fix(ai): support Sonnet 5.5 Messages request shapes

fix(ai): enable explicit caching on more message protocol routes (#51981 )
Co-authored-by: rekram1-node <rekram1-node@users.noreply.github.com>
2026-09-29 12:07:37 +00:00 · 2026-09-29 08:39:07 +00:00 · 2026-09-29 00:50:08 -05:00 · 2026-09-29 00:45:17 -05:00 · 2026-09-29 00:19:20 -05:00 · 2026-09-29 15:09:50 +10:00
245 changed files with 4330 additions and 1322 deletions
@@ -1,5 +0,0 @@
---
-"@opencode/core": patch
---
-
-Correct directory page headings when the read offset is zero.
@@ -24,6 +24,10 @@ on:
        description: "Override version (optional)"
        required: false
        type: string
+      release_notes:
+        description: "Reviewed V2 release notes for the Discord announcement (optional)"
+        required: false
+        type: string

 concurrency: ${{ github.workflow }}-${{ github.ref }}-${{ (github.ref_name == 'v2' && (inputs.version || inputs.bump) && 'release') || inputs.version || inputs.bump }}

@@ -653,3 +657,19 @@ jobs:
          OPENCODE_DESKTOP_DIST: /tmp/desktop
          CLOUDFLARE_ACCOUNT_ID: 15d29c8639fd3733b1b5486a2acfd968
          CLOUDFLARE_API_TOKEN: ${{ secrets.CLOUDFLARE_API_TOKEN }}
+
+  notify-discord-v2:
+    needs:
+      - version
+      - publish
+    if: github.repository == 'anomalyco/opencode' && github.ref_name == 'v2' && needs.version.outputs.release && needs.publish.result == 'success'
+    runs-on: blacksmith-4vcpu-ubuntu-2404
+    steps:
+      # Unlike dev, V2 publishes a tag rather than a GitHub Release event.
+      - name: Announce V2 release in Discord
+        uses: SethCohen/github-releases-to-discord@24d166886aee4646d448c8a389ff9e1ebcab3682 # v1.20.0
+        with:
+          webhook_url: ${{ secrets.DISCORD_WEBHOOK }}
+          release_name: OpenCode V2 ${{ needs.version.outputs.tag }}
+          release_body: ${{ inputs.release_notes }}
+          release_html_url: https://github.com/${{ github.repository }}/tree/${{ needs.version.outputs.tag }}
@@ -32,7 +32,7 @@
    },
    "packages/ai": {
      "name": "@opencode/ai",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@aws-sdk/credential-providers": "3.1057.0",
        "@opencode/schema": "workspace:*",
@@ -54,7 +54,7 @@
    },
    "packages/app": {
      "name": "@opencode/app",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@corvu/drawer": "catalog:",
        "@dnd-kit/abstract": "0.5.0",
@@ -112,7 +112,7 @@
    },
    "packages/cli": {
      "name": "@opencode/cli",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "bin": {
        "opencode": "./bin/opencode.cjs",
        "opencode2": "./bin/opencode2.cjs",
@@ -178,7 +178,7 @@
    },
    "packages/client": {
      "name": "@opencode/client",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@opencode/protocol": "workspace:*",
        "@opencode/schema": "workspace:*",
@@ -204,7 +204,7 @@
    },
    "packages/codemode": {
      "name": "@opencode/codemode",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "acorn": "8.15.0",
        "effect": "catalog:",
@@ -217,7 +217,7 @@
    },
    "packages/console/app": {
      "name": "@opencode/console-app",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@cloudflare/vite-plugin": "1.15.2",
        "@ibm/plex": "6.4.1",
@@ -253,7 +253,7 @@
    },
    "packages/console/core": {
      "name": "@opencode/console-core",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@aws-sdk/client-sts": "3.782.0",
        "@jsx-email/render": "1.1.1",
@@ -280,7 +280,7 @@
    },
    "packages/console/function": {
      "name": "@opencode/console-function",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@openauthjs/openauth": "0.0.0-20250322224806",
        "@opencode/console-core": "workspace:*",
@@ -297,7 +297,7 @@
    },
    "packages/console/mail": {
      "name": "@opencode/console-mail",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@jsx-email/all": "2.2.3",
        "@jsx-email/cli": "1.4.3",
@@ -321,7 +321,7 @@
    },
    "packages/console/support": {
      "name": "@opencode/console-support",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@cloudflare/vite-plugin": "1.15.2",
        "@opencode/console-core": "workspace:*",
@@ -341,7 +341,7 @@
    },
    "packages/core": {
      "name": "@opencode/core",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@ai-sdk/cohere": "3.0.27",
        "@ai-sdk/gateway": "3.0.104",
@@ -409,7 +409,7 @@
    },
    "packages/desktop": {
      "name": "@opencode/desktop",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@zip.js/zip.js": "2.7.62",
        "electron-context-menu": "5.0.0",
@@ -439,7 +439,7 @@
        "drizzle-kit": "catalog:",
        "drizzle-orm": "catalog:",
        "effect": "catalog:",
-        "electron": "44.4.3",
+        "electron": "44.4.5",
        "electron-builder": "26.15.7",
        "electron-vite": "6.0.0-beta.1",
        "puppeteer-core": "25.9.0",
@@ -458,7 +458,7 @@
    },
    "packages/enterprise": {
      "name": "@opencode/enterprise",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@hono/standard-validator": "catalog:",
        "@opencode-ai/sdk": "1.18.21",
@@ -495,7 +495,7 @@
    },
    "packages/function": {
      "name": "@opencode/function",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@octokit/auth-app": "8.0.1",
        "@octokit/rest": "catalog:",
@@ -511,7 +511,7 @@
    },
    "packages/http-recorder": {
      "name": "@opencode/http-recorder",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@effect/platform-node-shared": "4.0.0-rc.112",
      },
@@ -530,7 +530,7 @@
    },
    "packages/httpapi-codegen": {
      "name": "@opencode/httpapi-codegen",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "effect": "catalog:",
        "prettier": "3.6.2",
@@ -543,7 +543,7 @@
    },
    "packages/latex": {
      "name": "@opencode/latex",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@opencode/plugin": "workspace:*",
        "@opentui/core": "catalog:",
@@ -557,7 +557,7 @@
    },
    "packages/merman": {
      "name": "@opencode/merman",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@opencode/plugin": "workspace:*",
        "@opentui/core": "catalog:",
@@ -572,7 +572,7 @@
    },
    "packages/plugin": {
      "name": "@opencode/plugin",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@ai-sdk/provider": "3.0.8",
        "@opencode/ai": "workspace:*",
@@ -611,7 +611,7 @@
    },
    "packages/plugin-browser": {
      "name": "@opencode/plugin-browser",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@opencode/plugin": "workspace:*",
        "@opencode/schema": "workspace:*",
@@ -641,7 +641,7 @@
    },
    "packages/protocol": {
      "name": "@opencode/protocol",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@opencode/schema": "workspace:*",
        "effect": "catalog:",
@@ -656,7 +656,7 @@
    },
    "packages/schema": {
      "name": "@opencode/schema",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@standard-schema/spec": "catalog:",
        "effect": "catalog:",
@@ -680,7 +680,7 @@
    },
    "packages/sdk": {
      "name": "@opencode/sdk",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@opencode/client": "workspace:*",
        "@opencode/core": "workspace:*",
@@ -701,7 +701,7 @@
    },
    "packages/server": {
      "name": "@opencode/server",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@effect/platform-node": "catalog:",
        "@effect/platform-node-shared": "catalog:",
@@ -723,7 +723,7 @@
    },
    "packages/session-ui": {
      "name": "@opencode/session-ui",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@kobalte/core": "catalog:",
        "@opencode/client": "workspace:*",
@@ -758,7 +758,7 @@
    },
    "packages/simulation": {
      "name": "@opencode/simulation",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@opencode/ai": "workspace:*",
        "@opencode/core": "workspace:*",
@@ -778,7 +778,7 @@
    },
    "packages/stats/app": {
      "name": "@opencode/stats-app",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@ibm/plex": "6.4.1",
        "@kobalte/core": "catalog:",
@@ -812,7 +812,7 @@
    },
    "packages/stats/core": {
      "name": "@opencode/stats-core",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@aws-sdk/client-athena": "3.933.0",
        "@planetscale/database": "1.19.0",
@@ -831,7 +831,7 @@
    },
    "packages/stats/server": {
      "name": "@opencode/stats-server",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@aws-sdk/client-firehose": "3.933.0",
        "@effect/platform-node": "catalog:",
@@ -877,7 +877,7 @@
    },
    "packages/theme": {
      "name": "@opencode/theme",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@opentui/core": "catalog:",
        "effect": "catalog:",
@@ -891,7 +891,7 @@
    },
    "packages/tui": {
      "name": "@opencode/tui",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@opencode/client": "workspace:*",
        "@opencode/core": "workspace:*",
@@ -925,7 +925,7 @@
    },
    "packages/ui": {
      "name": "@opencode/ui",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@kobalte/core": "catalog:",
        "@pierre/diffs": "catalog:",
@@ -960,7 +960,7 @@
    },
    "packages/util": {
      "name": "@opencode/util",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@effect/opentelemetry": "catalog:",
        "@effect/platform-node": "catalog:",
@@ -998,7 +998,7 @@
    },
    "packages/web": {
      "name": "@opencode/web",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@astrojs/cloudflare": "12.6.3",
        "@astrojs/markdown-remark": "6.3.1",
@@ -1039,7 +1039,7 @@
    },
    "services/update": {
      "name": "@opencode/update",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "jose": "6.0.11",
        "semver": "catalog:",
@@ -1119,7 +1119,7 @@
    "@opentui/core": "0.5.12",
    "@opentui/keymap": "0.5.12",
    "@opentui/solid": "0.5.12",
-    "@pierre/diffs": "1.2.10",
+    "@pierre/diffs": "1.5.1",
    "@playwright/test": "1.59.1",
    "@sentry/solid": "10.71.0",
    "@sentry/vite-plugin": "5.4.0",
@@ -2530,11 +2530,11 @@

    "@peculiar/webcrypto": ["@peculiar/webcrypto@1.7.1", "", { "dependencies": { "@peculiar/asn1-schema": "^2.7.0", "@peculiar/json-schema": "^1.1.12", "@peculiar/utils": "^2.0.2", "tslib": "^2.8.1", "webcrypto-core": "^1.9.2" } }, "sha512-ODOov0sGMJMf3jPonOkgGqPknTsu+DdQ7kD++gz8aI+aFMOMHFbWAA2taqXXVTdP+OTOQR/znGvSpmkeI0WTYQ=="],

-    "@pierre/diffs": ["@pierre/diffs@1.2.10", "", { "dependencies": { "@pierre/theme": "1.0.3", "@pierre/theming": "0.0.1", "@shikijs/transformers": "^3.0.0 || ^4.0.0", "diff": "8.0.3", "hast-util-to-html": "9.0.5", "lru_map": "0.4.1", "shiki": "^3.0.0 || ^4.0.0" }, "peerDependencies": { "react": "^18.3.1 || ^19.0.0", "react-dom": "^18.3.1 || ^19.0.0" } }, "sha512-rPeAmDWarxFVTQpaf4y6wTxjZxU44xKJKoJti2zU21P06DVd9nRHZX+xSIObLB307Qjpaesyb1x/j0z94t7vLw=="],
+    "@pierre/diffs": ["@pierre/diffs@1.5.1", "", { "dependencies": { "@pierre/theme": "2.0.0", "@pierre/theming": "1.0.1", "@shikijs/transformers": "^3.0.0 || ^4.0.0", "diff": "9.0.0", "hast-util-to-html": "9.0.5", "lru_map": "0.4.1", "shiki": "^3.0.0 || ^4.0.0" }, "peerDependencies": { "react": "^18.3.1 || ^19.0.0", "react-dom": "^18.3.1 || ^19.0.0" }, "optionalPeers": ["react", "react-dom"] }, "sha512-+EXNfz4ZXI6FHr7P6ToWEORwyYiPVfAmzhA70xF+0y/oNvj7gbNTLJJ6jNzkBjuMbRlu564TAmgYZLc5OyHURA=="],

-    "@pierre/theme": ["@pierre/theme@1.0.3", "", {}, "sha512-sWHv11TMoqKxKDgTIk5VbhQjdPhs8DCcBxbjh3mRlS3YOM/OcrWoGX6MM8eBGn9cUu3M46Py0JnxsG2nJaFTuA=="],
+    "@pierre/theme": ["@pierre/theme@2.0.0", "", {}, "sha512-yNDd9GYLQl1mEUJR8AneJ5e4ohLIHQd/wZLWr4fagt78vS2RwwZNW530vVgHqXFAyFVcFlRmGUD5ramXH46OXw=="],

-    "@pierre/theming": ["@pierre/theming@0.0.1", "", { "peerDependencies": { "@pierre/theme": "^1.0.0", "@shikijs/themes": "^3.0.0 || ^4.0.0", "react": "^18.3.1 || ^19.0.0", "react-dom": "^18.3.1 || ^19.0.0", "shiki": "^3.0.0 || ^4.0.0" }, "optionalPeers": ["@pierre/theme", "@shikijs/themes", "react", "react-dom", "shiki"] }, "sha512-1thlEtJbqdyLzc1ZS2KQa1q7FzDGHT4dTEdKHoyQjOMeWWOmbVG5/ndEfOKfAb5Fzkz8cNJrOjFLiZoDH/A03A=="],
+    "@pierre/theming": ["@pierre/theming@1.0.1", "", { "peerDependencies": { "@pierre/theme": "^1.1.0 || ^2.0.0", "@shikijs/themes": "^3.0.0 || ^4.0.0", "react": "^18.3.1 || ^19.0.0", "react-dom": "^18.3.1 || ^19.0.0", "shiki": "^3.0.0 || ^4.0.0" }, "optionalPeers": ["@pierre/theme", "@shikijs/themes", "react", "react-dom", "shiki"] }, "sha512-WCI5Qd7iprDpISL9fBYOLe8RV53+b7mFNA3bPzl60/2CKCSrsKN8zEcep6Y3BAzvARlmca50zGjDodqPGiTUKA=="],

    "@pierre/trees": ["@pierre/trees@1.0.0-beta.4", "", { "dependencies": { "preact": "11.0.0-beta.0", "preact-render-to-string": "6.6.5" }, "peerDependencies": { "react": "^18.3.1 || ^19.0.0", "react-dom": "^18.3.1 || ^19.0.0" } }, "sha512-OfT1yk9ne8Te5+GB5zUY8yqE6B8BqjBHQJleH4lu8ltwNpoocZl4vXt1AzlEExpxI/pp+AFX5QG+lR3JjtTEag=="],

@@ -3870,7 +3870,7 @@

    "ejs": ["ejs@3.1.10", "", { "dependencies": { "jake": "^10.8.5" }, "bin": { "ejs": "bin/cli.js" } }, "sha512-UeJmFfOrAQS8OJWPZ4qtgHyWExa088/MtK5UEyoJGFH67cDEXkZSviOiKRCZ4Xij0zxI3JECgYs3oKx+AizQBA=="],

-    "electron": ["electron@44.4.3", "", { "dependencies": { "@electron-internal/extract-zip": "^1.0.1", "@electron/get": "^5.0.0", "@types/node": "^24.9.0" }, "bin": { "electron": "cli.js", "install-electron": "install.js" } }, "sha512-LTpSFTB40qVCXIX5xMo+cgHI/Jjkbjw7VpB26PccEbroqOn72LBukeaDwPVo1fBYzSzs0c9iPuAucFCO7Tw81Q=="],
+    "electron": ["electron@44.4.5", "", { "dependencies": { "@electron-internal/extract-zip": "^1.0.1", "@electron/get": "^5.0.0", "@types/node": "^24.9.0" }, "bin": { "electron": "cli.js", "install-electron": "install.js" } }, "sha512-SjgoaeYsSWZfJzubgQU7juvuXMTvn6/e1gAHdGFA/yuMbpF+I+skYqIJ6DdXBXHeWbkbpNpmwZCTpiivtlWZSw=="],

    "electron-builder": ["electron-builder@26.15.7", "", { "dependencies": { "app-builder-lib": "26.15.7", "builder-util": "26.15.3", "builder-util-runtime": "9.7.0", "chalk": "^4.1.2", "ci-info": "^4.2.0", "dmg-builder": "26.15.7", "fs-extra": "^10.1.0", "lazy-val": "^1.0.5", "simple-update-notifier": "2.0.0", "yargs": "^17.6.2" }, "bin": { "electron-builder": "./cli.js", "install-app-deps": "./install-app-deps.js" } }, "sha512-DBpaNzxsPs1BvEblzFoNriSbzsBqDCy/gseIngeEhYzQG1IxfB7Hvc2tBBVmpWE2BTQGP9J1RrAvDT+Vc/uAxg=="],

@@ -6258,11 +6258,7 @@

    "@parcel/watcher/detect-libc": ["detect-libc@1.0.3", "", { "bin": { "detect-libc": "./bin/detect-libc.js" } }, "sha512-pGjwhsmsp4kL2RTz08wcOlGN83otlqHeD/Z5T8GXZB+/YcpQ/dgo+lbU8ZsGxV0HIvqqxo9l7mqYwyYMD9bKDg=="],

-    "@pierre/diffs/diff": ["diff@8.0.3", "", {}, "sha512-qejHi7bcSD4hQAZE0tNAawRK1ZtafHDmMTMkrrIGgSLl7hTnQHmKCeB45xAcbfTqK2zowkM3j3bHt/4b/ARbYQ=="],
-
-    "@pierre/diffs/react": ["react@19.2.8", "", {}, "sha512-PWaYA1L/q9u2u7xYQi+Y3L3Yfnie7XyLeaJICV1MGD6LprsBxcAqGjYyr0eY3p+QdsA+x/Irkt4Qif8D63+Sbw=="],
-
-    "@pierre/diffs/react-dom": ["react-dom@19.2.8", "", { "dependencies": { "scheduler": "^0.27.0" }, "peerDependencies": { "react": "^19.2.8" } }, "sha512-rVprimfGBG3DR+Tq0IQG2DT5PxKth1WIGDmj5yPmlzr4YBe7uyE+Du4oVqTDXZSHGGGXRtTJEGSSePyQCMBglQ=="],
+    "@pierre/diffs/diff": ["diff@9.0.0", "", {}, "sha512-svtcdpS8CgJyqAjEQIXdb3OjhFVVYjzGAPO8WGCmRbrml64SPw/jJD4GoE98aR7r25A0XcgrK3F02yw9R/vhQw=="],

    "@pierre/trees/react": ["react@19.2.8", "", {}, "sha512-PWaYA1L/q9u2u7xYQi+Y3L3Yfnie7XyLeaJICV1MGD6LprsBxcAqGjYyr0eY3p+QdsA+x/Irkt4Qif8D63+Sbw=="],

@@ -7160,8 +7156,6 @@

    "@oxc-resolver/binding-wasm32-wasi/@emnapi/core/@emnapi/wasi-threads": ["@emnapi/wasi-threads@1.2.2", "", { "dependencies": { "tslib": "^2.4.0" } }, "sha512-c95qOXkHdydNKhscBTebqEC1CVAZpyqOfVfBzQ1qgzyl3gfeldUjIggDbIZgDKsHLgnsM+igH7TJ/eAasaVuMA=="],

-    "@pierre/diffs/react-dom/scheduler": ["scheduler@0.27.0", "", {}, "sha512-eNv+WrVbKu1f3vbYJT/xtiF5syA5HPIMtf9IgY/nKg0sWqzAUEvqY/xm7OcZc/qafLx/iO9FgOmeSAp4v5ti/Q=="],
-
    "@pierre/trees/react-dom/scheduler": ["scheduler@0.27.0", "", {}, "sha512-eNv+WrVbKu1f3vbYJT/xtiF5syA5HPIMtf9IgY/nKg0sWqzAUEvqY/xm7OcZc/qafLx/iO9FgOmeSAp4v5ti/Q=="],

    "@puppeteer/browsers/yargs/cliui": ["cliui@9.0.1", "", { "dependencies": { "string-width": "^7.2.0", "strip-ansi": "^7.1.0", "wrap-ansi": "^9.0.0" } }, "sha512-k7ndgKhwoQveBL+/1tqGJYNz097I7WOvwbmmU2AR5+magtbjPWQTS1C5vzGkBC8Ym8UWRzfKUzUUqFLypY4Q+w=="],
@@ -2,11 +2,11 @@
  "nodes": {
    "nixpkgs": {
      "locked": {
-        "lastModified": 1776683584,
-        "narHash": "sha256-NuTLMrr10Tng72hurYG8jYQ4XKK8wnpJmOGcPiis96g=",
+        "lastModified": 1790510107,
+        "narHash": "sha256-EVMNYv7hYDDD9TGVT/hIyTYgpiXA8y3m5xIEIxuGNU0=",
        "owner": "NixOS",
        "repo": "nixpkgs",
-        "rev": "9dd5558b06dbdacbf635a3dd36dce1b1a7ee3a89",
+        "rev": "3181085bfd08663b6b9e60bc7a8395c2aaa741bd",
        "type": "github"
      },
      "original": {
@@ -2,7 +2,7 @@
  "$schema": "https://json.schemastore.org/package.json",
  "name": "opencode",
  "description": "AI-powered development tool",
-  "version": "2.0.18",
+  "version": "2.0.19",
  "private": true,
  "type": "module",
  "packageManager": "bun@1.4.2",
@@ -68,7 +68,7 @@
      "@tsconfig/bun": "1.0.9",
      "@cloudflare/workers-types": "4.20251008.0",
      "@openauthjs/openauth": "0.0.0-20250322224806",
-      "@pierre/diffs": "1.2.10",
+      "@pierre/diffs": "1.5.1",
      "opentui-spinner": "0.0.7",
      "@solid-primitives/event-listener": "2.4.6",
      "@solid-primitives/media": "2.3.6",
@@ -98,11 +98,11 @@ When a provider supports multiple physical transports, selection remains executi

 Media does not fit the SSE-frames-to-event-state-machine LLM route. `MediaRoute.inline(...)` / `queued(...)` / `stream(...)` (`src/route/media.ts`) compose a `MediaProtocol` kind with `Endpoint` and `Auth` and own the transport plumbing: `http` option merging, URL/query rendering, auth headers, JSON vs multipart encoding, and handing the response back to the protocol. `MediaProtocol.inline` (`src/route/media-protocol.ts`) is `body.from(request)` plus `response.decode(response, context)`; each protocol declares `const route = MediaProtocol.identity({ id, name, provider })` once and decodes through `route.decodeJson` / `route.text` / `route.decodeStarted` so decode failures retain the raw body and HTTP context, raising `route.unsupported(operation, message)` for requests it cannot lower, and passes `route` as the first argument to `MediaProtocol.inline` / `queued` / `stream`. `Generation` (`src/generation.ts`) is the provider-neutral handle for a queued generation over a `GenerationRoute` (`status`, `result`, `cancel`). Image protocol files follow the same section order as LLM protocols and declare unsupported common fields once through the protocol's `unsupported` list.

-`MediaProtocol.queued` is the submit-then-poll kind every video route uses: `start` (body + decode into `{ token, snapshot }`), `status`, `result`, and optional `cancel` (with `activeOnly` when the provider's cancel endpoint deletes finished work, as Runway's does: the route refreshes status first and skips terminal generations), each addressed by a route-owned `token` whose `Schema.Codec` makes it serializable. `MediaRoute.inline` and `MediaRoute.queued` compose the two kinds with `Endpoint` and `Auth`; the queued route decodes the token once at the boundary (`start` output or `resume` input) and closes over it in a token-free `GenerationRoute` (`status`/`result`/`cancel` are plain Effects), so `Generation` never sees the token's shape and only carries the encoded JSON for persistence. Polls reuse the route's auth and deployment headers plus the request's `http` overlay after `start`, and resolve relative paths against the route base URL (provider-issued absolute URLs such as fal's `status_url` pass through). `result` is always its own GET even when the provider returns output inside the status document, so `Generation.await` behaves the same after `start` and after `resume`. `PollContext.auth` carries only what `Auth` added or changed so protocols can hand download credentials to output assets as transient `Media.Asset.headers` (Veo) — never part of `source` or JSON. Status strings map through a per-protocol `STATUS` table via `MediaProtocol.status`; terminal generations without output fail through `output.ended` / `output.contentPolicy` with the provider document on `reason.body`. `GenerationAwaitOptions` (`AwaitOptions` in `src/generation.ts`, `{ poll?: Poll }`) is the one options type for `await`, `events`, `Video.generate`, and `Video.stream`.
+`MediaProtocol.queued` is the submit-then-poll kind every video route uses: `start` (body + decode into `{ token, snapshot }`), `status`, `result`, and optional `cancel` (with `activeOnly` when the provider's cancel endpoint deletes finished work, as Runway's does: the route refreshes status first and skips terminal generations), each addressed by a route-owned `token` whose `Schema.Codec` makes it serializable. `MediaRoute.inline` and `MediaRoute.queued` compose the two kinds with `Endpoint` and `Auth`; the queued route decodes the token once at the boundary (`start` output or `resume` input) and closes over it in a token-free `GenerationRoute` (`status`/`result`/`cancel` are plain Effects), so `Generation` never sees the token's shape and only carries the encoded JSON for persistence. Polls reuse the route's auth and deployment headers plus the request's `http` overlay after `start`, and resolve relative paths against the route base URL (provider-issued absolute URLs such as fal's `status_url` pass through). `result` is always its own GET even when the provider returns output inside the status document, so `Generation.await` behaves the same after `start` and after `resume`. `PollContext.auth` carries only what `Auth` added or changed so protocols can hand download credentials to output assets as transient `Media.Asset.headers` (Veo) — never part of `source` or JSON. Status strings map through a per-protocol `STATUS` table via `MediaProtocol.status`; terminal generations without output fail through `output.ended` / `output.contentPolicy` with the provider document on `reason.body`; a `failed` generation maps the provider's error code through a per-protocol `FAILURE` table via `MediaProtocol.failure` so rejected inputs are not reported as retryable `ProviderInternal`. `GenerationAwaitOptions` (`AwaitOptions` in `src/generation.ts`, `{ poll?: Poll }`) is the one options type for `await`, `events`, `Video.generate`, and `Video.stream`.

 `MediaProtocol.stream` is the incremental kind every speech route uses, with the same discipline as LLM protocols. `MediaRoute.stream` submits the caller's request as `MediaProtocol.Addressed<Request>` (`{ ...request, mode }`, `mode: "generate" | "stream"`), so one provider stays one protocol: `body.from`, the endpoint path, and `frames` read `request.mode` to pick the body, path, and framing. `frames(bytes, context)` returns frames — `Framing.sse`, `Framing.lines`, `Framing.document` (a single-document response shaped like a streamed record), or the raw `bytes` for chunked audio. `initial()` is fresh per-response parser state; `step` folds each frame into it and emits modality events; `finish(state, context)` runs once after the last frame with the request, body, and observed `http` (header-only usage lives there) and emits exactly one terminal event or fails with `route.incomplete()`. Keep parser state to real accumulators and derive anything the request or body determines in `finish`. `generate` runs the same stream and folds it with the modality's `collect`. Request-derived URL parameters go on the body's `query` (array values repeat the parameter), applied before route and caller `http.query`. Decode frames with `route.decodeFrame` and raise stream-time failures with `route.frameError` (the frame stays on `reason.body`); protocols never thread HTTP context, because the route fills `reason.http` on stream errors that lack it. Speech protocols share `protocols/utils/speech-stream.ts` for deltas, timestamps, voice ids, PCM and container descriptions, and the terminal asset.

-Every modality route is the inline | stream | queued union (transcription uses all three: OpenAI and Gemini stream, Deepgram is inline, AssemblyAI is queued), every client is `MediaClient.make(Service, { modality, responseEvents })` (`src/media-client.ts`), which dispatches on the route's `kind`, and every model composes through `composeRoute`. fal queue protocols come from `protocols/utils/fal-queue.ts`, bodies are `json`, `multipart`, or `binary` (a raw upload), and a queued protocol that must upload media before submitting implements `start.prepare` (`MediaProtocol.Prepare`; AssemblyAI `/v2/upload`).
+Every modality route is the inline | stream | queued union (transcription uses all three: OpenAI and Gemini stream, Deepgram and ElevenLabs are inline, AssemblyAI is queued), every client is `MediaClient.make(Service, { modality, responseEvents })` (`src/media-client.ts`), which dispatches on the route's `kind`, and every model composes through `composeRoute`. fal queue protocols come from `protocols/utils/fal-queue.ts`, bodies are `json`, `multipart`, or `binary` (a raw upload), and a queued protocol that must upload media before submitting implements `start.prepare` (`MediaProtocol.Prepare`; AssemblyAI `/v2/upload`).

 ### URL Construction

@@ -129,8 +129,9 @@ VercelAIGateway.configure().experimental.evaluation("typesafe-ai/jev")

 OpenRouter reads `OPENROUTER_API_KEY`. Vercel reads `AI_GATEWAY_API_KEY`, then `VERCEL_OIDC_TOKEN`.
 The common API uses `boolean`; System One routes lower it to native `noul`.
-Choice and score confidence plus score legends remain available in provider metadata, and the
-provider's rounded probabilities are returned unchanged.
+Choice and score answers include `confidence` when the provider returns it, such as
+`response.answers.department.confidence`. Score legends remain available in provider metadata, and
+the provider's rounded probabilities are returned unchanged.

 ## Alibaba Cloud Model Studio

@@ -752,7 +753,10 @@ const events = Video.stream({ model: Runway.configure({ apiKey }).video("gen4.5"

 Status polls, result fetches, cancels, and asset downloads all run through the same request executor with the route's
 auth. `Generation.await` and `Generation.events` fail with a
-`Timeout` reason when `poll.timeout` (default 10 minutes) elapses. Failed,
+`Timeout` reason when `poll.timeout` (default 10 minutes) elapses. Status polls and result fetches retry transient
+failures (rate limits, provider 5xx, network errors) with backoff that honors `retry-after`, always within
+`poll.timeout`; submits and cancels never retry. Interrupting a wait (or aborting its `signal`) does not cancel the
+provider job, which keeps running and billing: call `cancel()` to stop it. Failed,
 cancelled, and expired generations fail typed with the provider's terminal document on `reason.body`; moderation
 outcomes (Veo `raiMediaFilteredReasons`, xAI `respect_moderation`, Runway `SAFETY.*` codes) surface as `notices` when
 a video is still returned and as a `ContentPolicy` reason when nothing is.
@@ -773,7 +777,9 @@ Provider notes:
 The promise client exposes the same surface: `ai.video.start(...)` resolves to a handle with `await`, `events`,
 `result`, `refresh`, `cancel`, and `token`; `ai.video.generate`, `ai.video.resume(model, token)`, and
 `ai.video.stream` mirror the Effect API. The handle's `status` and `progress` are a snapshot from when it was
-created; `refresh()` resolves to a new handle.
+created; `refresh()` resolves to a new handle. Every promise method and stream accepts `{ signal }`: like `fetch`,
+aborting rejects the Promise or throws from the `for await` loop with `signal.reason` (an `AbortError` `DOMException`
+unless `abort(reason)` passed one), while `break` stops a stream without throwing.

 ```ts
 import { ai } from "@opencode/ai/promise"
@@ -871,11 +877,12 @@ for await (const event of ai.speech.stream({ model, text: "Hello from OpenCode."
 ## Transcription

 Transcription (speech-to-text) is the one modality whose providers use every route kind: OpenAI and Gemini stream,
-Deepgram answers inline, and AssemblyAI is queued. `Transcription.generate` and `Transcription.stream` work on all of
-them; `Transcription.start` / `resume` return a `Generation` on queued routes and fail with `UnsupportedOperation`
-elsewhere. Models come from `.transcription(...)` selectors on the `OpenAI`, `Google`, `Deepgram`, and `AssemblyAI`
-facades. Common fields (`language`, `prompt`, `timestamps: "none" | "segment" | "word"`, `diarize`, `speakers`) lower
-natively or fail with a typed `AIError` before any network call; a route may return more than asked.
+Deepgram and ElevenLabs answer inline, and AssemblyAI is queued. `Transcription.generate` and `Transcription.stream`
+work on all of them; `Transcription.start` / `resume` return a `Generation` on queued routes and fail with
+`UnsupportedOperation` elsewhere. Models come from `.transcription(...)` selectors on the `OpenAI`, `Google`,
+`Deepgram`, `ElevenLabs`, and `AssemblyAI` facades. Common fields (`language`, `prompt`,
+`timestamps: "none" | "segment" | "word"`, `diarize`, `speakers`) lower natively or fail with a typed `AIError` before
+any network call; a route may return more than asked.

 ```ts
 import { Console, Effect, Stream } from "effect"
@@ -887,7 +894,7 @@ const openai = OpenAI.configure({ apiKey: process.env.OPENAI_API_KEY })
 const program = Effect.gen(function* () {
  const audio = yield* Media.file("./call.mp3")

-  // Speaker-labelled segments; labels are provider-native strings ("A", "0", "spk:0").
+  // Speaker-labelled segments; labels are provider-native strings ("A", "0", "spk:0", "speaker_0").
  const response = yield* Transcription.generate({
    model: Deepgram.configure({ apiKey }).transcription("nova-3"),
    audio,
@@ -897,7 +904,7 @@ const program = Effect.gen(function* () {
  response.text // "Hello from OpenCode."
  response.segments // [{ text, startSeconds, endSeconds, speaker: "0" }]
  response.words // [{ text, startSeconds, endSeconds, speaker, confidence }]
-  response.language // the provider's own value, lowercased ("en", "english", "en_us")
+  response.language // the provider's own value, lowercased ("en", "eng", "english", "en_us")

  // Text deltas as the model transcribes, then one finish carrying the whole transcript.
  yield* Transcription.stream({ model: openai.transcription("gpt-4o-mini-transcribe"), audio }).pipe(
@@ -921,7 +928,12 @@ Provider notes:
 - **OpenAI** takes inline audio only; `diarize` needs `gpt-4o-transcribe-diarize`, timestamps need `whisper-1`, and `whisper-1` does not stream.
 - **Gemini** needs a transcribe model (`gemini-3.5-transcribe`); `prompt` and `speakers` fail typed.
 - **Deepgram** detects the language unless `language` is set; vocabulary goes in `providerOptions.keyterm`.
- **AssemblyAI** uploads inline audio before submitting and is the only route that accepts `speakers`.
+- **ElevenLabs** (`scribe_v2`) uploads inline audio as the multipart `file` and sends a URL as `source_url`. Words
+  always carry timestamps, and segments are speaker turns, so `diarize`, `timestamps: "segment"`, or `speakers` turns
+  on diarization. `speakers` is an upper bound (`num_speakers`); `prompt` fails typed (vocabulary goes in
+  `providerOptions.keyterms`), as do webhook delivery and per-channel output (`use_multi_channel` without
+  `multichannel_output_style: "combined"`).
+- **AssemblyAI** uploads inline audio before submitting and treats `speakers` as the exact speaker count.

 The promise client mirrors the Effect API:

@@ -1,7 +1,6 @@
 # Media generation in `@opencode/ai` — public API direction

-Status: phases 1–4 implemented (through Image queued routes and partial images; ElevenLabs Scribe transcription
-pending); phase 5 proposal.
+Status: phases 1–4 implemented (through Image queued routes and partial images); phase 5 proposal.

