunk({ tool_calls: [{ index: 0, id: "call_1", function: { name: "lookup", arguments: "}" } }] }),
+        deltaChunk({}, "tool_calls"),
+      )
+      const response = yield* LLMClient.generate(
+        LLMRequest.update(request, {
+          tools: [ToolDefinition.make({ name: "lookup", description: "Lookup data", inputSchema: { type: "object" } })],
+        }),
+      ).pipe(Effect.provide(fixedResponse(body)))
+
+      expect(response.events.filter(LLMEvent.is.toolCall).map((event) => event.providerMetadata)).toEqual([
+        { openai: { extraContent: { google: { thought_signature: "sig_1" } } } },
+      ])
+    }),
+  )
+
   it.effect("does not finalize streamed tool calls when content is filtered", () =>
     Effect.gen(function* () {
       const body = sseEvents(

packages/ai/test/tool-schema-projection.test.ts

@@ -1,7 +1,7 @@
 import { describe, expect, test } from "bun:test"
 import { Effect, Schema } from "effect"
 import { LLM } from "../src/index.js"
-import { AnthropicMessages, Gemini, OpenAIChat, OpenAIResponses } from "../src/protocols.js"
+import { OpenAIChat } from "../src/protocols.js"
 import { ToolSchemaProjection } from "../src/protocols/utils/tool-schema.js"
 import { Tool, toDefinitions } from "../src/tool.js"
 import { Auth } from "../src/route.js"
@@ -9,126 +9,6 @@ import { compileRequest } from "../src/route/client.js"
 import { it } from "./lib/effect.js"
 
 describe("tool schema projections", () => {
-  test("only normalizes typed empty input structs, preserving raw schemas and output schemas", () => {
-    const schema = { not: { type: "null" } }
-    const definitions = Tool.toDefinitions({
-      typed: Tool.make({
-        description: "Typed",
-        parameters: Schema.Struct({}),
-        success: Schema.Struct({}),
-        execute: () => Effect.succeed({}),
-      }),
-      raw: Tool.make({ description: "Raw", jsonSchema: schema, execute: () => Effect.succeed({}) }),
-    })
-    expect(definitions[0]?.inputSchema).toEqual({ type: "object", properties: {}, additionalProperties: false })
-    expect(definitions[0]?.outputSchema).toEqual(schema)
-    expect(definitions[1]?.inputSchema).toEqual(schema)
-  })
-
-  test("retains empty input descriptions and preserves named outputs and explicit raw schemas", () => {
-    const parameters = Schema.Struct({}).annotate({ identifier: "Ping", description: "No arguments" })
-    const raw = { $ref: "#/$defs/Raw", $defs: { Raw: { not: { type: "null" }, description: "Raw schema" } } }
-    const definitions = Tool.toDefinitions({
-      typed: Tool.make({ description: "Ping", parameters, success: parameters, execute: () => Effect.succeed({}) }),
-      raw: Tool.make({ description: "Raw", jsonSchema: raw, execute: () => Effect.succeed({}) }),
-    })
-    expect(definitions[0]?.inputSchema).toEqual({
-      type: "object",
-      properties: {},
-      additionalProperties: false,
-      description: "No arguments",
-    })
-    expect(definitions[0]?.outputSchema).toEqual({
-      $ref: "#/$defs/Ping",
-      $defs: { Ping: { not: { type: "null" }, description: "No arguments" } },
-    })
-    expect(definitions[1]?.inputSchema).toEqual(raw)
-  })
-
-  const empty = { type: "object", properties: {}, additionalProperties: false }
-  const nonempty = {
-    type: "object",
-    properties: { query: { type: "string" } },
-    required: ["query"],
-    additionalProperties: false,
-  }
-  const raw = { type: "object", properties: { value: { type: "number" } }, additionalProperties: true }
-
-  for (const scenario of [
-    {
-      route: OpenAIChat.route,
-      tools: [empty, nonempty, raw].map((parameters, index) => ({
-        type: "function",
-        function: { name: ["ping", "lookup", "raw"][index], parameters },
-      })),
-    },
-    {
-      route: OpenAIResponses.route,
-      tools: [empty, nonempty, raw].map((parameters, index) => ({
-        type: "function",
-        name: ["ping", "lookup", "raw"][index],
-        parameters,
-      })),
-    },
-    {
-      route: AnthropicMessages.route,
-      tools: [empty, nonempty, raw].map((input_schema, index) => ({
-        name: ["ping", "lookup", "raw"][index],
-        input_schema,
-      })),
-    },
-    {
-      route: Gemini.route,
-      tools: [
-        {
-          functionDeclarations: [empty, nonempty, raw].map((parametersJsonSchema, index) => ({
-            name: ["ping", "lookup", "raw"][index],
-            parametersJsonSchema,
-          })),
-        },
-      ],
-    },
-  ]) {
-    for (const input of [
-      { name: "plain", schema: Schema.Struct({}) },
-      { name: "described", schema: Schema.Struct({}).annotate({ description: "No arguments" }) },
-      { name: "named", schema: Schema.Struct({}).annotate({ identifier: "Ping" }) },
-      {
-        name: "named and described",
-        schema: Schema.Struct({}).annotate({ identifier: "Ping", description: "No arguments" }),
-      },
-    ]) {
-      it.effect(
-        `${scenario.route.id} prepares ${input.name} empty Effect Struct tools alongside nonempty and raw schemas`,
-        () =>
-          Effect.gen(function* () {
-            const prepared = yield* compileRequest(
-              LLM.request({
-                model: scenario.route.with({ auth: Auth.bearer("test") }).model({ id: "test-model" }),
-                prompt: "Use a tool.",
-                tools: Tool.toDefinitions({
-                  ping: Tool.make({
-                    description: "Ping",
-                    parameters: input.schema,
-                    success: Schema.String,
-                    execute: () => Effect.succeed("pong"),
-                  }),
-                  lookup: Tool.make({
-                    description: "Lookup",
-                    parameters: Schema.Struct({ query: Schema.String }),
-                    success: Schema.String,
-                    execute: (input) => Effect.succeed(input.query),
-                  }),
-                  raw: Tool.make({ description: "Raw", jsonSchema: raw, execute: () => Effect.succeed("raw") }),
-                }),
-              }),
-            )
-            expect(prepared.body.tools).toMatchObject(scenario.tools)
-          }),
-      )
-    }
-  }
-
   test("moonshot strips $ref siblings and converts tuple arrays to a schema object", () => {
     expect(
       ToolSchemaProjection.moonshot({
@@ -211,12 +91,7 @@ describe("tool schema projections", () => {
       const exclusive = { oneOf: [{ type: "object" }, { type: "object", required: ["a"] }] }
       const object = { type: "object", properties: {} }
 
-      expect(yield* parameters(parameterless)).toEqual({
-        type: "object",
-        properties: {},
-        additionalProperties: false,
-        description: "No input.",
-      })
+      expect(yield* parameters(parameterless)).toEqual({ type: "object", description: "No input." })
       expect(yield* parameters({})).toEqual({ type: "object" })
       expect(yield* parameters({ description: "Query", properties: { q: { type: "string" } } })).toEqual({
         type: "object",

packages/ai/test/transcription.test.ts

@@ -3,7 +3,7 @@ import { Effect, Fiber, Layer, Stream } from "effect"
 import * as TestClock from "effect/testing/TestClock"
 import { HttpClientRequest } from "effect/unstable/http"
 import { Media, Transcription, TranscriptionClient, type TranscriptionEvent } from "../src/index.js"
-import { AssemblyAI, Deepgram, Google, OpenAI } from "../src/providers.js"
+import { AssemblyAI, Deepgram, ElevenLabs, Google, OpenAI } from "../src/providers.js"
 import { it } from "./lib/effect.js"
 import { dynamicResponse, json, observe, type Call } from "./lib/http.js"
 import { sseEvents } from "./lib/sse.js"
@@ -35,6 +35,9 @@ const formFields = (call: Call) =>
 const assemblyai = AssemblyAI.configure({ apiKey: "aai-key", baseURL: "https://assemblyai.test" }).transcription(
   "universal-3-5-pro",
 )
+const elevenlabs = ElevenLabs.configure({ apiKey: "test", baseURL: "https://elevenlabs.test" }).transcription(
+  "scribe_v2",
+)
 
 describe("Transcription", () => {
   it.effect("rejects what a route cannot honor before sending anything", () =>
@@ -459,6 +462,115 @@ describe("Transcription", () => {
     }),
   )
 
+  it.effect("rejects ElevenLabs prompts, webhooks, per-channel transcripts, and untimed diarization", () =>
+    Effect.gen(function* () {
+      const errors = yield* Effect.all(
+        [
+          Transcription.generate({ model: elevenlabs, audio, prompt: "OpenCode" }),
+          Transcription.generate({ model: elevenlabs, audio, providerOptions: { webhook: true } }),
+          Transcription.generate({ model: elevenlabs, audio, http: { body: { use_multi_channel: true } } }),
+          Transcription.generate({
+            model: elevenlabs,
+            audio,
+            diarize: true,
+            providerOptions: { timestamps_granularity: "none" },
+          }),
+          Transcription.generate({
+            model: elevenlabs,
+            audio: Media.ref("file_1", { provider: "elevenlabs", mediaType: "audio/mpeg" }),
+          }),
+        ].map((effect) => Effect.flip(effect)),
+      )
+      expect(errors.map((error) => [error.reason._tag, "operation" in error.reason && error.reason.operation])).toEqual(
+        [
+          ["UnsupportedOperation", "media.prompt"],
+          ["UnsupportedOperation", "transcription.webhook"],
+          ["UnsupportedOperation", "transcription.multichannel"],
+          ["UnsupportedOperation", "media.timestamps"],
+          ["InvalidRequest", false],
+        ],
+      )
+    }).pipe(Effect.provide(layer(() => Effect.die("an unsupported request reached the network")))),
+  )
+
+  it.effect("sends ElevenLabs URL audio as source_url and groups diarized words into speaker turns", () =>
+    Effect.gen(function* () {
+      const calls: Array<Call> = []
+      const token = (text: string, type: string, start: number, end: number, speaker_id?: string) => ({
+        text,
+        type,
+        start,
+        end,
+        speaker_id,
+        logprob: 0,
+      })
+      const response = yield* Transcription.generate({
+        model: elevenlabs,
+        audio: Media.url("https://a.test/call.mp3"),
+        language: "en",
+        speakers: 2,
+        providerOptions: { keyterms: ["OpenCode", "Scribe"], tag_audio_events: true, diarize: false },
+      }).pipe(
+        Effect.provide(
+          layer((input) =>
+            observe(calls, input).pipe(
+              Effect.as(
+                json(input, {
+                  language_code: "ENG",
+                  text: "Ready? (laughs) Yes. Go",
+                  words: [
+                    token("Ready?", "word", 0, 0.5, "speaker_0"),
+                    token(" ", "spacing", 0.5, 0.6, "speaker_0"),
+                    token("(laughs)", "audio_event", 0.6, 1, "speaker_0"),
+                    token(" ", "spacing", 1, 1.1, "speaker_0"),
+                    token("Yes.", "word", 1.2, 1.5, "speaker_1"),
+                    token(" ", "spacing", 1.5, 1.6, "speaker_1"),
+                    token("Go", "word", 1.6, 1.9, "speaker_0"),
+                  ],
+                  transcription_id: "tr_1",
+                  audio_duration_secs: 2,
+                }),
+              ),
+            ),
+          ),
+        ),
+      )
+
+      // `observe` re-encodes the FormData with a new boundary, so read the boundary from the sent body.
+      const boundary = /^--(\S+)/.exec(calls[0].body)?.[1]
+      const form = yield* Effect.promise(() =>
+        new Response(calls[0].body, {
+          headers: { "content-type": `multipart/form-data; boundary=${boundary}` },
+        }).formData(),
+      )
+      expect(calls[0].url).toBe("https://elevenlabs.test/v1/speech-to-text")
+      expect(calls[0].headers.get("xi-api-key")).toBe("test")
+      expect(Array.from(form.entries())).toEqual([
+        ["model_id", "scribe_v2"],
+        ["source_url", "https://a.test/call.mp3"],
+        ["language_code", "en"],
+        ["diarize", "true"],
+        ["num_speakers", "2"],
+        ["keyterms", "OpenCode"],
+        ["keyterms", "Scribe"],
+        ["tag_audio_events", "true"],
+      ])
+      expect(response.segments).toEqual([
+        { text: "Ready?", startSeconds: 0, endSeconds: 0.5, speaker: "speaker_0" },
+        { text: "Yes.", startSeconds: 1.2, endSeconds: 1.5, speaker: "speaker_1" },
+        { text: "Go", startSeconds: 1.6, endSeconds: 1.9, speaker: "speaker_0" },
+      ])
+      expect(response.words?.map((word) => [word.text, word.speaker, word.confidence])).toEqual([
+        ["Ready?", "speaker_0", 1],
+        ["Yes.", "speaker_1", 1],
+        ["Go", "speaker_0", 1],
+      ])
+      expect(response.language).toBe("eng")
+      expect(response.usage).toEqual({ type: "seconds", seconds: 2 })
+      expect(response.providerMetadata).toEqual({ elevenlabs: { transcriptionId: "tr_1" } })
+    }),
+  )
+
   it.effect("rejects reading an AssemblyAI result before the transcript finishes", () =>
     Effect.gen(function* () {
       const generation = yield* Transcription.resume(assemblyai, { transcriptID: "tr_1" })

packages/ai/test/video.test.ts

@@ -1,9 +1,10 @@
 import { describe, expect } from "bun:test"
-import { Effect, Layer, Stream } from "effect"
+import { Effect, Fiber, Layer, Stream } from "effect"
+import * as TestClock from "effect/testing/TestClock"
 import { Media, Video, VideoClient, type GenerationEvent, type VideoEvent } from "../src/index.js"
 import { Fal, Google, Runway, XAI } from "../src/providers.js"
 import { it } from "./lib/effect.js"
-import { dynamicResponse, json, observe, settle, type Call } from "./lib/http.js"
+import { dynamicResponse, json, observe, settle, type Call, type HandlerInput } from "./lib/http.js"
 
 const layer = (handler: Parameters<typeof dynamicResponse>[0]) =>
   VideoClient.layer.pipe(Layer.provideMerge(dynamicResponse(handler)))
@@ -162,27 +163,39 @@ describe("Video / Google Veo", () => {
     ),
   )
 
