feat(core): add Kimi Code OAuth

Co-authored-by: Aiden Cline <rekram1-node@users.noreply.github.com>
Co-authored-by: opencode-agent[bot] <219766164+opencode-agent[bot]@users.noreply.github.com>
Co-authored-by: Dax Raad <d@ironbay.co>
Co-authored-by: Dax <mail@thdxr.com>
Co-authored-by: opencode-agent[bot] <opencode-agent[bot]@users.noreply.github.com>
Co-authored-by: Aiden Cline <63023139+rekram1-node@users.noreply.github.com>
Co-authored-by: Nabs <nabil@instafork.com>
Co-authored-by: usrnk1 <7547651+usrnk1@users.noreply.github.com>
Co-authored-by: Brendan Allan <14191578+Brendonovich@users.noreply.github.com>
Co-authored-by: Aarav Sareen <96787824+arvsrn@users.noreply.github.com>
Co-authored-by: Brendan Allan <git@brendonovich.dev>
Co-authored-by: Victor Navarro <vn4varro@gmail.com>
Co-authored-by: Vladimir Glafirov <vglafirov@gitlab.com>
Co-authored-by: AidenGeunGeun <eastlandwyvern@gmail.com>
Co-authored-by: Mark <geraint0923@users.noreply.github.com>
Co-authored-by: Aiden Cline <aidenpcline@gmail.com>
Co-authored-by: Adam <2363879+adamdotdevin@users.noreply.github.com>
Co-authored-by: opencode <opencode@sst.dev>
Co-authored-by: Luke Parker <10430890+Hona@users.noreply.github.com>
Co-authored-by: David Hill <1879069+iamdavidhill@users.noreply.github.com>
Co-authored-by: Jay <air@live.ca>
Co-authored-by: Jay <53023+jayair@users.noreply.github.com>
Co-authored-by: BB84 <110078428+BB-84C@users.noreply.github.com>
Co-authored-by: Dustin Deus <deusdustin@gmail.com>
Co-authored-by: Frank <frank@anoma.ly>
Co-authored-by: Jack <jack@anoma.ly>
Co-authored-by: Sebastian <hasta84@gmail.com>
Co-authored-by: Jérôme Benoit <jerome.benoit@sap.com>
Co-authored-by: Test User <test@test.com>
Co-authored-by: Simon Klee <hello@simonklee.dk>
Co-authored-by: Rahul A Mistry <149420892+ProdigyRahul@users.noreply.github.com>
Co-authored-by: Qiping Li <liqiping1991@gmail.com>
Co-authored-by: liqiping <liqiping@msh.team>
Co-authored-by: OpeOginni <107570612+OpeOginni@users.noreply.github.com>
Co-authored-by: Matthias Reso <13337103+mreso@users.noreply.github.com>
Co-authored-by: tobwen <1864057+tobwen@users.noreply.github.com>
Co-authored-by: Daniel Polito <danielbpolito@gmail.com>
Co-authored-by: opencode <noreply@opencode.ai>

.changeset/canonical-tool-results.md

@@ -0,0 +1,8 @@
+---
+"@opencode-ai/plugin": minor
+"@opencode-ai/sdk": minor
+"@opencode-ai/client": minor
+"@opencode-ai/protocol": minor
+---
+
+Replace the V2 tool result model with one canonical representation per fact. Tools lose `structured`, projection callbacks, the `Structured` generic, and the exported `Tool.settle` interpreter; tool responses carry schema-validated `output`, model-visible `content`, and optional compact JSON `metadata`. Code Mode receives the validated encoded output. Durable tool success stores non-empty model content plus optional metadata; failure stores one error plus the final bounded partial snapshot. Progress carries metadata only, while `execute.after` hooks receive the canonical terminal outcome and managed `outputPaths`. A one-time migration rewrites existing projected tool rows and moves provider-hosted result payloads into provider-owned result state.

.github/workflows/test.yml

@@ -97,6 +97,11 @@ jobs:
         working-directory: packages/client
         run: bun run check:generated
 
+      - name: Check generated documentation
+        if: runner.os == 'Linux'
+        working-directory: packages/docs
+        run: bun run check:generated
+
   e2e:
     name: e2e (${{ matrix.settings.name }})
     if: github.ref_name != 'v2' && github.head_ref != 'v2'

bun.lock

@@ -61,6 +61,7 @@
         "@dnd-kit/helpers": "0.5.0",
         "@dnd-kit/solid": "0.5.0",
         "@kobalte/core": "catalog:",
+        "@opencode-ai/client": "file:vendor/opencode-ai-client-1.17.13.tgz",
         "@opencode-ai/core": "workspace:*",
         "@opencode-ai/schema": "workspace:*",
         "@opencode-ai/sdk": "workspace:*",
@@ -124,7 +125,7 @@
         "opencode2": "./bin/opencode2.cjs",
       },
       "dependencies": {
-        "@agentclientprotocol/sdk": "0.21.0",
+        "@agentclientprotocol/sdk": "1.2.1",
         "@effect/platform-node": "catalog:",
         "@opencode-ai/client": "workspace:*",
         "@opencode-ai/plugin": "workspace:*",
@@ -350,7 +351,7 @@
         "@ai-sdk/google": "3.0.73",
         "@ai-sdk/google-vertex": "4.0.128",
         "@ai-sdk/groq": "3.0.31",
-        "@ai-sdk/mistral": "3.0.27",
+        "@ai-sdk/mistral": "3.0.51",
         "@ai-sdk/openai": "3.0.84",
         "@ai-sdk/openai-compatible": "2.0.41",
         "@ai-sdk/perplexity": "3.0.26",
@@ -362,7 +363,7 @@
         "@aws-sdk/credential-providers": "3.1057.0",
         "@effect/platform-node": "catalog:",
         "@effect/sql-sqlite-bun": "catalog:",
-        "@ff-labs/fff-bun": "0.9.4",
+        "@ff-labs/fff-bun": "0.10.1",
         "@lydell/node-pty": "catalog:",
         "@modelcontextprotocol/sdk": "1.29.0",
         "@opencode-ai/ai": "workspace:*",
@@ -470,7 +471,9 @@
     "packages/docs": {
       "name": "@opencode-ai/docs",
       "devDependencies": {
+        "effect": "catalog:",
         "mint": "4.2.666",
+        "prettier": "3.6.2",
       },
     },
     "packages/effect-drizzle-sqlite": {
@@ -706,6 +709,7 @@
       "version": "1.18.4",
       "dependencies": {
         "@kobalte/core": "catalog:",
+        "@opencode-ai/client": "file:../app/vendor/opencode-ai-client-1.17.13.tgz",
         "@opencode-ai/core": "workspace:*",
         "@opencode-ai/sdk": "workspace:*",
         "@opencode-ai/ui": "workspace:*",
@@ -1079,6 +1083,7 @@
     "@ai-sdk/xai@3.0.102": "patches/@ai-sdk%2Fxai@3.0.102.patch",
     "@modelcontextprotocol/sdk@1.29.0": "patches/@modelcontextprotocol%2Fsdk@1.29.0.patch",
     "@standard-community/standard-openapi@0.2.9": "patches/@standard-community%2Fstandard-openapi@0.2.9.patch",
+    "@ai-sdk/mistral@3.0.51": "patches/@ai-sdk%2Fmistral@3.0.51.patch",
     "@npmcli/agent@4.0.2": "patches/@npmcli%2Fagent@4.0.2.patch",
     "@silvia-odwyer/photon-node@0.3.4": "patches/@silvia-odwyer%2Fphoton-node@0.3.4.patch",
     "solid-js@1.9.10": "patches/solid-js@1.9.10.patch",
@@ -1173,7 +1178,7 @@
 
     "@adobe/css-tools": ["@adobe/css-tools@4.5.0", "", {}, "sha512-6OzddxPio9UiWTCemp4N8cYLV2ZN1ncRnV1cVGtve7dhPOtRkleRyx32GQCYSwDYgaHU3USMm84tNsvKzRCa1Q=="],
 
-    "@agentclientprotocol/sdk": ["@agentclientprotocol/sdk@0.21.0", "", { "peerDependencies": { "zod": "^3.25.0 || ^4.0.0" } }, "sha512-ONj+Q8qOdNQp5XbH5jnMwzT9IKZJsSN0p0lkceS4GtUtNOPVLpNzSS8gqQdGMKfBvA0ESbkL8BTaSN1Rc9miEw=="],
+    "@agentclientprotocol/sdk": ["@agentclientprotocol/sdk@1.2.1", "", { "peerDependencies": { "zod": "^3.25.0 || ^4.0.0" } }, "sha512-jwYUdOQR7tc+Zfch53VL4JJyUNK/46q03uUTYb+PjECsmnNl94XFXOfYLJ8RBpMNidXd1rpOAVgb0vqD98xImA=="],
 
     "@ai-sdk/alibaba": ["@ai-sdk/alibaba@1.0.17", "", { "dependencies": { "@ai-sdk/openai-compatible": "2.0.41", "@ai-sdk/provider": "3.0.8", "@ai-sdk/provider-utils": "4.0.23" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-ZbE+U5bWz2JBc5DERLowx5+TKbjGBE93LqKZAWvuEn7HOSQMraxFMZuc0ST335QZJAyfBOzh7m1mPQ+y7EaaoA=="],
 
@@ -1205,7 +1210,7 @@
 
     "@ai-sdk/groq": ["@ai-sdk/groq@3.0.31", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@ai-sdk/provider-utils": "4.0.21" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-XbbugpnFmXGu2TlXiq8KUJskP6/VVbuFcnFIGDzDIB/Chg6XHsNnqrTF80Zxkh0Pd3+NvbM+2Uqrtsndk6bDAg=="],
 
-    "@ai-sdk/mistral": ["@ai-sdk/mistral@3.0.27", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@ai-sdk/provider-utils": "4.0.21" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-ZXe7nZQgliDdjz5ufH5RKpHWxbN72AzmzzKGbF/z+0K9GN5tUCnftrQRvTRFHA5jAzTapcm2BEevmGLVbMkW+A=="],
+    "@ai-sdk/mistral": ["@ai-sdk/mistral@3.0.51", "", { "dependencies": { "@ai-sdk/provider": "3.0.14", "@ai-sdk/provider-utils": "4.0.40" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-83eXY6p0lUFhSuMvNDmTKDuMciK5XDAWDlNh5c0L80tKjmtCFRItA1MZHp4IKe1r7eK8Rb5nN7qtxqMLUFRIRw=="],
 
     "@ai-sdk/openai": ["@ai-sdk/openai@3.0.48", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@ai-sdk/provider-utils": "4.0.21" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-ALmj/53EXpcRqMbGpPJPP4UOSWw0q4VGpnDo7YctvsynjkrKDmoneDG/1a7VQnSPYHnJp6tTRMf5ZdxZ5whulg=="],
 
@@ -1641,23 +1646,25 @@
 
     "@fastify/busboy": ["@fastify/busboy@2.1.1", "", {}, "sha512-vBZP4NlzfOlerQTnba4aqZoMhE/a9HY7HRqoOPaETQcSQuWEIyZMHGfVu6w9wGtGK5fED5qRs2DteVCjOH60sA=="],
 
-    "@ff-labs/fff-bin-darwin-arm64": ["@ff-labs/fff-bin-darwin-arm64@0.9.4", "", { "os": "darwin", "cpu": "arm64" }, "sha512-xyivu2xB++O5xXDx5Qm50JsU2aXt8YgXlGVhH/HE7UMYDrE6L6f1RYdYs8Y0bn0D3D0+bFBrN5ELPszK9E4Wbw=="],
+    "@ff-labs/fff-bin-android-arm64": ["@ff-labs/fff-bin-android-arm64@0.10.1", "", { "os": "android", "cpu": "arm64" }, "sha512-6Bsaa6yKEd2HV1M2WtqSYhoZucKYffIUms6GYoPN48QHP8hZgO8GXJ85/JDxKlkCJsN2hw1ROiwQK0+xUHYhFQ=="],
 
-    "@ff-labs/fff-bin-darwin-x64": ["@ff-labs/fff-bin-darwin-x64@0.9.4", "", { "os": "darwin", "cpu": "x64" }, "sha512-xLooAhCnTDCipPSMMZz7kGF3lhRHx6aP5fb6DJ0Ipyw/w/UWJb+xITJFszUl/QnIBoJ/qjDc93/FZMo1dk6gVA=="],
+    "@ff-labs/fff-bin-darwin-arm64": ["@ff-labs/fff-bin-darwin-arm64@0.10.1", "", { "os": "darwin", "cpu": "arm64" }, "sha512-7yUP+56sG3UTrLg7eepOD16yM2dgiD7g6Ase2XWQB7oXwLV7mBMylPKIli2pP3kHzfw9K+BS3WAwHKHJ2QhxYw=="],
 
-    "@ff-labs/fff-bin-linux-arm64-gnu": ["@ff-labs/fff-bin-linux-arm64-gnu@0.9.4", "", { "os": "linux", "cpu": "arm64" }, "sha512-m5+8vA+1veaUUWonwva1WsU6m1HRm8CpYUzr06KDB65mewlmPbqz7+Fh7hjEfiD8C4mHVHe6RysULvAH1yhsdw=="],
+    "@ff-labs/fff-bin-darwin-x64": ["@ff-labs/fff-bin-darwin-x64@0.10.1", "", { "os": "darwin", "cpu": "x64" }, "sha512-9zb+P1xtyqu/jVklm5RKF2zm9doRRsBNbkF/a8S4aSqSJoNlQR8ZF7C129fzOLfffVAjjgcO2l8oJgxOzHYiwQ=="],
 
-    "@ff-labs/fff-bin-linux-arm64-musl": ["@ff-labs/fff-bin-linux-arm64-musl@0.9.4", "", { "os": "linux", "cpu": "arm64" }, "sha512-EMeWm7CSTVkizy4ZEzUkLDP024tVcbCUthduuIhekFQRDsiaAze0YboIylWb9HBHJCZlCCoZrWAl4nnJbsX7AA=="],
+    "@ff-labs/fff-bin-linux-arm64-gnu": ["@ff-labs/fff-bin-linux-arm64-gnu@0.10.1", "", { "os": "linux", "cpu": "arm64" }, "sha512-KTwr9CUfCJv0vtG2xG+nMxDae/2NJY2/oVmtgSvTnH9baI6JprqsFGphbukx7mdW/QMPwBiYtoO8ZGoC7i92jA=="],
 
-    "@ff-labs/fff-bin-linux-x64-gnu": ["@ff-labs/fff-bin-linux-x64-gnu@0.9.4", "", { "os": "linux", "cpu": "x64" }, "sha512-pglE0uLkhnlE6bStXqfgUjYTSj+2sVwXaPfoA0QksidAsQor6NRt8004mygzC9DPubgHq5B9QezPfEwigKaP9Q=="],
+    "@ff-labs/fff-bin-linux-arm64-musl": ["@ff-labs/fff-bin-linux-arm64-musl@0.10.1", "", { "os": "linux", "cpu": "arm64" }, "sha512-oznmSpV+zjiAPiwqbA4y+SAsMaYvDhGllHiT9L4ebdQnSOfcQzlUwvo45OhBPwHBt47tIois4bkF/MITlDk54A=="],
 
-    "@ff-labs/fff-bin-linux-x64-musl": ["@ff-labs/fff-bin-linux-x64-musl@0.9.4", "", { "os": "linux", "cpu": "x64" }, "sha512-VNKxgl8qs3aTfXViX7lqRK1aLu311h8dtBFqG4Scv+9Oi7WprybUp5L7IZ8sxKERaDAaiJMXHodXa1c90QdK8w=="],
+    "@ff-labs/fff-bin-linux-x64-gnu": ["@ff-labs/fff-bin-linux-x64-gnu@0.10.1", "", { "os": "linux", "cpu": "x64" }, "sha512-KDpl8lwSEOauP/6FSJIvnARzE+ILm2rVIRQAio9dc5nn56EvlsryBWry0c5V0Tbw1PV0lNrZ+bzcIiPuTacvzw=="],
 
-    "@ff-labs/fff-bin-win32-arm64": ["@ff-labs/fff-bin-win32-arm64@0.9.4", "", { "os": "win32", "cpu": "arm64" }, "sha512-uFEt0aNL54vQxq1ivjxRuo+thnhS4wLqa4INl4VXnXJUmwB42XXxD+gsj7vzhBLLx4cFf0aWgy/+TVDR8yjZtQ=="],
+    "@ff-labs/fff-bin-linux-x64-musl": ["@ff-labs/fff-bin-linux-x64-musl@0.10.1", "", { "os": "linux", "cpu": "x64" }, "sha512-mZCpojVtGNDr/wdCUEAHdfrl6qORvKHv3Pw35TaOdshnG4wocoA5bBKTGj/zmAU11o0GMK4V+wUhdNrgqoE10w=="],
 
-    "@ff-labs/fff-bin-win32-x64": ["@ff-labs/fff-bin-win32-x64@0.9.4", "", { "os": "win32", "cpu": "x64" }, "sha512-Yd2Eyxj+slWv+0QDW9/xBpu9FXq+hwD0rXQD5184/88d+xwWCLKhEP2w8I6OO9XCg+kLT79UJb+k0WwXUtBtMw=="],
+    "@ff-labs/fff-bin-win32-arm64": ["@ff-labs/fff-bin-win32-arm64@0.10.1", "", { "os": "win32", "cpu": "arm64" }, "sha512-SbT76ETXC5AgV9J8sVDozKG8wzrrxsOn8lbBprlOtx+O5V5EYmS1W7BlsatTHy6ddQ3uU5oOYO04PWZBuP6wXg=="],
 
-    "@ff-labs/fff-bun": ["@ff-labs/fff-bun@0.9.4", "", { "optionalDependencies": { "@ff-labs/fff-bin-darwin-arm64": "0.9.4", "@ff-labs/fff-bin-darwin-x64": "0.9.4", "@ff-labs/fff-bin-linux-arm64-gnu": "0.9.4", "@ff-labs/fff-bin-linux-arm64-musl": "0.9.4", "@ff-labs/fff-bin-linux-x64-gnu": "0.9.4", "@ff-labs/fff-bin-linux-x64-musl": "0.9.4", "@ff-labs/fff-bin-win32-arm64": "0.9.4", "@ff-labs/fff-bin-win32-x64": "0.9.4" }, "os": [ "linux", "win32", "darwin", ], "cpu": [ "x64", "arm64", ] }, "sha512-7HUraaK/g5dStAnuKAuzsXVOQvqqX0ylo5G+DxYwsCjCDc42bjoEAAHqz/3Sn3raUNw97KMoz87XR9QyrLEfVw=="],
+    "@ff-labs/fff-bin-win32-x64": ["@ff-labs/fff-bin-win32-x64@0.10.1", "", { "os": "win32", "cpu": "x64" }, "sha512-dcpHUCBEZoXKQCdKa3bADfgcNyeyfM8tatXrILqIFYi9GL8E4GnzKx1rGkgP5ukVtuj0WuoJyyqSvGjpJPIT8w=="],
+
+    "@ff-labs/fff-bun": ["@ff-labs/fff-bun@0.10.1", "", { "optionalDependencies": { "@ff-labs/fff-bin-android-arm64": "0.10.1", "@ff-labs/fff-bin-darwin-arm64": "0.10.1", "@ff-labs/fff-bin-darwin-x64": "0.10.1", "@ff-labs/fff-bin-linux-arm64-gnu": "0.10.1", "@ff-labs/fff-bin-linux-arm64-musl": "0.10.1", "@ff-labs/fff-bin-linux-x64-gnu": "0.10.1", "@ff-labs/fff-bin-linux-x64-musl": "0.10.1", "@ff-labs/fff-bin-win32-arm64": "0.10.1", "@ff-labs/fff-bin-win32-x64": "0.10.1" }, "os": [ "!aix", "!sunos", "!freebsd", "!openbsd", ], "cpu": [ "x64", "arm64", ] }, "sha512-9oUCxypGbf2q3vNfKZ31wdzt5KqjhA9S6TwQaFol/j1lkSHVGvtIa3RvdGHPs1UUuvR/MO7b6pHj054BR9bXPQ=="],
 
     "@floating-ui/core": ["@floating-ui/core@1.8.0", "", { "dependencies": { "@floating-ui/utils": "^0.2.12" } }, "sha512-0CIZ5itps/8x7BG8dEIhs53BvCUH2PCoogtakwRTut+Arm58sJooJ0AuZhLw2HJYIR5cMLNPBSS728sPho2khQ=="],
 
@@ -6149,7 +6156,9 @@
 
     "@ai-sdk/groq/@ai-sdk/provider-utils": ["@ai-sdk/provider-utils@4.0.21", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@standard-schema/spec": "^1.1.0", "eventsource-parser": "^3.0.6" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-MtFUYI1/8mgDvRmaBDjbLJPFFrMG777AvSgyIFQtZHIMzm88R/12vYBBpnk7pfiWLFE1DSZzY4WDYzGbKAcmiw=="],
 
-    "@ai-sdk/mistral/@ai-sdk/provider-utils": ["@ai-sdk/provider-utils@4.0.21", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@standard-schema/spec": "^1.1.0", "eventsource-parser": "^3.0.6" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-MtFUYI1/8mgDvRmaBDjbLJPFFrMG777AvSgyIFQtZHIMzm88R/12vYBBpnk7pfiWLFE1DSZzY4WDYzGbKAcmiw=="],
+    "@ai-sdk/mistral/@ai-sdk/provider": ["@ai-sdk/provider@3.0.14", "", { "dependencies": { "json-schema": "^0.4.0" } }, "sha512-5X1k57JBJ4H7H1QjX7CnJYAB1I19r/trVZTMcSms7/kLNZ8RaU4Nt2agcwZzv82Hfx6Q7/TOLU7agAKeFfc8cA=="],
+
+    "@ai-sdk/mistral/@ai-sdk/provider-utils": ["@ai-sdk/provider-utils@4.0.40", "", { "dependencies": { "@ai-sdk/provider": "3.0.14", "@standard-schema/spec": "^1.1.0", "eventsource-parser": "^3.0.8" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-OL5IrpUm9Y8Dwy+w/vvFwPotS6m52O9W0op2oXgXdCROMJIBalBI0oro6OIBYkPxvm5Xg02GSkoQN25RlR0bnw=="],
 
     "@ai-sdk/openai/@ai-sdk/provider-utils": ["@ai-sdk/provider-utils@4.0.21", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@standard-schema/spec": "^1.1.0", "eventsource-parser": "^3.0.6" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-MtFUYI1/8mgDvRmaBDjbLJPFFrMG777AvSgyIFQtZHIMzm88R/12vYBBpnk7pfiWLFE1DSZzY4WDYzGbKAcmiw=="],
 
@@ -6579,6 +6588,8 @@
 
     "@openauthjs/openauth/jose": ["jose@5.9.6", "", {}, "sha512-AMlnetc9+CV9asI19zHmrgS/WYsWUwCn2R7RzlbJWD7F9eWYUTGyBmU9o6PxngtLGOiDGPRu+Uc4fhKzbpteZQ=="],
 
+    "@opencode-ai/app/@opencode-ai/client": ["@opencode-ai/client@vendor/opencode-ai-client-1.17.13.tgz", {}, "sha512-1cYJikTCrXNhnS2qQ3P3rtdbGqhvJKksswG0amJNqgaeUfz3xDlKEDx+YoIosT7Cqk/AtO18jtip0lYL3TVdHQ=="],
+
     "@opencode-ai/cli/semver": ["semver@7.7.4", "", { "bin": { "semver": "bin/semver.js" } }, "sha512-vFKC2IEtQnVhpT78h1Yp8wzwrf8CM+MzKMHGJZfBtzhZNycRFnXsHk6E5TxIkkMsgNS7mdX3AGB7x2QM2di4lA=="],
 
     "@opencode-ai/console-app/@smithy/eventstream-codec": ["@smithy/eventstream-codec@4.2.7", "", { "dependencies": { "@aws-crypto/crc32": "5.2.0", "@smithy/types": "^4.11.0", "@smithy/util-hex-encoding": "^4.2.0", "tslib": "^2.6.2" } }, "sha512-DrpkEoM3j9cBBWhufqBwnbbn+3nf1N9FP6xuVJ+e220jbactKuQgaZwjwP5CP1t+O94brm2JgVMD2atMGX3xIQ=="],
@@ -6597,6 +6608,8 @@
 
     "@opencode-ai/desktop/typescript": ["typescript@5.6.3", "", { "bin": { "tsc": "bin/tsc", "tsserver": "bin/tsserver" } }, "sha512-hjcS1mhfuyi4WW8IWtjP7brDrG2cuDZukyrYrSauoXGNgx0S7zceP07adYkJycEr56BOUTNPzbInooiN3fn1qw=="],
 
+    "@opencode-ai/session-ui/@opencode-ai/client": ["@opencode-ai/client@../app/vendor/opencode-ai-client-1.17.13.tgz", {}, "sha512-1cYJikTCrXNhnS2qQ3P3rtdbGqhvJKksswG0amJNqgaeUfz3xDlKEDx+YoIosT7Cqk/AtO18jtip0lYL3TVdHQ=="],
+
     "@opencode-ai/session-ui/@solid-primitives/resize-observer": ["@solid-primitives/resize-observer@2.1.3", "", { "dependencies": { "@solid-primitives/event-listener": "^2.4.3", "@solid-primitives/rootless": "^1.5.2", "@solid-primitives/static-store": "^0.1.2", "@solid-primitives/utils": "^6.3.2" }, "peerDependencies": { "solid-js": "^1.6.12" } }, "sha512-zBLje5E06TgOg93S7rGPldmhDnouNGhvfZVKOp+oG2XU8snA+GoCSSCz1M+jpNAg5Ek2EakU5UVQqL152WmdXQ=="],
 
     "@opencode-ai/storybook/@types/react": ["@types/react@18.0.25", "", { "dependencies": { "@types/prop-types": "*", "@types/scheduler": "*", "csstype": "^3.0.2" } }, "sha512-xD6c0KDT4m7n9uD4ZHi02lzskaiqcBxf4zi+tXZY98a04wvc0hi/TcCPC2FOESZi51Nd7tlUeOJY8RofL799/g=="],
@@ -6925,6 +6938,8 @@
 
     "aggregate-error/indent-string": ["indent-string@5.0.0", "", {}, "sha512-m6FAo/spmsW2Ab2fU35JTYwtOKa2yAwXSwgjSv1TJzh4Mh7mC3lzAOVLBprb72XsTrgkEIsl7YrFNAiDiRhIGg=="],
 
+    "ai-gateway-provider/@ai-sdk/mistral": ["@ai-sdk/mistral@3.0.27", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@ai-sdk/provider-utils": "4.0.21" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-ZXe7nZQgliDdjz5ufH5RKpHWxbN72AzmzzKGbF/z+0K9GN5tUCnftrQRvTRFHA5jAzTapcm2BEevmGLVbMkW+A=="],
+
     "ai-gateway-provider/@ai-sdk/openai": ["@ai-sdk/openai@3.0.84", "", { "dependencies": { "@ai-sdk/provider": "3.0.14", "@ai-sdk/provider-utils": "4.0.38" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-cmgbeJL0bbY0yTJH4/AdmP5E7MjWRL9G8UdhIi0JlV/So03o82ORJofW8OzwCZPTORVQblFbpZXYGDcUd9NdUQ=="],
 
     "ansi-align/string-width": ["string-width@4.2.3", "", { "dependencies": { "emoji-regex": "^8.0.0", "is-fullwidth-code-point": "^3.0.0", "strip-ansi": "^6.0.1" } }, "sha512-wKyQRQpjJ0sIp62ErSZdGsjMJWsap5oRNihHhu6G7JVO/9jIB6UyevL+tXuOqrng8j/cxKTWyWUwvSTriiZz/g=="],
@@ -8045,6 +8060,8 @@
 
     "@vitest/expect/@vitest/utils/@vitest/pretty-format": ["@vitest/pretty-format@3.2.4", "", { "dependencies": { "tinyrainbow": "^2.0.0" } }, "sha512-IVNZik8IVRJRTr9fxlitMKeJeXFFFN0JaB9PHPGQ8NKQbGpfjlTx9zO4RefN8gp7eqjNy8nyK3NZmBzOPeIxtA=="],
 
+    "ai-gateway-provider/@ai-sdk/mistral/@ai-sdk/provider-utils": ["@ai-sdk/provider-utils@4.0.21", "", { "dependencies": { "@ai-sdk/provider": "3.0.8", "@standard-schema/spec": "^1.1.0", "eventsource-parser": "^3.0.6" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-MtFUYI1/8mgDvRmaBDjbLJPFFrMG777AvSgyIFQtZHIMzm88R/12vYBBpnk7pfiWLFE1DSZzY4WDYzGbKAcmiw=="],
+
     "ai-gateway-provider/@ai-sdk/openai/@ai-sdk/provider": ["@ai-sdk/provider@3.0.14", "", { "dependencies": { "json-schema": "^0.4.0" } }, "sha512-5X1k57JBJ4H7H1QjX7CnJYAB1I19r/trVZTMcSms7/kLNZ8RaU4Nt2agcwZzv82Hfx6Q7/TOLU7agAKeFfc8cA=="],
 
     "ai-gateway-provider/@ai-sdk/openai/@ai-sdk/provider-utils": ["@ai-sdk/provider-utils@4.0.38", "", { "dependencies": { "@ai-sdk/provider": "3.0.14", "@standard-schema/spec": "^1.1.0", "eventsource-parser": "^3.0.8" }, "peerDependencies": { "zod": "^3.25.76 || ^4.1.8" } }, "sha512-/HHGmtKllqjg1OLc023v9w9kK3laW7Z6TzfZukYQWCsGBbzB9p60zTvvpXFVcs44NZBVXL3viOa1HRKUbeee8g=="],

nix/hashes.json

@@ -1,8 +1,8 @@
 {
   "nodeModules": {
-    "x86_64-linux": "sha256-qt11SKmOjq0KU542QFbs+u7YyJicn4drCcwCdg325yk=",
-    "aarch64-linux": "sha256-z68doReXTrWS7HeiAjc0btIjAsvzeZZ7hXAlHr0c77Q=",
-    "aarch64-darwin": "sha256-PILYH1Pi8XBvSkuZ+1sNnUTao5kba+m5Z8iJKx6YXPo=",
-    "x86_64-darwin": "sha256-KpcJzP4m0SUavu/WaSffgzOxrHq8ljdy0GOzs9p16lo="
+    "x86_64-linux": "sha256-0kcwV34P2C3yKg2eG9W2nW+OedrSBb+1TdpuUeYtauY=",
+    "aarch64-linux": "sha256-yHVygApQchAB34wrtFR4GU0CkmZOlLsl3wsp15u0xzs=",
+    "aarch64-darwin": "sha256-DyalcwyK2Wn5R6249keFcNVECbgtjYNjscOFqTi88FI=",
+    "x86_64-darwin": "sha256-BkGw0GWN9W9q+/g4FYR0MqxUuFP80BPoERO+ypz/arQ="
   }
 }

package.json

@@ -155,12 +155,12 @@
     "@types/node": "catalog:"
   },
   "patchedDependencies": {
-    "@ff-labs/fff-bun@0.9.3": "patches/@ff-labs%2Ffff-bun@0.9.3.patch",
     "@npmcli/agent@4.0.2": "patches/@npmcli%2Fagent@4.0.2.patch",
     "@silvia-odwyer/photon-node@0.3.4": "patches/@silvia-odwyer%2Fphoton-node@0.3.4.patch",
     "@standard-community/standard-openapi@0.2.9": "patches/@standard-community%2Fstandard-openapi@0.2.9.patch",
     "solid-js@1.9.10": "patches/solid-js@1.9.10.patch",
     "@ai-sdk/xai@3.0.102": "patches/@ai-sdk%2Fxai@3.0.102.patch",
+    "@ai-sdk/mistral@3.0.51": "patches/@ai-sdk%2Fmistral@3.0.51.patch",
     "gcp-metadata@8.1.2": "patches/gcp-metadata@8.1.2.patch",
     "pacote@21.5.0": "patches/pacote@21.5.0.patch",
     "@ai-sdk/google@3.0.73": "patches/@ai-sdk%2Fgoogle@3.0.73.patch",

packages/ai/example/tutorial.ts

@@ -78,7 +78,10 @@ const streamText = LLM.stream(request).pipe(
   Stream.tap((event) =>
     Effect.sync(() => {
       if (event.type === "text-delta") process.stdout.write(`\ntext: ${event.text}`)
-      if (event.type === "finish") process.stdout.write(`\nfinish: ${event.reason}\n`)
+      if (event.type === "finish")
+        process.stdout.write(
+          `\nfinish: ${event.reason.normalized}${event.reason.raw ? ` (${event.reason.raw})` : ""}\n`,
+        )
     }),
   ),
   Stream.runDrain,
@@ -194,7 +197,7 @@ const FakeProtocol = Protocol.make<FakeBody, string, string, void>({
     event: Schema.String,
     initial: () => undefined,
     step: (_, frame) => Effect.succeed([undefined, [{ type: "text-delta", id: "text-0", text: frame }]] as const),
-    onHalt: () => [{ type: "finish", reason: "stop" }],
+    onHalt: () => [{ type: "finish", reason: { normalized: "stop" } }],
   },
 })
 

packages/ai/src/llm.ts

@@ -81,7 +81,7 @@ const GENERATE_OBJECT_TOOL_NAME = "generate_object"
 
 const GENERATE_OBJECT_TOOL_DESCRIPTION = "Return the structured result by calling this tool."
 
-type GenerateObjectBase = Omit<RequestInput, "tools" | "toolChoice" | "responseFormat">
+type GenerateObjectBase = Omit<RequestInput, "tools" | "toolChoice">
 
 export class GenerateObjectResponse<T> {
   constructor(

packages/ai/src/protocols/anthropic-messages.ts

@@ -27,6 +27,7 @@ import { ToolSchemaProjection } from "./utils/tool-schema"
 import { ToolStream } from "./utils/tool-stream"
 
 const ADAPTER = "anthropic-messages"
+const MEDIA_MIMES = new Set<string>([...ProviderShared.IMAGE_MIMES, ...ProviderShared.PDF_MIMES])
 export const DEFAULT_BASE_URL = "https://api.anthropic.com/v1"
 export const PATH = "/messages"
 
@@ -56,6 +57,17 @@ const AnthropicImageBlock = Schema.Struct({
 })
 type AnthropicImageBlock = Schema.Schema.Type<typeof AnthropicImageBlock>
 
+const AnthropicDocumentBlock = Schema.Struct({
+  type: Schema.tag("document"),
+  source: Schema.Struct({
+    type: Schema.tag("base64"),
+    media_type: Schema.Literal("application/pdf"),
+    data: Schema.String,
+  }),
+  cache_control: Schema.optional(AnthropicCacheControl),
+})
+type AnthropicDocumentBlock = Schema.Schema.Type<typeof AnthropicDocumentBlock>
+
 const AnthropicThinkingBlock = Schema.Struct({
   type: Schema.tag("thinking"),
   thinking: Schema.String,
@@ -101,13 +113,10 @@ const AnthropicServerToolResultBlock = Schema.Struct({
 })
 type AnthropicServerToolResultBlock = Schema.Schema.Type<typeof AnthropicServerToolResultBlock>
 
-// Anthropic accepts either a plain string or an ordered array of text/image
-// blocks inside `tool_result.content`. The array form is required when a tool
-// returns image bytes (screenshot, image search, etc.) so they can be passed
-// to the model as proper image inputs instead of being JSON-stringified into
-// the prompt — which silently inflates context by megabytes and can push the
-// conversation over the model's token limit.
-const AnthropicToolResultContent = Schema.Union([AnthropicTextBlock, AnthropicImageBlock])
+// Anthropic accepts either a plain string or an ordered array of text, image, and
+// document blocks inside `tool_result.content`. The array form keeps media as native
+// model input instead of JSON-stringifying base64 into prompt text.
+const AnthropicToolResultContent = Schema.Union([AnthropicTextBlock, AnthropicImageBlock, AnthropicDocumentBlock])
 
 const AnthropicToolResultBlock = Schema.Struct({
   type: Schema.tag("tool_result"),
@@ -117,7 +126,12 @@ const AnthropicToolResultBlock = Schema.Struct({
   cache_control: Schema.optional(AnthropicCacheControl),
 })
 
-const AnthropicUserBlock = Schema.Union([AnthropicTextBlock, AnthropicImageBlock, AnthropicToolResultBlock])
+const AnthropicUserBlock = Schema.Union([
+  AnthropicTextBlock,
+  AnthropicImageBlock,
+  AnthropicDocumentBlock,
+  AnthropicToolResultBlock,
+])
 type AnthropicUserBlock = Schema.Schema.Type<typeof AnthropicUserBlock>
 const AnthropicAssistantBlock = Schema.Union([
   AnthropicTextBlock,
@@ -145,7 +159,7 @@ const AnthropicTool = Schema.Struct({
 type AnthropicTool = Schema.Schema.Type<typeof AnthropicTool>
 
 const AnthropicToolChoice = Schema.Union([
-  Schema.Struct({ type: Schema.Literals(["auto", "any"]) }),
+  Schema.Struct({ type: Schema.Literals(["auto", "any", "none"]) }),
   Schema.Struct({ type: Schema.tag("tool"), name: Schema.String }),
 ])
 
@@ -283,7 +297,7 @@ const lowerTool = (breakpoints: Cache.Breakpoints, tool: ToolDefinition, inputSc
 const lowerToolChoice = (toolChoice: NonNullable<LLMRequest["toolChoice"]>) =>
   ProviderShared.matchToolChoice("Anthropic Messages", toolChoice, {
     auto: () => ({ type: "auto" as const }),
-    none: () => undefined,
+    none: () => ({ type: "none" as const }),
     required: () => ({ type: "any" as const }),
     tool: (name) => ({ type: "tool" as const, name }),
   })
@@ -316,15 +330,23 @@ const lowerServerToolResult = Effect.fn("AnthropicMessages.lowerServerToolResult
   const wireType = serverToolResultType(part.name)
   if (!wireType)
     return yield* invalid(`Anthropic Messages does not know how to round-trip server tool result for ${part.name}`)
-  return { type: wireType, tool_use_id: part.id, content: part.result.value } satisfies AnthropicServerToolResultBlock
+  // Prefer the provider-owned replay payload; fall back to the result value for
+  // histories constructed directly from provider events.
+  const payload = part.providerMetadata?.anthropic?.["result"] ?? part.result.value
+  return { type: wireType, tool_use_id: part.id, content: payload } satisfies AnthropicServerToolResultBlock
 })
 
-const lowerImage = Effect.fn("AnthropicMessages.lowerImage")(function* (part: MediaPart) {
-  const media = yield* ProviderShared.validateMedia(
-    "Anthropic Messages",
-    part,
-    new Set<string>(ProviderShared.IMAGE_MIMES),
-  )
+const lowerMedia = Effect.fn("AnthropicMessages.lowerMedia")(function* (part: MediaPart) {
+  const media = yield* ProviderShared.validateMedia("Anthropic Messages", part, MEDIA_MIMES)
+  if (media.mime === "application/pdf")
+    return {
+      type: "document" as const,
+      source: {
+        type: "base64" as const,
+        media_type: "application/pdf" as const,
+        data: media.base64,
+      },
+    } satisfies AnthropicDocumentBlock
   return {
     type: "image" as const,
     source: {
@@ -335,25 +357,13 @@ const lowerImage = Effect.fn("AnthropicMessages.lowerImage")(function* (part: Me
   } satisfies AnthropicImageBlock
 })
 
-// Tool results may carry structured text/images. Keep media as provider-native
+// Tool results may carry structured text, images, and documents. Keep media as provider-native
 // content instead of JSON-stringifying base64 into a prompt string.
 const lowerToolResultContentItem = Effect.fn("AnthropicMessages.lowerToolResultContentItem")(function* (
   item: ToolContent,
 ) {
   if (item.type === "text") return { type: "text" as const, text: item.text } satisfies AnthropicTextBlock
-  const media = yield* ProviderShared.validateToolFile(
-    "Anthropic Messages",
-    item,
-    new Set<string>(ProviderShared.IMAGE_MIMES),
-  )
-  return {
-    type: "image" as const,
-    source: {
-      type: "base64" as const,
-      media_type: media.mime,
-      data: media.base64,
-    },
-  } satisfies AnthropicImageBlock
+  return yield* lowerMedia({ type: "media", mediaType: item.mime, data: item.uri, filename: item.name })
 })
 
 const lowerToolResultContent = Effect.fn("AnthropicMessages.lowerToolResultContent")(function* (part: ToolResultPart) {
@@ -445,7 +455,7 @@ const lowerMessages = Effect.fn("AnthropicMessages.lowerMessages")(function* (
           continue
         }
         if (part.type === "media") {
-          content.push(yield* lowerImage(part))
+          content.push(yield* lowerMedia(part))
           continue
         }
         return yield* ProviderShared.unsupportedContent("Anthropic Messages", "user", ["text", "media"])
@@ -535,7 +545,6 @@ const outputConfig = (request: LLMRequest) => {
 }
 
 const fromRequest = Effect.fn("AnthropicMessages.fromRequest")(function* (request: LLMRequest) {
-  const toolChoice = request.toolChoice ? yield* lowerToolChoice(request.toolChoice) : undefined
   const generation = request.generation
   const toolSchemaCompatibility = request.model.compatibility?.toolSchema
   const outputLimit = request.model.defaults?.limits?.output ?? request.model.route.defaults.limits?.output ?? 4096
@@ -544,7 +553,7 @@ const fromRequest = Effect.fn("AnthropicMessages.fromRequest")(function* (reques
   // over-mark we keep their tool hints and shed the message-tail ones first.
   const breakpoints = Cache.newBreakpoints(ANTHROPIC_BREAKPOINT_CAP)
   const tools =
-    request.tools.length === 0 || request.toolChoice?.type === "none"
+    request.tools.length === 0
       ? undefined
       : request.tools.map((tool) =>
           lowerTool(
@@ -553,6 +562,9 @@ const fromRequest = Effect.fn("AnthropicMessages.fromRequest")(function* (reques
             ToolSchemaProjection.modelCompatibility(tool.inputSchema, toolSchemaCompatibility),
           ),
         )
+  // Anthropic rejects tool_choice when tools are absent; "none" is only meaningful with tools present.
+  const toolChoice =
+    tools === undefined || !request.toolChoice ? undefined : yield* lowerToolChoice(request.toolChoice)
   const system =
     request.system.length === 0
       ? undefined
@@ -589,7 +601,7 @@ const fromRequest = Effect.fn("AnthropicMessages.fromRequest")(function* (reques
 // =============================================================================
 const mapFinishReason = (reason: string | null | undefined): FinishReason => {
   if (reason === "end_turn" || reason === "stop_sequence" || reason === "pause_turn") return "stop"
-  if (reason === "max_tokens") return "length"
+  if (reason === "max_tokens" || reason === "model_context_window_exceeded") return "length"
   if (reason === "tool_use") return "tool-calls"
   if (reason === "refusal") return "content-filter"
   return "unknown"
@@ -673,7 +685,9 @@ const serverToolResultEvent = (block: NonNullable<AnthropicEvent["content_block"
     name: SERVER_TOOL_RESULT_NAMES[block.type],
     result: isError ? { type: "error", value: block.content } : { type: "json", value: block.content },
     providerExecuted: true,
-    providerMetadata: anthropicMetadata({ blockType: block.type }),
+    // The complete payload is irreducible provider replay state: subsequent
+    // stateless requests must round-trip the typed result block verbatim.
+    providerMetadata: anthropicMetadata({ blockType: block.type, result: block.content }),
   })
 }
 