 ## Goal

@@ -271,8 +270,8 @@ Deferred: `Speech.session(...)` — input-streaming TTS where text arrives incre
 #### Transcription (STT)

 Shipped as the second half of phase 3 (`src/transcription.ts`, `src/transcription-client.ts`, protocols
-`openai-transcription`, `google-transcription`, `deepgram-transcription`, `assemblyai-transcription`; new `AssemblyAI`
-facade).
+`openai-transcription`, `google-transcription`, `deepgram-transcription`, `elevenlabs-transcription`,
+`assemblyai-transcription`; new `AssemblyAI` facade).

 ```ts
 const request = Transcription.request({
@@ -281,7 +280,7 @@ const request = Transcription.request({
  language: "en",                                  // provider-native passthrough
  timestamps: "segment",                           // none | segment | word
  diarize: true,
-  speakers: 2,                                     // exact speaker count (AssemblyAI only)
+  speakers: 2,                                     // speaker count (AssemblyAI exact, ElevenLabs maximum)
  providerOptions: { known_speaker_names: ["agent"] },
 })

@@ -309,17 +308,23 @@ upload); `packages/ai/AGENTS.md` (Media Routes) describes both.
 Settled rules:

 - **Timestamps.** A granularity the selected route or model cannot produce fails as `UnsupportedOperation`
-  (`media.timestamps`), following Speech; a route that returns more than asked (Deepgram and AssemblyAI always return
-  words) is not stripped. Segments always carry start and end times: Gemini times each transcription part from its
+  (`media.timestamps`), following Speech; a route that returns more than asked (Deepgram, ElevenLabs, and AssemblyAI
+  always return words) is not stripped. Segments always carry start and end times: Gemini times each transcription part from its
  word offsets, so segment timestamps and diarization also request word offsets there.
 - **Diarization.** `diarize` means segments (and words, where the provider labels them) carry `speaker`. Labels are
-  provider-native strings — OpenAI `A` or a known speaker name, Deepgram `0`, Gemini `spk:0`, AssemblyAI `A` — with no
-  cross-provider speaker model. `speakers` is the exact number of speakers to label, which AssemblyAI (`speakers_expected`, the only route that
-  accepts it) treats as a constraint rather than a hint.
+  provider-native strings — OpenAI `A` or a known speaker name, Deepgram `0`, Gemini `spk:0`, AssemblyAI `A`,
+  ElevenLabs `speaker_0` — with no cross-provider speaker model. `speakers` is the number of speakers to label:
+  AssemblyAI (`speakers_expected`) treats it as an exact constraint rather than a hint, and ElevenLabs
+  (`num_speakers`) as the maximum. Both turn on diarization for it; the other routes reject it.
+- **Segments from words.** ElevenLabs returns only a token list (`word`, `spacing`, `audio_event`), so its segments
+  are speaker turns: consecutive words and spacing with one `speaker_id`, text joined from the provider's own spacing
+  tokens. `words` drops spacing and audio events. Segments therefore need diarization, which `timestamps: "segment"`
+  turns on, as AssemblyAI's utterances need speaker labels.
 - **Language** is passed through (`language`, OpenAI `gpt-transcribe` `languages[]`, Gemini `languageCodes`,
-  AssemblyAI `language_code`). `response.language` is the provider's own value, lowercased but not normalized: an
-  ISO code on most routes (AssemblyAI's detection returns `en`), `english` from whisper-1. Deepgram and AssemblyAI
-  assume English unless asked to detect, so a missing `language` enables their detection.
+  AssemblyAI and ElevenLabs `language_code`). `response.language` is the provider's own value, lowercased but not
+  normalized: an ISO code on most routes (AssemblyAI's detection returns `en`, ElevenLabs ISO 639-3 `eng`), `english`
+  from whisper-1. Deepgram and AssemblyAI assume English unless asked to detect, so a missing `language` enables their
+  detection.
 - **Gemini** requires a transcribe model; other model ids fail with `UnsupportedOperation` before the call, because
  general models ignore `audioTranscriptionConfig` and answer conversationally. Streamed chunks carry whole speaker
  turns (one part per turn), which join with a space.
@@ -332,11 +337,12 @@ Settled rules:
 | OpenAI | stream (`stream: true` in `stream` mode; `whisper-1` ignores `stream`, so it emits only `finish`) | multipart `file` (inline only) | `whisper-1` (`verbose_json`); diarize model: `segment` | `gpt-4o-transcribe-diarize` (`diarized_json`) | `speakers`; `prompt` on the diarize model | `tokens` or `seconds` |
 | Gemini | stream (`generateContent` / `streamGenerateContent`) | `inlineData` or Gemini Files `fileData` | `audioTranscriptionConfig.wordTimestamp` | `audioTranscriptionConfig.diarization` | `prompt`, `speakers` | `tokens` |
 | Deepgram | inline | raw body, or JSON `{ url }` | words always; `segment` → `utterances` | `diarize_model=latest` + `utterances` | `prompt`, `speakers` | `seconds` (`metadata.duration`) |
+| ElevenLabs | inline | multipart `file`, or `source_url` | words always; `segment` → `diarize` (speaker turns) | `diarize` | `prompt`; `webhook`, per-channel `use_multi_channel` | `seconds` (`audio_duration_secs`) |
 | AssemblyAI | queued (upload → submit → poll) | `/v2/upload` then `audio_url`, or a URL | words always; `segment` → `speaker_labels` | `speaker_labels` | — | `seconds` (`audio_duration`) |

 Deferred: `Transcription.session(...)` — realtime STT over WebSocket (Deepgram live, AssemblyAI streaming, ElevenLabs
 realtime, OpenAI realtime transcription) — is the same future scoped `session` shape as input-streaming TTS and ships
-with the realtime work in phase 5. ElevenLabs Scribe is not implemented yet.
+with the realtime work in phase 5.

 ### `Generation` — shared async execution

@@ -361,6 +367,10 @@ Poll = { interval?: Duration; timeout?: Duration }

 `Generation` is not video-specific. Image routes on BFL, fal, Replicate, and Stability `upscale()` are queued; `Image.start` exists for them. A route declares itself `inline` or `queued`; `generate` on a queued route is `start` then `await`.

+Status polls and result reads retry transient failures (rate limits, provider 5xx, and transport errors, classified by the same `isRetryable` the Session runner uses) inside `MediaRoute.queued`. Only the HTTP exchange retries, never the decoded document: a terminal `failed` generation also surfaces as `ProviderInternal` and must not be re-read. Gaps grow exponentially from 1s with jitter, up to 30s each, honoring a provider `retry-after` up to that cap, for at most 8 retries. `await`, `events`, and `Video.stream` cut retries off at `poll.timeout` and fail with `Timeout`, so retries never extend the caller's deadline; a direct `result()` or `resume` read is bounded by the retry cap alone. `start` and `cancel` never retry: a repeated submit can start and bill a second job. The policy is internal; there is no option for it.
+
+Interrupting `await`, `events`, or `Video.stream` (or aborting the promise API's `signal`) stops waiting only. The provider job keeps running and billing; call `cancel()` explicitly to stop it.
+
 ### Usage