-  it.effect("surfaces an operation error as a failed generation with the provider body", () =>
-    Effect.gen(function* () {
-      const failure = {
-        name: operation,
-        done: true,
-        error: { code: 3, message: "Prompt violates policy", status: "INVALID_ARGUMENT" },
-      }
-      const error = yield* Video.generate({ model, prompt: "nope" }).pipe(
-        Effect.flip,
-        Effect.provide(
-          layer((input) =>
-            Effect.succeed(input.request.method === "POST" ? json(input, { name: operation }) : json(input, failure)),
-          ),
-        ),
-      )
-      expect(error.reason._tag).toBe("ProviderInternal")
-      expect(error.message).toBe("Google Veo operation failed: Prompt violates policy")
-      expect(error.reason.body).toBe(JSON.stringify(failure))
-      expect(error.reason.http?.status).toBe(200)
-    }),
-  )
+  for (const terminal of [
+    { error: { code: 3, message: "Prompt violates policy", status: "INVALID_ARGUMENT" }, tag: "InvalidRequest" },
+    { error: { code: 9, message: "Unsupported resolution", status: "FAILED_PRECONDITION" }, tag: "InvalidRequest" },
+    { error: { code: 11, message: "Duration out of range", status: "OUT_OF_RANGE" }, tag: "InvalidRequest" },
+    { error: { code: 7, message: "Permission denied", status: "PERMISSION_DENIED" }, tag: "Authentication" },
+    { error: { code: 16, message: "Invalid credentials", status: "UNAUTHENTICATED" }, tag: "Authentication" },
+    { error: { code: 8, message: "Quota exceeded", status: "RESOURCE_EXHAUSTED" }, tag: "RateLimit" },
+    { error: { code: 13, message: "Internal error", status: "INTERNAL" }, tag: "ProviderInternal" },
+    { error: { code: 14, message: "Service unavailable", status: "UNAVAILABLE" }, tag: "ProviderInternal" },
+    { error: { message: "Something broke" }, tag: "ProviderInternal" },
+  ]) {
+    it.effect(
+      `surfaces ${terminal.error.status ?? "an uncoded"} operation error as ${terminal.tag} with the provider body`,
+      () =>
+        Effect.gen(function* () {
+          const failure = { name: operation, done: true, error: terminal.error }
+          const error = yield* Video.generate({ model, prompt: "nope" }).pipe(
+            Effect.flip,
+            Effect.provide(
+              layer((input) =>
+                Effect.succeed(
+                  input.request.method === "POST" ? json(input, { name: operation }) : json(input, failure),
+                ),
+              ),
+            ),
+          )
+          expect(error.reason._tag).toBe(terminal.tag)
+          expect(error.message).toBe(`Google Veo operation failed: ${terminal.error.message}`)
+          expect(error.reason.body).toBe(JSON.stringify(failure))
+          expect(error.reason.http?.status).toBe(200)
+        }),
+    )
+  }
 
   it.effect("reports fully filtered output as a content policy failure", () =>
     Effect.gen(function* () {
@@ -332,12 +345,37 @@ describe("Video / xAI", () => {
   for (const terminal of [
     {
       body: { status: "failed", error: { code: "invalid_argument", message: "Prompt cannot be empty." } },
-      tag: "ProviderInternal",
+      tag: "InvalidRequest",
       message: "xAI Video generation failed (invalid_argument): Prompt cannot be empty.",
     },
+    {
+      body: { status: "failed", error: { code: "failed_precondition", message: "Extension is not supported." } },
+      tag: "InvalidRequest",
+      message: "xAI Video generation failed (failed_precondition): Extension is not supported.",
+    },
+    {
+      body: { status: "failed", error: { code: "permission_denied", message: "Team lacks access." } },
+      tag: "Authentication",
+      message: "xAI Video generation failed (permission_denied): Team lacks access.",
+    },
+    {
+      body: { status: "failed", error: { code: "service_unavailable", message: "Overloaded." } },
+      tag: "ProviderInternal",
+      message: "xAI Video generation failed (service_unavailable): Overloaded.",
+    },
+    {
+      body: { status: "failed", error: { code: "internal_error", message: "Generation failed." } },
+      tag: "ProviderInternal",
+      message: "xAI Video generation failed (internal_error): Generation failed.",
+    },
+    {
+      body: { status: "failed", error: { code: "constructor", message: "Future code." } },
+      tag: "ProviderInternal",
+      message: "xAI Video generation failed (constructor): Future code.",
+    },
     { body: { status: "expired" }, tag: "InvalidRequest", message: "xAI Video request req_1 expired" },
   ]) {
-    it.effect(`surfaces ${terminal.body.status} generations with the provider body`, () =>
+    it.effect(`surfaces ${terminal.body.error?.code ?? terminal.body.status} generations with the provider body`, () =>
       Effect.gen(function* () {
         const error = yield* Video.generate({ model, prompt: "x" }).pipe(Effect.flip)
         expect(error.reason._tag).toBe(terminal.tag)
@@ -558,7 +596,10 @@ describe("Video / fal", () => {
   ]) {
     it.effect(`fails await for ${failure.name} with the response_url body and HTTP context`, () =>
       Effect.gen(function* () {
-        const error = yield* Video.generate({ model, prompt: "x" }).pipe(Effect.flip)
+        // A transient 500 on the result fetch is retried first; the body and HTTP context survive the final failure.
+        const fiber = yield* Effect.forkChild(Video.generate({ model, prompt: "x" }).pipe(Effect.flip))
+        yield* TestClock.adjust("5 minutes")
+        const error = yield* Fiber.join(fiber)
         expect(error.reason._tag).toBe(failure.tag)
         expect(error.reason.body).toBe(JSON.stringify(failure.result.body))
         expect(error.reason.http).toMatchObject({ url: urls.response, status: failure.result.status })
@@ -765,6 +806,11 @@ describe("Video / Runway", () => {
       tag: "ProviderInternal",
       message: "Runway task failed (INTERNAL.BAD_OUTPUT.CODE01): Something broke",
     },
+    {
+      body: { status: "FAILED", failure: "Unsupported dimensions", failureCode: "ASSET.INVALID" },
+      tag: "InvalidRequest",
+      message: "Runway task failed (ASSET.INVALID): Unsupported dimensions",
+    },
     { body: { status: "CANCELLED" }, tag: "InvalidRequest", message: "Runway task task_1 was cancelled" },
   ]) {
     it.effect(`surfaces ${terminal.body.failureCode ?? terminal.body.status} with the task body`, () =>
@@ -908,6 +954,169 @@ describe("Video / Runway", () => {
   )
 })
 
+// ---------------------------------------------------------------------------
+// Transient read failures
+// ---------------------------------------------------------------------------
+
+describe("Video / transient read failures", () => {
+  const model = Runway.configure({ apiKey: "test", baseURL: "https://runway.test/v1" }).video("gen4.5")
+  const succeeded = { id: "task_1", status: "SUCCEEDED", output: ["https://runway.test/out.mp4"] }
+  const failure = (input: HandlerInput, status: number, headers?: Record<string, string>) =>
+    json(input, { error: `HTTP ${status}` }, { status, headers })
+  const methods = (calls: ReadonlyArray<Call>) => calls.map((call) => call.method)
+
+  it.effect("retries a 503 status poll and a 503 result read, then returns the result", () =>
+    Effect.gen(function* () {
+      const calls: Array<Call> = []
+      const response = yield* settle(
+        Video.generate({ model, prompt: "x" }, { poll: { interval: "1 second" } }),
+        5,
+      ).pipe(
+        Effect.provide(
+          layer((input) =>
+            Effect.gen(function* () {
+              const { call, nth } = yield* observe(calls, input)
+              if (call.method === "POST") return json(input, { id: "task_1" })
+              // 1: status fails, 2: status succeeds, 3: result fails, 4: result succeeds.
+              if (nth === 1 || nth === 3) return failure(input, 503)
+              return json(input, succeeded)
+            }),
+          ),
+        ),
+      )
+      expect(response.video.source).toMatchObject({ type: "url", url: "https://runway.test/out.mp4" })
+      expect(methods(calls)).toEqual(["POST", "GET", "GET", "GET", "GET"])
+    }),
+  )
+
+  it.effect("waits for a 429 retry-after before polling again", () =>
+    Effect.gen(function* () {
+      const calls: Array<Call> = []
+      const fiber = yield* Effect.forkChild(
+        Video.generate({ model, prompt: "x" }, { poll: { interval: "1 second" } }).pipe(
+          Effect.provide(
+            layer((input) =>
+              Effect.gen(function* () {
+                const { call, nth } = yield* observe(calls, input)
+                if (call.method === "POST") return json(input, { id: "task_1" })
+                if (nth === 1) return failure(input, 429, { "retry-after": "10" })
+                return json(input, succeeded)
+              }),
+            ),
+          ),
+        ),
+      )
+      yield* TestClock.adjust("9 seconds")
+      expect(methods(calls)).toEqual(["POST", "GET"])
+      yield* TestClock.adjust("1 second")
+      yield* Fiber.join(fiber)
+      expect(methods(calls)).toEqual(["POST", "GET", "GET", "GET"])
+    }),
+  )
+
+  it.effect("fails a 400 status poll without retrying", () =>
+    Effect.gen(function* () {
+      const calls: Array<Call> = []
+      const error = yield* Video.generate({ model, prompt: "x" }).pipe(
+        Effect.flip,
+        Effect.provide(
+          layer((input) =>
+            Effect.gen(function* () {
+              const { call } = yield* observe(calls, input)
+              return call.method === "POST" ? json(input, { id: "task_1" }) : failure(input, 400)
+            }),
+          ),
+        ),
+      )
+      expect(error.reason._tag).toBe("InvalidRequest")
+      expect(methods(calls)).toEqual(["POST", "GET"])
+    }),
+  )
+
+  it.effect("stops retrying at poll.timeout with a Timeout reason", () =>
+    Effect.gen(function* () {
+      const calls: Array<Call> = []
+      const error = yield* settle(
+        Video.generate({ model, prompt: "x" }, { poll: { interval: "1 second", timeout: "5 seconds" } }).pipe(
+          Effect.flip,
+        ),
+        6,
+      ).pipe(
+        Effect.provide(
+          layer((input) =>
+            Effect.gen(function* () {
+              const { call } = yield* observe(calls, input)
+              return call.method === "POST" ? json(input, { id: "task_1" }) : failure(input, 503)
+            }),
+          ),
+        ),
+      )
+      expect(error.reason._tag).toBe("Timeout")
+      expect(calls.filter((call) => call.method === "GET").length).toBeGreaterThan(1)
+    }),
+  )
+
+  it.effect("bounds a streamed result read's retries by poll.timeout", () =>
+    Effect.gen(function* () {
+      const calls: Array<Call> = []
+      const error = yield* settle(
+        Video.stream({ model, prompt: "x" }, { poll: { interval: "1 second", timeout: "5 seconds" } }).pipe(
+          Stream.runCollect,
+          Effect.flip,
+        ),
+        6,
+      ).pipe(
+        Effect.provide(
+          layer((input) =>
+            Effect.gen(function* () {
+              const { call, nth } = yield* observe(calls, input)
+              if (call.method === "POST") return json(input, { id: "task_1" })
+              return nth === 1 ? json(input, succeeded) : failure(input, 503)
+            }),
+          ),
+        ),
+      )
+      expect(error.reason._tag).toBe("Timeout")
+      expect(calls.filter((call) => call.method === "GET").length).toBeGreaterThan(2)
+    }),
+  )
+
+  it.effect("never retries a failed submit", () =>
+    Effect.gen(function* () {
+      const calls: Array<Call> = []
+      const error = yield* Video.generate({ model, prompt: "x" }).pipe(
+        Effect.flip,
+        Effect.provide(layer((input) => observe(calls, input).pipe(Effect.map(() => failure(input, 503))))),
+      )
+      expect(error.reason._tag).toBe("ProviderInternal")
+      expect(methods(calls)).toEqual(["POST"])
+    }),
+  )
+
+  it.effect("never retries a failed cancel", () =>
+    Effect.gen(function* () {
+      const calls: Array<Call> = []
+      const error = yield* Effect.gen(function* () {
+        const generation = yield* Video.start({ model, prompt: "x" })
+        return yield* generation.cancel().pipe(Effect.flip)
+      }).pipe(
+        Effect.provide(
+          layer((input) =>
+            Effect.gen(function* () {
+              const { call } = yield* observe(calls, input)
+              if (call.method === "POST") return json(input, { id: "task_1" })
+              if (call.method === "DELETE") return failure(input, 503)
+              return json(input, { id: "task_1", status: "RUNNING" })
+            }),
+          ),
+        ),
+      )
+      expect(error.reason._tag).toBe("ProviderInternal")
+      expect(methods(calls)).toEqual(["POST", "GET", "DELETE"])
+    }),
+  )
+})
+
 // ---------------------------------------------------------------------------
 // Shared queued behavior
 // ---------------------------------------------------------------------------

packages/app/src/providers/models/selection.tsx

@@ -45,7 +45,7 @@ const Current = Persistence.struct({ session: SessionsSchema })
 
 export const ModelSelectionSchema = Persistence.migrate(
   Current,
-  Persistence.legacy({
+  Schema.Struct({
     session: Persistence.optional(Schema.Record(Schema.String, Schema.Unknown)),
     pick: Persistence.optional(Schema.Record(Schema.String, Schema.Unknown)),
   }).pipe(

packages/app/src/runtime/persistence/schema.test.ts

@@ -32,7 +32,7 @@ describe("persistence schemas", () => {
 
   test("legacy migration observes missing fields before initial defaults are applied", () => {
     const current = Persistence.struct({ mode: Schema.Literals(["compact", "full"]), enabled: Schema.Boolean })
-    const stored = Persistence.legacy({
+    const stored = Schema.Struct({
       mode: Schema.optional(Schema.Unknown),
       expanded: Schema.optional(Schema.Boolean),
     }).pipe(
@@ -53,38 +53,6 @@ describe("persistence schemas", () => {
     expect(Schema.encodeSync(schema)(decode({ expanded: true }))).toEqual({ mode: "full", enabled: true })
   })
 
-  test("legacy read shapes carry unknown nested fields through to the current schema", () => {
-    const current = Persistence.struct({
-      general: Persistence.struct({
-        mode: Schema.Literals(["compact", "full"]),
-        theme: Schema.String,
-        nested: Persistence.struct({ keep: Schema.Boolean }),
-      }),
-      other: Persistence.struct({ flag: Schema.Boolean }),
-    })
-    const stored = Persistence.legacy({
-      general: Persistence.optional(Persistence.legacy({ expanded: Persistence.optional(Schema.Boolean) })),
-    }).pipe(
-      Schema.decode({
-        decode: SchemaGetter.transform((value) => {
-          const general = value.general
-          if (!general || general.expanded === undefined) return value
-          return { ...value, general: { ...general, mode: general.expanded ? "full" : "compact" } }
-        }),
-        encode: SchemaGetter.passthrough(),
-      }),
-    )
-    const schema = Persistence.withInitial(Persistence.migrate(current, stored), {
-      general: { mode: "compact", theme: "light", nested: { keep: false } },
-      other: { flag: false },
-    })
-    const decode = Schema.decodeUnknownSync(schema)
-    expect(decode({ general: { expanded: true, theme: "dark", nested: { keep: true } }, other: { flag: true } })).toEqual({
-      general: { mode: "full", theme: "dark", nested: { keep: true } },
-      other: { flag: true },
-    })
-  })
-
   test("initial merging preserves field codecs and replaces arrays rather than merging indexes", () => {
     const current = Persistence.struct({
       amount: Schema.NumberFromString.check(Schema.isFinite()),

packages/app/src/runtime/persistence/schema.ts

@@ -23,11 +23,13 @@ export function withInitial<S extends Schema.ConstraintCodec<object, unknown>>(
   initial: NoInfer<S["Type"]>,
 ) {
   const schema = isMigrated(definition) ? definition.current : definition
-  const read = isMigrated(definition) ? SchemaParser.decodeUnknownResult(definition.read) : Result.succeed<unknown>
+  const read = isMigrated(definition)
+    ? SchemaParser.decodeUnknownResult(definition.read, { onExcessProperty: "preserve" })
+    : Result.succeed<unknown>
   const encode = Schema.encodeUnknownSync(schema)
   return Schema.Unknown.pipe(
     Schema.decode<Schema.Unknown>({
-      decode: SchemaGetter.transformEffect((value) =>
+      decode: SchemaGetter.transformOrFail((value) =>
         Effect.fromResult(Result.map(read(value), (stored) => merge(initial, recover(schema.ast, stored, initial)))),
       ),
       encode: SchemaGetter.transform((value) => encode(value)),
@@ -36,12 +38,6 @@ export function withInitial<S extends Schema.ConstraintCodec<object, unknown>>(
   )
 }
 