@@ -822,7 +836,10 @@ const onMessageDelta = (state: ParserState, event: AnthropicEvent): StepResult =
   const usage = mergeUsage(state.usage, mapUsage(event.usage))
   const events: LLMEvent[] = []
   const lifecycle = Lifecycle.finish(state.lifecycle, events, {
-    reason: mapFinishReason(event.delta?.stop_reason),
+    reason: {
+      normalized: mapFinishReason(event.delta?.stop_reason),
+      raw: event.delta?.stop_reason ?? undefined,
+    },
     usage,
     providerMetadata: event.delta?.stop_sequence
       ? anthropicMetadata({ stopSequence: event.delta.stop_sequence })

packages/ai/src/protocols/bedrock-converse.ts

@@ -8,6 +8,7 @@ import {
   Usage,
   type CacheHint,
   type FinishReason,
+  type FinishReasonDetails,
   type JsonSchema,
   type LLMRequest,
   type ModelToolSchemaCompatibility,
@@ -52,6 +53,7 @@ const BedrockToolResultContentItem = Schema.Union([
   Schema.Struct({ text: Schema.String }),
   Schema.Struct({ json: Schema.Unknown }),
   BedrockMedia.ImageBlock,
+  BedrockMedia.DocumentBlock,
 ])
 
 const BedrockToolResultBlock = Schema.Struct({
@@ -283,8 +285,6 @@ const lowerToolResultContent = Effect.fn("BedrockConverse.lowerToolResultContent
       data: item.uri,
       filename: item.name,
     })
-    if (!("image" in media))
-      return yield* ProviderShared.invalidRequest("Bedrock Converse only supports image media in tool results")
     content.push(media)
   }
   return content
@@ -393,8 +393,13 @@ const fromRequest = Effect.fn("BedrockConverse.fromRequest")(function* (request:
   // tools → system → messages order to favour the highest-impact prefixes.
   const breakpoints = BedrockCache.breakpoints()
   const toolConfig =
-    request.tools.length > 0 && request.toolChoice?.type !== "none"
-      ? { tools: lowerTools(request.model.compatibility?.toolSchema, breakpoints, request.tools), toolChoice }
+    request.tools.length > 0
+      ? {
+          tools: lowerTools(request.model.compatibility?.toolSchema, breakpoints, request.tools),
+          // Converse has no native "none". Keep definitions stable for prompt
+          // caching and omit only the unsupported choice.
+          toolChoice,
+        }
       : undefined
   const system = request.system.length === 0 ? undefined : lowerSystem(breakpoints, request.system)
   const messages = yield* lowerMessages(request, breakpoints)
@@ -431,27 +436,29 @@ const fromRequest = Effect.fn("BedrockConverse.fromRequest")(function* (request:
 // =============================================================================
 const mapFinishReason = (reason: string): FinishReason => {
   if (reason === "end_turn" || reason === "stop_sequence") return "stop"
-  if (reason === "max_tokens") return "length"
+  if (reason === "max_tokens" || reason === "model_context_window_exceeded") return "length"
   if (reason === "tool_use") return "tool-calls"
   if (reason === "content_filtered" || reason === "guardrail_intervened") return "content-filter"
+  if (reason === "malformed_model_output" || reason === "malformed_tool_use") return "error"
   return "unknown"
 }
 
-// AWS Bedrock Converse reports `inputTokens` (inclusive total) with
-// `cacheReadInputTokens` and `cacheWriteInputTokens` as subsets. Pass
-// the total through and derive the non-cached breakdown. Bedrock does
-// not break reasoning out of `outputTokens` for any current model.
+// AWS reports inputTokens separately from cache reads and writes.
+// Bedrock does not break reasoning out of outputTokens for current models.
 const mapUsage = (usage: BedrockUsageSchema | undefined): Usage | undefined => {
   if (!usage) return undefined
-  const cacheTotal = (usage.cacheReadInputTokens ?? 0) + (usage.cacheWriteInputTokens ?? 0)
-  const nonCached = ProviderShared.subtractTokens(usage.inputTokens, cacheTotal)
+  const inputTokens = ProviderShared.sumTokens(
+    usage.inputTokens,
+    usage.cacheReadInputTokens,
+    usage.cacheWriteInputTokens,
+  )
   return new Usage({
-    inputTokens: usage.inputTokens,
+    inputTokens,
     outputTokens: usage.outputTokens,
-    nonCachedInputTokens: nonCached,
+    nonCachedInputTokens: usage.inputTokens,
     cacheReadInputTokens: usage.cacheReadInputTokens,
     cacheWriteInputTokens: usage.cacheWriteInputTokens,
-    totalTokens: ProviderShared.totalTokens(usage.inputTokens, usage.outputTokens, usage.totalTokens),
+    totalTokens: ProviderShared.totalTokens(inputTokens, usage.outputTokens, usage.totalTokens),
     providerMetadata: { bedrock: usage },
   })
 }
@@ -461,7 +468,7 @@ interface ParserState {
   // Bedrock splits the finish into `messageStop` (carries `stopReason`) and
   // `metadata` (carries usage). Hold the terminal event in state so `onHalt`
   // can emit exactly one finish after both chunks have had a chance to arrive.
-  readonly pendingFinish: { readonly reason: FinishReason; readonly usage?: Usage } | undefined
+  readonly pendingFinish: { readonly reason: FinishReasonDetails; readonly usage?: Usage } | undefined
   readonly hasToolCalls: boolean
   readonly lifecycle: Lifecycle.State
   readonly reasoningSignatures: Readonly<Record<number, string>>
@@ -578,7 +585,13 @@ const step = (state: ParserState, event: BedrockEvent) =>
       return [
         {
           ...state,
-          pendingFinish: { reason: mapFinishReason(event.messageStop.stopReason), usage: state.pendingFinish?.usage },
+          pendingFinish: {
+            reason: {
+              normalized: mapFinishReason(event.messageStop.stopReason),
+              raw: event.messageStop.stopReason,
+            },
+            usage: state.pendingFinish?.usage,
+          },
         },
         [],
       ] as const
@@ -586,7 +599,16 @@ const step = (state: ParserState, event: BedrockEvent) =>
 
     if (event.metadata) {
       const usage = mapUsage(event.metadata.usage)
-      return [{ ...state, pendingFinish: { reason: state.pendingFinish?.reason ?? "stop", usage } }, []] as const
+      return [
+        {
+          ...state,
+          pendingFinish: {
+            reason: state.pendingFinish?.reason ?? { normalized: "stop" },
+            usage,
+          },
+        },
+        [],
+      ] as const
     }
 
     const exception = (
@@ -619,8 +641,13 @@ const onHalt = (state: ParserState): ReadonlyArray<LLMEvent> =>
     ? (() => {
         const events: LLMEvent[] = []
         Lifecycle.finish(state.lifecycle, events, {
-          reason:
-            state.pendingFinish.reason === "stop" && state.hasToolCalls ? "tool-calls" : state.pendingFinish.reason,
+          reason: {
+            ...state.pendingFinish.reason,
+            normalized:
+              state.pendingFinish.reason.normalized === "stop" && state.hasToolCalls
+                ? "tool-calls"
+                : state.pendingFinish.reason.normalized,
+          },
           usage: state.pendingFinish.usage,
         })
         return events

packages/ai/src/protocols/gemini.ts

@@ -41,9 +41,11 @@ const GeminiInlineDataPart = Schema.Struct({
     data: Schema.String,
   }),
 })
+type GeminiInlineDataPart = Schema.Schema.Type<typeof GeminiInlineDataPart>
 
 const GeminiFunctionCallPart = Schema.Struct({
   functionCall: Schema.Struct({
+    id: Schema.optional(Schema.String),
     name: Schema.String,
     args: Schema.Unknown,
   }),
@@ -52,8 +54,10 @@ const GeminiFunctionCallPart = Schema.Struct({
 
 const GeminiFunctionResponsePart = Schema.Struct({
   functionResponse: Schema.Struct({
+    id: Schema.optional(Schema.String),
     name: Schema.String,
     response: Schema.Unknown,
+    parts: Schema.optional(Schema.Array(GeminiInlineDataPart)),
   }),
 })
 
@@ -197,8 +201,13 @@ const thoughtSignature = (providerMetadata: ProviderMetadata | undefined) => {
     : undefined
 }
 
+const functionCallId = (providerMetadata: ProviderMetadata | undefined) => {
+  const google = providerMetadata?.google
+  return ProviderShared.isRecord(google) && typeof google.functionCallId === "string" ? google.functionCallId : undefined
+}
+
 const lowerToolCall = (part: ToolCallPart) => ({
-  functionCall: { name: part.name, args: part.input },
+  functionCall: { id: functionCallId(part.providerMetadata), name: part.name, args: part.input },
   thoughtSignature: thoughtSignature(part.providerMetadata),
 })
 
@@ -255,6 +264,7 @@ const lowerMessages = Effect.fn("Gemini.lowerMessages")(function* (request: LLMR
       if (part.result.type !== "content") {
         parts.push({
           functionResponse: {
+            id: functionCallId(part.providerMetadata),
             name: part.name,
             response: {
               name: part.name,
@@ -266,20 +276,23 @@ const lowerMessages = Effect.fn("Gemini.lowerMessages")(function* (request: LLMR
       }
       const content: ReadonlyArray<ToolContent> = part.result.value
       const text = content.filter((item) => item.type === "text").map((item) => item.text)
+      const media: GeminiInlineDataPart[] = []
+      for (const item of content) {
+        if (item.type === "text") continue
+        const value = yield* ProviderShared.validateToolFile("Gemini", item, MEDIA_MIMES)
+        media.push({ inlineData: { mimeType: value.mime, data: value.base64 } })
+      }
       parts.push({
         functionResponse: {
+          id: functionCallId(part.providerMetadata),
           name: part.name,
           response: {
             name: part.name,
             content: text.join("\n"),
           },
+          parts: media.length > 0 ? media : undefined,
         },
       })
-      for (const item of content) {
-        if (item.type === "text") continue
-        const media = yield* ProviderShared.validateToolFile("Gemini", item, MEDIA_MIMES)
-        parts.push({ inlineData: { mimeType: media.mime, data: media.base64 } })
-      }
     }
     contents.push({ role: "user", parts })
   }
@@ -300,7 +313,7 @@ const thinkingConfig = (request: LLMRequest) => {
 }
 
 const fromRequest = Effect.fn("Gemini.fromRequest")(function* (request: LLMRequest) {
-  const toolsEnabled = request.tools.length > 0 && request.toolChoice?.type !== "none"
+  const hasTools = request.tools.length > 0
   const generation = request.generation
   const toolSchemaCompatibility = request.model.compatibility?.toolSchema
   const generationConfig = {
@@ -316,7 +329,7 @@ const fromRequest = Effect.fn("Gemini.fromRequest")(function* (request: LLMReque
     contents: yield* lowerMessages(request),
     systemInstruction:
       request.system.length === 0 ? undefined : { parts: [{ text: ProviderShared.joinText(request.system) }] },
-    tools: toolsEnabled
+    tools: hasTools
       ? [
           {
             functionDeclarations: request.tools.map((tool) =>
@@ -325,7 +338,7 @@ const fromRequest = Effect.fn("Gemini.fromRequest")(function* (request: LLMReque
           },
         ]
       : undefined,
-    toolConfig: toolsEnabled && request.toolChoice ? yield* lowerToolConfig(request.toolChoice) : undefined,
+    toolConfig: hasTools && request.toolChoice ? yield* lowerToolConfig(request.toolChoice) : undefined,
     generationConfig: Object.values(generationConfig).some((value) => value !== undefined)
       ? generationConfig
       : undefined,
@@ -369,10 +382,22 @@ const mapFinishReason = (finishReason: string | undefined, hasToolCalls: boolean
     finishReason === "SAFETY" ||
     finishReason === "BLOCKLIST" ||
     finishReason === "PROHIBITED_CONTENT" ||
-    finishReason === "SPII"
+    finishReason === "SPII" ||
+    finishReason === "MODEL_ARMOR" ||
+    finishReason === "IMAGE_PROHIBITED_CONTENT" ||
+    finishReason === "IMAGE_RECITATION" ||
+    finishReason === "LANGUAGE"
   )
     return "content-filter"
-  if (finishReason === "MALFORMED_FUNCTION_CALL") return "error"
+  if (
+    finishReason === "MALFORMED_FUNCTION_CALL" ||
+    finishReason === "UNEXPECTED_TOOL_CALL" ||
+    finishReason === "NO_IMAGE" ||
+    finishReason === "TOO_MANY_TOOL_CALLS" ||
+    finishReason === "MISSING_THOUGHT_SIGNATURE" ||
+    finishReason === "MALFORMED_RESPONSE"
+  )
+    return "error"
   return "unknown"
 }
 
@@ -389,7 +414,10 @@ const finish = (state: ParserState): ReadonlyArray<LLMEvent> =>
             )
           : state.lifecycle
         Lifecycle.finish(lifecycle, events, {
-          reason: mapFinishReason(state.finishReason, state.hasToolCalls),
+          reason: {
+            normalized: mapFinishReason(state.finishReason, state.hasToolCalls),
+            raw: state.finishReason,
+          },
           usage: state.usage,
         })
         return events
@@ -441,6 +469,10 @@ const step = (state: ParserState, event: GeminiEvent) => {
     if ("functionCall" in part) {
       const input = part.functionCall.args
       const id = `tool_${nextToolCallId++}`
+      const metadata = {
+        ...(part.functionCall.id === undefined ? {} : { functionCallId: part.functionCall.id }),
+        ...(part.thoughtSignature === undefined ? {} : { thoughtSignature: part.thoughtSignature }),
+      }
       lifecycle = Lifecycle.reasoningEnd(
         lifecycle,
         events,
@@ -453,9 +485,7 @@ const step = (state: ParserState, event: GeminiEvent) => {
           id,
           name: part.functionCall.name,
           input,
-          providerMetadata: part.thoughtSignature
-            ? googleMetadata({ thoughtSignature: part.thoughtSignature })
-            : undefined,
+          providerMetadata: Object.keys(metadata).length > 0 ? googleMetadata(metadata) : undefined,
         }),
       )
       hasToolCalls = true

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

@@ -5,9 +5,11 @@ import { Endpoint } from "../route/endpoint"
 import { HttpTransport } from "../route/transport"
 import { Protocol } from "../route/protocol"
 import {
+  LLMError,
   LLMEvent,
   Usage,
   type FinishReason,
+  type FinishReasonDetails,
   type JsonSchema,
   type LLMRequest,
   type MediaPart,
@@ -17,6 +19,7 @@ import {
   type ToolDefinition,
   type ToolContent,
 } from "../schema"
+import { classifyProviderFailure } from "../provider-error"
 import { isRecord, JsonObject, optionalArray, optionalNull, ProviderShared } from "./shared"
 import { OpenAIOptions } from "./utils/openai-options"
 import { Lifecycle } from "./utils/lifecycle"
@@ -25,6 +28,7 @@ import { ToolStream } from "./utils/tool-stream"
 
 const ADAPTER = "openai-chat"
 const IMAGE_MIMES = new Set<string>(ProviderShared.IMAGE_MIMES)
+const RESERVED_REASONING_FIELDS = new Set(["role", "content", "tool_calls"])
 export const DEFAULT_BASE_URL = "https://api.openai.com/v1"
 export const PATH = "/chat/completions"
 
@@ -70,15 +74,18 @@ const OpenAIChatMessage = Schema.Union([
     role: Schema.Literal("user"),
     content: Schema.Union([Schema.String, Schema.Array(OpenAIChatUserContent)]),
   }),
-  Schema.Struct({
-    role: Schema.Literal("assistant"),
-    content: Schema.NullOr(Schema.String),
-    tool_calls: optionalArray(OpenAIChatAssistantToolCall),
-    reasoning_content: Schema.optional(Schema.String),
-    reasoning: Schema.optional(Schema.String),
-    reasoning_text: Schema.optional(Schema.String),
-    reasoning_details: optionalArray(Schema.Unknown),
-  }),
+  Schema.StructWithRest(
+    Schema.Struct({
+      role: Schema.Literal("assistant"),
+      content: Schema.NullOr(Schema.String),
+      tool_calls: optionalArray(OpenAIChatAssistantToolCall),
+      reasoning_content: Schema.optional(Schema.String),
+      reasoning: Schema.optional(Schema.String),
+      reasoning_text: Schema.optional(Schema.String),
+      reasoning_details: Schema.optional(Schema.Unknown),
+    }),
+    [Schema.Record(Schema.String, Schema.Unknown)],
+  ),
   Schema.Struct({ role: Schema.Literal("tool"), tool_call_id: Schema.String, content: Schema.String }),
 ]).pipe(Schema.toTaggedUnion("role"))
 type OpenAIChatMessage = Schema.Schema.Type<typeof OpenAIChatMessage>
@@ -145,23 +152,33 @@ const OpenAIChatToolCallDelta = Schema.Struct({
 })
 type OpenAIChatToolCallDelta = Schema.Schema.Type<typeof OpenAIChatToolCallDelta>
 
-const OpenAIChatDelta = Schema.Struct({
-  content: optionalNull(Schema.String),
-  reasoning_content: optionalNull(Schema.String),
-  reasoning: optionalNull(Schema.String),
-  reasoning_text: optionalNull(Schema.String),
-  reasoning_details: optionalNull(Schema.Array(Schema.Unknown)),
-  tool_calls: optionalNull(Schema.Array(OpenAIChatToolCallDelta)),
-})
+const OpenAIChatDelta = Schema.StructWithRest(
+  Schema.Struct({
+    content: optionalNull(Schema.String),
+    reasoning_content: optionalNull(Schema.String),
+    reasoning: optionalNull(Schema.String),
+    reasoning_text: optionalNull(Schema.String),
+    reasoning_details: optionalNull(Schema.Unknown),
+    tool_calls: optionalNull(Schema.Array(OpenAIChatToolCallDelta)),
+  }),
+  [Schema.Record(Schema.String, Schema.Unknown)],
+)
 
 const OpenAIChatChoice = Schema.Struct({
   delta: optionalNull(OpenAIChatDelta),
   finish_reason: optionalNull(Schema.String),
+  native_finish_reason: optionalNull(Schema.String),
+})
+
+const OpenAIChatError = Schema.Struct({
+  code: optionalNull(Schema.Union([Schema.String, Schema.Number])),
+  message: Schema.String,
 })
 
 export const OpenAIChatEvent = Schema.Struct({
-  choices: Schema.Array(OpenAIChatChoice),
+  choices: optionalNull(Schema.Array(OpenAIChatChoice)),
   usage: optionalNull(OpenAIChatUsage),
+  error: optionalNull(OpenAIChatError),
 })
 export type OpenAIChatEvent = Schema.Schema.Type<typeof OpenAIChatEvent>
 type OpenAIChatRequestMessage = LLMRequest["messages"][number]
@@ -177,9 +194,9 @@ export interface ParserState {
   readonly pendingTools: Partial<Record<number, PendingToolDelta>>
   readonly toolCallEvents: ReadonlyArray<LLMEvent>
   readonly usage?: Usage
-  readonly finishReason?: FinishReason
+  readonly finishReason?: FinishReasonDetails
   readonly lifecycle: Lifecycle.State
-  readonly reasoningField?: "reasoning" | "reasoning_content" | "reasoning_text"
+  readonly reasoningField?: string
   readonly reasoningDetails: Array<unknown>
   readonly reasoningDetailsObserved: boolean
   readonly reasoningEmitted: boolean
@@ -227,7 +244,7 @@ const openAICompatibleReasoningContent = (native: unknown) =>
 
 const reasoningField = (part: ReasoningPart) => {
   const field = part.providerMetadata?.openai?.reasoningField
-  if (field === "reasoning" || field === "reasoning_content" || field === "reasoning_text") return field
+  return typeof field === "string" ? field : undefined
 }
 
 const reasoningDetails = (parts: ReadonlyArray<ReasoningPart>, native: unknown) => {
@@ -259,6 +276,7 @@ const lowerUserMessage = Effect.fn("OpenAIChat.lowerUserMessage")(function* (mes
 
 const lowerAssistantMessage = Effect.fn("OpenAIChat.lowerAssistantMessage")(function* (
   message: OpenAIChatRequestMessage,
+  configuredField?: string,
 ) {
   const content: TextPart[] = []
   const reasoning: ReasoningPart[] = []
@@ -285,24 +303,25 @@ const lowerAssistantMessage = Effect.fn("OpenAIChat.lowerAssistantMessage")(func
   const nativeReasoning = openAICompatibleReasoningContent(message.native?.openaiCompatible)
   const fullyStructured = reasoning.every((part) => Array.isArray(part.providerMetadata?.openai?.reasoningDetails))
   const field = (() => {
-    if (reasoning.length === 0) return
+    if (configuredField !== undefined) return configuredField
+    if (reasoning.length === 0) return undefined
     if (observedField !== undefined) return observedField
     if (nativeReasoning !== undefined) return "reasoning_content"
     if (!fullyStructured) return "reasoning_content"
   })()
-  const reasoningContent = (() => {
+  const reasoningText = (() => {
+    if (configuredField !== undefined) return reasoning.length === 0 ? (nativeReasoning ?? "") : text
     if (reasoning.length === 0) return nativeReasoning
-    if (field === "reasoning_content") return text
+    return text
   })()
-  return {
+  const result = {
     role: "assistant" as const,
     content: content.length === 0 ? null : ProviderShared.joinText(content),
     tool_calls: toolCalls.length === 0 ? undefined : toolCalls,
-    reasoning_content: reasoningContent,
-    reasoning: reasoning.length > 0 && field === "reasoning" ? text : undefined,
-    reasoning_text: reasoning.length > 0 && field === "reasoning_text" ? text : undefined,
     reasoning_details: details,
   }
+  if (field === undefined || reasoningText === undefined) return result
+  return { ...result, [field]: reasoningText }
 })
 
 const lowerToolMessages = Effect.fn("OpenAIChat.lowerToolMessages")(function* (message: OpenAIChatRequestMessage) {
@@ -328,9 +347,12 @@ const lowerToolMessages = Effect.fn("OpenAIChat.lowerToolMessages")(function* (m
   return { messages, images }
 })
 
-const lowerMessage = Effect.fn("OpenAIChat.lowerMessage")(function* (message: OpenAIChatRequestMessage) {
+const lowerMessage = Effect.fn("OpenAIChat.lowerMessage")(function* (
+  message: OpenAIChatRequestMessage,
+  reasoningField?: string,
+) {
   if (message.role === "user") return [yield* lowerUserMessage(message)]
-  if (message.role === "assistant") return [yield* lowerAssistantMessage(message)]
+  if (message.role === "assistant") return [yield* lowerAssistantMessage(message, reasoningField)]
   return (yield* lowerToolMessages(message)).messages
 })
 
@@ -368,7 +390,7 @@ const lowerMessages = Effect.fn("OpenAIChat.lowerMessages")(function* (request:
       continue
     }
     flushImages()
-    messages.push(...(yield* lowerMessage(message)))
+    messages.push(...(yield* lowerMessage(message, request.model.compatibility?.reasoningField)))
   }
   flushImages()
   return messages
@@ -386,6 +408,11 @@ const lowerOptions = Effect.fn("OpenAIChat.lowerOptions")(function* (request: LL
 const fromRequest = Effect.fn("OpenAIChat.fromRequest")(function* (request: LLMRequest) {
   // `fromRequest` returns the provider body only. Endpoint, auth, framing,
   // validation, and HTTP execution are composed by `Route.make`.
+  const reasoningField = request.model.compatibility?.reasoningField
+  if (reasoningField && RESERVED_REASONING_FIELDS.has(reasoningField))
+    return yield* ProviderShared.invalidRequest(
+      `OpenAI Chat reasoning field conflicts with reserved field ${reasoningField}`,
+    )
   const generation = request.generation
   const toolSchemaCompatibility = request.model.compatibility?.toolSchema
   return {
@@ -422,6 +449,7 @@ const mapFinishReason = (reason: string | null | undefined): FinishReason => {
   if (reason === "length") return "length"
   if (reason === "content_filter") return "content-filter"
   if (reason === "function_call" || reason === "tool_calls") return "tool-calls"
+  if (reason === "error") return "error"
   return "unknown"
 }
 
@@ -446,10 +474,18 @@ const mapUsage = (usage: OpenAIChatEvent["usage"]): Usage | undefined => {
   })
 }
 
-const reasoningDelta = (delta: Schema.Schema.Type<typeof OpenAIChatDelta> | null | undefined) => {
-  if (delta?.reasoning_content) return { field: "reasoning_content", text: delta.reasoning_content } as const
-  if (delta?.reasoning) return { field: "reasoning", text: delta.reasoning } as const
-  if (delta?.reasoning_text) return { field: "reasoning_text", text: delta.reasoning_text } as const
+const reasoningDelta = (
+  delta: Schema.Schema.Type<typeof OpenAIChatDelta> | null | undefined,
+  configuredField?: string,
+) => {
+  if (!delta) return undefined
+  const fields = new Set([configuredField, "reasoning_content", "reasoning", "reasoning_text"])
+  for (const field of fields) {
+    if (field === undefined) continue
+    const text = delta[field]
+    if (typeof text === "string" && text.length > 0) return { field, text }
+  }
+  return undefined
 }
 
 const detailText = (details: ReadonlyArray<unknown>) => {
@@ -507,10 +543,22 @@ const reasoningMetadata = (field: ParserState["reasoningField"], details?: Reado
 
 const step = (state: ParserState, event: OpenAIChatEvent) =>
   Effect.gen(function* () {
+    if (event.error)
+      return yield* new LLMError({
+        module: ADAPTER,
+        method: "stream",
+        reason: classifyProviderFailure({
+          message: event.error.message,
+          code: event.error.code === undefined || event.error.code === null ? undefined : String(event.error.code),
+          status: typeof event.error.code === "number" ? event.error.code : undefined,
+        }),
+      })
     const events: LLMEvent[] = []
     const usage = mapUsage(event.usage) ?? state.usage
-    const choice = event.choices[0]
-    const finishReason = choice?.finish_reason ? mapFinishReason(choice.finish_reason) : state.finishReason
+    const choice = event.choices?.[0]
+    const finishReason = choice?.finish_reason
+      ? { normalized: mapFinishReason(choice.finish_reason), raw: choice.native_finish_reason ?? choice.finish_reason }
+      : state.finishReason
     const delta = choice?.delta
     const toolDeltas = delta?.tool_calls ?? []
     let tools = state.tools
@@ -518,7 +566,7 @@ const step = (state: ParserState, event: OpenAIChatEvent) =>
 
     let lifecycle = state.lifecycle
 
-    const reasoning = reasoningDelta(delta)
+    const reasoning = reasoningDelta(delta, state.reasoningField)
     const reasoningField = state.reasoningField ?? (!state.lifecycle.text.has("text-0") ? reasoning?.field : undefined)
     const detailDelta = Array.isArray(delta?.reasoning_details) ? delta.reasoning_details : undefined
     if (detailDelta !== undefined) appendReasoningDetails(state.reasoningDetails, detailDelta)
@@ -602,7 +650,13 @@ const step = (state: ParserState, event: OpenAIChatEvent) =>
 const finishEvents = (state: ParserState): ReadonlyArray<LLMEvent> => {
   const events: LLMEvent[] = []
   const hasToolCalls = state.toolCallEvents.length > 0
-  const reason = state.finishReason === "stop" && hasToolCalls ? "tool-calls" : state.finishReason
+  const reason = state.finishReason
+    ? {
+        ...state.finishReason,
+        normalized:
+          state.finishReason.normalized === "stop" && hasToolCalls ? "tool-calls" : state.finishReason.normalized,
+      }
+    : undefined
   const metadata = reasoningMetadata(
     state.reasoningField,
     state.reasoningDetailsObserved ? state.reasoningDetails : undefined,
@@ -635,12 +689,12 @@ export const protocol = Protocol.make({
   },
   stream: {
     event: Protocol.jsonEvent(OpenAIChatEvent),
-    initial: () => ({
+    initial: (request) => ({
       tools: ToolStream.empty<number>(),
       pendingTools: {},
       toolCallEvents: [],
       lifecycle: Lifecycle.initial(),
-      reasoningField: undefined,
+      reasoningField: request.model.compatibility?.reasoningField,
       reasoningDetails: [],
       reasoningDetailsObserved: false,
       reasoningEmitted: false,

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

@@ -11,6 +11,7 @@ import {
   type FinishReason,
   type JsonSchema,
   type LLMRequest,
+  type MediaPart,
   type ProviderMetadata,
   type ReasoningPart,
   type TextPart,
@@ -28,6 +29,7 @@ import { ToolStream } from "./utils/tool-stream"
 import { OpenAIImage } from "./utils/openai-image"
 
 const ADAPTER = "openai-responses"
+const MEDIA_MIMES = new Set<string>([...ProviderShared.IMAGE_MIMES, ...ProviderShared.PDF_MIMES])
 export const DEFAULT_BASE_URL = "https://api.openai.com/v1"
 export const PATH = "/responses"
 
@@ -42,7 +44,17 @@ const OpenAIResponsesInputImage = Schema.Struct({
   type: Schema.tag("input_image"),
   image_url: Schema.String,
 })
-const OpenAIResponsesInputContent = Schema.Union([OpenAIResponsesInputText, OpenAIResponsesInputImage])
+const OpenAIResponsesInputFile = Schema.Struct({
+  type: Schema.tag("input_file"),
+  filename: Schema.String,
+  file_data: Schema.String,
+  mime_type: Schema.optional(Schema.String),
+})
+const OpenAIResponsesInputContent = Schema.Union([
+  OpenAIResponsesInputText,
+  OpenAIResponsesInputImage,
+  OpenAIResponsesInputFile,
+])
 type OpenAIResponsesInputContent = Schema.Schema.Type<typeof OpenAIResponsesInputContent>
 
 const OpenAIResponsesOutputText = Schema.Struct({
@@ -68,9 +80,13 @@ const OpenAIResponsesItemReference = Schema.Struct({
 })
 
 // `function_call_output.output` accepts either a plain string or an ordered
-// array of content items so tools can return images in addition to text.
+// array of content items so tools can return images and files in addition to text.
 // https://platform.openai.com/docs/api-reference/responses/object
-const OpenAIResponsesFunctionCallOutputContent = Schema.Union([OpenAIResponsesInputText, OpenAIResponsesInputImage])
+const OpenAIResponsesFunctionCallOutputContent = Schema.Union([
+  OpenAIResponsesInputText,
+  OpenAIResponsesInputImage,
+  OpenAIResponsesInputFile,
+])
 
 const OpenAIResponsesFunctionCallOutput = Schema.Union([
   Schema.String,
@@ -237,7 +253,7 @@ const OpenAIResponsesEvent = Schema.Struct({
       Schema.Struct({
         id: Schema.optional(Schema.String),
         service_tier: optionalNull(Schema.String),
-        incomplete_details: optionalNull(Schema.Struct({ reason: Schema.String })),
+        incomplete_details: optionalNull(Schema.Struct({ reason: Schema.optional(Schema.String) })),
         usage: optionalNull(OpenAIResponsesUsage),
         error: optionalNull(OpenAIResponsesErrorPayload),
       }),
@@ -343,42 +359,58 @@ const hostedToolItemID = (part: ToolResultPart) => {
     : undefined
 }
 
-const lowerUserContent = Effect.fn("OpenAIResponses.lowerUserContent")(function* (
-  part: LLMRequest["messages"][number]["content"][number],
-) {
-  if (part.type === "text") return { type: "input_text" as const, text: part.text }
-  if (part.type === "media") {
-    const media = yield* ProviderShared.validateMedia(
-      "OpenAI Responses",
-      part,
-      new Set<string>(ProviderShared.IMAGE_MIMES),
-    )
-    return { type: "input_image" as const, image_url: media.dataUrl }
+const lowerMedia = Effect.fn("OpenAIResponses.lowerMedia")(function* (part: MediaPart, provider: string) {
+  const media = yield* ProviderShared.validateMedia("OpenAI Responses", part, MEDIA_MIMES)
+  if (media.mime === "application/pdf") {
+    // xAI models inline bytes and MIME separately; OpenAI uses a data URL in file_data.
+    if (provider === "xai")
+      return {
+        type: "input_file" as const,
+        filename: part.filename ?? "document.pdf",
+        file_data: media.base64,
+        mime_type: media.mime,
+      }
+    return {
+      type: "input_file" as const,
+      filename: part.filename ?? "document.pdf",
+      file_data: media.dataUrl,
+    }
   }
-  return yield* ProviderShared.unsupportedContent("OpenAI Responses", "user", ["text", "media"])
-})
-
-// Tool results may carry structured text/images. Keep media as provider-native
-// content instead of JSON-stringifying base64 into a prompt string.
-const lowerToolResultContentItem = Effect.fn("OpenAIResponses.lowerToolResultContentItem")(function* (
-  item: ToolContent,
-) {
-  if (item.type === "text") return { type: "input_text" as const, text: item.text }
-  const media = yield* ProviderShared.validateToolFile(
-    "OpenAI Responses",
-    item,
-    new Set<string>(ProviderShared.IMAGE_MIMES),
-  )
   return { type: "input_image" as const, image_url: media.dataUrl }
 })
 
-const lowerToolResultOutput = Effect.fn("OpenAIResponses.lowerToolResultOutput")(function* (part: ToolResultPart) {
+const lowerUserContent = Effect.fn("OpenAIResponses.lowerUserContent")(function* (
+  part: LLMRequest["messages"][number]["content"][number],
+  provider: string,
+) {
+  if (part.type === "text") return { type: "input_text" as const, text: part.text }
+  if (part.type === "media") return yield* lowerMedia(part, provider)
+  return yield* ProviderShared.unsupportedContent("OpenAI Responses", "user", ["text", "media"])
+})
+
+// Tool results may carry structured text, images, and files. Keep media as provider-native
+// content instead of JSON-stringifying base64 into a prompt string.
+const lowerToolResultContentItem = Effect.fn("OpenAIResponses.lowerToolResultContentItem")(function* (
+  item: ToolContent,
+  provider: string,
+) {
+  if (item.type === "text") return { type: "input_text" as const, text: item.text }
+  return yield* lowerMedia(
+    { type: "media", mediaType: item.mime, data: item.uri, filename: item.name },
+    provider,
+  )
+})
+
+const lowerToolResultOutput = Effect.fn("OpenAIResponses.lowerToolResultOutput")(function* (
+  part: ToolResultPart,
+  provider: string,
+) {
   // Text/json/error results are encoded as a plain string for backward
   // compatibility with existing cassettes and provider expectations.
   if (part.result.type !== "content") return ProviderShared.toolResultText(part)
   // Preserve the narrowed array element type when compiled through a consumer package.
   const content: ReadonlyArray<ToolContent> = part.result.value
-  return yield* Effect.forEach(content, lowerToolResultContentItem)
+  return yield* Effect.forEach(content, (item) => lowerToolResultContentItem(item, provider))
 })
 
 const lowerMessages = Effect.fn("OpenAIResponses.lowerMessages")(function* (request: LLMRequest) {
@@ -401,7 +433,10 @@ const lowerMessages = Effect.fn("OpenAIResponses.lowerMessages")(function* (requ
     }
 
     if (message.role === "user") {
-      input.push({ role: "user", content: yield* Effect.forEach(message.content, lowerUserContent) })
+      input.push({
+        role: "user",
+        content: yield* Effect.forEach(message.content, (part) => lowerUserContent(part, request.model.provider)),
+      })
       continue
     }
 
@@ -460,7 +495,9 @@ const lowerMessages = Effect.fn("OpenAIResponses.lowerMessages")(function* (requ
             const content: ReadonlyArray<ToolContent> = part.result.value
             input.push({
               role: "user",
-              content: yield* Effect.forEach(content, lowerToolResultContentItem),
+              content: yield* Effect.forEach(content, (item) =>
+                lowerToolResultContentItem(item, request.model.provider),
+              ),
             })
           }
           if (itemID) hostedToolReferences.add(itemID)
@@ -483,7 +520,7 @@ const lowerMessages = Effect.fn("OpenAIResponses.lowerMessages")(function* (requ
       input.push({
         type: "function_call_output",
         call_id: part.id,
-        output: yield* lowerToolResultOutput(part),
+        output: yield* lowerToolResultOutput(part, request.model.provider),
       })
     }
   }
@@ -565,7 +602,8 @@ const mapUsage = (usage: OpenAIResponsesUsage | null | undefined) => {
 
 const mapFinishReason = (event: OpenAIResponsesEvent, hasFunctionCall: boolean): FinishReason => {
   const reason = event.response?.incomplete_details?.reason
-  if (reason === undefined || reason === null) return hasFunctionCall ? "tool-calls" : "stop"
+  if (reason === undefined || reason === null)
+    return hasFunctionCall ? "tool-calls" : event.type === "response.incomplete" ? "unknown" : "stop"
   if (reason === "max_output_tokens") return "length"
   if (reason === "content_filter") return "content-filter"
   return hasFunctionCall ? "tool-calls" : "unknown"
@@ -941,7 +979,10 @@ const onOutputItemDone = Effect.fn("OpenAIResponses.onOutputItemDone")(function*
 const onResponseFinish = (state: ParserState, event: OpenAIResponsesEvent): StepResult => {
   const events: LLMEvent[] = []
   const lifecycle = Lifecycle.finish(state.lifecycle, events, {
-    reason: mapFinishReason(event, state.hasFunctionCall),
+    reason: {
+      normalized: mapFinishReason(event, state.hasFunctionCall),
+      raw: event.response?.incomplete_details?.reason,
+    },
     usage: mapUsage(event.response?.usage),
     providerMetadata:
       event.response?.id || event.response?.service_tier

packages/ai/src/protocols/shared.ts

@@ -158,7 +158,8 @@ export const parseToolInput = (route: string, name: string, raw: string) =>
 export const IMAGE_MIMES = ["image/png", "image/jpeg", "image/gif", "image/webp"] as const
 export const VIDEO_MIMES = ["video/mp4", "video/webm", "video/quicktime"] as const
 export const AUDIO_MIMES = ["audio/wav", "audio/mp3", "audio/aiff", "audio/aac", "audio/ogg", "audio/flac"] as const
-export const MEDIA_MIMES = [...IMAGE_MIMES, ...VIDEO_MIMES, ...AUDIO_MIMES] as const
+export const PDF_MIMES = ["application/pdf"] as const
+export const MEDIA_MIMES = [...IMAGE_MIMES, ...VIDEO_MIMES, ...AUDIO_MIMES, ...PDF_MIMES] as const
 export const MAX_MEDIA_ENCODED_BYTES = 28 * 1024 * 1024
 export const MAX_MEDIA_DECODED_BYTES = 20 * 1024 * 1024
 

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

@@ -49,10 +49,10 @@ const DOCUMENT_FORMATS = {
   "text/markdown": "md",
 } as const satisfies Record<string, DocumentFormat>
 
-const documentBlock = (part: MediaPart, format: DocumentFormat, bytes: string): DocumentBlock => ({
+const documentBlock = (name: string, format: DocumentFormat, bytes: string): DocumentBlock => ({
   document: {
     format,
-    name: part.filename ?? `document.${format}`,
+    name,
     source: { bytes },
   },
 })
@@ -77,12 +77,14 @@ export const lower = Effect.fn("BedrockMedia.lower")(function* (part: MediaPart)
     return yield* ProviderShared.invalidRequest(`Bedrock Converse does not support image media type ${part.mediaType}`)
   const documentFormat = DOCUMENT_FORMATS[mime as keyof typeof DOCUMENT_FORMATS]
   if (documentFormat) {
+    if (!part.filename)
+      return yield* ProviderShared.invalidRequest("Bedrock Converse document media requires a filename")
     const media = yield* ProviderShared.validateMedia(
       "Bedrock Converse",
       part,
       new Set<string>(Object.keys(DOCUMENT_FORMATS)),
     )
-    return documentBlock(part, documentFormat, media.base64)
+    return documentBlock(part.filename, documentFormat, media.base64)
   }
   return yield* ProviderShared.invalidRequest(`Bedrock Converse does not support media type ${part.mediaType}`)
 })

packages/ai/src/protocols/utils/lifecycle.ts

@@ -1,4 +1,4 @@
-import { LLMEvent, type FinishReason, type ProviderMetadata, type Usage } from "../../schema"
+import { LLMEvent, type FinishReasonDetails, type ProviderMetadata, type Usage } from "../../schema"
 
 export interface State {
   readonly stepStarted: boolean
@@ -81,7 +81,7 @@ export const finish = (
   state: State,
   events: LLMEvent[],
   input: {
-    readonly reason: FinishReason
+    readonly reason: FinishReasonDetails
     readonly usage?: Usage
     readonly providerMetadata?: ProviderMetadata
   },

packages/ai/src/schema/events.ts

@@ -34,11 +34,12 @@ import { ProviderFailureClassification } from "./errors"
  *
  * **Semantics by provider**:
  *
- * - OpenAI Chat / Responses / Gemini / Bedrock: provider reports inclusive
+ * - OpenAI Chat / Responses / Gemini: provider reports inclusive
  *   `inputTokens` and an inclusive `outputTokens`; mapper subtracts to
  *   derive the breakdown.
- * - Anthropic: provider reports the breakdown natively (`input_tokens` is
- *   non-cached only); mapper sums to derive the inclusive `inputTokens`.
+ * - Anthropic and Bedrock report the input breakdown natively: Anthropic's
+ *   `input_tokens` and Bedrock's `inputTokens` are non-cached only. Their
+ *   mappers sum the breakdown to derive the inclusive `inputTokens`.
  *   Anthropic does *not* break extended-thinking out of `output_tokens`, so
  *   `reasoningTokens` is `undefined` and `outputTokens` carries the
  *   combined total — a documented limitation of the Anthropic API.
@@ -190,10 +191,16 @@ export const ToolError = Schema.Struct({
 }).annotate({ identifier: "LLM.Event.ToolError" })
 export type ToolError = Schema.Schema.Type<typeof ToolError>
 