 ```ts
@@ -402,7 +412,7 @@ for await (const event of ai.llm.stream(request)) { … }
 await ai.dispose()
 ```

-Streams become `AsyncIterable` via `Stream.toAsyncIterable`. `AIError` is thrown as-is. `AbortSignal` maps to interruption. Nothing in `src/*` except this entrypoint knows about promises.
+Streams become `AsyncIterable` via `Stream.toAsyncIterable`. `AIError` is thrown as-is. Aborting an `AbortSignal` interrupts the work and, like `fetch`, rejects the Promise or throws from the stream with `signal.reason` instead of ending the stream as if complete. Nothing in `src/*` except this entrypoint knows about promises.

 ### Providers

@@ -414,7 +424,7 @@ implemented):
 | `OpenAI` | responses (default), chat | Images API (stream) | *Sora skipped (decision 8)* | ✓ | ✓ | |
 | `Google` | Gemini | Gemini-native | Veo | Gemini TTS | `gemini-3.5-transcribe` | |
 | `XAI` | ✓ | ✓ | ✓ | | | |
-| `ElevenLabs` | | | | ✓ | *Scribe (pending)* | *soundEffect, music (phase 5)* |
+| `ElevenLabs` | | | | ✓ | Scribe | *soundEffect, music (phase 5)* |
 | `Cartesia` | | | | ✓ | | |
 | `Deepgram` | | | | Aura | ✓ | |
 | `Fal` | | ✓ (queued) | ✓ | | | |
@@ -467,7 +477,7 @@ Foundation + Image ship together as the reference implementation, serially. Vide

 1. **Foundation** — per-modality selectors, `Media`, `Generation`, `Poll`, `Usage` union, `MediaProtocol` kinds, `@opencode/ai/promise` with `llm` + `image`. Port the five existing image protocols onto it. Unify `MediaPart` and add the `media` LLM event (fixes Gemini image output being dropped).
 2. **Video** — ✅ Veo, xAI, fal, Runway shipped (`MediaProtocol.queued`, `Video.start/generate/resume/stream`, promise `ai.video`). Deferred: `Video.complete` (webhooks), Luma, Kling, MiniMax, Replicate.
-3. **Speech + Transcription** — ✅ Speech: OpenAI, Gemini TTS, ElevenLabs, Cartesia, Deepgram shipped (`MediaProtocol.stream`, `Speech.generate/stream`, promise `ai.speech`). ✅ Transcription: OpenAI, Gemini, Deepgram, AssemblyAI shipped across all three route kinds (`Transcription.generate/stream/start/resume`, promise `ai.transcription`). Pending: ElevenLabs Scribe. Deferred: `Speech.session` and `Transcription.session` (WebSocket streaming).
+3. **Speech + Transcription** — ✅ Speech: OpenAI, Gemini TTS, ElevenLabs, Cartesia, Deepgram shipped (`MediaProtocol.stream`, `Speech.generate/stream`, promise `ai.speech`). ✅ Transcription: OpenAI, Gemini, Deepgram, ElevenLabs Scribe, AssemblyAI shipped across all three route kinds (`Transcription.generate/stream/start/resume`, promise `ai.transcription`). Deferred: `Speech.session` and `Transcription.session` (WebSocket streaming).
 4. **Image queued routes and partials** — ✅ BFL, fal, Replicate, and Stability creative upscale queued; Stability generate inline; OpenAI `partial_images` streaming (`image-partial` restored). Imagen dropped: shut down on the Gemini API and discontinued on Vertex (2026-06-30). Deferred: Stability's synchronous edit and fast/conservative upscale endpoints.
 5. **Later** — ElevenLabs music/SFX, Lyria, `Speech.session` / `Transcription.session`, realtime.

@@ -1,6 +1,6 @@
 {
  "$schema": "https://json.schemastore.org/package.json",
-  "version": "2.0.18",
+  "version": "2.0.19",
  "name": "@opencode/ai",
  "type": "module",
  "license": "MIT",
@@ -38,8 +38,15 @@ const resolve = (policy: CachePolicy | undefined): CachePolicyObject => {
 // prefix caching, Gemini's implicit + out-of-band CachedContent). Skip the
 // whole policy pass for these — emitting hints would be harmless but pointless.
 const RESPECTS_INLINE_HINTS = new Set([
+  "alibaba-messages",
  "anthropic-messages",
+  "anthropic-compatible-messages",
+  "cloudflare-ai-gateway-messages",
  "google-vertex-messages",
+  "meta-messages",
+  "minimax-messages",
+  "moonshot-messages",
+  "zai-coding-messages",
  "bedrock-converse",
  "openrouter",
 ])
@@ -63,6 +63,7 @@ export const ChoiceAnswer = Schema.Struct({
  type: Schema.Literal("choice"),
  choice: Schema.String,
  probabilities: Schema.optional(Schema.Record(Schema.String, Probability)),
+  confidence: Schema.optional(Probability),
 })
 export type ChoiceAnswer = Schema.Schema.Type<typeof ChoiceAnswer>

@@ -70,6 +71,7 @@ export const ScoreAnswer = Schema.Struct({
  type: Schema.Literal("score"),
  score: Schema.Number,
  probabilities: Schema.optional(Schema.Record(Schema.String, Probability)),
+  confidence: Schema.optional(Probability),
 })
 export type ScoreAnswer = Schema.Schema.Type<typeof ScoreAnswer>

@@ -92,6 +94,7 @@ export type AnswerFor<Question extends EvaluationQuestion> = Question extends {
      readonly type: "choice"
      readonly choice: Extract<keyof Criteria, string>
      readonly probabilities?: Readonly<Record<Extract<keyof Criteria, string>, number>>
+      readonly confidence?: number
    }
  : Question extends { readonly type: "score" }
    ? ScoreAnswer
@@ -142,32 +142,37 @@ export const model = <Options extends EvaluationOptions = EvaluationOptions>(cfg
            Effect.mapError((cause) => fail("System One returned an invalid response", cause, text)),
          )

-          const confidence: Record<string, number> = {}
          const legend: Record<string, Record<string, Schema.Json>> = {}
          const answers = Object.fromEntries(
            Object.entries(data.answers).map(([id, answer]): [string, EvaluationAnswer] => {
              if (answer.type === "noul") return [id, { type: "boolean", probability: answer.noul }]
              if (answer.type === "choice") {
-                if (answer.confidence !== undefined) confidence[id] = answer.confidence
                return [
                  id,
                  {
                    type: "choice",
                    choice: answer.choice,
                    probabilities: answer.probabilities,
+                    ...(answer.confidence === undefined ? {} : { confidence: answer.confidence }),
                  },
                ]
              }
-              if (answer.confidence !== undefined) confidence[id] = answer.confidence
              if (answer.legend !== undefined) legend[id] = answer.legend
-              return [id, { type: "score", score: answer.score, probabilities: answer.probabilities }]
+              return [
+                id,
+                {
+                  type: "score",
+                  score: answer.score,
+                  probabilities: answer.probabilities,
+                  ...(answer.confidence === undefined ? {} : { confidence: answer.confidence }),
+                },
+              ]
            }),
          )
          const meta = {
            ...(data.id === undefined ? {} : { responseId: data.id }),
            ...(data.provider === undefined ? {} : { provider: data.provider }),
            ...data.provider_metadata?.[cfg.providerMetadataKey],
-            ...(Object.keys(confidence).length === 0 ? {} : { confidence }),
            ...(Object.keys(legend).length === 0 ? {} : { legend }),
          }
          return new EvaluationResponse({
@@ -102,7 +102,7 @@ export class Generation<Response> {
    return settled.pipe(
      // Non-completed terminal states also go through `result` so the route can surface its provider failure body.
      Effect.flatMap((generation) => generation.result()),
-      Effect.timeoutOrElse({ duration: timeout, orElse: () => this.timeoutError(timeout) }),
+      Effect.timeoutOrElse({ duration: timeout, orElse: () => timeoutError(this.id, timeout) }),
    )
  }

@@ -123,20 +123,7 @@ export class Generation<Response> {
      Clock.currentTimeMillis.pipe(
        Effect.map((start) => {
          const deadline = start + Duration.toMillis(timeout)
-          // Fail before polling once the deadline has passed: a fast status request could otherwise win the zero-budget
-          // race and schedule another zero-delay poll.
-          const refresh = Clock.currentTimeMillis.pipe(
-            Effect.flatMap((now) =>
-              now >= deadline
-                ? this.timeoutError(timeout)
-                : this.refresh().pipe(
-                    Effect.timeoutOrElse({
-                      duration: Duration.millis(deadline - now),
-                      orElse: () => this.timeoutError(timeout),
-                    }),
-                  ),
-            ),
-          )
+          const refresh = within(this.refresh(), this.id, timeout, deadline)
          const schedule = this.schedule(options?.poll).pipe(
            Schedule.modifyDelay((meta) =>
              Effect.succeed(Duration.min(meta.duration, Duration.millis(Math.max(0, deadline - meta.now)))),
@@ -157,15 +144,6 @@ export class Generation<Response> {
    return { type: "generation-progress", id: this.id, progress: this.progress }
  }

-  private timeoutError(timeout: Duration.Duration) {
-    return new AIError({
-      reason: new TimeoutError({
-        message: `Generation ${this.id} did not finish within ${Duration.format(timeout)}`,
-        timeoutMs: Duration.toMillis(timeout),
-      }),
-    })
-  }
-
  private poll(poll: Poll | undefined) {
    return this.refresh().pipe(
      Effect.repeat({ schedule: this.schedule(poll), until: (generation) => generation.terminal }),
@@ -177,12 +155,53 @@ export class Generation<Response> {
  }
 }

+/** `events` followed by the expanded result, with the result fetch bounded by the same `poll.timeout` deadline. */
 export const resultEvents = <Response, A>(
  generation: Generation<Response>,
  expand: (response: Response) => ReadonlyArray<A>,
  options?: AwaitOptions,
-): Stream.Stream<Observation | A, AIError> =>
-  generation.events(options).pipe(
-    Stream.filter((event): event is Observation => event.type !== "generation-finished"),
-    Stream.concat(Stream.fromIterableEffect(Effect.map(generation.result(), expand))),
+): Stream.Stream<Observation | A, AIError> => {
+  const timeout = Duration.fromInputUnsafe(options?.poll?.timeout ?? DEFAULT_POLL_TIMEOUT)
+  return Stream.unwrap(
+    Clock.currentTimeMillis.pipe(
+      Effect.map((start) =>
+        generation.events(options).pipe(
+          Stream.filter((event): event is Observation => event.type !== "generation-finished"),
+          Stream.concat(
+            Stream.fromIterableEffect(
+              within(generation.result(), generation.id, timeout, start + Duration.toMillis(timeout)).pipe(
+                Effect.map(expand),
+              ),
+            ),
+          ),
+        ),
+      ),
+    ),
  )
+}
+
+/**
+ * Run `effect` within the time left until `deadline`. Fails before starting once the deadline has passed: a fast
+ * request could otherwise win the zero-budget race and schedule another zero-delay poll.
+ */
+const within = <A>(effect: Effect.Effect<A, AIError>, id: string, timeout: Duration.Duration, deadline: number) =>
+  Clock.currentTimeMillis.pipe(
+    Effect.flatMap((now) =>
+      now >= deadline
+        ? Effect.fail(timeoutError(id, timeout))
+        : effect.pipe(
+            Effect.timeoutOrElse({
+              duration: Duration.millis(deadline - now),
+              orElse: () => Effect.fail(timeoutError(id, timeout)),
+            }),
+          ),
+    ),
+  )
+
+const timeoutError = (id: string, timeout: Duration.Duration) =>
+  new AIError({
+    reason: new TimeoutError({
+      message: `Generation ${id} did not finish within ${Duration.format(timeout)}`,
+      timeoutMs: Duration.toMillis(timeout),
+    }),
+  })
@@ -4,7 +4,7 @@ export { ImageClient } from "./image-client.js"
 export { Auth } from "./route/auth.js"
 export { Provider } from "./provider.js"
 export { ProviderPackage } from "./provider-package.js"
-export { isContextOverflow, isContextOverflowFailure } from "./provider-error.js"
+export { isContextOverflow, isContextOverflowFailure, isRetryable } from "./provider-error.js"
 export type {
  RouteLanguageModelInput,
  RouteRoutedLanguageModelInput,
@@ -42,7 +42,7 @@ export type GenerationHandle<Response> = Snapshot & {
  /** Serializable JSON; pass it back to `resume` from another process. */
  readonly token: unknown
  readonly await: (options?: AwaitOptions & RunOptions) => Promise<Response>
-  /** Status observations until the first terminal one, polling like `await`; abort ends iteration without throwing. */
+  /** Status observations until the first terminal one, polling like `await`; abort throws `signal.reason`. */
  readonly events: (options?: AwaitOptions & RunOptions) => AsyncIterable<Event>
  /** The result without polling; fails when the generation has not completed. */
  readonly result: (options?: RunOptions) => Promise<Response>
@@ -50,15 +50,16 @@ export type GenerationHandle<Response> = Snapshot & {
  readonly cancel: (options?: RunOptions) => Promise<void>
 }

+// Fails with `signal.reason` so aborted calls reject and aborted streams throw like `fetch`: an `AbortError` by default.
 const abortEffect = (signal: AbortSignal | undefined) =>
  signal === undefined
    ? Effect.never
-    : Effect.callback<void>((resume) => {
+    : Effect.callback<never, unknown>((resume) => {
        if (signal.aborted) {
-          resume(Effect.void)
+          resume(Effect.fail(signal.reason))
          return
        }
-        const onAbort = () => resume(Effect.void)
+        const onAbort = () => resume(Effect.fail(signal.reason))
        signal.addEventListener("abort", onAbort, { once: true })
        return Effect.sync(() => signal.removeEventListener("abort", onAbort))
      })
@@ -68,14 +69,14 @@ export const make = (options: Options = {}) => {

  /** Run any package Effect (for example `LLMClient.compact(...)`) inside this runtime. */
  const run = <A, E>(effect: Effect.Effect<A, E, Services>, options?: RunOptions) =>
-    runtime.runPromise(effect, { signal: options?.signal })
+    runtime.runPromise(Effect.raceFirst(effect, abortEffect(options?.signal)))

  const iterate = <A, E>(stream: Stream.Stream<A, E, Services>, options?: RunOptions): AsyncIterable<A> =>
    Stream.toAsyncIterable(
      Stream.unwrap(
        runtime.contextEffect.pipe(
          Effect.map(
-            (context): Stream.Stream<A, E> =>
+            (context): Stream.Stream<A, unknown> =>
              stream.pipe(Stream.interruptWhen(abortEffect(options?.signal)), Stream.provideContext(context)),
          ),
        ),
@@ -29,6 +29,7 @@ import { JsonObject, knownString, optionalArray, optionalNull, ProviderShared }
 import { classifyProviderFailure } from "../provider-error.js"
 import { effortUpdate, resolveEffortUpdates } from "../effort-updates.js"
 import * as Cache from "./utils/cache.js"
+import { claudeVersion, supportsThinkingBlockBinding, THINKING_BINDING_BETA } from "./utils/claude-model.js"
 import { Lifecycle } from "./utils/lifecycle.js"
 import { ToolStream } from "./utils/tool-stream.js"

@@ -285,7 +286,13 @@ const AnthropicThinkingEnabled = Schema.Struct({
 })
 const AnthropicThinkingAdaptive = Schema.Struct({ type: Schema.tag("adaptive"), ...AnthropicThinkingFields })
 const AnthropicThinkingDisabled = Schema.Struct({ type: Schema.tag("disabled") })
-const AnthropicThinking = Schema.Union([AnthropicThinkingEnabled, AnthropicThinkingAdaptive, AnthropicThinkingDisabled])
+const AnthropicThinkingBetweenTools = Schema.Struct({ type: Schema.tag("between_tools") })
+const AnthropicThinking = Schema.Union([
+  AnthropicThinkingEnabled,
+  AnthropicThinkingAdaptive,
+  AnthropicThinkingDisabled,
+  AnthropicThinkingBetweenTools,
+])
 type AnthropicThinking = typeof AnthropicThinking.Type

 // SDK OutputConfig:2684 {effort?: "low"|"medium"|"high"|"xhigh"|"max"|null, format?: JSONOutputFormat:2399}
@@ -331,7 +338,20 @@ const ThinkingEnabledInput = Schema.Union([
    encode: SchemaGetter.passthrough({ strict: false }),
  }),
 )
-const Thinking = Schema.Union([ThinkingEnabledInput, AnthropicThinkingAdaptive, AnthropicThinkingDisabled])
+// Retain unsupported extra fields through decoding so we can reject them instead of silently stripping them.
+const ThinkingBetweenToolsInput = Schema.Struct({
+  type: Schema.tag("between_tools"),
+  display: Schema.optional(Schema.String),
+  block_binding: Schema.optional(AnthropicThinkingBlockBinding),
+  budget_tokens: Schema.optional(Schema.Number),
+  budgetTokens: Schema.optional(Schema.Number),
+})
+const Thinking = Schema.Union([
+  ThinkingEnabledInput,
+  AnthropicThinkingAdaptive,
+  AnthropicThinkingDisabled,
+  ThinkingBetweenToolsInput,
+])

 const OutputConfigInput = Schema.Struct({
  effort: optionalNull(Schema.String),
@@ -988,22 +1008,6 @@ const lowerMessages = Effect.fn("AnthropicMessages.lowerMessages")(function* (
  return messages
 })

-// Accept gateway namespaces and Vertex suffixes without treating a snapshot date as a minor version.
-const claudeVersion = (id: string) => {
-  const match = /(?:^|[./])claude-(?<family>[a-z]+)-(?<major>\d+)(?:[.-](?<minor>\d{1,2}))?(?:$|[-:@])/.exec(
-    id.toLowerCase(),
-  )?.groups
-  if (!match) return undefined
-  return { family: match.family, major: Number(match.major), minor: Number(match.minor ?? 0) }
-}
-
-const supportsThinkingBlockBinding = (model: LLMRequest["model"]) => {
-  const override = model.compatibility?.supportsThinkingBlockBinding
-  if (override !== undefined) return override
-  const version = claudeVersion(model.id)
-  return version !== undefined && (version.major > 5 || (version.major === 5 && version.minor >= 1))
-}
-
 const supportsEffortUpdates = (model: LLMRequest["model"]) => {
  const override = model.compatibility?.supportsEffortUpdates
  if (override !== undefined) return override
@@ -1015,7 +1019,7 @@ const supportsEffortUpdates = (model: LLMRequest["model"]) => {
 }

 const applyThinkingBindingDefault = (model: LLMRequest["model"], thinking: AnthropicThinking | undefined) => {
-  if (thinking?.type === "disabled") return thinking
+  if (thinking?.type === "disabled" || thinking?.type === "between_tools") return thinking
  if (!supportsThinkingBlockBinding(model)) return thinking
  return {
    ...(thinking ?? { type: "adaptive" as const }),
@@ -1042,12 +1046,51 @@ const fromRequest = Effect.fn("AnthropicMessages.fromRequest")(function* (reques
  const format = outputConfig?.format ?? undefined
  const updates = resolveEffortUpdates(request, options.effort ?? outputConfig?.effort ?? undefined)
  const generation = request.generation
+  const version = claudeVersion(request.model.id)
+  const sonnet55 = version?.family === "sonnet" && version.major === 5 && version.minor === 5
+  if (options.thinking?.type === "between_tools") {
+    if (!sonnet55) return yield* invalid("Anthropic Messages between_tools thinking requires Claude Sonnet 5.5")
+    if (options.thinking.display !== undefined) return yield* invalid("between_tools does not support display")
+    if (options.thinking.block_binding !== undefined)
+      return yield* invalid("between_tools does not support block_binding")
+    if (options.thinking.budget_tokens !== undefined || options.thinking.budgetTokens !== undefined)
+      return yield* invalid("between_tools does not support thinking budgets")
+    if (updates.effort === "xhigh" || updates.effort === "max")
+      return yield* invalid("Claude Sonnet 5.5 between_tools requires effort high or below")
+    if (
+      updates.request.messages.some((message) => {
+        const update = effortUpdate(message)
+        return update !== undefined && (update.effort ?? DEFAULT_EFFORT) !== (updates.effort ?? DEFAULT_EFFORT)
+      })
+    )
+      return yield* invalid("Claude Sonnet 5.5 between_tools cannot change effort mid-conversation")
+  }
+  if (sonnet55) {
+    if (options.thinking?.type === "disabled")
+      return yield* invalid(
+        "Claude Sonnet 5.5 does not support disabled thinking; use between_tools at high effort or below",
+      )
+    if (options.thinking?.type === "enabled")
+      return yield* invalid("Claude Sonnet 5.5 does not support thinking budgets; use adaptive thinking and effort")
+    if (generation?.temperature !== undefined && generation.temperature !== 1)
+      return yield* invalid("Claude Sonnet 5.5 does not support non-default sampling parameters")
+    if (generation?.topP !== undefined && generation.topP < 0.99)
+      return yield* invalid("Claude Sonnet 5.5 does not support non-default sampling parameters")
+    if (generation?.topK !== undefined)
+      return yield* invalid("Claude Sonnet 5.5 does not support top_k sampling; omit topK")
+  }
  // Allocate the 4-breakpoint budget in invalidation order: tools → system →
  // messages. Tools live highest in the cache hierarchy, so when callers
  // over-mark we keep their tool hints and shed the message-tail ones first.
  const breakpoints = Cache.newBreakpoints(ANTHROPIC_BREAKPOINT_CAP)
  const flattened = ProviderShared.flattenToolRequest(updates.request)
  const tools = flattened.tools.length === 0 ? undefined : flattened.tools.map((tool) => lowerTool(breakpoints, tool))
+  if (
+    sonnet55 &&
+    tools !== undefined &&
+    (request.toolChoice?.type === "required" || request.toolChoice?.type === "tool")
+  )
+    return yield* invalid("Claude Sonnet 5.5 does not support forced tool choice; use auto or none")
  // 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 systemParts = request.system.filter((part) => part.text.length > 0)
@@ -1080,7 +1123,10 @@ const fromRequest = Effect.fn("AnthropicMessages.fromRequest")(function* (reques
    top_p: generation?.topP,
    top_k: generation?.topK,
    stop_sequences: generation?.stop,
-    thinking: applyThinkingBindingDefault(request.model, fitThinking(options.thinking, maxTokens)),
+    thinking: applyThinkingBindingDefault(
+      request.model,
+      options.thinking?.type === "between_tools" ? { type: "between_tools" } : fitThinking(options.thinking, maxTokens),
+    ),
    output_config,
    // top-level passthrough per SDK MessageCreateParamsBase:4638,4643,4649,4654,4670
    cache_control: options.cache_control ?? options.cacheControl,
@@ -1652,8 +1698,8 @@ function requiredBetaHeaders(body: Pick<AnthropicMessagesBody, "messages" | "con
    betas.push("mid-conversation-output-config-2026-07-01")

  const thinking = body.thinking
-  if (thinking && thinking.type !== "disabled" && thinking.block_binding)
-    betas.push("thinking-binding-controls-2026-08-01")
+  if (thinking && (thinking.type === "adaptive" || thinking.type === "enabled") && thinking.block_binding)
+    betas.push(THINKING_BINDING_BETA)
  return betas
 }

@@ -23,6 +23,7 @@ import { JsonObject, optionalArray, ProviderShared } from "./shared.js"
 import { BedrockAuth } from "./utils/bedrock-auth.js"
 import { BedrockCache } from "./utils/bedrock-cache.js"
 import { BedrockMedia } from "./utils/bedrock-media.js"
+import { supportsThinkingBlockBinding, THINKING_BINDING_BETA } from "./utils/claude-model.js"
 import { Lifecycle } from "./utils/lifecycle.js"
 import { MistralToolID } from "./utils/mistral-tool-id.js"
 import { ToolStream } from "./utils/tool-stream.js"
@@ -443,6 +444,23 @@ const decodeOptions = ProviderShared.validateWith(Schema.decodeUnknownEffect(Opt
 // Claude on Bedrock requires the thinking budget below `maxTokens`, with a minimum of 1,024.
 const MIN_THINKING_BUDGET = 1_024

+const isThinkingDisabled = Schema.is(
+  Schema.Struct({
+    additionalModelRequestFields: Schema.Struct({ thinking: Schema.Struct({ type: Schema.Literal("disabled") }) }),
+  }),
+)
+
+// Claude 5.1+ binds each thinking signature to the prefix above it. Ask Bedrock to drop the affected blocks instead of
+// failing when that prefix changes. `http.body` overlays this field by field, so callers can still override it.
+const applyThinkingBindingDefault = (request: LLMRequest, thinking: Readonly<Record<string, unknown>> | undefined) => {
+  if (isThinkingDisabled(request.http?.body)) return thinking
+  if (!supportsThinkingBlockBinding(request.model)) return thinking
+  return {
+    ...(thinking ?? { type: "adaptive" as const }),
+    block_binding: { prefix_mismatch_behavior: "drop_block" },
+  }
+}
+
 const fromRequest = Effect.fn("BedrockConverse.fromRequest")(function* (request: LLMRequest) {
  const toolChoice = request.toolChoice ? yield* lowerToolChoice(request.toolChoice) : undefined
  const flattened = ProviderShared.flattenToolRequest(request)
@@ -450,7 +468,8 @@ const fromRequest = Effect.fn("BedrockConverse.fromRequest")(function* (request:
  const options = yield* decodeOptions(request.providerOptions ?? {})
  const maxTokens =
    isNova2(request.model) && isHighReasoningEffort(request.http?.body) ? undefined : generation?.maxTokens
-  const thinking =
+  const thinking = applyThinkingBindingDefault(
+    request,
    options.thinking === undefined
      ? undefined
      : {
@@ -460,7 +479,8 @@ const fromRequest = Effect.fn("BedrockConverse.fromRequest")(function* (request:
            maxTokens,
            MIN_THINKING_BUDGET,
          ),
-        }
+        },
+  )
  // Bedrock-Claude shares Anthropic's 4-breakpoint cap. Spend the budget in
  // tools → system → messages order to favour the highest-impact prefixes.
  const breakpoints = BedrockCache.breakpoints(request.model.id)
@@ -509,6 +529,8 @@ const fromRequest = Effect.fn("BedrockConverse.fromRequest")(function* (request:
        : {
            ...(generation?.topK === undefined ? {} : { top_k: generation.topK }),
            ...(thinking === undefined ? {} : { thinking }),
+            // Converse takes Anthropic betas in the body, and Bedrock rejects `block_binding` without this one.
+            ...(thinking?.block_binding === undefined ? {} : { anthropic_beta: [THINKING_BINDING_BETA] }),
          },
  }
 })
@@ -555,7 +577,7 @@ interface ParserState {
  readonly hasToolCalls: boolean
  readonly lifecycle: Lifecycle.State
  readonly reasoningSignatures: Readonly<Record<number, string>>
-  readonly reasoningRedactedContent: Readonly<Record<number, ReadonlyArray<Uint8Array>>>
+  readonly reasoningRedactedContent: Readonly<Record<number, Uint8Array[]>>
 }

 const encodeRedactedContent = (chunks: ReadonlyArray<Uint8Array>) => Encoding.encodeBase64(concatBytes(chunks))
@@ -605,10 +627,9 @@ const step = (state: ParserState, event: BedrockEvent) =>
      const index = event.contentBlockDelta.contentBlockIndex
      const reasoning = event.contentBlockDelta.delta.reasoningContent
      const events: LLMEvent[] = []
-      const redactedChunks = yield* (() => {
+      const redactedChunk = yield* (() => {
        if (reasoning.redactedContent === undefined) return Effect.succeed(undefined)
        return Effect.fromResult(Encoding.decodeBase64(reasoning.redactedContent)).pipe(
-          Effect.map((chunk) => [...(state.reasoningRedactedContent[index] ?? []), chunk]),
          Effect.mapError((cause) =>
            ProviderShared.eventError(
              ADAPTER,
@@ -619,17 +640,21 @@ const step = (state: ParserState, event: BedrockEvent) =>
          ),
        )
      })()
-      const redactedData = redactedChunks === undefined ? reasoning.data : encodeRedactedContent(redactedChunks)
+      const redactedChunks = state.reasoningRedactedContent[index] ?? []
+      if (redactedChunk !== undefined) redactedChunks.push(redactedChunk)
      const metadata = (() => {
        if (reasoning.signature) return providerMetadata(state.providerMetadataKey, { signature: reasoning.signature })
-        if (redactedData !== undefined) return providerMetadata(state.providerMetadataKey, { redactedData })
+        if (redactedChunk === undefined && reasoning.data !== undefined)
+          return providerMetadata(state.providerMetadataKey, { redactedData: reasoning.data })
      })()
      const lifecycle = (() => {
-        if (reasoning.text === undefined && metadata === undefined) return state.lifecycle
-        return Lifecycle.reasoningDelta(state.lifecycle, events, `reasoning-${index}`, reasoning.text ?? "", metadata)
+        if (reasoning.text !== undefined || metadata !== undefined)
+          return Lifecycle.reasoningDelta(state.lifecycle, events, `reasoning-${index}`, reasoning.text ?? "", metadata)
+        if (redactedChunk !== undefined) return Lifecycle.reasoningStart(state.lifecycle, events, `reasoning-${index}`)
+        return state.lifecycle
      })()
      const reasoningRedactedContent = (() => {
-        if (redactedChunks !== undefined) return { ...state.reasoningRedactedContent, [index]: redactedChunks }
+        if (redactedChunk !== undefined) return { ...state.reasoningRedactedContent, [index]: redactedChunks }
        if (reasoning.data === undefined) return state.reasoningRedactedContent
        return Object.fromEntries(
          Object.entries(state.reasoningRedactedContent).filter(([key]) => key !== String(index)),
@@ -765,7 +790,19 @@ const onHalt = (state: ParserState): ReadonlyArray<LLMEvent> => {
    return state.finishReason.normalized
  })()
  const events: LLMEvent[] = []
-  Lifecycle.finish(state.lifecycle, events, {
+  const lifecycle = Object.entries(state.reasoningRedactedContent).reduce((current, [index, chunks]) => {
+    const signature = state.reasoningSignatures[Number(index)]
+    return Lifecycle.reasoningEnd(
+      current,
+      events,
+      `reasoning-${index}`,
+      providerMetadata(
+        state.providerMetadataKey,
+        signature ? { signature } : { redactedData: encodeRedactedContent(chunks) },
+      ),
+    )
+  }, state.lifecycle)
+  Lifecycle.finish(lifecycle, events, {
    reason: {
      ...state.finishReason,
      normalized,
@@ -6,6 +6,7 @@ import { mergeJsonRecords, type OpenString } from "../schema/index.js"
 import { TranscriptionModel, TranscriptionResponse, type TranscriptionRequestFor } from "../transcription.js"
 import { ProviderShared } from "./shared.js"
 import { MediaInput } from "./utils/media-input.js"
+import { SpeakerTurns } from "./utils/speaker-turns.js"

 const route = MediaProtocol.identity({ id: "deepgram-transcription", name: "Deepgram", provider: "deepgram" })
 export const DEFAULT_BASE_URL = "https://api.deepgram.com"
@@ -115,16 +116,6 @@ const speaker = (value: number | undefined) => (value === undefined ? undefined

 const wordText = (word: typeof Word.Type) => word.punctuated_word ?? word.word

-// Utterances split on pauses, not speakers: the v2 diarizer labels a whole utterance with one speaker even when its
-// words change speaker, so segments split each utterance at speaker changes.
-const speakerTurns = (words: ReadonlyArray<typeof Word.Type>) =>
-  words.reduce<Array<Array<typeof Word.Type>>>((turns, word) => {
-    const last = turns.at(-1)
-    if (last === undefined || last[0].speaker !== word.speaker) return [...turns, [word]]
-    last.push(word)
-    return turns
-  }, [])
-
 const decodeResponse = Effect.fn("DeepgramTranscription.decodeResponse")(function* (
  response: HttpClientResponse.HttpClientResponse,
 ) {
@@ -136,6 +127,8 @@ const decodeResponse = Effect.fn("DeepgramTranscription.decodeResponse")(functio
  const requestID = output.value.metadata?.request_id
  return new TranscriptionResponse({
    text: alternative.transcript,
+    // Utterances split on pauses, not speakers: the v2 diarizer labels a whole utterance with one speaker even when
+    // its words change speaker, so segments split each utterance at speaker changes.
    segments: output.value.results.utterances?.flatMap((utterance) =>
      utterance.words === undefined || utterance.words.length === 0
        ? [
@@ -146,7 +139,7 @@ const decodeResponse = Effect.fn("DeepgramTranscription.decodeResponse")(functio
              speaker: speaker(utterance.speaker),
            },
          ]
-        : speakerTurns(utterance.words).map((turn) => ({
+        : SpeakerTurns.group(utterance.words, (word) => word.speaker).map((turn) => ({
            text: turn.map(wordText).join(" "),
            startSeconds: turn[0].start,
            endSeconds: turn[turn.length - 1].end,
@@ -0,0 +1,211 @@
+import { Effect, Schema } from "effect"
+import type { HttpClientResponse } from "effect/unstable/http"
+import { MediaProtocol } from "../route/media-protocol.js"
+import { MediaRoute } from "../route/media.js"
+import { mergeJsonRecords, type OpenString } from "../schema/index.js"
+import { TranscriptionModel, TranscriptionResponse, type TranscriptionRequestFor } from "../transcription.js"
+import { mediaTypeExtension } from "../utils/media-type.js"
+import { ProviderShared, optionalNull } from "./shared.js"
+import { MediaInput } from "./utils/media-input.js"
+import { SpeakerTurns } from "./utils/speaker-turns.js"
+
+const route = MediaProtocol.identity({
+  id: "elevenlabs-transcription",
+  name: "ElevenLabs Transcription",
+  provider: "elevenlabs",
+})
+export const DEFAULT_BASE_URL = "https://api.elevenlabs.io"
+export const PATH = "/v1/speech-to-text"
+
+// ---------------------------------------------------------------------------
+// 1. Public model input
+// ---------------------------------------------------------------------------
+
+export type ElevenLabsTranscriptionOptions = {
+  readonly tag_audio_events?: boolean
+  readonly timestamps_granularity?: OpenString<"none" | "word" | "character">
+  readonly diarization_threshold?: number
+  readonly file_format?: OpenString<"pcm_s16le_16" | "other">
+  readonly temperature?: number
+  readonly seed?: number
+  readonly keyterms?: ReadonlyArray<string>
+  readonly no_verbatim?: boolean
+  readonly detect_speaker_roles?: boolean
+  readonly use_speaker_library?: boolean
+  readonly entity_detection?: string | ReadonlyArray<string>
+  readonly entity_redaction?: string | ReadonlyArray<string>
+  readonly entity_redaction_mode?: OpenString<"redacted" | "entity_type" | "enumerated_entity_type">
+} & Record<string, unknown>
+
+export type Request = TranscriptionRequestFor<ElevenLabsTranscriptionOptions>
+
+// ---------------------------------------------------------------------------
+// 2. Response schema
+// ---------------------------------------------------------------------------
+
+/** `type` is `word`, `spacing` (the whitespace between words), or `audio_event` (`(laughter)`). */
+const Token = Schema.Struct({
+  text: Schema.String,
+  type: Schema.String,
+  start: optionalNull(Schema.Number),
+  end: optionalNull(Schema.Number),
+  speaker_id: optionalNull(Schema.String),
+  logprob: optionalNull(Schema.Number),
+})
+type Token = Schema.Schema.Type<typeof Token>
+
+const Transcript = Schema.Struct({
+  language_code: optionalNull(Schema.String),
+  text: Schema.String,
+  words: optionalNull(Schema.Array(Token)),
+  transcription_id: optionalNull(Schema.String),
+  audio_duration_secs: optionalNull(Schema.Number),
+})
+
+// ---------------------------------------------------------------------------
+// 5. Request body construction
+// ---------------------------------------------------------------------------
+
+/** Speaker turns are the only segments ElevenLabs can produce, and `num_speakers` only applies to diarization. */
+const diarizes = (request: Request) =>
+  request.diarize === true || request.timestamps === "segment" || request.speakers !== undefined
+
+const RESERVED_FORM_FIELDS = new Set([
+  "file",
+  "cloud_storage_url",
+  "source_url",
+  "model_id",
+  "language_code",
+  "diarize",
+  "num_speakers",
+])
+
+const validate = (request: Request, overlay: Record<string, unknown>) => {
+  // Webhook requests return 202 with no transcript; the result arrives at a configured webhook instead.
+  if (overlay.webhook === true)
+    return Effect.fail(route.unsupported("transcription.webhook", `${route.name} does not deliver to webhooks`))
+  // Separate multichannel output replaces the transcript with one transcript per channel.
+  if (overlay.use_multi_channel === true && overlay.multichannel_output_style !== "combined")
+    return Effect.fail(
+      route.unsupported(
+        "transcription.multichannel",