-// A legacy read shape declares only the fields it migrates. Decoding strips unknown keys, so every
-// struct level in a `migrate` read schema must stay open for the current fields it does not name.
-export function legacy<const Fields extends Schema.Struct.Fields>(fields: Fields) {
-  return Schema.StructWithRest(Schema.Struct(fields), [Schema.Record(Schema.String, Schema.Unknown)])
-}
-
 // Object-level codecs own their recovery. Plain structs can recover fields independently.
 function recover(ast: SchemaAST.AST, value: unknown, initial: unknown): unknown {
   if (value === undefined) return initial

packages/app/src/runtime/server/persistence.ts

@@ -53,7 +53,7 @@ const State = Persistence.struct({
 export function serverState(canonicalLocalServer: () => string | undefined = () => undefined) {
   return Persistence.migrate(
     State,
-    Persistence.legacy({ projects: Projects, lastProject: LastProject }).pipe(
+    Schema.Struct({ projects: Projects, lastProject: LastProject }).pipe(
       Schema.decode({
         decode: SchemaGetter.transform((value) => {
           const canonical = canonicalLocalServer()

packages/app/src/settings/model.tsx

@@ -185,9 +185,9 @@ function legacyTimelineActivity(value: boolean | "hidden" | "compact" | "full" |
 
 export const settingsPersistence = Persistence.migrate(
   settingsSchema,
-  Persistence.legacy({
+  Schema.Struct({
     general: Persistence.optional(
-      Persistence.legacy({
+      Schema.Struct({
         // Keep invalid explicit values distinct from absent values so legacy preferences cannot replace them.
         timelineDetail: Schema.optional(
           Schema.NullOr(

packages/app/src/shell/state/layout.tsx

@@ -176,16 +176,16 @@ export const layoutSchema = Persistence.struct({
 
 export const layoutPersistence = Persistence.migrate(
   layoutSchema,
-  Persistence.legacy({
+  Schema.Struct({
     sidebar: Persistence.optional(
-      Persistence.legacy({
+      Schema.Struct({
         workspaces: Persistence.optional(Schema.Union([Schema.Boolean, Schema.Record(Schema.String, Schema.Boolean)])),
         workspacesDefault: Persistence.optional(Schema.Boolean),
       }),
     ),
-    review: Persistence.optional(Persistence.legacy({ panelOpened: Persistence.optional(Schema.Boolean) })),
+    review: Persistence.optional(Schema.Struct({ panelOpened: Persistence.optional(Schema.Boolean) })),
     fileTree: Persistence.optional(
-      Persistence.legacy({
+      Schema.Struct({
         opened: Persistence.optional(Schema.Boolean),
         width: Persistence.optional(Schema.Finite),
         tab: Persistence.optional(Schema.Literals(["changes", "all"])),

packages/cli/src/commands/commands.ts

@@ -3,8 +3,8 @@ import { Schema } from "effect"
 import { Spec } from "../framework/spec"
 import { Updater } from "../services/updater"
 
-export const PrintLogs = GlobalFlag.Setting("print-logs")({
-  flag: Flag.Boolean("print-logs").pipe(
+export const PrintLogs = GlobalFlag.setting("print-logs")({
+  flag: Flag.boolean("print-logs").pipe(
     Flag.withDescription("Print logs to stderr (server logs require --standalone)"),
     Flag.withDefault(false),
   ),
@@ -13,23 +13,23 @@ export const PrintLogs = GlobalFlag.Setting("print-logs")({
 declare const OPENCODE_CLI_NAME: string | undefined
 
 const ServerParams = {
-  standalone: Flag.Boolean("standalone").pipe(
+  standalone: Flag.boolean("standalone").pipe(
     Flag.withDescription("Run with a private server instead of the background service"),
     Flag.withDefault(false),
   ),
-  server: Flag.String("server").pipe(
+  server: Flag.string("server").pipe(
     Flag.withDescription("Connect to a server URL instead of the background service"),
     Flag.optional,
   ),
 }
 