+export const FinishReasonDetails = Schema.Struct({
+  normalized: FinishReason,
+  raw: Schema.optional(Schema.String),
+}).annotate({ identifier: "LLM.FinishReasonDetails" })
+export type FinishReasonDetails = Schema.Schema.Type<typeof FinishReasonDetails>
+
 export const StepFinish = Schema.Struct({
   type: Schema.tag("step-finish"),
   index: Schema.Number,
-  reason: FinishReason,
+  reason: FinishReasonDetails,
   usage: Schema.optional(Usage),
   providerMetadata: Schema.optional(ProviderMetadata),
 }).annotate({ identifier: "LLM.Event.StepFinish" })
@@ -201,7 +208,7 @@ export type StepFinish = Schema.Schema.Type<typeof StepFinish>
 
 export const Finish = Schema.Struct({
   type: Schema.tag("finish"),
-  reason: FinishReason,
+  reason: FinishReasonDetails,
   usage: Schema.optional(Usage),
   providerMetadata: Schema.optional(ProviderMetadata),
 }).annotate({ identifier: "LLM.Event.Finish" })
@@ -364,7 +371,7 @@ interface ResponseState {
   readonly events: ReadonlyArray<LLMEvent>
   readonly message: Message
   readonly usage?: Usage
-  readonly finishReason?: FinishReason
+  readonly finishReason?: FinishReasonDetails
   readonly textParts: Readonly<Record<string, ContentAssembly>>
   readonly reasoningParts: Readonly<Record<string, ContentAssembly>>
   readonly toolInputs: Readonly<Record<string, ToolInputAssembly>>
@@ -392,7 +399,7 @@ const appendEvent = (state: ResponseState, event: LLMEvent): ResponseState => {
     return {
       ...state,
       events,
-      finishReason: state.finishReason ?? "error",
+      finishReason: state.finishReason ?? { normalized: "error" },
     }
   }
   return {
@@ -579,7 +586,7 @@ export class LLMResponse extends Schema.Class<LLMResponse>("LLM.Response")({
   message: Message,
   events: Schema.Array(LLMEvent),
   usage: Schema.optional(Usage),
-  finishReason: FinishReason,
+  finishReason: FinishReasonDetails,
 }) {
   /** Concatenated assistant text assembled from streamed `text-delta` events. */
   get text() {

packages/ai/src/schema/messages.ts

@@ -261,13 +261,6 @@ export namespace ToolChoice {
   }
 }
 
-export const ResponseFormat = Schema.Union([
-  Schema.Struct({ type: Schema.Literal("text") }),
-  Schema.Struct({ type: Schema.Literal("json"), schema: JsonSchema }),
-  Schema.Struct({ type: Schema.Literal("tool"), tool: ToolDefinition }),
-]).pipe(Schema.toTaggedUnion("type"))
-export type ResponseFormat = Schema.Schema.Type<typeof ResponseFormat>
-
 export class LLMRequest extends Schema.Class<LLMRequest>("LLM.Request")({
   id: Schema.optional(Schema.String),
   model: ModelSchema,
@@ -278,7 +271,6 @@ export class LLMRequest extends Schema.Class<LLMRequest>("LLM.Request")({
   generation: Schema.optional(GenerationOptions),
   providerOptions: Schema.optional(ProviderOptions),
   http: Schema.optional(HttpOptions),
-  responseFormat: Schema.optional(ResponseFormat),
   cache: Schema.optional(CachePolicy),
   metadata: Schema.optional(Schema.Record(Schema.String, Schema.Unknown)),
 }) {}
@@ -296,7 +288,6 @@ export namespace LLMRequest {
     generation: request.generation,
     providerOptions: request.providerOptions,
     http: request.http,
-    responseFormat: request.responseFormat,
     cache: request.cache,
     metadata: request.metadata,
   })

packages/ai/src/schema/options.ts

@@ -168,6 +168,7 @@ export type ModelToolSchemaCompatibility = Schema.Schema.Type<typeof ModelToolSc
 
 export class ModelCompatibility extends Schema.Class<ModelCompatibility>("LLM.ModelCompatibility")({
   toolSchema: Schema.optional(ModelToolSchemaCompatibility),
+  reasoningField: Schema.optional(Schema.String),
 }) {}
 
 export namespace ModelCompatibility {

packages/ai/src/tool-runtime.ts

@@ -68,10 +68,29 @@ const result = (call: ToolCallPart, value: ToolResultValueType | ToolSettlement,
     events:
       settlement.result.type === "error"
         ? [
-            LLMEvent.toolError({ id: call.id, name: call.name, message: String(settlement.result.value), error }),
-            LLMEvent.toolResult({ id: call.id, name: call.name, result: settlement.result }),
+            LLMEvent.toolError({
+              id: call.id,
+              name: call.name,
+              message: String(settlement.result.value),
+              error,
+              providerMetadata: call.providerMetadata,
+            }),
+            LLMEvent.toolResult({
+              id: call.id,
+              name: call.name,
+              result: settlement.result,
+              providerMetadata: call.providerMetadata,
+            }),
           ]
-        : [LLMEvent.toolResult({ id: call.id, name: call.name, result: settlement.result, output: settlement.output })],
+        : [
+            LLMEvent.toolResult({
+              id: call.id,
+              name: call.name,
+              result: settlement.result,
+              output: settlement.output,
+              providerMetadata: call.providerMetadata,
+            }),
+          ],
   }
 }
 

packages/ai/test/adapter.test.ts

@@ -40,7 +40,7 @@ const fakeFraming: FramingDef<FakeEvent> = {
 
 const raiseEvent = (event: FakeEvent): import("../src/schema").LLMEvent =>
   event.type === "finish"
-    ? { type: "finish", reason: event.reason }
+    ? { type: "finish", reason: { normalized: event.reason } }
     : { type: "text-delta", id: "text-0", text: event.text }
 
 const fakeProtocol = Protocol.make<FakeBody, FakeEvent, FakeEvent, void>({

packages/ai/test/fixtures/recordings/pdf/anthropic-tool-result.json

@@ -0,0 +1,35 @@
+{
+  "version": 1,
+  "metadata": {
+    "tags": [
+      "prefix:pdf",
+      "pdf",
+      "provider:anthropic",
+      "protocol:anthropic-messages",
+      "tool",
+      "tool-result"
+    ],
+    "name": "pdf/anthropic-tool-result",
+    "recordedAt": "2026-07-22T18:15:39.002Z"
+  },
+  "interactions": [
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://api.anthropic.com/v1/messages",
+        "headers": {
+          "content-type": "application/json"
+        },
+        "body": "{\"model\":\"claude-haiku-4-5-20251001\",\"system\":[{\"type\":\"text\",\"text\":\"Read the PDF returned by the tool and follow the user's response format exactly.\"}],\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Return only the verification code from the PDF.\"}]},{\"role\":\"assistant\",\"content\":[{\"type\":\"tool_use\",\"id\":\"call_pdf_1\",\"name\":\"read_pdf\",\"input\":{}}]},{\"role\":\"user\",\"content\":[{\"type\":\"tool_result\",\"tool_use_id\":\"call_pdf_1\",\"content\":[{\"type\":\"text\",\"text\":\"PDF read successfully\"},{\"type\":\"document\",\"source\":{\"type\":\"base64\",\"media_type\":\"application/pdf\",\"data\":\"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\"}}]}]}],\"tools\":[{\"name\":\"read_pdf\",\"description\":\"Read the attached PDF.\",\"input_schema\":{\"type\":\"object\",\"properties\":{},\"additionalProperties\":false}}],\"stream\":true,\"max_tokens\":40,\"temperature\":0}"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "text/event-stream; charset=utf-8"
+        },
+        "body": "event: message_start\ndata: {\"type\":\"message_start\",\"message\":{\"model\":\"claude-haiku-4-5-20251001\",\"id\":\"msg_011CdHYzxyRpSVFgwTm6ccUr\",\"type\":\"message\",\"role\":\"assistant\",\"content\":[],\"stop_reason\":null,\"stop_sequence\":null,\"stop_details\":null,\"usage\":{\"input_tokens\":2229,\"cache_creation_input_tokens\":0,\"cache_read_input_tokens\":0,\"cache_creation\":{\"ephemeral_5m_input_tokens\":0,\"ephemeral_1h_input_tokens\":0},\"output_tokens\":2,\"service_tier\":\"standard\",\"inference_geo\":\"not_available\"}}        }\n\nevent: content_block_start\ndata: {\"type\":\"content_block_start\",\"index\":0,\"content_block\":{\"type\":\"text\",\"text\":\"\"}              }\n\nevent: ping\ndata: {\"type\": \"ping\"}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"text_delta\",\"text\":\"ORCH\"}  }\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"text_delta\",\"text\":\"ID-7391\"}           }\n\nevent: content_block_stop\ndata: {\"type\":\"content_block_stop\",\"index\":0               }\n\nevent: message_delta\ndata: {\"type\":\"message_delta\",\"delta\":{\"stop_reason\":\"end_turn\",\"stop_sequence\":null,\"stop_details\":null},\"usage\":{\"input_tokens\":2229,\"cache_creation_input_tokens\":0,\"cache_read_input_tokens\":0,\"output_tokens\":9}       }\n\nevent: message_stop\ndata: {\"type\":\"message_stop\" }\n\n"
+      }
+    }
+  ]
+}

packages/ai/test/fixtures/recordings/pdf/anthropic-user-input.json

@@ -0,0 +1,34 @@
+{
+  "version": 1,
+  "metadata": {
+    "tags": [
+      "prefix:pdf",
+      "pdf",
+      "provider:anthropic",
+      "protocol:anthropic-messages",
+      "user-input"
+    ],
+    "name": "pdf/anthropic-user-input",
+    "recordedAt": "2026-07-22T18:15:37.979Z"
+  },
+  "interactions": [
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://api.anthropic.com/v1/messages",
+        "headers": {
+          "content-type": "application/json"
+        },
+        "body": "{\"model\":\"claude-haiku-4-5-20251001\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"document\",\"source\":{\"type\":\"base64\",\"media_type\":\"application/pdf\",\"data\":\"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\"}},{\"type\":\"text\",\"text\":\"Return only the verification code from the PDF.\"}]}],\"stream\":true,\"max_tokens\":40,\"temperature\":0}"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "text/event-stream; charset=utf-8"
+        },
+        "body": "event: message_start\ndata: {\"type\":\"message_start\",\"message\":{\"model\":\"claude-haiku-4-5-20251001\",\"id\":\"msg_011CdHYzsayb45rgfamcjFt3\",\"type\":\"message\",\"role\":\"assistant\",\"content\":[],\"stop_reason\":null,\"stop_sequence\":null,\"stop_details\":null,\"usage\":{\"input_tokens\":1602,\"cache_creation_input_tokens\":0,\"cache_read_input_tokens\":0,\"cache_creation\":{\"ephemeral_5m_input_tokens\":0,\"ephemeral_1h_input_tokens\":0},\"output_tokens\":2,\"service_tier\":\"standard\",\"inference_geo\":\"not_available\"}}           }\n\nevent: content_block_start\ndata: {\"type\":\"content_block_start\",\"index\":0,\"content_block\":{\"type\":\"text\",\"text\":\"\"}         }\n\nevent: ping\ndata: {\"type\": \"ping\"}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"text_delta\",\"text\":\"ORCH\"}              }\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"text_delta\",\"text\":\"ID-7391\"}}\n\nevent: content_block_stop\ndata: {\"type\":\"content_block_stop\",\"index\":0      }\n\nevent: message_delta\ndata: {\"type\":\"message_delta\",\"delta\":{\"stop_reason\":\"end_turn\",\"stop_sequence\":null,\"stop_details\":null},\"usage\":{\"input_tokens\":1602,\"cache_creation_input_tokens\":0,\"cache_read_input_tokens\":0,\"output_tokens\":9}    }\n\nevent: message_stop\ndata: {\"type\":\"message_stop\"              }\n\n"
+      }
+    }
+  ]
+}

packages/ai/test/fixtures/recordings/pdf/bedrock-tool-result.json

@@ -0,0 +1,36 @@
+{
+  "version": 1,
+  "metadata": {
+    "tags": [
+      "prefix:pdf",
+      "pdf",
+      "provider:amazon-bedrock",
+      "protocol:bedrock-converse",
+      "tool",
+      "tool-result"
+    ],
+    "name": "pdf/bedrock-tool-result",
+    "recordedAt": "2026-07-22T18:15:52.400Z"
+  },
+  "interactions": [
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://bedrock-runtime.us-east-1.amazonaws.com/model/us.anthropic.claude-haiku-4-5-20251001-v1%3A0/converse-stream",
+        "headers": {
+          "content-type": "application/json"
+        },
+        "body": "{\"modelId\":\"us.anthropic.claude-haiku-4-5-20251001-v1:0\",\"messages\":[{\"role\":\"user\",\"content\":[{\"text\":\"Return only the verification code from the PDF.\"}]},{\"role\":\"assistant\",\"content\":[{\"toolUse\":{\"toolUseId\":\"call_pdf_1\",\"name\":\"read_pdf\",\"input\":{}}}]},{\"role\":\"user\",\"content\":[{\"toolResult\":{\"toolUseId\":\"call_pdf_1\",\"content\":[{\"text\":\"PDF read successfully\"},{\"document\":{\"format\":\"pdf\",\"name\":\"verification\",\"source\":{\"bytes\":\"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\"}}}],\"status\":\"success\"}}]}],\"system\":[{\"text\":\"Read the PDF returned by the tool and follow the user's response format exactly.\"}],\"inferenceConfig\":{\"maxTokens\":40,\"temperature\":0},\"toolConfig\":{\"tools\":[{\"toolSpec\":{\"name\":\"read_pdf\",\"description\":\"Read the attached PDF.\",\"inputSchema\":{\"json\":{\"type\":\"object\",\"properties\":{},\"additionalProperties\":false}}}}]}}"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "application/vnd.amazon.eventstream"
+        },
+        "body": "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",
+        "bodyEncoding": "base64"
+      }
+    }
+  ]
+}

packages/ai/test/fixtures/recordings/pdf/bedrock-user-input.json

@@ -0,0 +1,35 @@
+{
+  "version": 1,
+  "metadata": {
+    "tags": [
+      "prefix:pdf",
+      "pdf",
+      "provider:amazon-bedrock",
+      "protocol:bedrock-converse",
+      "user-input"
+    ],
+    "name": "pdf/bedrock-user-input",
+    "recordedAt": "2026-07-22T18:15:48.408Z"
+  },
+  "interactions": [
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://bedrock-runtime.us-east-1.amazonaws.com/model/us.anthropic.claude-haiku-4-5-20251001-v1%3A0/converse-stream",
+        "headers": {
+          "content-type": "application/json"
+        },
+        "body": "{\"modelId\":\"us.anthropic.claude-haiku-4-5-20251001-v1:0\",\"messages\":[{\"role\":\"user\",\"content\":[{\"document\":{\"format\":\"pdf\",\"name\":\"verification\",\"source\":{\"bytes\":\"JVBERi0xLjQKMSAwIG9iago8PCAvVHlwZSAvQ2F0YWxvZyAvUGFnZXMgMiAwIFIgPj4KZW5kb2JqCjIgMCBvYmoKPDwgL1R5cGUgL1BhZ2VzIC9LaWRzIFszIDAgUl0gL0NvdW50IDEgPj4KZW5kb2JqCjMgMCBvYmoKPDwgL1R5cGUgL1BhZ2UgL1BhcmVudCAyIDAgUiAvTWVkaWFCb3ggWzAgMCA2MTIgNzkyXSAvUmVzb3VyY2VzIDw8IC9Gb250IDw8IC9GMSA1IDAgUiA+PiA+PiAvQ29udGVudHMgNCAwIFIgPj4KZW5kb2JqCjQgMCBvYmoKPDwgL0xlbmd0aCA3NSA+PgpzdHJlYW0KQlQKL0YxIDE4IFRmCjcyIDcyMCBUZAooUERGIGNhc3NldHRlIHZlcmlmaWNhdGlvbiBjb2RlOiBPUkNISUQtNzM5MSkgVGoKRVQKZW5kc3RyZWFtCmVuZG9iago1IDAgb2JqCjw8IC9UeXBlIC9Gb250IC9TdWJ0eXBlIC9UeXBlMSAvQmFzZUZvbnQgL0hlbHZldGljYSA+PgplbmRvYmoKeHJlZgowIDYKMDAwMDAwMDAwMCA2NTUzNSBmIAowMDAwMDAwMDA5IDAwMDAwIG4gCjAwMDAwMDAwNTggMDAwMDAgbiAKMDAwMDAwMDExNSAwMDAwMCBuIAowMDAwMDAwMjQxIDAwMDAwIG4gCjAwMDAwMDAzNjUgMDAwMDAgbiAKdHJhaWxlcgo8PCAvU2l6ZSA2IC9Sb290IDEgMCBSID4+CnN0YXJ0eHJlZgo0MzUKJSVFT0YK\"}}},{\"text\":\"Return only the verification code from the PDF.\"}]}],\"inferenceConfig\":{\"maxTokens\":40,\"temperature\":0}}"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "application/vnd.amazon.eventstream"
+        },
+        "body": "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",
+        "bodyEncoding": "base64"
+      }
+    }
+  ]
+}

packages/ai/test/fixtures/recordings/pdf/gemini-tool-result.json

@@ -0,0 +1,53 @@
+{
+  "version": 1,
+  "metadata": {
+    "tags": [
+      "prefix:pdf",
+      "pdf",
+      "provider:google",
+      "protocol:gemini",
+      "tool",
+      "tool-result"
+    ],
+    "name": "pdf/gemini-tool-result",
+    "recordedAt": "2026-07-22T18:21:59.606Z"
+  },
+  "interactions": [
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://generativelanguage.googleapis.com/v1beta/models/gemini-3.5-flash:streamGenerateContent?alt=sse",
+        "headers": {
+          "content-type": "application/json"
+        },
+        "body": "{\"contents\":[{\"role\":\"user\",\"parts\":[{\"text\":\"Use read_pdf with path verification.pdf and return the verification code.\"}]}],\"systemInstruction\":{\"parts\":[{\"text\":\"Call read_pdf exactly once with path verification.pdf, then reply only with the verification code from its PDF.\"}]},\"tools\":[{\"functionDeclarations\":[{\"name\":\"read_pdf\",\"description\":\"Read the attached PDF.\",\"parameters\":{\"required\":[\"path\"],\"type\":\"object\",\"properties\":{\"path\":{\"type\":\"string\"}}}}]}],\"generationConfig\":{\"maxOutputTokens\":256,\"temperature\":0}}"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "text/event-stream"
+        },
+        "body": "data: {\"candidates\": [{\"content\": {\"parts\": [{\"functionCall\": {\"name\": \"read_pdf\",\"args\": {\"path\": \"verification.pdf\"},\"id\": \"58shgmez\"},\"thoughtSignature\": \"EqkCCqYCARFNMg/JrCTv5i3zYENFBVpZNFL3pbzJmi5Eu387ncF703xFMB4pwyaP7a1gi49EqBhCI2hWOpesU5nZQOLAhGgExKGa2GM+HzpEB5g62r0NFblm/BGkVZaImTuHR7bytfRC5jHQlHKo4OS27OLUVjvkMkBIYsvjhDErY7niERbXJVpyxTVqUf1GgZMSu8kC9/5WDlMs9xVKNT/6KMW4PhhSR9nXg4KZUa+bC03/ydhsWWgBa5aLCgvTq7WPj217xIsmUkSiRedIffPsUSNjYdMHUvWi8bOlvM1veEEP6GIfv5h9gXXzjnHbEHfQxV8PZuBAyY7iM6nqyfkJNdkZ1HdB7DXMBsMsRN6SgrIrFoXX2WaGrkoEI5tdZx1t/gdwF1jEVT6k\"}],\"role\": \"model\"},\"index\": 0}],\"usageMetadata\": {\"promptTokenCount\": 81,\"candidatesTokenCount\": 18,\"totalTokenCount\": 151,\"promptTokensDetails\": [{\"modality\": \"TEXT\",\"tokenCount\": 81}],\"thoughtsTokenCount\": 52,\"serviceTier\": \"standard\"},\"modelVersion\": \"gemini-3.5-flash\",\"responseId\": \"RAphaui3OaSHz7IPy8Kb4Ak\"}\r\n\r\ndata: {\"candidates\": [{\"content\": {\"parts\": [{\"text\": \"\"}],\"role\": \"model\"},\"finishReason\": \"STOP\",\"index\": 0}],\"usageMetadata\": {\"promptTokenCount\": 81,\"candidatesTokenCount\": 18,\"totalTokenCount\": 151,\"promptTokensDetails\": [{\"modality\": \"TEXT\",\"tokenCount\": 81}],\"thoughtsTokenCount\": 52,\"serviceTier\": \"standard\"},\"modelVersion\": \"gemini-3.5-flash\",\"responseId\": \"RAphaui3OaSHz7IPy8Kb4Ak\"}\r\n\r\n"
+      }
+    },
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://generativelanguage.googleapis.com/v1beta/models/gemini-3.5-flash:streamGenerateContent?alt=sse",
+        "headers": {
+          "content-type": "application/json"
+        },
+        "body": "{\"contents\":[{\"role\":\"user\",\"parts\":[{\"text\":\"Use read_pdf with path verification.pdf and return the verification code.\"}]},{\"role\":\"model\",\"parts\":[{\"functionCall\":{\"id\":\"58shgmez\",\"name\":\"read_pdf\",\"args\":{\"path\":\"verification.pdf\"}},\"thoughtSignature\":\"EqkCCqYCARFNMg/JrCTv5i3zYENFBVpZNFL3pbzJmi5Eu387ncF703xFMB4pwyaP7a1gi49EqBhCI2hWOpesU5nZQOLAhGgExKGa2GM+HzpEB5g62r0NFblm/BGkVZaImTuHR7bytfRC5jHQlHKo4OS27OLUVjvkMkBIYsvjhDErY7niERbXJVpyxTVqUf1GgZMSu8kC9/5WDlMs9xVKNT/6KMW4PhhSR9nXg4KZUa+bC03/ydhsWWgBa5aLCgvTq7WPj217xIsmUkSiRedIffPsUSNjYdMHUvWi8bOlvM1veEEP6GIfv5h9gXXzjnHbEHfQxV8PZuBAyY7iM6nqyfkJNdkZ1HdB7DXMBsMsRN6SgrIrFoXX2WaGrkoEI5tdZx1t/gdwF1jEVT6k\"}]},{\"role\":\"user\",\"parts\":[{\"functionResponse\":{\"id\":\"58shgmez\",\"name\":\"read_pdf\",\"response\":{\"name\":\"read_pdf\",\"content\":\"PDF read successfully\"},\"parts\":[{\"inlineData\":{\"mimeType\":\"application/pdf\",\"data\":\"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\"}}]}}]}],\"systemInstruction\":{\"parts\":[{\"text\":\"Call read_pdf exactly once with path verification.pdf, then reply only with the verification code from its PDF.\"}]},\"tools\":[{\"functionDeclarations\":[{\"name\":\"read_pdf\",\"description\":\"Read the attached PDF.\",\"parameters\":{\"required\":[\"path\"],\"type\":\"object\",\"properties\":{\"path\":{\"type\":\"string\"}}}}]}],\"generationConfig\":{\"maxOutputTokens\":256,\"temperature\":0}}"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "text/event-stream"
+        },
+        "body": "data: {\"candidates\": [{\"content\": {\"parts\": [{\"text\": \"ORCHID-7391\"}],\"role\": \"model\"},\"index\": 0}],\"usageMetadata\": {\"promptTokenCount\": 123,\"candidatesTokenCount\": 8,\"totalTokenCount\": 184,\"promptTokensDetails\": [{\"modality\": \"TEXT\",\"tokenCount\": 123}],\"thoughtsTokenCount\": 53,\"serviceTier\": \"standard\"},\"modelVersion\": \"gemini-3.5-flash\",\"responseId\": \"RgphaoL6CMjQz7IPjOnEmQI\"}\r\n\r\ndata: {\"candidates\": [{\"content\": {\"parts\": [{\"text\": \"\",\"thoughtSignature\": \"EqECCp4CARFNMg9obBl8O6iU9lawUIWiE+1vztZm9NtaT9FuyJz343hd9ruz+xPco4Q1DY1GF81ZiSI2ElBkt8Wfwsqtix9LNGSMvbZhhk/ZnB54t05M/Dft1kujcMvEdZUWUI/jWaJ349tO1bKVH9MacG5+gl0n4y8DwyQZSV3xIcet547drSkcA/TM03RB+yj1/dcLHsvUjmv9EnO897vZgO2Dk4tbZ2NyCtOeQ3JKVhUTLg2pjkGk+POCNiOdESWiUzxdQKw9LiV6nnzi071tXNiMeVimq6d7xAzRVNapI2uXynvn9Uk3eyn85purOFa8cKriK9oD6vcyGMqgd9+gu2m3to0IHqd7o+2YSr1m5qV1xT1R2/WRQEtb1b1AuOAU6w==\"}],\"role\": \"model\"},\"finishReason\": \"STOP\",\"index\": 0}],\"usageMetadata\": {\"promptTokenCount\": 1277,\"candidatesTokenCount\": 8,\"totalTokenCount\": 1338,\"promptTokensDetails\": [{\"modality\": \"IMAGE\",\"tokenCount\": 1102},{\"modality\": \"TEXT\",\"tokenCount\": 175}],\"thoughtsTokenCount\": 53,\"serviceTier\": \"standard\"},\"modelVersion\": \"gemini-3.5-flash\",\"responseId\": \"RgphaoL6CMjQz7IPjOnEmQI\"}\r\n\r\n"
+      }
+    }
+  ]
+}

packages/ai/test/fixtures/recordings/pdf/gemini-user-input.json

@@ -0,0 +1,34 @@
+{
+  "version": 1,
+  "metadata": {
+    "tags": [
+      "prefix:pdf",
+      "pdf",
+      "provider:google",
+      "protocol:gemini",
+      "user-input"
+    ],
+    "name": "pdf/gemini-user-input",
+    "recordedAt": "2026-07-22T18:20:55.140Z"
+  },
+  "interactions": [
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://generativelanguage.googleapis.com/v1beta/models/gemini-3.5-flash:streamGenerateContent?alt=sse",
+        "headers": {
+          "content-type": "application/json"
+        },
+        "body": "{\"contents\":[{\"role\":\"user\",\"parts\":[{\"inlineData\":{\"mimeType\":\"application/pdf\",\"data\":\"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\"}},{\"text\":\"Return only the verification code from the PDF.\"}]}],\"generationConfig\":{\"maxOutputTokens\":256,\"temperature\":0}}"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "text/event-stream"
+        },
+        "body": "data: {\"candidates\": [{\"content\": {\"parts\": [{\"text\": \"ORCH\"}],\"role\": \"model\"},\"index\": 0}],\"usageMetadata\": {\"promptTokenCount\": 10,\"candidatesTokenCount\": 2,\"totalTokenCount\": 127,\"promptTokensDetails\": [{\"modality\": \"TEXT\",\"tokenCount\": 10}],\"thoughtsTokenCount\": 115,\"serviceTier\": \"standard\"},\"modelVersion\": \"gemini-3.5-flash\",\"responseId\": \"BQpharW2KaPgz7IP6uSLiAw\"}\r\n\r\ndata: {\"candidates\": [{\"content\": {\"parts\": [{\"text\": \"ID-7391\"}],\"role\": \"model\"},\"index\": 0}],\"usageMetadata\": {\"promptTokenCount\": 10,\"candidatesTokenCount\": 8,\"totalTokenCount\": 133,\"promptTokensDetails\": [{\"modality\": \"TEXT\",\"tokenCount\": 10}],\"thoughtsTokenCount\": 115,\"serviceTier\": \"standard\"},\"modelVersion\": \"gemini-3.5-flash\",\"responseId\": \"BQpharW2KaPgz7IP6uSLiAw\"}\r\n\r\ndata: {\"candidates\": [{\"content\": {\"parts\": [{\"text\": \"\",\"thoughtSignature\": \"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\"}],\"role\": \"model\"},\"finishReason\": \"STOP\",\"index\": 0}],\"usageMetadata\": {\"promptTokenCount\": 530,\"candidatesTokenCount\": 8,\"totalTokenCount\": 653,\"promptTokensDetails\": [{\"modality\": \"IMAGE\",\"tokenCount\": 520},{\"modality\": \"TEXT\",\"tokenCount\": 10}],\"thoughtsTokenCount\": 115,\"serviceTier\": \"standard\"},\"modelVersion\": \"gemini-3.5-flash\",\"responseId\": \"BQpharW2KaPgz7IP6uSLiAw\"}\r\n\r\n"
+      }
+    }
+  ]
+}

packages/ai/test/lib/tool-runtime.ts

@@ -59,7 +59,12 @@ export const runTools = <T extends Tools>(options: RunOptions<T>) =>
             ...request.messages,
             Message.assistant(state.assistantContent),
             ...dispatched.map(([call, dispatched]) =>
-              Message.tool({ id: call.id, name: call.name, result: dispatched.result }),
+              Message.tool({
+                id: call.id,
+                name: call.name,
+                result: dispatched.result,
+                providerMetadata: call.providerMetadata,
+              }),
             ),
           ],
         })
@@ -78,7 +83,7 @@ const indexStep = (event: LLMEvent, index: number): LLMEvent => {
 const stepState = (events: ReadonlyArray<LLMEvent>) => {
   const assistantContent: ContentPart[] = []
   const toolCalls: ToolCallPart[] = []
-  let reason: Extract<LLMEvent, { type: "finish" }>["reason"] = "unknown"
+  let reason: Extract<LLMEvent, { type: "finish" }>["reason"] = { normalized: "unknown" }
   let usage: Usage | undefined
   let providerMetadata: ProviderMetadata | undefined
 

packages/ai/test/llm.test.ts

@@ -191,7 +191,7 @@ describe("llm constructors", () => {
       LLMResponse.text({
         events: [
           { type: "text-delta", id: "text-0", text: "hi" },
-          { type: "finish", reason: "stop" },
+          { type: "finish", reason: { normalized: "stop" } },
         ],
       }),
     ).toBe("hi")

packages/ai/test/provider/anthropic-messages.test.ts

@@ -235,9 +235,37 @@ describe("Anthropic Messages route", () => {
     }),
   )
 
-  // Regression: screenshot/read tool results must stay structured so base64
-  // image data is not JSON-stringified into `tool_result.content`.
-  it.effect("lowers image tool-result content as structured image blocks", () =>
+  it.effect("keeps tools and sends tool_choice none", () =>
+    Effect.gen(function* () {
+      const prepared = yield* LLMClient.prepare<AnthropicMessages.AnthropicMessagesBody>(
+        LLM.request({
+          id: "req_tool_choice_none",
+          model,
+          tools: [{ name: "lookup", description: "Look things up", inputSchema: { type: "object", properties: {} } }],
+          messages: [
+            Message.user("What is the weather?"),
+            Message.assistant([ToolCallPart.make({ id: "call_1", name: "lookup", input: { query: "weather" } })]),
+            Message.tool({ id: "call_1", name: "lookup", result: { forecast: "sunny" } }),
+          ],
+          toolChoice: "none",
+          cache: "none",
+        }),
+      )
+
+      expect(prepared.body.tools).toEqual([
+        {
+          name: "lookup",
+          description: "Look things up",
+          input_schema: { type: "object", properties: {} },
+        },
+      ])
+      expect(prepared.body.tool_choice).toEqual({ type: "none" })
+    }),
+  )
+
+  // Regression: read tool results must stay structured so base64 media data is
+  // not JSON-stringified into `tool_result.content`.
+  it.effect("lowers media tool-result content as structured blocks", () =>
     Effect.gen(function* () {
       const prepared = yield* LLMClient.prepare<AnthropicMessages.AnthropicMessagesBody>(
         LLM.request({
@@ -253,6 +281,7 @@ describe("Anthropic Messages route", () => {
               result: [
                 { type: "text", text: "Image read successfully" },
                 { type: "file", uri: "data:image/png;base64,AAECAw==", mime: "image/png" },
+                { type: "file", uri: "data:application/pdf;base64,JVBERi0xLjQ=", mime: "application/pdf" },
               ],
             }),
           ],
@@ -263,6 +292,7 @@ describe("Anthropic Messages route", () => {
       expect(expectToolResult(prepared.body).content).toEqual([
         { type: "text", text: "Image read successfully" },
         { type: "image", source: { type: "base64", media_type: "image/png", data: "AAECAw==" } },
+        { type: "document", source: { type: "base64", media_type: "application/pdf", data: "JVBERi0xLjQ=" } },
       ])
     }),
   )
@@ -292,7 +322,7 @@ describe("Anthropic Messages route", () => {
     }),
   )
 
-  it.effect("rejects non-image media in tool-result content with a clear error", () =>
+  it.effect("rejects unsupported media in tool-result content with a clear error", () =>
     Effect.gen(function* () {
       const error = yield* LLMClient.prepare(
         LLM.request({
@@ -418,12 +448,50 @@ describe("Anthropic Messages route", () => {
       ])
       expect(response.events.at(-1)).toMatchObject({
         type: "finish",
-        reason: "stop",
+        reason: { normalized: "stop", raw: "end_turn" },
         providerMetadata: { anthropic: { stopSequence: "\n\nHuman:" } },
       })
     }),
   )
 
+  it.effect("maps context-window truncation to length", () =>
+    Effect.gen(function* () {
+      const response = yield* LLMClient.generate(request).pipe(
+        Effect.provide(
+          fixedResponse(
+            sseEvents(
+              { type: "message_start", message: { usage: { input_tokens: 5 } } },
+              {
+                type: "message_delta",
+                delta: { stop_reason: "model_context_window_exceeded" },
+                usage: { output_tokens: 1 },
+              },
+            ),
+          ),
+        ),
+      )
+
+      expect(response.finishReason).toEqual({ normalized: "length", raw: "model_context_window_exceeded" })
+    }),
+  )
+
+  it.effect("preserves pause_turn while normalizing it to stop", () =>
+    Effect.gen(function* () {
+      const response = yield* LLMClient.generate(request).pipe(
+        Effect.provide(
+          fixedResponse(
+            sseEvents(
+              { type: "message_start", message: { usage: { input_tokens: 5 } } },
+              { type: "message_delta", delta: { stop_reason: "pause_turn" }, usage: { output_tokens: 1 } },
+            ),
+          ),
+        ),
+      )
+
+      expect(response.finishReason).toEqual({ normalized: "stop", raw: "pause_turn" })
+    }),
+  )
+
   it.effect("assembles streamed tool call input", () =>
     Effect.gen(function* () {
       const body = sseEvents(
@@ -473,10 +541,16 @@ describe("Anthropic Messages route", () => {
           providerExecuted: undefined,
           providerMetadata: undefined,
         },
-        { type: "step-finish", index: 0, reason: "tool-calls", usage, providerMetadata: undefined },
+        {
+          type: "step-finish",
+          index: 0,
+          reason: { normalized: "tool-calls", raw: "tool_use" },
+          usage,
+          providerMetadata: undefined,
+        },
         {
           type: "finish",
-          reason: "tool-calls",
+          reason: { normalized: "tool-calls", raw: "tool_use" },
           providerMetadata: undefined,
           usage,
         },
@@ -634,10 +708,20 @@ describe("Anthropic Messages route", () => {
         name: "web_search",
         result: { type: "json", value: [{ type: "web_search_result", url: "https://example.com", title: "Example" }] },
         providerExecuted: true,
-        providerMetadata: { anthropic: { blockType: "web_search_tool_result" } },
+        // The complete payload rides in provider metadata as irreducible replay
+        // state for later stateless requests.
+        providerMetadata: {
+          anthropic: {
+            blockType: "web_search_tool_result",
+            result: [{ type: "web_search_result", url: "https://example.com", title: "Example" }],
+          },
+        },
       })
       expect(response.text).toBe("Found it.")
-      expect(response.events.at(-1)).toMatchObject({ type: "finish", reason: "stop" })
+      expect(response.events.at(-1)).toMatchObject({
+        type: "finish",
+        reason: { normalized: "stop", raw: "end_turn" },
+      })
     }),
   )
 
@@ -756,7 +840,7 @@ describe("Anthropic Messages route", () => {
     }),
   )
 
-  it.effect("continues a conversation with user image content", () =>
+  it.effect("continues a conversation with user media content", () =>
     Effect.gen(function* () {
       const response = yield* LLMClient.generate(
         LLM.request({
@@ -766,6 +850,7 @@ describe("Anthropic Messages route", () => {
             Message.user([
               { type: "text", text: "What is in this image?" },
               { type: "media", mediaType: "image/png", data: "AAECAw==" },
+              { type: "media", mediaType: "application/pdf", data: "JVBERi0xLjQ=", filename: "report.pdf" },
             ]),
           ],
         }),
@@ -781,6 +866,7 @@ describe("Anthropic Messages route", () => {
                     content: [
                       { type: "text", text: "What is in this image?" },
                       { type: "image", source: { type: "base64", media_type: "image/png", data: "AAECAw==" } },
+                      { type: "document", source: { type: "base64", media_type: "application/pdf", data: "JVBERi0xLjQ=" } },
                     ],
                   },
                 ],

packages/ai/test/provider/bedrock-converse-cache.recorded.test.ts

@@ -13,12 +13,8 @@ const RECORDING_REGION = process.env.BEDROCK_RECORDING_REGION ?? "us-east-1"
 // call wouldn't deterministically prove cache mapping works. Override with
 // BEDROCK_CACHE_MODEL_ID if your account has access elsewhere.
 const model = AmazonBedrock.configure({
-  credentials: {
-    region: RECORDING_REGION,
-    accessKeyId: process.env.AWS_ACCESS_KEY_ID ?? "fixture",
-    secretAccessKey: process.env.AWS_SECRET_ACCESS_KEY ?? "fixture",
-    sessionToken: process.env.AWS_SESSION_TOKEN,
-  },
+  apiKey: process.env.AWS_BEARER_TOKEN_BEDROCK ?? "fixture",
+  region: RECORDING_REGION,
 }).model(process.env.BEDROCK_CACHE_MODEL_ID ?? "us.anthropic.claude-haiku-4-5-20251001-v1:0")
 
 const cacheRequest = LLM.request({
@@ -36,7 +32,7 @@ const recorded = recordedTests({
   prefix: "bedrock-converse-cache",
   provider: "amazon-bedrock",
   protocol: "bedrock-converse",
-  requires: ["AWS_ACCESS_KEY_ID", "AWS_SECRET_ACCESS_KEY"],
+  requires: ["AWS_BEARER_TOKEN_BEDROCK"],
   // Two identical requests in one cassette — replay walks the cassette in
   // recording order so the second call replays the cached-hit interaction.
 })
@@ -45,10 +41,20 @@ describe("Bedrock Converse cache recorded", () => {
   recorded.effect.with("writes then reads cachePoint on identical second call", { tags: ["cache"] }, () =>
     Effect.gen(function* () {
       const first = yield* LLMClient.generate(cacheRequest)
-      expect(first.usage?.cacheReadInputTokens ?? 0).toBeGreaterThanOrEqual(0)
+      expect(first.usage?.cacheWriteInputTokens ?? 0).toBeGreaterThan(0)
+      expect(first.usage?.inputTokens).toBe(
+        (first.usage?.nonCachedInputTokens ?? 0) +
+          (first.usage?.cacheReadInputTokens ?? 0) +
+          (first.usage?.cacheWriteInputTokens ?? 0),
+      )
 
       const second = yield* LLMClient.generate(cacheRequest)
       expect(second.usage?.cacheReadInputTokens ?? 0).toBeGreaterThan(0)
+      expect(second.usage?.inputTokens).toBe(
+        (second.usage?.nonCachedInputTokens ?? 0) +
+          (second.usage?.cacheReadInputTokens ?? 0) +
+          (second.usage?.cacheWriteInputTokens ?? 0),
+      )
     }),
   )
 })

packages/ai/test/provider/bedrock-converse.test.ts

@@ -154,6 +154,36 @@ describe("Bedrock Converse route", () => {
     }),
   )
 
+  it.effect("keeps tools and omits the unsupported choice when tool choice is none", () =>
+    Effect.gen(function* () {
+      const prepared = yield* LLMClient.prepare(
+        LLM.updateRequest(baseRequest, {
+          tools: [
+            {
+              name: "lookup",
+              description: "Lookup data",
+              inputSchema: { type: "object", properties: { query: { type: "string" } } },
+            },
+          ],
+          toolChoice: ToolChoice.make({ type: "none" }),
+        }),
+      )
+
+      expect(prepared.body.toolConfig).toMatchObject({
+        tools: [
+          {
+            toolSpec: {
+              name: "lookup",
+              description: "Lookup data",
+              inputSchema: { json: { type: "object", properties: { query: { type: "string" } } } },
+            },
+          },
+        ],
+      })
+      expect(prepared.body.toolConfig?.toolChoice).toBeUndefined()
+    }),
+  )
+
   it.effect("lowers assistant tool-call + tool-result message history", () =>
     Effect.gen(function* () {
       const prepared = yield* LLMClient.prepare(
@@ -260,7 +290,10 @@ describe("Bedrock Converse route", () => {
       // `metadata` (carries usage). We consolidate them into a single
       // terminal `finish` event with both.
       expect(finishes).toHaveLength(1)
-      expect(finishes[0]).toMatchObject({ type: "finish", reason: "stop" })
+      expect(finishes[0]).toMatchObject({
+        type: "finish",
+        reason: { normalized: "stop", raw: "end_turn" },
+      })
       expect(response.usage).toMatchObject({
         inputTokens: 5,
         outputTokens: 2,
@@ -269,6 +302,56 @@ describe("Bedrock Converse route", () => {
     }),
   )
 
+  it.effect("maps truncation and malformed output stop reasons", () =>
+    Effect.gen(function* () {
+      const reasons = [
+        ["model_context_window_exceeded", "length"],
+        ["malformed_model_output", "error"],
+        ["malformed_tool_use", "error"],
+      ] as const
+
+      for (const [raw, normalized] of reasons) {
+        const response = yield* LLMClient.generate(baseRequest).pipe(
+          Effect.provide(fixedBytes(eventStreamBody(["messageStop", { stopReason: raw }]))),
+        )
+        expect(response.finishReason).toEqual({ normalized, raw })
+      }
+    }),
+  )
+
+  it.effect("adds cache reads and writes to Bedrock input usage", () =>
+    Effect.gen(function* () {
+      const body = eventStreamBody(
+        ["messageStart", { role: "assistant" }],
+        ["contentBlockDelta", { contentBlockIndex: 0, delta: { text: "Hello" } }],
+        ["contentBlockStop", { contentBlockIndex: 0 }],
+        ["messageStop", { stopReason: "end_turn" }],
+        [
+          "metadata",
+          {
+            usage: {
+              inputTokens: 5,
+              outputTokens: 2,
+              totalTokens: 12,
+              cacheReadInputTokens: 3,
+              cacheWriteInputTokens: 2,
+            },
+          },
+        ],
+      )
+      const response = yield* LLMClient.generate(baseRequest).pipe(Effect.provide(fixedBytes(body)))
+
+      expect(response.usage).toMatchObject({
+        inputTokens: 10,
+        nonCachedInputTokens: 5,
+        cacheReadInputTokens: 3,
+        cacheWriteInputTokens: 2,
+        outputTokens: 2,
+        totalTokens: 12,
+      })
+    }),
+  )
+
   it.effect("assembles streamed tool call input", () =>
     Effect.gen(function* () {
       const body = eventStreamBody(
@@ -299,7 +382,10 @@ describe("Bedrock Converse route", () => {
         { type: "tool-input-delta", id: "tool_1", name: "lookup", text: '{"query"' },
         { type: "tool-input-delta", id: "tool_1", name: "lookup", text: ':"weather"}' },
       ])
-      expect(response.events.at(-1)).toMatchObject({ type: "finish", reason: "tool-calls" })
+      expect(response.events.at(-1)).toMatchObject({
+        type: "finish",
+        reason: { normalized: "tool-calls", raw: "tool_use" },
+      })
     }),
   )
 