+        `${route.name} returns a single transcript; set multichannel_output_style: "combined" to merge channels`,
+      ),
+    )
+  if (overlay.timestamps_granularity === "none" && (request.timestamps === "word" || diarizes(request)))
+    return Effect.fail(
+      route.unsupported(
+        "media.timestamps",
+        `${route.name} cannot return word timestamps or speaker turns with timestamps_granularity: "none"`,
+      ),
+    )
+  return Effect.void
+}
+
+const fromRequest = Effect.fn("ElevenLabsTranscription.fromRequest")(function* (request: Request) {
+  const overlay = mergeJsonRecords(request.providerOptions, request.http?.body) ?? {}
+  yield* validate(request, overlay)
+  const form = new FormData()
+  const url = ProviderShared.mediaUrl(request.audio)
+  if (url === undefined) {
+    const extension = mediaTypeExtension(request.audio.mediaType)
+    const audio = yield* MediaInput.inlineBytes(route.id, request.audio)
+    form.append(
+      "file",
+      MediaInput.blob(audio, request.audio.mediaType),
+      extension === undefined ? "audio" : `audio.${extension}`,
+    )
+  }
+  MediaInput.appendFields(
+    form,
+    {
+      model_id: request.model.id,
+      // `cloud_storage_url` is deprecated in favor of `source_url`, which accepts any hosted audio or video URL.
+      source_url: url,
+      language_code: request.language,
+      diarize: diarizes(request) ? true : undefined,
+      num_speakers: request.speakers,
+    },
+    { overlay, reserved: RESERVED_FORM_FIELDS, repeatArrays: "key" },
+  )
+  return MediaProtocol.multipart(form)
+})
+
+// ---------------------------------------------------------------------------
+// 6. Response decoding
+// ---------------------------------------------------------------------------
+
+const decodeTranscript = route.decodeJson(Transcript)
+
+type TimedWord = Token & { readonly start: number; readonly end: number }
+
+const isTimedWord = (token: Token): token is TimedWord =>
+  token.type === "word" && typeof token.start === "number" && typeof token.end === "number"
+
+/** Turn text keeps the provider's own spacing tokens, so languages written without spaces are not re-spaced. */
+const speakerTurns = (tokens: ReadonlyArray<Token>) =>
+  SpeakerTurns.group(
+    tokens.filter((token) => token.type === "word" || token.type === "spacing"),
+    (token) => token.speaker_id,
+  ).flatMap((turn) => {
+    const words = turn.filter(isTimedWord)
+    if (words.length === 0) return []
+    return [
+      {
+        text: turn
+          .map((token) => token.text)
+          .join("")
+          .trim(),
+        startSeconds: words[0].start,
+        endSeconds: words[words.length - 1].end,
+        speaker: turn[0].speaker_id ?? undefined,
+      },
+    ]
+  })
+
+const decodeResponse = Effect.fn("ElevenLabsTranscription.decodeResponse")(function* (
+  response: HttpClientResponse.HttpClientResponse,
+  context: MediaProtocol.DecodeContext<Request>,
+) {
+  const output = yield* decodeTranscript(response)
+  const transcript = output.value
+  const tokens = transcript.words ?? []
+  const duration = transcript.audio_duration_secs ?? undefined
+  const transcriptionID = transcript.transcription_id ?? undefined
+  return new TranscriptionResponse({
+    text: transcript.text,
+    segments: diarizes(context.request) ? speakerTurns(tokens) : undefined,
+    words: tokens.filter(isTimedWord).map((word) => ({
+      text: word.text,
+      startSeconds: word.start,
+      endSeconds: word.end,
+      speaker: word.speaker_id ?? undefined,
+      confidence: typeof word.logprob === "number" ? Math.exp(word.logprob) : undefined,
+    })),
+    language: transcript.language_code?.toLowerCase(),
+    durationSeconds: duration,
+    usage: duration === undefined ? undefined : { type: "seconds", seconds: duration },
+    providerMetadata: transcriptionID === undefined ? undefined : { elevenlabs: { transcriptionId: transcriptionID } },
+  })
+})
+
+// ---------------------------------------------------------------------------
+// 7. Protocol and route
+// ---------------------------------------------------------------------------
+
+export const protocol = MediaProtocol.inline<Request, TranscriptionResponse>(route, {
+  unsupported: ["prompt"],
+  body: { from: fromRequest },
+  response: { decode: decodeResponse },
+})
+
+export const model = (input: MediaRoute.ModelInput) =>
+  TranscriptionModel.fromRoute<ElevenLabsTranscriptionOptions>(
+    { protocol, baseURL: DEFAULT_BASE_URL, path: PATH },
+    input,
+  )
+
+export const ElevenLabsTranscription = {
+  protocol,
+  model,
+} as const
@@ -36,7 +36,9 @@ const StartResponse = Schema.Struct({ name: Schema.String })

 const Operation = Schema.Struct({
  done: Schema.optional(Schema.Boolean),
-  error: Schema.optional(Schema.Struct({ message: Schema.optional(Schema.String) })),
+  error: Schema.optional(
+    Schema.Struct({ code: Schema.optional(Schema.Number), message: Schema.optional(Schema.String) }),
+  ),
  response: Schema.optional(
    Schema.Struct({
      generateVideoResponse: Schema.optional(
@@ -60,6 +62,16 @@ const Operation = Schema.Struct({
  metadata: Schema.optional(Schema.Unknown),
 })

+// Operation errors are `google.rpc.Status`; unlisted codes (INTERNAL, UNAVAILABLE, ...) are provider-side.
+const FAILURE = {
+  3: "InvalidRequest", // INVALID_ARGUMENT
+  7: "Authentication", // PERMISSION_DENIED
+  8: "RateLimit", // RESOURCE_EXHAUSTED
+  9: "InvalidRequest", // FAILED_PRECONDITION
+  11: "InvalidRequest", // OUT_OF_RANGE
+  16: "Authentication", // UNAUTHENTICATED
+} as const satisfies Record<number, MediaProtocol.Failure>
+
 // ---------------------------------------------------------------------------
 // 5. Request body construction
 // ---------------------------------------------------------------------------
@@ -154,6 +166,7 @@ const decodeResult = Effect.fn("GoogleVideo.decodeResult")(function* (
    return yield* output.ended(
      "failed",
      `${route.name} operation failed${operation.error?.message === undefined ? "" : `: ${operation.error.message}`}`,
+      MediaProtocol.failure(FAILURE, operation.error?.code),
    )
  const generated = operation.response?.generateVideoResponse
  // Downloads require the same API key as the poll; the asset carries it transiently and follows the redirect.
@@ -10,14 +10,19 @@ const WebSearch = Schema.Struct({
  name: Schema.Literal("web_search"),
  user_location: MetaResponses.WebSearch.fields.user_location,
 })
+const MetaCacheControl = Schema.Struct({
+  type: Schema.tag("ephemeral"),
+  ttl: Schema.optional(Schema.Literals(["5m", "1h"])),
+})
+const FunctionTool = Schema.Struct({
+  name: Schema.String,
+  description: Schema.String,
+  input_schema: JsonObject,
+  cache_control: Schema.optional(MetaCacheControl),
+})
 const Body = Schema.Struct({
  ...AnthropicMessages.AnthropicMessagesBody.fields,
-  tools: optionalArray(
-    Schema.Union([
-      Schema.Struct({ name: Schema.String, description: Schema.String, input_schema: JsonObject }),
-      WebSearch,
-    ]),
-  ),
+  tools: optionalArray(Schema.Union([FunctionTool, WebSearch])),
 })

 const fromRequest = Effect.fn("MetaMessages.fromRequest")(function* (request: LLMRequest) {
@@ -64,6 +64,14 @@ const OpenAIChatTool = Schema.Struct({
 })
 type OpenAIChatTool = Schema.Schema.Type<typeof OpenAIChatTool>

+// Gemini's OpenAI-compatible surface carries thought signatures in tool call
+// `extra_content` and rejects replayed parallel calls without them:
+// https://ai.google.dev/gemini-api/docs/thinking#signatures
+const ExtraContent = Schema.Struct({
+  google: Schema.Struct({ thought_signature: Schema.String }),
+})
+const decodeExtraContent = (value: unknown) => Option.getOrUndefined(Schema.decodeUnknownOption(ExtraContent)(value))
+
 const OpenAIChatAssistantToolCall = Schema.Struct({
  id: Schema.String,
  type: Schema.tag("function"),
@@ -71,6 +79,7 @@ const OpenAIChatAssistantToolCall = Schema.Struct({
    name: Schema.String,
    arguments: Schema.String,
  }),
+  extra_content: Schema.optional(ExtraContent),
 })
 type OpenAIChatAssistantToolCall = Schema.Schema.Type<typeof OpenAIChatAssistantToolCall>

@@ -112,12 +121,6 @@ const decodeReasoningDetail = Schema.decodeUnknownOption(ReasoningDetail)
 const knownReasoningDetails = (details: ReadonlyArray<unknown>) =>
  details.flatMap((detail) => Option.toArray(decodeReasoningDetail(detail)))

-// Intentionally omit Gemini's provider-specific `extra_content.google.thought_signature`
-// extension until direct Google OpenAI-compatible routing is supported here:
-// https://github.com/vercel/ai/issues/11590
-// https://github.com/vercel/ai/pull/11745
-// https://ai.google.dev/gemini-api/docs/thought-signatures#openai
-
 const OpenAIChatUserContent = Schema.Union([
  Schema.Struct({
    type: Schema.Literal("text"),
@@ -242,6 +245,7 @@ const OpenAIChatToolCallDelta = Schema.Struct({
  index: optionalNull(Schema.Number),
  id: optionalNull(Schema.String),
  function: optionalNull(OpenAIChatToolCallDeltaFunction),
+  extra_content: optionalNull(Schema.Unknown),
 })
 type OpenAIChatToolCallDelta = Schema.Schema.Type<typeof OpenAIChatToolCallDelta>

@@ -294,6 +298,7 @@ interface PendingToolDelta {
  readonly id?: string
  readonly name?: string
  readonly input: string
+  readonly extraContent?: Schema.Schema.Type<typeof ExtraContent>
 }

 export interface ParserState {
@@ -347,13 +352,17 @@ const lowerToolChoice = (toolChoice: NonNullable<LLMRequest["toolChoice"]>) =>
    tool: (name) => ({ type: "function" as const, function: { name } }),
  })

-const lowerToolCall = (part: ToolCallPart, options: LoweringOptions): OpenAIChatAssistantToolCall => ({
+const lowerToolCall = (
+  part: ToolCallPart,
+  options: LoweringOptions & { readonly providerMetadataKey: string },
+): OpenAIChatAssistantToolCall => ({
  id: options.toolCallID?.(part.id) ?? part.id,
  type: "function",
  function: {
    name: part.name,
    arguments: ProviderShared.encodeJson(part.input === undefined ? {} : part.input),
  },
+  extra_content: decodeExtraContent(part.providerMetadata?.[options.providerMetadataKey]?.extraContent),
 })

 const lowerMedia = Effect.fn("OpenAIChat.lowerMedia")(function* (part: MediaPart) {
@@ -721,7 +730,9 @@ const detectSupportsStore = (provider: string, baseURL: string | undefined): boo
    p === "vercel-ai-gateway" || url.includes("ai-gateway.vercel.sh") || url.includes("vercel.sh")
  const isAntLing = p === "ant-ling" || url.includes("api.ant-ling.com")
  const isOpencode = p === "opencode" || url.includes("opencode.ai")
+  const isGemini = url.includes("generativelanguage.googleapis.com")
  const isNonStandard =
+    isGemini ||
    isNvidia ||
    isCerebras ||
    isXai ||
@@ -1114,12 +1125,13 @@ const step = (state: ParserState, event: OpenAIChatEvent) =>
      const id = current?.id ?? pending?.id ?? (tool.id || undefined)
      const name = current?.name ?? pending?.name ?? (tool.function?.name || undefined)
      const text = `${pending?.input ?? ""}${tool.function?.arguments ?? ""}`
+      const extraContent = pending?.extraContent ?? decodeExtraContent(tool.extra_content)
      latestToolIndex = index
      nextToolIndex = Math.max(nextToolIndex, index + 1)
      if (!current && (!id || !name)) {
        pendingTools = {
          ...pendingTools,
-          [index]: { id: id || undefined, name: name || undefined, input: text },
+          [index]: { id: id || undefined, name: name || undefined, input: text, extraContent },
        }
        continue
      }
@@ -1131,7 +1143,12 @@ const step = (state: ParserState, event: OpenAIChatEvent) =>
        ADAPTER,
        tools,
        index,
-        { id: id || undefined, name: name || undefined, text },
+        {
+          id: id || undefined,
+          name: name || undefined,
+          text,
+          providerMetadata: extraContent && { [state.providerMetadataKey]: { extraContent } },
+        },
        "OpenAI Chat tool call delta is missing id or name",
      )
      if (ToolStream.isError(result))
@@ -193,7 +193,7 @@ const fromRequest = Effect.fn("OpenAITranscription.fromRequest")(function* (requ
    {
      overlay: mergeJsonRecords(request.providerOptions, request.http?.body),
      reserved: RESERVED_FORM_FIELDS,
-      repeatArrays: true,
+      repeatArrays: "key[]",
    },
  )
  return MediaProtocol.multipart(form)
@@ -137,7 +137,12 @@ const decodeResult = Effect.fn("RunwayVideo.decodeResult")(function* (
    const message = `${route.name} task failed${code === undefined ? "" : ` (${code})`}${task.failure ? `: ${task.failure}` : ""}`
    // Runway failure codes are dotted paths; every moderation outcome carries a SAFETY segment.
    if (code !== undefined && /(^|\.)SAFETY(\.|$)/.test(code)) return yield* output.contentPolicy(message)
-    return yield* output.ended("failed", message)
+    // ASSET.INVALID rejects the caller's input media; Runway documents it as not retryable.
+    return yield* output.ended(
+      "failed",
+      message,
+      code !== undefined && /^ASSET\.INVALID(\.|$)/.test(code) ? "InvalidRequest" : "ProviderInternal",
+    )
  }
  if (status === "cancelled")
    return yield* output.ended("cancelled", `${route.name} task ${context.token.taskID} was cancelled`)
@@ -0,0 +1,19 @@
+import type { LLMRequest } from "../../schema/index.js"
+
+export const THINKING_BINDING_BETA = "thinking-binding-controls-2026-08-01"
+
+// Accept gateway namespaces and Vertex suffixes without treating a snapshot date as a minor version.
+export const claudeVersion = (id: string) => {
+  const match = /(?:^|[./])claude-(?<family>[a-z]+)-(?<major>\d+)(?:[.-](?<minor>\d{1,2}))?(?:$|[-:@])/.exec(
+    id.toLowerCase(),
+  )?.groups
+  if (!match) return undefined
+  return { family: match.family, major: Number(match.major), minor: Number(match.minor ?? 0) }
+}
+
+export const supportsThinkingBlockBinding = (model: LLMRequest["model"]) => {
+  const override = model.compatibility?.supportsThinkingBlockBinding
+  if (override !== undefined) return override
+  const version = claudeVersion(model.id)
+  return version !== undefined && (version.major > 5 || (version.major === 5 && version.minor >= 1))
+}
@@ -71,8 +71,9 @@ export const imageOutput = (
 }

 /**
- * Append multipart text fields: strings as-is, other values as JSON, or arrays as repeated `key[]` parts with
- * `repeatArrays`. `overlay` keys in `reserved` are dropped so `http.body` cannot replace route-owned fields.
+ * Append multipart text fields: strings as-is, other values as JSON, or scalar arrays as one part per item with
+ * `repeatArrays`, named `key[]` or `key`. `overlay` keys in `reserved` are dropped so `http.body` cannot replace
+ * route-owned fields.
 */
 export const appendFields = (
  form: FormData,
@@ -80,13 +81,13 @@ export const appendFields = (
  options: {
    readonly overlay?: Record<string, unknown>
    readonly reserved: ReadonlySet<string>
-    readonly repeatArrays?: true
+    readonly repeatArrays?: "key[]" | "key"
  },
 ) => {
  const overlay = Object.entries(options.overlay ?? {}).filter(([key]) => !options.reserved.has(key))
  Object.entries(mergeJsonRecords(fields, Object.fromEntries(overlay)) ?? {}).forEach(([key, value]) => {
-    if (Array.isArray(value) && options.repeatArrays)
-      return value.forEach((item) => form.append(`${key}[]`, String(item)))
+    if (Array.isArray(value) && value.every(isScalar) && options.repeatArrays !== undefined)
+      return value.forEach((item) => form.append(options.repeatArrays === "key[]" ? `${key}[]` : key, String(item)))
    form.append(key, typeof value === "string" ? value : encodeJson(value))
  })
 }
@@ -0,0 +1,10 @@
+/** Split an ordered token list into runs of consecutive tokens with the same speaker. */
+export const group = <Item>(items: ReadonlyArray<Item>, speaker: (item: Item) => unknown) =>
+  items.reduce<Array<Array<Item>>>((turns, item) => {
+    const last = turns.at(-1)
+    if (last === undefined || speaker(last[0]) !== speaker(item)) return [...turns, [item]]
+    last.push(item)
+    return turns
+  }, [])
+
+export * as SpeakerTurns from "./speaker-turns.js"
@@ -147,7 +147,12 @@ export const appendOrStart = <K extends StreamKey>(
  route: string,
  tools: State<K>,
  key: K,
-  delta: { readonly id?: string; readonly name?: string; readonly text: string },
+  delta: {
+    readonly id?: string
+    readonly name?: string
+    readonly text: string
+    readonly providerMetadata?: ProviderMetadata
+  },
  missingToolMessage: string,
 ): AppendOutcome<K> | AIError => {
  const current = tools[key]
@@ -161,7 +166,7 @@ export const appendOrStart = <K extends StreamKey>(
    namespace: current?.namespace,
    input: `${current?.input ?? ""}${delta.text}`,
    providerExecuted: current?.providerExecuted,
-    providerMetadata: current?.providerMetadata,
+    providerMetadata: current?.providerMetadata ?? delta.providerMetadata,
  }
  if (current && delta.text.length === 0 && current.id === id && current.name === name)
    return { tools, tool: current, events: [] }
@@ -65,6 +65,13 @@ const STATUS = {
  expired: "expired",
 } as const satisfies Record<string, Status>

+// Documented video error codes; `service_unavailable`, `internal_error`, and unknown codes are provider-side.
+const FAILURE = {
+  invalid_argument: "InvalidRequest",
+  failed_precondition: "InvalidRequest",
+  permission_denied: "Authentication",
+} as const satisfies Record<string, MediaProtocol.Failure>
+
 // ---------------------------------------------------------------------------
 // 5. Request body construction
 // ---------------------------------------------------------------------------
@@ -143,6 +150,7 @@ const decodeResult = Effect.fn("XAIVideo.decodeResult")(function* (
    return yield* output.ended(
      "failed",
      `${route.name} generation failed${code === undefined ? "" : ` (${code})`}${message === undefined ? "" : `: ${message}`}`,
+      MediaProtocol.failure(FAILURE, code),
    )
  }
  if (status !== "completed")
@@ -1,4 +1,4 @@
-import { Option, Schema } from "effect"
+import { Option, Schema, SchemaGetter } from "effect"
 import {
  AuthenticationError,
  ContentPolicyError,
@@ -58,6 +58,47 @@ export const isContextOverflowFailure = (failure: unknown) =>
    ? failure.reason._tag === "InvalidRequest" && failure.reason.classification === "context-overflow"
    : Schema.is(ProviderErrorEvent)(failure) && failure.classification === "context-overflow"

+/**
+ * Whether a failed call may succeed when sent again: rate limits, provider-side failures, transport failures that did
+ * not deliver an accepted write, and unrecognized failures. Callers decide which calls are safe to repeat.
+ */
+export const isRetryable = (error: AIError) => {
+  const override = error.reason.http?.headers["x-should-retry"]
+  if (override === "true") return true
+  if (override === "false") return false
+  switch (error.reason._tag) {
+    case "RateLimit":
+    case "ProviderInternal":
+      return true
+    // A WebSocket acknowledgment marks delivery accepted before model output may exist.
+    // Read failures can still recover; the caller chooses retry versus continuation from durable output.
+    case "Transport":
+      return (
+        error.reason.delivery !== "rejected" &&
+        (error.reason.delivery !== "accepted" || error.reason.operation === "read")
+      )
+    case "InvalidProviderOutput":
+      return error.reason.classification === "incomplete-stream"
+    // Unrecognized failures retry: classification records affirmative
+    // deterministic evidence, and transient failures are exactly the ones
+    // that arrive in shapes no classifier anticipates.
+    case "UnknownProvider":
+      return true
+    case "Authentication":
+    case "QuotaExceeded":
+    case "ContentPolicy":
+    case "InvalidRequest":
+    case "UnsupportedOperation":
+    case "NoRoute":
+    case "Timeout":
+      return false
+    default: {
+      const exhaustive: never = error.reason
+      return exhaustive
+    }
+  }
+}
+
 const decodeJson = Schema.decodeUnknownOption(Schema.fromJsonString(Schema.Unknown))
 // OpenCode Zen reports account caps as typed 429/402 errors that are not throttles.
 const QUOTA_CODES = new Set([
@@ -68,7 +109,8 @@ const QUOTA_CODES = new Set([
  "freeusagelimiterror",
  "creditlimitexceeded",
 ])
-const AUTH_CODES = new Set(["authentication_error", "permission_error"])
+// Google reports an invalid API key as HTTP 400 INVALID_ARGUMENT with this `details[].reason`.
+const AUTH_CODES = new Set(["authentication_error", "permission_error", "api_key_invalid"])
 const SERVER_CODES = new Set([
  "api_error",
  "internal_error",
@@ -113,6 +155,41 @@ const CONTENT_POLICY_TEXT =
 const SERVER_ERROR_TEXT =
  /\b(?:try again|(?:please |you can )?retry (?:the |this |your )?request|try (?:the |this |your )?request again|(?:currently |temporarily )?at capacity|overloaded|temporarily unavailable|service[-_\s]?unavailable|(?:server|internal)[-_\s]?error|server (?:is )?busy|provider returned (?:an )?error|resource[-_\s]?exhausted|upstream (?:connect|connection|request)|request buffer limit while retrying upstream)\b/i

+const Message = Schema.String.check(Schema.isPattern(/\S/))
+
+const messageAt = <Fields extends Schema.Struct.Fields>(
+  fields: Fields,
+  message: (body: Schema.Struct<Fields>["Type"]) => string,
+) =>
+  Schema.Struct(fields).pipe(
+    Schema.decodeTo(Schema.String, {
+      decode: SchemaGetter.transform(message),
+      encode: SchemaGetter.forbidden(() => "Provider error messages are decode-only"),
+    }),
+  )
+
+// Common error body layouts that carry a human-readable message, in priority order.
+// Provider-specific layouts belong in their protocol.
+const decodeMessage = Schema.decodeUnknownOption(
+  Schema.fromJsonString(
+    Schema.Union([
+      messageAt({ error: Schema.Struct({ message: Message }) }, (body) => body.error.message),
+      messageAt({ error: Message }, (body) => body.error),
+      messageAt({ message: Message }, (body) => body.message),
+      // AWS services
+      messageAt({ Message: Message }, (body) => body.Message),
+      // RFC 9457 problem details
+      messageAt({ detail: Message }, (body) => body.detail),
+      messageAt(
+        { errors: Schema.NonEmptyArray(Schema.Struct({ message: Message })) },
+        (body) => body.errors[0].message,
+      ),
+    ]),
+  ),
+)
+
+export const providerErrorMessage = (body: string) => Option.getOrUndefined(decodeMessage(body))
+
 export interface ProviderFailure {
  readonly message: string
  readonly status?: number | undefined
@@ -218,6 +295,10 @@ function providerCodes(value: unknown) {
    error?.type,
    error?.status,
    error?.error_type,
+    // Google `google.rpc.ErrorInfo` details carry the specific reason.
+    ...(Array.isArray(error?.details)
+      ? error.details.map((detail) => (isRecord(detail) ? detail.reason : undefined))
+      : []),
    inner?.code,
    metadata?.error_type,
    responseError?.code,
@@ -28,7 +28,8 @@ export type Settings = ProviderPackage.Settings &
    readonly provider?: string
  }

-export const routes = [AnthropicMessages.route]
+const compatibleRoute = AnthropicMessages.route.with({ id: "anthropic-compatible-messages", provider: id })
+export const routes = [compatibleRoute]

 const auth = (input: ProviderAuthOption<"optional">) => {
  if ("auth" in input && input.auth) return input.auth
@@ -43,7 +44,7 @@ export const configure = (input: Config) => {
      message: "Anthropic-compatible providers require a baseURL",
    })
  const { provider: _, baseURL, apiKey: _apiKey, auth: _auth, ...rest } = input
-  const route = AnthropicMessages.route.with({
+  const route = (provider === "anthropic" ? AnthropicMessages.route : compatibleRoute).with({
    ...rest,
    provider,
    endpoint: { baseURL },
@@ -3,8 +3,10 @@ import type { ProviderAuthOption } from "../route/auth-options.js"
 import { MediaRoute } from "../route/media.js"
 import { type HttpOptions, ProviderID, type ModelID } from "../schema/index.js"
 import { ElevenLabsSpeech } from "../protocols/elevenlabs-speech.js"
+import { ElevenLabsTranscription } from "../protocols/elevenlabs-transcription.js"

 export type { ElevenLabsOutputFormat, ElevenLabsSpeechOptions } from "../protocols/elevenlabs-speech.js"
+export type { ElevenLabsTranscriptionOptions } from "../protocols/elevenlabs-transcription.js"

 export const id = ProviderID.make("elevenlabs")

@@ -24,12 +26,15 @@ const auth = (options: ProviderAuthOption<"optional">) => {
 export const configure = (input: Config = {}) => {
  const media = MediaRoute.deployment(input, auth(input))
  const speech = (modelID: string | ModelID) => ElevenLabsSpeech.model({ ...media, id: modelID })
+  const transcription = (modelID: string | ModelID) => ElevenLabsTranscription.model({ ...media, id: modelID })
  return {
    id,
    speech,
+    transcription,
    configure,
  }
 }

 export const provider = configure()
 export const speech = provider.speech
+export const transcription = provider.transcription
@@ -35,13 +35,13 @@ const RESPONSES_WEBSOCKET_ROTATE_AFTER_MS = 24 * 60 * 1000

 const responsesRoute = Route.make({
  compact: { endpoint: XAIResponses.compact },
-  id: "openai-responses",
+  id: "xai-responses",
  provider: id,
  providerMetadataKey: "xai",
  protocol: XAIResponses.protocol,
  endpoint: Endpoint.path("/responses", { baseURL }),
  transport: OpenResponsesChannel.transport({
-    id: "openai-responses",
+    id: "xai-responses",
    name: "xAI Responses",
    rotateAfterMs: RESPONSES_WEBSOCKET_ROTATE_AFTER_MS,
    // xAI continues a chain only from stored responses: with `store: false` (the route default) `previous_response_id`
@@ -53,7 +53,7 @@ const responsesRoute = Route.make({
 })

 const chatRoute = Route.make({
-  id: "openai-compatible-chat",
+  id: "xai-chat",
  provider: id,
  providerMetadataKey: "xai",
  protocol: OpenAIChat.protocol,
@@ -8,7 +8,7 @@ import {
  HttpClientResponse,
 } from "effect/unstable/http"
 import { HttpContext, HttpRateLimitDetails, AIError, TransportError } from "../schema/index.js"
-import { classifyProviderFailure } from "../provider-error.js"
+import { classifyProviderFailure, providerErrorMessage } from "../provider-error.js"
 import { Service, type HttpMiddleware, type Interface } from "./executor-service.js"

 export { Service } from "./executor-service.js"
@@ -84,21 +84,17 @@ export const responseHttp = (response: HttpClientResponse.HttpClientResponse) =>
    headers: headerDetails(response.headers),
  })

-const decodeProviderBody = Schema.decodeUnknownOption(
-  Schema.fromJsonString(
-    Schema.Struct({
-      message: Schema.optionalKey(Schema.String),
-      error: Schema.optionalKey(Schema.Struct({ message: Schema.optionalKey(Schema.String) })),
-    }),
-  ),
-)
+const MAX_BODY_CHARS = 2000

+// Without a recognized message, show the raw body so the provider's explanation is never dropped.
 const providerMessage = (status: number, body: string | void) => {
-  const decoded = body === undefined ? undefined : Option.getOrUndefined(decodeProviderBody(body))
-  return (
-    [decoded?.error?.message, decoded?.message].find((message) => message?.trim()) ??
-    `Provider request failed with HTTP ${status}`
-  )
+  const fallback = `Provider request failed with HTTP ${status}`
+  const text = body?.trim() ?? ""
+  const message = providerErrorMessage(text)
+  if (message) return message
+  // Gateway and proxy HTML error pages are markup, not an explanation.
+  if (!text || /^<(?:!doctype|html)/i.test(text)) return fallback
+  return `${fallback}: ${text.length > MAX_BODY_CHARS ? `${text.slice(0, MAX_BODY_CHARS)}…` : text}`
 }

 const statusError = (response: HttpClientResponse.HttpClientResponse) =>
@@ -5,12 +5,14 @@ import { Media } from "../media.js"
 import type { AuthInput } from "./auth.js"
 import {
  AIError,
+  AuthenticationError,
  ContentPolicyError,
  HttpContext,
  InvalidProviderOutputError,
  InvalidRequestError,
  ProviderID,
  ProviderInternalError,
+  RateLimitError,
  UnsupportedOperationError,
 } from "../schema/index.js"

@@ -188,6 +190,16 @@ export const stream = <Request, Event, Frame, State>(
 // Response helpers
 // ---------------------------------------------------------------------------

+/** Reasons a provider can report for a `failed` generation; anything it does not classify is `ProviderInternal`. */
+const FAILURES = {
+  InvalidRequest: InvalidRequestError,
+  Authentication: AuthenticationError,
+  RateLimit: RateLimitError,
+  ProviderInternal: ProviderInternalError,
+}
+
+export type Failure = keyof typeof FAILURES
+
 const context = (response: HttpClientResponse.HttpClientResponse) =>
  new HttpContext({ url: response.request.url, status: response.status, headers: response.headers })

@@ -199,9 +211,10 @@ export const identity = (input: { readonly id: string; readonly name: string; re

  /**
   * Read a text body while retaining the original payload and HTTP context on every downstream error. `invalid` is a
-   * malformed provider document; `ended` is a generation that reached a terminal status without output (`failed` is
-   * provider-side, `cancelled`/`expired` mean the result will never exist); `pending` is a `result()` read before the
-   * generation finished, which is caller misuse; `contentPolicy` is a moderated result.
+   * malformed provider document; `ended` is a generation that reached a terminal status without output (`failed`
+   * carries the provider's classification, defaulting to `ProviderInternal`; `cancelled`/`expired` mean the result
+   * will never exist); `pending` is a `result()` read before the generation finished, which is caller misuse;
+   * `contentPolicy` is a moderated result.
   */
  const text = Effect.fn("MediaProtocol.text")(function* (response: HttpClientResponse.HttpClientResponse) {
    const http = context(response)
@@ -223,11 +236,15 @@ export const identity = (input: { readonly id: string; readonly name: string; re
      http,
      invalid: (message: string, cause?: unknown) =>
        new AIError({ reason: new InvalidProviderOutputError({ route: input.id, message, body, http, cause }) }),
-      ended: (status: Exclude<Status, "queued" | "running" | "completed">, message: string) =>
+      ended: (
+        status: Exclude<Status, "queued" | "running" | "completed">,
+        message: string,
+        failure: Failure = "ProviderInternal",
+      ) =>
        new AIError({
          reason:
            status === "failed"
-              ? new ProviderInternalError({ message, body, http })
+              ? new FAILURES[failure]({ message, body, http })
              : new InvalidRequestError({ message, body, http }),
        }),
      pending: (id: string) =>
@@ -303,6 +320,10 @@ export const status = <Table extends Record<string, Status>>(
  return Effect.succeed(table[raw])
 }

+/** Map a provider error code through the protocol's table; missing or unmapped codes are `ProviderInternal`. */
+export const failure = (table: Readonly<Record<string, Failure>>, code: string | number | undefined): Failure =>
+  code !== undefined && Object.hasOwn(table, code) ? table[code] : "ProviderInternal"
+
 /** A `url` asset whose provider-declared retention window starts now. */
 export const expiringUrl = (url: string, retention: Duration.Duration, options?: Parameters<typeof Media.url>[1]) =>
  Clock.currentTimeMillis.pipe(
@@ -1,4 +1,4 @@
-import { Effect, Schema, Stream } from "effect"
+import { Duration, Effect, Schedule, Schema, Stream } from "effect"
 import { Headers, HttpClientRequest, type HttpClientResponse } from "effect/unstable/http"
 import { Auth, type AuthInput } from "./auth.js"
 import { Endpoint } from "./endpoint.js"
@@ -7,6 +7,7 @@ import { RequestExecutor } from "./executor.js"
 import { MediaProtocol } from "./media-protocol.js"
 import { Generation, isTerminal } from "../generation.js"
 import type { Media } from "../media.js"
+import { isRetryable } from "../provider-error.js"
 import {
  AIError,
  AIErrorReason,
@@ -137,6 +138,32 @@ export const inline = <Request extends MediaRequest, Response>(
  }
 }

+const READ_RETRY_MAX_DELAY = Duration.seconds(30)
+
+/**
+ * Status and result reads retry transient failures; `start` and `cancel` never do. Gaps grow exponentially from 1s,
+ * jittered, up to 30s each, for at most 8 retries (about two minutes when every attempt fails), so a direct
+ * `Generation.result()` stays bounded; `await` and `events` also cut retries off at `poll.timeout`. A provider
+ * `retryAfterMs` raises the gap, still capped at 30s.
+ */
+const READ_RETRY = Schedule.max([
+  Schedule.min([Schedule.exponential("1 second"), Schedule.spaced(READ_RETRY_MAX_DELAY)]),
+  Schedule.recurs(8),
+]).pipe(
+  Schedule.jittered,
+  Schedule.setInputType<AIError>(),
+  Schedule.modifyDelay(({ input, duration }) =>
+    Effect.succeed(
+      Duration.min(
+        input.reason._tag === "RateLimit" || input.reason._tag === "ProviderInternal"
+          ? Duration.max(duration, Duration.millis(input.reason.retryAfterMs ?? 0))
+          : duration,
+        READ_RETRY_MAX_DELAY,
+      ),
+    ),
+  ),
+)
+
 /**
 * Compose a queued media protocol the same way, adding `start`/`resume` handles whose polls reuse the route's auth,
 * deployment headers, and (for `start`) the request's `http` overlay. The token is decoded once at the boundary and
@@ -154,6 +181,8 @@ export const queued = <Request extends MediaRequest, Response, Token>(
  const generationRoute = (token: Token, http: HttpOptions | undefined, execute: Execute) => {
    const materialize = (asset: Media.Asset) =>
      asset.materialize().pipe(Effect.provideService(RequestExecutorService, { execute }))
+    // Only the GET exchange retries: a decoded terminal failure (`output.ended`) can be a `ProviderInternal` too, and
+    // re-reading it would spin until the caller's deadline.
    const poll = <A>(operation: {
      readonly path: (token: Token) => string
      readonly decode: (
@@ -161,9 +190,10 @@ export const queued = <Request extends MediaRequest, Response, Token>(
        context: MediaProtocol.PollContext<Token>,
      ) => Effect.Effect<A, AIError>
    }) =>
-      transport
-        .call("GET", operation.path(token), http, execute)
-        .pipe(Effect.flatMap((sent) => operation.decode(sent.response, { token, auth: sent.auth, materialize })))
+      transport.call("GET", operation.path(token), http, execute).pipe(
+        Effect.retry({ schedule: READ_RETRY, while: isRetryable }),
+        Effect.flatMap((sent) => operation.decode(sent.response, { token, auth: sent.auth, materialize })),
+      )
    const status = poll(protocol.status)
    const cancel = protocol.cancel
    const send =
@@ -103,7 +103,7 @@ export type TranscriptionRequestInput<Model extends TranscriptionModel = Transcr
 // Response and events
 // ---------------------------------------------------------------------------

-/** Speaker labels are provider-native (`A`, `0`, `spk:0`, or a known speaker name). */
+/** Speaker labels are provider-native (`A`, `0`, `spk:0`, `speaker_0`, or a known speaker name). */
 export const TranscriptionSegment = Schema.Struct({
  text: Schema.String,
  startSeconds: Schema.Number,
@@ -3,7 +3,17 @@ import { Effect } from "effect"
 import { CacheHint, LLM, Message } from "../src/index.js"
 import { Auth } from "../src/route.js"
 import { compileRequest } from "../src/route/client.js"
-import { AmazonBedrock, GoogleVertexMessages } from "../src/providers.js"
+import {
+  Alibaba,
+  AmazonBedrock,
+  AnthropicCompatible,
+  CloudflareAIGateway,
+  GoogleVertexMessages,
+  Meta,
+  MiniMax,
+  Moonshot,
+  ZAICodingPlan,
+} from "../src/providers.js"
 import * as AnthropicMessages from "../src/protocols/anthropic-messages.js"