 const PermissionParams = {
-  auto: Flag.Boolean("auto").pipe(
+  auto: Flag.boolean("auto").pipe(
     Flag.withDescription("Auto-approve permissions that are not explicitly denied"),
     Flag.withDefault(false),
   ),
-  yolo: Flag.Boolean("yolo").pipe(Flag.withDefault(false), Flag.withHidden),
-  dangerouslySkipPermissions: Flag.Boolean("dangerously-skip-permissions").pipe(
+  yolo: Flag.boolean("yolo").pipe(Flag.withDefault(false), Flag.withHidden),
+  dangerouslySkipPermissions: Flag.boolean("dangerously-skip-permissions").pipe(
     Flag.withDefault(false),
     Flag.withHidden,
   ),
@@ -40,32 +40,32 @@ const Root = Spec.make(typeof OPENCODE_CLI_NAME === "string" ? OPENCODE_CLI_NAME
   params: {
     ...ServerParams,
     ...PermissionParams,
-    directory: Argument.String("directory").pipe(
+    directory: Argument.string("directory").pipe(
       Argument.withDescription("Directory to start OpenCode in"),
       Argument.optional,
     ),
-    continue: Flag.Boolean("continue").pipe(
+    continue: Flag.boolean("continue").pipe(
       Flag.withAlias("c"),
       Flag.withDescription("Continue the last session"),
       Flag.withDefault(false),
     ),
-    session: Flag.String("session").pipe(
+    session: Flag.string("session").pipe(
       Flag.withAlias("s"),
-      Flag.withDescription("Session ID to continue"),
+      Flag.withDescription("Session ID to continue, or to create if it does not exist"),
       Flag.optional,
     ),
-    prompt: Flag.String("prompt").pipe(Flag.withDescription("Prompt to use"), Flag.optional),
+    prompt: Flag.string("prompt").pipe(Flag.withDescription("Prompt to use"), Flag.optional),
   },
   commands: [
     Spec.make("upgrade", {
       description: "Upgrade OpenCode to the latest or a specific version",
       aliases: ["update"],
       params: {
-        target: Argument.String("target").pipe(
+        target: Argument.string("target").pipe(
           Argument.withDescription("Version to upgrade to (with or without a leading v)"),
           Argument.optional,
         ),
-        method: Flag.Literals("method", Updater.methods).pipe(
+        method: Flag.choice("method", Updater.methods).pipe(
           Flag.withAlias("m"),
           Flag.withDescription("Installation method to use"),
           Flag.optional,
@@ -75,21 +75,21 @@ const Root = Spec.make(typeof OPENCODE_CLI_NAME === "string" ? OPENCODE_CLI_NAME
     Spec.make("uninstall", {
       description: "Uninstall OpenCode and remove all related files",
       params: {
-        keepConfig: Flag.Boolean("keep-config").pipe(
+        keepConfig: Flag.boolean("keep-config").pipe(
           Flag.withAlias("c"),
           Flag.withDescription("Keep configuration files"),
           Flag.withDefault(false),
         ),
-        keepData: Flag.Boolean("keep-data").pipe(
+        keepData: Flag.boolean("keep-data").pipe(
           Flag.withAlias("d"),
           Flag.withDescription("Keep session data and snapshots"),
           Flag.withDefault(false),
         ),
-        dryRun: Flag.Boolean("dry-run").pipe(
+        dryRun: Flag.boolean("dry-run").pipe(
           Flag.withDescription("Show what would be removed without removing"),
           Flag.withDefault(false),
         ),
-        force: Flag.Boolean("force").pipe(
+        force: Flag.boolean("force").pipe(
           Flag.withAlias("f"),
           Flag.withDescription("Skip confirmation prompts"),
           Flag.withDefault(false),
@@ -101,17 +101,17 @@ const Root = Spec.make(typeof OPENCODE_CLI_NAME === "string" ? OPENCODE_CLI_NAME
       description: "Make a request to the running server",
       params: {
         ...ServerParams,
-        request: Argument.String("operation | method path").pipe(
+        request: Argument.string("operation | method path").pipe(
           Argument.withDescription("OpenAPI operation ID, or an HTTP method followed by a path"),
           Argument.variadic({ min: 1, max: 2 }),
         ),
-        data: Flag.String("data").pipe(Flag.withAlias("d"), Flag.withDescription("Request body"), Flag.optional),
-        header: Flag.String("header").pipe(
+        data: Flag.string("data").pipe(Flag.withAlias("d"), Flag.withDescription("Request body"), Flag.optional),
+        header: Flag.string("header").pipe(
           Flag.withAlias("H"),
           Flag.withDescription("Request header in name:value form"),
           Flag.atMost(100),
         ),
-        param: Flag.KeyValuePair("param").pipe(Flag.withDescription("OpenAPI path or query parameter"), Flag.optional),
+        param: Flag.keyValuePair("param").pipe(Flag.withDescription("OpenAPI path or query parameter"), Flag.optional),
       },
     }),
     Spec.make("debug", {
@@ -122,7 +122,7 @@ const Root = Spec.make(typeof OPENCODE_CLI_NAME === "string" ? OPENCODE_CLI_NAME
         Spec.make("paths", {
           description: "Show global paths (data, config, cache, state)",
           params: {
-            name: Argument.Literals("name", [
+            name: Argument.choice("name", [
               "db",
               "home",
               "data",
@@ -134,9 +134,7 @@ const Root = Spec.make(typeof OPENCODE_CLI_NAME === "string" ? OPENCODE_CLI_NAME
               "log",
               "repos",
             ]).pipe(
-              Argument.withDescription(
-                "Print only one path: db, home, data, config, cache, state, tmp, bin, log, repos",
-              ),
+              Argument.withDescription("Print only one path: db, home, data, config, cache, state, tmp, bin, log, repos"),
               Argument.optional,
             ),
           },
@@ -150,7 +148,7 @@ const Root = Spec.make(typeof OPENCODE_CLI_NAME === "string" ? OPENCODE_CLI_NAME
           description: "list integrations and credentials",
           params: {
             ...ServerParams,
-            format: Flag.Literals("format", ["default", "json"]).pipe(
+            format: Flag.choice("format", ["default", "json"]).pipe(
               Flag.withDescription("Output format"),
               Flag.withDefault("default"),
             ),
@@ -160,12 +158,12 @@ const Root = Spec.make(typeof OPENCODE_CLI_NAME === "string" ? OPENCODE_CLI_NAME
           description: "connect an integration",
           params: {
             ...ServerParams,
-            target: Argument.String("target").pipe(
+            target: Argument.string("target").pipe(
               Argument.withDescription("Integration ID, name, or well-known provider URL"),
               Argument.optional,
             ),
-            method: Flag.String("method").pipe(Flag.withDescription("Authentication method ID"), Flag.optional),
-            answer: Flag.String("answer").pipe(
+            method: Flag.string("method").pipe(Flag.withDescription("Authentication method ID"), Flag.optional),
+            answer: Flag.string("answer").pipe(
               Flag.withDescription("Provider form answer (key=value; repeat for multiple fields)"),
               Flag.atMost(100),
             ),
@@ -175,11 +173,11 @@ const Root = Spec.make(typeof OPENCODE_CLI_NAME === "string" ? OPENCODE_CLI_NAME
           description: "log out of a saved account",
           params: {
             ...ServerParams,
-            target: Argument.String("target").pipe(
+            target: Argument.string("target").pipe(
               Argument.withDescription("Integration ID or name"),
               Argument.optional,
             ),
-            credential: Argument.String("credential").pipe(
+            credential: Argument.string("credential").pipe(
               Argument.withDescription("Credential ID or label (opens an account picker when omitted)"),
               Argument.optional,
             ),
@@ -189,11 +187,11 @@ const Root = Spec.make(typeof OPENCODE_CLI_NAME === "string" ? OPENCODE_CLI_NAME
           description: "switch the active account for an integration",
           params: {
             ...ServerParams,
-            target: Argument.String("target").pipe(
+            target: Argument.string("target").pipe(
               Argument.withDescription("Integration ID or name"),
               Argument.optional,
             ),
-            credential: Argument.String("credential").pipe(
+            credential: Argument.string("credential").pipe(
               Argument.withDescription("Credential ID or label (opens an account picker when omitted)"),
               Argument.optional,
             ),
@@ -208,21 +206,21 @@ const Root = Spec.make(typeof OPENCODE_CLI_NAME === "string" ? OPENCODE_CLI_NAME
         Spec.make("add", {
           description: "Add an MCP server to your configuration",
           params: {
-            name: Argument.String("name").pipe(Argument.withDescription("Name of the MCP server")),
-            command: Argument.String("command").pipe(
+            name: Argument.string("name").pipe(Argument.withDescription("Name of the MCP server")),
+            command: Argument.string("command").pipe(
               Argument.withDescription("Command and arguments for a local server, passed after --"),
               Argument.variadic({ min: 0 }),
             ),
-            url: Flag.String("url").pipe(Flag.withDescription("URL for a remote MCP server"), Flag.optional),
-            header: Flag.KeyValuePair("header").pipe(
+            url: Flag.string("url").pipe(Flag.withDescription("URL for a remote MCP server"), Flag.optional),
+            header: Flag.keyValuePair("header").pipe(
               Flag.withDescription("HTTP header for a remote server, as name=value"),
               Flag.optional,
             ),
-            env: Flag.KeyValuePair("env").pipe(
+            env: Flag.keyValuePair("env").pipe(
               Flag.withDescription("Environment variable for a local server, as name=value"),
               Flag.optional,
             ),
-            global: Flag.Boolean("global").pipe(
+            global: Flag.boolean("global").pipe(
               Flag.withDescription("Write to the global config instead of the project config"),
               Flag.withDefault(false),
             ),
@@ -231,12 +229,12 @@ const Root = Spec.make(typeof OPENCODE_CLI_NAME === "string" ? OPENCODE_CLI_NAME
         Spec.make("auth", {
           description: "Authenticate with an OAuth-capable remote MCP server",
           params: {
-            name: Argument.String("name").pipe(Argument.withDescription("Name of the MCP server"), Argument.optional),
+            name: Argument.string("name").pipe(Argument.withDescription("Name of the MCP server"), Argument.optional),
           },
         }),
         Spec.make("logout", {
           description: "Remove stored OAuth credentials for an MCP server",
-          params: { name: Argument.String("name").pipe(Argument.withDescription("Name of the MCP server")) },
+          params: { name: Argument.string("name").pipe(Argument.withDescription("Name of the MCP server")) },
         }),
       ],
     }),
@@ -246,7 +244,7 @@ const Root = Spec.make(typeof OPENCODE_CLI_NAME === "string" ? OPENCODE_CLI_NAME
         Spec.make("list", {
           description: "List plugins",
           params: {
-            builtin: Flag.Boolean("builtin").pipe(
+            builtin: Flag.boolean("builtin").pipe(
               Flag.withDescription("Include built-in server plugins"),
               Flag.withDefault(false),
             ),
@@ -255,13 +253,13 @@ const Root = Spec.make(typeof OPENCODE_CLI_NAME === "string" ? OPENCODE_CLI_NAME
         Spec.make("add", {
           description: "Install a plugin and add it to the global configuration",
           params: {
-            package: Argument.String("package").pipe(Argument.withDescription("npm registry or Git package specifier")),
+            package: Argument.string("package").pipe(Argument.withDescription("npm registry or Git package specifier")),
           },
         }),
         Spec.make("check", {
           description: "Check package plugins for updates",
           params: {
-            target: Argument.String("target").pipe(
+            target: Argument.string("target").pipe(
               Argument.withDescription("Configured package target"),
               Argument.optional,
             ),
@@ -270,7 +268,7 @@ const Root = Spec.make(typeof OPENCODE_CLI_NAME === "string" ? OPENCODE_CLI_NAME
         Spec.make("update", {
           description: "Update package plugins",
           params: {
-            target: Argument.String("target").pipe(
+            target: Argument.string("target").pipe(
               Argument.withDescription("Configured package target; omit to update all outdated plugins"),
               Argument.optional,
             ),
@@ -279,7 +277,7 @@ const Root = Spec.make(typeof OPENCODE_CLI_NAME === "string" ? OPENCODE_CLI_NAME
         Spec.make("remove", {
           description: "Remove a plugin from global configuration",
           params: {
-            package: Argument.String("package").pipe(Argument.withDescription("configured package specifier")),
+            package: Argument.string("package").pipe(Argument.withDescription("configured package specifier")),
           },
         }),
       ],
@@ -292,108 +290,108 @@ const Root = Spec.make(typeof OPENCODE_CLI_NAME === "string" ? OPENCODE_CLI_NAME
       description: "Show shareable usage statistics",
       params: {
         ...ServerParams,
-        days: Flag.Int("days").pipe(
+        days: Flag.integer("days").pipe(
           Flag.withSchema(Schema.Int.check(Schema.isGreaterThanOrEqualTo(0))),
           Flag.withDescription("Show the last N days; 0 means today"),
           Flag.optional,
         ),
-        year: Flag.Int("year").pipe(
+        year: Flag.integer("year").pipe(
           Flag.withSchema(Schema.Int.check(Schema.isBetween({ minimum: 1970, maximum: 9_999 }))),
           Flag.withDescription("Show a calendar year"),
           Flag.optional,
         ),
-        all: Flag.Boolean("all").pipe(Flag.withDescription("Show lifetime statistics"), Flag.withDefault(false)),
-        project: Flag.String("project").pipe(
+        all: Flag.boolean("all").pipe(Flag.withDescription("Show lifetime statistics"), Flag.withDefault(false)),
+        project: Flag.string("project").pipe(
           Flag.withDescription('Filter by project ID, or use "." for the current project'),
           Flag.optional,
         ),
-        models: Flag.Boolean("models").pipe(Flag.withDescription("Show model usage"), Flag.withDefault(false)),
-        tools: Flag.Boolean("tools").pipe(Flag.withDescription("Show tool reliability"), Flag.withDefault(false)),
-        cost: Flag.Boolean("cost").pipe(Flag.withDescription("Show cost and token details"), Flag.withDefault(false)),
-        full: Flag.Boolean("full").pipe(Flag.withDescription("Show every detailed section"), Flag.withDefault(false)),
-        limit: Flag.Int("limit").pipe(
+        models: Flag.boolean("models").pipe(Flag.withDescription("Show model usage"), Flag.withDefault(false)),
+        tools: Flag.boolean("tools").pipe(Flag.withDescription("Show tool reliability"), Flag.withDefault(false)),
+        cost: Flag.boolean("cost").pipe(Flag.withDescription("Show cost and token details"), Flag.withDefault(false)),
+        full: Flag.boolean("full").pipe(Flag.withDescription("Show every detailed section"), Flag.withDefault(false)),
+        limit: Flag.integer("limit").pipe(
           Flag.withSchema(Schema.Int.check(Schema.isGreaterThanOrEqualTo(1))),
           Flag.withDescription("Number of rows in detailed sections"),
           Flag.withDefault(5),
         ),
-        json: Flag.Boolean("json").pipe(Flag.withDescription("Output statistics as JSON"), Flag.withDefault(false)),
+        json: Flag.boolean("json").pipe(Flag.withDescription("Output statistics as JSON"), Flag.withDefault(false)),
       },
     }),
     Spec.make("mini", {
       description: "Start the minimal interactive interface",
       params: {
         ...ServerParams,
-        continue: Flag.Boolean("continue").pipe(
+        continue: Flag.boolean("continue").pipe(
           Flag.withAlias("c"),
           Flag.withDescription("Continue the last session"),
           Flag.withDefault(false),
         ),
-        session: Flag.String("session").pipe(
+        session: Flag.string("session").pipe(
           Flag.withAlias("s"),
-          Flag.withDescription("Session ID to continue"),
+          Flag.withDescription("Session ID to continue, or to create if it does not exist"),
           Flag.optional,
         ),
-        fork: Flag.Boolean("fork").pipe(
+        fork: Flag.boolean("fork").pipe(
           Flag.withDescription("Fork the session when continuing"),
           Flag.withDefault(false),
         ),
-        replay: Flag.Boolean("replay").pipe(
+        replay: Flag.boolean("replay").pipe(
           Flag.withDescription("Restore session history on resume and resize (disable with --no-replay)"),
           Flag.optional,
         ),
-        replayLimit: Flag.Int("replay-limit").pipe(
+        replayLimit: Flag.integer("replay-limit").pipe(
           Flag.withDescription("Limit replay to the newest N messages (default: 200)"),
           Flag.optional,
         ),
-        model: Flag.String("model").pipe(
+        model: Flag.string("model").pipe(
           Flag.withAlias("m"),
           Flag.withDescription("Model to use in the format provider/model"),
           Flag.optional,
         ),
-        agent: Flag.String("agent").pipe(Flag.withDescription("Agent to use"), Flag.optional),
-        prompt: Flag.String("prompt").pipe(Flag.withDescription("Prompt to use"), Flag.optional),
-        demo: Flag.Boolean("demo").pipe(Flag.withDefault(false), Flag.withHidden),
+        agent: Flag.string("agent").pipe(Flag.withDescription("Agent to use"), Flag.optional),
+        prompt: Flag.string("prompt").pipe(Flag.withDescription("Prompt to use"), Flag.optional),
+        demo: Flag.boolean("demo").pipe(Flag.withDefault(false), Flag.withHidden),
       },
     }),
     Spec.make("run", {
       description: "Run OpenCode with a message",
       params: {
         ...ServerParams,
-        message: Argument.String("message").pipe(
+        message: Argument.string("message").pipe(
           Argument.withDescription("Message to send"),
           Argument.variadic({ min: 0 }),
         ),
-        continue: Flag.Boolean("continue").pipe(
+        continue: Flag.boolean("continue").pipe(
           Flag.withAlias("c"),
           Flag.withDescription("Continue the last session"),
           Flag.withDefault(false),
         ),
-        session: Flag.String("session").pipe(
+        session: Flag.string("session").pipe(
           Flag.withAlias("s"),
-          Flag.withDescription("Session ID to continue"),
+          Flag.withDescription("Session ID to continue, or to create if it does not exist"),
           Flag.optional,
         ),
-        fork: Flag.Boolean("fork").pipe(
+        fork: Flag.boolean("fork").pipe(
           Flag.withDescription("Fork the session before continuing"),
           Flag.withDefault(false),
         ),
-        model: Flag.String("model").pipe(
+        model: Flag.string("model").pipe(
           Flag.withAlias("m"),
           Flag.withDescription("Model to use in the format provider/model#variant"),
           Flag.optional,
         ),
-        agent: Flag.String("agent").pipe(Flag.withDescription("Agent to use"), Flag.optional),
-        format: Flag.Literals("format", ["default", "json"]).pipe(
+        agent: Flag.string("agent").pipe(Flag.withDescription("Agent to use"), Flag.optional),
+        format: Flag.choice("format", ["default", "json"]).pipe(
           Flag.withDescription("Output format"),
           Flag.withDefault("default"),
         ),
-        file: Flag.String("file").pipe(
+        file: Flag.string("file").pipe(
           Flag.withAlias("f"),
           Flag.withDescription("File to attach to the message"),
           Flag.atMost(100),
         ),
-        title: Flag.String("title").pipe(Flag.withDescription("Session title"), Flag.optional),
-        thinking: Flag.Boolean("thinking").pipe(Flag.withDescription("Show thinking blocks"), Flag.withDefault(false)),
+        title: Flag.string("title").pipe(Flag.withDescription("Session title"), Flag.optional),
+        thinking: Flag.boolean("thinking").pipe(Flag.withDescription("Show thinking blocks"), Flag.withDefault(false)),
         ...PermissionParams,
       },
     }),
@@ -404,13 +402,13 @@ const Root = Spec.make(typeof OPENCODE_CLI_NAME === "string" ? OPENCODE_CLI_NAME
           description: "List top-level sessions in the current project, newest first",
           params: {
             ...ServerParams,
-            maxCount: Flag.Int("max-count").pipe(
+            maxCount: Flag.integer("max-count").pipe(
               Flag.withAlias("n"),
               Flag.withSchema(Schema.Int.check(Schema.isGreaterThanOrEqualTo(1))),
               Flag.withDescription("Limit to N most recent sessions (default: 100)"),
               Flag.optional,
             ),
-            format: Flag.Literals("format", ["table", "json"]).pipe(
+            format: Flag.choice("format", ["table", "json"]).pipe(
               Flag.withDescription("Output format"),
               Flag.withDefault("table"),
             ),
@@ -420,18 +418,18 @@ const Root = Spec.make(typeof OPENCODE_CLI_NAME === "string" ? OPENCODE_CLI_NAME
           description: "Delete a session and its child sessions",
           params: {
             ...ServerParams,
-            sessionID: Argument.String("sessionID").pipe(Argument.withDescription("Session ID to delete")),
+            sessionID: Argument.string("sessionID").pipe(Argument.withDescription("Session ID to delete")),
           },
         }),
         Spec.make("export", {
           description: "Export session data as JSON",
           params: {
             ...ServerParams,
-            session: Argument.String("session").pipe(
+            session: Argument.string("session").pipe(
               Argument.withDescription("Session ID to export"),
               Argument.optional,
             ),
-            sanitize: Flag.Boolean("sanitize").pipe(
+            sanitize: Flag.boolean("sanitize").pipe(
               Flag.withDescription("Redact sensitive transcript and file data"),
               Flag.withDefault(false),
             ),
@@ -441,8 +439,8 @@ const Root = Spec.make(typeof OPENCODE_CLI_NAME === "string" ? OPENCODE_CLI_NAME
           description: "Import session data from a JSON file or URL",
           params: {
             ...ServerParams,
-            file: Argument.String("file").pipe(Argument.withDescription("JSON file or URL to import")),
-            directory: Flag.String("directory").pipe(
+            file: Argument.string("file").pipe(Argument.withDescription("JSON file or URL to import")),
+            directory: Flag.string("directory").pipe(
               Flag.withDescription("Directory in which to import the session"),
               Flag.optional,
             ),
@@ -460,8 +458,8 @@ const Root = Spec.make(typeof OPENCODE_CLI_NAME === "string" ? OPENCODE_CLI_NAME
         Spec.make("get", {
           description: "Get service configuration",
           params: {
-            key: Argument.String("key").pipe(Argument.withDescription("Service setting or env"), Argument.optional),
-            name: Argument.String("name").pipe(
+            key: Argument.string("key").pipe(Argument.withDescription("Service setting or env"), Argument.optional),
+            name: Argument.string("name").pipe(
               Argument.withDescription("Environment variable name"),
               Argument.optional,
             ),
@@ -470,11 +468,11 @@ const Root = Spec.make(typeof OPENCODE_CLI_NAME === "string" ? OPENCODE_CLI_NAME
         Spec.make("set", {
           description: "Set service configuration",
           params: {
-            key: Argument.String("key").pipe(Argument.withDescription("Service setting or env")),
-            value: Argument.String("value").pipe(
+            key: Argument.string("key").pipe(Argument.withDescription("Service setting or env")),
+            value: Argument.string("value").pipe(
               Argument.withDescription("Setting value or environment variable name"),
             ),
-            nestedValue: Argument.String("env-value").pipe(
+            nestedValue: Argument.string("env-value").pipe(
               Argument.withDescription("Environment variable value"),
               Argument.optional,
             ),
@@ -483,8 +481,8 @@ const Root = Spec.make(typeof OPENCODE_CLI_NAME === "string" ? OPENCODE_CLI_NAME
         Spec.make("unset", {
           description: "Unset service configuration",
           params: {
-            key: Argument.String("key").pipe(Argument.withDescription("Service setting or env")),
-            name: Argument.String("name").pipe(
+            key: Argument.string("key").pipe(Argument.withDescription("Service setting or env")),
+            name: Argument.string("name").pipe(
               Argument.withDescription("Environment variable name"),
               Argument.optional,
             ),
@@ -501,7 +499,7 @@ const Root = Spec.make(typeof OPENCODE_CLI_NAME === "string" ? OPENCODE_CLI_NAME
     Spec.make("pair", {
       description: "Print one-time links to connect a browser or app",
       params: {
-        url: Flag.String("url").pipe(
+        url: Flag.string("url").pipe(
           Flag.withDescription("Use an external HTTP(S) server URL in pairing links"),
           Flag.mapTryCatch(
             (value) => {
@@ -519,15 +517,15 @@ const Root = Spec.make(typeof OPENCODE_CLI_NAME === "string" ? OPENCODE_CLI_NAME
     Spec.make("serve", {
       description: "Start the v2 API and web server",
       params: {
-        hostname: Flag.String("hostname").pipe(Flag.optional),
-        port: Flag.Int("port").pipe(Flag.optional),
-        cors: Flag.String("cors").pipe(
+        hostname: Flag.string("hostname").pipe(Flag.optional),
+        port: Flag.integer("port").pipe(Flag.optional),
+        cors: Flag.string("cors").pipe(
           Flag.withSchema(Schema.NonEmptyString),
           Flag.withDescription("Additional allowed CORS origin (repeat for multiple origins)"),
           Flag.atLeast(0),
         ),
-        service: Flag.Boolean("service").pipe(Flag.withDefault(false)),
-        stdio: Flag.Boolean("stdio").pipe(Flag.withDefault(false)),
+        service: Flag.boolean("service").pipe(Flag.withDefault(false)),
+        stdio: Flag.boolean("stdio").pipe(Flag.withDefault(false)),
       },
     }),
   ],

packages/cli/src/commands/handlers/default.ts

@@ -11,6 +11,10 @@ import { UpdatePreflight } from "../../services/update-preflight"
 import { Npm } from "@opencode/util/npm"
 import { OPENCODE_ARTIFACT, OPENCODE_CHANNEL, OPENCODE_VERSION } from "../../version"
 import { Env } from "../../env"
+import { Service } from "@opencode/client/effect/service"
+import { OpenCode } from "@opencode/client/promise"
+import { findSession } from "../../session-target"
+import { errorMessage } from "../../util/error"
 
 export default Runtime.handler(Commands, (input) =>
   Effect.gen(function* () {
@@ -46,6 +50,15 @@ export default Runtime.handler(Commands, (input) =>
         Effect.promise(() => preflight.fail("OpenCode update could not start the new background service")),
       ),
     )
+    const session = Option.getOrUndefined(input.session)
+    // A missing --session ID becomes the ID of the session the first prompt creates.
+    const sessionExists =
+      session !== undefined &&
+      (yield* Effect.tryPromise({
+        try: () =>
+          findSession(OpenCode.make({ baseUrl: server.endpoint.url, headers: Service.headers(server.endpoint) }), session),
+        catch: (cause) => new Error(errorMessage(cause)),
+      })) !== undefined
     const updater = yield* Updater.Service
     let installing: string | undefined
     const updateListeners = new Set<(version: string) => void>()
@@ -81,7 +94,8 @@ export default Runtime.handler(Commands, (input) =>
       },
       args: {
         continue: input.continue,
-        sessionID: Option.getOrUndefined(input.session),
+        sessionID: sessionExists ? session : undefined,
+        newSessionID: sessionExists ? undefined : session,
         prompt: Option.getOrUndefined(input.prompt),
         auto: input.auto || input.yolo || input.dangerouslySkipPermissions,
       },

packages/cli/src/env.ts

@@ -7,8 +7,8 @@ import { Config } from "effect"
 // The opencode server password: sent by clients connecting to an explicit
 // --server, and adopted by a manually run or standalone server. The legacy
 // name is still honored.
-export const password = Config.Redacted("OPENCODE_PASSWORD").pipe(
-  Config.orElse(() => Config.Redacted("OPENCODE_SERVER_PASSWORD")),
+export const password = Config.redacted("OPENCODE_PASSWORD").pipe(
+  Config.orElse(() => Config.redacted("OPENCODE_SERVER_PASSWORD")),
   Config.withDefault(undefined),
 )
 

packages/cli/src/run/noninteractive.ts

@@ -135,6 +135,7 @@ export async function runNonInteractivePrompt(input: Input) {
   const replyPermission = async (request: { id: string; action: string; resources: ReadonlyArray<string> }) => {
     if (!input.auto) {
       permissionRejected = true
+      if (input.compatibility !== "v1") process.exitCode = 1
       UI.println(
         UI.Style.TEXT_WARNING_BOLD + "!",
         UI.Style.TEXT_NORMAL +
@@ -163,6 +164,7 @@ export async function runNonInteractivePrompt(input: Input) {
       if (!formAlreadySettled(error)) throw error
     }
     formCancelled = true
+    if (input.compatibility !== "v1") process.exitCode = 1
   }
 
   const consume = async () => {
@@ -493,7 +495,8 @@ export async function runNonInteractivePrompt(input: Input) {
       if (event.type === "session.execution.interrupted") {
         if (input.compatibility === "v1" && (permissionRejected || formCancelled)) return
         if (event.data.reason === "user" && interrupted) process.exitCode = 130
-        if (event.data.reason !== "user" && !emittedError) {
+        // A declined tool call ends the step with an interruption; it was already reported above.
+        if (event.data.reason !== "user" && !emittedError && !permissionRejected && !formCancelled) {
           emittedError = true
           process.exitCode = 1
           const error = { type: "aborted" as const, message: `Session interrupted: ${event.data.reason}` }
@@ -620,7 +623,9 @@ export async function runNonInteractivePrompt(input: Input) {
         UI.error(item.state.error.message)
       }
 