@@ -325,7 +411,7 @@ describe("Bedrock Converse route", () => {
         name: "lookup",
         raw: '{"query":"partial',
       })
-      expect(response.finishReason).toBe("tool-calls")
+      expect(response.finishReason).toEqual({ normalized: "tool-calls", raw: "end_turn" })
     }),
   )
 
@@ -549,10 +635,12 @@ describe("Bedrock Converse route", () => {
         LLM.request({
           id: "req_doc",
           model,
+          cache: "none",
           messages: [
             Message.user([
+              { type: "text", text: "Summarize these documents." },
               { type: "media", mediaType: "application/pdf", data: "UERGREFUQQ==", filename: "report.pdf" },
-              { type: "media", mediaType: "text/csv", data: "Q1NWREFUQQ==" },
+              { type: "media", mediaType: "text/csv", data: "Q1NWREFUQQ==", filename: "data.csv" },
             ]),
           ],
         }),
@@ -563,10 +651,9 @@ describe("Bedrock Converse route", () => {
           {
             role: "user",
             content: [
-              // Filename round-trips when supplied.
+              { text: "Summarize these documents." },
               { document: { format: "pdf", name: "report.pdf", source: { bytes: "UERGREFUQQ==" } } },
-              // Falls back to a stable placeholder when filename is missing.
-              { document: { format: "csv", name: "document.csv", source: { bytes: "Q1NWREFUQQ==" } } },
+              { document: { format: "csv", name: "data.csv", source: { bytes: "Q1NWREFUQQ==" } } },
             ],
           },
         ],
@@ -574,6 +661,96 @@ describe("Bedrock Converse route", () => {
     }),
   )
 
+  it.effect("requires names for document media", () =>
+    Effect.gen(function* () {
+      const error = yield* LLMClient.prepare(
+        LLM.request({
+          model,
+          messages: [Message.user({ type: "media", mediaType: "application/pdf", data: "UERGREFUQQ==" })],
+        }),
+      ).pipe(Effect.flip)
+
+      expect(error.message).toContain("document media requires a filename")
+    }),
+  )
+
+  it.effect("passes named document-only messages through for provider validation", () =>
+    Effect.gen(function* () {
+      const prepared = yield* LLMClient.prepare<BedrockConverse.BedrockConverseBody>(
+        LLM.request({
+          model,
+          cache: "none",
+          messages: [
+            Message.user({
+              type: "media",
+              mediaType: "application/pdf",
+              data: "UERGREFUQQ==",
+              filename: "report.pdf",
+            }),
+          ],
+        }),
+      )
+
+      expect(prepared.body.messages).toEqual([
+        {
+          role: "user",
+          content: [{ document: { format: "pdf", name: "report.pdf", source: { bytes: "UERGREFUQQ==" } } }],
+        },
+      ])
+    }),
+  )
+
+  it.effect("lowers document media in tool results", () =>
+    Effect.gen(function* () {
+      const prepared = yield* LLMClient.prepare<BedrockConverse.BedrockConverseBody>(
+        LLM.request({
+          model,
+          messages: [
+            Message.assistant([ToolCallPart.make({ id: "call_1", name: "read", input: { path: "report.pdf" } })]),
+            Message.tool({
+              id: "call_1",
+              name: "read",
+              result: {
+                type: "content",
+                value: [
+                  { type: "text", text: "Read successfully" },
+                  {
+                    type: "file",
+                    uri: "data:application/pdf;base64,UERGREFUQQ==",
+                    mime: "application/pdf",
+                    name: "report",
+                  },
+                ],
+              },
+            }),
+          ],
+        }),
+      )
+
+      expect(prepared.body.messages).toEqual([
+        {
+          role: "assistant",
+          content: [{ toolUse: { toolUseId: "call_1", name: "read", input: { path: "report.pdf" } } }],
+        },
+        {
+          role: "user",
+          content: [
+            {
+              toolResult: {
+                toolUseId: "call_1",
+                status: "success",
+                content: [
+                  { text: "Read successfully" },
+                  { document: { format: "pdf", name: "report", source: { bytes: "UERGREFUQQ==" } } },
+                ],
+              },
+            },
+          ],
+        },
+      ])
+    }),
+  )
+
   it.effect("rejects unsupported image media types", () =>
     Effect.gen(function* () {
       const error = yield* LLMClient.prepare(

packages/ai/test/provider/gemini.test.ts

@@ -70,6 +70,7 @@ describe("Gemini route", () => {
             Message.user([
               { type: "text", text: "What is in this image?" },
               { type: "media", mediaType: "image/png", data: "AAECAw==" },
+              { type: "media", mediaType: "application/pdf", data: "JVBERi0xLjQ=" },
             ]),
             Message.assistant([ToolCallPart.make({ id: "call_1", name: "lookup", input: { query: "weather" } })]),
             Message.tool({ id: "call_1", name: "lookup", result: { forecast: "sunny" } }),
@@ -81,7 +82,11 @@ describe("Gemini route", () => {
         contents: [
           {
             role: "user",
-            parts: [{ text: "What is in this image?" }, { inlineData: { mimeType: "image/png", data: "AAECAw==" } }],
+            parts: [
+              { text: "What is in this image?" },
+              { inlineData: { mimeType: "image/png", data: "AAECAw==" } },
+              { inlineData: { mimeType: "application/pdf", data: "JVBERi0xLjQ=" } },
+            ],
           },
           {
             role: "model",
@@ -90,7 +95,12 @@ describe("Gemini route", () => {
           {
             role: "user",
             parts: [
-              { functionResponse: { name: "lookup", response: { name: "lookup", content: '{"forecast":"sunny"}' } } },
+              {
+                functionResponse: {
+                  name: "lookup",
+                  response: { name: "lookup", content: '{"forecast":"sunny"}' },
+                },
+              },
             ],
           },
         ],
@@ -110,7 +120,7 @@ describe("Gemini route", () => {
     }),
   )
 
-  it.effect("continues image tool results as inline vision input without base64 text", () =>
+  it.effect("continues media tool results as inline model input without base64 text", () =>
     Effect.gen(function* () {
       const prepared = yield* LLMClient.prepare<Gemini.GeminiBody>(
         LLM.request({
@@ -125,6 +135,7 @@ describe("Gemini route", () => {
                 value: [
                   { type: "text", text: "Image read successfully" },
                   { type: "file", uri: "data:image/png;base64,AAECAw==", mime: "image/png", name: "pixel.png" },
+                  { type: "file", uri: "data:application/pdf;base64,JVBERi0xLjQ=", mime: "application/pdf" },
                 ],
               },
             }),
@@ -141,9 +152,12 @@ describe("Gemini route", () => {
               functionResponse: {
                 name: "read",
                 response: { name: "read", content: "Image read successfully" },
+                parts: [
+                  { inlineData: { mimeType: "image/png", data: "AAECAw==" } },
+                  { inlineData: { mimeType: "application/pdf", data: "JVBERi0xLjQ=" } },
+                ],
               },
             },
-            { inlineData: { mimeType: "image/png", data: "AAECAw==" } },
           ],
         },
       ])
@@ -174,8 +188,13 @@ describe("Gemini route", () => {
         {
           role: "user",
           parts: [
-            { functionResponse: { name: "read", response: { name: "read", content: "" } } },
-            { inlineData: { mimeType: "image/jpeg", data: "/9j/" } },
+            {
+              functionResponse: {
+                name: "read",
+                response: { name: "read", content: "" },
+                parts: [{ inlineData: { mimeType: "image/jpeg", data: "/9j/" } }],
+              },
+            },
           ],
         },
       ])
@@ -214,11 +233,11 @@ describe("Gemini route", () => {
     }),
   )
 
-  it.effect("omits tools when tool choice is none", () =>
+  it.effect("keeps tools and sends function calling mode NONE", () =>
     Effect.gen(function* () {
       const prepared = yield* LLMClient.prepare(
         LLM.request({
-          id: "req_no_tools",
+          id: "req_tool_choice_none",
           model,
           prompt: "Say hello.",
           tools: [{ name: "lookup", description: "Lookup data", inputSchema: { type: "object" } }],
@@ -226,8 +245,10 @@ describe("Gemini route", () => {
         }),
       )
 
-      expect(prepared.body).toEqual({
+      expect(prepared.body).toMatchObject({
         contents: [{ role: "user", parts: [{ text: "Say hello." }] }],
+        tools: [{ functionDeclarations: [{ name: "lookup", description: "Lookup data" }] }],
+        toolConfig: { functionCallingConfig: { mode: "NONE" } },
       })
     }),
   )
@@ -352,10 +373,16 @@ describe("Gemini route", () => {
         { type: "text-delta", id: "text-0", text: "Hello" },
         { type: "text-delta", id: "text-0", text: "!" },
         { type: "text-end", id: "text-0" },
-        { type: "step-finish", index: 0, reason: "stop", usage, providerMetadata: undefined },
+        {
+          type: "step-finish",
+          index: 0,
+          reason: { normalized: "stop", raw: "STOP" },
+          usage,
+          providerMetadata: undefined,
+        },
         {
           type: "finish",
-          reason: "stop",
+          reason: { normalized: "stop", raw: "STOP" },
           usage,
         },
       ])
@@ -372,7 +399,10 @@ describe("Gemini route", () => {
               parts: [
                 { text: "thinking", thought: true },
                 { text: "", thought: true, thoughtSignature: "thought_sig" },
-                { functionCall: { name: "lookup", args: { query: "weather" } }, thoughtSignature: "tool_sig" },
+                {
+                  functionCall: { id: "provider_call", name: "lookup", args: { query: "weather" } },
+                  thoughtSignature: "tool_sig",
+                },
               ],
             },
             finishReason: "STOP",
@@ -398,7 +428,10 @@ describe("Gemini route", () => {
         id: "reasoning-0",
         providerMetadata: { google: { thoughtSignature: "thought_sig" } },
       })
-      expect(toolCall).toMatchObject({ providerMetadata: { google: { thoughtSignature: "tool_sig" } } })
+      expect(toolCall).toMatchObject({
+        id: "tool_0",
+        providerMetadata: { google: { functionCallId: "provider_call", thoughtSignature: "tool_sig" } },
+      })
       expect(response.events.findIndex((event) => event.type === "reasoning-end")).toBeLessThan(
         response.events.findIndex((event) => event.type === "tool-call"),
       )
@@ -416,6 +449,13 @@ describe("Gemini route", () => {
                 providerMetadata: toolCall?.providerMetadata,
               }),
             ]),
+            Message.tool({
+              id: "tool_0",
+              name: "lookup",
+              result: "done",
+              resultType: "text",
+              providerMetadata: toolCall?.providerMetadata,
+            }),
           ],
         }),
       )
@@ -424,7 +464,22 @@ describe("Gemini route", () => {
           role: "model",
           parts: [
             { text: "thinking", thought: true, thoughtSignature: "thought_sig" },
-            { functionCall: { name: "lookup", args: { query: "weather" } }, thoughtSignature: "tool_sig" },
+            {
+              functionCall: { id: "provider_call", name: "lookup", args: { query: "weather" } },
+              thoughtSignature: "tool_sig",
+            },
+          ],
+        },
+        {
+          role: "user",
+          parts: [
+            {
+              functionResponse: {
+                id: "provider_call",
+                name: "lookup",
+                response: { name: "lookup", content: "done" },
+              },
+            },
           ],
         },
       ])
@@ -480,10 +535,16 @@ describe("Gemini route", () => {
           providerExecuted: undefined,
           providerMetadata: undefined,
         },
-        { type: "step-finish", index: 0, reason: "tool-calls", usage, providerMetadata: undefined },
+        {
+          type: "step-finish",
+          index: 0,
+          reason: { normalized: "tool-calls", raw: "STOP" },
+          usage,
+          providerMetadata: undefined,
+        },
         {
           type: "finish",
-          reason: "tool-calls",
+          reason: { normalized: "tool-calls", raw: "STOP" },
           usage,
         },
       ])
@@ -498,7 +559,7 @@ describe("Gemini route", () => {
             content: {
               role: "model",
               parts: [
-                { functionCall: { name: "lookup", args: { query: "weather" } } },
+                { functionCall: { id: "tool_0", name: "lookup", args: { query: "weather" } } },
                 { functionCall: { name: "lookup", args: { query: "news" } } },
               ],
             },
@@ -513,10 +574,19 @@ describe("Gemini route", () => {
       ).pipe(Effect.provide(fixedResponse(body)))
 
       expect(response.toolCalls).toEqual([
-        { type: "tool-call", id: "tool_0", name: "lookup", input: { query: "weather" } },
+        {
+          type: "tool-call",
+          id: "tool_0",
+          name: "lookup",
+          input: { query: "weather" },
+          providerMetadata: { google: { functionCallId: "tool_0" } },
+        },
         { type: "tool-call", id: "tool_1", name: "lookup", input: { query: "news" } },
       ])
-      expect(response.events.at(-1)).toMatchObject({ type: "finish", reason: "tool-calls" })
+      expect(response.events.at(-1)).toMatchObject({
+        type: "finish",
+        reason: { normalized: "tool-calls", raw: "STOP" },
+      })
     }),
   )
 
@@ -536,9 +606,41 @@ describe("Gemini route", () => {
       )
 
       expect(length.events.map((event) => event.type)).toEqual(["step-start", "step-finish", "finish"])
-      expect(length.events.at(-1)).toMatchObject({ type: "finish", reason: "length" })
+      expect(length.events.at(-1)).toMatchObject({
+        type: "finish",
+        reason: { normalized: "length", raw: "MAX_TOKENS" },
+      })
       expect(filtered.events.map((event) => event.type)).toEqual(["step-start", "step-finish", "finish"])
-      expect(filtered.events.at(-1)).toMatchObject({ type: "finish", reason: "content-filter" })
+      expect(filtered.events.at(-1)).toMatchObject({
+        type: "finish",
+        reason: { normalized: "content-filter", raw: "SAFETY" },
+      })
+    }),
+  )
+
+  it.effect("maps current blocking and invalid-output finish reasons", () =>
+    Effect.gen(function* () {
+      const reasons = [
+        ["MODEL_ARMOR", "content-filter"],
+        ["IMAGE_PROHIBITED_CONTENT", "content-filter"],
+        ["IMAGE_RECITATION", "content-filter"],
+        ["LANGUAGE", "content-filter"],
+        ["UNEXPECTED_TOOL_CALL", "error"],
+        ["NO_IMAGE", "error"],
+        ["IMAGE_OTHER", "unknown"],
+        ["TOO_MANY_TOOL_CALLS", "error"],
+        ["MISSING_THOUGHT_SIGNATURE", "error"],
+        ["MALFORMED_RESPONSE", "error"],
+      ] as const
+
+      for (const [raw, normalized] of reasons) {
+        const response = yield* LLMClient.generate(request).pipe(
+          Effect.provide(
+            fixedResponse(sseEvents({ candidates: [{ content: { role: "model", parts: [] }, finishReason: raw }] })),
+          ),
+        )
+        expect(response.finishReason).toEqual({ normalized, raw })
+      }
     }),
   )
 

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

@@ -1,6 +1,6 @@
 import { describe, expect } from "bun:test"
 import { Effect } from "effect"
-import { LLM, LLMEvent, LLMResponse } from "../../src"
+import { LLM, LLMEvent, LLMResponse, Model } from "../../src"
 import { OpenAIChat } from "../../src/protocols/openai-chat"
 import * as OpenAICompatible from "../../src/providers/openai-compatible"
 import * as OpenRouter from "../../src/providers/openrouter"
@@ -11,22 +11,28 @@ import { expectWeatherToolLoop, goldenWeatherToolLoopRequest, runWeatherToolLoop
 const cases = [
   {
     name: "OpenRouter",
-    model: OpenRouter.configure({
-      apiKey: process.env.OPENROUTER_API_KEY ?? "fixture",
-      providerOptions: { openrouter: { reasoning: { max_tokens: 1024 } } },
-    }).model("anthropic/claude-sonnet-4.6"),
+    model: Model.update(
+      OpenRouter.configure({
+        apiKey: process.env.OPENROUTER_API_KEY ?? "fixture",
+        providerOptions: { openrouter: { reasoning: { max_tokens: 1024 } } },
+      }).model("anthropic/claude-sonnet-4.6"),
+      { compatibility: { reasoningField: "reasoning" } },
+    ),
     requires: ["OPENROUTER_API_KEY"],
     cassette: "openrouter-reasoning",
     structured: true,
   },
   {
     name: "Vercel AI Gateway",
-    model: OpenAICompatible.configure({
-      provider: "vercel-ai-gateway",
-      baseURL: "https://ai-gateway.vercel.sh/v1",
-      apiKey: process.env.AI_GATEWAY_API_KEY ?? "fixture",
-      http: { body: { reasoning: { enabled: true, max_tokens: 1024 } } },
-    }).model("anthropic/claude-sonnet-4.6"),
+    model: Model.update(
+      OpenAICompatible.configure({
+        provider: "vercel-ai-gateway",
+        baseURL: "https://ai-gateway.vercel.sh/v1",
+        apiKey: process.env.AI_GATEWAY_API_KEY ?? "fixture",
+        http: { body: { reasoning: { enabled: true, max_tokens: 1024 } } },
+      }).model("anthropic/claude-sonnet-4.6"),
+      { compatibility: { reasoningField: "reasoning" } },
+    ),
     requires: ["AI_GATEWAY_API_KEY"],
     cassette: "vercel-ai-gateway-reasoning",
     structured: true,

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

@@ -92,6 +92,45 @@ describe("OpenAI Chat route", () => {
     }),
   )
 
+  it.effect("writes reasoning to a configured custom field on every assistant message", () =>
+    Effect.gen(function* () {
+      const prepared = yield* LLMClient.prepare<OpenAIChat.OpenAIChatBody>(
+        LLM.request({
+          model: Model.update(model, { compatibility: { reasoningField: "vendor_reasoning" } }),
+          messages: [
+            Message.assistant([
+              {
+                type: "reasoning",
+                text: "thinking",
+                providerMetadata: { openai: { reasoningField: "reasoning" } },
+              },
+              { type: "text", text: "Hello" },
+            ]),
+            Message.assistant("Done"),
+          ],
+        }),
+      )
+
+      expect(prepared.body.messages).toEqual([
+        { role: "assistant", content: "Hello", vendor_reasoning: "thinking" },
+        { role: "assistant", content: "Done", vendor_reasoning: "" },
+      ])
+    }),
+  )
+
+  it.effect("rejects reasoning fields that conflict with assistant message fields", () =>
+    Effect.gen(function* () {
+      const error = yield* LLMClient.prepare(
+        LLM.request({
+          model: Model.update(model, { compatibility: { reasoningField: "content" } }),
+          messages: [Message.assistant([{ type: "reasoning", text: "thinking" }])],
+        }),
+      ).pipe(Effect.flip)
+
+      expect(error.message).toContain("reserved field content")
+    }),
+  )
+
   it.effect("maps OpenAI provider options to Chat options", () =>
     Effect.gen(function* () {
       const prepared = yield* LLMClient.prepare<OpenAIChat.OpenAIChatBody>(
@@ -530,10 +569,16 @@ describe("OpenAI Chat route", () => {
         { type: "text-delta", id: "text-0", text: "Hello" },
         { type: "text-delta", id: "text-0", text: "!" },
         { type: "text-end", id: "text-0" },
-        { type: "step-finish", index: 0, reason: "stop", usage, providerMetadata: undefined },
+        {
+          type: "step-finish",
+          index: 0,
+          reason: { normalized: "stop", raw: "stop" },
+          usage,
+          providerMetadata: undefined,
+        },
         {
           type: "finish",
-          reason: "stop",
+          reason: { normalized: "stop", raw: "stop" },
           usage,
         },
       ])
@@ -570,6 +615,35 @@ describe("OpenAI Chat route", () => {
     }),
   )
 
+  it.effect("parses and replays a configured custom reasoning field", () =>
+    Effect.gen(function* () {
+      const custom = Model.update(model, { compatibility: { reasoningField: "vendor_reasoning" } })
+      const response = yield* LLMClient.generate(LLM.updateRequest(request, { model: custom })).pipe(
+        Effect.provide(
+          fixedResponse(
+            sseEvents(
+              { choices: [{ delta: { vendor_reasoning: "thinking" } }] },
+              { choices: [{ delta: { content: "Hello" } }] },
+              { choices: [{ delta: {}, finish_reason: "stop" }] },
+            ),
+          ),
+        ),
+      )
+
+      expect(response.reasoning).toBe("thinking")
+      expect(response.message.content.find((part) => part.type === "reasoning")?.providerMetadata).toEqual({
+        openai: { reasoningField: "vendor_reasoning" },
+      })
+
+      const replay = yield* LLMClient.prepare<OpenAIChat.OpenAIChatBody>(
+        LLM.request({ model: custom, messages: [response.message] }),
+      )
+      expect(replay.body.messages).toEqual([
+        { role: "assistant", content: "Hello", vendor_reasoning: "thinking" },
+      ])
+    }),
+  )
+
   it.effect("preserves and replays reasoning details alongside scalar reasoning", () =>
     Effect.gen(function* () {
       const details = [
@@ -969,8 +1043,14 @@ describe("OpenAI Chat route", () => {
           providerExecuted: undefined,
           providerMetadata: undefined,
         },
-        { type: "step-finish", index: 0, reason: "tool-calls", usage: undefined, providerMetadata: undefined },
-        { type: "finish", reason: "tool-calls", usage: undefined },
+        {
+          type: "step-finish",
+          index: 0,
+          reason: { normalized: "tool-calls", raw: "tool_calls" },
+          usage: undefined,
+          providerMetadata: undefined,
+        },
+        { type: "finish", reason: { normalized: "tool-calls", raw: "tool_calls" }, usage: undefined },
       ])
     }),
   )

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

@@ -232,7 +232,10 @@ describe("OpenAI-compatible Chat route", () => {
 
       expect(response.text).toBe("Hello!")
       expect(response.usage).toMatchObject({ inputTokens: 5, outputTokens: 2, totalTokens: 7 })
-      expect(response.events.at(-1)).toMatchObject({ type: "finish", reason: "stop" })
+      expect(response.events.at(-1)).toMatchObject({
+        type: "finish",
+        reason: { normalized: "stop", raw: "stop" },
+      })
     }),
   )
 })

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

@@ -5,6 +5,7 @@ import { LLM, LLMError, LLMEvent, Message, Model, ToolCallPart, ToolResultPart,
 import { Auth, LLMClient, RequestExecutor, WebSocketExecutor } from "../../src/route"
 import * as Azure from "../../src/providers/azure"
 import * as OpenAI from "../../src/providers/openai"
+import * as XAI from "../../src/providers/xai"
 import * as OpenAIResponses from "../../src/protocols/openai-responses"
 import * as ProviderShared from "../../src/protocols/shared"
 import { continuationRequest, nativeOpenAIResponsesContinuation } from "../continuation-scenarios"
@@ -16,6 +17,8 @@ const model = OpenAIResponses.route
   .with({ endpoint: { baseURL: "https://api.openai.test/v1/" }, auth: Auth.bearer("test") })
   .model({ id: "gpt-4.1-mini" })
 
+const xaiModel = XAI.configure({ apiKey: "test", baseURL: "https://api.x.ai/v1" }).responses("grok-4.5")
+
 const request = LLM.request({
   id: "req_1",
   model,
@@ -524,7 +527,77 @@ describe("OpenAI Responses route", () => {
     }),
   )
 
-  it.effect("rejects non-image media in tool-result content with a clear error", () =>
+  it.effect("lowers PDF tool-result content as structured input_file array", () =>
+    Effect.gen(function* () {
+      const prepared = yield* LLMClient.prepare<OpenAIResponses.OpenAIResponsesBody>(
+        LLM.request({
+          id: "req_tool_result_pdf",
+          model,
+          messages: [
+            Message.assistant([ToolCallPart.make({ id: "call_1", name: "read", input: {} })]),
+            Message.tool({
+              id: "call_1",
+              name: "read",
+              resultType: "content",
+              result: [
+                {
+                  type: "file",
+                  uri: "data:application/pdf;base64,JVBERi0xLjQ=",
+                  mime: "application/pdf",
+                  name: "report.pdf",
+                },
+              ],
+            }),
+          ],
+        }),
+      )
+
+      expect(expectToolOutput(prepared.body).output).toEqual([
+        {
+          type: "input_file",
+          filename: "report.pdf",
+          file_data: "data:application/pdf;base64,JVBERi0xLjQ=",
+        },
+      ])
+    }),
+  )
+
+  it.effect("uses xAI inline file encoding for PDF tool results", () =>
+    Effect.gen(function* () {
+      const prepared = yield* LLMClient.prepare<OpenAIResponses.OpenAIResponsesBody>(
+        LLM.request({
+          model: xaiModel,
+          messages: [
+            Message.assistant([ToolCallPart.make({ id: "call_1", name: "read", input: {} })]),
+            Message.tool({
+              id: "call_1",
+              name: "read",
+              resultType: "content",
+              result: [
+                {
+                  type: "file",
+                  uri: "data:application/pdf;base64,JVBERi0xLjQ=",
+                  mime: "application/pdf",
+                  name: "report.pdf",
+                },
+              ],
+            }),
+          ],
+        }),
+      )
+
+      expect(expectToolOutput(prepared.body).output).toEqual([
+        {
+          type: "input_file",
+          filename: "report.pdf",
+          file_data: "JVBERi0xLjQ=",
+          mime_type: "application/pdf",
+        },
+      ])
+    }),
+  )
+
+  it.effect("rejects unsupported media in tool-result content with a clear error", () =>
     Effect.gen(function* () {
       const error = yield* LLMClient.prepare(
         LLM.request({
@@ -783,13 +856,13 @@ describe("OpenAI Responses route", () => {
         {
           type: "step-finish",
           index: 0,
-          reason: "stop",
+          reason: { normalized: "stop", raw: undefined },
           providerMetadata: { openai: { responseId: "resp_1", serviceTier: "default" } },
           usage,
         },
         {
           type: "finish",
-          reason: "stop",
+          reason: { normalized: "stop", raw: undefined },
           providerMetadata: { openai: { responseId: "resp_1", serviceTier: "default" } },
           usage,
         },
@@ -797,6 +870,39 @@ describe("OpenAI Responses route", () => {
     }),
   )
 
+  it.effect("maps incomplete response reasons", () =>
+    Effect.gen(function* () {
+      const generate = (incompleteDetails: object) =>
+        LLMClient.generate(request).pipe(
+          Effect.provide(
+            fixedResponse(
+              sseEvents({
+                type: "response.incomplete",
+                response: { id: "resp_incomplete", incomplete_details: incompleteDetails },
+              }),
+            ),
+          ),
+        )
+
+      const length = yield* generate({ reason: "max_output_tokens" })
+      const contentFilter = yield* generate({ reason: "content_filter" })
+      const unknown = yield* generate({})
+      const custom = yield* generate({ reason: "provider_limit" })
+
+      expect([
+        length.finishReason,
+        contentFilter.finishReason,
+        unknown.finishReason,
+        custom.finishReason,
+      ]).toEqual([
+        { normalized: "length", raw: "max_output_tokens" },
+        { normalized: "content-filter", raw: "content_filter" },
+        { normalized: "unknown", raw: undefined },
+        { normalized: "unknown", raw: "provider_limit" },
+      ])
+    }),
+  )
+
   // OpenAI's documented stream orders output text within one message item; no
   // provider-valid same-kind overlap is evidenced, so done boundaries close it.
   it.effect("closes sequential output messages before starting the next", () =>
@@ -847,8 +953,8 @@ describe("OpenAI Responses route", () => {
         { type: "text-delta", id: "msg_1", text: "Hello" },
         { type: "reasoning-end", id: "rs_1" },
         { type: "text-end", id: "msg_1" },
-        { type: "step-finish", index: 0, reason: "stop" },
-        { type: "finish", reason: "stop" },
+        { type: "step-finish", index: 0, reason: { normalized: "stop", raw: undefined } },
+        { type: "finish", reason: { normalized: "stop", raw: undefined } },
       ])
       expect(response.events.filter((event) => event.type === "finish")).toHaveLength(1)
       expect(response.message.content).toEqual([
@@ -939,8 +1045,8 @@ describe("OpenAI Responses route", () => {
           id: "rs_1:1",
           providerMetadata: { openai: { itemId: "rs_1", reasoningEncryptedContent: "encrypted-state" } },
         },
-        { type: "step-finish", index: 0, reason: "stop" },
-        { type: "finish", reason: "stop" },
+        { type: "step-finish", index: 0, reason: { normalized: "stop", raw: undefined } },
+        { type: "finish", reason: { normalized: "stop", raw: undefined } },
       ])
     }),
   )
@@ -1323,10 +1429,16 @@ describe("OpenAI Responses route", () => {
           providerExecuted: undefined,
           providerMetadata: { openai: { itemId: "item_1" } },
         },
-        { type: "step-finish", index: 0, reason: "tool-calls", usage, providerMetadata: undefined },
+        {
+          type: "step-finish",
+          index: 0,
+          reason: { normalized: "tool-calls", raw: undefined },
+          usage,
+          providerMetadata: undefined,
+        },
         {
           type: "finish",
-          reason: "tool-calls",
+          reason: { normalized: "tool-calls", raw: undefined },
           providerMetadata: undefined,
           usage,
         },
@@ -1366,7 +1478,7 @@ describe("OpenAI Responses route", () => {
         name: "lookup",
         raw: '{"query":"partial',
       })
-      expect(response.finishReason).toBe("tool-calls")
+      expect(response.finishReason.normalized).toBe("tool-calls")
       expect(response.events.some(LLMEvent.is.toolCall)).toBeFalse()
     }),
   )
@@ -1393,7 +1505,7 @@ describe("OpenAI Responses route", () => {
         name: "lookup",
         raw: '{"query":"partial',
       })
-      expect(response.finishReason).toBe("tool-calls")
+      expect(response.finishReason.normalized).toBe("tool-calls")
     }),
   )
 
@@ -1526,20 +1638,64 @@ describe("OpenAI Responses route", () => {
     }),
   )
 
-  it.effect("lowers user image content", () =>
+  it.effect("lowers user image and PDF content", () =>
     Effect.gen(function* () {
       const prepared = yield* LLMClient.prepare<OpenAIResponses.OpenAIResponsesBody>(
         LLM.request({
           id: "req_media",
           model,
-          messages: [Message.user({ type: "media", mediaType: "image/png", data: "AAECAw==" })],
+          messages: [
+            Message.user([
+              { type: "media", mediaType: "image/png", data: "AAECAw==" },
+              { type: "media", mediaType: "application/pdf", data: "JVBERi0xLjQ=", filename: "report.pdf" },
+            ]),
+          ],
         }),
       )
 
       expect(prepared.body.input).toEqual([
         {
           role: "user",
-          content: [{ type: "input_image", image_url: "data:image/png;base64,AAECAw==" }],
+          content: [
+            { type: "input_image", image_url: "data:image/png;base64,AAECAw==" },
+            {
+              type: "input_file",
+              filename: "report.pdf",
+              file_data: "data:application/pdf;base64,JVBERi0xLjQ=",
+            },
+          ],
+        },
+      ])
+    }),
+  )
+
+  it.effect("uses xAI inline file encoding for user PDFs", () =>
+    Effect.gen(function* () {
+      const prepared = yield* LLMClient.prepare<OpenAIResponses.OpenAIResponsesBody>(
+        LLM.request({
+          model: xaiModel,
+          messages: [
+            Message.user({
+              type: "media",
+              mediaType: "application/pdf",
+              data: "data:application/pdf;base64,JVBERi0xLjQ=",
+              filename: "report.pdf",
+            }),
+          ],
+        }),
+      )
+
+      expect(prepared.body.input).toEqual([
+        {
+          role: "user",
+          content: [
+            {
+              type: "input_file",
+              filename: "report.pdf",
+              file_data: "JVBERi0xLjQ=",
+              mime_type: "application/pdf",
+            },
+          ],
         },
       ])
     }),
@@ -1551,11 +1707,11 @@ describe("OpenAI Responses route", () => {
         LLM.request({
           id: "req_media",
           model,
-          messages: [Message.user({ type: "media", mediaType: "application/pdf", data: "AAECAw==" })],
+          messages: [Message.user({ type: "media", mediaType: "application/x-tar", data: "AAECAw==" })],
         }),
       ).pipe(Effect.flip)
 
-      expect(error.message).toContain("OpenAI Responses does not support media type application/pdf")
+      expect(error.message).toContain("OpenAI Responses does not support media type application/x-tar")
     }),
   )
 

packages/ai/test/provider/openrouter.test.ts

@@ -4,6 +4,8 @@ import { LLM, Message } from "../../src"
 import { LLMClient } from "../../src/route"
 import * as OpenRouter from "../../src/providers/openrouter"
 import { it } from "../lib/effect"
+import { fixedResponse } from "../lib/http"
+import { sseEvents } from "../lib/sse"
 
 describe("OpenRouter", () => {
   it.effect("prepares OpenRouter models through the OpenAI-compatible Chat route", () =>
@@ -54,6 +56,42 @@ describe("OpenRouter", () => {
     }),
   )
 
+  it.effect("preserves the upstream provider finish reason", () =>
+    Effect.gen(function* () {
+      const model = OpenRouter.configure({ apiKey: "test-key" }).model("anthropic/claude-sonnet-4.6")
+      const response = yield* LLMClient.generate(LLM.request({ model, prompt: "Say hello." })).pipe(
+        Effect.provide(
+          fixedResponse(
+            sseEvents({
+              choices: [{ delta: { content: "Hello" }, finish_reason: "stop", native_finish_reason: "end_turn" }],
+            }),
+          ),
+        ),
+      )
+
+      expect(response.finishReason).toEqual({ normalized: "stop", raw: "end_turn" })
+    }),
+  )
+
+  it.effect("fails on a mid-stream provider error", () =>
+    Effect.gen(function* () {
+      const model = OpenRouter.configure({ apiKey: "test-key" }).model("openai/gpt-4o-mini")
+      const error = yield* LLMClient.generate(LLM.request({ model, prompt: "Say hello." })).pipe(
+        Effect.provide(
+          fixedResponse(
+            sseEvents({
+              error: { code: 502, message: "Provider disconnected" },
+            }),
+          ),
+        ),
+        Effect.flip,
+      )
+
+      expect(error.reason).toMatchObject({ _tag: "ProviderInternal" })
+      expect(error.message).toContain("Provider disconnected")
+    }),
+  )
+
   it.effect("preserves manually supplied reasoning details", () =>
     Effect.gen(function* () {
       const details = [

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

@@ -0,0 +1,207 @@
+import { describe, expect } from "bun:test"
+import { Effect, Schema, Stream } from "effect"
+import { LLM, LLMResponse, Message, ToolDefinition, type Model } from "../../src"
+import { AmazonBedrock, Anthropic, Google, OpenAI, XAI } from "../../src/providers"
+import { LLMClient } from "../../src/route"
+import { Tool } from "../../src/tool"
+import { runTools } from "../lib/tool-runtime"
+import { recordedTests } from "../recorded-test"
+
+const CODE = "ORCHID-7391"
+const PDF =
+  "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"
+
+const openai = OpenAI.configure({ apiKey: process.env.OPENAI_API_KEY ?? "fixture" })
+const anthropic = Anthropic.configure({ apiKey: process.env.ANTHROPIC_API_KEY ?? "fixture" })
+const google = Google.configure({ apiKey: process.env.GOOGLE_API_KEY ?? "fixture" })
+const xai = XAI.configure({ apiKey: process.env.XAI_API_KEY ?? "fixture" })
+const bedrock = AmazonBedrock.configure({
+  apiKey: process.env.AWS_BEDROCK_API_KEY ?? "fixture",
+  region: process.env.AWS_REGION ?? "us-east-1",
+})
+
+const targets: ReadonlyArray<{
+  readonly id: string
+  readonly name: string
+  readonly provider: string
+  readonly protocol: string
+  readonly requires: string
+  readonly filename: string
+  readonly maxTokens: number
+  readonly model: Model
+}> = [
+  {
+    id: "openai",
+    name: "OpenAI Responses gpt-4o-mini",
+    provider: "openai",
+    protocol: "openai-responses",
+    requires: "OPENAI_API_KEY",
+    filename: "verification.pdf",
+    maxTokens: 40,
+    model: openai.responses("gpt-4o-mini"),
+  },
+  {
+    id: "anthropic",
+    name: "Anthropic Haiku 4.5",
+    provider: "anthropic",
+    protocol: "anthropic-messages",
+    requires: "ANTHROPIC_API_KEY",
+    filename: "verification.pdf",
+    maxTokens: 40,
+    model: anthropic.model("claude-haiku-4-5-20251001"),
+  },
+  {
+    id: "gemini",
+    name: "Gemini 3.5 Flash",
+    provider: "google",
+    protocol: "gemini",
+    requires: "GOOGLE_API_KEY",
+    filename: "verification.pdf",
+    maxTokens: 256,
+    model: google.model("gemini-3.5-flash"),
+  },
+  {
+    id: "xai",
+    name: "xAI Grok 4.5",
+    provider: "xai",
+    protocol: "openai-responses",
+    requires: "XAI_API_KEY",
+    filename: "verification.pdf",
+    maxTokens: 40,
+    model: xai.responses("grok-4.5"),
+  },
+  {
+    id: "bedrock",
+    name: "Bedrock Claude Haiku 4.5",
+    provider: "amazon-bedrock",
+    protocol: "bedrock-converse",
+    requires: "AWS_BEDROCK_API_KEY",
+    filename: "verification",
+    maxTokens: 40,
+    model: bedrock.model("us.anthropic.claude-haiku-4-5-20251001-v1:0"),
+  },
+]
+
+const recorded = recordedTests({ prefix: "pdf", tags: ["pdf"] })
+const prompt = "Return only the verification code from the PDF."
+const readPdf = ToolDefinition.make({
+  name: "read_pdf",
+  description: "Read the attached PDF.",
+  inputSchema: { type: "object", properties: {}, additionalProperties: false },
+})
+const readPdfRuntime = Tool.make({
+  description: readPdf.description,
+  parameters: Schema.Struct({ path: Schema.String }),
+  success: Schema.String,
+  execute: () => Effect.succeed("PDF read successfully"),
+  toModelOutput: () => [
+    { type: "text", text: "PDF read successfully" },
+    {
+      type: "file",
+      uri: `data:application/pdf;base64,${PDF}`,
+      mime: "application/pdf",
+      name: "verification.pdf",
+    },
+  ],
+})
+
+const expectCode = (response: LLMResponse) => {
+  expect(response.finishReason.normalized).toBe("stop")
+  expect(response.text.toUpperCase()).toContain(CODE)
+}
+
+describe("PDF recorded", () => {
+  for (const target of targets) {
+    recorded.effect.with(
+      `reads a user PDF with ${target.name}`,
+      {
+        id: `${target.id}-user-input`,
+        provider: target.provider,
+        protocol: target.protocol,
+        requires: [target.requires],
+        tags: ["user-input"],
+      },
+      Effect.gen(function* () {
+        expectCode(
+          yield* LLMClient.generate(
+            LLM.request({
+              id: `recorded_pdf_${target.id}_user_input`,
+              model: target.model,
+              cache: "none",
+              generation: { maxTokens: target.maxTokens, temperature: 0 },
+              messages: [
+                Message.user([
+                  { type: "media", mediaType: "application/pdf", data: PDF, filename: target.filename },
+                  { type: "text", text: prompt },
+                ]),
+              ],
+            }),
+          ),
+        )
+      }),
+    )
+
+    recorded.effect.with(
+      `reads a PDF tool result with ${target.name}`,
+      {
+        id: `${target.id}-tool-result`,
+        provider: target.provider,
+        protocol: target.protocol,
+        requires: [target.requires],
+        tags: ["tool", "tool-result"],
+      },
+      Effect.gen(function* () {
+        if (target.id === "gemini") {
+          const events = Array.from(
+            yield* runTools({
+              request: LLM.request({
+                id: "recorded_pdf_gemini_tool_result",
+                model: target.model,
+                system:
+                  "Call read_pdf exactly once with path verification.pdf, then reply only with the verification code from its PDF.",
+                prompt: "Use read_pdf with path verification.pdf and return the verification code.",
+                cache: "none",
+                generation: { maxTokens: target.maxTokens, temperature: 0 },
+              }),
+              tools: { read_pdf: readPdfRuntime },
+            }).pipe(Stream.runCollect),
+          )
+          expect(events.at(-1)).toMatchObject({ type: "finish", reason: { normalized: "stop" } })
+          expect(LLMResponse.text({ events }).toUpperCase()).toContain(CODE)
+          return
+        }
+
+        expectCode(
+          yield* LLMClient.generate(
+            LLM.request({
+              id: `recorded_pdf_${target.id}_tool_result`,
+              model: target.model,
+              system: "Read the PDF returned by the tool and follow the user's response format exactly.",
+              cache: "none",
+              generation: { maxTokens: target.maxTokens, temperature: 0 },
+              messages: [
+                Message.user(prompt),
+                Message.assistant([{ type: "tool-call", id: "call_pdf_1", name: readPdf.name, input: {} }]),
+                Message.tool({
+                  id: "call_pdf_1",
+                  name: readPdf.name,
+                  resultType: "content",
+                  result: [
+                    { type: "text", text: "PDF read successfully" },
+                    {
+                      type: "file",
+                      uri: `data:application/pdf;base64,${PDF}`,
+                      mime: "application/pdf",
+                      name: target.filename,
+                    },
+                  ],
+                }),
+              ],
+              tools: [readPdf],
+            }),
+          ),
+        )
+      }),
+    )
+  }
+})

packages/ai/test/recorded-scenarios.ts

@@ -125,8 +125,8 @@ const assistantContent = (events: ReadonlyArray<LLMEvent>) =>
 
 export const expectFinish = (
   events: ReadonlyArray<LLMEvent>,
-  reason: Extract<LLMEvent, { readonly type: "finish" }>["reason"],
-) => expect(events.at(-1)).toMatchObject({ type: "finish", reason })
+  reason: FinishReason,
+) => expect(events.at(-1)).toMatchObject({ type: "finish", reason: { normalized: reason } })
 
 export const expectWeatherToolCall = (response: LLMResponse) =>
   expect(response.toolCalls).toMatchObject([
@@ -136,10 +136,10 @@ export const expectWeatherToolCall = (response: LLMResponse) =>
 export const expectWeatherToolLoop = (events: ReadonlyArray<LLMEvent>) => {
   const finishes = events.filter(LLMEvent.is.finish)
   expect(finishes).toHaveLength(1)
-  expect(finishes[0]?.reason).toBe("stop")
+  expect(finishes[0]?.reason.normalized).toBe("stop")
 
   const stepFinishes = events.filter(LLMEvent.is.stepFinish)
-  expect(stepFinishes.map((event) => event.reason)).toEqual(["tool-calls", "stop"])
+  expect(stepFinishes.map((event) => event.reason.normalized)).toEqual(["tool-calls", "stop"])
 
   const toolCalls = events.filter(LLMEvent.is.toolCall)
   expect(toolCalls).toHaveLength(1)
@@ -503,7 +503,7 @@ export const eventSummary = (events: ReadonlyArray<LLMEvent>) => {
       continue
     }
     if (event.type === "finish") {
-      summary.push({ type: "finish", reason: event.reason, usage: usageSummary(event.usage) })
+      summary.push({ type: "finish", reason: event.reason.normalized, usage: usageSummary(event.usage) })
     }
   }
   return summary.map((item) => Object.fromEntries(Object.entries(item).filter((entry) => entry[1] !== undefined)))

packages/ai/test/response.test.ts

@@ -14,11 +14,11 @@ describe("LLMResponse reducer", () => {
       LLMEvent.reasoningEnd({ id: "r1", providerMetadata: { anthropic: { signature: "sig" } } }),
       LLMEvent.textDelta({ id: "t1", text: "Answer" }),
       LLMEvent.textEnd({ id: "t1" }),
-      LLMEvent.finish({ reason: "stop", usage: { outputTokens: 5 } }),
+      LLMEvent.finish({ reason: { normalized: "stop" }, usage: { outputTokens: 5 } }),
     ]
     const response = LLMResponse.fromEvents(events)
 