 import * as Gemini from "../src/protocols/gemini.js"
 import * as OpenAIChat from "../src/protocols/openai-chat.js"
@@ -107,6 +117,54 @@ describe("applyCachePolicy", () => {
    }),
  )

+  it.effect("'auto' emits Anthropic cache markers on Anthropic-compatible routes", () =>
+    Effect.gen(function* () {
+      const prepared = yield* compileRequest(
+        LLM.request({
+          model: AnthropicCompatible.configure({ apiKey: "test", baseURL: "https://messages.example.test/v1" }).model(
+            "compatible",
+          ),
+          system: "You are concise.",
+          prompt: "hi",
+        }),
+      )
+
+      expect(prepared.route).toBe("anthropic-compatible-messages")
+      expect(prepared.body).toMatchObject({
+        system: [{ type: "text", text: "You are concise.", cache_control: { type: "ephemeral" } }],
+        messages: [{ role: "user", content: [{ type: "text", text: "hi", cache_control: { type: "ephemeral" } }] }],
+      })
+    }),
+  )
+
+  const messagesModels = [
+    ["alibaba-messages", Alibaba.configure({ region: "ap-southeast-1", apiKey: "test" }).messages("qwen3.8-max")],
+    [
+      "cloudflare-ai-gateway-messages",
+      CloudflareAIGateway.configure({ accountId: "test", gatewayId: "test", apiKey: "test" }).model(
+        "anthropic/claude-sonnet-4-6",
+      ),
+    ],
+    ["meta-messages", Meta.configure({ apiKey: "test" }).messages("muse-spark-1.3")],
+    ["minimax-messages", MiniMax.configure({ apiKey: "test" }).model("MiniMax-M3")],
+    ["moonshot-messages", Moonshot.configure({ apiKey: "test" }).messages("kimi-k3")],
+    ["zai-coding-messages", ZAICodingPlan.configure({ apiKey: "test" }).messages("glm-5.3")],
+  ] as const
+
+  messagesModels.forEach(([route, model]) =>
+    it.effect(`'auto' emits cache markers on ${route}`, () =>
+      Effect.gen(function* () {
+        const prepared = yield* compileRequest(LLM.request({ model, system: "Sys", prompt: "hi" }))
+
+        expect(prepared.route).toBe(route)
+        expect(prepared.body).toMatchObject({
+          system: [{ type: "text", text: "Sys", cache_control: { type: "ephemeral" } }],
+          messages: [{ role: "user", content: [{ type: "text", text: "hi", cache_control: { type: "ephemeral" } }] }],
+        })
+      }),
+    ),
+  )
+
  it.effect("'auto' is a no-op on OpenAI (implicit caching protocol)", () =>
    Effect.gen(function* () {
      const prepared = yield* compileRequest(
@@ -39,17 +39,18 @@ describe("experimental Evaluation", () => {
        type: "choice",
        choice: "billing",
        probabilities: { billing: 0.9, technical: 0.1 },
+        confidence: 0.8,
      })
      expect(response.answers.urgency).toEqual({
        type: "score",
        score: 1.2,
        probabilities: { "0": 0, "1": 0.8, "2": 0.2 },
+        confidence: 0.6,
      })
      expect(response.answers.refund).toEqual({ type: "boolean", probability: 0.97 })
      expect(response.usage?.totalTokens).toBe(36)
      expect(response.providerMetadata).toEqual({
        typesafe: {
-          confidence: { department: 0.8, urgency: 0.6 },
          legend: { urgency: { "0": "Can wait", "1": "Needs attention", "2": "Blocking" } },
        },
      })
@@ -26,8 +26,10 @@ const request = Evaluation.request({
 const result = EvaluationClient.evaluate(request)
 type Result = Success<typeof result>
 type Choice = Assert<Equal<Result["answers"]["topic"]["choice"], "billing" | "support">>
+type Confidence = Assert<Equal<Result["answers"]["topic"]["confidence"], number | undefined>>
 type ClientRequirements = Assert<Equal<Requirements<typeof result>, Service>>
 void (true satisfies Choice)
+void (true satisfies Confidence)
 void (true satisfies ClientRequirements)

 Effect.gen(function* () {
@@ -273,10 +273,56 @@ describe("RequestExecutor", () => {
      expectAIError(error)
      expect(error.reason).toMatchObject({ _tag: "InvalidRequest" })
      expect("classification" in error.reason ? error.reason.classification : undefined).toBeUndefined()
-      expect(error.message).toBe("Provider request failed with HTTP 400")
+      expect(error.message).toBe("Provider request failed with HTTP 400: invalid parameter")
    }).pipe(Effect.provide(fixedResponse("invalid parameter", { status: 400 }))),
  )

+  it.effect("shows unrecognized provider error bodies", () =>
+    Effect.gen(function* () {
+      const executor = yield* RequestExecutor.Service
+      const error = yield* executor.execute(request).pipe(Effect.flip)
+
+      expect(error.message).toBe(
+        'Provider request failed with HTTP 422: {"object":"error","message":{"detail":[{"msg":"Input should be less than or equal to 1.5"}]}}',
+      )
+    }).pipe(
+      Effect.provide(
+        fixedResponse('{"object":"error","message":{"detail":[{"msg":"Input should be less than or equal to 1.5"}]}}', {
+          status: 422,
+        }),
+      ),
+    ),
+  )
+
+  it.effect("shows messages from common provider error layouts", () =>
+    Effect.gen(function* () {
+      const executor = yield* RequestExecutor.Service
+      const error = yield* executor.execute(request).pipe(Effect.flip)
+
+      expect(error.message).toBe("Invalid API Key")
+    }).pipe(Effect.provide(fixedResponse('{"detail":"Invalid API Key"}', { status: 401 }))),
+  )
+
+  it.effect("truncates long unrecognized provider error bodies", () =>
+    Effect.gen(function* () {
+      const executor = yield* RequestExecutor.Service
+      const error = yield* executor.execute(request).pipe(Effect.flip)
+
+      expect(error.message).toBe(`Provider request failed with HTTP 400: ${"x".repeat(2000)}…`)
+      expect(error.reason.body).toHaveLength(5000)
+    }).pipe(Effect.provide(fixedResponse("x".repeat(5000), { status: 400 }))),
+  )
+
+  it.effect("does not show HTML error pages", () =>
+    Effect.gen(function* () {
+      const executor = yield* RequestExecutor.Service
+      const error = yield* executor.execute(request).pipe(Effect.flip)
+
+      expect(error.message).toBe("Provider request failed with HTTP 502")
+      expect(error.reason.body).toContain("Bad Gateway")
+    }).pipe(Effect.provide(fixedResponse("<!DOCTYPE html><html><body>Bad Gateway</body></html>", { status: 502 }))),
+  )
+
  it.effect("preserves structured provider messages from large error bodies", () =>
    Effect.gen(function* () {
      const executor = yield* RequestExecutor.Service
@@ -299,7 +345,7 @@ describe("RequestExecutor", () => {
    ),
  )

-  it.effect("falls back when structured provider messages are empty", () =>
+  it.effect("shows the body when structured provider messages are empty", () =>
    Effect.gen(function* () {
      const executor = yield* RequestExecutor.Service
      const error = yield* executor.execute(request).pipe(Effect.flip)
@@ -308,7 +354,7 @@ describe("RequestExecutor", () => {
      expect(error.reason).toMatchObject({
        _tag: "InvalidRequest",
      })
-      expect(error.message).toBe("Provider request failed with HTTP 400")
+      expect(error.message).toBe('Provider request failed with HTTP 400: {"error":{"message":"  "}}')
    }).pipe(Effect.provide(fixedResponse('{"error":{"message":"  "}}', { status: 400 }))),
  )

@@ -154,8 +154,8 @@ describe("public exports", () => {
    expect(XAI.model).toBeFunction()
    expect(XAI.provider.responses).toBe(XAI.responses)
    expect(XAI.provider.chat).toBe(XAI.chat)
-    expect(XAI.configure({ apiKey: "fixture" }).responses("grok-4.3").route.id).toBe("openai-responses")
-    expect(XAI.configure({ apiKey: "fixture" }).chat("grok-4.3").route.id).toBe("openai-compatible-chat")
+    expect(XAI.configure({ apiKey: "fixture" }).responses("grok-4.3").route.id).toBe("xai-responses")
+    expect(XAI.configure({ apiKey: "fixture" }).chat("grok-4.3").route.id).toBe("xai-chat")
    expect(OpenAI.configure({ apiKey: "fixture" }).image("gpt-image-2").route.id).toBe("openai-images")
    expect(OpenAI.provider.image).toBe(OpenAI.image)
    expect(Google.configure({ apiKey: "fixture" }).image("imagen-4.0-generate-001").route.id).toBe("google-images")
@@ -197,6 +197,11 @@ describe("public exports", () => {
    expect(Google.configure({ apiKey: "fixture" }).transcription("gemini-3.5-transcribe").route.kind).toBe("stream")
    expect(Deepgram.configure({ apiKey: "fixture" }).transcription("nova-3").route.kind).toBe("inline")
    expect(AssemblyAI.configure({ apiKey: "fixture" }).transcription("universal-3-5-pro").route.kind).toBe("queued")
+    expect(ElevenLabs.configure({ apiKey: "fixture" }).transcription("scribe_v2").route.id).toBe(
+      "elevenlabs-transcription",
+    )
+    expect(ElevenLabs.configure({ apiKey: "fixture" }).transcription("scribe_v2").route.kind).toBe("inline")
+    expect(ElevenLabs.provider.transcription).toBe(ElevenLabs.transcription)
  })

  test("protocol barrels expose supported low-level routes", () => {
@@ -10,7 +10,7 @@
      "usage"
    ],
    "name": "alibaba-messages/qwen-3-7-plus-streams-thinking-disabled",
-    "recordedAt": "2026-09-08T03:10:57.819Z"
+    "recordedAt": "2026-09-29T05:26:24.450Z"
  },
  "interactions": [
    {
@@ -21,14 +21,14 @@
        "headers": {
          "content-type": "application/json"
        },
-        "body": "{\"model\":\"qwen3.7-plus\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is 173 multiplied by 219? Reply with only the final integer.\"}]}],\"stream\":true,\"max_tokens\":4096,\"thinking\":{\"type\":\"disabled\"}}"
+        "body": "{\"model\":\"qwen3.7-plus\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is 173 multiplied by 219? Reply with only the final integer.\",\"cache_control\":{\"type\":\"ephemeral\"}}]}],\"stream\":true,\"max_tokens\":4096,\"thinking\":{\"type\":\"disabled\"}}"
      },
      "response": {
        "status": 200,
        "headers": {
          "content-type": "text/event-stream"
        },
-        "body": "event:ping\ndata:{\"type\":\"ping\"}\n\nevent:message_start\ndata:{\"message\":{\"model\":\"qwen3.7-plus\",\"id\":\"msg_c4d58b4f-a61d-9d0c-a9e4-cb45d34b1120\",\"role\":\"assistant\",\"type\":\"message\",\"content\":[],\"usage\":{\"input_tokens\":20,\"output_tokens\":0}},\"type\":\"message_start\"}\n\nevent:content_block_start\ndata:{\"type\":\"content_block_start\",\"content_block\":{\"type\":\"text\",\"text\":\"\"},\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"text_delta\",\"text\":\"3\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"text_delta\",\"text\":\"7887\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_stop\ndata:{\"type\":\"content_block_stop\",\"index\":0}\n\nevent:message_delta\ndata:{\"delta\":{\"stop_reason\":\"end_turn\"},\"type\":\"message_delta\",\"usage\":{\"output_tokens\":5,\"cache_creation_input_tokens\":0,\"input_tokens\":32,\"cache_read_input_tokens\":0,\"prompt_tokens_details\":{\"cached_tokens\":0}}}\n\nevent:message_stop\ndata:{\"type\":\"message_stop\"}\n\n"
+        "body": "event:ping\ndata:{\"type\":\"ping\"}\n\nevent:message_start\ndata:{\"message\":{\"model\":\"qwen3.7-plus\",\"id\":\"msg_39067759-5f01-9b3a-b2c1-09111797f7b5\",\"role\":\"assistant\",\"type\":\"message\",\"content\":[],\"usage\":{\"input_tokens\":20,\"output_tokens\":0}},\"type\":\"message_start\"}\n\nevent:content_block_start\ndata:{\"type\":\"content_block_start\",\"content_block\":{\"type\":\"text\",\"text\":\"\"},\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"text_delta\",\"text\":\"3\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"text_delta\",\"text\":\"788\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"text_delta\",\"text\":\"7\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_stop\ndata:{\"type\":\"content_block_stop\",\"index\":0}\n\nevent:message_delta\ndata:{\"delta\":{\"stop_reason\":\"end_turn\"},\"type\":\"message_delta\",\"usage\":{\"cache_creation\":{\"ephemeral_5m_input_tokens\":0},\"output_tokens\":5,\"cache_creation_input_tokens\":0,\"input_tokens\":32,\"cache_read_input_tokens\":0,\"prompt_tokens_details\":{\"cached_tokens\":0}}}\n\nevent:message_stop\ndata:{\"type\":\"message_stop\"}\n\n"
      }
    }
  ]
@@ -9,7 +9,7 @@
      "structured-output"
    ],
    "name": "alibaba-messages/qwen-3-8-max-follows-a-json-schema",
-    "recordedAt": "2026-09-08T03:11:30.530Z"
+    "recordedAt": "2026-09-29T05:26:41.466Z"
  },
  "interactions": [
    {
@@ -20,14 +20,14 @@
        "headers": {
          "content-type": "application/json"
        },
-        "body": "{\"model\":\"qwen3.8-max\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Return a JSON object with one key \\\"city\\\" set to the capital city of France.\"}]}],\"stream\":true,\"max_tokens\":1024,\"thinking\":{\"type\":\"disabled\"},\"output_config\":{\"format\":{\"type\":\"json_schema\",\"schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false}}}}"
+        "body": "{\"model\":\"qwen3.8-max\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Return a JSON object with one key \\\"city\\\" set to the capital city of France.\",\"cache_control\":{\"type\":\"ephemeral\"}}]}],\"stream\":true,\"max_tokens\":1024,\"thinking\":{\"type\":\"disabled\"},\"output_config\":{\"format\":{\"type\":\"json_schema\",\"schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false}}}}"
      },
      "response": {
        "status": 200,
        "headers": {
          "content-type": "text/event-stream"
        },
-        "body": "event:ping\ndata:{\"type\":\"ping\"}\n\nevent:message_start\ndata:{\"message\":{\"model\":\"qwen3.8-max\",\"id\":\"msg_16e067c1-984b-94d3-9abb-11792d794271\",\"role\":\"assistant\",\"type\":\"message\",\"content\":[],\"usage\":{\"input_tokens\":18,\"output_tokens\":0}},\"type\":\"message_start\"}\n\nevent:content_block_start\ndata:{\"type\":\"content_block_start\",\"content_block\":{\"type\":\"text\",\"text\":\"\"},\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"text_delta\",\"text\":\"{\\\"\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"text_delta\",\"text\":\"city\\\":\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"text_delta\",\"text\":\" \\\"Paris\\\"}\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_stop\ndata:{\"type\":\"content_block_stop\",\"index\":0}\n\nevent:message_delta\ndata:{\"delta\":{\"stop_reason\":\"end_turn\"},\"type\":\"message_delta\",\"usage\":{\"output_tokens\":6,\"cache_creation_input_tokens\":0,\"input_tokens\":32,\"cache_read_input_tokens\":0,\"prompt_tokens_details\":{\"cached_tokens\":0}}}\n\nevent:message_stop\ndata:{\"type\":\"message_stop\"}\n\n"
+        "body": "event:ping\ndata:{\"type\":\"ping\"}\n\nevent:message_start\ndata:{\"message\":{\"model\":\"qwen3.8-max\",\"id\":\"msg_61ee9b9d-a224-9b69-98f7-9f9ea3937b41\",\"role\":\"assistant\",\"type\":\"message\",\"content\":[],\"usage\":{\"input_tokens\":18,\"output_tokens\":0}},\"type\":\"message_start\"}\n\nevent:content_block_start\ndata:{\"type\":\"content_block_start\",\"content_block\":{\"type\":\"text\",\"text\":\"\"},\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"text_delta\",\"text\":\"{\\\"\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"text_delta\",\"text\":\"city\\\":\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"type\":\"text_delta\",\"text\":\" \\\"Paris\\\"}\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_stop\ndata:{\"type\":\"content_block_stop\",\"index\":0}\n\nevent:message_delta\ndata:{\"delta\":{\"stop_reason\":\"end_turn\"},\"type\":\"message_delta\",\"usage\":{\"cache_creation\":{\"ephemeral_5m_input_tokens\":0},\"output_tokens\":6,\"cache_creation_input_tokens\":0,\"input_tokens\":32,\"cache_read_input_tokens\":0,\"prompt_tokens_details\":{\"cached_tokens\":0}}}\n\nevent:message_stop\ndata:{\"type\":\"message_stop\"}\n\n"
      }
    }
  ]
@@ -10,7 +10,7 @@
      "tool-choice"
    ],
    "name": "alibaba-messages/qwen-3-8-max-obeys-named-tool-choice",
-    "recordedAt": "2026-09-08T03:11:06.590Z"
+    "recordedAt": "2026-09-29T05:26:40.212Z"
  },
  "interactions": [
    {
@@ -21,14 +21,14 @@
        "headers": {
          "content-type": "application/json"
        },
-        "body": "{\"model\":\"qwen3.8-max\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Find the current weather in Paris.\"}]}],\"tools\":[{\"name\":\"get_weather\",\"description\":\"Get weather in a city\",\"input_schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\",\"enum\":[\"Paris\"]}},\"required\":[\"city\"]}}],\"tool_choice\":{\"type\":\"tool\",\"name\":\"get_weather\"},\"stream\":true,\"max_tokens\":4096,\"thinking\":{\"type\":\"disabled\"}}"
+        "body": "{\"model\":\"qwen3.8-max\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Find the current weather in Paris.\",\"cache_control\":{\"type\":\"ephemeral\"}}]}],\"tools\":[{\"name\":\"get_weather\",\"description\":\"Get weather in a city\",\"input_schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\",\"enum\":[\"Paris\"]}},\"required\":[\"city\"]},\"cache_control\":{\"type\":\"ephemeral\"}}],\"tool_choice\":{\"type\":\"tool\",\"name\":\"get_weather\"},\"stream\":true,\"max_tokens\":4096,\"thinking\":{\"type\":\"disabled\"}}"
      },
      "response": {
        "status": 200,
        "headers": {
          "content-type": "text/event-stream"
        },
-        "body": "event:ping\ndata:{\"type\":\"ping\"}\n\nevent:message_start\ndata:{\"message\":{\"model\":\"qwen3.8-max\",\"id\":\"msg_0e8f1abf-f2bc-9a86-a6a7-14804ac17eac\",\"role\":\"assistant\",\"type\":\"message\",\"content\":[],\"usage\":{\"input_tokens\":45,\"output_tokens\":0}},\"type\":\"message_start\"}\n\nevent:content_block_start\ndata:{\"type\":\"content_block_start\",\"content_block\":{\"name\":\"get_weather\",\"input\":{},\"id\":\"toolu_cf9cab33261f4709ae096d8a\",\"type\":\"tool_use\"},\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"partial_json\":\"\",\"type\":\"input_json_delta\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"partial_json\":\"{\\\"city\\\": \\\"Paris\",\"type\":\"input_json_delta\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"partial_json\":\"\\\"\",\"type\":\"input_json_delta\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"partial_json\":\"}\",\"type\":\"input_json_delta\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_stop\ndata:{\"type\":\"content_block_stop\",\"index\":0}\n\nevent:message_delta\ndata:{\"delta\":{\"stop_reason\":\"end_turn\"},\"type\":\"message_delta\",\"usage\":{\"output_tokens\":19,\"cache_creation_input_tokens\":0,\"input_tokens\":288,\"cache_read_input_tokens\":0,\"prompt_tokens_details\":{\"cached_tokens\":0}}}\n\nevent:message_stop\ndata:{\"type\":\"message_stop\"}\n\n"
+        "body": "event:ping\ndata:{\"type\":\"ping\"}\n\nevent:message_start\ndata:{\"message\":{\"model\":\"qwen3.8-max\",\"id\":\"msg_dab3e1c5-e75e-978d-902e-1b0a82918cff\",\"role\":\"assistant\",\"type\":\"message\",\"content\":[],\"usage\":{\"input_tokens\":45,\"output_tokens\":0}},\"type\":\"message_start\"}\n\nevent:content_block_start\ndata:{\"type\":\"content_block_start\",\"content_block\":{\"name\":\"get_weather\",\"input\":{},\"id\":\"toolu_9a1c3c06a04744cc97df33a2\",\"type\":\"tool_use\"},\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"partial_json\":\"\",\"type\":\"input_json_delta\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"partial_json\":\"{\\\"city\\\": \\\"Paris\",\"type\":\"input_json_delta\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"partial_json\":\"\\\"\",\"type\":\"input_json_delta\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_delta\ndata:{\"delta\":{\"partial_json\":\"}\",\"type\":\"input_json_delta\"},\"type\":\"content_block_delta\",\"index\":0}\n\nevent:content_block_stop\ndata:{\"type\":\"content_block_stop\",\"index\":0}\n\nevent:message_delta\ndata:{\"delta\":{\"stop_reason\":\"end_turn\"},\"type\":\"message_delta\",\"usage\":{\"cache_creation\":{\"ephemeral_5m_input_tokens\":0},\"output_tokens\":19,\"cache_creation_input_tokens\":0,\"input_tokens\":288,\"cache_read_input_tokens\":0,\"prompt_tokens_details\":{\"cached_tokens\":0}}}\n\nevent:message_stop\ndata:{\"type\":\"message_stop\"}\n\n"
      }
    }
  ]
@@ -0,0 +1,34 @@
+{
+  "version": 1,
+  "metadata": {
+    "tags": [
+      "prefix:bedrock-converse-thinking-binding",
+      "provider:amazon-bedrock",
+      "protocol:bedrock-converse",
+      "reasoning"
+    ],
+    "name": "bedrock-converse-thinking-binding/accepts-the-default-binding-with-no-thinking-configured",
+    "recordedAt": "2026-09-28T23:09:14.527Z"
+  },
+  "interactions": [
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://bedrock-runtime.us-east-1.amazonaws.com/model/global.anthropic.claude-opus-5-5/converse-stream",
+        "headers": {
+          "content-type": "application/json"
+        },
+        "body": "{\"modelId\":\"global.anthropic.claude-opus-5-5\",\"messages\":[{\"role\":\"user\",\"content\":[{\"text\":\"Say hello.\"}]}],\"system\":[{\"text\":\"Reply with the single word 'Hello'.\"}],\"inferenceConfig\":{\"maxTokens\":1024},\"additionalModelRequestFields\":{\"thinking\":{\"type\":\"adaptive\",\"block_binding\":{\"prefix_mismatch_behavior\":\"drop_block\"}},\"anthropic_beta\":[\"thinking-binding-controls-2026-08-01\"]}}"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "application/vnd.amazon.eventstream"
+        },
+        "body": "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",
+        "bodyEncoding": "base64"
+      }
+    }
+  ]
+}
@@ -0,0 +1,32 @@
+{
+  "version": 1,
+  "metadata": {
+    "tags": [
+      "prefix:elevenlabs-transcription",
+      "provider:elevenlabs",
+      "protocol:elevenlabs-transcription"
+    ],
+    "name": "elevenlabs-transcription/groups-diarized-words-into-speaker-turns",
+    "recordedAt": "2026-09-27T09:35:28.265Z"
+  },
+  "interactions": [
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://api.elevenlabs.io/v1/speech-to-text",
+        "headers": {
+          "content-type": "multipart/form-data; boundary=----WebKitFormBoundary356bdc14864a477dbacbfcf60d1ecceb"
+        },
+        "body": "--BOUNDARY\r\nContent-Disposition: form-data; name=\"file\"; filename=\"audio.mp3\"\r\nContent-Type: audio/mpeg\r\n\r\n[audio]\r\n--BOUNDARY\r\nContent-Disposition: form-data; name=\"model_id\"\r\n\r\nscribe_v2\r\n--BOUNDARY\r\nContent-Disposition: form-data; name=\"diarize\"\r\n\r\ntrue\r\n--BOUNDARY--\r\n"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "application/json"
+        },
+        "body": "{\"language_code\":\"eng\",\"language_probability\":0.9495430588722229,\"text\":\"Did the release ship? Yes, it shipped this morning\",\"words\":[{\"text\":\"Did\",\"start\":0.34,\"end\":0.44,\"type\":\"word\",\"speaker_id\":\"speaker_0\",\"logprob\":-1.7881377516459906e-6},{\"text\":\" \",\"start\":0.44,\"end\":0.48,\"type\":\"spacing\",\"speaker_id\":\"speaker_0\",\"logprob\":-1.1920928244535389e-7},{\"text\":\"the\",\"start\":0.48,\"end\":0.56,\"type\":\"word\",\"speaker_id\":\"speaker_0\",\"logprob\":-1.1920928244535389e-7},{\"text\":\" \",\"start\":0.56,\"end\":0.6,\"type\":\"spacing\",\"speaker_id\":\"speaker_0\",\"logprob\":-7.152531907195225e-6},{\"text\":\"release\",\"start\":0.6,\"end\":0.92,\"type\":\"word\",\"speaker_id\":\"speaker_0\",\"logprob\":-7.152531907195225e-6},{\"text\":\" \",\"start\":0.92,\"end\":0.94,\"type\":\"spacing\",\"speaker_id\":\"speaker_0\",\"logprob\":-8.344646857949556e-7},{\"text\":\"ship?\",\"start\":0.94,\"end\":1.26,\"type\":\"word\",\"speaker_id\":\"speaker_0\",\"logprob\":-7.414704032271402e-6},{\"text\":\" \",\"start\":1.26,\"end\":1.26,\"type\":\"spacing\",\"speaker_id\":\"speaker_0\",\"logprob\":-0.0009363081189803779},{\"text\":\"Yes,\",\"start\":1.68,\"end\":2.02,\"type\":\"word\",\"speaker_id\":\"speaker_1\",\"logprob\":-0.003542040009030245},{\"text\":\" \",\"start\":2.02,\"end\":2.48,\"type\":\"spacing\",\"speaker_id\":\"speaker_1\",\"logprob\":-3.933898824470816e-6},{\"text\":\"it\",\"start\":2.48,\"end\":2.62,\"type\":\"word\",\"speaker_id\":\"speaker_1\",\"logprob\":-3.933898824470816e-6},{\"text\":\" \",\"start\":2.62,\"end\":2.64,\"type\":\"spacing\",\"speaker_id\":\"speaker_1\",\"logprob\":-0.000013589766240329482},{\"text\":\"shipped\",\"start\":2.66,\"end\":2.9,\"type\":\"word\",\"speaker_id\":\"speaker_1\",\"logprob\":-0.000013589766240329482},{\"text\":\" \",\"start\":2.9,\"end\":2.94,\"type\":\"spacing\",\"speaker_id\":\"speaker_1\",\"logprob\":0.0},{\"text\":\"this\",\"start\":2.94,\"end\":3.12,\"type\":\"word\",\"speaker_id\":\"speaker_1\",\"logprob\":0.0},{\"text\":\" \",\"start\":3.12,\"end\":3.18,\"type\":\"spacing\",\"speaker_id\":\"speaker_1\",\"logprob\":-3.576278118089249e-7},{\"text\":\"morning\",\"start\":3.18,\"end\":3.5,\"type\":\"word\",\"speaker_id\":\"speaker_1\",\"logprob\":-3.576278118089249e-7}],\"transcription_id\":\"cs3I2282TH8hjw12brNg\",\"audio_duration_secs\":3.5526875}"
+      }
+    }
+  ]
+}
@@ -0,0 +1,50 @@
+{
+  "version": 1,
+  "metadata": {
+    "tags": [
+      "prefix:elevenlabs-transcription",
+      "provider:elevenlabs",
+      "protocol:elevenlabs-transcription"
+    ],
+    "name": "elevenlabs-transcription/transcribes-audio-with-word-timestamps",
+    "recordedAt": "2026-09-27T09:35:27.686Z"
+  },
+  "interactions": [
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://api.elevenlabs.io/v1/speech-to-text",
+        "headers": {
+          "content-type": "multipart/form-data; boundary=----WebKitFormBoundarye2be7b31e94441bbbeb35a9c890a9d74"
+        },
+        "body": "--BOUNDARY\r\nContent-Disposition: form-data; name=\"file\"; filename=\"audio.mp3\"\r\nContent-Type: audio/mpeg\r\n\r\n[audio]\r\n--BOUNDARY\r\nContent-Disposition: form-data; name=\"model_id\"\r\n\r\nscribe_v2\r\n--BOUNDARY--\r\n"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "application/json"
+        },
+        "body": "{\"language_code\":\"eng\",\"language_probability\":0.6618340611457825,\"text\":\"Hello from OpenCode\",\"words\":[{\"text\":\"Hello\",\"start\":0.4,\"end\":0.66,\"type\":\"word\",\"logprob\":-0.000014781842764932662},{\"text\":\" \",\"start\":0.66,\"end\":0.74,\"type\":\"spacing\",\"logprob\":-3.814689989667386e-6},{\"text\":\"from\",\"start\":0.74,\"end\":0.84,\"type\":\"word\",\"logprob\":-3.814689989667386e-6},{\"text\":\" \",\"start\":0.84,\"end\":0.9,\"type\":\"spacing\",\"logprob\":-0.018268775194883347},{\"text\":\"OpenCode\",\"start\":0.9,\"end\":1.44,\"type\":\"word\",\"logprob\":-0.1251817401498556}],\"transcription_id\":\"D4VfnANM2ArCHTujIb9q\",\"audio_duration_secs\":1.54125}"
+      }
+    },
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://api.elevenlabs.io/v1/speech-to-text",
+        "headers": {
+          "content-type": "multipart/form-data; boundary=----WebKitFormBoundaryfb80d0e44d9e44d299416ed546a04056"
+        },
+        "body": "--BOUNDARY\r\nContent-Disposition: form-data; name=\"file\"; filename=\"audio.mp3\"\r\nContent-Type: audio/mpeg\r\n\r\n[audio]\r\n--BOUNDARY\r\nContent-Disposition: form-data; name=\"model_id\"\r\n\r\nscribe_v2\r\n--BOUNDARY--\r\n"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "application/json"
+        },
+        "body": "{\"language_code\":\"eng\",\"language_probability\":0.6618340611457825,\"text\":\"Hello from OpenCode\",\"words\":[{\"text\":\"Hello\",\"start\":0.4,\"end\":0.66,\"type\":\"word\",\"logprob\":-0.000023007127310847864},{\"text\":\" \",\"start\":0.66,\"end\":0.74,\"type\":\"spacing\",\"logprob\":-2.3841830625315197e-6},{\"text\":\"from\",\"start\":0.74,\"end\":0.84,\"type\":\"word\",\"logprob\":-2.3841830625315197e-6},{\"text\":\" \",\"start\":0.84,\"end\":0.9,\"type\":\"spacing\",\"logprob\":-0.008306833915412426},{\"text\":\"OpenCode\",\"start\":0.9,\"end\":1.44,\"type\":\"word\",\"logprob\":-0.1075385226868093}],\"transcription_id\":\"SkYplzfq1DW8Ae3bWnoy\",\"audio_duration_secs\":1.54125}"
+      }
+    }
+  ]
+}
@@ -2,9 +2,16 @@
  "version": 1,
  "metadata": {
    "model": "muse-spark-1.3",
-    "tags": ["prefix:meta-messages", "provider:meta", "protocol:meta-messages", "tool", "tool-loop", "reasoning"],
+    "tags": [
+      "prefix:meta-messages",
+      "provider:meta",
+      "protocol:meta-messages",
+      "tool",
+      "tool-loop",
+      "reasoning"
+    ],
    "name": "meta-messages/replays-encrypted-thinking-through-a-tool-loop",
-    "recordedAt": "2026-09-07T17:27:03.540Z"
+    "recordedAt": "2026-09-29T05:29:52.700Z"
  },
  "interactions": [
    {
@@ -15,14 +22,14 @@
        "headers": {
          "content-type": "application/json"
        },
-        "body": "{\"model\":\"muse-spark-1.3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Look up the current weather in Paris using lookup_weather. After receiving the result, report Paris's weather in one short sentence.\"}]}],\"tools\":[{\"name\":\"lookup_weather\",\"description\":\"Look up current weather\",\"input_schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\",\"enum\":[\"Paris\"]}},\"required\":[\"city\"],\"additionalProperties\":false}}],\"tool_choice\":{\"type\":\"auto\"},\"stream\":true,\"max_tokens\":1024,\"thinking\":{\"type\":\"adaptive\",\"display\":\"omitted\"},\"output_config\":{\"effort\":\"low\"}}"
+        "body": "{\"model\":\"muse-spark-1.3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Look up the current weather in Paris using lookup_weather. After receiving the result, report Paris's weather in one short sentence.\",\"cache_control\":{\"type\":\"ephemeral\"}}]}],\"tools\":[{\"name\":\"lookup_weather\",\"description\":\"Look up current weather\",\"input_schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\",\"enum\":[\"Paris\"]}},\"required\":[\"city\"],\"additionalProperties\":false},\"cache_control\":{\"type\":\"ephemeral\"}}],\"tool_choice\":{\"type\":\"auto\"},\"stream\":true,\"max_tokens\":1024,\"thinking\":{\"type\":\"adaptive\",\"display\":\"omitted\"},\"output_config\":{\"effort\":\"low\"}}"
      },
      "response": {
        "status": 200,
        "headers": {
          "content-type": "text/event-stream"
        },
-        "body": "event: message_start\ndata: {\"message\":{\"content\":[],\"id\":\"msg_6a9ef3e5a96d9a155dd4463b\",\"model\":\"muse-spark-1.3\",\"role\":\"assistant\",\"stop_reason\":null,\"stop_sequence\":null,\"type\":\"message\",\"usage\":{\"input_tokens\":0,\"output_tokens\":0}},\"type\":\"message_start\"}\n\nevent: content_block_start\ndata: {\"content_block\":{\"data\":\"Q-PaDgGyJ4hIKk41uslnSV0PGvrTkwJ5D-t5skfjtkIt-ABXsehMcLKJJ8RJHRKW2-XhkpPrex0aOkIdqWl99vpCgtOHIFFaSc4b3oGxA8XDx4T_2aKANfYrR1DYwYzGe6ZZ-DQnU0bnpVUzCcXkghkLdyTcJr2p8cvVo1rymFpB0wZsbQRBhxCMR6PrY4i0aOTe8_waq_Po1a4l3YzKnzZIIvYP090o5kltv7MAwqChXjQeTJlKq7ECFa6HVeoTa43oiLmoD2Bzih0VfvBvQfbSh2uDypRM7-f65sp35-VuZfwsM33ZTvefzDbd8zd0D50I6wcybsj8gulDhWWpY7cxoN1Xasy-ImvisACGeppIN66maIFq5dMT2s8_CQ8a2EQ0hw9kwJaIiygZCdRofs-T1yaGWvnQxL6MpNh6SXux9T1ZfuexNrXOhz5cR3_s1euhq3-hI3GDCUDLAtkjiigSE3w6PExrwHTHnvkuAOTP0Lw7DH4NtKv-RFFeZaQOk_0Bi2EV43tR0Hq_chtEDiSpoezDjexPWfdZvhRIaO6PwyJaQ8jVOaLUr6bh6jQ3IM19lv6R7lY4Neno8fLxMwTbf7v7q02lfhOaZe3jR1fqOFUq8e4VXV76_rJBgzThqPNqO8OI_betgX5d2KMcwWAkaZjmrP3rxA7g5xp_Q7bkFiBaaTd3HbYIk_cKbtLOS6TIIphb4SX6ADA2qJ0zoo98P2NOceZODT2WrLjKCHl5dT6b9l2feH9m21pW576ULfKhVSMzuy0cmmWI7rv2P4q-2Fw2klsDVJAc6q22bFjfDgzhybKuhuM_p1SYb8aswNrgggV-cqHWDpF1FdVpL5fHMO74l1uD8Sj_9wuuD0asMQustuvsnYq2EdI0lLvONFMApWCU0s3QA8_P0Iyf0YoCZOm5QGnA7l3O5nAPkFF4kxLSsgRe9zuP6A4oKBDLN8EHwZ3pB4WZGWpUT12cJxplmT3_n8xKaMgaz13qs27uvUm3wMI1seyfpkMwUPHmt1ftpk9f_1OAg3fvQgIkWPTp6K9NzVzEry6SP7zbPfls8yn529Qrbki7ZM_oz3xEvDg367ZCe97eVnjiqRrYsYM2MmDsQq9lUwkgXb84kpK6a4pEzX9NDvhTqhw7RI6RL9E-2Ki4ciUfHv5LVTZ0rNweCo6SYXC11f8FCeObIW_Esr2mqYpORFS4SDMU-4I1HQfD9z6cPjL22APpv9a7Pp1phI8x_aQZkPU7LkyBWyVNDeusI7wq_LC0UgJ0vCAguKcAvN7gxwpCo5MEEZivRuYBldEMwRo4he2WQQke9KEokqREdlPF3Lvaav0fqPfXqhJyHAq8bYBHWdzMjDJ_dJwhdbLQ-iNLmrK5JNg2vPDglWSznBXbrSX4iyMFk1Ni2Y1SQUIOOxS_InIwCg\",\"type\":\"redacted_thinking\"},\"index\":0,\"type\":\"content_block_start\"}\n\nevent: content_block_stop\ndata: {\"index\":0,\"type\":\"content_block_stop\"}\n\nevent: content_block_start\ndata: {\"content_block\":{\"text\":\"\",\"type\":\"text\"},\"index\":1,\"type\":\"content_block_start\"}\n\nevent: content_block_delta\ndata: {\"delta\":{\"text\":\"I'll look up the current weather in Paris.\",\"type\":\"text_delta\"},\"index\":1,\"type\":\"content_block_delta\"}\n\nevent: content_block_stop\ndata: {\"index\":1,\"type\":\"content_block_stop\"}\n\nevent: content_block_start\ndata: {\"content_block\":{\"id\":\"call_01a07ce8bb767c109c12f0a202e2ac19\",\"input\":{},\"name\":\"lookup_weather\",\"type\":\"tool_use\"},\"index\":2,\"type\":\"content_block_start\"}\n\nevent: content_block_delta\ndata: {\"delta\":{\"partial_json\":\"{\\\"city\\\":\\\"Paris\\\"}\",\"type\":\"input_json_delta\"},\"index\":2,\"type\":\"content_block_delta\"}\n\nevent: content_block_stop\ndata: {\"index\":2,\"type\":\"content_block_stop\"}\n\nevent: message_delta\ndata: {\"delta\":{\"stop_reason\":\"tool_use\",\"stop_sequence\":null},\"type\":\"message_delta\",\"usage\":{\"cache_creation_input_tokens\":0,\"cache_read_input_tokens\":113,\"input_tokens\":451,\"output_tokens\":155,\"output_tokens_details\":{\"thinking_tokens\":87}}}\n\nevent: message_stop\ndata: {\"type\":\"message_stop\"}\n\n"
+        "body": "event: message_start\ndata: {\"message\":{\"content\":[],\"id\":\"msg_6abb4ccec3772e65cd44417d\",\"model\":\"muse-spark-1.3\",\"role\":\"assistant\",\"stop_reason\":null,\"stop_sequence\":null,\"type\":\"message\",\"usage\":{\"input_tokens\":0,\"output_tokens\":0}},\"type\":\"message_start\"}\n\nevent: content_block_start\ndata: {\"content_block\":{\"data\":\"Q-PaDgFT_IXY3RXUUduHqe1_WSgTF5_gMh29lCBV6vhfXW34eU6nJO7gUfRPczMK4nZfQhrqQewRujwjtNKR69DHHqTP35Q0jDnuZ4GZX9qBZT1OH9JhcMl1FxvccpatEcuH2Nju9Rf12KFHAOm9eKK6wFiaZgEHcT1wPbRYVZVZ8VxLeKk-ED3wkmWFhUFJRLSgJguWBMvEMbtIUlAKsJ6qkUxClfQKMm3eft1yf9ajseT32eloGzBE48IhyXu6tpeUDs9UatFgZOHKtHmvtKsPqRw-ddbimLnMtdkexwa8xR7EVTVuwBezunqhssfYAdR4c4t6VDpACh2UL3LcVUF9b0reiwpUfdpYrwjpB3bTCWyzGjwvIwGeuoR6VrWHz5nqVbt3bBprJXqJ4IRLKAXFFlMhClkz0MFNPBufcXSdh9i9NjbNp5c8lXCSkhMfhYX9B9KbQKl3DxUCjEY_VZk0nQJwt9zQVwTzWPzl9fTkBWrdebpXCg-z4lPmU5GLyGY3MlF24eDoSfJfqibF1HHqztluSHi4XEulrwMh4dpZmLhlLxlFxwnC8LjY_Rg8uOyzeoCzsMj-R9WrZ6n9jLZrxJPVo17nFjsuSwt6zMRS9Cna6adGFso0jIKF4BNTcZXlVt0b_TWA9AY4xpGSaAQXKYRBdAZNzTK5hj-bvyfWVTBepTBKm7pAtJW2e05mVBFDqRwEr3kcKkMTRMEj8vztSX4sNjV7Sw6bDbPjb_uFeoaNkq1ua9N7ZkKsyLn80ysWQ6IL-B_AVM1toAI0bVVYQmHbRSz1MgybcT5vjK2TWfCgxBuqw1ARU3oEM1iWTvpuHkFDNGeZnT4IWc_z_vLtQVnqSlqXPtnAmJ0WJgvQGSBhojSa9QMxRz_l4LZHmXUtfdMdUHTbrZwbfoL6eIyZf43ah-sXILJWTX9wXuYqnaclwvuO3EFiDUioSIBxWvAj2HNe5HpzayuvJqneRAukiVynt9SOo79VcBKAFsHW_KhUz58KjndfvOFP7byXv_W6Xa00ve_3GEaCANjFIl7ratBEuFYtpbVTT7TGIyGmuPQTVnGe7CAcFiAvGSwoaMwqvdGheKxeR7_cZvSYREeUnL5mXev8-MKY6_AtddOanQhf9pshxAXrIUtVFqin5MGhL2j787niURU9-o_VhLgzaIqfjbfMKkzdZ3-ESyDloOeD3CwoAsD_AVIrQZQHYbpYzFYasH0VrItar07ItxWZt_sCehTOi7Jtk5G8e7fd1HtCWmrp2iArioSIp8aLOphI9lazM7taIpfF_y0EMt3x5ENSvhtEmSk4kCJQnNyRv21uHT4uD0XjdQJbHeoRhzHDxoLHUOqAX9fGBzMFO8ZsWJxl8ebiCJeJ9Jzzr9bXeUKH5cP2VymoXPs3AWBrTpw1WfADM5sjHDJLzw\",\"type\":\"redacted_thinking\"},\"index\":0,\"type\":\"content_block_start\"}\n\nevent: content_block_stop\ndata: {\"index\":0,\"type\":\"content_block_stop\"}\n\nevent: content_block_start\ndata: {\"content_block\":{\"text\":\"\",\"type\":\"text\"},\"index\":1,\"type\":\"content_block_start\"}\n\nevent: content_block_delta\ndata: {\"delta\":{\"text\":\"I'll look up the current weather in Paris.\",\"type\":\"text_delta\"},\"index\":1,\"type\":\"content_block_delta\"}\n\nevent: content_block_stop\ndata: {\"index\":1,\"type\":\"content_block_stop\"}\n\nevent: content_block_start\ndata: {\"content_block\":{\"id\":\"call_01a0eba40810714cbd0a8a84496badc7\",\"input\":{},\"name\":\"lookup_weather\",\"type\":\"tool_use\"},\"index\":2,\"type\":\"content_block_start\"}\n\nevent: content_block_delta\ndata: {\"delta\":{\"partial_json\":\"{\\\"city\\\":\\\"Paris\\\"}\",\"type\":\"input_json_delta\"},\"index\":2,\"type\":\"content_block_delta\"}\n\nevent: content_block_stop\ndata: {\"index\":2,\"type\":\"content_block_stop\"}\n\nevent: message_delta\ndata: {\"delta\":{\"stop_reason\":\"tool_use\",\"stop_sequence\":null},\"type\":\"message_delta\",\"usage\":{\"cache_creation_input_tokens\":0,\"cache_read_input_tokens\":0,\"input_tokens\":564,\"output_tokens\":97,\"output_tokens_details\":{\"thinking_tokens\":29}}}\n\nevent: message_stop\ndata: {\"type\":\"message_stop\"}\n\n"