-      if (message.error && !emittedError) {
+      // A declined tool call ends its step with an interrupted-step error that is
+      // only a consequence of our own rejection; it was already reported above.
+      if (message.error && !emittedError && !permissionRejected && !formCancelled) {
         emittedError = true
         process.exitCode = 1
         if (!emit("error", timestamp, { error: message.error })) UI.error(message.error.message)

packages/cli/src/services/service-registration.ts

@@ -4,7 +4,6 @@ import { Service, type Info } from "@opencode/client/effect/service"
 import path from "node:path"
 import { Effect, FileSystem, Schedule, Schema } from "effect"
 import { HttpServer } from "effect/unstable/http"
-import { NetAddress } from "effect/unstable/net"
 import { OPENCODE_VERSION } from "../version"
 
 const infoJson = Schema.fromJsonString(Service.Info)
@@ -12,7 +11,7 @@ const encodeInfo = Schema.encodeEffect(infoJson)
 const decodeInfo = Schema.decodeUnknownEffect(infoJson)
 
 export const register = Effect.fnUntraced(function* (options: {
-  readonly address: NetAddress.SocketAddress
+  readonly address: HttpServer.Address
   readonly password: string
   readonly id: string
   readonly file: string

packages/cli/src/session-target.ts

@@ -63,6 +63,7 @@ export async function resolveSessionTarget(input: {
     (await input.client.session
       .create(
         {
+          id: input.session,
           agent: prepared.agent,
           model: prepared.model,
           location: { directory: location.directory },
@@ -101,14 +102,11 @@ async function selectSession(input: {
   fork?: boolean
   signal?: AbortSignal
 }) {
-  const explicit = input.session
-    ? await input.client.session.get({ sessionID: input.session }, ...requestOptions(input.signal)).catch((error) => {
-        if (error && typeof error === "object" && "_tag" in error && error._tag === "SessionNotFoundError")
-          return undefined
-        throw error
-      })
-    : undefined
-  if (input.session && !explicit) throw new Error("Session not found")
+  const explicit = input.session ? await findSession(input.client, input.session, input.signal) : undefined
+  if (input.session && !explicit) {
+    if (input.fork) throw new Error("Session not found")
+    return { session: undefined }
+  }
   if (explicit)
     return {
       session: input.fork
@@ -133,6 +131,13 @@ async function selectSession(input: {
   }
 }
 
+export function findSession(client: OpenCodeClient, sessionID: string, signal?: AbortSignal) {
+  return client.session.get({ sessionID }, ...requestOptions(signal)).catch((error) => {
+    if (error && typeof error === "object" && "_tag" in error && error._tag === "SessionNotFoundError") return undefined
+    throw error
+  })
+}
+
 async function latestSession(
   client: OpenCodeClient,
   location: LocationGetOutput,

packages/cli/src/ssh-askpass.ts

@@ -1,6 +1,5 @@
 import { NodeSocket } from "@effect/platform-node"
 import { Effect, Schema, Stdio, Stream } from "effect"
-import { Socket } from "effect/unstable/socket"
 
 const Response = Schema.fromJsonString(Schema.Struct({ value: Schema.NullOr(Schema.String) }))
 const Port = Schema.NumberFromString.check(Schema.isInt(), Schema.isGreaterThan(0), Schema.isLessThanOrEqualTo(65535))
@@ -11,15 +10,16 @@ export const askpass = Effect.gen(function* () {
   const port = yield* Schema.decodeUnknownEffect(Port)(process.env.OPENCODE_SSH_ASKPASS_PORT)
   const stdio = yield* Stdio.Stdio
   const socket = yield* NodeSocket.makeNet({ host: "127.0.0.1", port })
-  const writer = yield* socket.writer
+  const write = yield* socket.writer
   const response = { text: "" }
   yield* Effect.all(
     [
-      Effect.gen(function* () {
-        const pull = yield* Socket.readerString(socket)
-        while (true) response.text += (yield* pull).join("")
-      }).pipe(Effect.catchReason("SocketError", "SocketCloseError", () => Effect.void)),
-      writer.write(
+      socket.runString((text) =>
+        Effect.sync(() => {
+          response.text += text
+        }),
+      ),
+      write(
         JSON.stringify({
           token: process.env.OPENCODE_SSH_ASKPASS_TOKEN,
           text: process.argv.slice(2).join(" "),

packages/cli/test/service.test.ts

@@ -4,7 +4,6 @@ import { Global } from "@opencode/util/global"
 import { OPENCODE_VERSION } from "../src/version"
 import { expect, test } from "bun:test"
 import { Effect, Schema } from "effect"
-import { NetAddress } from "effect/unstable/net"
 import fs from "node:fs/promises"
 import os from "node:os"
 import path from "node:path"
@@ -502,7 +501,7 @@ test("service registration replaces a stale owner with the bound address", async
   try {
     const cleanup = await Effect.runPromise(
       ServiceRegistration.register({
-        address: NetAddress.inetAddressFromIpStringUnsafe("127.0.0.1", 4321),
+        address: { _tag: "TcpAddress", hostname: "127.0.0.1", port: 4321 },
         password: "secret",
         id: "owner",
         file: registration,

packages/cli/test/session-target.test.ts

@@ -42,6 +42,28 @@ describe("session target resolver", () => {
     })
   })
 
+  test("creates a missing explicit Session with its ID", async () => {
+    const client = OpenCode.make({ baseUrl: "https://opencode.test" })
+    spyOn(client.session, "get").mockRejectedValue({ _tag: "SessionNotFoundError" })
+    spyOn(client.location, "get").mockResolvedValue(location("/project"))
+    const create = spyOn(client.session, "create").mockResolvedValue(session("ses_chosen", "/project"))
+
+    const target = await resolveSessionTarget({ client, session: "ses_chosen", prepare })
+    expect(create).toHaveBeenCalledWith(expect.objectContaining({ id: "ses_chosen" }))
+    expect(target).toMatchObject({ session: { id: "ses_chosen" }, resume: false })
+  })
+
+  test("does not create a missing explicit Session to fork", async () => {
+    const client = OpenCode.make({ baseUrl: "https://opencode.test" })
+    spyOn(client.session, "get").mockRejectedValue({ _tag: "SessionNotFoundError" })
+    const create = spyOn(client.session, "create")
+
+    await expect(resolveSessionTarget({ client, session: "ses_chosen", fork: true, prepare })).rejects.toThrow(
+      "Session not found",
+    )
+    expect(create).not.toHaveBeenCalled()
+  })
+
   test("paginates to continue the exact directory", async () => {
     const client = OpenCode.make({ baseUrl: "https://opencode.test" })
     spyOn(client.location, "get").mockResolvedValue(location("/project"))

packages/client/package.json

@@ -37,7 +37,7 @@
     "@opencode/protocol": "workspace:*"
   },
   "peerDependencies": {
-    "effect": "4.0.0-rc.117",
+    "effect": "4.0.0-rc.112",
     "solid-js": ">=1.9.0"
   },
   "peerDependenciesMeta": {

packages/client/src/promise/generated/types.ts

@@ -2117,6 +2117,7 @@ export type ConfigEntry =
             name?: string
             env?: Array<string>
             package?: string
+            compatibility?: ModelCompatibility
             settings?: ConfigProviderSettings
             headers?: { [x: string]: string }
             body?: { [x: string]: JsonValue }

packages/codemode/src/tool-schema.ts

@@ -1,4 +1,4 @@
-import { JsonPointer, Schema, SchemaAST } from "effect"
+import { JsonPointer, Schema } from "effect"
 import type { Tool, JsonSchema, SchemaType } from "./tool.js"
 
 const isEffectSchema = (schema: SchemaType): schema is Schema.Decoder<unknown> & Schema.Top => Schema.isSchema(schema)
@@ -12,14 +12,8 @@ const renderKey = (name: string): string => (identifierSegment.test(name) ? name
 const effectNumberSentinel = (schema: JsonSchema) =>
   schema.type === "string" &&
   Array.isArray(schema.enum) &&
-  (schema.enum.length === 1 ||
-    (schema.enum.length === 3 && ["NaN", "Infinity", "-Infinity"].every((value) => schema.enum?.includes(value)))) &&
-  schema.enum.every((value) => value === "NaN" || value === "Infinity" || value === "-Infinity")
-
-const definitionName = (ref: string): string | undefined => {
-  const tokens = JsonPointer.parseUriFragment(ref)
-  return tokens?.length === 2 && (tokens[0] === "$defs" || tokens[0] === "definitions") ? tokens[1] : undefined
-}
+  schema.enum.length === 1 &&
+  (schema.enum[0] === "NaN" || schema.enum[0] === "Infinity" || schema.enum[0] === "-Infinity")
 
 const intersection = (members: ReadonlyArray<string>): string => {
   const concrete = members.filter((member) => member !== "unknown")
@@ -44,7 +38,8 @@ const hasUnresolvedRef = (
   if (visited.has(schema)) return false
   const nextVisited = new Set([...visited, schema])
   if (schema.$ref !== undefined) {
-    const name = definitionName(schema.$ref)
+    const segment = schema.$ref.match(/^#\/(?:\$defs|definitions)\/([^/]+)$/)?.[1]
+    const name = segment === undefined ? undefined : JsonPointer.unescapeToken(segment)
     if (name === undefined || definitions[name] === undefined || seen.has(name)) return true
     if (hasUnresolvedRef(definitions[name], definitions, new Set([...seen, name]), nextVisited)) return true
   }
@@ -135,7 +130,8 @@ const renderSchema = (
       ? ctx
       : { ...ctx, definitions: { ...ctx.definitions, ...(schema.definitions ?? {}), ...(schema.$defs ?? {}) } }
   if (schema.$ref) {
-    const name = definitionName(schema.$ref)
+    const segment = schema.$ref.match(/^#\/(?:\$defs|definitions)\/([^/]+)$/)?.[1]
+    const name = segment === undefined ? undefined : JsonPointer.unescapeToken(segment)
     if (!name || !nested.definitions[name] || seen.has(name)) return "unknown"
     return intersection([
       renderSchema(nested.definitions[name], nested, depth, new Set([...seen, name])),
@@ -207,7 +203,7 @@ const renderSchema = (
 export const toTypeScript = (schema: Schema.Top, decoded = false, pretty = false): string => {
   try {
     const visible = decoded ? Schema.toType(schema) : schema
-    const document = Schema.toJsonSchemaDocument(visible, { onExcessProperty: "error" }) as {
+    const document = Schema.toJsonSchemaDocument(visible) as {
       readonly schema: JsonSchema
       readonly definitions?: Readonly<Record<string, JsonSchema>>
     }
@@ -234,7 +230,7 @@ export type InputProperty = {
 export const inputProperties = <R>(tool: Tool<R>): Array<InputProperty> => {
   try {
     const document = isEffectSchema(tool.input)
-      ? (Schema.toJsonSchemaDocument(tool.input, { onExcessProperty: "error" }) as {
+      ? (Schema.toJsonSchemaDocument(tool.input) as {
           readonly schema: JsonSchema
           readonly definitions?: Readonly<Record<string, JsonSchema>>
         })
@@ -245,7 +241,8 @@ export const inputProperties = <R>(tool: Tool<R>): Array<InputProperty> => {
     const definitions = document.definitions ?? {}
     let schema = document.schema
     if (schema.$ref !== undefined) {
-      const name = definitionName(schema.$ref)
+      const segment = schema.$ref.match(/^#\/(?:\$defs|definitions)\/([^/]+)$/)?.[1]
+      const name = segment === undefined ? undefined : JsonPointer.unescapeToken(segment)
       const resolved = name === undefined ? undefined : definitions[name]
       if (resolved === undefined) return []
       schema = resolved
@@ -264,13 +261,10 @@ export const inputProperties = <R>(tool: Tool<R>): Array<InputProperty> => {
 export const inputTypeScript = <R>(tool: Tool<R>, pretty = false): string =>
   isEffectSchema(tool.input) ? toTypeScript(tool.input, false, pretty) : jsonSchemaToTypeScript(tool.input, pretty)
 
-// Effect 4.0 models an empty Struct as a non-nullish object, so inspect the encoded AST callers supply.
-// Raw JSON Schema inputs retain the compact `{}` rendering check.
-export const isEmptyInput = <R>(tool: Tool<R>): boolean => {
-  if (!isEffectSchema(tool.input)) return inputTypeScript(tool) === "{}"
-  const encoded = SchemaAST.toEncoded(tool.input.ast)
-  return SchemaAST.isObjects(encoded) && encoded.propertySignatures.length === 0 && encoded.indexSignatures.length === 0
-}
+// Empty object schemas render as `{}` in compact form; anything with properties,
+// an index signature, or union members renders differently, so equality is a
+// conservative emptiness test for both Effect and JSON Schema inputs.
+export const isEmptyInput = <R>(tool: Tool<R>): boolean => inputTypeScript(tool) === "{}"
 
 export const outputTypeScript = <R>(tool: Tool<R>, pretty = false): string =>
   tool.output === undefined

packages/codemode/test/signature.test.ts

@@ -1,13 +1,7 @@
 import { describe, expect, test } from "bun:test"
-import { Effect, Schema, SchemaGetter } from "effect"
+import { Effect, Schema } from "effect"
 import { CodeMode, Tool } from "../src/index.js"
-import {
-  decodeInput,
-  inputProperties,
-  inputTypeScript,
-  jsonSchemaToTypeScript,
-  outputTypeScript,
-} from "../src/tool-schema.js"
+import { inputTypeScript, jsonSchemaToTypeScript, outputTypeScript } from "../src/tool-schema.js"
 