-    expect(response?.finishReason).toBe("stop")
+    expect(response?.finishReason).toEqual({ normalized: "stop" })
     expect(response?.usage).toMatchObject({ outputTokens: 5 })
     expect(response?.events).toEqual(events)
     expect(response?.events.map((event) => event.type)).toEqual([
@@ -62,18 +62,26 @@ describe("LLMResponse reducer", () => {
 
   test("uses terminal usage when present and keeps prior usage when finish omits it", () => {
     const withFinishUsage = LLMResponse.fromEvents([
-      LLMEvent.stepFinish({ index: 0, reason: "stop", usage: { inputTokens: 3 } }),
-      LLMEvent.finish({ reason: "stop", usage: { outputTokens: 2 } }),
+      LLMEvent.stepFinish({ index: 0, reason: { normalized: "stop" }, usage: { inputTokens: 3 } }),
+      LLMEvent.finish({ reason: { normalized: "stop" }, usage: { outputTokens: 2 } }),
     ])
     const withoutFinishUsage = LLMResponse.fromEvents([
-      LLMEvent.stepFinish({ index: 0, reason: "stop", usage: { inputTokens: 3 } }),
-      LLMEvent.finish({ reason: "stop" }),
+      LLMEvent.stepFinish({ index: 0, reason: { normalized: "stop" }, usage: { inputTokens: 3 } }),
+      LLMEvent.finish({ reason: { normalized: "stop" } }),
     ])
 
     expect(withFinishUsage?.usage).toMatchObject({ outputTokens: 2 })
     expect(withoutFinishUsage?.usage).toMatchObject({ inputTokens: 3 })
   })
 
+  test("preserves the raw finish reason", () => {
+    const response = LLMResponse.fromEvents([
+      LLMEvent.finish({ reason: { normalized: "unknown", raw: "provider_limit" } }),
+    ])
+
+    expect(response?.finishReason).toEqual({ normalized: "unknown", raw: "provider_limit" })
+  })
+
   test("assembles tool-call content only after the completed tool call event", () => {
     const pending = reduce([
       LLMEvent.toolInputStart({ id: "call_1", name: "lookup" }),
@@ -88,7 +96,7 @@ describe("LLMResponse reducer", () => {
       LLMEvent.toolInputDelta({ id: "call_1", name: "lookup", text: ':"weather"}' }),
       LLMEvent.toolInputEnd({ id: "call_1", name: "lookup" }),
       LLMEvent.toolCall({ id: "call_1", name: "lookup", input: { query: "weather" } }),
-      LLMEvent.finish({ reason: "tool-calls" }),
+      LLMEvent.finish({ reason: { normalized: "tool-calls" } }),
     ])
 
     expect(response?.message.content).toEqual([

packages/ai/test/schema.test.ts

@@ -48,8 +48,12 @@ describe("llm schema", () => {
   })
 
   test("finish constructors accept usage input", () => {
-    expect(LLMEvent.stepFinish({ index: 0, reason: "stop", usage: { inputTokens: 1 } }).usage).toBeInstanceOf(Usage)
-    expect(LLMEvent.finish({ reason: "stop", usage: { outputTokens: 2 } }).usage).toBeInstanceOf(Usage)
+    expect(
+      LLMEvent.stepFinish({ index: 0, reason: { normalized: "stop" }, usage: { inputTokens: 1 } }).usage,
+    ).toBeInstanceOf(Usage)
+    expect(LLMEvent.finish({ reason: { normalized: "stop" }, usage: { outputTokens: 2 } }).usage).toBeInstanceOf(
+      Usage,
+    )
   })
 
   test("content part tagged union exposes guards", () => {

packages/ai/test/tool-runtime.test.ts

@@ -183,6 +183,51 @@ describe("LLMClient tools", () => {
     }),
   )
 
+  it.effect("preserves provider metadata on dispatched tool results", () =>
+    Effect.gen(function* () {
+      const tool = Tool.make({
+        description: "Return text.",
+        parameters: Schema.Struct({}),
+        success: Schema.String,
+        execute: () => Effect.succeed("hello"),
+      })
+      const providerMetadata = { google: { functionCallId: "provider_call" } }
+      const dispatched = yield* ToolRuntime.dispatch(
+        { tool },
+        LLMEvent.toolCall({ id: "call_1", name: "tool", input: {}, providerMetadata }),
+      )
+
+      expect(dispatched.events).toEqual([
+        LLMEvent.toolResult({
+          id: "call_1",
+          name: "tool",
+          result: { type: "text", value: "hello" },
+          output: { structured: "hello", content: [{ type: "text", text: "hello" }] },
+          providerMetadata,
+        }),
+      ])
+
+      const failed = yield* ToolRuntime.dispatch(
+        {},
+        LLMEvent.toolCall({ id: "call_2", name: "missing", input: {}, providerMetadata }),
+      )
+      expect(failed.events).toEqual([
+        LLMEvent.toolError({
+          id: "call_2",
+          name: "missing",
+          message: "Unknown tool: missing",
+          providerMetadata,
+        }),
+        LLMEvent.toolResult({
+          id: "call_2",
+          name: "missing",
+          result: { type: "error", value: "Unknown tool: missing" },
+          providerMetadata,
+        }),
+      ])
+    }),
+  )
+
   it.effect("uses the narrow default projection for encoded typed success", () =>
     Effect.gen(function* () {
       const text = Tool.make({

packages/app/e2e/performance/timeline-stability/fixture.ts

@@ -97,6 +97,7 @@ export async function setupTimeline(
     locale?: string
     deviceScaleFactor?: number
     seedHistory?: boolean
+    protocol?: "v1" | "v2"
   } = {},
 ) {
   const sessions = input.sessions ?? [session()]
@@ -114,6 +115,7 @@ export async function setupTimeline(
     retry: input.eventRetry ?? 20,
   })
   await mockOpenCodeServer(page, {
+    protocol: input.protocol,
     directory,
     project: project(),
     provider: provider(),

packages/app/e2e/regression/session-timeline-lifecycle-state.spec.ts

@@ -32,6 +32,23 @@ for (const expanded of [false, true]) {
   })
 }
 
+test("shows and expands a running shell command without shimmering it", async ({ page }) => {
+  const id = "prt_shell_running_command"
+  const command = "sleep 10 && echo done"
+  await setupTimeline(page, {
+    messages: [userMessage(), assistantMessage([shell(id, "running", "still running", command)], { completed: false })],
+    settings: { shellToolPartsExpanded: false },
+  })
+
+  const tool = page.locator(`[data-timeline-part-id="${id}"]`)
+  await expect(tool.locator('[data-component="text-shimmer"]')).toHaveAttribute("data-active", "true")
+  await expect(tool.locator('[data-component="shell-submessage"]')).toHaveText(command)
+  await expect(tool.locator('[data-component="shell-submessage"] [data-component="text-shimmer"]')).toHaveCount(0)
+  await tool.locator('[data-slot="collapsible-trigger"]').click()
+  await expect(tool.locator('[data-slot="collapsible-trigger"]')).toHaveAttribute("aria-expanded", "true")
+  await expect(tool.locator('[data-slot="bash-pre"]')).toContainText("still running")
+})
+
 test("transitions thinking and hidden reasoning through busy to idle", async ({ page }) => {
   const reasoningID = "prt_reasoning_hidden"
   const assistant = assistantMessage([reasoningPart(reasoningID, "## Inspecting stability")], { completed: false })

packages/app/e2e/regression/session-timeline-transport.spec.ts

@@ -89,8 +89,8 @@ test("reconnects after a stream error", async ({ page }) => {
   expect((await timeline.transport.connections())[0]?.endedBy).toBe("error")
 })
 
-test("records event IDs and reconnect Last-Event-ID headers", async ({ page }) => {
-  const timeline = await setupTimeline(page, { eventRetry: 10 })
+test("does not request replay when reconnecting the volatile V2 event stream", async ({ page }) => {
+  const timeline = await setupTimeline(page, { eventRetry: 10, protocol: "v2" })
   const first = await timeline.transport.send(partUpdated(textPart("prt_transport_id", "event with id")), {
     id: "timeline-event-7",
   })
@@ -100,7 +100,7 @@ test("records event IDs and reconnect Last-Event-ID headers", async ({ page }) =
   const connection = await timeline.transport.waitForConnection({ after: first.connectionID })
 
   expect(first.eventID).toBe("timeline-event-7")
-  expect(connection.headers["last-event-id"]).toBe("timeline-event-7")
+  expect(connection.headers["last-event-id"]).toBeUndefined()
 })
 
 test("passes through non-event fetches", async ({ page }) => {

packages/app/e2e/utils/mock-server.ts

@@ -4,6 +4,7 @@ const emptyList = new Set(["/skill", "/command", "/lsp", "/formatter", "/vcs/sta
 const emptyObject = new Set(["/global/config", "/config", "/provider/auth", "/mcp", "/experimental/resource"])
 
 export interface MockServerConfig {
+  protocol?: "v1" | "v2"
   provider: unknown
   directory: string
   project: unknown
@@ -53,8 +54,20 @@ export async function mockOpenCodeServer(page: Page, config: MockServerConfig) {
     if (url.port !== targetPort && url.port !== appPort) return route.fallback()
 
     const path = url.pathname
-    if (path === "/global/event" || path === "/event") return sse(route, config.events?.(), config.eventRetry)
-    if (path === "/global/health") return json(route, { healthy: true })
+    if (path === "/global/event" || path === "/event" || path === "/api/event") {
+      const events = config.events?.()
+      return sse(
+        route,
+        path === "/api/event"
+          ? [{ id: "evt_mock_connected", type: "server.connected", data: {} }, ...(events?.map(currentEvent) ?? [])]
+          : events,
+        config.eventRetry,
+      )
+    }
+    if (path === "/global/health")
+      return config.protocol === "v2" ? json(route, {}, undefined, 404) : json(route, { healthy: true })
+    if (path === "/api/health" && config.protocol === "v2")
+      return json(route, { healthy: true, version: "2.0.0", pid: 1 })
     if (path === "/experimental/capabilities") return json(route, { backgroundSubagents: true })
     if (path === "/permission")
       return json(route, typeof config.permissions === "function" ? config.permissions() : (config.permissions ?? []))
@@ -83,10 +96,129 @@ export async function mockOpenCodeServer(page: Page, config: MockServerConfig) {
         },
         data: [],
       })
+    if (path === "/api/agent")
+      return json(route, {
+        location: location(config),
+        data: [
+          {
+            id: "build",
+            name: "Build",
+            mode: "primary",
+            hidden: false,
+            request: { settings: {}, headers: {}, body: {} },
+            permissions: [],
+          },
+        ],
+      })
+    if (path === "/api/command") return json(route, { location: location(config), data: [] })
+    if (path === "/api/mcp") return json(route, { location: location(config), data: [] })
+    if (path === "/api/mcp/resource")
+      return json(route, { location: location(config), data: { resources: [], templates: [] } })
+    const integration = path.match(/^\/api\/integration\/([^/]+)$/)?.[1]
+    if (integration && route.request().method() === "GET")
+      return json(route, {
+        location: location(config),
+        data: { id: integration, name: integration, methods: [{ type: "key", label: "API key" }], connections: [] },
+      })
+    if (/^\/api\/integration\/[^/]+\/connect\/key$/.test(path) && route.request().method() === "POST")
+      return route.fulfill({ status: 204, headers: { "access-control-allow-origin": "*" } })
+    if (path === "/api/project") return json(route, [config.project])
+    if (path === "/api/project/current")
+      return json(route, { id: (config.project as { id?: string }).id, directory: config.directory })
+    if (path.startsWith("/api/project/") && route.request().method() === "PATCH") return json(route, config.project)
+    if (path === "/api/path")
+      return json(route, {
+        state: config.directory,
+        config: config.directory,
+        worktree: config.directory,
+        directory: config.directory,
+        home: "C:/OpenCode",
+      })
+    if (path === "/api/permission/request")
+      return json(route, {
+        location: location(config),
+        data: (typeof config.permissions === "function" ? config.permissions() : (config.permissions ?? [])).map(
+          currentPermission,
+        ),
+      })
+    if (path === "/api/question/request")
+      return json(route, {
+        location: location(config),
+        data: typeof config.questions === "function" ? config.questions() : (config.questions ?? []),
+      })
+    if (path === "/api/vcs")
+      return json(route, { location: location(config), data: { branch: "main", defaultBranch: "main" } })
+    if (path === "/api/vcs/status") return json(route, { location: location(config), data: [] })
+    if (path === "/api/vcs/diff") return json(route, { location: location(config), data: config.vcsDiff ?? [] })
+    if (path === "/api/pty/shells") return json(route, { location: location(config), data: [] })
+    if (/^\/api\/pty\/[^/]+\/connect-token$/.test(path))
+      return json(route, { location: location(config), data: { ticket: "e2e-ticket", expires_in: 60 } })
     if (emptyObject.has(path)) return json(route, {})
     if (emptyList.has(path)) return json(route, [])
+    if (path === "/api/session") {
+      const directory = url.searchParams.get("directory")
+      const parentID = url.searchParams.get("parentID")
+      const limit = Number(url.searchParams.get("limit") ?? 50)
+      const offset = Number(url.searchParams.get("cursor") ?? 0)
+      const sessions = config.sessions
+        .filter((session) => !directory || session.directory === directory)
+        .filter((session) => parentID !== "null" || session.parentID === undefined)
+        .filter((session) => {
+          const search = url.searchParams.get("search")?.toLowerCase()
+          return (
+            !search ||
+            String(session.title ?? "")
+              .toLowerCase()
+              .includes(search)
+          )
+        })
+      const ordered = url.searchParams.get("order") === "asc" ? sessions.toReversed() : sessions
+      const data = ordered.slice(offset, offset + limit)
+      const next = offset + limit < ordered.length ? String(offset + limit) : undefined
+      return json(route, {
+        data: data.map((session) => currentSession(session, config.directory)),
+        cursor: { next },
+      })
+    }
+    if (path === "/api/session/active") {
+      const statuses = (config.sessionStatus ?? {}) as Record<string, { type?: string }>
+      return json(route, {
+        data: Object.fromEntries(
+          Object.entries(statuses).flatMap(([id, status]) =>
+            status.type === "idle" ? [] : [[id, { type: "running" }]],
+          ),
+        ),
+      })
+    }
+    if (/^\/api\/session\/[^/]+\/shell$/.test(path) && route.request().method() === "POST") {
+      return route.fulfill({ status: 204, headers: { "access-control-allow-origin": "*" } })
+    }
+    if (/^\/api\/session\/[^/]+\/question\/[^/]+\/(reply|reject)$/.test(path) && route.request().method() === "POST") {
+      return route.fulfill({ status: 204, headers: { "access-control-allow-origin": "*" } })
+    }
+    if (/^\/api\/session\/[^/]+\/permission\/[^/]+\/reply$/.test(path) && route.request().method() === "POST") {
+      return route.fulfill({ status: 204, headers: { "access-control-allow-origin": "*" } })
+    }
+    if (
+      /^\/api\/session\/[^/]+\/(archive|rename|interrupt|revert\/clear|revert\/commit)$/.test(path) &&
+      route.request().method() === "POST"
+    ) {
+      return route.fulfill({ status: 204, headers: { "access-control-allow-origin": "*" } })
+    }
+    if (/^\/api\/session\/[^/]+$/.test(path) && route.request().method() === "DELETE") {
+      return route.fulfill({ status: 204, headers: { "access-control-allow-origin": "*" } })
+    }
     if (path in staticRoutes) return json(route, staticRoutes[path])
 
+    const currentSessionMatch = path.match(/^\/api\/session\/([^/]+)$/)
+    if (currentSessionMatch) {
+      const session = config.sessions.find((item) => item.id === currentSessionMatch[1])
+      if (!session) return json(route, { error: "Session not found" }, undefined, 404)
+      return json(route, {
+        data: currentSession(session, config.directory),
+      })
+    }
+
     const sessionMatch = path.match(/^\/session\/([^/]+)$/)
     if (sessionMatch) {
       const session = config.sessions.find((s) => s.id === sessionMatch[1])
@@ -107,6 +239,24 @@ export async function mockOpenCodeServer(page: Page, config: MockServerConfig) {
 
     if (/^\/session\/[^/]+\/(children|diff)$/.test(path)) return json(route, [])
 
+    const currentMessagesMatch = path.match(/^\/api\/session\/([^/]+)\/message$/)
+    if (currentMessagesMatch) {
+      const token = url.searchParams.get("cursor") ?? undefined
+      const before = token ? cursors.get(token) : undefined
+      if (token && !before) return json(route, { error: "Invalid cursor" }, undefined, 400)
+      config.onMessages?.({ sessionID: currentMessagesMatch[1], before, phase: "start" })
+      await config.beforeMessagesResponse?.({ sessionID: currentMessagesMatch[1]!, before })
+      if (config.messageDelay !== undefined) await new Promise((resolve) => setTimeout(resolve, config.messageDelay))
+      const pageData = config.pageMessages(currentMessagesMatch[1], Number(url.searchParams.get("limit") ?? 50), before)
+      config.onMessages?.({ sessionID: currentMessagesMatch[1], before, phase: "end" })
+      const cursor = pageData.cursor ? `cursor_${++nextCursor}` : undefined
+      if (cursor) cursors.set(cursor, pageData.cursor!)
+      return json(route, {
+        data: pageData.items.map(currentMessage).reverse(),
+        cursor: { next: cursor },
+      })
+    }
+
     const messagesMatch = path.match(/^\/session\/([^/]+)\/message$/)
     if (messagesMatch) {
       const token = url.searchParams.get("before") ?? undefined
@@ -129,6 +279,115 @@ export async function mockOpenCodeServer(page: Page, config: MockServerConfig) {
   })
 }
 
+function location(config: MockServerConfig) {
+  return {
+    directory: config.directory,
+    project: { id: (config.project as { id?: string }).id, directory: config.directory },
+  }
+}
+
+function currentPermission(value: unknown) {
+  const permission = value as Record<string, unknown>
+  if (permission.action) return permission
+  const tool = permission.tool as { messageID?: string; callID?: string } | undefined
+  return {
+    id: permission.id,
+    sessionID: permission.sessionID,
+    action: permission.permission,
+    resources: permission.patterns ?? [],
+    save: permission.always,
+    metadata: permission.metadata,
+    source:
+      tool?.messageID && tool.callID ? { type: "tool", messageID: tool.messageID, callID: tool.callID } : undefined,
+  }
+}
+
+export function currentSession(session: { id: string } & Record<string, unknown>, fallbackDirectory?: string) {
+  const time = session.time && typeof session.time === "object" ? session.time : {}
+  return {
+    id: session.id,
+    parentID: session.parentID,
+    projectID: session.projectID ?? "project",
+    agent: session.agent ?? "build",
+    model: session.model ?? { id: "mock-model", providerID: "mock-provider" },
+    cost: session.cost ?? 0,
+    tokens: session.tokens ?? { input: 0, output: 0, reasoning: 0, cache: { read: 0, write: 0 } },
+    time: {
+      created: "created" in time && typeof time.created === "number" ? time.created : 0,
+      updated: "updated" in time && typeof time.updated === "number" ? time.updated : 0,
+      ...(session.time && typeof session.time === "object" && "archived" in session.time
+        ? { archived: session.time.archived }
+        : {}),
+    },
+    title: session.title ?? session.id,
+    location: {
+      directory: typeof session.directory === "string" ? session.directory : fallbackDirectory,
+      ...(typeof session.workspaceID === "string" ? { workspaceID: session.workspaceID } : {}),
+    },
+    subpath: session.path,
+    revert: session.revert,
+  }
+}
+
+function currentMessage(value: unknown) {
+  const item = value as {
+    info: Record<string, unknown> & { id: string; role: "user" | "assistant"; time: { created: number } }
+    parts: Array<Record<string, unknown> & { type: string }>
+  }
+  if (item.info.role === "user") {
+    return {
+      id: item.info.id,
+      type: "user",
+      time: item.info.time,
+      text: item.parts
+        .flatMap((part) => (part.type === "text" && typeof part.text === "string" ? [part.text] : []))
+        .join("\n"),
+    }
+  }
+  return {
+    id: item.info.id,
+    type: "assistant",
+    time: item.info.time,
+    agent: item.info.agent ?? "build",
+    model: { id: item.info.modelID ?? "model", providerID: item.info.providerID ?? "provider" },
+    cost: item.info.cost,
+    tokens: item.info.tokens,
+    error: item.info.error,
+    content: item.parts.flatMap<unknown>((part) => {
+      if (part.type === "text" || part.type === "reasoning") return [{ type: part.type, text: part.text ?? "" }]
+      if (part.type !== "tool") return []
+      const state = part.state as Record<string, unknown>
+      return [
+        {
+          type: "tool",
+          id: part.id,
+          name: part.tool,
+          time: state.time ?? { created: item.info.time.created },
+          state:
+            state.status === "pending"
+              ? { status: "streaming", input: state.raw ?? JSON.stringify(state.input ?? {}) }
+              : state.status === "completed"
+                ? {
+                    status: "completed",
+                    input: state.input ?? {},
+                    structured: state.metadata ?? {},
+                    content: [{ type: "text", text: state.output ?? "" }],
+                  }
+                : state.status === "error"
+                  ? {
+                      status: "error",
+                      input: state.input ?? {},
+                      structured: state.metadata ?? {},
+                      content: [],
+                      error: { type: "ToolError", message: state.error ?? "Tool failed" },
+                    }
+                  : { status: "running", input: state.input ?? {}, structured: state.metadata ?? {}, content: [] },
+        },
+      ]
+    }),
+  }
+}
+
 function json(route: Route, body: unknown, headers?: Record<string, string>, status = 200) {
   return route.fulfill({
     status,
@@ -149,3 +408,18 @@ function sse(route: Route, events?: unknown[], retry?: number) {
     body: `${retry === undefined ? "" : `retry: ${retry}\n\n`}${events?.map((event) => `data: ${JSON.stringify(event)}\n\n`).join("") || ": ok\n\n"}`,
   })
 }
+
+function currentEvent(input: unknown) {
+  if (!input || typeof input !== "object" || !("payload" in input)) return input
+  const envelope = input as { directory?: string; payload?: unknown }
+  if (!envelope.payload || typeof envelope.payload !== "object") return input
+  const payload = envelope.payload as { id?: string; type?: string; properties?: unknown }
+  if (!payload.type) return input
+  return {
+    id: payload.id ?? `evt_mock_${Date.now()}`,
+    created: Date.now(),
+    type: payload.type,
+    data: payload.properties ?? {},
+    location: envelope.directory && envelope.directory !== "global" ? { directory: envelope.directory } : undefined,
+  }
+}

packages/app/e2e/utils/sse-transport.ts

@@ -3,7 +3,7 @@ import type { Page } from "@playwright/test"
 export type SseConnectionRecord = {
   id: number
   url: string
-  path: "/global/event" | "/event"
+  path: "/global/event" | "/event" | "/api/event"
   headers: Record<string, string>
   openedAt: number
   endedAt?: number
@@ -93,6 +93,21 @@ export async function installSseTransport<T>(
           eventOptions.retry === undefined ? "" : `retry: ${eventOptions.retry}\n`,
           `data: ${JSON.stringify(payload)}\n\n`,
         ].join("")
+      const currentEvent = (input: unknown) => {
+        if (!input || typeof input !== "object" || !("payload" in input)) return input
+        const envelope = input as { directory?: string; payload?: unknown }
+        if (!envelope.payload || typeof envelope.payload !== "object") return input
+        const payload = envelope.payload as { id?: string; type?: string; properties?: unknown }
+        if (!payload.type) return input
+        return {
+          id: payload.id ?? `evt_mock_${Date.now()}`,
+          created: Date.now(),
+          type: payload.type,
+          data: payload.properties ?? {},
+          location:
+            envelope.directory && envelope.directory !== "global" ? { directory: envelope.directory } : undefined,
+        }
+      }
       const acknowledge = (
         connection: Connection,
         bytes: number,
@@ -140,15 +155,13 @@ export async function installSseTransport<T>(
           output.forEach((chunk) => connection.controller.enqueue(chunk))
           return acknowledge(connection, input.bytes.length, output.length)
         }
-        const encoded = input.deliveries.map((delivery) => ({
-          delivery,
-          bytes: encoder.encode(frame(delivery.payload, delivery.options)),
-        }))
+        const encoded = input.deliveries.map((delivery) => {
+          const payload = connection.path === "/api/event" ? currentEvent(delivery.payload) : delivery.payload
+          return { delivery, payload, bytes: encoder.encode(frame(payload, delivery.options)) }
+        })
         encoded.forEach((item) => marker(item.delivery.options?.marker))
         if (input.burst) {
-          const bytes = encoder.encode(
-            encoded.map((item) => frame(item.delivery.payload, item.delivery.options)).join(""),
-          )
+          const bytes = encoder.encode(encoded.map((item) => frame(item.payload, item.delivery.options)).join(""))
           connection.controller.enqueue(bytes)
           return encoded.map((item) => acknowledge(connection, item.bytes.byteLength, 1, item.delivery.options?.id))
         }
@@ -161,7 +174,10 @@ export async function installSseTransport<T>(
       const fetch = (input: RequestInfo | URL, init?: RequestInit) => {
         const request = new Request(input, init)
         const url = new URL(request.url)
-        if (url.origin !== server || (url.pathname !== "/global/event" && url.pathname !== "/event"))
+        if (
+          url.origin !== server ||
+          (url.pathname !== "/global/event" && url.pathname !== "/event" && url.pathname !== "/api/event")
+        )
           return originalFetch(request)
 
         const id = ++nextConnectionID
@@ -177,6 +193,10 @@ export async function installSseTransport<T>(
             record.controller = controller
             connections.push(record)
             if (retry !== undefined) controller.enqueue(encoder.encode(`retry: ${retry}\n\n`))
+            if (url.pathname === "/api/event")
+              controller.enqueue(
+                encoder.encode(frame({ id: `evt_mock_connected_${id}`, type: "server.connected", data: {} })),
+              )
             request.signal.addEventListener(
               "abort",
               () => {

packages/app/package.json

@@ -53,6 +53,7 @@
     "@dnd-kit/helpers": "0.5.0",
     "@dnd-kit/solid": "0.5.0",
     "@kobalte/core": "catalog:",
+    "@opencode-ai/client": "file:vendor/opencode-ai-client-1.17.13.tgz",
     "@opencode-ai/core": "workspace:*",
     "@opencode-ai/schema": "workspace:*",
     "@opencode-ai/sdk": "workspace:*",

packages/app/src/context/server-sdk.test.ts

@@ -1,5 +1,6 @@
 import { describe, expect, test } from "bun:test"
-import { coalesceServerEvents, enqueueServerEvent, resumeStreamAfterPageShow } from "./server-sdk"
+import { adaptServerEvent, coalesceServerEvents, enqueueServerEvent, resumeStreamAfterPageShow } from "./server-sdk"
+import type { OpenCodeEvent } from "@opencode-ai/client/promise"
 import type { Event } from "@opencode-ai/sdk/v2/client"
 
 describe("resumeStreamAfterPageShow", () => {
@@ -14,6 +15,23 @@ describe("resumeStreamAfterPageShow", () => {
   })
 })
 
+describe("adaptServerEvent", () => {
+  test("preserves V2 events while adapting permission requests for existing consumers", () => {
+    const current = {
+      id: "evt_1",
+      created: 1,
+      type: "permission.v2.asked",
+      data: { id: "perm_1", sessionID: "ses_1", action: "read", resources: ["src/**"] },
+    } as OpenCodeEvent
+
+    expect(adaptServerEvent(current)).toMatchObject({
+      type: "permission.asked",
+      properties: { id: "perm_1", sessionID: "ses_1", permission: "read", patterns: ["src/**"] },
+      current,
+    })
+  })
+})
+
 describe("coalesceServerEvents", () => {
   const delta = (value: string, field = "text", partID = "part") => ({
     directory: "/repo",
@@ -34,6 +52,24 @@ describe("coalesceServerEvents", () => {
     expect(result[0]?.payload).toMatchObject({ id: "second", properties: { delta: "hello world" } })
   })
 
+  test("merges adjacent current text deltas", () => {
+    const current = (id: string, value: string) =>
+      adaptServerEvent({
+        id,
+        created: 1,
+        type: "session.text.delta",
+        location: { directory: "/repo" },
+        data: { sessionID: "ses", assistantMessageID: "msg", ordinal: 0, delta: value },
+      } as OpenCodeEvent)
+    const result = coalesceServerEvents([
+      { directory: "/repo", payload: current("evt_1", "hello ") },
+      { directory: "/repo", payload: current("evt_2", "world") },
+    ])
+
+    expect(result).toHaveLength(1)
+    expect(result[0]?.payload.current).toMatchObject({ id: "evt_2", data: { delta: "hello world" } })
+  })
+
   test("preserves event boundaries and distinct fields", () => {
     const status = {
       directory: "/repo",

packages/app/src/context/server-sdk.tsx

@@ -1,21 +1,60 @@
+import type { OpenCodeEvent } from "@opencode-ai/client/promise"
 import type { Event } from "@opencode-ai/sdk/v2/client"
 import { createSimpleContext } from "@opencode-ai/ui/context"
 import { createGlobalEmitter } from "@solid-primitives/event-bus"
 import { makeEventListener } from "@solid-primitives/event-listener"
 import { type Accessor, batch, createMemo, onCleanup, onMount } from "solid-js"
-import { createSdkForServer } from "@/utils/server"
+import { createApiForServer, createSdkForServer, type ServerApi } from "@/utils/server"
 import { useLanguage } from "./language"
 import { usePlatform } from "./platform"
 import { ServerConnection, useServer } from "./server"
 import { createRefCountMap } from "@/utils/refcount"
 import { useGlobal } from "./global"
 import { ServerScope } from "@/utils/server-scope"
+import { detectServerProtocol, type ServerProtocol } from "@/utils/server-protocol"
+import { createCompatibleApi, type CompatibleApi } from "@/utils/server-compat"
 
 const isAbortError = (error: unknown) =>
   error !== null && typeof error === "object" && "name" in error && error.name === "AbortError"
 
 const isStreamClosed = (error: unknown, signal?: AbortSignal) => isAbortError(error) || signal?.aborted === true
-type QueuedServerEvent = { directory: string; payload: Event }
+export type ServerEvent = Event & { current?: OpenCodeEvent }
+type QueuedServerEvent = { directory: string; payload: ServerEvent }
+type CurrentDelta = Extract<
+  OpenCodeEvent,
+  { type: "session.text.delta" | "session.reasoning.delta" | "session.tool.input.delta" | "session.compaction.delta" }
+>
+
+export function adaptServerEvent(event: OpenCodeEvent): ServerEvent {
+  if (event.type === "permission.v2.asked") {
+    return {
+      id: event.id,
+      type: "permission.asked",
+      properties: {
+        id: event.data.id,
+        sessionID: event.data.sessionID,
+        permission: event.data.action,
+        patterns: event.data.resources,
+        always: event.data.save ?? [],
+        metadata: event.data.metadata ?? {},
+        tool:
+          event.data.source?.type === "tool"
+            ? { messageID: event.data.source.messageID, callID: event.data.source.callID }
+            : undefined,
+      },
+      current: event,
+    } as ServerEvent
+  }
+  if (event.type === "permission.v2.replied")
+    return { id: event.id, type: "permission.replied", properties: event.data, current: event } as ServerEvent
+  if (event.type === "question.v2.asked")
+    return { id: event.id, type: "question.asked", properties: event.data, current: event } as ServerEvent
+  if (event.type === "question.v2.replied")
+    return { id: event.id, type: "question.replied", properties: event.data, current: event } as ServerEvent
+  if (event.type === "question.v2.rejected")
+    return { id: event.id, type: "question.rejected", properties: event.data, current: event } as ServerEvent
+  return { id: event.id, type: event.type, properties: event.data, current: event } as ServerEvent
+}
 
 const coalescedKey = (event: QueuedServerEvent) => {
   if (event.payload.type === "lsp.updated") return `lsp.updated:${event.directory}`
@@ -40,6 +79,34 @@ export function enqueueServerEvent(queue: QueuedServerEvent[], event: QueuedServ
 export function coalesceServerEvents(events: QueuedServerEvent[]) {
   const output: QueuedServerEvent[] = []
   events.forEach((event) => {
+    const current = currentDelta(event.payload.current)
+    if (current) {
+      const previous = output[output.length - 1]
+      const prior = currentDelta(previous?.payload.current)
+      if (
+        previous &&
+        prior &&
+        previous.directory === event.directory &&
+        currentDeltaKey(prior) === currentDeltaKey(current)
+      ) {
+        const fragment = currentDeltaFragment(prior) + currentDeltaFragment(current)
+        const data =
+          current.type === "session.compaction.delta"
+            ? { ...current.data, text: fragment }
+            : { ...current.data, delta: fragment }
+        output[output.length - 1] = {
+          directory: event.directory,
+          payload: {
+            ...event.payload,
+            properties: data,
+            current: { ...current, data } as CurrentDelta,
+          } as ServerEvent,
+        }
+        return
+      }
+      output.push(event)
+      return
+    }
     if (event.payload.type !== "message.part.delta") {
       output.push(event)
       return
@@ -71,12 +138,52 @@ export function coalesceServerEvents(events: QueuedServerEvent[]) {
   return output
 }
 
+function currentDelta(event: OpenCodeEvent | undefined): CurrentDelta | undefined {
+  if (
+    event?.type === "session.text.delta" ||
+    event?.type === "session.reasoning.delta" ||
+    event?.type === "session.tool.input.delta" ||
+    event?.type === "session.compaction.delta"
+  )
+    return event
+}
+
+function currentDeltaKey(event: CurrentDelta) {
+  if (event.type === "session.tool.input.delta")
+    return `${event.type}:${event.data.sessionID}:${event.data.assistantMessageID}:${event.data.callID}`
+  if (event.type === "session.compaction.delta") return `${event.type}:${event.data.sessionID}`
+  return `${event.type}:${event.data.sessionID}:${event.data.assistantMessageID}:${event.data.ordinal}`
+}
+
+function currentDeltaFragment(event: CurrentDelta) {
+  return event.type === "session.compaction.delta" ? event.data.text : event.data.delta
+}
+
 export function resumeStreamAfterPageShow(event: PageTransitionEvent, start: () => unknown) {
   if (!event.persisted) return
   start()
 }
 
-function createServerSdkContextBase(server: ServerConnection.Any, scope: ServerScope) {
+type ServerEventEmitter = ReturnType<typeof createGlobalEmitter<{ [key: string]: ServerEvent }>>
+type ServerSDKBase = {
+  server: ServerConnection.Any
+  scope: ServerScope
+  protocol: Promise<ServerProtocol>
+  url: string
+  client: ReturnType<typeof createSdkForServer>
+  api: CompatibleApi
+  currentApi: ServerApi
+  event: {
+    on: ServerEventEmitter["on"]
+    listen: ServerEventEmitter["listen"]
+    start: () => Promise<void> | undefined
+  }
+  createClient: (
+    opts: Omit<Parameters<typeof createSdkForServer>[0], "server" | "fetch">,
+  ) => ReturnType<typeof createSdkForServer>
+}
+
+function createServerSdkContextBase(server: ServerConnection.Any, scope: ServerScope): ServerSDKBase {
   const platform = usePlatform()
   const abort = new AbortController()
 
@@ -91,13 +198,15 @@ function createServerSdkContextBase(server: ServerConnection.Any, scope: ServerS
     }
   })()
 
+  const eventApi = createApiForServer({ server: server.http, fetch: eventFetch })
   const eventSdk = createSdkForServer({
     signal: abort.signal,
     fetch: eventFetch,
     server: server.http,
   })
+  const protocol = detectServerProtocol(server.http, platform.fetch ?? globalThis.fetch)
   const emitter = createGlobalEmitter<{
-    [key: string]: Event
+    [key: string]: ServerEvent
   }>()
 
   type Queued = QueuedServerEvent
@@ -142,21 +251,6 @@ function createServerSdkContextBase(server: ServerConnection.Any, scope: ServerS
   let run: Promise<void> | undefined
   let started = false
   let generation = 0
-  const HEARTBEAT_TIMEOUT_MS = 15_000
-  let lastEventAt = Date.now()
-  let heartbeat: ReturnType<typeof setTimeout> | undefined
-  const resetHeartbeat = () => {
-    lastEventAt = Date.now()
-    if (heartbeat) clearTimeout(heartbeat)
-    heartbeat = setTimeout(() => {
-      attempt?.abort()
-    }, HEARTBEAT_TIMEOUT_MS)
-  }
-  const clearHeartbeat = () => {
-    if (!heartbeat) return
-    clearTimeout(heartbeat)
-    heartbeat = undefined
-  }
 
   const start = () => {
     if (started) return run
@@ -168,35 +262,24 @@ function createServerSdkContextBase(server: ServerConnection.Any, scope: ServerS
       // oxlint-disable-next-line no-unmodified-loop-condition -- `started` is set to false by stop() which also aborts; both flags are checked to allow graceful exit
       while (!abort.signal.aborted && started && generation === active) {
         attempt = new AbortController()
-        lastEventAt = Date.now()
         const onAbort = () => {
           attempt?.abort()
         }
         abort.signal.addEventListener("abort", onAbort)
         try {
-          const events = await eventSdk.global.event({
-            signal: attempt.signal,
-            onSseError: (error) => {
-              if (isStreamClosed(error, attempt?.signal)) return
-              if (streamErrorLogged) return
-              streamErrorLogged = true
-              console.error("[global-sdk] event stream error", {
-                url: server.http.url,
-                fetch: eventFetch ? "platform" : "webview",
-                error,
-              })
-            },
-          })
+          const kind = await protocol
+          const events =
+            kind === "v1"
+              ? (await eventSdk.global.event({ signal: attempt.signal })).stream
+              : eventApi.event.subscribe({ signal: attempt.signal })
           let yielded = Date.now()
-          resetHeartbeat()
-          for await (const event of events.stream) {
-            resetHeartbeat()
+          for await (const event of events) {
             streamErrorLogged = false
-            if (event.payload.type !== "sync") {
-              const directory = event.directory ?? "global"
-              const payload = event.payload as Event
-              if (enqueueServerEvent(queue, { directory, payload })) schedule()
-            }
+            const legacy = "payload" in event
+            if (legacy && event.payload.type === "sync") continue
+            const directory = legacy ? (event.directory ?? "global") : (event.location?.directory ?? "global")
+            const payload = legacy ? (event.payload as Event) : adaptServerEvent(event)
+            if (enqueueServerEvent(queue, { directory, payload })) schedule()
 
             if (Date.now() - yielded < STREAM_YIELD_MS) continue
             yielded = Date.now()
@@ -214,7 +297,6 @@ function createServerSdkContextBase(server: ServerConnection.Any, scope: ServerS
         } finally {
           abort.signal.removeEventListener("abort", onAbort)
           attempt = undefined
-          clearHeartbeat()
         }
 
         if (abort.signal.aborted || !started || generation !== active) return
@@ -233,18 +315,11 @@ function createServerSdkContextBase(server: ServerConnection.Any, scope: ServerS
     started = false
     generation++
     attempt?.abort()
-    clearHeartbeat()
   }
 
   onMount(() => {
     makeEventListener(window, "pagehide", stop)
     makeEventListener(window, "pageshow", (event) => resumeStreamAfterPageShow(event, start))
-    makeEventListener(document, "visibilitychange", () => {
-      if (document.visibilityState !== "visible") return
-      if (!started) return
-      if (Date.now() - lastEventAt < HEARTBEAT_TIMEOUT_MS) return
-      attempt?.abort()
-    })
   })
 
   onCleanup(() => {
@@ -258,12 +333,24 @@ function createServerSdkContextBase(server: ServerConnection.Any, scope: ServerS
     fetch: platform.fetch,
     throwOnError: true,
   })
+  const currentApi: ServerApi = createApiForServer({ server: server.http, fetch: platform.fetch })
+  const legacy = (directory?: string) =>
+    createSdkForServer({
+      server: server.http,
+      fetch: platform.fetch,
+      throwOnError: true,
+      directory,
+    })
+  const api = createCompatibleApi({ protocol, current: currentApi, legacy })
 
   return {
     server,
     scope,
+    protocol,
     url: server.http.url,
     client: sdk,
+    api,
+    currentApi,
     event: {
       on: emitter.on.bind(emitter),
       listen: emitter.listen.bind(emitter),
@@ -279,7 +366,6 @@ function createServerSdkContextBase(server: ServerConnection.Any, scope: ServerS
   }
 }
 