      }
    },
    {
@@ -33,14 +40,14 @@
        "headers": {
          "content-type": "application/json"
        },
-        "body": "{\"model\":\"muse-spark-1.3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Look up the current weather in Paris using lookup_weather. After receiving the result, report Paris's weather in one short sentence.\"}]},{\"role\":\"assistant\",\"content\":[{\"type\":\"redacted_thinking\",\"data\":\"Q-PaDgGyJ4hIKk41uslnSV0PGvrTkwJ5D-t5skfjtkIt-ABXsehMcLKJJ8RJHRKW2-XhkpPrex0aOkIdqWl99vpCgtOHIFFaSc4b3oGxA8XDx4T_2aKANfYrR1DYwYzGe6ZZ-DQnU0bnpVUzCcXkghkLdyTcJr2p8cvVo1rymFpB0wZsbQRBhxCMR6PrY4i0aOTe8_waq_Po1a4l3YzKnzZIIvYP090o5kltv7MAwqChXjQeTJlKq7ECFa6HVeoTa43oiLmoD2Bzih0VfvBvQfbSh2uDypRM7-f65sp35-VuZfwsM33ZTvefzDbd8zd0D50I6wcybsj8gulDhWWpY7cxoN1Xasy-ImvisACGeppIN66maIFq5dMT2s8_CQ8a2EQ0hw9kwJaIiygZCdRofs-T1yaGWvnQxL6MpNh6SXux9T1ZfuexNrXOhz5cR3_s1euhq3-hI3GDCUDLAtkjiigSE3w6PExrwHTHnvkuAOTP0Lw7DH4NtKv-RFFeZaQOk_0Bi2EV43tR0Hq_chtEDiSpoezDjexPWfdZvhRIaO6PwyJaQ8jVOaLUr6bh6jQ3IM19lv6R7lY4Neno8fLxMwTbf7v7q02lfhOaZe3jR1fqOFUq8e4VXV76_rJBgzThqPNqO8OI_betgX5d2KMcwWAkaZjmrP3rxA7g5xp_Q7bkFiBaaTd3HbYIk_cKbtLOS6TIIphb4SX6ADA2qJ0zoo98P2NOceZODT2WrLjKCHl5dT6b9l2feH9m21pW576ULfKhVSMzuy0cmmWI7rv2P4q-2Fw2klsDVJAc6q22bFjfDgzhybKuhuM_p1SYb8aswNrgggV-cqHWDpF1FdVpL5fHMO74l1uD8Sj_9wuuD0asMQustuvsnYq2EdI0lLvONFMApWCU0s3QA8_P0Iyf0YoCZOm5QGnA7l3O5nAPkFF4kxLSsgRe9zuP6A4oKBDLN8EHwZ3pB4WZGWpUT12cJxplmT3_n8xKaMgaz13qs27uvUm3wMI1seyfpkMwUPHmt1ftpk9f_1OAg3fvQgIkWPTp6K9NzVzEry6SP7zbPfls8yn529Qrbki7ZM_oz3xEvDg367ZCe97eVnjiqRrYsYM2MmDsQq9lUwkgXb84kpK6a4pEzX9NDvhTqhw7RI6RL9E-2Ki4ciUfHv5LVTZ0rNweCo6SYXC11f8FCeObIW_Esr2mqYpORFS4SDMU-4I1HQfD9z6cPjL22APpv9a7Pp1phI8x_aQZkPU7LkyBWyVNDeusI7wq_LC0UgJ0vCAguKcAvN7gxwpCo5MEEZivRuYBldEMwRo4he2WQQke9KEokqREdlPF3Lvaav0fqPfXqhJyHAq8bYBHWdzMjDJ_dJwhdbLQ-iNLmrK5JNg2vPDglWSznBXbrSX4iyMFk1Ni2Y1SQUIOOxS_InIwCg\"},{\"type\":\"text\",\"text\":\"I'll look up the current weather in Paris.\"},{\"type\":\"tool_use\",\"id\":\"call_01a07ce8bb767c109c12f0a202e2ac19\",\"name\":\"lookup_weather\",\"input\":{\"city\":\"Paris\"}}]},{\"role\":\"user\",\"content\":[{\"type\":\"tool_result\",\"tool_use_id\":\"call_01a07ce8bb767c109c12f0a202e2ac19\",\"content\":\"{\\\"condition\\\":\\\"sunny\\\"}\"}]}],\"tools\":[{\"name\":\"lookup_weather\",\"description\":\"Look up current weather\",\"input_schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\",\"enum\":[\"Paris\"]}},\"required\":[\"city\"],\"additionalProperties\":false}}],\"tool_choice\":{\"type\":\"none\"},\"stream\":true,\"max_tokens\":1024,\"thinking\":{\"type\":\"adaptive\",\"display\":\"omitted\"},\"output_config\":{\"effort\":\"low\"}}"
+        "body": "{\"model\":\"muse-spark-1.3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Look up the current weather in Paris using lookup_weather. After receiving the result, report Paris's weather in one short sentence.\"}]},{\"role\":\"assistant\",\"content\":[{\"type\":\"redacted_thinking\",\"data\":\"Q-PaDgFT_IXY3RXUUduHqe1_WSgTF5_gMh29lCBV6vhfXW34eU6nJO7gUfRPczMK4nZfQhrqQewRujwjtNKR69DHHqTP35Q0jDnuZ4GZX9qBZT1OH9JhcMl1FxvccpatEcuH2Nju9Rf12KFHAOm9eKK6wFiaZgEHcT1wPbRYVZVZ8VxLeKk-ED3wkmWFhUFJRLSgJguWBMvEMbtIUlAKsJ6qkUxClfQKMm3eft1yf9ajseT32eloGzBE48IhyXu6tpeUDs9UatFgZOHKtHmvtKsPqRw-ddbimLnMtdkexwa8xR7EVTVuwBezunqhssfYAdR4c4t6VDpACh2UL3LcVUF9b0reiwpUfdpYrwjpB3bTCWyzGjwvIwGeuoR6VrWHz5nqVbt3bBprJXqJ4IRLKAXFFlMhClkz0MFNPBufcXSdh9i9NjbNp5c8lXCSkhMfhYX9B9KbQKl3DxUCjEY_VZk0nQJwt9zQVwTzWPzl9fTkBWrdebpXCg-z4lPmU5GLyGY3MlF24eDoSfJfqibF1HHqztluSHi4XEulrwMh4dpZmLhlLxlFxwnC8LjY_Rg8uOyzeoCzsMj-R9WrZ6n9jLZrxJPVo17nFjsuSwt6zMRS9Cna6adGFso0jIKF4BNTcZXlVt0b_TWA9AY4xpGSaAQXKYRBdAZNzTK5hj-bvyfWVTBepTBKm7pAtJW2e05mVBFDqRwEr3kcKkMTRMEj8vztSX4sNjV7Sw6bDbPjb_uFeoaNkq1ua9N7ZkKsyLn80ysWQ6IL-B_AVM1toAI0bVVYQmHbRSz1MgybcT5vjK2TWfCgxBuqw1ARU3oEM1iWTvpuHkFDNGeZnT4IWc_z_vLtQVnqSlqXPtnAmJ0WJgvQGSBhojSa9QMxRz_l4LZHmXUtfdMdUHTbrZwbfoL6eIyZf43ah-sXILJWTX9wXuYqnaclwvuO3EFiDUioSIBxWvAj2HNe5HpzayuvJqneRAukiVynt9SOo79VcBKAFsHW_KhUz58KjndfvOFP7byXv_W6Xa00ve_3GEaCANjFIl7ratBEuFYtpbVTT7TGIyGmuPQTVnGe7CAcFiAvGSwoaMwqvdGheKxeR7_cZvSYREeUnL5mXev8-MKY6_AtddOanQhf9pshxAXrIUtVFqin5MGhL2j787niURU9-o_VhLgzaIqfjbfMKkzdZ3-ESyDloOeD3CwoAsD_AVIrQZQHYbpYzFYasH0VrItar07ItxWZt_sCehTOi7Jtk5G8e7fd1HtCWmrp2iArioSIp8aLOphI9lazM7taIpfF_y0EMt3x5ENSvhtEmSk4kCJQnNyRv21uHT4uD0XjdQJbHeoRhzHDxoLHUOqAX9fGBzMFO8ZsWJxl8ebiCJeJ9Jzzr9bXeUKH5cP2VymoXPs3AWBrTpw1WfADM5sjHDJLzw\"},{\"type\":\"text\",\"text\":\"I'll look up the current weather in Paris.\"},{\"type\":\"tool_use\",\"id\":\"call_01a0eba40810714cbd0a8a84496badc7\",\"name\":\"lookup_weather\",\"input\":{\"city\":\"Paris\"}}]},{\"role\":\"user\",\"content\":[{\"type\":\"tool_result\",\"tool_use_id\":\"call_01a0eba40810714cbd0a8a84496badc7\",\"content\":\"{\\\"condition\\\":\\\"sunny\\\"}\",\"cache_control\":{\"type\":\"ephemeral\"}}]}],\"tools\":[{\"name\":\"lookup_weather\",\"description\":\"Look up current weather\",\"input_schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\",\"enum\":[\"Paris\"]}},\"required\":[\"city\"],\"additionalProperties\":false},\"cache_control\":{\"type\":\"ephemeral\"}}],\"tool_choice\":{\"type\":\"none\"},\"stream\":true,\"max_tokens\":1024,\"thinking\":{\"type\":\"adaptive\",\"display\":\"omitted\"},\"output_config\":{\"effort\":\"low\"}}"
      },
      "response": {
        "status": 200,
        "headers": {
          "content-type": "text/event-stream"
        },
-        "body": "event: message_start\ndata: {\"message\":{\"content\":[],\"id\":\"msg_6a9ef3e77f6ef36fdd8f4925\",\"model\":\"muse-spark-1.3\",\"role\":\"assistant\",\"stop_reason\":null,\"stop_sequence\":null,\"type\":\"message\",\"usage\":{\"input_tokens\":0,\"output_tokens\":0}},\"type\":\"message_start\"}\n\nevent: content_block_start\ndata: {\"content_block\":{\"data\":\"Q-PaDgH-GUZkiqnb_seFaP70it_GxAEIUjt2BLllpyzfckiBOUVwr72xGQsSnj0y9aOhoaQ24A_HB0MHh4XWyYziVdRgq6lDPLHkJlmMzbusZxUZUx7D7B8kD8HrBbiTeIFbFlHaM9MiZW_PpYY9fpkdc7aeuX0mORdK8XTT3JPjvW1HPp4Qqp_iEOl9G2iM2Y6xno8SqeTcbc4EQs1LePaKrq86dBPmXBjkgQbYfvIw57o0SBEyelcudtnzJnaluOyOQdV2Ytk_r_xrYSCoBwgbf2KBCOFjdeQyruuwVZZ32JJdVOpWLw8eopUwAo2xYOZP0g8S8hTmOFvDKuzXipm1OoAXwD8Swm6ED3IIo0hHA5xSfMygDCee47nd-EpShNPamkCKodfX1QvePEJsIQK2iTgkh8IGUeEEne5dxgLuXvEAbeqGDvEy6T7IoSgZnc-KPtH6SoWM_kgc_eF_oN73Nxg2prMyCqTUNg5Qs2WLPjA9wSLmmnCoiDr1bYNIuQyn6adgv0-nZZXETJoRAHJBj65Asa8kbLyCYesb192178xCj2aBSdwyj-jc0i328sa9STS7mUSI7KvOt0Yi3kllLs1aSnHW-ogsUJUM7tTf83VO9fRRU_aW4H6qr4OAr8jbBKSD3bxE0AekDd24ZS-8YIjiP1tMOAPZ2JGQrNqbxnaeqhCZzD2nl-E8TMXaAJIk4L3oZtV80xJiUW7mLEf_jQBPAWhph4ujbkDaufGvNrl4FXyBJ-XpKMIA5z0jAYU2b3ul5-Qn5Km7Oc8fPu1M_0XGAOKG-pF9ppr4y-an4B4mKDYoAiSHp3cjv-fW57D87wBfQPaJRjOzWhzqENO-5MlB0CEsnDtrLveE2ui8wSECszParUNk5SEaeSYvrXLY0QkaE7CTK9ljwTKjJM34r1a8o16KFxGuzMrloNlxIYIaO_suM9CDuf8wNwe8KkAV2Kt28g9LwkL5b3mtI7ZSjTdHYOOhFFMzs-sjXboQoGAJGOhMnCQNc3E5-goSzvOzEIXehSTs8Mzyq8d3C2k5F9PSgdO6ZouHVURDgbEXTqWqoqjQ8huk5AbrUX16QwhJambd6P-3i--Idz9CbIVuWIqiMm80TvYlMttobYxTyFDIJrKJTrVA0PkAOFvOMfYt27d7z2ZMrTf6Vtm_DNniuhVbvVU3ZcWbb4LO-XkwH3bfHB-sckpwURP34KzOMvogaqWaMAZlabdd-lQKCc7tMhmo9BrYwHHvLxAELD2qQnyym43Yo1iJNAyrqoUAFk6K029fDon7h9ybmKZdBxRtS3arUesY_91Xep0tA0Y1UYUKo8zKjK3Op_DbVyC5OoR8rxpumKiqk2PtG7RPf-WjEXGkleGqZtxix7ILSkQXxW6McY1r_6LAh2Nv0nUzqS019tTb7mx2OLyt2g\",\"type\":\"redacted_thinking\"},\"index\":0,\"type\":\"content_block_start\"}\n\nevent: content_block_stop\ndata: {\"index\":0,\"type\":\"content_block_stop\"}\n\nevent: content_block_start\ndata: {\"content_block\":{\"text\":\"\",\"type\":\"text\"},\"index\":1,\"type\":\"content_block_start\"}\n\nevent: content_block_delta\ndata: {\"delta\":{\"text\":\"It's sunny in Paris.\",\"type\":\"text_delta\"},\"index\":1,\"type\":\"content_block_delta\"}\n\nevent: content_block_stop\ndata: {\"index\":1,\"type\":\"content_block_stop\"}\n\nevent: message_delta\ndata: {\"delta\":{\"stop_reason\":\"end_turn\",\"stop_sequence\":null},\"type\":\"message_delta\",\"usage\":{\"cache_creation_input_tokens\":0,\"cache_read_input_tokens\":0,\"input_tokens\":210,\"output_tokens\":50,\"output_tokens_details\":{\"thinking_tokens\":35}}}\n\nevent: message_stop\ndata: {\"type\":\"message_stop\"}\n\n"
+        "body": "event: message_start\ndata: {\"message\":{\"content\":[],\"id\":\"msg_6abb4cd0b3f15768e1ae4287\",\"model\":\"muse-spark-1.3\",\"role\":\"assistant\",\"stop_reason\":null,\"stop_sequence\":null,\"type\":\"message\",\"usage\":{\"input_tokens\":0,\"output_tokens\":0}},\"type\":\"message_start\"}\n\nevent: content_block_start\ndata: {\"content_block\":{\"data\":\"Q-PaDgF70ZwJMdvZQh6urOFUjgHa2IrdJbBv8RFXDpivwOudmj9QoCi81uRWeArjn_7V2nNk6i6jlHMjN7ACeZUE-faBnl4bTI10Fs0w0SSgcdkMaume2hpXBrZB85wlEttQviz-Pc5EHhAzU5QFIrK83CQkhJENqcfY3NJW1-55JFqlXmWSFV0GtNp3clG7V0LR1Zaq54hqIUY5iwf1pB8VIXLxPca3LwXMGbQPgjOgj_WNKHEBGl6mIafeca1OlGuDrJPN9tWBhlfxJCkcRU0zl14NA8chEyr96N40KrPewjVAlWO3jSejy9V7PnglilNewhUXOEQ75w2tYiZDajBfz6iG_n27zD3uvgD3QQthdyeUhJqlBaX81zMIe39Ctfo-cX-62cKwE3_EHy_7SxkwY5Olbf_bwL4GGzR39MObZoyv8-ZU1kwwVuSLXuDFvIx6iaAMZ50U4xXYbOphAaw2rylql0_kiPlFS9V3Fr_Jvx4vplj-8xh9JI7Uu9t9O7ltECpN9Qfu32fqxzWy9-ZVIh15gzhyegNeICBOcz6b9s3CIFHnzRcU69Ru9-lbydKv7scII_2xxLd-wlHQDCXHXyTeTeZjbTRiul0u5J2m8gGefF-j0lVChJOh8F4vBltzYTFTiQoSP8KtL61VJOt6dLsxOQA0Rq4PR5Lcs2fAfJbKb7jYB23bmXvQQ1d76keuvq_yoSIhrSyxLvXRCxouoWttkI8QC0u7O5pZUIPVfiYMI-j3bbc63BFOu4wAGbckm8Txo-gAY8UYAAwMBX17SD5EcTR82njKmd1R0Y8XOJLiwZRlN0ou-syq8xhahVgd0VcyB1HKr1f9mbhJdqFkKGpWh9-SR6jT6fKCCFxeMA3caczpG5wP_q5SGgyUiK0GWYpHabjSeJWac-04TDOfqL4QwLEKuL4PjlINe9OZY1n1lPJa2_MS9YGt6qlgLe3uZSEBwHk-ul5_yRetU8bd7lYcwDtUHT6puEkdjqeYwYQ8XWkUjoYwvSIMB_2v_owa5p9gPzf5Fr_zWqG7pizrStNNHq1MjXQX8Pl4Z6e2LZ2NjItfjR1GKdErNEJWXyh0oHCQKD1fIOXl64lpQorAHUcKV2HZm_SkwV7kxvzAfhdeT9Fe3AXZmtPBS1m0ZMMYNMYsNKb813JnWu8LvNg_zgXLBWsiB-hl4kCk1NKVAsCoA0i8JUFnGGm_uQp6t06a5NQYEXvi5A0akZTacle4UTBflNdsIVR6tSaO_m49nnr-XYSIh3tEzfjOsXpFz5L_A9SBDdPSGpcMJrs00nl1wDpF78OKC8NhwkIx8ydwF5A-ecXf91SbgqzVgv2T-wzuziA1wjJbPsGzTxP_wULUc2P5-ftFAMpsiRHB_-7hq6ZGo3HwNWjK2DTTN_89u7RCjuErEVPXUv-2fQ\",\"type\":\"redacted_thinking\"},\"index\":0,\"type\":\"content_block_start\"}\n\nevent: content_block_stop\ndata: {\"index\":0,\"type\":\"content_block_stop\"}\n\nevent: content_block_start\ndata: {\"content_block\":{\"text\":\"\",\"type\":\"text\"},\"index\":1,\"type\":\"content_block_start\"}\n\nevent: content_block_delta\ndata: {\"delta\":{\"text\":\"It's sunny in Paris right now.\",\"type\":\"text_delta\"},\"index\":1,\"type\":\"content_block_delta\"}\n\nevent: content_block_stop\ndata: {\"index\":1,\"type\":\"content_block_stop\"}\n\nevent: message_delta\ndata: {\"delta\":{\"stop_reason\":\"end_turn\",\"stop_sequence\":null},\"type\":\"message_delta\",\"usage\":{\"cache_creation_input_tokens\":0,\"cache_read_input_tokens\":0,\"input_tokens\":152,\"output_tokens\":55,\"output_tokens_details\":{\"thinking_tokens\":38}}}\n\nevent: message_stop\ndata: {\"type\":\"message_stop\"}\n\n"
      }
    }
  ]
@@ -2,9 +2,16 @@
  "version": 1,
  "metadata": {
    "model": "muse-spark-1.3",
-    "tags": ["prefix:meta-messages", "provider:meta", "protocol:meta-messages", "text", "reasoning", "adaptive"],
+    "tags": [
+      "prefix:meta-messages",
+      "provider:meta",
+      "protocol:meta-messages",
+      "text",
+      "reasoning",
+      "adaptive"
+    ],
    "name": "meta-messages/streams-text-with-adaptive-thinking",
-    "recordedAt": "2026-09-07T17:26:18.565Z"
+    "recordedAt": "2026-09-29T05:29:46.263Z"
  },
  "interactions": [
    {
@@ -15,14 +22,14 @@
        "headers": {
          "content-type": "application/json"
        },
-        "body": "{\"model\":\"muse-spark-1.3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is 173 multiplied by 219? Reply with only the final integer.\"}]}],\"stream\":true,\"max_tokens\":2048,\"thinking\":{\"type\":\"adaptive\",\"display\":\"omitted\"},\"output_config\":{\"effort\":\"low\"}}"
+        "body": "{\"model\":\"muse-spark-1.3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is 173 multiplied by 219? Reply with only the final integer.\",\"cache_control\":{\"type\":\"ephemeral\"}}]}],\"stream\":true,\"max_tokens\":2048,\"thinking\":{\"type\":\"adaptive\",\"display\":\"omitted\"},\"output_config\":{\"effort\":\"low\"}}"
      },
      "response": {
        "status": 200,
        "headers": {
          "content-type": "text/event-stream"
        },
-        "body": "event: message_start\ndata: {\"message\":{\"content\":[],\"id\":\"msg_6a9ef3b8e46a777cfdc94a93\",\"model\":\"muse-spark-1.3\",\"role\":\"assistant\",\"stop_reason\":null,\"stop_sequence\":null,\"type\":\"message\",\"usage\":{\"input_tokens\":0,\"output_tokens\":0}},\"type\":\"message_start\"}\n\nevent: content_block_start\ndata: {\"content_block\":{\"data\":\"Q-PaDgFtwwNGqSqKxPk9Zj-j9xogYigpDsDHrLKPV-DxmXcbhtXDPrGPuj5qB4l1FslhuEQFCA8zIRyNGaCmzM0JG4GOZe3LpFYM2iegBbi24l4V7souryAwUs_7PrInxObuguMwh2S66ML6PwlfVRVTAwPsgDSCl6Y9tkoDHr2KBRY2fzJhmjkotuFRK2LYvNp9pKi89JxnoIKK8B_UJc_B2r4vU_Txq9_rWTmo2eXFoGOSMZNaHpVrvACRQKC1jc6-8Pj5JkJN11_Cs2fHqlaCwOoPDVJxHXUXP1AMHU1mG0jR4qf9wUaz8kMmyCBBijlfQJ4G7nsQs7LJO9gS2ropmynDoO5IEIAFf7ekxLw54Fx3JigC0_qz4Jx4a04Ey8JBzWRlZNdqggpq2_I_VoT3S0zhCYDp8ZAJQs2JqvvF-ZmLcMPH1PmpkgRySqXl5TDxERIpdL3aOUzTl-PTHVMIGEcSAz84fFwU4p1kS5llGEGC6jHlClscEEto1Y-qthL6BoeDALzk7GHEMVQD0bfC4E5yGCh0_xlWqsG3XPj0wpYKBc0hfh7vjO1NpzPxCtaDjnRwR6TzSo6x_HrEL3VELArHhpYAXl30fNO-EepduZ3Hd_kWqWj_GhdIM4dRh2zoytbhIesVD7OvBqU47urKFnpXw4kswJ-NoVVNk00ysMMHwobT9BdJL9UCoXlNzyErPe8LkA9f0VrKkuLCg5FDr_DCEYXHXr7fdRmC3JTKuzvxffvPYppUt3hs5gbdXWgT2iZzunt4bSfFne7BPkj9OGREyfLcukvGAh_oqPLXuu0lert9wbTAqRUTyM5Y1nSjw3h2B3jv91mH78mGvhy8LeVNLkrSMxEa4GtrrUvlzkPnZayc_LE2Sr7JnQjhwylVNWvkcIAjstOZShjPKe4pUJwj-cUXmXZB7Zwr-Q9WLtprFgQoBvadd5DHD4aynsYEabKZVcOqhV8l2zyaUCGobUzdPqBC5kk5-VPmNTqm6Qs91mb1y_5ydmHjTWmSW6qtN_op-Xfwqr_hllvOjhnAvvDJWUOKH-YIgZw_k_db2mzW1hO093jSDMYv6wpiy_5XWMNJBjcH8hvR_pFjXIqScUnKPranEZvCyGfHR-UBNJ89s_JEE49chcIt8LiukBeXQ_TOe29kzWnT1tYtfGQXP8FY2Wukw5yhvP3coGp1-LPZRuw3BLP2tWmiijmyj5lMikp8MIeqOztN8zgsArZ9jq21EtDSNfpO_0C4GEOtCZQYvZHRpDeY966XDnN7Blenn_8FZ95M-M-1My8hsmF__JrnY4ZFZr2274f_FbyJaSqGj6H-YRuzawO2TVLWHxAr6v2LCiB_QX01PwUI1yaJmP0mI-Qz5zXgSHzfVzhF7l1zEnM8qIYcSXzD1Gp3rjpn2sq-rR-JLqeHq080Hl0X9c8lzozw3qCpvcTfA-4ZTdXU9ax3nt7emcPVFo9N_JBjYashC7KvjkIWjMhQoTbIRlO18gjEa-Dvtsmo4_xE1ApYRoylbhxg3_fQJjKLfCBv32V6BM8qWKINL7d1nYP7PtAKnglCdnT_dK0_pCK6ejGfmdWZgVj0DhVZUCXf2kN530Y0hoCb1jBgwJ16a5gUqJMtnWScarIGSVrsYMA_uEt7DwQzGYAGESVIgi8JVATkxoq4EbyOLCHX7MIKmAPGV2WWTjWAWLnE2ITjlXtBkUAwjq2v957BMgIqxSNxEjG75Gd0i1XjZAujCSCXMrywZ72-VdQy4cD6kzH9mv04fZ7_dqn9eKPHBY7_T7V6myRDj_ImkffXcygmd7F-_-kHMExI6ABas1WtfDjkYgbRM0jMtIHYL-W9xT8vCSLSdvHcb5Y8XSXT5GTwI7eIlBHnCvFrgunbCo9bJJlT2Gc1RcgeZ4rg3yu1MNF4Mfk6DBwDhduGh5l7nypL00B0HokLfF4H7N1oSKL9jdVE3oMyJuA9NV1SJiyqcneSVHBzqjFZ5sszFXPlBKEz31izxFToAF4tDYMR507zYLcxyLA4AmHlkmn0qeozPb5qk-qZB6yLywtewv8O1KqxieAEJnEmyiqGnoKBdkjpeYmplErSxJyzoRX4fXb9mOdb-izJgvqSQ5uLm0_EXf3OklpMoAJ2CPJ6cxpg_5bhiwbgEtafCuDyXVL9Zzi872yUb_Z-ATlqU1M2Ai67f1piHIUDzMn4kulXQhPMb_R4eznMbX_aRigQh92-t1USoFtX2vmyCUQageFcrHHK524gPQ7rkOfDvZ8GHPXi3YZFnzGkSKjQD0jumFtzDiRqYkkMECep0zgY8MjuWLMjlMuigpkzSm8GPZ2aFeIMxJCYR8iMf7fH9NyHAJnicx4wdW_UqqgY5jfVtDvPSL0SRScyyK0jNdmofDHjWp4Tehih5OOw81E3BYLCiIv2p2zTMRSTZxFyG3HI91tIEaJu_RnIMFxzCilaP1LcbMrjyFzBtLJiXXJ--eFYyIMYKgfbWIOTsjLLJGC8NS2wuzaXB-C6GLsuSEHci5a8f5KGqaXK99LvHtY4k36WhEoVUjQEGY7HNJrtdjBUlqDgnT9iO06gGd2QCGvlP4us-Z3q2Bcyhf0LzOgn_Bpjc6YBk4TNF1AMxG15qmhnsrWcGElkpk3Vh9npC8--vkvhh7pOPfTZlNjQQh900OemY9gwxHyCBbt1096g4qkYOntGJmw-wVjyWxOt9K9CaM9WxY3wFyOmwqiFL1PK4CMeKMZk54iZ1ZiyXDOvsO7qUa9XQGDy3W8ic6R3DUzdkxEEBFYHAjDy3qE\",\"type\":\"redacted_thinking\"},\"index\":0,\"type\":\"content_block_start\"}\n\nevent: content_block_stop\ndata: {\"index\":0,\"type\":\"content_block_stop\"}\n\nevent: content_block_start\ndata: {\"content_block\":{\"text\":\"\",\"type\":\"text\"},\"index\":1,\"type\":\"content_block_start\"}\n\nevent: content_block_delta\ndata: {\"delta\":{\"text\":\"37887\",\"type\":\"text_delta\"},\"index\":1,\"type\":\"content_block_delta\"}\n\nevent: content_block_stop\ndata: {\"index\":1,\"type\":\"content_block_stop\"}\n\nevent: message_delta\ndata: {\"delta\":{\"stop_reason\":\"end_turn\",\"stop_sequence\":null},\"type\":\"message_delta\",\"usage\":{\"cache_creation_input_tokens\":0,\"cache_read_input_tokens\":0,\"input_tokens\":23,\"output_tokens\":266,\"output_tokens_details\":{\"thinking_tokens\":254}}}\n\nevent: message_stop\ndata: {\"type\":\"message_stop\"}\n\n"
+        "body": "event: message_start\ndata: {\"message\":{\"content\":[],\"id\":\"msg_6abb4cc8199fc8fa6763470e\",\"model\":\"muse-spark-1.3\",\"role\":\"assistant\",\"stop_reason\":null,\"stop_sequence\":null,\"type\":\"message\",\"usage\":{\"input_tokens\":0,\"output_tokens\":0}},\"type\":\"message_start\"}\n\nevent: content_block_start\ndata: {\"content_block\":{\"data\":\"Q-PaDgEdq_xGJ7Hl5i3AUq-IGolHfh7VsPu8914OD3BSVMiPCf1QVZ4O553OKpiejFGIkjBEfR2gGxcXlTsKuK78wfAiGAft2yQIHPeCJt4Csoxc3UUX405gUHqO9M06WeU118pTrlITW4g4dElALKmE2zi_pkQzEvU07jPqsF4n-3-9FkEnJ3D5Ag0UsU4LI1Mn5-EwPyPkitspoB-ytXsugMGQTMMfInzNq0OKDDMAO88aRQv24EslYBviairfM5c-k6dqOdGfsg_SntRiZJVNoo1yowGhQuiMKXreeQiQj_hrSVEXo8PVybmaCXtfW0I_2rI7JKR1uO-fxUHZckcCvLKMS3Wa2cwPUM9MPAnq05l3lbD1LpqZ_UPlf534p8_0BmF4hVGI2pamDWkL--7UaWrGFYtwBc3r9GVW0aIZC1ArnGjXsInKCnJuJ-elKu8H0Wp8-lxrsEfqtmxCamrsil8jOkIMezwSMUGtawhcOSdOnyQRje2b3OXiRx7Y-XZjrBlErbS13tdMJhXGlVqp9tazXlKdIt9CpMfMxjYW-Z5VkrJNymsBcjW1r2x5DC2VzGcqcha91rBkskrhKGWix95cdaEqUkP66DW9jThk4RS__E_oyt8DMTpvCxoZ5pe_mLkuS-ZpYKFeZbRegegIQErP_yuhvPWCwTYZymW4uUTVEmxdJ1otAST4ICF4ChsbHLLzJc4XHO7TA5GcwEc69m-poLTFrJvuYRErYhHHONOGWZGoyaPXApsmytUW6-lH2OiVpViVrLg_qvDw1NwyTgguQfP1d6JJYTmnjgN-Pa9170lqGzMI1fVjsC9zY5e6qe6NiyOwpxbFoV-jfdzyfeKX5LMVacpj2xV6dk6dYW7zcIZ3rJJvCpnwJROCjKbSRa4RvBFWNW2xjiWi1tYltzsz1YR1RHZJEN8szlfJjdMrfJdR5GbOiiDMcwGgGNOF5kbQqLgkggzR-B4lUNGLvSyBjAd_AdLpab0r9j1XdKBPWLFiXfAtX8lPSfeCSV41LFxKopB-MIVOpgtrwW6dsEayU7_w4Tc1nBTtYOGf2cGUV2XYzEpt5vxzCDC-og8WZ2lr3hOczp543-_I8n2ZOQEEk1k3suykPiQen_wgcpRccm18Aqsjy2t3uitZ-p1p4g0s6tG6Y_DCS4ku713v9Uw2ezHosl4Qk5JVk-KNvi9ZCYb9Jmc7PqHubP6Ua_UTyIeTiBB60zK5EgatIglUv3_NudfsplEH8YJkMvoAPJk-HW7c2WwzoymfA4TFoCg8vt3YHGAtuiyqF17-S3sfhl9J6oX-7FFpGn6bRqgwguC6sHUQw3bqWtyG4LjUy3_qzWfCI5zSm1hxjd6YRaxkdlv37Ol3Ua-65b3gRmQoUlA7omPbHuC8r2TNnG_ltsp9EMJlz7HN-Gyggw\",\"type\":\"redacted_thinking\"},\"index\":0,\"type\":\"content_block_start\"}\n\nevent: content_block_stop\ndata: {\"index\":0,\"type\":\"content_block_stop\"}\n\nevent: content_block_start\ndata: {\"content_block\":{\"text\":\"\",\"type\":\"text\"},\"index\":1,\"type\":\"content_block_start\"}\n\nevent: content_block_delta\ndata: {\"delta\":{\"text\":\"37887\",\"type\":\"text_delta\"},\"index\":1,\"type\":\"content_block_delta\"}\n\nevent: content_block_stop\ndata: {\"index\":1,\"type\":\"content_block_stop\"}\n\nevent: message_delta\ndata: {\"delta\":{\"stop_reason\":\"end_turn\",\"stop_sequence\":null},\"type\":\"message_delta\",\"usage\":{\"cache_creation_input_tokens\":0,\"cache_read_input_tokens\":0,\"input_tokens\":23,\"output_tokens\":161,\"output_tokens_details\":{\"thinking_tokens\":149}}}\n\nevent: message_stop\ndata: {\"type\":\"message_stop\"}\n\n"
      }
    }
  ]
@@ -2,9 +2,16 @@
  "version": 1,
  "metadata": {
    "model": "muse-spark-1.3",
-    "tags": ["prefix:meta-messages", "provider:meta", "protocol:meta-messages", "text", "reasoning", "enabled"],
+    "tags": [
+      "prefix:meta-messages",
+      "provider:meta",
+      "protocol:meta-messages",
+      "text",
+      "reasoning",
+      "enabled"
+    ],
    "name": "meta-messages/streams-text-with-enabled-thinking",
-    "recordedAt": "2026-09-07T17:26:20.464Z"
+    "recordedAt": "2026-09-29T05:29:50.023Z"
  },
  "interactions": [
    {
@@ -15,14 +22,14 @@
        "headers": {
          "content-type": "application/json"
        },
-        "body": "{\"model\":\"muse-spark-1.3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is 173 multiplied by 219? Reply with only the final integer.\"}]}],\"stream\":true,\"max_tokens\":2048,\"thinking\":{\"type\":\"enabled\",\"budget_tokens\":1024,\"display\":\"omitted\"},\"output_config\":{\"effort\":\"low\"}}"
+        "body": "{\"model\":\"muse-spark-1.3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is 173 multiplied by 219? Reply with only the final integer.\",\"cache_control\":{\"type\":\"ephemeral\"}}]}],\"stream\":true,\"max_tokens\":2048,\"thinking\":{\"type\":\"enabled\",\"budget_tokens\":1024,\"display\":\"omitted\"},\"output_config\":{\"effort\":\"low\"}}"
      },
      "response": {
        "status": 200,
        "headers": {
          "content-type": "text/event-stream"
        },
-        "body": "event: message_start\ndata: {\"message\":{\"content\":[],\"id\":\"msg_6a9ef3bbb7e691b3ea26427b\",\"model\":\"muse-spark-1.3\",\"role\":\"assistant\",\"stop_reason\":null,\"stop_sequence\":null,\"type\":\"message\",\"usage\":{\"input_tokens\":0,\"output_tokens\":0}},\"type\":\"message_start\"}\n\nevent: content_block_start\ndata: {\"content_block\":{\"data\":\"Q-PaDgEpowvGua1C8z2RSICyyeSLruZ1JBUhrhLhgqf_XauiaESRHyHgIPVF0Cfxp7eLB_ESNObq7vJNDLdffE-RaN5nEauXhRxH6fJErC-4H_KELZFGF-qNnGu2DWl-gEojkwwkq1HtTtT3rOEk5isGjdribnDvR7a1zkpG3I0BxE_UyseISDSbkev5tyV7DkiH4xyv2ZmwuO3HHGgmAztEek9vm0ZTElZ8PIPvHG6P38aYGTGKrTjyOhmN3LBa_NFvtQQkUMKRB3n7L_N5KB1NbYkPzLEJ6L5dL9DJZBSsZms0O62QZ2zs2oWZ-ekQWL4oIuiRozWVpmwzjtkJl9WXtyvdL-4MACucXMSN9V7hWzC50g-DgdeFPSslsA9gy619wTNPPIxPymGWeD9LYKR3iwTRLNYzuycHakNqikhiwz9MweMod5GLTdbtypZJcV7ourz58jmK4YKsqleVPVvXM6bIoNuT2yGj23-tAYxQszGXQMHxSTnaLAHl6sUdiwTqX4wbFYfX-ogkIZsrca9mv5E2gkH1wJl19GPCxFaSDCHxh3QAW0RIExKUJly9Ydpoegmojfo0F4Hjt13zDm03fLEQ0eY8GjxIIHDt_zVRQGTW8d4tgZpTt4K9H1TTefG34EerN7jl7L-WNUe_gKorN4aSYBS6S6ma4Vb91NlUQ4cEGBKVQvumYe16p9Xj6Te-tCuiBmTOCq6iDsTH-eMlip_Bc18MD2BCGr2NdF4PB2vqHGSPIvSHDRXBjoPNtm18opAsUnOBu7-tysb8-EKFd5z7JbWgegQWNs11FdX0uFtC-U9ROwbHLJ3IHk4m2UHc2USwi7v4Xe6FtnkJ0VCZTajFUTXW33lwO3UsHuqEbxVnU_Rzuj6Ryjb08bpXpJBjIEGf2wBS3_I78cuXKOChHu-evtnjezc77joRUP8_I8pWsQbQ6bHABD95p8q6ZdQpDr9XQALbVg3ZvD5_QgF59rIxkW9a2L78oQpu0O3UT7-jxNFe38-OXuEr3VTv7RzISu1zjvBZD0k9-2q-T9BAJmsK6oPajJQWKwHBYF3w6vbsQ8tRDdh2uerhlAIWU0YL92gPCmT3mR6HxSGjAx08t-gib_YrzvWn0oTfLNk_BNfAMpG7Mj2GYNbyTkd_tjNZ2fOwVKbygsoFIUEvh2B-xyHOYuhXfxzI8-Gt55FMGDLLKcHfgmOZAUz1xVkIdm6bcuRFuQppgTzYIr66GN6tsr9KxTN2GZ2NHCwexe0hSAGfKVyLr8QBxTDRlzubBqe-osgQJrJtS7uM1MuWK_8grkZrNsn6g3ami0JboEmM_Ct3gVhkXo6lhCCcjn1gnGX-HOLczT3Xty1wYkeayUpi9x326nrSmypxzbzCRS3bOaPvSoBCszri0uTfUnVQK5kTVuRD30fGxauPhA\",\"type\":\"redacted_thinking\"},\"index\":0,\"type\":\"content_block_start\"}\n\nevent: content_block_stop\ndata: {\"index\":0,\"type\":\"content_block_stop\"}\n\nevent: content_block_start\ndata: {\"content_block\":{\"text\":\"\",\"type\":\"text\"},\"index\":1,\"type\":\"content_block_start\"}\n\nevent: content_block_delta\ndata: {\"delta\":{\"text\":\"37887\",\"type\":\"text_delta\"},\"index\":1,\"type\":\"content_block_delta\"}\n\nevent: content_block_stop\ndata: {\"index\":1,\"type\":\"content_block_stop\"}\n\nevent: message_delta\ndata: {\"delta\":{\"stop_reason\":\"end_turn\",\"stop_sequence\":null},\"type\":\"message_delta\",\"usage\":{\"cache_creation_input_tokens\":0,\"cache_read_input_tokens\":0,\"input_tokens\":23,\"output_tokens\":143,\"output_tokens_details\":{\"thinking_tokens\":131}}}\n\nevent: message_stop\ndata: {\"type\":\"message_stop\"}\n\n"
+        "body": "event: message_start\ndata: {\"message\":{\"content\":[],\"id\":\"msg_6abb4ccc0beea22bb95a41de\",\"model\":\"muse-spark-1.3\",\"role\":\"assistant\",\"stop_reason\":null,\"stop_sequence\":null,\"type\":\"message\",\"usage\":{\"input_tokens\":0,\"output_tokens\":0}},\"type\":\"message_start\"}\n\nevent: content_block_start\ndata: {\"content_block\":{\"data\":\"Q-PaDgGoJiKtl-javJ6dY04Ws79OK_mVBNQgu19iuCSru9wUy0jS0-87v1Lr1jC3I6cI8gnBvTl3HcRgR8MqmTOddFg5f_QSqhUweOVsCzaNL18Bjkye_cK3jGmlc9IsGLJ8dGFvFMPwflkMcofmwZ1P0EsMivXgwsDsWuiHP3PAP6_DfKgpVnNoz1oxNXgoVMTaNylNHtKHXpeC4_doHgWONMjhca771bIh_x0sRT-mQlONkr6HHgzzpCftEGOgnELEC7DlmJ46CDe_VSuaiUk8VLeNV4xyNm4XBHoyFuEn2N4tmG6mxo3cQlN2er8lY39XmY5gqy4ZIJddoY4sVFxBfL-axfDDv89hAhTYgXxH4dj4MyAj5TPWdyVZwunw2dRwf9JobQW-HCGcPxW6rqE7znOAegWSLD-mKRGZXNp7-kTY5Wicv9toV-VsBIFc1YpHFRpw36pxZftd2JnbW38dNYH0fO_QYnCknHxE9RA68uFpu_JvvpHOO0sFAuqwOCMynQyqFZRY9vVJBMYnuB_RIY_WCEuZwt7hV9es1aPk2QJyAWFh-LnNDzp9ktLaNwnnJxRpEK1r0PMbUsIQJMuxcNH7lCstE2dGBf02O4lH4HlZSHNsLcZuUjb01HCISf7cQXzIjG6rO_47m52h6bMpYZITElM66XVlKRE5V3wF_7sQ2BaT4g8GLxxTkgh-C0x8ISPVaU773cDvJSuOI-5FlUbviG9oQG_0PxU5ulQDCMSEM4wZENu6ZRlngTloFSxHJfeQvShiy9pC9kv-DuOT1stUT4HqpV0bV7WGrJjlX9l17JbMgjMBwzhNWTJwGiuw2Ya2cCveYgSzxMZtcI_YH9mv0n53c2h7_1Lq2-kVDx_R5UngrMLu9YxjIwIgK_UtbtnTXJ-q5X4DexgovoBPjzc2GOQeK0DoOnfOczVLMALAkQMnyxCQ65ZuawVuJFmIKY9ooznuqWjl5mLxVCn5Fyhk2uTKjFlbW1JO-RdvNF9CMRD2y2bY2Igy4w9Gh1R_xAhM7rwF0dt_p2g8CUjqsEyIn9bSGuRuzXfkxNz7KYfyCD2rkZc1gw8oU7jiLEpNl5gCkcj7bNql7lcDYgJtGSDRwZlIzZcb7MaxFHyFw7dXGtrOIvLL5eF8TOidjaRaY27xkCCBkQXWeIiX0qV5AuojjrpRAJsVVvdT5s2dHd1IYHU0nnsePU1Dd7gyB59upU9W1AaFrXjx0pn4MsNuYDcyLyzihq1lCeK23OSoXkwH9UI-zaLkV6MGUf_K0jMJPr6FrMgYF1x_SpXYOKSXPHhY5UE3pGLIL5_vFCRkAkMcvpw-H3tyljgnCZwt3g-Yuy4Uj05MS3PseQxuUor-0trgRBaBW4AdB925t2D41RJ4xp3HnEpjEkNFJ8Hsqbs3QxyVoTAvElXOrQ\",\"type\":\"redacted_thinking\"},\"index\":0,\"type\":\"content_block_start\"}\n\nevent: content_block_stop\ndata: {\"index\":0,\"type\":\"content_block_stop\"}\n\nevent: content_block_start\ndata: {\"content_block\":{\"text\":\"\",\"type\":\"text\"},\"index\":1,\"type\":\"content_block_start\"}\n\nevent: content_block_delta\ndata: {\"delta\":{\"text\":\"37887\",\"type\":\"text_delta\"},\"index\":1,\"type\":\"content_block_delta\"}\n\nevent: content_block_stop\ndata: {\"index\":1,\"type\":\"content_block_stop\"}\n\nevent: message_delta\ndata: {\"delta\":{\"stop_reason\":\"end_turn\",\"stop_sequence\":null},\"type\":\"message_delta\",\"usage\":{\"cache_creation_input_tokens\":0,\"cache_read_input_tokens\":0,\"input_tokens\":23,\"output_tokens\":198,\"output_tokens_details\":{\"thinking_tokens\":186}}}\n\nevent: message_stop\ndata: {\"type\":\"message_stop\"}\n\n"
      }
    }
  ]
@@ -11,7 +11,7 @@
      "reasoning"
    ],
    "name": "minimax-messages/m2-7-streams-default-thinking",
-    "recordedAt": "2026-09-07T16:53:20.721Z"
+    "recordedAt": "2026-09-29T05:27:50.902Z"
  },
  "interactions": [
    {
@@ -22,14 +22,14 @@
        "headers": {
          "content-type": "application/json"
        },
-        "body": "{\"model\":\"MiniMax-M2.7\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is 173 multiplied by 219? Reply with only the final integer.\"}]}],\"stream\":true,\"max_tokens\":1536}"
+        "body": "{\"model\":\"MiniMax-M2.7\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is 173 multiplied by 219? Reply with only the final integer.\",\"cache_control\":{\"type\":\"ephemeral\"}}]}],\"stream\":true,\"max_tokens\":1536}"
      },
      "response": {
        "status": 200,
        "headers": {
          "content-type": "text/event-stream; charset=utf-8"
        },
-        "body": "event: message_start\ndata: {\"type\":\"message_start\",\"message\":{\"id\":\"bd0c49bb4f5e6f26b77bab9b5a917484\",\"type\":\"message\",\"role\":\"assistant\",\"content\":[],\"model\":\"MiniMax-M2.7\",\"stop_reason\":null,\"stop_sequence\":null,\"usage\":{\"input_tokens\":57,\"output_tokens\":0}}}\n\nevent: ping\ndata: {\"type\":\"ping\"}\n\nevent: content_block_start\ndata: {\"type\":\"content_block_start\",\"index\":0,\"content_block\":{\"type\":\"thinking\",\"thinking\":\"\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\"The user\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" asks: \\\"What is 173 multiplied by 219? Reply with only the final integer.\\\" So we compute 173 * 219. Compute:\\n\\n173 * 219 = \"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\"173 * (200 + 19) = 173*200 + 173*19 = 34600 + (173*19). 173*19 = 173*20\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" - 173 = 3460 - 173 = 3287. So total = 34600 + 3287 = 37887.\\n\\nAlternatively compute directly: 219 * \"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\"173 = 219 * 173 = (219 * 100) + (219 * 70) + (219 * 3) = 21900 + 15330 + 657\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" = 37887.\\n\\nThus answer is 37887. We must reply with only the final integer: \\\"37887\\\". No extra text.\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"signature_delta\",\"signature\":\"1625da2f905565076ee90b9c2919db39b1719731c0820eca2f2a1c9c28324e87\"}}\n\nevent: content_block_stop\ndata: {\"type\":\"content_block_stop\",\"index\":0}\n\nevent: content_block_start\ndata: {\"type\":\"content_block_start\",\"index\":1,\"content_block\":{\"type\":\"text\",\"text\":\"\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":1,\"delta\":{\"type\":\"text_delta\",\"text\":\"37887\"}}\n\nevent: content_block_stop\ndata: {\"type\":\"content_block_stop\",\"index\":1}\n\nevent: message_delta\ndata: {\"type\":\"message_delta\",\"delta\":{\"stop_reason\":\"end_turn\"},\"usage\":{\"input_tokens\":57,\"output_tokens\":187,\"output_tokens_details\":{\"thinking_tokens\":184}}}\n\nevent: message_stop\ndata: {\"type\":\"message_stop\"}\n\n"
+        "body": "event: message_start\ndata: {\"type\":\"message_start\",\"message\":{\"id\":\"419c5ecf093decc95250bc4cc3afce52\",\"type\":\"message\",\"role\":\"assistant\",\"content\":[],\"model\":\"MiniMax-M2.7\",\"stop_reason\":null,\"stop_sequence\":null,\"usage\":{\"input_tokens\":0,\"output_tokens\":0,\"cache_creation_input_tokens\":21,\"cache_read_input_tokens\":36}}}\n\nevent: ping\ndata: {\"type\":\"ping\"}\n\nevent: content_block_start\ndata: {\"type\":\"content_block_start\",\"index\":0,\"content_block\":{\"type\":\"thinking\",\"thinking\":\"\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\"The user\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" asks: \\\"What is 173 multiplied by 219? Reply with only the final integer.\\\"\\n\\nWe need to calculate 173 * 219 = ?\\n\\nLet's compute.\\n\\n173 *\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" 219:\\n\\nOption 1: compute 173 * 200 = 34,600 (actually 173*200 = 34,600\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\"? Wait 173 * 200 = 34,600? Let's check: 173 * 2 = 346, then times 100 = 34,600. Yes\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\".)\\n\\n173 * 19 = 173 * 20 - 173 = 3,460 - 173 = 3\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\",287.\\n\\nAdd them: 34,600 + 3,287 = 37,887.\\n\\nThus product is 37,887.\\n\\nAlternatively, compute \"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\"219 * 173: 219*100 = 21,900; 219*70 = 15,330; 219*3 = 657\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\"; sum = 21,900 + 15,330 = 37,230; +657 = 37,887. Same.\\n\\nThus answer: 378\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\"87.\\n\\nThe user wants only the final integer. So reply \\\"37887\\\". No other text.\\n\\nThus final answer: 37887.\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"signature_delta\",\"signature\":\"48b0f683a3fb6cfc2e060ff709c12a905c76d2e5bdddc709fb5b1cfc5aa600f7\"}}\n\nevent: content_block_stop\ndata: {\"type\":\"content_block_stop\",\"index\":0}\n\nevent: content_block_start\ndata: {\"type\":\"content_block_start\",\"index\":1,\"content_block\":{\"type\":\"text\",\"text\":\"\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":1,\"delta\":{\"type\":\"text_delta\",\"text\":\"37887\"}}\n\nevent: content_block_stop\ndata: {\"type\":\"content_block_stop\",\"index\":1}\n\nevent: message_delta\ndata: {\"type\":\"message_delta\",\"delta\":{\"stop_reason\":\"end_turn\"},\"usage\":{\"input_tokens\":0,\"output_tokens\":259,\"cache_creation_input_tokens\":21,\"cache_read_input_tokens\":36,\"output_tokens_details\":{\"thinking_tokens\":256}}}\n\nevent: message_stop\ndata: {\"type\":\"message_stop\"}\n\n"
      }
    }
  ]
@@ -13,7 +13,7 @@
      "usage"
    ],
    "name": "minimax-messages/m3-continues-a-tool-loop-with-adaptive-thinking",
-    "recordedAt": "2026-09-07T16:53:25.185Z"
+    "recordedAt": "2026-09-29T05:27:53.421Z"
  },
  "interactions": [
    {
@@ -24,14 +24,14 @@
        "headers": {
          "content-type": "application/json"
        },
-        "body": "{\"model\":\"MiniMax-M3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Look up the current weather in Paris using get_weather before answering. After receiving the result, report the weather in one short sentence.\"}]}],\"tools\":[{\"name\":\"get_weather\",\"description\":\"Get the current weather in a city\",\"input_schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\",\"enum\":[\"Paris\"]}},\"required\":[\"city\"],\"additionalProperties\":false}}],\"tool_choice\":{\"type\":\"auto\"},\"stream\":true,\"max_tokens\":1536,\"thinking\":{\"type\":\"adaptive\"}}"
+        "body": "{\"model\":\"MiniMax-M3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Look up the current weather in Paris using get_weather before answering. After receiving the result, report the weather in one short sentence.\",\"cache_control\":{\"type\":\"ephemeral\"}}]}],\"tools\":[{\"name\":\"get_weather\",\"description\":\"Get the current weather in a city\",\"input_schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\",\"enum\":[\"Paris\"]}},\"required\":[\"city\"],\"additionalProperties\":false},\"cache_control\":{\"type\":\"ephemeral\"}}],\"tool_choice\":{\"type\":\"auto\"},\"stream\":true,\"max_tokens\":1536,\"thinking\":{\"type\":\"adaptive\"}}"
      },
      "response": {
        "status": 200,
        "headers": {
          "content-type": "text/event-stream; charset=utf-8"
        },
-        "body": "event: message_start\ndata: {\"type\":\"message_start\",\"message\":{\"id\":\"6a532037868639a6189e7c0b9e1c9aa2\",\"type\":\"message\",\"role\":\"assistant\",\"content\":[],\"model\":\"MiniMax-M3\",\"stop_reason\":null,\"stop_sequence\":null,\"usage\":{\"input_tokens\":0,\"output_tokens\":0,\"service_tier\":\"standard\"},\"service_tier\":\"standard\"}}\n\nevent: ping\ndata: {\"type\":\"ping\"}\n\nevent: content_block_start\ndata: {\"type\":\"content_block_start\",\"index\":0,\"content_block\":{\"type\":\"thinking\",\"thinking\":\"\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\"The user wants me\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" to look up the\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" current weather in Paris\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" using the get_\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\"weather tool, then\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" report it\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" in one short sentence\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\". Let\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" me call the tool\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\".\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"signature_delta\",\"signature\":\"f05cb5f4873950f23d194289c41d79b96ebd37c9411a45b306ed44f135a910d4\"}}\n\nevent: content_block_stop\ndata: {\"type\":\"content_block_stop\",\"index\":0}\n\nevent: content_block_start\ndata: {\"type\":\"content_block_start\",\"index\":1,\"content_block\":{\"type\":\"tool_use\",\"id\":\"call_01a07cc9f2d47d83a6424ff3\",\"name\":\"get_weather\",\"input\":{}}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":1,\"delta\":{\"type\":\"input_json_delta\",\"partial_json\":\"{\\\"city\\\":\\\"Paris\\\"}\"}}\n\nevent: content_block_stop\ndata: {\"type\":\"content_block_stop\",\"index\":1}\n\nevent: message_delta\ndata: {\"type\":\"message_delta\",\"delta\":{\"stop_reason\":\"tool_use\"},\"usage\":{\"input_tokens\":239,\"output_tokens\":63,\"cache_read_input_tokens\":203,\"service_tier\":\"standard\",\"output_tokens_details\":{\"thinking_tokens\":33}}}\n\nevent: message_stop\ndata: {\"type\":\"message_stop\"}\n\n"