 // A raw JSON Schema tool in the shape an MCP adapter produces: render-only input schema
 // whose property descriptions and constraints must surface as JSDoc in pretty signatures.
@@ -531,34 +525,6 @@ describe("pretty signature rendering", () => {
 })
 
 describe("JSON Schema definition scope", () => {
-  test.each(["Lookup Input", "café", "A/B~C% D#E"])(
-    "resolves Effect definition %s in signatures and input metadata",
-    (identifier) => {
-      const tool = Tool.make({
-        description: "Named tool",
-        input: Schema.Struct({ city: Schema.String }).annotate({ identifier }),
-        output: Schema.Struct({ city: Schema.String }).annotate({ identifier }),
-        execute: (input) => Effect.succeed(input),
-      })
-      expect(inputTypeScript(tool)).toBe("{ city: string }")
-      expect(outputTypeScript(tool)).toBe("{ city: string }")
-      expect(inputProperties(tool)).toEqual([{ name: "city", description: undefined, required: true }])
-    },
-  )
-
-  test.each(["#/$defs/%", "#/$defs/A~2B", "#/$defs/Missing", "#/$defs/Loop", "https://example.test/schema"])(
-    "keeps malformed, unresolved, and recursive reference %s unknown",
-    ($ref) => {
-      const tool = Tool.make({
-        description: "Unresolved tool",
-        input: { $ref, $defs: { Loop: { $ref: "#/$defs/Loop" } } },
-        execute: () => Effect.succeed(null),
-      })
-      expect(inputTypeScript(tool)).toBe("unknown")
-      expect(inputProperties(tool)).toEqual([])
-    },
-  )
-
   test.each(["definitions", "$defs"])("resolves root %s and lets $defs take precedence", (key) => {
     const schema = { $ref: `#/${key}/Value`, [key]: { Value: { type: "string" } } }
     expect(jsonSchemaToTypeScript(schema)).toBe("string")
@@ -646,51 +612,14 @@ describe("non-identifier property names render as quoted keys", () => {
       input: Schema.Struct({ "foo-bar": Schema.String, plain: Schema.optionalKey(Schema.Number) }),
       execute: () => Effect.succeed(null),
     })
-    expect(inputTypeScript(tool)).toBe('{ "foo-bar": string; plain?: number }')
-    expect(inputTypeScript(tool, true)).toBe(["{", '  "foo-bar": string,', "  plain?: number,", "}"].join("\n"))
+    expect(inputTypeScript(tool)).toBe('{ "foo-bar": string; plain?: number | "Infinity" | "-Infinity" | "NaN" }')
+    expect(inputTypeScript(tool, true)).toBe(
+      ["{", '  "foo-bar": string,', '  plain?: number | "Infinity" | "-Infinity" | "NaN",', "}"].join("\n"),
+    )
   })
 })
 
 describe("union schemas render every alternative", () => {
-  test("Effect numbers advertise the numeric values accepted by the input decoder", () => {
-    const tool = Tool.make({
-      description: "Numeric tool",
-      input: Schema.Struct({ amount: Schema.Number }),
-      output: Schema.Number,
-      execute: (input) => Effect.succeed(input.amount),
-    })
-    expect(inputTypeScript(tool)).toBe("{ amount: number }")
-    expect(inputTypeScript(tool, true)).toBe("{\n  amount: number,\n}")
-    expect(outputTypeScript(tool)).toBe("number")
-    expect(outputTypeScript(tool, true)).toBe("number")
-    expect(decodeInput(tool, { amount: 42 })).toEqual({ amount: 42 })
-    for (const amount of ["NaN", "Infinity", "-Infinity"]) {
-      expect(() => decodeInput(tool, { amount })).toThrow("Expected number")
-    }
-  })
-
-  test("keeps unrelated and partial grouped string enums alongside numbers", () => {
-    expect(
-      jsonSchemaToTypeScript({
-        anyOf: [{ type: "number" }, { type: "string", enum: ["NaN", "Infinity", "unknown"] }],
-      }),
-    ).toBe('number | "NaN" | "Infinity" | "unknown"')
-    expect(
-      jsonSchemaToTypeScript({
-        anyOf: [{ type: "number" }, { type: "string", enum: ["NaN", "Infinity"] }],
-      }),
-    ).toBe('number | "NaN" | "Infinity"')
-    const tool = Tool.make({
-      description: "Number or status",
-      input: Schema.Union([Schema.Number, Schema.Literal("unknown")]),
-      output: Schema.Union([Schema.Number, Schema.Literal("unknown")]),
-      execute: (input) => Effect.succeed(input),
-    })
-    expect(inputTypeScript(tool)).toContain('"unknown"')
-    expect(outputTypeScript(tool)).toContain('"unknown"')
-    expect(decodeInput(tool, "unknown")).toBe("unknown")
-  })
-
   test("anyOf with a number branch keeps sibling alternatives", () => {
     const schema = {
       anyOf: [{ type: "string" }, { type: "number" }],
@@ -878,73 +807,6 @@ describe("JSDoc signatures in catalogs and search results", () => {
   })
 })
 
-describe("empty input signatures agree with decoding", () => {
-  test.each([
-    { name: "a plain empty struct", input: Schema.Struct({}) },
-    {
-      name: "an annotated empty struct",
-      input: Schema.Struct({}).annotate({ identifier: "Empty", description: "No input" }),
-    },
-    { name: "a checked empty struct", input: Schema.Struct({}).check(Schema.makeFilter(() => true)) },
-    {
-      name: "an empty encoded struct transformed to a non-empty struct",
-      input: Schema.Struct({}).pipe(
-        Schema.decodeTo(Schema.Struct({ token: Schema.String }), {
-          decode: SchemaGetter.transform(() => ({ token: "x" })),
-          encode: SchemaGetter.transform(() => ({})),
-        }),
-      ),
-    },
-    { name: "a raw JSON Schema empty object", input: { type: "object", properties: {} } },
-  ])("$name advertises () and runs with zero arguments", async ({ input }) => {
-    const runtime = CodeMode.make({
-      tools: {
-        ping: Tool.make({ description: "Ping", input, output: Schema.String, execute: () => Effect.succeed("pong") }),
-      },
-    })
-    const signature = "tools.ping(): Promise<string>"
-    expect(runtime.catalog[0]?.signature).toBe(signature)
-    const result = await Effect.runPromise(runtime.execute('return search({ query: "tools.ping" })'))
-    expect(result.ok).toBe(true)
-    if (!result.ok) throw new Error("search failed")
-    expect(result.value).toMatchObject({ items: [{ signature }] })
-    expect(await Effect.runPromise(runtime.execute("return await tools.ping()"))).toMatchObject({
-      ok: true,
-      value: "pong",
-    })
-  })
-
-  test("a required encoded input transformed to an empty struct keeps its required fields", async () => {
-    const consume = Tool.make({
-      description: "Consume token",
-      input: Schema.Struct({ token: Schema.String }).pipe(
-        Schema.decodeTo(Schema.Struct({}), {
-          decode: SchemaGetter.transform(() => ({})),
-          encode: SchemaGetter.transform(() => ({ token: "x" })),
-        }),
-      ),
-      output: Schema.String,
-      execute: () => Effect.succeed("consumed"),
-    })
-    const runtime = CodeMode.make({ tools: { consume } })
-    const signature = "tools.consume({\n  token: string,\n}): Promise<string>"
-    expect(() => decodeInput(consume, {})).toThrow()
-    expect(runtime.catalog[0]?.signature).toBe(signature)
-    const result = await Effect.runPromise(runtime.execute('return search({ query: "tools.consume" })'))
-    expect(result.ok).toBe(true)
-    if (!result.ok) throw new Error("search failed")
-    expect(result.value).toMatchObject({ items: [{ signature }] })
-    expect(await Effect.runPromise(runtime.execute("return await tools.consume()"))).toMatchObject({
-      ok: false,
-      error: { kind: "InvalidToolInput" },
-    })
-    expect(await Effect.runPromise(runtime.execute('return await tools.consume({ token: "t" })'))).toMatchObject({
-      ok: true,
-      value: "consumed",
-    })
-  })
-})
-
 describe("non-identifier tool paths", () => {
   const resolveLibrary = Tool.make({
     description: "Resolve a Context7 library ID",

packages/core/package.json

@@ -66,12 +66,6 @@
       "node": "./src/shell/parser-wasm.node.ts",
       "default": "./src/shell/parser-wasm.bun.ts"
     },
-    "#process-lock-ffi": {
-      "workerd": "./src/util/process-lock-ffi.workerd.ts",
-      "bun": "./src/util/process-lock-ffi.bun.ts",
-      "node": "./src/util/process-lock-ffi.node.ts",
-      "default": "./src/util/process-lock-ffi.bun.ts"
-    },
     "#v1-migration": {
       "types": "./src/database/v1-migration.bun.ts",
       "bun": "./src/database/v1-migration.bun.ts",
@@ -98,8 +92,7 @@
     "@types/bun": "catalog:",
     "@types/node": "catalog:",
     "@types/which": "3.0.4",
-    "drizzle-kit": "catalog:",
-    "fast-check": "catalog:"
+    "drizzle-kit": "catalog:"
   },
   "dependencies": {
     "@ai-sdk/cohere": "3.0.27",

packages/core/script/build.ts

@@ -26,7 +26,6 @@ const result = await Bun.build({
     "#fff",
     "#photon-wasm",
     "#shell-parser-wasm",
-    "#process-lock-ffi",
     "#v1-migration",
   ],
   splitting: true,

packages/core/src/config.ts

@@ -99,7 +99,7 @@ export const layer = (options?: Options) =>
       const wellknown = yield* WellKnown.Service
       const reloadLock = Semaphore.makeUnsafe(1)
       const updateLock = Semaphore.makeUnsafe(1)
-      const decodeOptions = { errors: "all", onExcessProperty: "ignore" } as const
+      const decodeOptions = { errors: "all", onExcessProperty: "ignore", propertyOrder: "original" } as const
       const decodeInfo = Schema.decodeUnknownOption(Info, decodeOptions)
       const parseInfo = Effect.fn("Config.parseInfo")(function* (text: string, source: string) {
         const errors: ParseError[] = []
@@ -330,8 +330,7 @@ export const layer = (options?: Options) =>
         function* (patch: Patch) {
           const directory = initial.global ?? AbsolutePath.make(globalService.config)
           const candidates = ConfigDiscovery.names.map((name) => path.join(directory, name))
-          const filepath =
-            (yield* Effect.filter(candidates, fs.isFile)).at(-1) ?? path.join(directory, "opencode.jsonc")
+          const filepath = (yield* Effect.filter(candidates, fs.isFile)).at(-1) ?? path.join(directory, "opencode.jsonc")
           const text = (yield* fs.readFileStringSafe(filepath)) ?? "{}\n"
           const updated = yield* Effect.try({
             try: () =>

packages/core/src/config/normalize.ts

@@ -42,7 +42,7 @@ export type Result =
     }
   | { readonly type: "rejected"; readonly diagnostics: readonly Diagnostic[] }
 
-const options = { errors: "all", onExcessProperty: "ignore" } as const
+const options = { errors: "all", onExcessProperty: "ignore", propertyOrder: "original" } as const
 const unsupportedTopLevel = ["logLevel", "server", "subagent_depth", "layout"] as const
 const unsupportedExperimental = [
   "disable_paste_summary",

packages/core/src/config/plugin/agent.ts

@@ -196,11 +196,11 @@ function decode(file: { directory: string; filepath: string; primary: boolean },
   const agent = legacy
     ? Option.getOrUndefined(
         Option.map(
-          decodeLegacyAgent({ name, ...markdown.data, prompt: body }, { errors: "all" }),
+          decodeLegacyAgent({ name, ...markdown.data, prompt: body }, { errors: "all", propertyOrder: "original" }),
           ConfigMigrateV1.migrateAgent,
         ),
       )
-    : Option.getOrUndefined(decodeAgent({ ...data, system: body }, { errors: "all" }))
+    : Option.getOrUndefined(decodeAgent({ ...data, system: body }, { errors: "all", propertyOrder: "original" }))
   if (!agent) return
   const info = Option.getOrUndefined(
     decodeConfig({

packages/core/src/config/plugin/provider.ts

@@ -99,6 +99,13 @@ export const Plugin = define({
       if (configuredDefault !== undefined) models.default.set(configuredDefault.providerID, configuredDefault.model)
       for (const [item, definition] of sources.models) {
         const providerID = definition.providerID
+        if (item.compatibility !== undefined)
+          for (const model of models.list(providerID)) {
+            if (Object.hasOwn(item.models ?? {}, model.id)) continue
+            models.update(providerID, model.id, (draft) => {
+              draft.compatibility = { ...draft.compatibility, ...item.compatibility }
+            })
+          }
         for (const [id, config] of Object.entries(item.models ?? {})) {
           const source = definition.models.get(id)
           const inherit = source?.inherit || !models.get(providerID, id)
@@ -111,6 +118,8 @@ export const Plugin = define({
             if (config.family !== undefined) model.family = config.family
             if (config.name !== undefined) model.name = config.name
             if (config.modelID !== undefined) model.modelID = config.modelID
+            if (item.compatibility !== undefined)
+              model.compatibility = { ...model.compatibility, ...item.compatibility }
             if (config.compatibility !== undefined)
               model.compatibility = { ...model.compatibility, ...config.compatibility }
             if (config.package !== undefined) model.package = config.package

packages/core/src/effect/websocket-constructor.ts

@@ -48,9 +48,10 @@ const proxy = (value: string, environment: Environment = process.env) => {
   )
 }
 
-const constructorOptions = (input: Socket.WebSocketConstructorOptions | undefined): WebSocketOptions => {
+const constructorOptions = (input: string | Array<string> | undefined): WebSocketOptions => {
   if (typeof input === "string" || Array.isArray(input)) return { protocols: input }
-  return { headers: input?.headers === undefined ? undefined : Headers.fromInput(input.headers) }
+  // AI routes pass handshake options through Effect's browser-shaped constructor.
+  return (input ?? {}) as WebSocketOptions
 }
 
 const proxyAgent = (url: string, selectedProxy: string | undefined) => {

packages/core/src/file-access.ts

@@ -30,12 +30,6 @@ export interface ExternalDirectoryAuthorization {
   readonly save: string
 }
 