-type ServerSDKBase = ReturnType<typeof createServerSdkContextBase>
 export type ServerSDK = ServerSDKBase & {
   ensureDirSdkContext: (directory: string) => ReturnType<typeof createDirSdkContext>
 }
@@ -309,7 +395,7 @@ export const { use: useServerSDK, provider: ServerSDKProvider } = createSimpleCo
 })
 
 type SDKEventMap = {
-  [key in Event["type"]]: Extract<Event, { type: key }>
+  [key in Event["type"]]: Extract<ServerEvent, { type: key }>
 }
 
 function createDirSdkContext(directory: string, serverSDK: ServerSDKBase) {
@@ -329,6 +415,12 @@ function createDirSdkContext(directory: string, serverSDK: ServerSDKBase) {
     scope: serverSDK.scope,
     directory,
     client,
+    api: createCompatibleApi({
+      protocol: serverSDK.protocol,
+      current: serverSDK.currentApi,
+      legacy: (next) => serverSDK.createClient({ directory: next ?? directory, throwOnError: true }),
+      directory,
+    }),
     event: emitter,
     get url() {
       return serverSDK.url

packages/app/src/pages/layout/project-avatar-state.ts

@@ -13,7 +13,6 @@ export function useSessionTabAvatarState(
   const global = useGlobal()
   const notification = useNotification()
   const permission = usePermission()
-  const permissionState = createMemo(() => permission.ensureServerState(server()))
   const connection = createMemo(() => global.servers.list().find((item) => ServerConnection.key(item) === server()))
   const sync = createMemo(() => {
     const conn = connection()
@@ -22,9 +21,10 @@ export function useSessionTabAvatarState(
   const hasPermissions = createMemo(() => {
     const serverSync = sync()
     if (!serverSync) return false
+    const permissionState = permission.ensureServerState(server())
     const [store] = serverSync.child(directory(), { bootstrap: false })
     return !!sessionPermissionRequest(store.session, serverSync.session.data.permission, sessionId(), (item) => {
-      return !permissionState().autoResponds(item, directory())
+      return !permissionState.autoResponds(item, directory())
     })
   })
   const hasQuestions = createMemo(() => {
@@ -34,9 +34,11 @@ export function useSessionTabAvatarState(
     return !!sessionQuestionRequest(store.session, serverSync.session.data.question, sessionId())
   })
   const needsAttention = createMemo(() => hasPermissions() || hasQuestions())
-  const unread = createMemo(
-    () => needsAttention() || notification.ensureServerState(server()).session.unseenCount(sessionId()) > 0,
-  )
+  const notificationState = createMemo(() => {
+    if (!connection()) return
+    return notification.ensureServerState(server())
+  })
+  const unread = createMemo(() => needsAttention() || (notificationState()?.session.unseenCount(sessionId()) ?? 0) > 0)
   const loading = createMemo(() => {
     const serverSync = sync()
     if (!serverSync) return false

packages/app/src/utils/server-compat.test.ts

@@ -0,0 +1,113 @@
+import { describe, expect, test } from "bun:test"
+import { createApiForServer, createSdkForServer } from "./server"
+import { createCompatibleApi } from "./server-compat"
+
+function setup(protocol: "v1" | "v2" | Promise<"v1" | "v2">) {
+  const requests: Request[] = []
+  const fetcher = Object.assign(
+    async (input: string | URL | Request, init?: RequestInit) => {
+      const request = new Request(input, init)
+      requests.push(request)
+      if (request.method === "PATCH") {
+        return Response.json({
+          id: "ses_1",
+          slug: "ses_1",
+          projectID: "project",
+          directory: "/repo",
+          title: "Session",
+          version: "1",
+          time: { created: 1, updated: 1 },
+        })
+      }
+      if (request.method === "POST" && request.url.endsWith("/prompt_async"))
+        return new Response(undefined, { status: 204 })
+      if (request.method === "POST" && request.url.endsWith("/prompt")) {
+        return Response.json({
+          admittedSeq: 1,
+          id: "msg_1",
+          sessionID: "ses_1",
+          timeCreated: 1,
+          type: "user",
+          data: { text: "hello" },
+          delivery: "steer",
+        })
+      }
+      if (request.method === "GET") return Response.json([])
+      return new Response(undefined, { status: 204 })
+    },
+    { preconnect: globalThis.fetch.preconnect },
+  )
+  const server = { url: "http://localhost:4096" }
+  const api = createCompatibleApi({
+    protocol: typeof protocol === "string" ? Promise.resolve(protocol) : protocol,
+    current: createApiForServer({ server, fetch: fetcher }),
+    legacy: (directory) => createSdkForServer({ server, fetch: fetcher, directory, throwOnError: true }),
+    directory: "/repo",
+  })
+  return { api, requests }
+}
+
+describe("createCompatibleApi", () => {
+  test("routes V1 archive through the legacy session update", async () => {
+    const { api, requests } = setup("v1")
+    await api.session.archive({ sessionID: "ses_1", directory: "/repo" })
+
+    const url = new URL(requests[0]!.url)
+    expect(url.pathname).toBe("/session/ses_1")
+    expect(requests[0]!.headers.get("x-opencode-directory")).toBe("%2Frepo")
+    expect(requests[0]!.method).toBe("PATCH")
+    expect(await requests[0]!.json()).toMatchObject({ time: { archived: expect.any(Number) } })
+  })
+
+  test("converts current prompts to the V1 prompt contract", async () => {
+    const { api, requests } = setup("v1")
+    await api.session.prompt({
+      sessionID: "ses_1",
+      id: "msg_1",
+      text: "hello",
+      agent: "build",
+      model: { providerID: "provider", modelID: "model" },
+    })
+
+    expect(new URL(requests[0]!.url).pathname).toBe("/session/ses_1/prompt_async")
+    expect(await requests[0]!.json()).toMatchObject({
+      messageID: "msg_1",
+      agent: "build",
+      model: { providerID: "provider", modelID: "model" },
+      parts: [{ type: "text", text: "hello" }],
+    })
+  })
+
+  test("keeps V2 session actions on the current API", async () => {
+    const { api, requests } = setup("v2")
+    await api.session.archive({ sessionID: "ses_1" })
+
+    expect(new URL(requests[0]!.url).pathname).toBe("/api/session/ses_1/archive")
+    expect(requests[0]!.method).toBe("POST")
+  })
+
+  test("resolves protocol detection once across implementation methods", async () => {
+    let detections = 0
+    const resolved = Promise.resolve<"v1" | "v2">("v2")
+    const protocol = new Proxy(resolved, {
+      get(target, property) {
+        if (property !== "then") return Reflect.get(target, property, target)
+        detections++
+        return target.then.bind(target)
+      },
+    })
+    const { api } = setup(protocol)
+
+    await api.session.archive({ sessionID: "ses_1" })
+    await api.session.list()
+
+    expect(detections).toBe(1)
+  })
+
+  test("uses the global V1 session search endpoint", async () => {
+    const { api, requests } = setup("v1")
+    await api.session.list({ parentID: null, search: "session", limit: 50 })
+
+    expect(new URL(requests[0]!.url).pathname).toBe("/experimental/session")
+  })
+})

packages/app/src/utils/server-compat.ts

@@ -0,0 +1,495 @@
+import type { ServerApi } from "./server"
+import type { ServerProtocol } from "./server-protocol"
+import type { OpencodeClient, Session } from "@opencode-ai/sdk/v2/client"
+import type {
+  Project,
+  ProjectCurrent,
+  SessionApi,
+  SessionCommandInput,
+  SessionCommandOutput,
+  SessionCompactInput,
+  SessionCompactOutput,
+  SessionInfo,
+  SessionPromptInput,
+  SessionPromptOutput,
+  SessionShellInput,
+  SessionShellOutput,
+} from "@opencode-ai/client/promise"
+
+type LegacyClient = OpencodeClient
+type LegacyFor = (directory?: string) => LegacyClient
+type CompatibleSessionApi = Omit<
+  SessionApi,
+  "prompt" | "command" | "shell" | "compact" | "rename" | "archive" | "remove"
+> & {
+  prompt: (input: SessionPromptInput & LegacyPrompt) => Promise<SessionPromptOutput>
+  command: (input: SessionCommandInput) => Promise<SessionCommandOutput>
+  shell: (input: SessionShellInput & LegacyPrompt) => Promise<SessionShellOutput>
+  compact: (input: SessionCompactInput & { model?: LegacyPrompt["model"] }) => Promise<SessionCompactOutput>
+  rename: (input: Parameters<SessionApi["rename"]>[0] & LegacyLocation) => ReturnType<SessionApi["rename"]>
+  archive: (input: Parameters<SessionApi["archive"]>[0] & LegacyLocation) => ReturnType<SessionApi["archive"]>
+  remove: (input: Parameters<SessionApi["remove"]>[0] & LegacyLocation) => ReturnType<SessionApi["remove"]>
+}
+export type CompatibleApi = Omit<ServerApi, "session"> & { readonly session: CompatibleSessionApi }
+type LegacyPrompt = {
+  agent?: string
+  model?: { providerID: string; modelID: string }
+  variant?: string
+}
+type LegacyLocation = { directory?: string }
+type CompatibleInput = {
+  protocol: Promise<ServerProtocol>
+  current: ServerApi
+  legacy: LegacyFor
+  directory?: string
+}
+
+function mime(uri: string) {
+  const match = /^data:([^;,]+)/.exec(uri)
+  return match?.[1] ?? "application/octet-stream"
+}
+
+function sessionInfo(session: Session): SessionInfo {
+  return {
+    id: session.id,
+    parentID: session.parentID,
+    projectID: session.projectID,
+    agent: session.agent,
+    model: session.model && {
+      id: session.model.id,
+      providerID: session.model.providerID,
+      variant: session.model.variant,
+    },
+    cost: session.cost ?? 0,
+    tokens: session.tokens ?? { input: 0, output: 0, reasoning: 0, cache: { read: 0, write: 0 } },
+    time: session.time,
+    title: session.title,
+    location: { directory: session.directory, workspaceID: session.workspaceID },
+    subpath: session.path,
+    revert: session.revert && {
+      messageID: session.revert.messageID,
+      partID: session.revert.partID,
+      snapshot: session.revert.snapshot,
+    },
+  }
+}
+
+export function createCompatibleApi(input: CompatibleInput): CompatibleApi {
+  const v1 = createV1Api(input)
+  return lazyApi(
+    input.protocol.then((protocol) => (protocol === "v1" ? v1 : input.current)),
+    input.current,
+  )
+}
+
+function lazyApi<T extends object>(implementation: Promise<T>, shape: T): T {
+  const cache = new Map<PropertyKey, unknown>()
+  return new Proxy(shape, {
+    get(target, property, receiver) {
+      const sample = Reflect.get(target, property, receiver)
+      if (typeof sample === "function") {
+        return (...args: unknown[]) =>
+          implementation.then((value) => {
+            const method = Reflect.get(value, property)
+            if (typeof method !== "function") throw new Error(`API method unavailable: ${String(property)}`)
+            return Reflect.apply(method, value, args)
+          })
+      }
+      if (sample === null || typeof sample !== "object") return sample
+      if (cache.has(property)) return cache.get(property)
+      const nested = lazyApi(
+        implementation.then((value) => {
+          const result = Reflect.get(value, property)
+          if (result === null || typeof result !== "object") {
+            throw new Error(`API namespace unavailable: ${String(property)}`)
+          }
+          return result
+        }),
+        sample,
+      )
+      cache.set(property, nested)
+      return nested
+    },
+  })
+}
+
+function createV1Api(input: CompatibleInput): CompatibleApi {
+  const directory = (location?: { directory?: string }) => location?.directory ?? input.directory
+  const legacy = (location?: { directory?: string }) => input.legacy(directory(location))
+  const located = <T>(data: T, value?: { directory?: string }) => ({
+    location: {
+      directory: directory(value) ?? "",
+      project: { id: "", directory: directory(value) ?? "" },
+    },
+    data,
+  })
+
+  return {
+    ...input.current,
+    session: {
+      ...input.current.session,
+      async list(
+        value?: Parameters<ServerApi["session"]["list"]>[0],
+        options?: Parameters<ServerApi["session"]["list"]>[1],
+      ) {
+        if (!value?.directory && value?.search !== undefined) {
+          const result = await legacy().experimental.session.list(
+            {
+              roots: value.parentID === null ? true : undefined,
+              search: value.search,
+              limit: value.limit,
+            },
+            options,
+          )
+          return { data: (result.data ?? []).map(sessionInfo), cursor: {} }
+        }
+        const result = await legacy({ directory: value?.directory }).session.list({
+          directory: value?.directory,
+          roots: value?.parentID === null ? true : undefined,
+          search: value?.search,
+          limit: value?.limit,
+        })
+        return { data: (result.data ?? []).map(sessionInfo), cursor: {} }
+      },
+      async create(value?: Parameters<ServerApi["session"]["create"]>[0]) {
+        const result = await legacy(value?.location ?? undefined).session.create({
+          directory: directory(value?.location ?? undefined),
+        })
+        if (!result.data) throw new Error("Failed to create session")
+        return sessionInfo(result.data)
+      },
+      async get(value: Parameters<ServerApi["session"]["get"]>[0]) {
+        const result = await legacy().session.get(value)
+        if (!result.data) throw new Error(`Session not found: ${value.sessionID}`)
+        return sessionInfo(result.data)
+      },
+      async active() {
+        const result = await legacy().session.status()
+        return Object.fromEntries(
+          Object.entries(result.data ?? {}).flatMap(([sessionID, status]) =>
+            status.type === "idle" ? [] : [[sessionID, { type: "running" as const }]],
+          ),
+        )
+      },
+      async rename(value: Parameters<ServerApi["session"]["rename"]>[0] & LegacyLocation) {
+        await legacy(value).session.update({ sessionID: value.sessionID, title: value.title })
+      },
+      async archive(value: Parameters<ServerApi["session"]["archive"]>[0] & LegacyLocation) {
+        await legacy(value).session.update({ sessionID: value.sessionID, time: { archived: Date.now() } })
+      },
+      async remove(value: Parameters<ServerApi["session"]["remove"]>[0] & LegacyLocation) {
+        await legacy(value).session.delete(value)
+      },
+      async fork(value: Parameters<ServerApi["session"]["fork"]>[0]) {
+        const result = await legacy().session.fork(value)
+        if (!result.data) throw new Error("Failed to fork session")
+        return sessionInfo(result.data)
+      },
+      async interrupt(value: Parameters<ServerApi["session"]["interrupt"]>[0]) {
+        await legacy().session.abort(value)
+      },
+      async prompt(value: SessionPromptInput & LegacyPrompt) {
+        await legacy().session.promptAsync({
+          sessionID: value.sessionID,
+          messageID: value.id ?? undefined,
+          agent: value.agent,
+          model: value.model,
+          variant: value.variant,
+          parts: [
+            { type: "text", text: value.text },
+            ...(value.files ?? []).map((file) => ({
+              type: "file" as const,
+              mime: mime(file.uri),
+              url: file.uri,
+              filename: file.name,
+            })),
+            ...(value.agents ?? []).map((agent) => ({
+              type: "agent" as const,
+              name: agent.name,
+              source: agent.mention
+                ? { value: agent.mention.text, start: agent.mention.start, end: agent.mention.end }
+                : undefined,
+            })),
+          ],
+        })
+        return {
+          admittedSeq: 0,
+          id: value.id ?? "",
+          sessionID: value.sessionID,
+          timeCreated: Date.now(),
+          type: "user",
+          data: { text: value.text },
+          delivery: value.delivery ?? "steer",
+        }
+      },
+      async command(value: SessionCommandInput) {
+        await legacy().session.command({
+          sessionID: value.sessionID,
+          messageID: value.id ?? undefined,
+          command: value.command,
+          arguments: value.arguments ?? "",
+          agent: value.agent ?? undefined,
+          model: value.model ? `${value.model.providerID}/${value.model.id}` : undefined,
+          variant: value.model?.variant,
+          parts: value.files?.map((file) => ({
+            type: "file" as const,
+            mime: mime(file.uri),
+            url: file.uri,
+            filename: file.name,
+          })),
+        })
+        return {
+          admittedSeq: 0,
+          id: value.id ?? "",
+          sessionID: value.sessionID,
+          timeCreated: Date.now(),
+          type: "user",
+          data: { text: `/${value.command} ${value.arguments ?? ""}`.trim() },
+          delivery: value.delivery ?? "steer",
+        }
+      },
+      async shell(value: SessionShellInput & LegacyPrompt) {
+        await legacy().session.shell({
+          sessionID: value.sessionID,
+          command: value.command,
+          agent: value.agent,
+          model: value.model,
+        })
+      },
+      compact: async (value: SessionCompactInput & { model?: LegacyPrompt["model"] }) => {
+        if (!value.model) throw new Error("A model is required to compact a V1 session")
+        await legacy().session.summarize({
+          sessionID: value.sessionID,
+          providerID: value.model.providerID,
+          modelID: value.model.modelID,
+        })
+        return {
+          admittedSeq: 0,
+          id: value.id ?? "",
+          sessionID: value.sessionID,
+          timeCreated: Date.now(),
+          type: "compaction",
+        }
+      },
+      revert: {
+        stage: async (value: Parameters<ServerApi["session"]["revert"]["stage"]>[0]) => {
+          await legacy().session.revert(value)
+          return { messageID: value.messageID }
+        },
+        clear: async (value: Parameters<ServerApi["session"]["revert"]["clear"]>[0]) => {
+          await legacy().session.unrevert(value)
+        },
+        commit: input.current.session.revert.commit,
+      },
+    },
+    project: {
+      ...input.current.project,
+      async list() {
+        return ((await legacy().project.list()).data ?? []) as Project[]
+      },
+      async current(value?: Parameters<ServerApi["project"]["current"]>[0]) {
+        const result = await legacy(value?.location).project.current()
+        if (!result.data) throw new Error("Project not found")
+        return { id: result.data.id, directory: result.data.worktree } satisfies ProjectCurrent
+      },
+      async update(value: Parameters<ServerApi["project"]["update"]>[0]) {
+        const project = (await legacy().project.list()).data?.find((item) => item.id === value.projectID)
+        const result = await legacy({ directory: project?.worktree }).project.update({
+          ...value,
+          directory: project?.worktree,
+        })
+        if (!result.data) throw new Error(`Project not found: ${value.projectID}`)
+        return result.data as Project
+      },
+      async directories(value: Parameters<ServerApi["project"]["directories"]>[0]) {
+        const result = await legacy(value.location).worktree.list()
+        return (result.data ?? []).map((item) => ({ directory: item }))
+      },
+    },
+    path: {
+      ...input.current.path,
+      async get(value?: Parameters<ServerApi["path"]["get"]>[0]) {
+        const result = await legacy(value?.location).path.get()
+        if (!result.data) throw new Error("Path unavailable")
+        return result.data
+      },
+    },
+    vcs: {
+      ...input.current.vcs,
+      async get(value?: Parameters<ServerApi["vcs"]["get"]>[0]) {
+        const result = await legacy(value?.location).vcs.get()
+        return located({ branch: result.data?.branch, defaultBranch: undefined }, value?.location)
+      },
+      async status(value?: Parameters<ServerApi["vcs"]["status"]>[0]) {
+        const result = await legacy(value?.location).vcs.status()
+        return located(result.data ?? [], value?.location)
+      },
+      async diff(value: Parameters<ServerApi["vcs"]["diff"]>[0]) {
+        const result = await legacy(value.location).vcs.diff({
+          mode: value.mode === "working" ? "git" : value.mode,
+          context: value.context,
+        })
+        return located(
+          (result.data ?? []).map((file) => ({
+            file: file.file,
+            patch: file.patch ?? "",
+            additions: file.additions,
+            deletions: file.deletions,
+            status: file.status ?? "modified",
+          })),
+          value.location,
+        )
+      },
+    },
+    file: {
+      ...input.current.file,
+      async list(value?: Parameters<ServerApi["file"]["list"]>[0]) {
+        const result = await legacy(value?.location).file.list({ path: value?.path ?? "" })
+        return located(result.data ?? [], value?.location)
+      },
+      async find(value: Parameters<ServerApi["file"]["find"]>[0]) {
+        const result = await legacy(value.location).find.files({
+          query: value.query,
+          type: value.type,
+          limit: value.limit,
+        })
+        return located(
+          (result.data ?? []).map((path) => ({ path, type: value.type ?? "file" })),
+          value.location,
+        )
+      },
+    },
+    integration: {
+      ...input.current.integration,
+      async get(value: Parameters<ServerApi["integration"]["get"]>[0]) {
+        const methods = ((await legacy(value.location).provider.auth()).data?.[value.integrationID] ?? []).map(
+          (method, index) =>
+            method.type === "api"
+              ? { type: "key" as const, label: method.label }
+              : { type: "oauth" as const, id: String(index), label: method.label, prompts: method.prompts },
+        )
+        return located(
+          {
+            id: value.integrationID,
+            name: value.integrationID,
+            methods,
+            connections: [],
+          },
+          value.location,
+        )
+      },
+      connect: {
+        ...input.current.integration.connect,
+        key: async (value: Parameters<ServerApi["integration"]["connect"]["key"]>[0]) => {
+          await legacy(value.location).auth.set({
+            providerID: value.integrationID,
+            auth: { type: "api", key: value.key },
+          })
+        },
+      },
+      oauth: {
+        ...input.current.integration.oauth,
+        connect: async (value: Parameters<ServerApi["integration"]["oauth"]["connect"]>[0]) => {
+          const method = Number(value.methodID)
+          const result = await legacy(value.location).provider.oauth.authorize(
+            { providerID: value.integrationID, method, inputs: value.inputs },
+            { throwOnError: true },
+          )
+          if (!result.data) throw new Error("Failed to start OAuth authorization")
+          return located(
+            {
+              attemptID: `${value.integrationID}:${method}`,
+              url: result.data.url,
+              instructions: result.data.instructions,
+              mode: result.data.method,
+              time: { created: Date.now(), expires: Date.now() + 10 * 60 * 1000 },
+            },
+            value.location,
+          )
+        },
+        complete: async (value: Parameters<ServerApi["integration"]["oauth"]["complete"]>[0]) => {
+          const method = Number(value.attemptID.split(":").at(-1))
+          await legacy(value.location).provider.oauth.callback(
+            { providerID: value.integrationID, method, code: value.code },
+            { throwOnError: true },
+          )
+        },
+        status: async (value: Parameters<ServerApi["integration"]["oauth"]["status"]>[0]) => {
+          const method = Number(value.attemptID.split(":").at(-1))
+          await legacy(value.location).provider.oauth.callback(
+            { providerID: value.integrationID, method },
+            { throwOnError: true },
+          )
+          return located(
+            { status: "complete" as const, time: { created: Date.now(), expires: Date.now() } },
+            value.location,
+          )
+        },
+      },
+    },
+    pty: {
+      ...input.current.pty,
+      async shells(value?: Parameters<ServerApi["pty"]["shells"]>[0]) {
+        return located((await legacy(value?.location).pty.shells()).data ?? [], value?.location)
+      },
+      async list(value?: Parameters<ServerApi["pty"]["list"]>[0]) {
+        return located((await legacy(value?.location).pty.list()).data ?? [], value?.location)
+      },
+      async create(value?: Parameters<ServerApi["pty"]["create"]>[0]) {
+        const result = await legacy(value?.location).pty.create({
+          command: value?.command,
+          args: value?.args ? [...value.args] : undefined,
+          cwd: value?.cwd,
+          title: value?.title,
+          env: value?.env,
+        })
+        if (!result.data) throw new Error("Failed to create terminal")
+        return located(result.data, value?.location)
+      },
+      async get(value: Parameters<ServerApi["pty"]["get"]>[0]) {
+        const result = await legacy(value.location).pty.get({ ptyID: value.ptyID })
+        if (!result.data) throw new Error(`Terminal not found: ${value.ptyID}`)
+        return located(result.data, value.location)
+      },
+      async update(value: Parameters<ServerApi["pty"]["update"]>[0]) {
+        const result = await legacy(value.location).pty.update({
+          ptyID: value.ptyID,
+          title: value.title,
+          size: value.size,
+        })
+        if (!result.data) throw new Error(`Terminal not found: ${value.ptyID}`)
+        return located(result.data, value.location)
+      },
+      async remove(value: Parameters<ServerApi["pty"]["remove"]>[0]) {
+        await legacy(value.location).pty.remove({ ptyID: value.ptyID })
+      },
+      async connectToken(value: Parameters<ServerApi["pty"]["connectToken"]>[0]) {
+        const result = await legacy(value.location).pty.connectToken({ ptyID: value.ptyID })
+        if (!result.data) throw new Error(`Failed to connect terminal: ${value.ptyID}`)
+        return located(result.data, value.location)
+      },
+    },
+    permission: {
+      ...input.current.permission,
+      async reply(value: Parameters<ServerApi["permission"]["reply"]>[0]) {
+        await legacy().permission.respond({
+          sessionID: value.sessionID,
+          permissionID: value.requestID,
+          response: value.reply,
+        })
+      },
+    },
+    question: {
+      ...input.current.question,
+      async reply(value: Parameters<ServerApi["question"]["reply"]>[0]) {
+        await legacy().question.reply({
+          requestID: value.requestID,
+          answers: value.answers.map((answer) => [...answer]),
+        })
+      },
+      async reject(value: Parameters<ServerApi["question"]["reject"]>[0]) {
+        await legacy().question.reject({ requestID: value.requestID })
+      },
+    },
+  }
+}

packages/app/src/utils/server-health.test.ts

@@ -14,15 +14,45 @@ function abortFromInput(input: RequestInfo | URL, init?: RequestInit) {
 
 describe("checkServerHealth", () => {
   test("returns healthy response with version", async () => {
-    const fetch = (async () =>
-      new Response(JSON.stringify({ healthy: true, version: "1.2.3" }), {
+    let request: URL | undefined
+    const fetch = (async (input: RequestInfo | URL) => {
+      request = input instanceof URL ? input : new URL(input instanceof Request ? input.url : input)
+      return new Response(JSON.stringify({ healthy: true, version: "1.2.3" }), {
         status: 200,
         headers: { "content-type": "application/json" },
-      })) as unknown as typeof globalThis.fetch
+      })
+    }) as unknown as typeof globalThis.fetch
 
     const result = await checkServerHealth(server, fetch)
 
     expect(result).toEqual({ healthy: true, version: "1.2.3" })
+    expect(request?.pathname).toBe("/api/health")
+  })
+
+  test("falls back to the V1 health endpoint", async () => {
+    const paths: string[] = []
+    const fetch = (async (input: RequestInfo | URL) => {
+      const url = input instanceof URL ? input : new URL(input instanceof Request ? input.url : input)
+      paths.push(url.pathname)
+      if (url.pathname === "/api/health") return new Response(undefined, { status: 404 })
+      return Response.json({ healthy: true, version: "1.18.4" })
+    }) as unknown as typeof globalThis.fetch
+
+    expect(await checkServerHealth(server, fetch)).toEqual({ healthy: true, version: "1.18.4" })
+    expect(paths).toEqual(["/api/health", "/global/health"])
+  })
+
+  test("falls back when the current health response is malformed", async () => {
+    const paths: string[] = []
+    const fetch = (async (input: RequestInfo | URL) => {
+      const url = input instanceof URL ? input : new URL(input instanceof Request ? input.url : input)
+      paths.push(url.pathname)
+      if (url.pathname === "/api/health") return Response.json({})
+      return Response.json({ healthy: true, version: "1.18.4" })
+    }) as unknown as typeof globalThis.fetch
+
+    expect(await checkServerHealth(server, fetch)).toEqual({ healthy: true, version: "1.18.4" })
+    expect(paths).toEqual(["/api/health", "/global/health"])
   })
 
   test("allows slow servers thirty seconds by default", async () => {
@@ -142,7 +172,7 @@ describe("checkServerHealth", () => {
       retryDelayMs: 1,
     })
 
-    expect(count).toBe(3)
+    expect(count).toBe(6)
     expect(result).toEqual({ healthy: false })
   })
 })

packages/app/src/utils/server-health.ts

@@ -1,6 +1,7 @@
 import { usePlatform } from "@/context/platform"
 import { ServerConnection } from "@/context/server"
-import { createSdkForServer } from "./server"
+import { authTokenFromCredentials, createSdkForServer } from "./server"
+import { ClientError, OpenCode } from "@opencode-ai/client"
 import { Accessor, createEffect, onCleanup } from "solid-js"
 import { createStore, reconcile } from "solid-js/store"
 
@@ -61,6 +62,7 @@ function wait(ms: number, signal?: AbortSignal) {
 
 function retryable(error: unknown, signal?: AbortSignal) {
   if (signal?.aborted) return false
+  if (error instanceof ClientError) return error.reason === "Transport"
   if (!(error instanceof Error)) return false
   if (error.name === "AbortError" || error.name === "TimeoutError") return false
   if (error instanceof TypeError) return true
@@ -82,15 +84,31 @@ export async function checkServerHealth(
       .then(() => attempt(count + 1))
       .catch(() => ({ healthy: false }))
   }
-  const attempt = (count: number): Promise<ServerHealth> =>
-    createSdkForServer({
-      server,
+  const attempt = async (count: number): Promise<ServerHealth> => {
+    const current = await OpenCode.make({
+      baseUrl: server.url,
       fetch,
-      signal,
+      headers: server.password
+        ? {
+            Authorization: `Basic ${authTokenFromCredentials({ username: server.username, password: server.password })}`,
+          }
+        : undefined,
     })
+      .health.get({ signal })
+      .then((x) =>
+        typeof x.healthy === "boolean"
+          ? { data: { healthy: x.healthy, version: x.version } }
+          : { error: new Error("Invalid health response") },
+      )
+      .catch((error) => ({ error }))
+    if ("data" in current && current.data) return current.data
+    if (signal?.aborted) return { healthy: false }
+
+    return createSdkForServer({ server, fetch, signal })
       .global.health()
       .then((x) => (x.error ? next(count, x.error) : { healthy: x.data?.healthy === true, version: x.data?.version }))
       .catch((error) => next(count, error))
+  }
   return attempt(0).finally(() => timeout?.clear?.())
 }
 

packages/app/src/utils/server-protocol.test.ts

@@ -0,0 +1,40 @@
+import { describe, expect, test } from "bun:test"
+import { detectServerProtocol } from "./server-protocol"
+
+const server = { url: "http://localhost:4096" }
+const json = (value: unknown, status = 200) =>
+  new Response(JSON.stringify(value), { status, headers: { "content-type": "application/json" } })
+const mockFetch = (run: (input: string | URL | Request) => Promise<Response>) =>
+  Object.assign(run, { preconnect: globalThis.fetch.preconnect })
+
+describe("detectServerProtocol", () => {
+  test("prefers the legacy health endpoint when both API generations exist", async () => {
+    const fetcher = mockFetch((input) => {
+      const path = new URL(input instanceof Request ? input.url : input).pathname
+      if (path === "/global/health") return Promise.resolve(json({ healthy: true, version: "1.18.4" }))
+      return Promise.resolve(json({ healthy: true, version: "2.0.0", pid: 123 }))
+    })
+
+    expect(await detectServerProtocol(server, fetcher)).toBe("v1")
+  })
+
+  test("recognizes V2 health by its process identifier", async () => {
+    const fetcher = mockFetch((input) => {
+      const path = new URL(input instanceof Request ? input.url : input).pathname
+      if (path === "/global/health") return Promise.resolve(json({}, 404))
+      return Promise.resolve(json({ healthy: true, version: "2.0.0", pid: 123 }))
+    })
+
+    expect(await detectServerProtocol(server, fetcher)).toBe("v2")
+  })
+
+  test("recognizes the transitional V1 API health response", async () => {
+    const fetcher = mockFetch((input) => {
+      const path = new URL(input instanceof Request ? input.url : input).pathname
+      if (path === "/global/health") return Promise.resolve(json({}, 404))
+      return Promise.resolve(json({ healthy: true }))
+    })
+
+    expect(await detectServerProtocol(server, fetcher)).toBe("v1")
+  })
+})

packages/app/src/utils/server-protocol.ts

@@ -0,0 +1,35 @@
+import type { ServerConnection } from "@/context/server"
+import { authTokenFromCredentials } from "./server"
+
+export type ServerProtocol = "v1" | "v2"
+
+function headers(server: ServerConnection.HttpBase) {
+  if (!server.password) return
+  return {
+    Authorization: `Basic ${authTokenFromCredentials({ username: server.username, password: server.password })}`,
+  }
+}
+
+async function probe(server: ServerConnection.HttpBase, fetch: typeof globalThis.fetch, path: string) {
+  const response = await fetch(new URL(path, server.url), {
+    headers: headers(server),
+    signal: AbortSignal.timeout(5_000),
+  })
+  if (!response.ok || !response.headers.get("content-type")?.includes("application/json")) return
+  const value: unknown = await response.json()
+  if (!value || typeof value !== "object") return
+  return value
+}
+
+export async function detectServerProtocol(
+  server: ServerConnection.HttpBase,
+  fetch: typeof globalThis.fetch,
+): Promise<ServerProtocol> {
+  const legacy = await probe(server, fetch, "/global/health").catch(() => undefined)
+  if (legacy && "healthy" in legacy && legacy.healthy === true) return "v1"
+
+  const current = await probe(server, fetch, "/api/health").catch(() => undefined)
+  if (current && "pid" in current && typeof current.pid === "number") return "v2"
+  if (current && "healthy" in current && current.healthy === true) return "v1"
+  return "v2"
+}

packages/app/src/utils/server.ts

@@ -1,4 +1,5 @@
 import { createOpencodeClient } from "@opencode-ai/sdk/v2/client"
+import { OpenCode, type OpenCodeClient } from "@opencode-ai/client/promise"
 import type { ServerConnection } from "@/context/server"
 import { decode64 } from "@/utils/base64"
 
@@ -39,3 +40,23 @@ export function createSdkForServer({
     baseUrl: server.url,
   })
 }
+
+export function createApiForServer(input: {
+  server: ServerConnection.HttpBase
+  fetch?: typeof globalThis.fetch
+}): OpenCodeClient {
+  return OpenCode.make({
+    baseUrl: input.server.url,
+    fetch: input.fetch,
+    headers: input.server.password
+      ? {
+          Authorization: `Basic ${authTokenFromCredentials({
+            username: input.server.username,
+            password: input.server.password,
+          })}`,
+        }
+      : undefined,
+  })
+}
+
+export type ServerApi = OpenCodeClient

packages/cli/package.json

@@ -11,7 +11,6 @@
     "bin"
   ],
   "exports": {
-    "./daemon": "./src/daemon.ts",
     "./run": "./src/run/index.ts",
     "./server-process": "./src/server-process.ts"
   },
@@ -23,7 +22,7 @@
     "typecheck": "tsgo --noEmit"
   },
   "dependencies": {
-    "@agentclientprotocol/sdk": "0.21.0",
+    "@agentclientprotocol/sdk": "1.2.1",
     "@effect/platform-node": "catalog:",
     "@opencode-ai/client": "workspace:*",
     "@opencode-ai/plugin": "workspace:*",

packages/cli/src/acp/agent.ts

@@ -5,6 +5,7 @@ import {
   type AuthenticateRequest,
   type CancelNotification,
   type CloseSessionRequest,
+  type DeleteSessionRequest,
   type ForkSessionRequest,
   type InitializeRequest,
   type ListSessionsRequest,
@@ -13,7 +14,6 @@ import {
   type PromptRequest,
   type ResumeSessionRequest,
   type SetSessionConfigOptionRequest,
-  type SetSessionModelRequest,
   type SetSessionModeRequest,
 } from "@agentclientprotocol/sdk"
 import type { OpenCodeClient } from "@opencode-ai/client/promise"
@@ -28,12 +28,12 @@ export function create(client: OpenCodeClient, connection: AgentSideConnection)
     newSession: (params: NewSessionRequest) => run(service.newSession(params)),
     loadSession: (params: LoadSessionRequest) => run(service.loadSession(params)),
     listSessions: (params: ListSessionsRequest) => run(service.listSessions(params)),
+    deleteSession: (params: DeleteSessionRequest) => run(service.deleteSession(params)),
     resumeSession: (params: ResumeSessionRequest) => run(service.resumeSession(params)),
     closeSession: (params: CloseSessionRequest) => run(service.closeSession(params)),
     unstable_forkSession: (params: ForkSessionRequest) => run(service.forkSession(params)),
     setSessionConfigOption: (params: SetSessionConfigOptionRequest) => run(service.setSessionConfigOption(params)),
     setSessionMode: (params: SetSessionModeRequest) => run(service.setSessionMode(params)),
-    unstable_setSessionModel: (params: SetSessionModelRequest) => run(service.setSessionModel(params)),
     prompt: (params: PromptRequest) => run(service.prompt(params)),
     cancel: (params: CancelNotification) => run(service.cancel(params)),
   } satisfies Agent

packages/cli/src/acp/event.ts

@@ -28,7 +28,7 @@ export type TurnControl = {
 type ToolState = {
   readonly name: string
   input: ToolInput
-  structured: Record<string, unknown>
+  metadata: Record<string, unknown>
   content: ToolContent
 }
 
@@ -38,7 +38,7 @@ export type TurnStart =
   | { readonly type: "compaction"; readonly id: string }
 
 function emptyToolState(): ToolState {
-  return { name: "tool", input: {}, structured: {}, content: [] }
+  return { name: "tool", input: {}, metadata: {}, content: [] }
 }
 
 export async function streamTurn(input: {
@@ -47,7 +47,7 @@ export async function streamTurn(input: {
   readonly sessionID: string
   readonly cwd: string
   readonly start: TurnStart
-  readonly userMessageID?: string | null
+  readonly writeTextFile: boolean
   readonly submit: (signal: AbortSignal) => Promise<unknown>
   readonly control: TurnControl
 }): Promise<PromptResponse> {
@@ -120,7 +120,7 @@ export async function streamTurn(input: {
       }
       if (event.type === "session.tool.input.started") {
         assistantMessageID = event.data.assistantMessageID
-        tools.set(event.data.callID, { name: event.data.name, input: {}, structured: {}, content: [] })
+        tools.set(event.data.callID, { name: event.data.name, input: {}, metadata: {}, content: [] })
         await update({
           sessionUpdate: "tool_call",
           ...pendingToolCall({
@@ -151,15 +151,13 @@ export async function streamTurn(input: {
       if (event.type === "session.tool.progress") {
         const current = tools.get(event.data.callID)
         if (!current) continue
-        current.structured = event.data.structured
-        current.content = event.data.content
+        current.metadata = event.data.metadata
         await update({
           sessionUpdate: "tool_call_update",
           ...runningToolUpdate({
             toolCallId: event.data.callID,
             toolName: current.name,
             state: { input: current.input },
-            content: current.content,
             cwd: input.cwd,
           }),
         })
@@ -170,11 +168,12 @@ export async function streamTurn(input: {
         tools.delete(event.data.callID)
         await syncEditedFiles({
           connection: input.connection,
+          writeTextFile: input.writeTextFile,
           sessionID: input.sessionID,
           cwd: input.cwd,
           toolName: current.name,
           toolInput: current.input,
-          structured: event.data.structured,
+          metadata: event.data.metadata ?? {},
         }).catch(() => {})
         await update({
           sessionUpdate: "tool_call_update",
@@ -182,9 +181,8 @@ export async function streamTurn(input: {
             toolCallId: event.data.callID,
             toolName: current.name,
             input: current.input,
-            structured: event.data.structured,
+            metadata: event.data.metadata,
             content: event.data.content,
-            result: event.data.result,
           }),
         })
         continue
@@ -198,8 +196,8 @@ export async function streamTurn(input: {
             toolCallId: event.data.callID,
             toolName: current.name,
             input: current.input,
-            structured: current.structured,
-            content: current.content,
+            metadata: event.data.metadata ?? current.metadata,
+            content: event.data.content ?? current.content,
             error: event.data.error.message,
             cwd: input.cwd,
           }),
@@ -231,7 +229,7 @@ export async function streamTurn(input: {
       if (!started) {
         streamController.abort()
         await completed.catch(() => {})
-        return response(undefined, undefined, "interrupted", true, undefined, input.userMessageID)
+        return response(undefined, undefined, "interrupted", true, undefined)
       }
     }
     const terminal = await completed
@@ -246,7 +244,6 @@ export async function streamTurn(input: {
       terminal,
       control.cancelled,
       finish,
-      input.userMessageID,
     )
   } catch (error) {
     streamController.abort()
@@ -342,9 +339,8 @@ async function replayMessage(
               toolCallId: part.id,
               toolName: part.name,
               input: part.state.input,
-              structured: part.state.structured,
+              metadata: part.state.metadata,
               content: part.state.content,
-              result: part.state.result,
             }),
           },
         })
@@ -358,7 +354,6 @@ async function replayMessage(
               toolCallId: part.id,
               toolName: part.name,
               state: { input: part.state.input },
-              content: part.state.content,
               cwd,
             }),
           },
@@ -373,7 +368,7 @@ async function replayMessage(
               toolCallId: part.id,
               toolName: part.name,
               input: part.state.input,
-              structured: part.state.structured,
+              metadata: part.state.metadata,
               content: part.state.content,
               error: part.state.error.message,
               cwd,
@@ -400,7 +395,6 @@ function response(
   terminal: "succeeded" | "failed" | "interrupted",
   cancelled: boolean,
   finish: SessionMessageAssistant["finish"],
-  messageID: string | null | undefined,
 ): PromptResponse {
   const error = assistant?.error ?? executionError
   if (error?.type === "provider.auth") throw new ACPError.AuthRequiredError()
@@ -423,7 +417,7 @@ function response(
       }
     : undefined
   const stopReason = resolveStopReason({ terminal, cancelled, finish, error: error?.type })
-  return { stopReason, ...(usage ? { usage } : {}), ...(messageID ? { userMessageId: messageID } : {}), _meta: {} }
+  return { stopReason, ...(usage ? { usage } : {}), _meta: {} }
 }
 
 function resolveStopReason(input: {

packages/cli/src/acp/permission.ts

@@ -53,15 +53,16 @@ export async function replyPermission(input: {
 
 export async function syncEditedFiles(input: {
   readonly connection: Partial<Pick<AgentSideConnection, "writeTextFile">>
+  readonly writeTextFile: boolean
   readonly sessionID: string
   readonly cwd: string
   readonly toolName: string
   readonly toolInput: ToolInput
-  readonly structured: Readonly<Record<string, unknown>>
+  readonly metadata: Readonly<Record<string, unknown>>
 }) {
-  if (!input.connection.writeTextFile || toToolKind(input.toolName) !== "edit") return
-  const files = Array.isArray(input.structured.files)
-    ? input.structured.files.flatMap((file): string[] => {
+  if (!input.writeTextFile || !input.connection.writeTextFile || toToolKind(input.toolName) !== "edit") return
+  const files = Array.isArray(input.metadata.files)
+    ? input.metadata.files.flatMap((file): string[] => {
         if (!file || typeof file !== "object") return []
         const path = Reflect.get(file, "file")
         return typeof path === "string" ? [path] : []

packages/cli/src/acp/service.ts

@@ -16,6 +16,8 @@ import type {
   CancelNotification,
   CloseSessionRequest,
   CloseSessionResponse,
+  DeleteSessionRequest,
+  DeleteSessionResponse,
   ForkSessionRequest,
   ForkSessionResponse,
   InitializeRequest,
@@ -33,8 +35,6 @@ import type {
   ResumeSessionResponse,
   SetSessionConfigOptionRequest,
   SetSessionConfigOptionResponse,
-  SetSessionModelRequest,
-  SetSessionModelResponse,
   SetSessionModeRequest,
   SetSessionModeResponse,
 } from "@agentclientprotocol/sdk"
@@ -47,7 +47,8 @@ import { ACPError } from "./error"
 
 export const AuthMethodID = "opencode-login"
 