+        "body": "event: message_start\ndata: {\"type\":\"message_start\",\"message\":{\"id\":\"6e8c4645c02dd05c2f08c22e5eba9a89\",\"type\":\"message\",\"role\":\"assistant\",\"content\":[],\"model\":\"MiniMax-M3\",\"stop_reason\":null,\"stop_sequence\":null,\"usage\":{\"input_tokens\":0,\"output_tokens\":0,\"service_tier\":\"standard\"},\"service_tier\":\"standard\"}}\n\nevent: ping\ndata: {\"type\":\"ping\"}\n\nevent: content_block_start\ndata: {\"type\":\"content_block_start\",\"index\":0,\"content_block\":{\"type\":\"thinking\",\"thinking\":\"\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\"The user wants me\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" to look up the\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" current weather in Paris\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" using the get_\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\"weather tool, then\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" report the weather in\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" one short sentence after\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" receiving the result.\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" Let\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" me call the tool\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\".\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"signature_delta\",\"signature\":\"61f13458806572210eb8e1809b12f191297eea1a7f0104aa12f86595ef5eb1dc\"}}\n\nevent: content_block_stop\ndata: {\"type\":\"content_block_stop\",\"index\":0}\n\nevent: content_block_start\ndata: {\"type\":\"content_block_start\",\"index\":1,\"content_block\":{\"type\":\"tool_use\",\"id\":\"call_01a0eba239b7718ba67e5aa3\",\"name\":\"get_weather\",\"input\":{}}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":1,\"delta\":{\"type\":\"input_json_delta\",\"partial_json\":\"{\\\"city\\\":\\\"Paris\\\"}\"}}\n\nevent: content_block_stop\ndata: {\"type\":\"content_block_stop\",\"index\":1}\n\nevent: message_delta\ndata: {\"type\":\"message_delta\",\"delta\":{\"stop_reason\":\"tool_use\"},\"usage\":{\"input_tokens\":239,\"output_tokens\":68,\"cache_read_input_tokens\":203,\"service_tier\":\"standard\",\"output_tokens_details\":{\"thinking_tokens\":38}}}\n\nevent: message_stop\ndata: {\"type\":\"message_stop\"}\n\n"
      }
    },
    {
@@ -42,14 +42,14 @@
        "headers": {
          "content-type": "application/json"
        },
-        "body": "{\"model\":\"MiniMax-M3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Look up the current weather in Paris using get_weather before answering. After receiving the result, report the weather in one short sentence.\"}]},{\"role\":\"assistant\",\"content\":[{\"type\":\"thinking\",\"thinking\":\"The user wants me to look up the current weather in Paris using the get_weather tool, then report it in one short sentence. Let me call the tool.\",\"signature\":\"f05cb5f4873950f23d194289c41d79b96ebd37c9411a45b306ed44f135a910d4\"},{\"type\":\"tool_use\",\"id\":\"call_01a07cc9f2d47d83a6424ff3\",\"name\":\"get_weather\",\"input\":{\"city\":\"Paris\"}}]},{\"role\":\"user\",\"content\":[{\"type\":\"tool_result\",\"tool_use_id\":\"call_01a07cc9f2d47d83a6424ff3\",\"content\":\"{\\\"condition\\\":\\\"sunny\\\",\\\"temperature\\\":\\\"18C\\\"}\"}]}],\"tools\":[{\"name\":\"get_weather\",\"description\":\"Get the current weather in a city\",\"input_schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\",\"enum\":[\"Paris\"]}},\"required\":[\"city\"],\"additionalProperties\":false}}],\"tool_choice\":{\"type\":\"none\"},\"stream\":true,\"max_tokens\":1536,\"thinking\":{\"type\":\"adaptive\"}}"
+        "body": "{\"model\":\"MiniMax-M3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Look up the current weather in Paris using get_weather before answering. After receiving the result, report the weather in one short sentence.\"}]},{\"role\":\"assistant\",\"content\":[{\"type\":\"thinking\",\"thinking\":\"The user wants me to look up the current weather in Paris using the get_weather tool, then report the weather in one short sentence after receiving the result. Let me call the tool.\",\"signature\":\"61f13458806572210eb8e1809b12f191297eea1a7f0104aa12f86595ef5eb1dc\"},{\"type\":\"tool_use\",\"id\":\"call_01a0eba239b7718ba67e5aa3\",\"name\":\"get_weather\",\"input\":{\"city\":\"Paris\"}}]},{\"role\":\"user\",\"content\":[{\"type\":\"tool_result\",\"tool_use_id\":\"call_01a0eba239b7718ba67e5aa3\",\"content\":\"{\\\"condition\\\":\\\"sunny\\\",\\\"temperature\\\":\\\"18C\\\"}\",\"cache_control\":{\"type\":\"ephemeral\"}}]}],\"tools\":[{\"name\":\"get_weather\",\"description\":\"Get the current weather in a city\",\"input_schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\",\"enum\":[\"Paris\"]}},\"required\":[\"city\"],\"additionalProperties\":false},\"cache_control\":{\"type\":\"ephemeral\"}}],\"tool_choice\":{\"type\":\"none\"},\"stream\":true,\"max_tokens\":1536,\"thinking\":{\"type\":\"adaptive\"}}"
      },
      "response": {
        "status": 200,
        "headers": {
          "content-type": "text/event-stream; charset=utf-8"
        },
-        "body": "event: message_start\ndata: {\"type\":\"message_start\",\"message\":{\"id\":\"e9e7ea89f63eca1cd17a037aef28eed1\",\"type\":\"message\",\"role\":\"assistant\",\"content\":[],\"model\":\"MiniMax-M3\",\"stop_reason\":null,\"stop_sequence\":null,\"usage\":{\"input_tokens\":0,\"output_tokens\":0,\"service_tier\":\"standard\"},\"service_tier\":\"standard\"}}\n\nevent: ping\ndata: {\"type\":\"ping\"}\n\nevent: content_block_start\ndata: {\"type\":\"content_block_start\",\"index\":0,\"content_block\":{\"type\":\"text\",\"text\":\"\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"text_delta\",\"text\":\"The weather\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"text_delta\",\"text\":\" in Paris is sunny\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"text_delta\",\"text\":\" with\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"text_delta\",\"text\":\" a\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"text_delta\",\"text\":\" temperature of 18\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"text_delta\",\"text\":\"°C.\"}}\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\"},\"usage\":{\"input_tokens\":164,\"output_tokens\":16,\"cache_read_input_tokens\":128,\"service_tier\":\"standard\"}}\n\nevent: message_stop\ndata: {\"type\":\"message_stop\"}\n\n"
+        "body": "event: message_start\ndata: {\"type\":\"message_start\",\"message\":{\"id\":\"0f6a842fc54eecab0d6df9ffebd8dd3b\",\"type\":\"message\",\"role\":\"assistant\",\"content\":[],\"model\":\"MiniMax-M3\",\"stop_reason\":null,\"stop_sequence\":null,\"usage\":{\"input_tokens\":0,\"output_tokens\":0,\"service_tier\":\"standard\"},\"service_tier\":\"standard\"}}\n\nevent: ping\ndata: {\"type\":\"ping\"}\n\nevent: content_block_start\ndata: {\"type\":\"content_block_start\",\"index\":0,\"content_block\":{\"type\":\"thinking\",\"thinking\":\"\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\"The weather\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" in Paris is sunny\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" with a\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" temperature of 18\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\"°C. I'll\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" report this in one\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\"short sentence.\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"signature_delta\",\"signature\":\"fefe2c0e5f3f0a0edc24b21d37c8b7fb12ed0755bd1898f71acc2325f1b35958\"}}\n\nevent: content_block_stop\ndata: {\"type\":\"content_block_stop\",\"index\":0}\n\nevent: content_block_start\ndata: {\"type\":\"content_block_start\",\"index\":1,\"content_block\":{\"type\":\"text\",\"text\":\"\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":1,\"delta\":{\"type\":\"text_delta\",\"text\":\"It's\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":1,\"delta\":{\"type\":\"text_delta\",\"text\":\" currently\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":1,\"delta\":{\"type\":\"text_delta\",\"text\":\" sunny in\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":1,\"delta\":{\"type\":\"text_delta\",\"text\":\" Paris with a temperature\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":1,\"delta\":{\"type\":\"text_delta\",\"text\":\" of 18°C\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":1,\"delta\":{\"type\":\"text_delta\",\"text\":\".\"}}\n\nevent: content_block_stop\ndata: {\"type\":\"content_block_stop\",\"index\":1}\n\nevent: message_delta\ndata: {\"type\":\"message_delta\",\"delta\":{\"stop_reason\":\"end_turn\"},\"usage\":{\"input_tokens\":169,\"output_tokens\":38,\"cache_read_input_tokens\":128,\"service_tier\":\"standard\",\"output_tokens_details\":{\"thinking_tokens\":22}}}\n\nevent: message_stop\ndata: {\"type\":\"message_stop\"}\n\n"
      }
    }
  ]
@@ -11,7 +11,7 @@
      "usage"
    ],
    "name": "minimax-messages/m3-generates-a-named-tool-call-with-default-thinking-off",
-    "recordedAt": "2026-09-07T16:53:24.366Z"
+    "recordedAt": "2026-09-29T05:27:51.660Z"
  },
  "interactions": [
    {
@@ -22,14 +22,14 @@
        "headers": {
          "content-type": "application/json"
        },
-        "body": "{\"model\":\"MiniMax-M3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Use get_weather to look up the current weather in Paris.\"}]}],\"tools\":[{\"name\":\"get_weather\",\"description\":\"Get the current weather in a city\",\"input_schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\",\"enum\":[\"Paris\"]}},\"required\":[\"city\"],\"additionalProperties\":false}}],\"tool_choice\":{\"type\":\"tool\",\"name\":\"get_weather\"},\"stream\":true,\"max_tokens\":512}"
+        "body": "{\"model\":\"MiniMax-M3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Use get_weather to look up the current weather in Paris.\",\"cache_control\":{\"type\":\"ephemeral\"}}]}],\"tools\":[{\"name\":\"get_weather\",\"description\":\"Get the current weather in a city\",\"input_schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\",\"enum\":[\"Paris\"]}},\"required\":[\"city\"],\"additionalProperties\":false},\"cache_control\":{\"type\":\"ephemeral\"}}],\"tool_choice\":{\"type\":\"tool\",\"name\":\"get_weather\"},\"stream\":true,\"max_tokens\":512}"
      },
      "response": {
        "status": 200,
        "headers": {
          "content-type": "text/event-stream; charset=utf-8"
        },
-        "body": "event: message_start\ndata: {\"type\":\"message_start\",\"message\":{\"id\":\"a60a8adb2eff7545f809b9df2689f1b8\",\"type\":\"message\",\"role\":\"assistant\",\"content\":[],\"model\":\"MiniMax-M3\",\"stop_reason\":null,\"stop_sequence\":null,\"usage\":{\"input_tokens\":0,\"output_tokens\":0,\"service_tier\":\"standard\"},\"service_tier\":\"standard\"}}\n\nevent: ping\ndata: {\"type\":\"ping\"}\n\nevent: content_block_start\ndata: {\"type\":\"content_block_start\",\"index\":0,\"content_block\":{\"type\":\"text\",\"text\":\"\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"text_delta\",\"text\":\"I'll\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"text_delta\",\"text\":\" look\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"text_delta\",\"text\":\" up the current weather\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"text_delta\",\"text\":\" in Paris for you\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"text_delta\",\"text\":\".\"}}\n\nevent: content_block_stop\ndata: {\"type\":\"content_block_stop\",\"index\":0}\n\nevent: content_block_start\ndata: {\"type\":\"content_block_start\",\"index\":1,\"content_block\":{\"type\":\"tool_use\",\"id\":\"call_b0246853f3c4432ea455cc99\",\"name\":\"get_weather\",\"input\":{}}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":1,\"delta\":{\"type\":\"input_json_delta\",\"partial_json\":\"{\\\"city\\\":\\\"Paris\\\"}\"}}\n\nevent: content_block_stop\ndata: {\"type\":\"content_block_stop\",\"index\":1}\n\nevent: message_delta\ndata: {\"type\":\"message_delta\",\"delta\":{\"stop_reason\":\"tool_use\"},\"usage\":{\"input_tokens\":401,\"output_tokens\":39,\"service_tier\":\"standard\"}}\n\nevent: message_stop\ndata: {\"type\":\"message_stop\"}\n\n"
+        "body": "event: message_start\ndata: {\"type\":\"message_start\",\"message\":{\"id\":\"5f4a7ce22c5a82497fedc65028aa4825\",\"type\":\"message\",\"role\":\"assistant\",\"content\":[],\"model\":\"MiniMax-M3\",\"stop_reason\":null,\"stop_sequence\":null,\"usage\":{\"input_tokens\":0,\"output_tokens\":0,\"service_tier\":\"standard\"},\"service_tier\":\"standard\"}}\n\nevent: ping\ndata: {\"type\":\"ping\"}\n\nevent: content_block_start\ndata: {\"type\":\"content_block_start\",\"index\":0,\"content_block\":{\"type\":\"text\",\"text\":\"\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"text_delta\",\"text\":\"I'll\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"text_delta\",\"text\":\" look\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"text_delta\",\"text\":\" up the current weather\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"text_delta\",\"text\":\" in Paris for you\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"text_delta\",\"text\":\".\"}}\n\nevent: content_block_stop\ndata: {\"type\":\"content_block_stop\",\"index\":0}\n\nevent: content_block_start\ndata: {\"type\":\"content_block_start\",\"index\":1,\"content_block\":{\"type\":\"tool_use\",\"id\":\"call_01a0eba235fb7281a0f2ea2c\",\"name\":\"get_weather\",\"input\":{}}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":1,\"delta\":{\"type\":\"input_json_delta\",\"partial_json\":\"{\\\"city\\\":\\\"Paris\\\"}\"}}\n\nevent: content_block_stop\ndata: {\"type\":\"content_block_stop\",\"index\":1}\n\nevent: message_delta\ndata: {\"type\":\"message_delta\",\"delta\":{\"stop_reason\":\"tool_use\"},\"usage\":{\"input_tokens\":287,\"output_tokens\":39,\"cache_read_input_tokens\":128,\"service_tier\":\"standard\"}}\n\nevent: message_stop\ndata: {\"type\":\"message_stop\"}\n\n"
      }
    }
  ]
@@ -11,7 +11,7 @@
      "thinking-off"
    ],
    "name": "minimax-messages/m3-streams-text-with-thinking-disabled",
-    "recordedAt": "2026-09-07T16:53:16.028Z"
+    "recordedAt": "2026-09-29T05:27:36.888Z"
  },
  "interactions": [
    {
@@ -22,14 +22,14 @@
        "headers": {
          "content-type": "application/json"
        },
-        "body": "{\"model\":\"MiniMax-M3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is 173 multiplied by 219? Reply with only the final integer.\"}]}],\"stream\":true,\"max_tokens\":1536,\"thinking\":{\"type\":\"disabled\"}}"
+        "body": "{\"model\":\"MiniMax-M3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is 173 multiplied by 219? Reply with only the final integer.\",\"cache_control\":{\"type\":\"ephemeral\"}}]}],\"stream\":true,\"max_tokens\":1536,\"thinking\":{\"type\":\"disabled\"}}"
      },
      "response": {
        "status": 200,
        "headers": {
          "content-type": "text/event-stream; charset=utf-8"
        },
-        "body": "event: message_start\ndata: {\"type\":\"message_start\",\"message\":{\"id\":\"01664c047875a0f573c966467c8cccc1\",\"type\":\"message\",\"role\":\"assistant\",\"content\":[],\"model\":\"MiniMax-M3\",\"stop_reason\":null,\"stop_sequence\":null,\"usage\":{\"input_tokens\":0,\"output_tokens\":0,\"service_tier\":\"standard\"},\"service_tier\":\"standard\"}}\n\nevent: ping\ndata: {\"type\":\"ping\"}\n\nevent: content_block_start\ndata: {\"type\":\"content_block_start\",\"index\":0,\"content_block\":{\"type\":\"text\",\"text\":\"\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"text_delta\",\"text\":\"378\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"text_delta\",\"text\":\"87\"}}\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\"},\"usage\":{\"input_tokens\":51,\"output_tokens\":3,\"cache_read_input_tokens\":128,\"service_tier\":\"standard\"}}\n\nevent: message_stop\ndata: {\"type\":\"message_stop\"}\n\n"
+        "body": "event: message_start\ndata: {\"type\":\"message_start\",\"message\":{\"id\":\"444066751666f2071c999bfd0b4c16b0\",\"type\":\"message\",\"role\":\"assistant\",\"content\":[],\"model\":\"MiniMax-M3\",\"stop_reason\":null,\"stop_sequence\":null,\"usage\":{\"input_tokens\":0,\"output_tokens\":0,\"service_tier\":\"standard\"},\"service_tier\":\"standard\"}}\n\nevent: ping\ndata: {\"type\":\"ping\"}\n\nevent: content_block_start\ndata: {\"type\":\"content_block_start\",\"index\":0,\"content_block\":{\"type\":\"text\",\"text\":\"\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"text_delta\",\"text\":\"378\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"text_delta\",\"text\":\"87\"}}\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\"},\"usage\":{\"input_tokens\":179,\"output_tokens\":3,\"service_tier\":\"standard\"}}\n\nevent: message_stop\ndata: {\"type\":\"message_stop\"}\n\n"
      }
    }
  ]
@@ -2,9 +2,16 @@
  "version": 1,
  "metadata": {
    "model": "kimi-k3",
-    "tags": ["prefix:moonshot-messages", "provider:moonshot", "protocol:messages", "tool", "tool-choice", "usage"],
+    "tags": [
+      "prefix:moonshot-messages",
+      "provider:moonshot",
+      "protocol:messages",
+      "tool",
+      "tool-choice",
+      "usage"
+    ],
    "name": "moonshot-messages/k3-respects-tool-choice-required",
-    "recordedAt": "2026-09-07T20:37:07.770Z"
+    "recordedAt": "2026-09-29T05:28:21.798Z"
  },
  "interactions": [
    {
@@ -15,14 +22,14 @@
        "headers": {
          "content-type": "application/json"
        },
-        "body": "{\"model\":\"kimi-k3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Use get_weather to look up the current weather in Paris.\"}]}],\"tools\":[{\"name\":\"get_weather\",\"description\":\"Get the current weather in a city\",\"input_schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\",\"enum\":[\"Paris\"]}},\"required\":[\"city\"],\"additionalProperties\":false}}],\"tool_choice\":{\"type\":\"any\"},\"stream\":true,\"max_tokens\":4096,\"output_config\":{\"effort\":\"low\"}}"
+        "body": "{\"model\":\"kimi-k3\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Use get_weather to look up the current weather in Paris.\",\"cache_control\":{\"type\":\"ephemeral\"}}]}],\"tools\":[{\"name\":\"get_weather\",\"description\":\"Get the current weather in a city\",\"input_schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\",\"enum\":[\"Paris\"]}},\"required\":[\"city\"],\"additionalProperties\":false},\"cache_control\":{\"type\":\"ephemeral\"}}],\"tool_choice\":{\"type\":\"any\"},\"stream\":true,\"max_tokens\":4096,\"output_config\":{\"effort\":\"low\"}}"
      },
      "response": {
        "status": 200,
        "headers": {
          "content-type": "text/event-stream"
        },
-        "body": "event: message_start\ndata: {\"type\":\"message_start\",\"message\":{\"id\":\"chatcmpl-2f2e02780e8a031b1b1307171\",\"type\":\"message\",\"role\":\"assistant\",\"content\":[],\"model\":\"kimi-k3\",\"stop_reason\":null,\"stop_sequence\":null,\"usage\":{\"input_tokens\":223,\"cache_creation_input_tokens\":0,\"cache_read_input_tokens\":0,\"output_tokens\":0,\"service_tier\":\"standard\",\"inference_geo\":\"not_available\",\"prompt_tokens\":223,\"cached_tokens\":0}}}\n\nevent: content_block_start\ndata: {\"type\":\"content_block_start\",\"index\":0,\"content_block\":{\"type\":\"thinking\",\"thinking\":\"\",\"signature\":\"\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\"Need\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" use\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" get\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\"_we\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\"ather\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" for\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" Paris\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\".\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" Call\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" function\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\".\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" Then\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" final\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" summarize\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" result\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\".\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" Use\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" tool\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\".\"}}\n\nevent: content_block_stop\ndata: {\"type\":\"content_block_stop\",\"index\":0}\n\nevent: content_block_start\ndata: {\"type\":\"content_block_start\",\"index\":1,\"content_block\":{\"type\":\"tool_use\",\"id\":\"get_weather_0\",\"name\":\"get_weather\",\"input\":{}}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":1,\"delta\":{\"type\":\"input_json_delta\",\"partial_json\":\"{\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":1,\"delta\":{\"type\":\"input_json_delta\",\"partial_json\":\"\\\"city\\\": \\\"\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":1,\"delta\":{\"type\":\"input_json_delta\",\"partial_json\":\"Paris\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":1,\"delta\":{\"type\":\"input_json_delta\",\"partial_json\":\"\\\"\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":1,\"delta\":{\"type\":\"input_json_delta\",\"partial_json\":\"}\"}}\n\nevent: content_block_stop\ndata: {\"type\":\"content_block_stop\",\"index\":1}\n\nevent: message_delta\ndata: {\"type\":\"message_delta\",\"delta\":{\"stop_reason\":\"tool_use\",\"stop_sequence\":null},\"usage\":{\"input_tokens\":0,\"cache_creation_input_tokens\":0,\"cache_read_input_tokens\":223,\"output_tokens\":69,\"output_tokens_details\":{\"thinking_tokens\":19},\"prompt_tokens\":223,\"completion_tokens\":69,\"total_tokens\":292,\"cached_tokens\":223}}\n\nevent: message_stop\ndata: {\"type\":\"message_stop\"}\n\n"
+        "body": "event: message_start\ndata: {\"type\":\"message_start\",\"message\":{\"id\":\"chatcmpl-c877bb3f-cb6b-9d0f-b91e-37849d7bff39\",\"type\":\"message\",\"role\":\"assistant\",\"content\":[],\"model\":\"kimi-k3\",\"stop_reason\":null,\"stop_sequence\":null,\"usage\":{\"input_tokens\":223,\"cache_creation_input_tokens\":0,\"cache_read_input_tokens\":0,\"output_tokens\":0,\"cache_creation\":{\"ephemeral_5m_input_tokens\":0,\"ephemeral_1h_input_tokens\":0},\"service_tier\":\"standard\",\"inference_geo\":\"not_available\",\"prompt_tokens\":223,\"cached_tokens\":0}}}\n\nevent: content_block_start\ndata: {\"type\":\"content_block_start\",\"index\":0,\"content_block\":{\"type\":\"thinking\",\"thinking\":\"\",\"signature\":\"\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\"The\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" user explicitly\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" asks to use\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" get_weather for\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" Paris. Need call\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" the\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" tool. Do\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"thinking_delta\",\"thinking\":\" that.\"}}\n\nevent: content_block_stop\ndata: {\"type\":\"content_block_stop\",\"index\":0}\n\nevent: content_block_start\ndata: {\"type\":\"content_block_start\",\"index\":1,\"content_block\":{\"type\":\"tool_use\",\"id\":\"get_weather_0_7e180ea4\",\"name\":\"get_weather\",\"input\":{}}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":1,\"delta\":{\"type\":\"input_json_delta\",\"partial_json\":\"{\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":1,\"delta\":{\"type\":\"input_json_delta\",\"partial_json\":\"\\\"city\\\":\\\"Paris\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":1,\"delta\":{\"type\":\"input_json_delta\",\"partial_json\":\"\\\"\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":1,\"delta\":{\"type\":\"input_json_delta\",\"partial_json\":\"}\"}}\n\nevent: content_block_stop\ndata: {\"type\":\"content_block_stop\",\"index\":1}\n\nevent: message_delta\ndata: {\"type\":\"message_delta\",\"delta\":{\"stop_reason\":\"tool_use\",\"stop_sequence\":null},\"usage\":{\"input_tokens\":223,\"cache_creation_input_tokens\":0,\"cache_read_input_tokens\":0,\"output_tokens\":73,\"cache_creation\":{\"ephemeral_5m_input_tokens\":0,\"ephemeral_1h_input_tokens\":0},\"output_tokens_details\":{\"thinking_tokens\":20},\"prompt_tokens\":223,\"completion_tokens\":73,\"total_tokens\":296,\"cached_tokens\":0}}\n\nevent: message_stop\ndata: {\"type\":\"message_stop\"}\n\n"
      }
    }
  ]
@@ -0,0 +1,54 @@
+{
+  "version": 1,
+  "metadata": {
+    "model": "gemini-3.8-flash",
+    "tags": [
+      "prefix:openai-compatible-chat",
+      "provider:google",
+      "protocol:openai-chat",
+      "tool",
+      "tool-loop",
+      "continuation"
+    ],
+    "name": "gemini-parallel-tool-signatures",
+    "recordedAt": "2026-09-28T03:12:05.083Z"
+  },
+  "interactions": [
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://generativelanguage.googleapis.com/v1beta/openai/chat/completions",
+        "headers": {
+          "content-type": "application/json"
+        },
+        "body": "{\"model\":\"gemini-3.8-flash\",\"messages\":[{\"role\":\"system\",\"content\":\"Call get_weather for every requested city in parallel, then answer in one short sentence.\"},{\"role\":\"user\",\"content\":\"What is the weather in Paris and in Tokyo?\"}],\"tools\":[{\"type\":\"function\",\"function\":{\"name\":\"get_weather\",\"description\":\"Get current weather for a city.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false},\"strict\":false}}],\"stream\":true,\"stream_options\":{\"include_usage\":true}}"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "text/event-stream"
+        },
+        "body": "data: {\"choices\":[{\"delta\":{\"role\":\"assistant\",\"tool_calls\":[{\"extra_content\":{\"google\":{\"thought_signature\":\"ErYCCrMCAWkUfRNGh+/Zbc8YUSzk1yfWAfROcjA4HyF1x69jz6167w8zd4n6kZQQ5FDeBZ5HZMEbEkQ4ENOpzsQL8roCR6wONkhXpiduWrTD6XwbP8KGNkf6D1tX/JlBh7G5Cl+0rdjiSOl/mdY1lcjbkfyCRFs5T8odNWMG7WD3rCrXJDFQ/5QfOl+tqVTceKGz2yyXBhOhvsQDU33ulR9tHQJo/Fmx3HNyDdwvmyKUXm+kgqHsYZnkdv6y6xZwy9zBXGUO4QwxelMw3Rrc24Mp2rNbEDZS3YEeP72Jn/hIP5a8XWOx6+zop/4/CjYxxSfN/tJRY5d48NAKRNFzUN1Az8SvAs/N5X2I3/5ZMaDnQWW/BVdS9fm2KFYJ2baqtBiRRnJxMq4ELArkKjGZzHpd97XG8YjV6g==\"}},\"function\":{\"arguments\":\"{\\\"city\\\":\\\"Paris\\\"}\",\"name\":\"get_weather\"},\"id\":\"call_723181\",\"type\":\"function\"}]},\"index\":0}],\"created\":1790565123,\"id\":\"A9u5aoufBp3rz7IPke_3oAo\",\"model\":\"gemini-3.8-flash\",\"object\":\"chat.completion.chunk\",\"usage\":{\"completion_tokens\":16,\"prompt_tokens\":74,\"total_tokens\":132}}\n\ndata: {\"choices\":[{\"delta\":{\"role\":\"assistant\",\"tool_calls\":[{\"function\":{\"arguments\":\"{\\\"city\\\":\\\"Tokyo\\\"}\",\"name\":\"get_weather\"},\"id\":\"call_723184\",\"type\":\"function\"}]},\"index\":0}],\"created\":1790565123,\"id\":\"A9u5aoufBp3rz7IPke_3oAo\",\"model\":\"gemini-3.8-flash\",\"object\":\"chat.completion.chunk\",\"usage\":{\"completion_tokens\":32,\"prompt_tokens\":74,\"total_tokens\":148}}\n\ndata: {\"choices\":[{\"delta\":{\"role\":\"assistant\"},\"finish_reason\":\"stop\",\"index\":0}],\"created\":1790565124,\"id\":\"A9u5aoufBp3rz7IPke_3oAo\",\"model\":\"gemini-3.8-flash\",\"object\":\"chat.completion.chunk\",\"usage\":{\"completion_tokens\":32,\"prompt_tokens\":74,\"total_tokens\":148}}\n\ndata: [DONE]\n\n"
+      }
+    },
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://generativelanguage.googleapis.com/v1beta/openai/chat/completions",
+        "headers": {
+          "content-type": "application/json"
+        },
+        "body": "{\"model\":\"gemini-3.8-flash\",\"messages\":[{\"role\":\"system\",\"content\":\"Call get_weather for every requested city in parallel, then answer in one short sentence.\"},{\"role\":\"user\",\"content\":\"What is the weather in Paris and in Tokyo?\"},{\"role\":\"assistant\",\"content\":null,\"tool_calls\":[{\"id\":\"call_723181\",\"type\":\"function\",\"function\":{\"name\":\"get_weather\",\"arguments\":\"{\\\"city\\\":\\\"Paris\\\"}\"},\"extra_content\":{\"google\":{\"thought_signature\":\"ErYCCrMCAWkUfRNGh+/Zbc8YUSzk1yfWAfROcjA4HyF1x69jz6167w8zd4n6kZQQ5FDeBZ5HZMEbEkQ4ENOpzsQL8roCR6wONkhXpiduWrTD6XwbP8KGNkf6D1tX/JlBh7G5Cl+0rdjiSOl/mdY1lcjbkfyCRFs5T8odNWMG7WD3rCrXJDFQ/5QfOl+tqVTceKGz2yyXBhOhvsQDU33ulR9tHQJo/Fmx3HNyDdwvmyKUXm+kgqHsYZnkdv6y6xZwy9zBXGUO4QwxelMw3Rrc24Mp2rNbEDZS3YEeP72Jn/hIP5a8XWOx6+zop/4/CjYxxSfN/tJRY5d48NAKRNFzUN1Az8SvAs/N5X2I3/5ZMaDnQWW/BVdS9fm2KFYJ2baqtBiRRnJxMq4ELArkKjGZzHpd97XG8YjV6g==\"}}},{\"id\":\"call_723184\",\"type\":\"function\",\"function\":{\"name\":\"get_weather\",\"arguments\":\"{\\\"city\\\":\\\"Tokyo\\\"}\"}}]},{\"role\":\"tool\",\"tool_call_id\":\"call_723181\",\"content\":\"{\\\"temperature\\\":22,\\\"condition\\\":\\\"sunny\\\"}\"},{\"role\":\"tool\",\"tool_call_id\":\"call_723184\",\"content\":\"{\\\"temperature\\\":0,\\\"condition\\\":\\\"unknown\\\"}\"}],\"tools\":[{\"type\":\"function\",\"function\":{\"name\":\"get_weather\",\"description\":\"Get current weather for a city.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false},\"strict\":false}}],\"stream\":true,\"stream_options\":{\"include_usage\":true}}"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "text/event-stream"
+        },
+        "body": "data: {\"choices\":[{\"delta\":{\"content\":\"It is currently sunny and 22°C in Paris,\",\"role\":\"assistant\"},\"index\":0}],\"created\":1790565125,\"id\":\"BNu5auWeB-2fz7IPxY6l4QY\",\"model\":\"gemini-3.8-flash\",\"object\":\"chat.completion.chunk\",\"usage\":{\"completion_tokens\":13,\"prompt_tokens\":150,\"total_tokens\":226}}\n\ndata: {\"choices\":[{\"delta\":{\"content\":\" while Tokyo is 0°C.\",\"role\":\"assistant\"},\"index\":0}],\"created\":1790565125,\"id\":\"BNu5auWeB-2fz7IPxY6l4QY\",\"model\":\"gemini-3.8-flash\",\"object\":\"chat.completion.chunk\",\"usage\":{\"completion_tokens\":21,\"prompt_tokens\":150,\"total_tokens\":234}}\n\ndata: {\"choices\":[{\"delta\":{\"extra_content\":{\"google\":{\"thought_signature\":\"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\"}},\"role\":\"assistant\"},\"finish_reason\":\"stop\",\"index\":0}],\"created\":1790565125,\"id\":\"BNu5auWeB-2fz7IPxY6l4QY\",\"model\":\"gemini-3.8-flash\",\"object\":\"chat.completion.chunk\",\"usage\":{\"completion_tokens\":21,\"prompt_tokens\":192,\"total_tokens\":276}}\n\ndata: [DONE]\n\n"
+      }
+    }
+  ]
+}
@@ -842,6 +842,30 @@ describe("Image", () => {
    ),
  )

+  const falDetail = { detail: [{ loc: ["body", "prompt"], msg: "Invalid input", type: "value_error" }] }
+  it.effect(
+    "fails a fal await whose COMPLETED status carries an error with the response_url body and HTTP context",
+    () =>
+      Effect.gen(function* () {
+        const generation = yield* Image.resume(Fal.configure({ apiKey: "test" }).image("fal-ai/flux/schnell"), falToken)
+        expect(generation.status).toBe("failed")
+        const error = yield* generation.await().pipe(Effect.flip)
+        expect(error.reason._tag).toBe("InvalidRequest")
+        expect(error.reason.body).toBe(JSON.stringify(falDetail))
+        expect(error.reason.http).toMatchObject({ url: falToken.responseURL, status: 422 })
+      }).pipe(
+        Effect.provide(
+          layer((input) =>
+            Effect.succeed(
+              input.request.url === falToken.statusURL
+                ? json(input, { status: "COMPLETED", error: "Invalid input", error_type: "ValidationError" })
+                : json(input, falDetail, { status: 422 }),
+            ),
+          ),
+        ),
+      ),
+  )
+
  const moderated = { id: "req_1", status: "Content Moderated" }
  const prediction = {
    id: "p_1",
@@ -22,7 +22,8 @@ const chatBody = sseEvents(
 /**
 * Executor layer that answers chat completions with SSE text, image generations with one base64 PNG, Runway video
 * tasks with a queued submission that succeeds on the second poll, speech with raw audio or SSE audio deltas, OpenAI
- * transcription with JSON or SSE text deltas, and AssemblyAI transcripts that complete on the first poll.
+ * transcription with JSON or SSE text deltas, AssemblyAI transcripts that complete on the first poll, and `slow.test`
+ * chat completions that send one text delta and never finish.
 */
 const executor = (seen: Array<string>) =>
  RequestExecutor.layer.pipe(
@@ -55,6 +56,18 @@ const executor = (seen: Array<string>) =>
              output: "https://replicate.test/a.webp",
              urls: { get: "https://replicate.test/p_1", cancel: "https://replicate.test/p_1/cancel" },
            })
+          if (web.url.startsWith("https://slow.test"))
+            return input.respond(
+              new ReadableStream({
+                start: (controller) =>
+                  controller.enqueue(
+                    new TextEncoder().encode(
+                      `data: ${JSON.stringify({ choices: [{ delta: { content: "Hello" } }] })}\n\n`,
+                    ),
+                  ),
+              }),
+              { headers: { "content-type": "text/event-stream" } },
+            )
          if (web.url.endsWith("/chat/completions"))
            return input.respond(chatBody, { headers: { "content-type": "text/event-stream" } })
          if (web.url.endsWith("/audio/speech"))
@@ -304,6 +317,77 @@ describe("AI promise client", () => {
    await ai.dispose()
  })

+  test("aborted calls reject and aborted streams throw with the signal's reason", async () => {
+    const ai = AI.make({ layer: executor([]) })
+    const slow = OpenAI.configure({ apiKey: "test", baseURL: "https://slow.test/v1" }).chat("gpt-4o-mini")
+    const aborted = new AbortController()
+    aborted.abort()
+    const reason = new Error("mine")
+
+    const rejected = await ai.run(Effect.never, { signal: aborted.signal }).catch((error: unknown) => error)
+    expect(rejected).toBe(aborted.signal.reason)
+    expect(rejected).toMatchObject({ name: "AbortError" })
+
+    const inFlight = new AbortController()
+    setTimeout(() => inFlight.abort(reason), 10)
+    expect(
+      await ai.llm
+        .generate({ model: slow, prompt: "Hello" }, { signal: inFlight.signal })
+        .catch((error: unknown) => error),
+    ).toBe(reason)
+
+    const preAborted = await Array.fromAsync(
+      ai.speech.stream({ model: openai.speech("gpt-4o-mini-tts"), text: "Hello" }, { signal: aborted.signal }),
+    ).catch((error: unknown) => error)
+    expect(preAborted).toBe(aborted.signal.reason)
+    expect(preAborted).toMatchObject({ name: "AbortError" })
+
+    const midStream = new AbortController()
+    const deltas: Array<string> = []
+    const midStreamFailure = await Array.fromAsync(
+      ai.llm.stream({ model: slow, prompt: "Hello" }, { signal: midStream.signal }),
+      (event) => {
+        if (!LLMEvent.is.textDelta(event)) return
+        deltas.push(event.text)
+        midStream.abort()
+      },
+    ).catch((error: unknown) => error)
+    expect(deltas).toEqual(["Hello"])
+    expect(midStreamFailure).toBe(midStream.signal.reason)
+    expect(midStreamFailure).toMatchObject({ name: "AbortError" })
+
+    const model = Runway.configure({ apiKey: "test", baseURL: "https://runway.test/v1" }).video("gen4.5")
+    const generation = await ai.video.start({ model, prompt: "A kite" })