-export const externalDirectoryPermission = (input: ExternalDirectoryAuthorization) => ({
-  action: input.action,
-  resources: [input.resource],
-  save: [input.save],
-})
-
 export interface Target {
   readonly absolute: AbsolutePath
   /** Location-relative for internal paths, absolute for external paths. */

packages/core/src/file.ts

@@ -1,6 +0,0 @@
-export * as File from "./file.js"
-
-import { FileDiff } from "@opencode/schema/file-diff"
-
-export const Diff = FileDiff.Info
-export type Diff = typeof Diff.Type

packages/core/src/generate.ts

@@ -1,6 +1,7 @@
 export * as Generate from "./generate.js"
 
 import { LLM, LLMClient, AIError } from "@opencode/ai"
+import { SessionID } from "@opencode/schema/session-id"
 import { Context, Effect, Layer, Schema } from "effect"
 import { makeLocationNode } from "@opencode/util/effect/app-node"
 import { llmClient } from "./effect/app-node-platform.js"
@@ -60,15 +61,24 @@ export const layer = Layer.effect(
             ? `Model unavailable: ${input.model.providerID}/${input.model.id}`
             : "No model specified and no supported model is available",
         })
-      const response = yield* llm.generate(LLM.request({ model: resolved.model, prompt: input.prompt })).pipe(
-        Effect.mapError(
-          (error: AIError) =>
-            new UnavailableError({
-              message: error.message,
-              service: resolved.ref.providerID,
-            }),
-        ),
-      )
+      const response = yield* llm
+        .generate(
+          LLM.request({
+            model: resolved.model,
+            prompt: input.prompt,
+            // Gateways require session attribution even for a stateless call; no Session is stored.
+            http: { headers: { "x-opencode-session": SessionID.create() } },
+          }),
+        )
+        .pipe(
+          Effect.mapError(
+            (error: AIError) =>
+              new UnavailableError({
+                message: error.message,
+                service: resolved.ref.providerID,
+              }),
+          ),
+        )
       return response.text
     })
 

packages/core/src/git.ts

@@ -7,7 +7,7 @@ import { AbsolutePath, RelativePath } from "./schema.js"
 import { FSUtil } from "@opencode/util/fs-util"
 import { AppProcess } from "@opencode/util/process"
 import { makeGlobalNode } from "@opencode/util/effect/app-node"
-import { File } from "./file.js"
+import { FileDiff } from "@opencode/schema/file-diff"
 import { KeyedMutex } from "./effect/keyed-mutex.js"
 import { VcsPatch } from "./vcs/patch.js"
 import { gitExecutable } from "./util/git-executable.js"
@@ -152,7 +152,7 @@ export interface Interface {
       to: TreeID
       context?: number
       paths?: readonly RelativePath[]
-    }) => Effect.Effect<readonly File.Diff[], OperationError>
+    }) => Effect.Effect<readonly FileDiff.Info[], OperationError>
     readonly restore: (input: {
       repository: Repository
       files: ReadonlyMap<RelativePath, TreeID>
@@ -571,7 +571,7 @@ const layer = Layer.effect(
           additions: stat?.additions ?? 0,
           deletions: stat?.deletions ?? 0,
           patch: stat?.binary ? "" : (patches.get(entry.file) ?? VcsPatch.emptyPatch(entry.file)),
-        } satisfies File.Diff
+        } satisfies FileDiff.Info
       })
     })
 

packages/core/src/instance.ts

@@ -152,7 +152,7 @@ export function layer(ref: Location.Ref, options: Options = {}): Layer.Layer<Ser
   const replacements: LayerNode.Replacements = [
     ...(options.discovery === false ? vanillaReplacements : []),
     ...(options.replacements ?? []),
-    Location.node.replace(Location.boundNode(ref, { discovery: options.discovery })),
+    Location.node.replace(Location.boundNode(ref)),
     InstancePlugins.node.replace(InstancePlugins.bound(options.plugins ?? [])),
   ]
 

packages/core/src/location-mutation.ts

@@ -1,3 +0,0 @@
-/** @deprecated Use FileAccess for path resolution and authorization. */
-export { FileAccess as LocationMutation } from "./file-access.js"
-export * from "./file-access.js"

packages/core/src/location-services.ts

@@ -8,7 +8,6 @@ import { LocationServiceMap } from "./location-service-map.js"
 export { LocationServiceMap } from "./location-service-map.js"
 
 export type LocationServices = Instance.Services
-export type LocationError = Instance.Error
 
 export function buildLocationServiceMap(
   replacements: LayerNode.Replacements = [],

packages/core/src/location.ts

@@ -16,12 +16,12 @@ export class Service extends Context.Service<Service, Interface>()("@opencode/Lo
 
 export const node = LayerNode.unbound(Service, tags.values.location)
 
-const layer = (ref: Ref, options?: { readonly discovery?: boolean }) =>
+const layer = (ref: Ref) =>
   Layer.effect(
     Service,
     Effect.gen(function* () {
       const project = yield* Project.Service
-      const resolved = yield* project.resolve(ref.directory, options)
+      const resolved = yield* project.resolve(ref.directory)
       return Service.of({
         directory: ref.directory,
         workspaceID: ref.workspaceID,
@@ -31,9 +31,9 @@ const layer = (ref: Ref, options?: { readonly discovery?: boolean }) =>
     }),
   )
 
-export const boundNode = (ref: Ref, options?: { readonly discovery?: boolean }) =>
+export const boundNode = (ref: Ref) =>
   makeLocationNode({
     service: Service,
-    layer: layer(ref, options),
+    layer: layer(ref),
     deps: [Project.node],
   })

packages/core/src/mcp/index.ts

@@ -45,8 +45,6 @@ export const ResourceTemplate = Mcp.ResourceTemplate
 export type ResourceTemplate = Mcp.ResourceTemplate
 export const ResourceCatalog = Mcp.ResourceCatalog
 export type ResourceCatalog = Mcp.ResourceCatalog
-export const ResourceContentPart = Mcp.ResourceContentPart
-export type ResourceContentPart = Mcp.ResourceContentPart
 export const ResourceContent = Mcp.ResourceContent
 export type ResourceContent = Mcp.ResourceContent
 

packages/core/src/project.ts

@@ -65,7 +65,7 @@ export interface Interface {
   /** Records Project activity for recency ordering, at most once per minute per Project. */
   readonly activate: (projectID: ID) => Effect.Effect<void>
   /** Resolves and persists the owning Project. */
-  readonly resolve: (input: AbsolutePath, options?: { readonly discovery?: boolean }) => Effect.Effect<Resolved>
+  readonly resolve: (input: AbsolutePath) => Effect.Effect<Resolved>
 }
 
 export class Service extends Context.Service<Service, Interface>()("@opencode/Project") {}
@@ -334,10 +334,7 @@ const layer = Layer.effect(
       }
     })
 
-    const resolve = Effect.fn("Project.resolve")(function* (
-      input: AbsolutePath,
-      _options?: { readonly discovery?: boolean },
-    ) {
+    const resolve = Effect.fn("Project.resolve")(function* (input: AbsolutePath) {
       const directory = AbsolutePath.make(yield* fs.resolve(input))
       const native = yield* fs.up({ targets: [".git", ".hg"], start: directory, mode: "first" }).pipe(
         Effect.map((matches) => matches[0]),

packages/core/src/pty.ts

@@ -6,7 +6,6 @@ import { Context, Effect, Layer, Schema, Types } from "effect"
 import { Pty } from "@opencode/schema/pty"
 import { Bus } from "./bus.js"
 import { Location } from "./location.js"
-import { PtyID } from "./pty/schema.js"
 import { ShellSelect } from "./shell/select.js"
 import { lazy } from "./util/lazy.js"
 
@@ -35,6 +34,9 @@ type Active = {
   listeners: Disp[]
 }
 
+export const ID = Pty.ID
+export type ID = Pty.ID
+
 export const Info = Pty.Info
 export type Info = Types.DeepMutable<typeof Info.Type>
 
@@ -69,21 +71,21 @@ export type Attachment = {
 }
 
 export class NotFoundError extends Schema.TaggedError<NotFoundError>()("Pty.NotFoundError", {
-  ptyID: PtyID,
+  ptyID: ID,
 }) {}
 
 export class ExitedError extends Schema.TaggedError<ExitedError>()("Pty.ExitedError", {
-  ptyID: PtyID,
+  ptyID: ID,
 }) {}
 
 export interface Interface {
   readonly list: () => Effect.Effect<Info[]>
-  readonly get: (id: PtyID) => Effect.Effect<Info, NotFoundError>
+  readonly get: (id: ID) => Effect.Effect<Info, NotFoundError>
   readonly create: (input: CreateInput) => Effect.Effect<Info>
-  readonly update: (id: PtyID, input: UpdateInput) => Effect.Effect<Info, NotFoundError>
-  readonly remove: (id: PtyID) => Effect.Effect<void, NotFoundError>
-  readonly write: (id: PtyID, data: string) => Effect.Effect<void, NotFoundError>
-  readonly attach: (id: PtyID, input: AttachInput) => Effect.Effect<Attachment, NotFoundError | ExitedError>
+  readonly update: (id: ID, input: UpdateInput) => Effect.Effect<Info, NotFoundError>
+  readonly remove: (id: ID) => Effect.Effect<void, NotFoundError>
+  readonly write: (id: ID, data: string) => Effect.Effect<void, NotFoundError>
+  readonly attach: (id: ID, input: AttachInput) => Effect.Effect<Attachment, NotFoundError | ExitedError>
 }
 
 export class Service extends Context.Service<Service, Interface>()("@opencode/Pty") {}
@@ -96,8 +98,8 @@ const layer = Layer.effect(
     const shell = yield* ShellSelect.Service
     const context = yield* Effect.context()
     const runFork = Effect.runForkWith(context)
-    const sessions = new Map<PtyID, Active>()
-    const exitOrder: PtyID[] = []
+    const sessions = new Map<ID, Active>()
+    const exitOrder: ID[] = []
 
     function notifyEnd(session: Active, event: { exitCode?: number }) {
       for (const subscriber of session.subscribers.values()) {
@@ -131,13 +133,13 @@ const layer = Layer.effect(
       }),
     )
 
-    const requireSession = Effect.fn("Pty.requireSession")(function* (id: PtyID) {
+    const requireSession = Effect.fn("Pty.requireSession")(function* (id: ID) {
       const session = sessions.get(id)
       if (!session) return yield* new NotFoundError({ ptyID: id })
       return session
     })
 
-    const removeSession = Effect.fnUntraced(function* (id: PtyID) {
+    const removeSession = Effect.fnUntraced(function* (id: ID) {
       const session = sessions.get(id)
       if (!session) return
       sessions.delete(id)
@@ -148,7 +150,7 @@ const layer = Layer.effect(
       yield* bus.publish(Pty.Event.Deleted, { id: session.info.id })
     })
 
-    const remove = Effect.fn("Pty.remove")(function* (id: PtyID) {
+    const remove = Effect.fn("Pty.remove")(function* (id: ID) {
       yield* requireSession(id)
       yield* removeSession(id)
     })
@@ -157,12 +159,12 @@ const layer = Layer.effect(
       return Array.from(sessions.values()).map((session) => session.info)
     })
 
-    const get = Effect.fn("Pty.get")(function* (id: PtyID) {
+    const get = Effect.fn("Pty.get")(function* (id: ID) {
       return (yield* requireSession(id)).info
     })
 
     const create = Effect.fn("Pty.create")(function* (input: CreateInput) {
-      const id = PtyID.ascending()
+      const id = ID.ascending()
       const command = input.command || (yield* shell.resolve({ priority: "config" }))
       const args = ShellSelect.login(command) ? [...(input.args ?? []), "-l"] : [...(input.args ?? [])]
       const cwd = input.cwd || location.directory
@@ -242,7 +244,7 @@ const layer = Layer.effect(
       return info
     })
 
-    const update = Effect.fn("Pty.update")(function* (id: PtyID, input: UpdateInput) {
+    const update = Effect.fn("Pty.update")(function* (id: ID, input: UpdateInput) {
       const session = yield* requireSession(id)
       if (input.title) session.info.title = input.title
       if (input.size && session.info.status === "running") session.process.resize(input.size.cols, input.size.rows)
@@ -250,12 +252,12 @@ const layer = Layer.effect(
       return session.info
     })
 
-    const write = Effect.fn("Pty.write")(function* (id: PtyID, data: string) {
+    const write = Effect.fn("Pty.write")(function* (id: ID, data: string) {
       const session = yield* requireSession(id)
       if (session.info.status === "running") session.process.write(data)
     })
 
-    const attach = Effect.fn("Pty.attach")(function* (id: PtyID, input: AttachInput) {
+    const attach = Effect.fn("Pty.attach")(function* (id: ID, input: AttachInput) {
       const session = yield* requireSession(id)
       if (session.info.status !== "running") return yield* new ExitedError({ ptyID: id })
       yield* Effect.logInfo("client attached to session", { id, directory: location.directory })

packages/core/src/pty/schema.ts

@@ -1 +0,0 @@
-export { ID as PtyID } from "@opencode/schema/pty"

packages/core/src/pty/ticket.ts

@@ -2,7 +2,7 @@ export * as PtyTicket from "./ticket.js"
 
 import type { Workspace } from "@opencode/schema/workspace"
 import { PtyTicket } from "@opencode/schema/pty-ticket"
-import { PtyID } from "./schema.js"
+import type { Pty } from "@opencode/schema/pty"
 import { Cache, Context, Duration, Effect, Layer } from "effect"
 import { makeGlobalNode } from "@opencode/util/effect/app-node"
 
@@ -12,7 +12,7 @@ const CAPACITY = 10_000
 export const ConnectToken = PtyTicket.ConnectToken
 
 export type Scope = {
-  readonly ptyID: PtyID
+  readonly ptyID: Pty.ID
   readonly directory?: string
   readonly workspaceID?: Workspace.ID
 }

packages/core/src/repository.ts

@@ -145,8 +145,9 @@ function parts(input: string) {
     .filter(Boolean)
 }
 
+// cachePath makes each `:`-separated host part a directory.
 function safeHost(input: string) {
-  return Boolean(input) && !input.startsWith("-") && !/[\s/\\]/.test(input)
+  return Boolean(input) && !input.startsWith("-") && input.split(":").every(safeSegment)
 }
 
 function safeSegment(input: string) {

packages/core/src/session/error.ts

@@ -50,15 +50,6 @@ export class StepFailedError extends Schema.TaggedError<StepFailedError>()("Sess
   }
 }
 
-export class UserInterruptedError extends Schema.TaggedError<UserInterruptedError>()(
-  "Session.UserInterruptedError",
-  {},
-) {
-  override get message() {
-    return "Session interrupted by user"
-  }
-}
-
 export class PromptConflictError extends Schema.TaggedError<PromptConflictError>()("Session.PromptConflictError", {
   sessionID: SessionSchema.ID,
   messageID: SessionMessage.ID,

packages/core/src/session/execution.ts

@@ -12,7 +12,6 @@ import { SessionRunner } from "./runner/index.js"
 import { SessionSchema } from "./schema.js"
 import { SessionStore } from "./store.js"
 import { toSessionError } from "./to-session-error.js"
-import { UserInterruptedError } from "./error.js"
 import { SessionInbox } from "./inbox.js"
 
 export interface Interface {
@@ -51,9 +50,7 @@ type InterruptReason = "user" | "shutdown" | "inactivity"
 export function terminal(exit: Exit.Exit<void, SessionRunner.RunError>, reason?: InterruptReason) {
   if (Exit.isSuccess(exit)) return { type: "succeeded" as const }
   if (Cause.hasInterrupts(exit.cause)) return { type: "interrupted" as const, reason: reason ?? "shutdown" }
-  const failure = Cause.squash(exit.cause)
-  if (failure instanceof UserInterruptedError) return { type: "interrupted" as const, reason: "user" as const }
-  return { type: "failed" as const, error: toSessionError(failure) }
+  return { type: "failed" as const, error: toSessionError(Cause.squash(exit.cause)) }
 }
 
 /** Process-local execution: drains run in this process using the selected instance. */

packages/core/src/session/model-request.ts

@@ -273,12 +273,12 @@ export const layer = Layer.effect(
         model: model.model,
         http: {
           headers: {
-            "x-session-affinity": session.id,
-            "X-Session-Id": session.id,
+            "x-session-affinity": affinity,
+            "X-Session-Id": affinity,
             ...(session.parentID ? { "x-parent-session-id": session.parentID } : {}),
             "User-Agent": App.useragent(app),
             "x-opencode-project": session.projectID,
-            "x-opencode-session": session.id,
+            "x-opencode-session": affinity,
             "x-opencode-client": app.name,
           },
         },

packages/core/src/session/runner/index.ts

@@ -4,7 +4,7 @@ import type { AIError } from "@opencode/ai"
 import { Context, Data, Effect } from "effect"
 import { SessionSchema } from "../schema.js"
 import type { Promotable } from "../inbox.js"
-import type { AgentNotFoundError, MessageDecodeError, StepFailedError, UserInterruptedError } from "../error.js"
+import type { AgentNotFoundError, MessageDecodeError, StepFailedError } from "../error.js"
 import { SessionRunnerModel } from "./model.js"
 import type { Instructions } from "../../instructions/index.js"
 