-type Connection = Pick<AgentSideConnection, "sessionUpdate" | "requestPermission">
+type Connection = Pick<AgentSideConnection, "sessionUpdate" | "requestPermission"> &
+  Partial<Pick<AgentSideConnection, "writeTextFile">>
 
 type Catalog = {
   readonly providers: ConfigOptionProvider[]
@@ -83,12 +84,12 @@ export interface Interface {
   newSession(input: NewSessionRequest): Promise<NewSessionResponse>
   loadSession(input: LoadSessionRequest): Promise<LoadSessionResponse>
   listSessions(input: ListSessionsRequest): Promise<ListSessionsResponse>
+  deleteSession(input: DeleteSessionRequest): Promise<DeleteSessionResponse>
   resumeSession(input: ResumeSessionRequest): Promise<ResumeSessionResponse>
   closeSession(input: CloseSessionRequest): Promise<CloseSessionResponse>
   forkSession(input: ForkSessionRequest): Promise<ForkSessionResponse>
   setSessionConfigOption(input: SetSessionConfigOptionRequest): Promise<SetSessionConfigOptionResponse>
   setSessionMode(input: SetSessionModeRequest): Promise<SetSessionModeResponse>
-  setSessionModel(input: SetSessionModelRequest): Promise<SetSessionModelResponse>
   prompt(input: PromptRequest): Promise<PromptResponse>
   cancel(input: CancelNotification): Promise<void>
 }
@@ -98,6 +99,7 @@ export function make(input: { readonly client: OpenCodeClient; readonly connecti
   const catalogs = new Map<string, Promise<Catalog>>()
   const registeredMcp = new Map<string, Set<string>>()
   const active = new Map<string, TurnControl>()
+  const capabilities = { writeTextFile: false }
 
   const catalog = (cwd: string) => {
     const cached = catalogs.get(cwd)
@@ -157,6 +159,7 @@ export function make(input: { readonly client: OpenCodeClient; readonly connecti
 
   return {
     initialize: async (params) => {
+      capabilities.writeTextFile = params.clientCapabilities?.fs?.writeTextFile === true
       const authMethod: AuthMethod = {
         description: "Run `opencode auth login` in the terminal",
         name: "Login with opencode",
@@ -173,7 +176,7 @@ export function make(input: { readonly client: OpenCodeClient; readonly connecti
           loadSession: true,
           mcpCapabilities: { http: true, sse: false },
           promptCapabilities: { embeddedContext: true, image: true },
-          sessionCapabilities: { close: {}, fork: {}, list: {}, resume: {} },
+          sessionCapabilities: { close: {}, delete: {}, fork: {}, list: {}, resume: {} },
         },
         authMethods: [authMethod],
         agentInfo: { name: "OpenCode", version: OPENCODE_VERSION },
@@ -216,6 +219,14 @@ export function make(input: { readonly client: OpenCodeClient; readonly connecti
         ...(page.cursor.next ? { nextCursor: page.cursor.next } : {}),
       }
     },
+    deleteSession: async (params) => {
+      await input.client.session.remove({ sessionID: params.sessionId }).catch((error) => {
+        if (!isSessionNotFoundError(error)) throw error
+      })
+      sessions.delete(params.sessionId)
+      registeredMcp.delete(params.sessionId)
+      return {}
+    },
     resumeSession: async (params) => {
       const session = await getSession(input.client, params.sessionId)
       const state = await attach(session, session.location.directory, params.mcpServers ?? [])
@@ -270,13 +281,6 @@ export function make(input: { readonly client: OpenCodeClient; readonly connecti
       await selectMode(input.client, await requireSession(params.sessionId), params.modeId)
       return {}
     },
-    setSessionModel: async (params) => {
-      const state = await requireSession(params.sessionId)
-      const selected = requireModel(state.catalog, params.modelId)
-      state.model = selected
-      await input.client.session.switchModel({ sessionID: state.id, model: selected })
-      return {}
-    },
     prompt: async (params) => {
       const state = await requireSession(params.sessionId)
       if (active.has(state.id)) {
@@ -295,7 +299,7 @@ export function make(input: { readonly client: OpenCodeClient; readonly connecti
         sessionID: state.id,
         cwd: state.cwd,
         start: prepared.start,
-        userMessageID: params.messageId,
+        writeTextFile: capabilities.writeTextFile,
         control,
         submit: (signal) => submitPrompt(input.client, state, prepared, signal),
       }).finally(() => {
@@ -479,6 +483,7 @@ async function registerMcpServers(
 
 function mcpConfig(server: McpServer) {
   if ("type" in server) {
+    if (server.type === "acp") throw new Error("MCP-over-ACP is not supported")
     return {
       type: "remote" as const,
       url: server.url,

packages/cli/src/acp/tool.ts

@@ -1,5 +1,6 @@
 import { isAbsolute, resolve } from "node:path"
 import type { ToolCall, ToolCallContent, ToolCallLocation, ToolCallUpdate, ToolKind } from "@agentclientprotocol/sdk"
+import { readDisplayText } from "@opencode-ai/tui/mini/tool"
 
 export type ToolInput = Record<string, unknown>
 export type ToolContent = ReadonlyArray<
@@ -100,11 +101,12 @@ export function completedToolUpdate(input: {
   readonly toolName: string
   readonly input: ToolInput
   readonly content: ToolContent
-  readonly structured: Readonly<Record<string, unknown>>
-  readonly result?: unknown
+  readonly metadata?: Readonly<Record<string, unknown>>
 }): ToolCallUpdate {
   const normalized = toolContent(input.content)
-  const read = input.toolName.toLocaleLowerCase() === "read" ? readDisplayText(input.structured) : undefined
+  // Read's model content is a JSON page envelope; show the clean text instead.
+  const firstText = input.content.find((part) => part.type === "text")
+  const read = input.toolName.toLocaleLowerCase() === "read" && firstText ? readDisplayText(firstText.text) : undefined
   const images = normalized.filter((part) => part.type === "content" && part.content.type === "image")
   const primary =
     read === undefined
@@ -128,8 +130,7 @@ export function completedToolUpdate(input: {
     status: "completed",
     content: [...primary, ...diff, ...images],
     rawOutput: {
-      structured: input.structured,
-      ...(input.result === undefined ? {} : { result: input.result }),
+      ...(input.metadata === undefined ? {} : { metadata: input.metadata }),
     },
   }
 }
@@ -138,8 +139,8 @@ export function errorToolUpdate(input: {
   readonly toolCallId: string
   readonly toolName: string
   readonly input: ToolInput
-  readonly content: ToolContent
-  readonly structured: Readonly<Record<string, unknown>>
+  readonly content?: ToolContent
+  readonly metadata?: Readonly<Record<string, unknown>>
   readonly error: string
   readonly cwd?: string
 }): ToolCallUpdate {
@@ -150,8 +151,11 @@ export function errorToolUpdate(input: {
     title: toolTitle(input.toolName, input.input, undefined),
     locations: toLocations(input.toolName, input.input, input.cwd),
     rawInput: rawInput(input.toolName, input.input, input.cwd),
-    content: [...toolContent(input.content), { type: "content", content: { type: "text", text: input.error } }],
-    rawOutput: { structured: input.structured, error: input.error },
+    content: [...toolContent(input.content ?? []), { type: "content", content: { type: "text", text: input.error } }],
+    rawOutput: {
+      ...(input.metadata === undefined ? {} : { metadata: input.metadata }),
+      error: input.error,
+    },
   }
 }
 
@@ -164,21 +168,6 @@ function toolContent(content: ToolContent): ToolCallContent[] {
   })
 }
 
-function readDisplayText(structured: Readonly<Record<string, unknown>>) {
-  if (typeof structured.content === "string") {
-    if (structured.type === "text-page" || structured.encoding === "utf8") return structured.content
-  }
-  if (!Array.isArray(structured.entries)) return undefined
-  return structured.entries
-    .flatMap((entry): string[] => {
-      if (typeof entry === "string") return [entry]
-      if (!entry || typeof entry !== "object") return []
-      const path = Reflect.get(entry, "path")
-      return typeof path === "string" ? [path] : []
-    })
-    .join("\n")
-}
-
 function toolTitle(toolName: string, input: ToolInput, fallback: string | undefined) {
   if (isShell(toolName)) return stringValue(input.command) ?? stringValue(input.cmd) ?? fallback ?? toolName
   return fallback || toolName

packages/cli/src/commands/commands.ts

@@ -32,6 +32,7 @@ export const Commands = Spec.make(typeof OPENCODE_CLI_NAME === "string" ? OPENCO
       Flag.withDescription("Session ID to continue"),
       Flag.optional,
     ),
+    prompt: Flag.string("prompt").pipe(Flag.withDescription("Prompt to use"), Flag.optional),
   },
   commands: [
     Spec.make("acp", { description: "Start an Agent Client Protocol server" }),
@@ -139,11 +140,11 @@ export const Commands = Spec.make(typeof OPENCODE_CLI_NAME === "string" ? OPENCO
           Flag.withDefault(false),
         ),
         replay: Flag.boolean("replay").pipe(
-          Flag.withDescription("Replay session history on resume and after resize"),
-          Flag.withDefault(true),
+          Flag.withDescription("Restore session history on resume and resize (disable with --no-replay)"),
+          Flag.optional,
         ),
         replayLimit: Flag.integer("replay-limit").pipe(
-          Flag.withDescription("Cap visible replay to the newest N messages"),
+          Flag.withDescription("Limit replay to the newest N messages (default: 200)"),
           Flag.optional,
         ),
         model: Flag.string("model").pipe(

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

@@ -55,7 +55,11 @@ export default Runtime.handler(Commands, (input) =>
             }
           : undefined,
       },
-      args: { continue: input.continue, sessionID: Option.getOrUndefined(input.session) },
+      args: {
+        continue: input.continue,
+        sessionID: Option.getOrUndefined(input.session),
+        prompt: Option.getOrUndefined(input.prompt),
+      },
       config: {
         path: config.path,
         get: () => runPromise(config.get()),

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

@@ -28,8 +28,8 @@ export default Runtime.handler(Commands.commands.mini, (input) =>
         model: Option.getOrUndefined(input.model),
         agent: Option.getOrUndefined(input.agent),
         prompt: Option.getOrUndefined(input.prompt),
-        replay: input.replay,
-        replayLimit: Option.getOrUndefined(input.replayLimit),
+        replay: Option.getOrUndefined(input.replay) ?? resolved.mini?.replay ?? true,
+        replayLimit: Option.getOrUndefined(input.replayLimit) ?? resolved.mini?.replay_limit,
         demo: input.demo,
         tuiConfig: resolved,
         config: {

packages/cli/src/mini.ts

@@ -2,7 +2,6 @@ import { Service, type Endpoint } from "@opencode-ai/client/effect/service"
 import { ClientError, OpenCode, type OpenCodeClient } from "@opencode-ai/client/promise"
 import type { MiniFrontendInput } from "@opencode-ai/tui/mini"
 import { setTimeout } from "node:timers/promises"
-import { waitForCatalogReady } from "./services/catalog"
 import { readStdin } from "./util/io"
 import { createMiniHost, INTERACTIVE_INPUT_ERROR, usingInteractiveStdin } from "./mini-host"
 import { parseSessionTargetModel, resolveSessionTarget, type SessionTargetPreparation } from "./session-target"
@@ -214,63 +213,7 @@ function parseModel(value?: string) {
 }
 
 function prepareTarget(requestedAgent?: string): SessionTargetPreparation {
-  return async (input) => {
-    if (input.model)
-      await waitForCatalogReady({
-        sdk: input.client,
-        directory: input.location.directory,
-        workspace: input.location.workspaceID,
-        model: { providerID: input.model.providerID, modelID: input.model.id },
-        signal: input.signal,
-      })
-    return {
-      model: input.model,
-      agent: requestedAgent
-        ? await validateAgent(
-            input.client,
-            input.location.directory,
-            input.location.workspaceID,
-            requestedAgent,
-            input.signal,
-          )
-        : input.agent,
-    }
-  }
-}
-
-async function validateAgent(
-  sdk: OpenCodeClient,
-  directory: string,
-  workspace: string | undefined,
-  name?: string,
-  signal?: AbortSignal,
-) {
-  if (!name) return
-  const deadline = Date.now() + 5_000
-  let agents: Awaited<ReturnType<OpenCodeClient["agent"]["list"]>> | undefined
-  while (Date.now() < deadline && !signal?.aborted) {
-    agents = await sdk.agent.list({ location: { directory, workspace } }, { signal }).catch((error) => {
-      if (signal && error instanceof ClientError && error.reason === "Transport") throw error
-      return undefined
-    })
-    const agent = agents?.data.find((item) => item.id === name)
-    if (agent?.mode === "subagent") {
-      warning(`agent "${name}" is a subagent, not a primary agent. Falling back to default agent`)
-      return
-    }
-    if (agent) return name
-    await setTimeout(25, undefined, { signal }).catch(() => {})
-  }
-  if (signal?.aborted) return
-  if (!agents) {
-    warning("failed to list agents. Falling back to default agent")
-    return
-  }
-  warning(`agent "${name}" not found. Falling back to default agent`)
-}
-
-function warning(message: string) {
-  process.stderr.write(`\x1b[93m\x1b[1m!\x1b[0m ${message}\n`)
+  return async (input) => ({ model: input.model, agent: requestedAgent ?? input.agent })
 }
 
 function fail(message: string): never {

packages/cli/src/node/plugin-runtime.promise.ts

@@ -10,6 +10,7 @@ import {
   Reference,
   Skill,
 } from "@opencode-ai/plugin/v2"
+import { Tool } from "@opencode-ai/plugin/v2/tool"
 
 const key = Symbol.for("opencode.plugin.v2.promise")
 ;(globalThis as typeof globalThis & { [key]?: unknown })[key] = {
@@ -23,4 +24,5 @@ const key = Symbol.for("opencode.plugin.v2.promise")
   Provider,
   Reference,
   Skill,
+  Tool,
 }

packages/cli/src/run/noninteractive.ts

@@ -10,7 +10,7 @@ import type {
 import { SessionMessage } from "@opencode-ai/schema/session-message"
 import { EOL } from "node:os"
 import { readFile } from "node:fs/promises"
-import { toolOutputText, type MiniToolPart } from "@opencode-ai/tui/mini/tool"
+import { nonEmptyToolContent, toolOutputText, type MiniToolPart } from "@opencode-ai/tui/mini/tool"
 import { UI } from "./ui"
 
 type Model = {
@@ -55,7 +55,7 @@ type ToolState = StartedPart & {
   raw?: string
   provider?: unknown
   providerState?: SessionMessageAssistantTool["providerState"]
-  structured: Record<string, JsonValue>
+  metadata: Record<string, JsonValue>
   content: LLMToolContent[]
 }
 
@@ -211,10 +211,17 @@ export async function runNonInteractivePrompt(input: Input) {
       }
       if (!promoted && event.type === "session.execution.failed") {
         prePromotionError = event.data.error
+        if (finalizing) return
         continue
       }
+      if (
+        !promoted &&
+        finalizing &&
+        (event.type === "session.execution.succeeded" || event.type === "session.execution.interrupted")
+      )
+        return
       if (!promoted) continue
-      if (finalizing) continue
+      if (finalizing && !event.type.startsWith("session.execution.")) continue
 
       if (event.type === "session.step.started") {
         const part = {
@@ -299,7 +306,7 @@ export async function runNonInteractivePrompt(input: Input) {
           assistantMessageID: event.data.assistantMessageID,
           tool: event.data.name,
           input: {},
-          structured: {},
+          metadata: {},
           content: [],
         })
         continue
@@ -327,7 +334,7 @@ export async function runNonInteractivePrompt(input: Input) {
           raw: current?.raw,
           provider: { executed: event.data.executed, state: event.data.state },
           providerState: event.data.state,
-          structured: {},
+          metadata: {},
           content: [],
         })
         continue
@@ -335,8 +342,7 @@ export async function runNonInteractivePrompt(input: Input) {
       if (event.type === "session.tool.progress") {
         const current = tools.get(toolKey(event.data.assistantMessageID, event.data.callID))
         if (current) {
-          current.structured = event.data.structured
-          current.content = event.data.content
+          current.metadata = event.data.metadata
         }
         continue
       }
@@ -353,9 +359,8 @@ export async function runNonInteractivePrompt(input: Input) {
           state: {
             status: "completed",
             input: current.input,
-            structured: event.data.structured,
+            metadata: event.data.metadata,
             content: event.data.content,
-            result: event.data.result,
           },
           time: { created: current.timestamp, ran: current.timestamp, completed: time },
         }
@@ -372,9 +377,8 @@ export async function runNonInteractivePrompt(input: Input) {
             output: toolOutputText(current.tool, event.data.content),
             title: current.tool,
             metadata: {
-              structured: event.data.structured,
+              metadata: event.data.metadata,
               content: event.data.content,
-              result: event.data.result,
               providerCall: current.provider,
               providerResult: { executed: event.data.executed, state: event.data.resultState },
               rawInput: current.raw,
@@ -391,6 +395,8 @@ export async function runNonInteractivePrompt(input: Input) {
         const key = toolKey(event.data.assistantMessageID, event.data.callID)
         const current = tools.get(key) ?? fallbackTool(event)
         const error = event.data.error.message
+        const metadata = event.data.metadata ?? current.metadata
+        const content = event.data.content ?? nonEmptyToolContent(current.content)
         const tool: SessionMessageAssistantTool = {
           type: "tool",
           id: event.data.callID,
@@ -401,10 +407,9 @@ export async function runNonInteractivePrompt(input: Input) {
           state: {
             status: "error",
             input: current.input,
-            structured: current.structured,
-            content: current.content,
+            metadata,
+            content,
             error: event.data.error,
-            result: event.data.result,
           },
           time: { created: current.timestamp, ran: current.timestamp, completed: time },
         }
@@ -420,7 +425,6 @@ export async function runNonInteractivePrompt(input: Input) {
             input: current.input,
             error,
             metadata: {
-              result: event.data.result,
               providerCall: current.provider,
               providerResult: { executed: event.data.executed, state: event.data.resultState },
               rawInput: current.raw,
@@ -432,15 +436,14 @@ export async function runNonInteractivePrompt(input: Input) {
         renderedTools.add(key)
         if (input.compatibility === "v1" && (permissionRejected || formCancelled)) continue
         if (!emit("tool_use", time, { part })) {
-          if (toolOutputText(current.tool, current.content).trim())
+          if (content && toolOutputText(current.tool, content).trim())
             await input.renderTool({
               ...tool,
               state: {
                 status: "completed",
                 input: current.input,
-                structured: current.structured,
-                content: current.content,
-                result: event.data.result,
+                metadata,
+                content,
               },
             })
           await input.renderToolError(tool)
@@ -588,14 +591,14 @@ export async function runNonInteractivePrompt(input: Input) {
                   input: item.state.input,
                   output: toolOutputText(item.name, item.state.content),
                   title: item.name,
-                  metadata: { structured: item.state.structured, content: item.state.content, result: item.state.result },
+                  metadata: { metadata: item.state.metadata, content: item.state.content },
                   time: { start: item.time.ran ?? item.time.created, end: item.time.completed ?? timestamp },
                 }
               : {
                   status: "error",
                   input: item.state.input,
                   error: item.state.error.message,
-                  metadata: { structured: item.state.structured, content: item.state.content, result: item.state.result },
+                  metadata: { metadata: item.state.metadata, content: item.state.content },
                   time: { start: item.time.ran ?? item.time.created, end: item.time.completed ?? timestamp },
                 },
         }
@@ -605,8 +608,16 @@ export async function runNonInteractivePrompt(input: Input) {
           await input.renderTool(item)
           continue
         }
-        if (toolOutputText(item.name, item.state.content).trim()) {
-          await input.renderTool({ ...item, state: { ...item.state, status: "completed" } })
+        if (item.state.content && toolOutputText(item.name, item.state.content).trim()) {
+          await input.renderTool({
+            ...item,
+            state: {
+              status: "completed",
+              input: item.state.input,
+              metadata: item.state.metadata,
+              content: item.state.content,
+            },
+          })
         }
         await input.renderToolError(item)
         UI.error(item.state.error.message)
@@ -618,7 +629,10 @@ export async function runNonInteractivePrompt(input: Input) {
         if (!emit("error", timestamp, { error: message.error })) UI.error(message.error.message)
       }
     }
-    return projected.found
+    return {
+      found: projected.found,
+      responded: projected.messages.some((message) => message.type === "assistant"),
+    }
   }
 
   const interrupt = () => {
@@ -708,9 +722,18 @@ export async function runNonInteractivePrompt(input: Input) {
     const waiting = input.client.session.wait({ sessionID: input.sessionID })
     await Promise.race([waiting, completed.then(() => waiting)])
     finalizing = true
-    controller.abort()
-    const found = await reconcile()
-    if (!found && !interrupted && !permissionRejected && !formCancelled && !emittedError) {
+    const projected = await reconcile()
+    if (
+      !projected.responded &&
+      !interrupted &&
+      !permissionRejected &&
+      !formCancelled &&
+      !emittedError &&
+      !prePromotionError
+    ) {
+      await completed
+    }
+    if (!projected.found && !interrupted && !permissionRejected && !formCancelled && !emittedError) {
       const error = prePromotionError ?? { type: "unknown", message: "Prompt was not promoted" }
       emittedError = true
       process.exitCode = 1
@@ -771,7 +794,7 @@ function fallbackTool(event: {
     assistantMessageID: event.data.assistantMessageID,
     tool: "tool",
     input: {},
-    structured: {},
+    metadata: {},
     content: [],
   }
 }

packages/cli/src/run/run.ts

@@ -5,7 +5,6 @@ import { open } from "node:fs/promises"
 import path from "node:path"
 import { readStdin } from "../util/io"
 import { ServerConnection } from "../services/server-connection"
-import { waitForCatalogReady } from "../services/catalog"
 import { parseSessionTargetModel, resolveSessionTarget } from "../session-target"
 import { toolInlineInfo } from "@opencode-ai/tui/mini/tool"
 import { runNonInteractivePrompt } from "./noninteractive"
@@ -95,9 +94,11 @@ async function execute(input: RunCommandInput, prepared: Prepared, endpoint: End
     prepare: async (next) => {
       const selected =
         next.model ??
-        (await client.model
-          .default({ location: { directory: next.location.directory, workspace: next.location.workspaceID } })
-          .then((result) => result.data))
+        (options.variant
+          ? await client.model
+              .default({ location: { directory: next.location.directory, workspace: next.location.workspaceID } })
+              .then((result) => result.data)
+          : undefined)
       const model = selected
         ? {
             providerID: selected.providerID,
@@ -107,25 +108,7 @@ async function execute(input: RunCommandInput, prepared: Prepared, endpoint: End
         : undefined
       if ((options.variant ?? explicit?.variant) && !model)
         throw new RunTargetError("Cannot select a variant before selecting a model", next.session?.id)
-      if (model) {
-        await waitForCatalogReady({
-          sdk: client,
-          directory: next.location.directory,
-          workspace: next.location.workspaceID,
-          model: { providerID: model.providerID, modelID: model.id },
-        })
-        const available = await client.model.list({
-          location: { directory: next.location.directory, workspace: next.location.workspaceID },
-        })
-        if (!available.data.some((item) => item.providerID === model.providerID && item.id === model.id))
-          throw new RunTargetError(`Model unavailable: ${model.providerID}/${model.id}`, next.session?.id)
-      }
-      return {
-        model,
-        agent: input.agent
-          ? await validateAgent(client, next.location.directory, next.location.workspaceID, input.agent)
-          : next.agent,
-      }
+      return { model, agent: next.agent }
     },
   }).catch((error) => {
     if (!(error instanceof RunTargetError)) throw error
@@ -190,28 +173,6 @@ export function parseRunModel(value?: string) {
   }
 }
 
-async function validateAgent(client: OpenCodeClient, directory: string, workspace: string | undefined, name?: string) {
-  if (!name) return
-  const agents = await client.agent
-    .list({ location: { directory, workspace } })
-    .then((result) => result.data)
-    .catch(() => undefined)
-  if (!agents) {
-    warning("failed to list agents. Falling back to default agent")
-    return
-  }
-  const agent = agents.find((item) => item.id === name)
-  if (!agent) {
-    warning(`agent "${name}" not found. Falling back to default agent`)
-    return
-  }
-  if (agent.mode === "subagent") {
-    warning(`agent "${name}" is a subagent, not a primary agent. Falling back to default agent`)
-    return
-  }
-  return name
-}
-
 async function prepareFile(input: string, directory: string, options: ExecutionOptions): Promise<FilePart> {
   const file = path.resolve(directory, input)
   const handle = await open(file, "r").catch(() => fail(`File not found: ${input}`))

packages/cli/src/services/catalog.ts

@@ -1,43 +0,0 @@
-import { ClientError, type OpenCodeClient } from "@opencode-ai/client/promise"
-
-// Location plugins initialize asynchronously, so explicit model selection must
-// wait for that exact model before prompt admission. The execution path owns
-// the authoritative error if readiness times out.
-export async function waitForCatalogReady(input: {
-  sdk: OpenCodeClient
-  directory: string
-  workspace?: string
-  model: { providerID: string; modelID: string }
-  timeoutMs?: number
-  signal?: AbortSignal
-}) {
-  const deadline = Date.now() + (input.timeoutMs ?? 5_000)
-  while (Date.now() < deadline && !input.signal?.aborted) {
-    const models = await input.sdk.model
-      .list(
-        { location: { directory: input.directory, workspace: input.workspace } },
-        { signal: input.signal },
-      )
-      .then((result) => result.data)
-      .catch((error) => {
-        if (input.signal && error instanceof ClientError && error.reason === "Transport") throw error
-        return undefined
-      })
-    if (models?.some((model) => model.providerID === input.model.providerID && model.id === input.model.modelID)) return
-    await wait(25, input.signal)
-  }
-}
-
-function wait(delay: number, signal?: AbortSignal) {
-  if (!signal) return new Promise<void>((resolve) => setTimeout(resolve, delay))
-  if (signal.aborted) return Promise.resolve()
-  return new Promise<void>((resolve) => {
-    const timer = setTimeout(done, delay)
-    signal.addEventListener("abort", done, { once: true })
-    function done() {
-      clearTimeout(timer)
-      signal?.removeEventListener("abort", done)
-      resolve()
-    }
-  })
-}

packages/cli/src/services/updater.ts

@@ -95,7 +95,7 @@ export const layer = Layer.effect(
       const response = yield* Effect.tryPromise({
         try: () =>
           fetch(
-            `https://registry.npmjs.org/${encodeURIComponent(packageName)}/${encodeURIComponent(OPENCODE_CHANNEL)}`,
+            `https://update.opencode.ai/api/${encodeURIComponent(channel)}/cli/npm`,
             { headers: { "User-Agent": `opencode/${OPENCODE_VERSION}` }, signal: AbortSignal.timeout(10_000) },
           ),
         catch: (cause) => new Error("Failed to check for updates", { cause }),

packages/cli/src/session-target.ts

@@ -74,7 +74,7 @@ export async function resolveSessionTarget(input: {
     session,
     location,
     model: prepared.model,
-    agent: prepared.agent,
+    agent: prepared.agent ?? session.agent,
     resume: selected !== undefined,
   }
 }

packages/cli/test/acp/event-behavior.test.ts

@@ -214,12 +214,11 @@ describe("acp event behavior", () => {
           }),
         )
         send(
-          durableEvent("session.tool.progress", {
+          ephemeralEvent("session.tool.progress", {
             sessionID: "ses_tools",
             assistantMessageID: "msg_tools",
             callID: "call_ok",
-            structured: { phase: 1 },
-            content: [{ type: "text", text: "working" }],
+            metadata: { phase: 1 },
           }),
         )
         send(
@@ -227,9 +226,8 @@ describe("acp event behavior", () => {
             sessionID: "ses_tools",
             assistantMessageID: "msg_tools",
             callID: "call_ok",
-            structured: { exit: 0 },
+            metadata: { exit: 0 },
             content: [{ type: "text", text: "done" }],
-            result: { code: 0 },
             executed: true,
           }),
         )
@@ -251,12 +249,11 @@ describe("acp event behavior", () => {
           }),
         )
         send(
-          durableEvent("session.tool.progress", {
+          ephemeralEvent("session.tool.progress", {
             sessionID: "ses_tools",
             assistantMessageID: "msg_tools",
             callID: "call_fail",
-            structured: { bytes: 0 },
-            content: [{ type: "text", text: "opening" }],
+            metadata: { bytes: 0 },
           }),
         )
         send(
@@ -265,6 +262,8 @@ describe("acp event behavior", () => {
             assistantMessageID: "msg_tools",
             callID: "call_fail",
             error: { type: "tool.error", message: "not found" },
+            metadata: { bytes: 0 },
+            content: [{ type: "text", text: "opening" }],
             executed: true,
           }),
         )
@@ -311,12 +310,10 @@ describe("acp event behavior", () => {
         locations: [{ path: resolve("/workspace", "sub") }],
         rawInput: { command: "printf done", workdir: "sub" },
       })
-      expect(updates[2]?.update).toMatchObject({
-        content: [{ type: "content", content: { type: "text", text: "working" } }],
-      })
+      expect(updates[2]?.update).not.toHaveProperty("content")
       expect(updates[3]?.update).toMatchObject({
         content: [{ type: "content", content: { type: "text", text: "done" } }],
-        rawOutput: { structured: { exit: 0 }, result: { code: 0 } },
+        rawOutput: { metadata: { exit: 0 } },
       })
       expect(updates[7]?.update).toMatchObject({
         kind: "read",
@@ -325,7 +322,7 @@ describe("acp event behavior", () => {
           { type: "content", content: { type: "text", text: "opening" } },
           { type: "content", content: { type: "text", text: "not found" } },
         ],
-        rawOutput: { structured: { bytes: 0 }, error: "not found" },
+        rawOutput: { metadata: { bytes: 0 }, error: "not found" },
       })
       expect(response.stopReason).toBe("end_turn")
     } finally {
@@ -377,7 +374,7 @@ describe("acp event behavior", () => {
         { type: "content", content: { type: "text", text: "done" } },
         { type: "content", content: { type: "image", mimeType: "image/png", data: "AAAA" } },
       ],
-      rawOutput: { structured: { exit: 0 }, result: { code: 0 } },
+      rawOutput: { metadata: { exit: 0 } },
     })
     expect(updates[8]?.update).toMatchObject({
       toolCallId: "call_running",
@@ -437,6 +434,7 @@ describe("acp event behavior", () => {
       sessionID: "ses_cancel",
       cwd: "/workspace",
       start: { type: "input", id: "input_cancel" },
+      writeTextFile: false,
       control,
       submit: async (signal) => {
         await fixture.client.session.prompt(
@@ -479,6 +477,7 @@ describe("acp event behavior", () => {
       sessionID: "ses_cancel_admission",
       cwd: "/workspace",
       start: { type: "input", id: "input_cancel_admission" },
+      writeTextFile: false,
       control,
       submit: (signal) =>
         fixture.client.session.prompt(
@@ -564,7 +563,7 @@ function turn(input: {
     sessionID: input.sessionID,
     cwd: "/workspace",
     start: { type: "input", id: input.inputID },
-    userMessageID: `client_${input.inputID}`,
+    writeTextFile: false,
     control: { cancelled: false, admission: new AbortController() },
     submit: (signal) =>
       input.fixture.client.session.prompt({ sessionID: input.sessionID, id: input.inputID, text: "hello" }, { signal }),
@@ -614,12 +613,11 @@ function replayFixtureMessages(): SessionMessageInfo[] {
           state: {
             status: "completed",
             input: { command: "printf done" },
-            structured: { exit: 0 },
+            metadata: { exit: 0 },
             content: [
               { type: "text", text: "done" },
               { type: "file", uri: "data:image/png;base64,AAAA", mime: "image/png", name: "image.png" },
             ],
-            result: { code: 0 },
           },
         },
         {
@@ -630,8 +628,7 @@ function replayFixtureMessages(): SessionMessageInfo[] {
           state: {
             status: "running",
             input: { command: "pwd" },
-            structured: {},
-            content: [{ type: "text", text: "/workspace" }],
+            metadata: {},
           },
         },
         {
@@ -642,7 +639,7 @@ function replayFixtureMessages(): SessionMessageInfo[] {
           state: {
             status: "error",
             input: { filePath: "/workspace/missing.ts" },
-            structured: { bytes: 0 },
+            metadata: { bytes: 0 },
             content: [{ type: "text", text: "partial" }],
             error: { type: "tool.error", message: "failed hard" },
           },
@@ -675,7 +672,7 @@ function replayToolMessage(id: string) {
         state: {
           status: "completed",
           input: { command: "printf done" },
-          structured: { exit: 0 },
+          metadata: { exit: 0 },
           content: [{ type: "text", text: "done" }],
         },
       },

packages/cli/test/acp/event.test.ts

@@ -85,7 +85,6 @@ test("acp prompt resolves after ordered turn updates", async () => {
 
   try {
     const id = "msg_prompt"
-    const userMessageID = "client-message"
     const response = await streamTurn({
       client,
       connection: {
@@ -97,7 +96,7 @@ test("acp prompt resolves after ordered turn updates", async () => {
       sessionID: "ses_test",
       cwd: "/workspace",
       start: { type: "input", id },
-      userMessageID,
+      writeTextFile: false,
       control: { cancelled: false, admission: new AbortController() },
       submit: () => client.session.prompt({ sessionID: "ses_test", id, text: "hi" }),
     })
@@ -112,7 +111,7 @@ test("acp prompt resolves after ordered turn updates", async () => {
         },
       },
     ])
-    expect(response).toMatchObject({ stopReason: "end_turn", userMessageId: userMessageID, usage: { totalTokens: 2 } })
+    expect(response).toMatchObject({ stopReason: "end_turn", usage: { totalTokens: 2 } })
   } finally {
     events?.close()
     await server.stop(true)

packages/cli/test/acp/initialize-auth.subprocess.test.ts

@@ -14,6 +14,7 @@ describe("acp initialize/auth subprocess", () => {
     expect(initialized.agentCapabilities?.mcpCapabilities?.sse).toBe(false)
     expect(initialized.agentCapabilities?.loadSession).toBe(true)
     expect(initialized.agentCapabilities?.sessionCapabilities?.close).toEqual({})
+    expect(initialized.agentCapabilities?.sessionCapabilities?.delete).toEqual({})
     expect(initialized.agentCapabilities?.sessionCapabilities?.fork).toEqual({})
     expect(initialized.agentCapabilities?.sessionCapabilities?.list).toEqual({})
     expect(initialized.agentCapabilities?.sessionCapabilities?.resume).toEqual({})

packages/cli/test/acp/lifecycle.subprocess.test.ts

@@ -1,5 +1,6 @@
 import type {
   CloseSessionResponse,
+  DeleteSessionResponse,
   ListSessionsResponse,
   LoadSessionResponse,
   ResumeSessionResponse,
@@ -60,6 +61,20 @@ describe("acp lifecycle subprocess", () => {
     expect(listed.sessions.some((item) => item.sessionId === session.sessionId)).toBe(true)
   }, 60_000)
 
+  test("delete capability and delete request", async () => {
+    await using fixture = await createAcpFixture()
+    const acp = fixture.spawn()
+    const initialized = await initialize(acp)
+    expect(initialized.agentCapabilities?.sessionCapabilities?.delete).toEqual({})
+    const session = await newSession(acp, fixture.home)
+
+    expect(
+      expectOk(await acp.request<DeleteSessionResponse>("session/delete", { sessionId: session.sessionId })),
+    ).toEqual({})
+    const listed = expectOk(await acp.request<ListSessionsResponse>("session/list", { cwd: fixture.home }))
+    expect(listed.sessions.some((item) => item.sessionId === session.sessionId)).toBe(false)
+  }, 60_000)
+
   test("resume capability advertisement", async () => {
     await using fixture = await createAcpFixture()
     const initialized = await initialize(fixture.spawn())

packages/cli/test/acp/permission-behavior.test.ts

@@ -4,6 +4,7 @@ import fs from "node:fs/promises"
 import os from "node:os"
 import path from "node:path"
 import { streamTurn } from "../../src/acp/event"
+import { syncEditedFiles } from "../../src/acp/permission"
 import { createSseFixture, durableEvent, ephemeralEvent, withTimeout } from "./sse-fixture"
 
 type SessionUpdateParams = Parameters<AgentSideConnection["sessionUpdate"]>[0]
@@ -12,6 +13,27 @@ type Connection = Pick<AgentSideConnection, "sessionUpdate" | "requestPermission
 type Fixture = ReturnType<typeof createSseFixture>
 
 describe("acp permission behavior", () => {
+  test("does not sync edits when writeTextFile was not advertised", async () => {
+    const writes: Parameters<AgentSideConnection["writeTextFile"]>[0][] = []
+
+    await syncEditedFiles({
+      connection: {
+        writeTextFile: async (input) => {
+          writes.push(input)
+          return {}
+        },
+      },
+      writeTextFile: false,
+      sessionID: "ses_no_write",
+      cwd: "/workspace",
+      toolName: "edit",
+      toolInput: { filePath: "/workspace/file.ts" },
+      metadata: {},
+    })
+
+    expect(writes).toEqual([])
+  })
+
   test("forwards allow-once and allow-always selections to the generated client", async () => {
     const permissionRequests: RequestPermissionRequest[] = []
     const fixture = createSseFixture({
@@ -171,7 +193,7 @@ describe("acp permission behavior", () => {
             sessionID: "ses_edit",
             assistantMessageID: "msg_edit",
             callID: "call_edit",
-            structured: { files: [{ file: "file.ts" }], replacements: 1 },
+            metadata: { files: [{ file: "file.ts" }], replacements: 1 },
             content: [{ type: "text", text: "edited" }],
             executed: true,
           }),
@@ -264,7 +286,7 @@ describe("acp permission behavior", () => {
             sessionID: "ses_patch",
             assistantMessageID: "msg_patch",
             callID: "call_patch",
-            structured: { files: [{ file: "first.ts" }, { file: "second.ts" }] },
+            metadata: { files: [{ file: "first.ts" }, { file: "second.ts" }] },
             content: [{ type: "text", text: "patched" }],
             executed: true,
           }),
@@ -465,6 +487,7 @@ function startTurn(fixture: Fixture, connection: Connection, sessionID: string,
     sessionID,
     cwd,
     start: { type: "input", id: inputID },
+    writeTextFile: true,
     control: { cancelled: false, admission: new AbortController() },
     submit: (signal) => fixture.client.session.prompt({ sessionID, id: inputID, text: "hello" }, { signal }),
   })

packages/cli/test/acp/service-directory.test.ts

@@ -1,6 +1,6 @@
 import { describe, expect, test } from "bun:test"
 import type { McpServer, SessionConfigOption } from "@agentclientprotocol/sdk"
-import { makeACPFixture, makeSession, secondModel, testModel } from "./service-fixture"
+import { makeACPFixture, makeSession, secondModel } from "./service-fixture"
 
 describe("acp service directory behavior", () => {
   test("creates sessions from a catalog shared by concurrent callers in the same cwd", async () => {
@@ -134,7 +134,6 @@ describe("acp service directory behavior", () => {
       configId: "mode",
       value: "plan",
     })
-    await fixture.service.setSessionModel({ sessionId: session.sessionId, modelId: "test/test-model/high" })
     await fixture.service.setSessionMode({ sessionId: session.sessionId, modeId: "build" })
 
     expect(currentValue(selectedModel, "model")).toBe("test/second-model")
@@ -148,7 +147,6 @@ describe("acp service directory behavior", () => {
     ).toEqual([
       { model: { providerID: "test", id: secondModel.id } },
       { model: { providerID: "test", id: secondModel.id, variant: "medium" } },
-      { model: { providerID: "test", id: testModel.id, variant: "high" } },
     ])
     expect(
       fixture.requests

packages/cli/test/acp/service-lifecycle.test.ts

@@ -225,6 +225,33 @@ describe("acp service lifecycle", () => {
       "/api/session/missing/interrupt",
     ])
   })
+
+  test("deletes sessions from backing and local storage", async () => {
+    await using fixture = makeACPFixture({
+      fetch(request) {
+        if (request.method === "POST" && request.path === "/api/session") {
+          return Response.json({ data: makeSession("ses_delete") })
+        }
+        if (request.method === "DELETE" && request.path === "/api/session/ses_delete") {
+          return new Response(null, { status: 204 })
+        }
+        return undefined
+      },
+    })
+    const session = await fixture.service.newSession({ cwd: "/workspace", mcpServers: [] })
+
+    expect(await fixture.service.deleteSession({ sessionId: session.sessionId })).toEqual({})
+    expect(fixture.requests).toContainEqual({
+      method: "DELETE",
+      path: "/api/session/ses_delete",
+      query: {},
+      body: undefined,
+    })
+    const missing = await fixture.service
+      .setSessionConfigOption({ sessionId: session.sessionId, configId: "effort", value: "high" })
+      .catch((error: unknown) => error)
+    expect(missing).toMatchObject({ _tag: "ACPSessionNotFoundError", sessionId: session.sessionId })
+  })
 })
 
 function currentValue(result: { readonly configOptions?: readonly SessionConfigOption[] | null }, id: string) {

packages/cli/test/acp/service-usage.test.ts

@@ -45,17 +45,14 @@ describe("acp service prompt routing and usage", () => {
 
     const commandResult = await fixture.service.prompt({
       sessionId: session.sessionId,
-      messageId: "client-command",
       prompt: [{ type: "text", text: "/review now" }],
     })
     const skillResult = await fixture.service.prompt({
       sessionId: session.sessionId,
-      messageId: "client-skill",
       prompt: [{ type: "text", text: "/verify" }],
     })
     const compactResult = await fixture.service.prompt({
       sessionId: session.sessionId,
-      messageId: "client-compact",
       prompt: [{ type: "text", text: "/compact" }],
     })
 
@@ -154,13 +151,11 @@ describe("acp service prompt routing and usage", () => {
 
     const response = await fixture.service.prompt({
       sessionId: session.sessionId,
-      messageId: "client-message",
       prompt: [{ type: "text", text: "hello" }],
     })
 
     expect(response).toEqual({
       stopReason: "end_turn",
-      userMessageId: "client-message",
       usage: {
         inputTokens: 100,
         outputTokens: 40,

packages/cli/test/acp/tool.test.ts

@@ -63,7 +63,7 @@ describe("acp tools", () => {
           { type: "file", mime: "image/png", name: "image.png", uri: `data:image/png;base64,${image}` },
           { type: "file", mime: "text/plain", name: "note.txt", uri: "data:text/plain;base64,bm90ZQ==" },
         ],
-        structured: {},
+        metadata: {},
       }).content,
     ).toEqual([
       {
@@ -93,7 +93,7 @@ describe("acp tools", () => {
           content: "created",
         },
         content: [{ type: "text", text: "wrote /tmp/file.ts" }],
-        structured: {},
+        metadata: {},
       }).content,
     ).toEqual([
       {
@@ -103,20 +103,22 @@ describe("acp tools", () => {
     ])
   })
 