@@ -14,7 +14,6 @@ export type RunError =
   | MessageDecodeError
   | AgentNotFoundError
   | StepFailedError
-  | UserInterruptedError
   | Instructions.InitializationBlocked
 
 export type Continuation = { readonly step: number }

packages/core/src/session/runner/model.ts

@@ -29,19 +29,6 @@ export class ModelUnavailableError extends Schema.TaggedError<ModelUnavailableEr
     return `Model unavailable: ${this.providerID}/${this.modelID}`
   }
 }
-export const VariantUnavailableError = ModelResolver.VariantUnavailableError
-export type VariantUnavailableError = ModelResolver.VariantUnavailableError
-export const UnsupportedPackageError = ModelResolver.UnsupportedPackageError
-export type UnsupportedPackageError = ModelResolver.UnsupportedPackageError
-export const ModelConfigurationError = ModelResolver.ModelConfigurationError
-export type ModelConfigurationError = ModelResolver.ModelConfigurationError
-export const ModelInitializationError = ModelResolver.ModelInitializationError
-export type ModelInitializationError = ModelResolver.ModelInitializationError
-export const UnresolvedProviderVariablesError = ModelResolver.UnresolvedProviderVariablesError
-export type UnresolvedProviderVariablesError = ModelResolver.UnresolvedProviderVariablesError
-export const UnsupportedCompactionError = ModelResolver.UnsupportedCompactionError
-export type UnsupportedCompactionError = ModelResolver.UnsupportedCompactionError
-
 export type Error = ModelNotSelectedError | ModelUnavailableError | ModelResolver.Error
 export type Resolved = ModelResolver.Resolved
 

packages/core/src/session/runner/retry.ts

@@ -1,6 +1,6 @@
 export * as SessionRunnerRetry from "./retry.js"
 
-import { AIError, isContextOverflowFailure } from "@opencode/ai"
+import { AIError, isRetryable } from "@opencode/ai"
 import { Agent } from "@opencode/schema/agent"
 import { Model } from "@opencode/schema/model"
 import { SessionError } from "@opencode/schema/session-error"
@@ -10,7 +10,8 @@ import type { PluginHooks } from "../../plugin/hooks.js"
 import { SessionEvent } from "../event.js"
 import { SessionMessage } from "../message.js"
 import { SessionSchema } from "../schema.js"
-import { toSessionError } from "../to-session-error.js"
+
+export { isRetryable }
 
 interface Input {
   readonly cause: AIError
@@ -27,43 +28,6 @@ export interface Decision {
   readonly delay: number
 }
 
-export function isRetryable(error: AIError) {
-  const override = error.reason.http?.headers["x-should-retry"]
-  if (override === "true") return true
-  if (override === "false") return false
-  switch (error.reason._tag) {
-    case "RateLimit":
-    case "ProviderInternal":
-      return true
-    // A WebSocket acknowledgment marks delivery accepted before model output may exist.
-    // Read failures can still recover; the Step chooses retry versus continuation from durable output.
-    case "Transport":
-      return (
-        error.reason.delivery !== "rejected" &&
-        (error.reason.delivery !== "accepted" || error.reason.operation === "read")
-      )
-    case "InvalidProviderOutput":
-      return error.reason.classification === "incomplete-stream"
-    // Unrecognized failures retry: classification records affirmative
-    // deterministic evidence, and transient failures are exactly the ones
-    // that arrive in shapes no classifier anticipates.
-    case "UnknownProvider":
-      return true
-    case "Authentication":
-    case "QuotaExceeded":
-    case "ContentPolicy":
-    case "InvalidRequest":
-    case "UnsupportedOperation":
-    case "NoRoute":
-    case "Timeout":
-      return false
-    default: {
-      const exhaustive: never = error.reason
-      return exhaustive
-    }
-  }
-}
-
 /** Bound provider-requested delays so a hostile or buggy retry-after cannot stall a session for hours. */
 const RETRY_AFTER_MAX = Duration.toMillis("15 minutes")
 
@@ -119,24 +83,6 @@ export const policy = (sessionID: SessionSchema.ID) =>
       })
   })
 
-/**
- * Retries one auxiliary request's transient failures under a shared `policy` allowance, letting the
- * session retry hook adjust each decision. Context overflow is never transient: callers recover it.
- */
-export const transient =
-  (decide: Effect.Success<ReturnType<typeof policy>>, input: Pick<Input, "agent" | "model" | "hook">) =>
-  <A, R>(effect: Effect.Effect<A, AIError, R>) =>
-    Effect.retry(effect, {
-      while: (cause) =>
-        Effect.gen(function* () {
-          if (isContextOverflowFailure(cause)) return false
-          const decision = yield* decide({ ...input, cause, error: toSessionError(cause), retry: isRetryable(cause) })
-          if (!decision.retry) return false
-          yield* Effect.sleep(decision.delay)
-          return true
-        }),
-    })
-
 export const make = (bus: Bus.Interface, sessionID: SessionSchema.ID) =>
   Effect.gen(function* () {
     const decide = yield* policy(sessionID)

packages/core/src/session/to-session-error.ts

@@ -3,7 +3,8 @@ import { Tool } from "@opencode/schema/tool"
 import { SessionError } from "@opencode/schema/session-error"
 import { Permission } from "../permission.js"
 import { Integration } from "../integration.js"
-import { AgentNotFoundError, StepFailedError, UserInterruptedError } from "./error.js"
+import { AgentNotFoundError, StepFailedError } from "./error.js"
+import { ModelResolver } from "../model-resolver.js"
 import { SessionRunnerModel } from "./runner/model.js"
 
 export function toSessionError(cause: unknown): SessionError.Error {
@@ -48,18 +49,17 @@ export function toSessionError(cause: unknown): SessionError.Error {
     return unwrapped.message === "" ? { ...unwrapped, type: "tool.execution", message: cause.message } : unwrapped
   }
   if (cause instanceof StepFailedError) return cause.error
-  if (cause instanceof SessionRunnerModel.UnsupportedCompactionError)
+  if (cause instanceof ModelResolver.UnsupportedCompactionError)
     return { type: "provider.unsupported-operation", message: cause.message }
   if (cause instanceof AgentNotFoundError) return { type: "unknown", message: cause.message }
-  if (cause instanceof UserInterruptedError) return { type: "aborted", message: cause.message }
   if (
     cause instanceof SessionRunnerModel.ModelNotSelectedError ||
     cause instanceof SessionRunnerModel.ModelUnavailableError ||
-    cause instanceof SessionRunnerModel.VariantUnavailableError ||
-    cause instanceof SessionRunnerModel.UnsupportedPackageError ||
-    cause instanceof SessionRunnerModel.ModelConfigurationError ||
-    cause instanceof SessionRunnerModel.ModelInitializationError ||
-    cause instanceof SessionRunnerModel.UnresolvedProviderVariablesError
+    cause instanceof ModelResolver.VariantUnavailableError ||
+    cause instanceof ModelResolver.UnsupportedPackageError ||
+    cause instanceof ModelResolver.ModelConfigurationError ||
+    cause instanceof ModelResolver.ModelInitializationError ||
+    cause instanceof ModelResolver.UnresolvedProviderVariablesError
   )
     return { type: "provider.no-route", message: cause.message }
   if (cause instanceof Integration.AuthorizationError) return { type: "provider.auth", message: cause.message }

packages/core/src/snapshot.ts

@@ -3,7 +3,7 @@ export * as Snapshot from "./snapshot.js"
 import { makeLocationNode } from "@opencode/util/effect/app-node"
 import path from "path"
 import { Context, Effect, Fiber, Layer, Schema, Scope } from "effect"
-import { File } from "./file.js"
+import { FileDiff } from "@opencode/schema/file-diff"
 import { FSUtil } from "@opencode/util/fs-util"
 import { Git } from "./git.js"
 import { Global } from "@opencode/util/global"
@@ -58,7 +58,7 @@ export interface Interface extends State.Transformable<Editor> {
    * Generate structured per-file diffs between two captured trees. `context`
    * controls unchanged lines around each unified diff hunk.
    */
-  readonly diff: (input: DiffInput) => Effect.Effect<readonly File.Diff[], Error>
+  readonly diff: (input: DiffInput) => Effect.Effect<readonly FileDiff.Info[], Error>
 
   /**
    * Restore selected project-relative paths from their associated trees. A path

packages/core/src/tool/runtime.ts

@@ -1,7 +1,7 @@
 import type { ToolDefinition } from "@opencode/ai"
 import { Tool } from "@opencode/schema/tool"
 import type { StandardJSONSchemaV1, StandardSchemaV1 } from "@standard-schema/spec"
-import { Cache, Effect, JsonPointer, JsonSchema, Schema, SchemaIssue, SchemaRepresentation } from "effect"
+import { Cache, Effect, JsonSchema, Schema, SchemaIssue, SchemaRepresentation } from "effect"
 import { $ZodType, toJSONSchema } from "zod/v4/core"
 
 const formatEffectIssues = SchemaIssue.makeFormatterStandardSchemaV1()
@@ -155,24 +155,7 @@ const validateStandard = (
 const inputJsonSchema = (schema: Tool.ValueSchema<any>): JsonSchema.JsonSchema => {
   if (schema === undefined || schema === null) return {}
   if (isStandardSchema(schema)) return standardJsonSchema(schema, "input")
-  if (!Schema.isSchema(schema)) return schema
-  const json = toJsonSchema(schema)
-  // Empty Effect structs describe non-null values, but tool parameters must be
-  // objects. Normalize after inlining named schemas, retaining their metadata.
-  if (
-    schema.ast._tag === "Objects" &&
-    schema.ast.propertySignatures.length === 0 &&
-    schema.ast.indexSignatures.length === 0 &&
-    schema.ast.encoding === undefined &&
-    schema.ast.checks === undefined &&
-    isRecord(json.not) &&
-    json.not.type === "null" &&
-    Object.keys(json.not).length === 1
-  ) {
-    const { not: _, ...metadata } = json
-    return { ...metadata, type: "object", properties: {}, additionalProperties: false }
-  }
-  return json
+  return Schema.isSchema(schema) ? toJsonSchema(schema) : schema
 }
 
 const outputJsonSchema = (schema: Tool.ValueSchema<any>): JsonSchema.JsonSchema => {
@@ -187,7 +170,7 @@ const standardJsonSchema = (schema: StandardSchemaV1<any, any>, io: "input" | "o
 }
 
 const toJsonSchema = (schema: Schema.Top): JsonSchema.JsonSchema => {
-  const document = Schema.toJsonSchemaDocument(schema, { onExcessProperty: "error" })
+  const document = Schema.toJsonSchemaDocument(schema)
   // Effect emits valid JSON Schema that some inference providers handle poorly. Simplify it
   // without changing validation: `{ type: "integer", allOf: [{ minimum: 0 }] }` becomes
   // `{ type: "integer", minimum: 0 }` only when no keyword would be overwritten. Named schemas
@@ -237,8 +220,8 @@ const inlineLocalReferences = (
 
   const localDefinitions = definitions ?? (isRecord(value.$defs) ? value.$defs : undefined)
   if (typeof value.$ref === "string" && localDefinitions) {
-    const tokens = JsonPointer.parseUriFragment(value.$ref)
-    const name = tokens?.length === 2 && tokens[0] === "$defs" ? tokens[1] : undefined
+    const segment = value.$ref.match(/^#\/\$defs\/([^/]+)$/)?.[1]
+    const name = segment?.replaceAll("~1", "/").replaceAll("~0", "~")
     if (name && !seen.has(name)) {
       const target = localDefinitions[name]
       if (target) {

packages/core/src/util/array.ts

@@ -1,10 +0,0 @@
-export function findLast<T>(
-  items: readonly T[],
-  predicate: (item: T, index: number, items: readonly T[]) => boolean,
-): T | undefined {
-  for (let i = items.length - 1; i >= 0; i -= 1) {
-    const item = items[i]
-    if (predicate(item, i, items)) return item
-  }
-  return undefined
-}

packages/core/src/util/process-lock-ffi.bun.ts

@@ -1,50 +0,0 @@
-import { dlopen, read, type Pointer } from "bun:ffi"
-import { existsSync } from "node:fs"
-
-export type LockResult =
-  | { readonly acquired: true }
-  | { readonly acquired: false; readonly held: true }
-  | { readonly acquired: false; readonly held: false; readonly code: number }
-
-const LOCK_EX = 2
-const LOCK_NB = 4
-const DARWIN_EWOULDBLOCK = 35
-const LINUX_EWOULDBLOCK = 11
-
-export function lockDarwin(fd: number): LockResult {
-  const library = dlopen("/usr/lib/libSystem.B.dylib", {
-    flock: { args: ["i32", "i32"], returns: "i32" },
-    __error: { args: [], returns: "ptr" },
-  })
-  try {
-    const result = library.symbols.flock(fd, LOCK_EX | LOCK_NB)
-    const code = result === 0 ? 0 : errorCode(library.symbols.__error())
-    if (result === 0) return { acquired: true }
-    if (code === DARWIN_EWOULDBLOCK) return { acquired: false, held: true }
-    return { acquired: false, held: false, code }
-  } finally {
-    library.close()
-  }
-}
-
-export function lockLinux(fd: number): LockResult {
-  const musl = `/lib/libc.musl-${process.arch === "arm64" ? "aarch64" : "x86_64"}.so.1`
-  const library = dlopen(existsSync(musl) ? musl : "libc.so.6", {
-    flock: { args: ["i32", "i32"], returns: "i32" },
-    __errno_location: { args: [], returns: "ptr" },
-  })
-  try {
-    const result = library.symbols.flock(fd, LOCK_EX | LOCK_NB)
-    const code = result === 0 ? 0 : errorCode(library.symbols.__errno_location())
-    if (result === 0) return { acquired: true }
-    if (code === LINUX_EWOULDBLOCK) return { acquired: false, held: true }
-    return { acquired: false, held: false, code }
-  } finally {
-    library.close()
-  }
-}
-
-function errorCode(pointer: Pointer | bigint | null) {
-  if (pointer === null) throw new Error("Failed to read process lock error code")
-  return read.i32(pointer, 0)
-}

packages/core/src/util/process-lock-ffi.node.ts

@@ -1,43 +0,0 @@
-import { dlopen, getInt32 } from "node:ffi"
-
-export type LockResult =
-  | { readonly acquired: true }
-  | { readonly acquired: false; readonly held: true }
-  | { readonly acquired: false; readonly held: false; readonly code: number }
-
-const LOCK_EX = 2
-const LOCK_NB = 4
-const DARWIN_EWOULDBLOCK = 35
-const LINUX_EWOULDBLOCK = 11
-
-export function lockDarwin(fd: number): LockResult {
-  const library = dlopen("/usr/lib/libSystem.B.dylib", {
-    flock: { arguments: ["int32", "int32"], return: "int32" },
-    __error: { arguments: [], return: "pointer" },
-  })
-  try {
-    const result = library.functions.flock(fd, LOCK_EX | LOCK_NB)
-    const code = result === 0 ? 0 : getInt32(library.functions.__error(), 0)
-    if (result === 0) return { acquired: true }
-    if (code === DARWIN_EWOULDBLOCK) return { acquired: false, held: true }
-    return { acquired: false, held: false, code }
-  } finally {
-    library.lib.close()
-  }
-}
-
-export function lockLinux(fd: number): LockResult {
-  const library = dlopen("libc.so.6", {
-    flock: { arguments: ["int32", "int32"], return: "int32" },
-    __errno_location: { arguments: [], return: "pointer" },
-  })
-  try {
-    const result = library.functions.flock(fd, LOCK_EX | LOCK_NB)
-    const code = result === 0 ? 0 : getInt32(library.functions.__errno_location(), 0)
-    if (result === 0) return { acquired: true }
-    if (code === LINUX_EWOULDBLOCK) return { acquired: false, held: true }
-    return { acquired: false, held: false, code }
-  } finally {
-    library.lib.close()
-  }
-}