-  test("uses clean structured read content instead of model-facing formatting", () => {
+  test("unwraps read's JSON page envelope instead of showing model-facing formatting", () => {
     expect(
       completedToolUpdate({
         toolCallId: "tool-read",
         toolName: "read",
         input: { path: "/tmp/file.ts" },
-        content: [{ type: "text", text: "<content>1: first\n2: second</content>" }],
-        structured: {
-          type: "text-page",
-          content: "first\nsecond",
-          mime: "text/plain",
-          offset: 1,
-          truncated: false,
-        },
+        content: [
+          {
+            type: "text",
+            text: JSON.stringify(
+              { type: "text-page", content: "first\nsecond", mime: "text/plain", offset: 1, truncated: false },
+              null,
+              2,
+            ),
+          },
+        ],
       }).content,
     ).toEqual([{ type: "content", content: { type: "text", text: "first\nsecond" } }])
 
@@ -125,13 +127,17 @@ describe("acp tools", () => {
         toolCallId: "tool-list",
         toolName: "read",
         input: { path: "/tmp" },
-        content: [],
-        structured: {
-          entries: [
-            { path: "a.ts", type: "file" },
-            { path: "src", type: "directory" },
-          ],
-        },
+        content: [
+          {
+            type: "text",
+            text: JSON.stringify({
+              entries: [
+                { path: "a.ts", type: "file" },
+                { path: "src", type: "directory" },
+              ],
+            }),
+          },
+        ],
       }).content,
     ).toEqual([{ type: "content", content: { type: "text", text: "a.ts\nsrc" } }])
   })
@@ -171,7 +177,7 @@ describe("acp tools", () => {
           newString: "after",
         },
         content: [{ type: "text", text: "Edit applied successfully." }],
-        structured: { output: "Edit applied successfully." },
+        metadata: { output: "Edit applied successfully." },
       }),
     ).toEqual({
       toolCallId: "tool-1",
@@ -189,7 +195,7 @@ describe("acp tools", () => {
         },
       ],
       rawOutput: {
-        structured: { output: "Edit applied successfully." },
+        metadata: { output: "Edit applied successfully." },
       },
     })
   })
@@ -209,7 +215,7 @@ describe("acp tools", () => {
     })
   })
 
-  test("builds completed raw output with structured data and optional result", () => {
+  test("builds completed raw output with optional metadata", () => {
     const attachments = [
       {
         type: "file",
@@ -225,12 +231,10 @@ describe("acp tools", () => {
         toolName: "read",
         input: {},
         content: [],
-        structured: { output: "done", metadata: { exit: 0 }, attachments },
-        result: "done",
+        metadata: { output: "done", metadata: { exit: 0 }, attachments },
       }).rawOutput,
     ).toEqual({
-      structured: { output: "done", metadata: { exit: 0 }, attachments },
-      result: "done",
+      metadata: { output: "done", metadata: { exit: 0 }, attachments },
     })
 
     expect(
@@ -239,9 +243,8 @@ describe("acp tools", () => {
         toolName: "read",
         input: {},
         content: [],
-        structured: { output: "done" },
       }).rawOutput,
-    ).toEqual({ structured: { output: "done" } })
+    ).toEqual({})
   })
 
   test("extracts image attachments only from data URLs", () => {
@@ -255,7 +258,7 @@ describe("acp tools", () => {
           { type: "file", mime: "image/png", uri: "https://example.com/image.png" },
           { type: "file", mime: "text/plain", uri: "data:text/plain;base64,BBBB" },
         ],
-        structured: {},
+        metadata: {},
       }).content,
     ).toEqual([
       {
@@ -272,7 +275,7 @@ describe("acp tools", () => {
         toolName: "read",
         input: { filePath: "/tmp/a" },
         content: [{ type: "text", text: "partial output" }],
-        structured: { path: "/tmp/a" },
+        metadata: { path: "/tmp/a" },
         error: "failed",
       }),
     ).toEqual({
@@ -286,7 +289,7 @@ describe("acp tools", () => {
         { type: "content", content: { type: "text", text: "partial output" } },
         { type: "content", content: { type: "text", text: "failed" } },
       ],
-      rawOutput: { structured: { path: "/tmp/a" }, error: "failed" },
+      rawOutput: { metadata: { path: "/tmp/a" }, error: "failed" },
     })
   })
 })

packages/cli/test/config.test.ts

@@ -131,7 +131,7 @@ test("updates a config draft while preserving JSONC comments", async () => {
         const service = yield* Config.Service
         return yield* service.update((draft) => {
           draft.prompt = { paste: "compact" }
-          draft.mini = { thinking: "hide", shell_output: "hide", turn_summary: "hide", mono: true }
+          draft.mini = { thinking: "hide", shell_output: "hide", turn_summary: "hide", splash: "hide", mono: true }
         })
       }),
     )
@@ -139,7 +139,7 @@ test("updates a config draft while preserving JSONC comments", async () => {
     expect(config).toEqual({
       animations: true,
       prompt: { paste: "compact" },
-      mini: { thinking: "hide", shell_output: "hide", turn_summary: "hide", mono: true },
+      mini: { thinking: "hide", shell_output: "hide", turn_summary: "hide", splash: "hide", mono: true },
     })
     expect(await Bun.file(path.join(directory, "cli.json")).text()).toContain("// Keep this comment")
   } finally {

packages/cli/test/drive/mini-interactive.drive.mjs

@@ -16,7 +16,30 @@ export default defineScript({
       const preload = Bun.resolveSync("@opentui/solid/preload", path.join(root, "packages/cli"))
       const session = `mini-stage2-${process.pid}`
       const snapshots = path.join(artifacts, "mini-stage2")
-      yield* Effect.promise(() => mkdir(snapshots, { recursive: true }))
+      const explicitDirectory = path.join(artifacts, "explicit-model")
+      yield* Effect.promise(() => Promise.all([snapshots, explicitDirectory].map((dir) => mkdir(dir, { recursive: true }))))
+      /** @param {string} directory @param {string | undefined} model */
+      const mini = (directory, model) => [
+        "env",
+        `PWD=${directory}`,
+        `OPENCODE_PASSWORD=${registration.password}`,
+        `OPENCODE_CONFIG_DIR=${path.join(artifacts, "files/.opencode")}`,
+        `OPENCODE_TEST_HOME=${artifacts}`,
+        `XDG_CACHE_HOME=${path.join(artifacts, "home/.cache")}`,
+        `XDG_CONFIG_HOME=${path.join(artifacts, "home/.config")}`,
+        `XDG_DATA_HOME=${path.join(artifacts, "logs")}`,
+        `XDG_STATE_HOME=${path.join(artifacts, "home/.local/state")}`,
+        "OPENCODE_DISABLE_AUTOUPDATE=1",
+        "OPENCODE_DIRECT_TRACE=1",
+        process.execPath,
+        "--conditions=browser",
+        `--preload=${preload}`,
+        path.join(root, "packages/cli/src/index.ts"),
+        "mini",
+        "--server",
+        registration.url,
+        ...(model ? ["--model", model] : []),
+      ]
 
       yield* llm.queue(
         Llm.toolCall({
@@ -42,26 +65,7 @@ export default defineScript({
               "-y",
               "30",
               "--",
-              "env",
-              `PWD=${path.join(artifacts, "files")}`,
-              `OPENCODE_PASSWORD=${registration.password}`,
-              `OPENCODE_CONFIG_DIR=${path.join(artifacts, "files/.opencode")}`,
-              `OPENCODE_TEST_HOME=${artifacts}`,
-              `XDG_CACHE_HOME=${path.join(artifacts, "home/.cache")}`,
-              `XDG_CONFIG_HOME=${path.join(artifacts, "home/.config")}`,
-              `XDG_DATA_HOME=${path.join(artifacts, "logs")}`,
-              `XDG_STATE_HOME=${path.join(artifacts, "home/.local/state")}`,
-              "OPENCODE_DISABLE_AUTOUPDATE=1",
-              "OPENCODE_DIRECT_TRACE=1",
-              process.execPath,
-              "--conditions=browser",
-              `--preload=${preload}`,
-              path.join(root, "packages/cli/src/index.ts"),
-              "mini",
-              "--server",
-              registration.url,
-              "--model",
-              "simulation/gpt-sim-model",
+              ...mini(path.join(artifacts, "files"), undefined),
             ]),
           ),
         )
@@ -72,7 +76,16 @@ export default defineScript({
         if (first.includes("drive mini response complete"))
           throw new Error("response rendered before prompt submission")
 
-        yield* Effect.promise(() => waitForPane(session, "Simulated Model", 15_000))
+        yield* Effect.promise(() => waitForPane(session, "Default model", 15_000))
+        yield* Effect.promise(() => tmux(["send-keys", "-t", session, "C-p"]))
+        yield* Effect.promise(() => waitForVisiblePane(session, "Commands"))
+        yield* Effect.promise(() => tmux(["send-keys", "-t", session, "-l", "model"]))
+        yield* Effect.promise(() => waitForVisiblePane(session, "Switch model"))
+        yield* Effect.promise(() => tmux(["send-keys", "-H", "-t", session, "0d"]))
+        yield* Effect.promise(() => waitForVisiblePane(session, "Select model"))
+        yield* Effect.promise(() => waitForVisiblePane(session, "Simulated Model", 15_000))
+        yield* Effect.promise(() => tmux(["send-keys", "-t", session, "Escape"]))
+        yield* Effect.promise(() => waitForVisiblePane(session, "Ask anything..."))
         yield* Effect.promise(() => tmux(["send-keys", "-t", session, "-l", "exercise the mini frontend"]))
         yield* Effect.sleep(100)
         yield* Effect.promise(() => tmux(["send-keys", "-H", "-t", session, "0d"]))
@@ -134,7 +147,7 @@ export default defineScript({
         yield* Effect.promise(() => tmux(["send-keys", "-H", "-t", session, "0d"]))
         yield* Effect.promise(() => waitForPane(session, "$ sleep 10"))
         yield* Effect.promise(() => tmux(["send-keys", "-t", session, "Escape"]))
-        const armed = yield* Effect.promise(() => waitForPane(session, "again to interrupt"))
+        const armed = yield* Effect.promise(() => waitForPane(session, "esc again"))
         yield* Effect.promise(() => Bun.write(path.join(snapshots, "04-interrupt-armed.txt"), armed))
         yield* Effect.promise(() => tmux(["send-keys", "-t", session, "Escape"]))
         const interrupted = yield* Effect.promise(() => waitForPane(session, "Step interrupted", 10_000))
@@ -144,7 +157,7 @@ export default defineScript({
           if (!(await paneAlive(session))) throw new Error("Mini exited while interrupting an active turn")
         })
         yield* Effect.promise(() => tmux(["send-keys", "-t", session, "C-c"]))
-        yield* Effect.promise(() => waitForPane(session, "Press ctrl+c again to exit"))
+        yield* Effect.promise(() => waitForPane(session, "EXIT  Press ctrl+"))
         yield* Effect.promise(() => tmux(["send-keys", "-t", session, "C-c"]))
         yield* Effect.promise(() => waitForDeadPane(session))
         const status = yield* Effect.promise(() => paneDeadStatus(session))
@@ -153,6 +166,75 @@ export default defineScript({
         if (!exited.includes("Continue") || !exited.includes("opencode mini -s"))
           throw new Error("Mini exit splash was not rendered before teardown")
         yield* Effect.promise(() => Bun.write(path.join(snapshots, "06-exit-teardown.txt"), exited))
+
+        yield* Effect.promise(() => tmux(["clear-history", "-t", session]))
+        yield* Effect.promise(() =>
+          tmux([
+            "respawn-pane",
+            "-k",
+            "-t",
+            session,
+            "--",
+            ...mini(explicitDirectory, "simulation/gpt-sim-model"),
+          ]),
+        )
+        const explicitModel = yield* Effect.promise(() => waitForPane(session, "Simulated Model", 15_000))
+        yield* Effect.promise(() => Bun.write(path.join(snapshots, "07-explicit-model.txt"), explicitModel))
+        yield* Effect.promise(() => tmux(["send-keys", "-t", session, "C-c"]))
+        yield* Effect.promise(() => waitForPane(session, "EXIT  Press ctrl+"))
+        yield* Effect.promise(() => tmux(["send-keys", "-t", session, "C-c"]))
+        yield* Effect.promise(() => waitForDeadPane(session))
+        if ((yield* Effect.promise(() => paneDeadStatus(session))) !== 0)
+          throw new Error("Explicit-model Mini did not exit cleanly")
+
+        yield* Effect.promise(async () => {
+          for (const failure of [
+            {
+              args: ["--model", "simulation/definitely-missing"],
+              capture: "08-unavailable-model.txt",
+              expected: "Model unavailable: simulation/definitely-missing",
+            },
+            {
+              args: ["--agent", "definitely-missing"],
+              capture: "09-unavailable-agent.txt",
+              expected: 'Agent not found: "definitely-missing"',
+            },
+          ]) {
+            const child = Bun.spawn(
+              [
+                process.execPath,
+                path.join(root, "packages/cli/src/index.ts"),
+                "run",
+                "--server",
+                registration.url,
+                ...failure.args,
+                "optimistic selection check",
+              ],
+              {
+                cwd: path.join(root, "packages/cli"),
+                env: {
+                  ...process.env,
+                  PWD: path.join(artifacts, "files"),
+                  OPENCODE_PASSWORD: registration.password,
+                  OPENCODE_CONFIG_DIR: path.join(artifacts, "files/.opencode"),
+                  OPENCODE_DISABLE_AUTOUPDATE: "1",
+                },
+                stdin: "ignore",
+                stdout: "pipe",
+                stderr: "pipe",
+              },
+            )
+            const [exitCode, stdout, stderr] = await Promise.all([
+              child.exited,
+              new Response(child.stdout).text(),
+              new Response(child.stderr).text(),
+            ])
+            await Bun.write(path.join(snapshots, failure.capture), stdout + stderr)
+            if (exitCode !== 1) throw new Error(`${failure.expected} run exited with status ${exitCode}`)
+            if (!stderr.includes(failure.expected))
+              throw new Error(`Selection failure was not diagnosed by execution: ${stderr}`)
+          }
+        })
       })
 
       yield* journey.pipe(Effect.ensuring(Effect.promise(() => tmux(["kill-session", "-t", session], true))))
@@ -188,6 +270,19 @@ function captureVisiblePane(session) {
   return tmux(["capture-pane", "-p", "-t", session])
 }
 
+/** @param {string} session @param {string} text @param {number} [timeout] */
+async function waitForVisiblePane(session, text, timeout = 5_000) {
+  const deadline = Date.now() + timeout
+  let last = ""
+  while (Date.now() < deadline) {
+    last = await captureVisiblePane(session)
+    if (last.includes(text)) return last
+    if (!(await paneAlive(session))) throw new Error(`Mini exited before rendering ${JSON.stringify(text)}:\n${last}`)
+    await Bun.sleep(50)
+  }
+  throw new Error(`Timed out waiting for visible ${JSON.stringify(text)}:\n${last}`)
+}
+
 /** @param {string} session */
 async function paneAlive(session) {
   return (await tmux(["display-message", "-p", "-t", session, "#{pane_dead}"], true)).trim() === "0"

packages/cli/test/import-boundaries.test.ts

@@ -18,10 +18,17 @@ describe("CLI frontend import boundaries", () => {
   test("exposes only the intentional package entrypoints", async () => {
     const run = await import("@opencode-ai/cli/run")
     const mini = await import("@opencode-ai/tui/mini")
+    const tool = await import("@opencode-ai/tui/mini/tool")
     const cli = await Bun.file(path.join(root, "packages/cli/package.json")).json()
 
     expect(Object.keys(run).sort()).toEqual(["runNonInteractive", "runV1Bridge"])
     expect(Object.keys(mini).sort()).toEqual(["runMiniFrontend"])
+    expect(Object.keys(tool).sort()).toEqual([
+      "nonEmptyToolContent",
+      "readDisplayText",
+      "toolInlineInfo",
+      "toolOutputText",
+    ])
     expect(Object.keys(cli.exports).filter((key) => key === "./mini" || key.startsWith("./mini/"))).toEqual([])
   })
 

packages/cli/test/mini.test.ts

@@ -121,11 +121,12 @@ describe("mini command", () => {
     expect(result.stdout).toContain("run        Run OpenCode with a message")
   })
 
-  test("exposes run without legacy attach or command modes", async () => {
+  test("exposes run without legacy interactive, attach, or command modes", async () => {
     const result = await cli(["run", "--help"])
 
     expect(result.exitCode).toBe(0)
     expect(result.stdout).toContain("--server string")
+    expect(result.stdout).not.toContain("--interactive")
     expect(result.stdout).not.toContain("--variant")
     expect(result.stdout).not.toContain("--attach")
     expect(result.stdout).not.toContain("--command")
@@ -138,32 +139,47 @@ describe("mini command", () => {
     expect(result.stderr).not.toContain("You must provide a message")
   })
 
-  test("preserves a run failure exit code", async () => {
-    let modelRequests = 0
+  test("passes explicit selections to session creation without catalog preflight", async () => {
+    const requests: string[] = []
+    let session: unknown
     const server = Bun.serve({
       port: 0,
-      fetch(request) {
+      async fetch(request) {
         const url = new URL(request.url)
+        requests.push(url.pathname)
         if (url.pathname === "/api/health")
           return Response.json({ healthy: true, version: OPENCODE_VERSION, pid: process.pid })
         if (url.pathname === "/api/location")
           return Response.json({ directory: process.cwd(), project: { id: "global", directory: process.cwd() } })
-        if (url.pathname === "/api/model") {
-          modelRequests++
-          return Response.json({
-            location: { directory: process.cwd(), project: { id: "global", directory: process.cwd() } },
-            data: modelRequests === 1 ? [{ id: "missing", providerID: "definitely" }] : [],
-          })
+        if (url.pathname === "/api/session") {
+          session = await request.json()
+          return new Response("boom", { status: 500 })
         }
         return new Response(undefined, { status: 404 })
       },
     })
 
     try {
-      const result = await cli(["run", "--server", server.url.toString(), "--model", "definitely/missing", "hi"])
+      const result = await cli([
+        "run",
+        "--server",
+        server.url.toString(),
+        "--model",
+        "definitely/missing",
+        "--agent",
+        "definitely-missing",
+        "hi",
+      ])
 
       expect(result.exitCode).toBe(1)
-      expect(result.stderr).toContain("Model unavailable: definitely/missing")
+      expect(result.stderr).toContain("UnexpectedStatus")
+      expect(session).toMatchObject({
+        agent: "definitely-missing",
+        model: { providerID: "definitely", id: "missing" },
+      })
+      expect(requests).not.toContain("/api/model")
+      expect(requests).not.toContain("/api/agent")
+      expect(requests).not.toContain("/api/location/wait")
     } finally {
       server.stop(true)
     }
@@ -197,11 +213,16 @@ describe("mini command", () => {
 
     expect(result.exitCode).toBe(0)
     expect(result.stdout).toContain("--server string")
+    expect(result.stdout).toContain("--prompt string")
+    expect(result.stdout).toContain("--replay")
+    expect(result.stdout).toContain("disable with --no-replay")
+    expect(result.stdout).toContain("--replay-limit integer")
+    expect(result.stdout).toContain("Limit replay to the newest N messages (default: 200)")
     expect(result.stdout).not.toContain("SUBCOMMANDS")
   })
 
   test("routes local and explicit-server invocations into mini", async () => {
-    for (const args of [["mini"], ["mini", "--server", "http://127.0.0.1:1"]]) {
+    for (const args of [["mini"], ["mini", "--no-replay"], ["mini", "--server", "http://127.0.0.1:1"]]) {
       const result = await cli(args)
 
       expect(result.exitCode).toBe(1)

packages/cli/test/run/noninteractive.test.ts

@@ -130,25 +130,25 @@ function failedTool(inputID: string): V2Event[] {
       id: "evt_failed_tool_progress",
       created: 3,
       type: "session.tool.progress",
-      durable: { aggregateID: "ses_1", seq: 3, version: 1 },
       data: {
         sessionID: "ses_1",
         assistantMessageID: "msg_failed_tool",
         callID: "call_failed_tool",
-        structured: { checkpoint: 1 },
-        content: [{ type: "text", text: "partial output" }],
+        metadata: { checkpoint: 1 },
       },
     },
     {
       id: "evt_failed_tool_terminal",
       created: 4,
       type: "session.tool.failed",
-      durable: { aggregateID: "ses_1", seq: 4, version: 1 },
+      durable: { aggregateID: "ses_1", seq: 4, version: 2 },
       data: {
         sessionID: "ses_1",
         assistantMessageID: "msg_failed_tool",
         callID: "call_failed_tool",
         error: { type: "unknown", message: "tool failed" },
+        metadata: { checkpoint: 1 },
+        content: [{ type: "text", text: "partial output" }],
         executed: true,
       },
     },
@@ -156,6 +156,53 @@ function failedTool(inputID: string): V2Event[] {
   ]
 }
 
+function successfulGrep(inputID: string): V2Event[] {
+  const text = "Found 2 matches\n/src/a.ts:\n  Line 1: needle\n/src/b.ts:\n  Line 2: needle"
+  return [
+    prompted(inputID),
+    {
+      id: "evt_grep_input",
+      created: 1,
+      type: "session.tool.input.started",
+      durable: { aggregateID: "ses_1", seq: 1, version: 1 },
+      data: {
+        sessionID: "ses_1",
+        assistantMessageID: "msg_grep",
+        callID: "call_grep",
+        name: "grep",
+      },
+    },
+    {
+      id: "evt_grep_called",
+      created: 2,
+      type: "session.tool.called",
+      durable: { aggregateID: "ses_1", seq: 2, version: 1 },
+      data: {
+        sessionID: "ses_1",
+        assistantMessageID: "msg_grep",
+        callID: "call_grep",
+        input: { pattern: "needle" },
+        executed: true,
+      },
+    },
+    {
+      id: "evt_grep_success",
+      created: 3,
+      type: "session.tool.success",
+      durable: { aggregateID: "ses_1", seq: 3, version: 2 },
+      data: {
+        sessionID: "ses_1",
+        assistantMessageID: "msg_grep",
+        callID: "call_grep",
+        metadata: { matches: 2 },
+        content: [{ type: "text", text }],
+        executed: false,
+      },
+    },
+    settled(),
+  ]
+}
+
 // Runs one non-interactive prompt against a mocked SDK. `turn` produces the
 // live events the prompt admission triggers, keyed by the generated message ID.
 async function run(input: {
@@ -169,6 +216,7 @@ async function run(input: {
   renderToolError?: (part: SessionMessageAssistantTool) => Promise<void>
   messages?: (inputID: string) => SessionMessageInfo[]
   wait?: () => Promise<void>
+  terminalDelay?: number
 }) {
   const sdk = OpenCode.make({ baseUrl: "https://opencode.test" })
   const values: V2Event[] = [{ id: "evt_connected", type: "server.connected", data: {} }]
@@ -183,7 +231,10 @@ async function run(input: {
         })
         continue
       }
-      if (value.type.startsWith("session.execution.")) setTimeout(wait.resolve, 0)
+      if (value.type.startsWith("session.execution.")) {
+        if (input.terminalDelay) await Bun.sleep(input.terminalDelay)
+        setTimeout(wait.resolve, 0)
+      }
       yield value
     }
   })()
@@ -206,9 +257,7 @@ async function run(input: {
   spyOn(sdk.session, "wait").mockImplementation(() => input.wait?.() ?? wait.promise)
   spyOn(sdk.message, "list").mockImplementation(() =>
     ok({
-      data: input.messages?.(promptID) ?? [
-        { id: promptID, type: "user", text: "hello", time: { created: 1 } },
-      ],
+      data: input.messages?.(promptID) ?? [{ id: promptID, type: "user", text: "hello", time: { created: 1 } }],
       cursor: {},
     }),
   )
@@ -251,7 +300,7 @@ async function capture(input: Parameters<typeof run>[0]) {
   })
   try {
     await run(input)
-    return { stdout: stdout.join(""), stderr: stderr.join("") }
+    return { stdout: stdout.join(""), stderr: stderr.join(""), exitCode: process.exitCode }
   } finally {
     process.exitCode = exitCode ?? 0
     stdoutWrite.mockRestore()
@@ -264,6 +313,32 @@ afterEach(() => {
 })
 
 describe("runNonInteractivePrompt", () => {
+  test("keeps formatted tool output and compact tool metadata in JSON", async () => {
+    const output = await capture({ format: "json", turn: successfulGrep })
+    const events = output.stdout
+      .split("\n")
+      .filter(Boolean)
+      .map((line) => JSON.parse(line))
+
+    expect(events).toHaveLength(1)
+    expect(events[0]).toMatchObject({
+      type: "tool_use",
+      part: {
+        tool: "grep",
+        state: {
+          status: "completed",
+          output: expect.stringContaining("Found 2 matches"),
+          metadata: {
+            metadata: { matches: 2 },
+            content: [{ type: "text", text: expect.stringContaining("/src/a.ts") }],
+          },
+        },
+      },
+    })
+    expect(events[0].part.state.metadata.metadata).toEqual({ matches: 2 })
+    expect(events[0].part.state.metadata.result).toBeUndefined()
+  })
+
   test("uses session.wait then reconciles projected output without a terminal event", async () => {
     const idle = Promise.withResolvers<void>()
     let done = false
@@ -319,6 +394,26 @@ describe("runNonInteractivePrompt", () => {
         error: { type: "provider.transport", message: "instructions unavailable" },
       }),
     ])
+    expect(output.exitCode).toBe(1)
+  })
+
+  test("waits for a terminal failure when idle wins before projection", async () => {
+    for (const promotedBeforeFailure of [true, false]) {
+      const output = await capture({
+        format: "json",
+        turn: (messageID) => [
+          ...(promotedBeforeFailure ? [prompted(messageID)] : []),
+          executionFailed("selection unavailable"),
+        ],
+        messages: (messageID) =>
+          promotedBeforeFailure ? [{ id: messageID, type: "user", text: "hello", time: { created: 1 } }] : [],
+        wait: () => Promise.resolve(),
+        terminalDelay: 10,
+      })
+
+      expect(output.exitCode).toBe(1)
+      expect(output.stdout).toContain("selection unavailable")
+    }
   })
 
   test("cancels session and global form blockers and exits on pre-promotion interrupt", async () => {
@@ -413,14 +508,14 @@ describe("runNonInteractivePrompt", () => {
       ],
     })
 
-    expect(output).toEqual({ stdout: "", stderr: "" })
+    expect(output).toEqual({ stdout: "", stderr: "", exitCode: 0 })
   })
 
-  test("renders native failed tool output before the terminal error", async () => {
+  test("renders a native terminal failure snapshot when live progress was missed", async () => {
     const rendered: SessionMessageAssistantTool[] = []
     const failed: SessionMessageAssistantTool[] = []
     await capture({
-      turn: failedTool,
+      turn: (inputID) => failedTool(inputID).filter((event) => event.type !== "session.tool.progress"),
       renderTool: (part) => {
         rendered.push(part)
         return Promise.resolve()
@@ -436,7 +531,7 @@ describe("runNonInteractivePrompt", () => {
         id: "call_failed_tool",
         state: {
           status: "completed",
-          structured: { checkpoint: 1 },
+          metadata: { checkpoint: 1 },
           content: [{ type: "text", text: "partial output" }],
         },
       },
@@ -446,7 +541,7 @@ describe("runNonInteractivePrompt", () => {
         id: "call_failed_tool",
         state: {
           status: "error",
-          structured: { checkpoint: 1 },
+          metadata: { checkpoint: 1 },
           content: [{ type: "text", text: "partial output" }],
           error: { message: "tool failed" },
         },
@@ -476,7 +571,7 @@ describe("runNonInteractivePrompt", () => {
       },
     })
     expect(events[0].part.state.output).toBeUndefined()
-    expect(events[0].part.state.metadata.structured).toBeUndefined()
+    expect(events[0].part.state.metadata.metadata).toBeUndefined()
     expect(events[0].part.state.metadata.content).toBeUndefined()
     expect(output.stderr).toBe("")
   })

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

@@ -78,6 +78,15 @@ describe("session target resolver", () => {
     expect(order).toEqual(["prepare", "create"])
   })
 
+  test("uses the agent resolved by the server for a fresh Session", async () => {
+    const client = OpenCode.make({ baseUrl: "https://opencode.test" })
+    spyOn(client.location, "get").mockResolvedValue(location("/project"))
+    spyOn(client.session, "create").mockResolvedValue({ ...session("ses_fresh", "/project"), agent: "review" })
+
+    const target = await resolveSessionTarget({ client, prepare })
+    expect(target.agent).toBe("review")
+  })
+
   test("does not retry an ambiguous Session creation", async () => {
     const client = OpenCode.make({ baseUrl: "https://opencode.test" })
     spyOn(client.location, "get").mockResolvedValue(location("/project"))

packages/cli/vite.node.config.ts

@@ -75,6 +75,10 @@ export const define = sdk.Plugin.define`
   const effectPluginModule = promisePluginModule
     .replace("opencode.plugin.v2.promise", "opencode.plugin.v2.effect")
     .replace("Promise plugin", "Effect plugin")
+  const promiseToolModule = `const sdk = globalThis[Symbol.for("opencode.plugin.v2.promise")]
+if (!sdk) throw new Error("OpenCode Promise plugin SDK is unavailable")
+export const Tool = sdk.Tool
+export const make = sdk.Tool.make`
   const effectToolModule = `const sdk = globalThis[Symbol.for("opencode.plugin.v2.effect")]
 if (!sdk) throw new Error("OpenCode Effect plugin SDK is unavailable")
 export const Tool = sdk.Tool
@@ -83,10 +87,8 @@ export const RegistrationError = sdk.Tool.RegistrationError
 export const make = sdk.Tool.make
 export const validateName = sdk.Tool.validateName
 export const registrationEntries = sdk.Tool.registrationEntries
-export const withPermission = sdk.Tool.withPermission
-export const permission = sdk.Tool.permission
-export const definition = sdk.Tool.definition
-export const settle = sdk.Tool.settle`
+export const validateNamespace = sdk.Tool.validateNamespace
+export const toLLMDefinition = sdk.Tool.toLLMDefinition`
   return `#!/usr/bin/env -S node ${nodeExecArgv.join(" ")}
 import __cjs_mod__ from "node:module"
 import { chmodSync as __ocChmod, existsSync as __ocExists, lstatSync as __ocLstat, mkdirSync as __ocMkdir, renameSync as __ocRename, rmSync as __ocRm, writeFileSync as __ocWrite } from "node:fs"
@@ -100,6 +102,7 @@ const require = __cjs_mod__.createRequire(import.meta.url)
 const __ocPluginModules = ${JSON.stringify({
     "@opencode-ai/plugin/v2": "opencode:plugin-v2",
     "@opencode-ai/plugin/v2/plugin": "opencode:plugin-v2-plugin",
+    "@opencode-ai/plugin/v2/tool": "opencode:plugin-v2-tool",
     "@opencode-ai/plugin/v2/effect": "opencode:plugin-v2-effect",
     "@opencode-ai/plugin/v2/effect/plugin": "opencode:plugin-v2-effect-plugin",
     "@opencode-ai/plugin/v2/effect/tool": "opencode:plugin-v2-effect-tool",
@@ -107,6 +110,7 @@ const __ocPluginModules = ${JSON.stringify({
 const __ocPluginSources = ${JSON.stringify({
     "opencode:plugin-v2": promiseModule,
     "opencode:plugin-v2-plugin": promisePluginModule,
+    "opencode:plugin-v2-tool": promiseToolModule,
     "opencode:plugin-v2-effect": effectModule,
     "opencode:plugin-v2-effect-plugin": effectPluginModule,
     "opencode:plugin-v2-effect-tool": effectToolModule,

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

@@ -8,7 +8,7 @@ export type ModelRef = { id: string; providerID: string; variant?: string }
 
 export type ProviderSettings = { [x: string]: JsonValue }
 
-export type AgentColor = string | "primary" | "secondary" | "accent" | "success" | "warning" | "error" | "info"
+export type AgentColor = string
 
 export type PermissionV2Effect = "allow" | "deny" | "ask"
 
@@ -104,6 +104,12 @@ export type SessionMessageProviderState = { [x: string]: JsonValue }
 
 export type SessionMessageToolStateStreaming = { status: "streaming"; input: string }
 
+export type SessionMessageToolStateRunning = {
+  status: "running"
+  input: { [x: string]: JsonValue }
+  metadata: { [x: string]: JsonValue }
+}
+
 export type ToolTextContent = { type: "text"; text: string }
 
 export type ToolFileContent = { type: "file"; uri: string; mime: string; name?: string }
@@ -163,6 +169,8 @@ export type SessionMessageProviderState7 = { [x: string]: any }
 
 export type EventLogSynced = { type: "log.synced"; aggregateID: string; seq?: number }
 
+export type ModelReasoningField = "reasoning" | "reasoning_content" | "reasoning_text" | (string & {})
+
 export type ModelCapabilities = { tools: boolean; input: Array<string>; output: Array<string> }
 
 export type ModelVariant = {
@@ -916,6 +924,15 @@ export type SessionToolInputDelta = {
   data: { sessionID: string; assistantMessageID: string; callID: string; delta: string }
 }
 
+export type SessionToolProgress = {
+  id: string
+  created: number
+  metadata?: { [x: string]: any }
+  type: "session.tool.progress"
+  location?: LocationRef
+  data: { sessionID: string; assistantMessageID: string; callID: string; metadata: { [x: string]: JsonValue } }
+}
+
 export type SessionCompactionDelta = {
   id: string
   created: number
@@ -1094,7 +1111,7 @@ export type TuiCommandExecute = {
       | "prompt.clear"
       | "prompt.submit"
       | "agent.cycle"
-      | string
+      | (string & {})
   }
 }
 
@@ -1385,23 +1402,7 @@ export type SessionToolCalled = {
   }
 }
 
-export type SessionToolFailed = {
-  id: string
-  created: number
-  metadata?: { [x: string]: any }
-  type: "session.tool.failed"
-  durable: { aggregateID: string; seq: number; version: 1 }
-  location?: LocationRef
-  data: {
-    sessionID: string
-    assistantMessageID: string
-    callID: string
-    error: SessionStructuredError
-    result?: any
-    executed: boolean
-    resultState?: SessionMessageProviderState7
-  }
-}
+export type ModelCompatibility = { reasoningField?: ModelReasoningField }
 
 export type ModelCost = {
   tier?: { type: "context"; size: number }
@@ -1823,44 +1824,19 @@ export type SessionPendingUserData1 = {
   metadata?: { [x: string]: any }
 }
 
-export type SessionMessageToolStateRunning = {
-  status: "running"
-  input: { [x: string]: JsonValue }
-  structured: { [x: string]: JsonValue }
-  content: Array<LLMToolContent>
-}
-
 export type SessionMessageToolStateCompleted = {
   status: "completed"
   input: { [x: string]: JsonValue }
-  content: Array<LLMToolContent>
-  structured: { [x: string]: JsonValue }
-  result?: JsonValue
+  content: [LLMToolContent, ...Array<LLMToolContent>]
+  metadata?: { [x: string]: JsonValue }
 }
 
 export type SessionMessageToolStateError = {
   status: "error"
   input: { [x: string]: JsonValue }
-  content: Array<LLMToolContent>
-  structured: { [x: string]: JsonValue }
   error: SessionStructuredError
-  result?: JsonValue
-}
-
-export type SessionToolProgress = {
-  id: string
-  created: number
-  metadata?: { [x: string]: any }
-  type: "session.tool.progress"
-  durable: { aggregateID: string; seq: number; version: 1 }
-  location?: LocationRef
-  data: {
-    sessionID: string
-    assistantMessageID: string
-    callID: string
-    structured: { [x: string]: any }
-    content: Array<LLMToolContent>
-  }
+  content?: [LLMToolContent, ...Array<LLMToolContent>]
+  metadata?: { [x: string]: JsonValue }
 }
 
 export type SessionToolSuccess = {
@@ -1868,20 +1844,38 @@ export type SessionToolSuccess = {
   created: number
   metadata?: { [x: string]: any }
   type: "session.tool.success"
-  durable: { aggregateID: string; seq: number; version: 1 }
+  durable: { aggregateID: string; seq: number; version: 2 }
   location?: LocationRef
   data: {
     sessionID: string
     assistantMessageID: string
     callID: string
-    structured: { [x: string]: any }
-    content: Array<LLMToolContent>
-    result?: any
+    content: [LLMToolContent, ...Array<LLMToolContent>]
+    metadata?: { [x: string]: JsonValue }
     executed: boolean
     resultState?: SessionMessageProviderState6
   }
 }
 
+export type SessionToolFailed = {
+  id: string
+  created: number
+  metadata?: { [x: string]: any }
+  type: "session.tool.failed"
+  durable: { aggregateID: string; seq: number; version: 2 }
+  location?: LocationRef
+  data: {
+    sessionID: string
+    assistantMessageID: string
+    callID: string
+    error: SessionStructuredError
+    content?: [LLMToolContent, ...Array<LLMToolContent>]
+    metadata?: { [x: string]: JsonValue }
+    executed: boolean
+    resultState?: SessionMessageProviderState7
+  }
+}
+
 export type SessionMessageCompaction =
   | SessionMessageCompactionRunning
   | SessionMessageCompactionCompleted
@@ -1893,6 +1887,7 @@ export type ModelInfo = {
   providerID: string
   family?: string
   name: string
+  compatibility?: ModelCompatibility
   package?: string
   settings?: { [x: string]: JsonValue }
   headers?: { [x: string]: string }
@@ -2219,7 +2214,6 @@ export type SessionEventDurable =
   | SessionToolInputStarted
   | SessionToolInputEnded
   | SessionToolCalled
-  | SessionToolProgress
   | SessionToolSuccess
   | SessionToolFailed
   | SessionRetryScheduled

packages/codemode/README.md

@@ -33,7 +33,7 @@ const lookupOrder = Tool.make({
   description: "Look up an order by ID",
   input: Schema.Struct({ id: Schema.String }),
   output: Schema.Struct({ id: Schema.String, status: Schema.String }),
-  run: ({ id }) => Effect.succeed({ id, status: "open" }),
+  execute: ({ id }) => Effect.succeed({ id, status: "open" }),
 })
 
 const runtime = CodeMode.make({
@@ -55,10 +55,10 @@ const result = await Effect.runPromise(
 ### `Tool.make`
 
 `input` and `output` accept either an Effect Schema or a render-only JSON Schema document. Effect Schema input is
-decoded before `run`; Effect Schema output is decoded and safely copied before the program sees it. JSON Schemas only
-shape the model-visible signature. Without `output`, the signature uses `Promise<unknown>`.
+decoded before `execute`; Effect Schema output is decoded and safely copied before the program sees it. JSON Schemas
+only shape the model-visible signature. Without `output`, the signature uses `Promise<void>`.
 
-Descriptions and schemas are model-visible contracts. Authorization belongs in `run`.
+Descriptions and schemas are model-visible contracts. Authorization belongs in `execute`.
 
 Dots in tool names create namespaces: `{ "issues.list": tool }` and `{ issues: { list: tool } }` both expose
 `tools.issues.list(...)`. Other characters use bracket notation, such as

packages/codemode/interpreter-support.md

@@ -136,8 +136,8 @@ ultimate source of truth.
 - [x] Optional property access and optional calls.
 - [x] Function/tool calls and spread arguments.
 - [x] Sequence expressions (the comma operator).
-- [x] `await` for CodeMode promises; a plain value passes through unchanged, though every `await` still defers its
-      continuation one reaction turn.
+- [x] `await` for CodeMode promises and callable thenables; a plain value passes through unchanged, though every
+      `await` still defers its continuation one reaction turn.
 - [x] `new` for Array, Object, Error types, Date, RegExp, Map, Set, URL, URLSearchParams, and Promise.
 - [x] Arithmetic operators: `+`, `-`, `*`, `/`, `%`, and `**`.
 - [x] Equality and ordering: `==`, `!=`, `===`, `!==`, `<`, `<=`, `>`, and `>=`.
@@ -152,7 +152,8 @@ ultimate source of truth.
 ## Promises and tools
 
 - [x] Tool calls start eagerly and return supervised, run-once CodeMode promises.
-- [x] Direct `await`, repeated awaits, and implicit resolution when a promise is returned from a function/program.
+- [x] Direct `await`, repeated awaits, and recursive thenable assimilation when a promise or thenable is returned from
+      a function/program.
 - [x] `Promise.resolve` and `Promise.reject`.
 - [x] `Promise.all`, `Promise.allSettled`, `Promise.race`, and `Promise.any` over finite collections, custom synchronous
       iterators, and synchronous generators containing promises and plain values.
@@ -178,13 +179,16 @@ ultimate source of truth.
       the catch-normalized reasons in input order, and empty input rejects with an empty `AggregateError`.
 - [x] `new Promise((resolve, reject) => ...)`: the executor runs synchronously and receives first-class resolve/reject
       callables that settle the promise exactly once (they may escape the executor and settle later); an executor
-      throw rejects unless the promise already settled, resolving with a promise adopts it, and resolving with the
-      promise itself rejects with a `TypeError`. Resolver callables work anywhere callbacks are accepted, including
-      `.then`/`.catch` handlers and collection callbacks, but remain opaque references that cannot cross the data
-      boundary.
-- [ ] Thenable assimilation; objects with a callable `then` field remain plain data.
+      throw rejects unless the promise already settled, resolving with a promise or callable thenable adopts it, and
+      resolving with the promise itself rejects with a `TypeError`. Resolver callables work anywhere callbacks are
+      accepted, including `.then`/`.catch` handlers and collection callbacks, but remain opaque references that cannot
+      cross the data boundary.
+- [x] Recursive assimilation of objects with an own callable `then` field across `Promise.resolve`, combinators,
+      constructors, reactions, `finally`, `await`, and async returns. Thenable methods run deferred, receive
+      first-call-wins resolve/reject functions, and ignore throws after settlement. Inherited/accessor `then` fields
+      and a JavaScript `this` receiver remain outside the supported object/function model.
 - [x] Dotted tool names are canonicalized into namespace paths; a path can be both callable and a namespace, and the
-      last definition supplied for a canonical path wins.
+      last tool supplied for a canonical path wins.
 - [x] Tool path segments may be named `constructor`, `prototype`, or `__proto__` because paths use inert Map keys.
 - [x] Outbound tool arguments follow JSON serialization semantics, like `JSON.stringify`: object properties with
       `undefined` values are dropped, `undefined` array elements and non-finite numbers become `null`, and sparse

packages/codemode/src/interpreter/execute.ts

@@ -45,7 +45,7 @@ export const executeWithLimits = <const Provided extends Record<string, unknown>
           const program = parseProgram(options.code)
           const promises = new PromiseRuntime<Services<Provided>>(scope)
           const interpreter = new Interpreter<Services<Provided>>(
-            tools.invoke,
+            tools.execute,
             tools.search,
             tools.keys,
             promises,