+    const polling = new AbortController()
+    const events: Array<string> = []
+    const eventsFailure = await Array.fromAsync(
+      generation.events({ poll: { interval: 60_000 }, signal: polling.signal }),
+      (event) => {
+        events.push(event.type)
+        polling.abort(reason)
+      },
+    ).catch((error: unknown) => error)
+    expect(events).toEqual(["generation-progress"])
+    expect(eventsFailure).toBe(reason)
+
+    await ai.dispose()
+  })
+
+  test("breaking out of an abortable stream cleans up without throwing", async () => {
+    const ai = AI.make({ layer: executor([]) })
+    const slow = OpenAI.configure({ apiKey: "test", baseURL: "https://slow.test/v1" }).chat("gpt-4o-mini")
+    const controller = new AbortController()
+    const deltas: Array<string> = []
+    for await (const event of ai.llm.stream({ model: slow, prompt: "Hello" }, { signal: controller.signal })) {
+      if (!LLMEvent.is.textDelta(event)) continue
+      deltas.push(event.text)
+      break
+    }
+    controller.abort()
+    expect(deltas).toEqual(["Hello"])
+    await ai.dispose()
+  })
+
  test("the default client is created lazily and can be disposed", async () => {
    expect(typeof AI.ai.llm.generate).toBe("function")
    expect(typeof AI.ai.image.generate).toBe("function")
@@ -1,6 +1,6 @@
 import { describe, expect, test } from "bun:test"
 import { isContextOverflow } from "../src/index.js"
-import { classifyProviderFailure } from "../src/provider-error.js"
+import { classifyProviderFailure, providerErrorMessage } from "../src/provider-error.js"

 describe("provider error classification", () => {
  test("classifies provider token limit messages as context overflow", () => {
@@ -355,6 +355,32 @@ describe("provider error rawBody classification", () => {
    }
  })

+  test("classifies Google invalid API keys as authentication failures", () => {
+    const rawBody = JSON.stringify({
+      error: {
+        code: 400,
+        message: "API key not valid. Please pass a valid API key.",
+        status: "INVALID_ARGUMENT",
+        details: [
+          {
+            "@type": "type.googleapis.com/google.rpc.ErrorInfo",
+            reason: "API_KEY_INVALID",
+            domain: "googleapis.com",
+          },
+          {
+            "@type": "type.googleapis.com/google.rpc.LocalizedMessage",
+            locale: "en-US",
+            message: "API key not valid. Please pass a valid API key.",
+          },
+        ],
+      },
+    })
+    expect(
+      classifyProviderFailure({ message: "API key not valid. Please pass a valid API key.", status: 400, rawBody })
+        ._tag,
+    ).toBe("Authentication")
+  })
+
  test("classifies overflow signals buried in the raw payload when the summary is vague", () => {
    const reason = classifyProviderFailure({
      message: "Request failed",
@@ -370,3 +396,42 @@ describe("provider error rawBody classification", () => {
    ).toBe("QuotaExceeded")
  })
 })
+
+describe("provider error messages", () => {
+  test("reads messages from common error body layouts", () => {
+    expect(
+      [
+        '{"error":{"message":"Invalid API Key","type":"invalid_request_error"}}',
+        '{"code":"invalid-argument","error":"Incorrect API key provided."}',
+        '{"message":"1 validation error detected"}',
+        '{"Message":"Invalid API Key format: Must start with pre-defined prefix"}',
+        '{"type":"about:blank","title":"Gone","status":410,"detail":"The model has reached its end of life"}',
+        '{"result":null,"success":false,"errors":[{"code":10000,"message":"Authentication error"}]}',
+      ].map(providerErrorMessage),
+    ).toEqual([
+      "Invalid API Key",
+      "Incorrect API key provided.",
+      "1 validation error detected",
+      "Invalid API Key format: Must start with pre-defined prefix",
+      "The model has reached its end of life",
+      "Authentication error",
+    ])
+  })
+
+  test("prefers the nested error message over a top-level message", () => {
+    expect(providerErrorMessage('{"message":"Bad Request","error":{"message":"model not found"}}')).toBe(
+      "model not found",
+    )
+  })
+
+  test("ignores blank, non-string, and non-JSON messages", () => {
+    expect(
+      [
+        '{"error":{"message":"  "}}',
+        '{"message":{"detail":[{"msg":"too high"}]}}',
+        '{"errors":[]}',
+        "invalid parameter",
+      ].map(providerErrorMessage),
+    ).toEqual([undefined, undefined, undefined, undefined])
+  })
+})
@@ -300,7 +300,9 @@ describe("provider package entrypoints", () => {
    })

    expect(String(selected.provider)).toBe("example")
-    expect(selected.route.id).toBe("anthropic-messages")
+    expect(selected.route.id).toBe("anthropic-compatible-messages")
+    expect(selected.route.protocol).toBe("anthropic-messages")
+    expect(selected.route.providerMetadataKey).toBe("example")
    expect(selected.route.endpoint).toMatchObject({
      baseURL: "https://messages.example.test/v1",
    })
@@ -319,6 +321,7 @@ describe("provider package entrypoints", () => {
      thinking: { type: "adaptive" },
    })

+    expect(selected.route.id).toBe("anthropic-messages")
    expect(selected.route.defaults.providerOptions).toEqual({ thinking: { type: "adaptive" } })
  })

@@ -9,6 +9,7 @@ import {
  Message,
  ToolCallPart,
  ToolDefinition,
+  ToolChoice,
  Usage,
  Media,
 } from "../../src/index.js"
@@ -199,6 +200,131 @@ describe("Anthropic Messages route", () => {
    }),
  )

+  it.effect("sends Sonnet 5.5 between-tools thinking without binding or a binding beta", () =>
+    Effect.gen(function* () {
+      const sonnet = AnthropicMessages.route.model({ id: "claude-sonnet-5-5" })
+      const input = LLM.request({
+        model: sonnet,
+        prompt: "Hello",
+        providerOptions: { thinking: { type: "between_tools" }, effort: "medium" },
+      })
+      const compiled = yield* compileRequest(input)
+      const prepared = yield* AnthropicMessages.route.prepareTransport(compiled.body, input)
+
+      expect(compiled.body.thinking).toEqual({ type: "between_tools" })
+      expect(compiled.body.output_config).toEqual({ effort: "medium" })
+      expect(prepared.request.headers["anthropic-beta"]).not.toContain("thinking-binding-controls")
+      expect(
+        (yield* compileRequest(LLMRequest.update(input, { providerOptions: { effort: "high" } }))).body.thinking,
+      ).toEqual({
+        type: "adaptive",
+        block_binding: { prefix_mismatch_behavior: "drop_block" },
+      })
+    }),
+  )
+
+  it.effect("rejects Sonnet 5.5 thinking settings that cannot retain caller intent", () =>
+    Effect.gen(function* () {
+      const sonnet = AnthropicMessages.route.model({ id: "anthropic/claude-sonnet-5-5" })
+      const invalid = [
+        { thinking: { type: "disabled" } },
+        { thinking: { type: "enabled", budgetTokens: 2048 } },
+        { thinking: { type: "between_tools", block_binding: { prefix_mismatch_behavior: "drop_block" } } },
+        { thinking: { type: "between_tools", display: "summarized" } },
+        { thinking: { type: "between_tools", budget_tokens: 2048 } },
+        { thinking: { type: "between_tools" }, effort: "xhigh" },
+        { thinking: { type: "between_tools" }, output_config: { effort: "max" } },
+      ]
+      const errors = yield* Effect.forEach(invalid, (providerOptions) =>
+        compileRequest(LLM.request({ model: sonnet, prompt: "Hello", providerOptions })).pipe(Effect.flip),
+      )
+      expect(errors.map((error) => error.reason._tag)).toEqual(invalid.map(() => "InvalidRequest"))
+      expect(errors[0]?.message).toContain("between_tools")
+      expect(errors[1]?.message).toContain("adaptive")
+      expect(errors[2]?.message).toContain("block_binding")
+      expect(errors[3]?.message).toContain("display")
+      expect(errors[4]?.message).toContain("budgets")
+      expect(errors[5]?.message).toContain("effort")
+      const older = yield* compileRequest(
+        LLM.request({
+          model: AnthropicMessages.route.model({ id: "claude-sonnet-5" }),
+          prompt: "Hello",
+          providerOptions: { thinking: { type: "between_tools" } },
+        }),
+      ).pipe(Effect.flip)
+      expect(older.reason._tag).toBe("InvalidRequest")
+    }),
+  )
+
+  it.effect("rejects forced tools and non-default sampling only on Sonnet 5.5", () =>
+    Effect.gen(function* () {
+      const sonnet = AnthropicMessages.route.model({ id: "claude-sonnet-5-5" })
+      const tools = [{ name: "lookup", description: "Look up", inputSchema: { type: "object", properties: {} } }]
+      for (const toolChoice of ["required", ToolChoice.named("lookup")] as const) {
+        const error = yield* compileRequest(LLM.request({ model: sonnet, prompt: "Hello", tools, toolChoice })).pipe(
+          Effect.flip,
+        )
+        expect(error.reason._tag).toBe("InvalidRequest")
+        expect(error.message).toContain("tool choice")
+      }
+      for (const generation of [{ temperature: 0.5 }, { topP: 0.98 }, { topK: 10 }]) {
+        const error = yield* compileRequest(LLM.request({ model: sonnet, prompt: "Hello", generation })).pipe(
+          Effect.flip,
+        )
+        expect(error.reason._tag).toBe("InvalidRequest")
+        expect(error.message).toContain("sampling")
+      }
+      const accepted = yield* compileRequest(
+        LLM.request({
+          model: sonnet,
+          prompt: "Hello",
+          tools,
+          toolChoice: "auto",
+          generation: { temperature: 1, topP: 0.99 },
+        }),
+      )
+      expect(accepted.body.tool_choice).toEqual({ type: "auto" })
+      expect(accepted.body.temperature).toBe(1)
+      expect(accepted.body.top_p).toBe(0.99)
+      expect(
+        (yield* compileRequest(LLM.request({ model: sonnet, prompt: "Hello", tools, toolChoice: "none" }))).body
+          .tool_choice,
+      ).toEqual({ type: "none" })
+      expect(
+        (yield* compileRequest(
+          LLM.request({
+            model: AnthropicMessages.route.model({ id: "claude-sonnet-5" }),
+            prompt: "Hello",
+            tools,
+            toolChoice: "required",
+          }),
+        )).body.tool_choice,
+      ).toEqual({ type: "any" })
+    }),
+  )
+
+  it.effect("does not send per-message effort changes with Sonnet 5.5 between-tools thinking", () =>
+    Effect.gen(function* () {
+      const sonnet = AnthropicMessages.route.model({
+        id: "claude-sonnet-5-5",
+        compatibility: { supportsEffortUpdates: true },
+      })
+      const error = yield* compileRequest(
+        LLM.request({
+          model: sonnet,
+          messages: [
+            Message.user("Before"),
+            Message.effort({ effort: "low", previous: "medium" }),
+            Message.user("After"),
+          ],
+          providerOptions: { thinking: { type: "between_tools" }, effort: "low" },
+        }),
+      ).pipe(Effect.flip)
+      expect(error.reason._tag).toBe("InvalidRequest")
+      expect(error.message).toContain("mid-conversation")
+    }),
+  )
+
  it.effect("lowers passthrough provider options and accepts either key spelling", () =>
    Effect.gen(function* () {
      const snake = yield* compileRequest(
@@ -0,0 +1,103 @@
+import { describe, expect } from "bun:test"
+import { Effect } from "effect"
+import { LLM, LLMRequest, Message } from "../../src/index.js"
+import { LLMClient } from "../../src/route.js"
+import { AmazonBedrock } from "../../src/providers.js"
+import { recordedTests } from "../recorded-test.js"
+
+const RECORDING_REGION = process.env.BEDROCK_RECORDING_REGION ?? "us-east-1"
+
+// Claude Opus 5.5 enforces the conversation-prefix check on Bedrock, so a changed system prompt is a real
+// mismatch. Override with BEDROCK_BINDING_MODEL_ID for another model that enforces it.
+const modelID = process.env.BEDROCK_BINDING_MODEL_ID ?? "global.anthropic.claude-opus-5-5"
+
+// Mirrors the "high" variant, so the recording covers the real overlay and default merge.
+const model = (blockBinding?: { readonly prefix_mismatch_behavior: string }) =>
+  AmazonBedrock.model(modelID, {
+    apiKey: process.env.AWS_BEARER_TOKEN_BEDROCK ?? "fixture",
+    region: RECORDING_REGION,
+    body: {
+      additionalModelRequestFields: {
+        thinking: { type: "adaptive", display: "summarized", ...(blockBinding ? { block_binding: blockBinding } : {}) },
+        output_config: { effort: "high" },
+      },
+    },
+  })
+
+const question = "How many positive integers below 5000 have exactly 12 positive divisors? Reply with the number only."
+
+const first = LLM.request({
+  id: "recorded_bedrock_thinking_binding_first",
+  model: model(),
+  system: "You are a concise assistant.",
+  prompt: question,
+  cache: "none",
+  generation: { maxTokens: 12_000 },
+})
+
+const recorded = recordedTests({
+  prefix: "bedrock-converse-thinking-binding",
+  provider: "amazon-bedrock",
+  protocol: "bedrock-converse",
+  requires: ["AWS_BEARER_TOKEN_BEDROCK"],
+})
+
+describe("Bedrock Converse thinking binding recorded", () => {
+  recorded.effect.with("accepts the default binding with no thinking configured", { tags: ["reasoning"] }, () =>
+    Effect.gen(function* () {
+      const response = yield* LLMClient.generate(
+        LLM.request({
+          id: "recorded_bedrock_thinking_binding_default",
+          model: AmazonBedrock.model(modelID, {
+            apiKey: process.env.AWS_BEARER_TOKEN_BEDROCK ?? "fixture",
+            region: RECORDING_REGION,
+          }),
+          system: "Reply with the single word 'Hello'.",
+          prompt: "Say hello.",
+          cache: "none",
+          generation: { maxTokens: 1_024 },
+        }),
+      )
+
+      expect(response.finishReason?.normalized).toBe("stop")
+      expect(response.text).toMatch(/hello/i)
+    }),
+  )
+
+  recorded.effect.with(
+    "keeps a session working after the system prompt changes",
+    { tags: ["reasoning"] },
+    () =>
+      Effect.gen(function* () {
+        const turn = yield* LLMClient.generate(first)
+        // The signed thinking block is what Bedrock binds to the first system prompt.
+        expect(turn.message.content.some((part) => part.type === "reasoning")).toBe(true)
+
+        // Replay the assistant turn under a different system prompt, as a prompt rebuild or compaction would.
+        const next = LLMRequest.update(first, {
+          id: "recorded_bedrock_thinking_binding_next",
+          system: [{ type: "text", text: "You are a concise assistant. Today is Monday." }],
+          messages: [
+            ...first.messages,
+            Message.assistant(turn.message.content),
+            Message.user("Now double it. Reply with the number only."),
+          ],
+        })
+
+        const bound = yield* LLMClient.generate(next)
+        expect(bound.finishReason?.normalized).toBe("stop")
+        expect(bound.text).toMatch(/\d/)
+
+        // The same replay is rejected when the caller asks for the default `error` behavior, proving the check is
+        // enforced and that the default `drop_block` is what let the request above through.
+        const rejected = yield* LLMClient.generate(
+          LLMRequest.update(next, {
+            id: "recorded_bedrock_thinking_binding_error",
+            model: model({ prefix_mismatch_behavior: "error" }),
+          }),
+        ).pipe(Effect.flip)
+        expect(rejected.message).toContain("bound to a different conversation")
+      }),
+    60_000,
+  )
+})
@@ -0,0 +1,100 @@
+import { describe, expect } from "bun:test"
+import { Effect } from "effect"
+import { GenerationOptions, LanguageModel, LLM } from "../../src/index.js"
+import { compileRequest } from "../../src/route/client.js"
+import { AmazonBedrock } from "../../src/providers.js"
+import { it } from "../lib/effect.js"
+
+const binding = { prefix_mismatch_behavior: "drop_block" }
+const beta = ["thinking-binding-controls-2026-08-01"]
+
+const bedrock = (id: string, settings: Parameters<typeof AmazonBedrock.model>[1] = {}) =>
+  AmazonBedrock.model(id, { baseURL: "https://bedrock-runtime.test", apiKey: "test-bearer", ...settings })
+
+const fields = (model: LanguageModel, generation?: GenerationOptions) =>
+  compileRequest(
+    LLM.request({ id: "req_1", model, system: "You are concise.", prompt: "Say hello.", cache: "none", generation }),
+  ).pipe(Effect.map((prepared) => prepared.body.additionalModelRequestFields))
+
+describe("Bedrock Converse thinking block binding", () => {
+  for (const id of [
+    "global.anthropic.claude-fable-5-1",
+    "us.anthropic.claude-fable-5-1-v1:0",
+    "anthropic.claude-fable-5.1",
+    "anthropic.claude-mythos-5-1",
+    "us.anthropic.claude-opus-5-5",
+    "global.anthropic.claude-sonnet-5-5",
+    "anthropic.claude-opus-6",
+  ]) {
+    it.effect(`defaults adaptive thinking to drop_block with the beta for ${id}`, () =>
+      Effect.gen(function* () {
+        expect(yield* fields(bedrock(id))).toEqual({
+          thinking: { type: "adaptive", block_binding: binding },
+          anthropic_beta: beta,
+        })
+      }),
+    )
+  }
+
+  for (const id of [
+    "global.anthropic.claude-opus-5",
+    "us.anthropic.claude-sonnet-5",
+    "global.anthropic.claude-fable-5",
+    "anthropic.claude-fable-5-v1:0",
+    "global.anthropic.claude-opus-4-8",
+    "us.anthropic.claude-opus-4-5-20251101-v1:0",
+    "us.anthropic.claude-haiku-4-5-20251001-v1:0",
+    "anthropic.claude-3-5-sonnet-20241022-v2:0",
+    "us.amazon.nova-2-lite-v1:0",
+  ]) {
+    it.effect(`leaves ${id} untouched`, () =>
+      Effect.gen(function* () {
+        expect(yield* fields(bedrock(id))).toBeUndefined()
+      }),
+    )
+  }
+
+  it.effect("binds a manual thinking budget and keeps top_k", () =>
+    Effect.gen(function* () {
+      expect(
+        yield* fields(
+          bedrock("global.anthropic.claude-fable-5-1", { thinking: { type: "enabled", budgetTokens: 4_000 } }),
+          GenerationOptions.make({ maxTokens: 64_000, topK: 40 }),
+        ),
+      ).toEqual({
+        top_k: 40,
+        thinking: { type: "enabled", budget_tokens: 4_000, block_binding: binding },
+        anthropic_beta: beta,
+      })
+    }),
+  )
+
+  it.effect("does not bind disabled thinking", () =>
+    Effect.gen(function* () {
+      expect(
+        yield* fields(
+          bedrock("global.anthropic.claude-fable-5-1", {
+            body: { additionalModelRequestFields: { thinking: { type: "disabled" } } },
+          }),
+        ),
+      ).toBeUndefined()
+    }),
+  )
+
+  it.effect("honors the compatibility override in both directions", () =>
+    Effect.gen(function* () {
+      const arn = "arn:aws:bedrock:us-east-1:123456789012:application-inference-profile/abc123"
+      expect(yield* fields(bedrock(arn))).toBeUndefined()
+      expect(
+        yield* fields(LanguageModel.update(bedrock(arn), { compatibility: { supportsThinkingBlockBinding: true } })),
+      ).toEqual({ thinking: { type: "adaptive", block_binding: binding }, anthropic_beta: beta })
+      expect(
+        yield* fields(
+          LanguageModel.update(bedrock("global.anthropic.claude-fable-5-1"), {
+            compatibility: { supportsThinkingBlockBinding: false },
+          }),
+        ),
+      ).toBeUndefined()
+    }),
+  )
+})
@@ -1301,11 +1301,11 @@ describe("Bedrock Converse route", () => {
          ),
        ),
      )
-      expect(response.events.filter((event) => event.type === "reasoning-delta" && event.text === "").at(-1)).toEqual({
-        type: "reasoning-delta",
+      expect(response.events.filter((event) => event.type === "reasoning-delta")).toEqual([])
+      expect(response.events.find((event) => event.type === "reasoning-start")).toEqual({
+        type: "reasoning-start",
        id: "reasoning-0",
-        text: "",
-        providerMetadata: { bedrock: { redactedData } },
+        providerMetadata: undefined,
      })
      expect(response.events.find((event) => event.type === "reasoning-end")).toEqual({
        type: "reasoning-end",
@@ -1383,6 +1383,13 @@ describe("Bedrock Converse route", () => {
        ),
      )

+      expect(response.events.filter((event) => event.type === "reasoning-delta")).toEqual([])
+      expect(response.events.find((event) => event.type === "reasoning-end")).toEqual({
+        type: "reasoning-end",
+        id: "reasoning-0",
+        providerMetadata: { bedrock: { redactedData: "AQID" } },
+        text: undefined,
+      })
      expect(response.message.content).toEqual([
        { type: "reasoning", text: "", providerMetadata: { bedrock: { redactedData: "AQID" } } },
      ])
@@ -0,0 +1,50 @@
+import { describe, expect } from "bun:test"
+import { Effect, Stream } from "effect"
+import { Transcription } from "../../src/index.js"
+import { ElevenLabs } from "../../src/providers.js"
+import { recordedTests } from "../recorded-test.js"
+import { TRANSCRIPT, audio, audioRecording, dialog } from "./transcription-recording.js"
+
+const model = ElevenLabs.configure({ apiKey: process.env.ELEVENLABS_API_KEY ?? "fixture" }).transcription("scribe_v2")
+
+const recorded = recordedTests({
+  prefix: "elevenlabs-transcription",
+  provider: "elevenlabs",
+  protocol: "elevenlabs-transcription",
+  requires: ["ELEVENLABS_API_KEY"],
+  options: audioRecording,
+})
+
+describe("ElevenLabs Transcription recorded", () => {
+  recorded.effect("transcribes audio with word timestamps", () =>
+    Effect.gen(function* () {
+      const request = Transcription.request({ model, audio: yield* audio, timestamps: "word" })
+      const response = yield* Transcription.generate(request)
+
+      expect(response.text).toMatch(TRANSCRIPT)
+      expect(response.words?.map((word) => word.text)).toEqual(["Hello", "from", "OpenCode"])
+      expect(response.words?.every((word) => word.speaker === undefined && (word.confidence ?? 0) > 0)).toBe(true)
+      expect(response.segments).toBeUndefined()
+      expect(response.language).toBe("eng")
+      expect(response.durationSeconds).toBeGreaterThan(0)
+      expect(response.usage).toEqual({ type: "seconds", seconds: response.durationSeconds })
+      expect(response.providerMetadata?.elevenlabs?.transcriptionId).toEqual(expect.any(String))
+
+      const events = Array.from(yield* Stream.runCollect(Transcription.stream(request)))
+      expect(events.map((event) => event.type)).toEqual(["finish"])
+    }),
+  )
+
+  recorded.effect("groups diarized words into speaker turns", () =>
+    Effect.gen(function* () {
+      const response = yield* Transcription.generate({ model, audio: yield* dialog, diarize: true })
+
+      expect(response.segments?.map((segment) => segment.speaker)).toEqual(["speaker_0", "speaker_1"])
+      expect(response.segments?.[0].text).toMatch(/^Did the release ship\?$/)
+      expect(response.segments?.[1].text).toMatch(/^Yes, it shipped this morning\.?$/)
+      expect(response.segments?.map((segment) => segment.text).join(" ")).toBe(response.text)
+      expect(response.words?.some((word) => word.text.trim() === "")).toBe(false)
+      expect(new Set(response.words?.map((word) => word.speaker))).toEqual(new Set(["speaker_0", "speaker_1"]))
+    }),
+  )
+})
@@ -92,5 +92,6 @@ const assertEvaluation = <Options extends EvaluationOptions>(
    expect(response.answers.refund.probability).toBeGreaterThan(0.5)
    expect(response.usage?.inputTokens).toBeGreaterThan(0)
    expect(response.usage?.outputTokens).toBeGreaterThan(0)
-    expect(response.providerMetadata?.[metadataKey]?.confidence).toBeDefined()
+    expect(response.answers.department.confidence).toBeGreaterThan(0)
+    expect(response.answers.urgency.confidence).toBeGreaterThan(0)
  })
@@ -0,0 +1,68 @@
+import { describe, expect } from "bun:test"
+import { Effect } from "effect"
+import { LLM, LLMEvent, LLMRequest, Message, ToolRuntime, toDefinitions } from "../../src/index.js"
+import * as OpenAICompatible from "../../src/providers/openai-compatible.js"
+import { LLMClient } from "../../src/route.js"
+import { compileRequest } from "../../src/route/client.js"
+import { recordedTests } from "../recorded-test.js"
+import { weatherRuntimeTool, weatherToolName } from "../recorded-scenarios.js"
+
+const model = OpenAICompatible.configure({
+  provider: "google",
+  baseURL: "https://generativelanguage.googleapis.com/v1beta/openai",
+  apiKey: process.env.GOOGLE_GENERATIVE_AI_API_KEY ?? "fixture",
+}).model("gemini-3.8-flash")
+
+const recorded = recordedTests({
+  prefix: "openai-compatible-chat",
+  provider: "google",
+  protocol: "openai-chat",
+  requires: ["GOOGLE_GENERATIVE_AI_API_KEY"],
+  tags: ["tool", "tool-loop", "continuation"],
+  metadata: { model: model.id },
+})
+
+describe("Gemini OpenAI-compatible Chat recorded", () => {
+  recorded.effect.with(
+    "replays thought signatures through a parallel tool loop",
+    { cassette: "openai-compatible-chat/gemini-parallel-tool-signatures" },
+    () =>
+      Effect.gen(function* () {
+        const tools = { [weatherToolName]: weatherRuntimeTool }
+        const request = LLM.request({
+          model,
+          system: "Call get_weather for every requested city in parallel, then answer in one short sentence.",
+          prompt: "What is the weather in Paris and in Tokyo?",
+          tools: toDefinitions(tools),
+          cache: "none",
+        })
+        const first = yield* LLMClient.generate(request)
+        const calls = first.events.filter(LLMEvent.is.toolCall)
+        expect(calls.map((call) => call.input)).toEqual([{ city: "Paris" }, { city: "Tokyo" }])
+        const extraContent = calls[0]?.providerMetadata?.google?.extraContent
+        expect(extraContent).toEqual({ google: { thought_signature: expect.any(String) } })
+
+        const results = yield* Effect.forEach(calls, (call) => ToolRuntime.dispatch(tools, call))
+        const continuation = LLMRequest.update(request, {
+          messages: [
+            ...request.messages,
+            first.message,
+            ...calls.map((call, index) =>
+              Message.tool({ id: call.id, name: call.name, result: results[index]!.result }),
+            ),
+          ],
+        })
+        const prepared = yield* compileRequest(continuation)
+        const assistant = prepared.body.messages.find((message) => message.role === "assistant")
+        expect(assistant?.role === "assistant" ? assistant.tool_calls?.[0]?.extra_content : undefined).toEqual(
+          extraContent,
+        )
+
+        const second = yield* LLMClient.generate(continuation)
+        expect(second.events.filter(LLMEvent.is.toolCall)).toHaveLength(0)
+        expect(second.text).toMatch(/Paris/)
+        expect(second.text).toMatch(/Tokyo/)
+      }),
+    60_000,
+  )
+})
@@ -33,7 +33,12 @@ it.effect("Meta selects Messages and lowers native search alongside ordinary fun
      output_config: { effort: "low" },
      tools: [
        { type: "web_search", name: "web_search", user_location: { type: "approximate", country: "US" } },
-        { name: "lookup", description: "Lookup", input_schema: { type: "object" } },
+        {
+          name: "lookup",
+          description: "Lookup",
+          input_schema: { type: "object" },
+          cache_control: { type: "ephemeral" },
+        },
      ],
    })
    const entrypoint = yield* Effect.promise(() => import("@opencode/ai/providers/meta/messages"))
@@ -472,6 +472,45 @@ describe("OpenAI Chat route", () => {
    }),
  )

+  it.effect("replays Gemini thought signatures as tool call extra content", () =>
+    Effect.gen(function* () {
+      const prepared = yield* compileRequest(
+        LLM.request({
+          model,
+          messages: [
+            Message.user("Weather in Paris and Tokyo?"),
+            Message.assistant([
+              ToolCallPart.make({
+                id: "call_1",
+                name: "lookup",
+                input: { city: "Paris" },
+                providerMetadata: { openai: { extraContent: { google: { thought_signature: "sig_1" } } } },
+              }),
+              ToolCallPart.make({ id: "call_2", name: "lookup", input: { city: "Tokyo" } }),
+            ]),
+            Message.tool({ id: "call_1", name: "lookup", result: "Sunny" }),
+            Message.tool({ id: "call_2", name: "lookup", result: "Rainy" }),
+          ],
+        }),
+      )
+
+      const assistant = prepared.body.messages[1]
+      expect(assistant?.role === "assistant" ? assistant.tool_calls : undefined).toEqual([
+        {
+          id: "call_1",
+          type: "function",
+          function: { name: "lookup", arguments: encodeJson({ city: "Paris" }) },
+          extra_content: { google: { thought_signature: "sig_1" } },
+        },
+        {
+          id: "call_2",
+          type: "function",
+          function: { name: "lookup", arguments: encodeJson({ city: "Tokyo" }) },
+        },
+      ])
+    }),
+  )
+
  it.effect("limits OpenAI and Azure Chat tool call IDs to 40 characters", () =>
    Effect.gen(function* () {
      const id = `call_${"a".repeat(48)}`
@@ -1805,6 +1844,78 @@ describe("OpenAI Chat route", () => {
    }),
  )

+  it.effect("preserves Gemini thought signatures on streamed parallel tool calls", () =>
+    Effect.gen(function* () {
+      // Gemini's OpenAI-compatible endpoint omits `index`, streams each call whole,
+      // and signs only the first call of a parallel batch.
+      const body = sseEvents(
+        deltaChunk({
+          role: "assistant",
+          tool_calls: [
+            {
+              extra_content: { google: { thought_signature: "sig_1" } },
+              id: "call_1",
+              type: "function",
+              function: { name: "lookup", arguments: '{"city":"Paris"}' },
+            },
+          ],
+        }),
+        deltaChunk({
+          role: "assistant",
+          tool_calls: [{ id: "call_2", type: "function", function: { name: "lookup", arguments: '{"city":"Tokyo"}' } }],
+        }),
+        deltaChunk({}, "stop"),
+      )
+      const response = yield* LLMClient.generate(
+        LLMRequest.update(request, {
+          tools: [ToolDefinition.make({ name: "lookup", description: "Lookup data", inputSchema: { type: "object" } })],
+        }),
+      ).pipe(Effect.provide(fixedResponse(body)))
+
+      expect(response.events.filter(LLMEvent.is.toolCall)).toEqual([
+        {
+          type: "tool-call",
+          id: "call_1",
+          name: "lookup",
+          input: { city: "Paris" },
+          providerExecuted: undefined,
+          providerMetadata: { openai: { extraContent: { google: { thought_signature: "sig_1" } } } },
+        },
+        {
+          type: "tool-call",
+          id: "call_2",
+          name: "lookup",
+          input: { city: "Tokyo" },
+          providerExecuted: undefined,
+          providerMetadata: undefined,
+        },
+      ])
+    }),
+  )
+
+  it.effect("keeps extra content that arrives before the tool identity", () =>
+    Effect.gen(function* () {
+      const body = sseEvents(
+        deltaChunk({
+          tool_calls: [
+            { index: 0, extra_content: { google: { thought_signature: "sig_1" } }, function: { arguments: "{" } },
+          ],
+        }),
+        deltaChunk({ tool_calls: [{ index: 0, id: "call_1", function: { name: "lookup", arguments: "}" } }] }),
+        deltaChunk({}, "tool_calls"),
+      )
+      const response = yield* LLMClient.generate(
+        LLMRequest.update(request, {
+          tools: [ToolDefinition.make({ name: "lookup", description: "Lookup data", inputSchema: { type: "object" } })],
+        }),
+      ).pipe(Effect.provide(fixedResponse(body)))
+
+      expect(response.events.filter(LLMEvent.is.toolCall).map((event) => event.providerMetadata)).toEqual([
+        { openai: { extraContent: { google: { thought_signature: "sig_1" } } } },
+      ])
+    }),
+  )
+
  it.effect("does not finalize streamed tool calls when content is filtered", () =>
    Effect.gen(function* () {
      const body = sseEvents(
@@ -56,7 +56,9 @@ describe("xAI Responses route", () => {
      expect(XAIResponses.protocol.body).not.toBe(OpenAIResponses.protocol.body)

      const prepared = yield* compileRequest(LLM.request({ model, prompt: "Hello" }))
+      expect(prepared.route).toBe("xai-responses")
      expect(prepared.protocol).toBe("xai-responses")
+      expect(prepared.model.route.providerMetadataKey).toBe("xai")
      expect(prepared.body.store).toBe(false)
      expect(prepared.body.include).toEqual(["reasoning.encrypted_content"])
    }),
@@ -298,3 +300,14 @@ describe("xAI Responses route", () => {
    }),
  )
 })
+
+it.effect("names the xAI Chat route separately from its OpenAI Chat protocol", () =>
+  Effect.gen(function* () {
+    const prepared = yield* compileRequest(
+      LLM.request({ model: XAI.configure({ apiKey: "test" }).chat("grok-4.6"), prompt: "Hello" }),
+    )
+    expect(prepared.route).toBe("xai-chat")
+    expect(prepared.protocol).toBe("openai-chat")
+    expect(prepared.model.route.providerMetadataKey).toBe("xai")
+  }),
+)
@@ -2,10 +2,11 @@ import { describe, expect } from "bun:test"
 import { Effect, Fiber, Layer, Stream } from "effect"
 import * as TestClock from "effect/testing/TestClock"
 import { HttpClientRequest } from "effect/unstable/http"
-import { Media, Transcription, TranscriptionClient } from "../src/index.js"
-import { AssemblyAI, Deepgram, Google, OpenAI } from "../src/providers.js"
+import { Media, Transcription, TranscriptionClient, type TranscriptionEvent } from "../src/index.js"
+import { AssemblyAI, Deepgram, ElevenLabs, Google, OpenAI } from "../src/providers.js"
 import { it } from "./lib/effect.js"
 import { dynamicResponse, json, observe, type Call } from "./lib/http.js"
+import { sseEvents } from "./lib/sse.js"

 const layer = (handler: Parameters<typeof dynamicResponse>[0]) =>
  TranscriptionClient.layer.pipe(Layer.provideMerge(dynamicResponse(handler)))
@@ -16,9 +17,27 @@ const deepgram = Deepgram.configure({ apiKey: "test", baseURL: "https://deepgram
 const google = Google.configure({ apiKey: "test", baseURL: "https://google.test/v1beta" }).transcription(
  "gemini-3.5-transcribe",
 )
+/**
+ * Multipart fields of a recorded request, with repeated names collected in order. The boundary comes from the body:
+ * each conversion of a FormData request to a web request picks a fresh one, so the recorded headers may not match.
+ */
+const formFields = (call: Call) =>
+  Effect.promise(() =>
+    new Response(call.body, {
+      headers: { "content-type": `multipart/form-data; boundary=${call.body.slice(2, call.body.indexOf("\r\n"))}` },
+    }).formData(),
+  ).pipe(
+    Effect.map((form) =>
+      Object.fromEntries([...new Set(form.keys())].map((key) => [key, form.getAll(key).map((value) => String(value))])),
+    ),
+  )
+
 const assemblyai = AssemblyAI.configure({ apiKey: "aai-key", baseURL: "https://assemblyai.test" }).transcription(
  "universal-3-5-pro",
 )
+const elevenlabs = ElevenLabs.configure({ apiKey: "test", baseURL: "https://elevenlabs.test" }).transcription(
+  "scribe_v2",
+)

 describe("Transcription", () => {
  it.effect("rejects what a route cannot honor before sending anything", () =>
@@ -129,6 +148,198 @@ describe("Transcription", () => {
    }),
  )

+  it.effect("streams diarized segments and finishes with the accumulated segments", () =>
+    Effect.gen(function* () {
+      const calls: Array<Call> = []
+      const body = sseEvents(
+        { type: "transcript.text.segment", id: "seg_0", text: " Hello", start: 0.25, end: 0.7, speaker: "A" },
+        { type: "transcript.text.segment", id: "seg_1", text: " there.", start: 0.7, end: 1.25, speaker: "B" },
+        { type: "transcript.text.done", text: "Hello there.", usage: { type: "duration", seconds: 2 } },
+      )
+      const events = Array.from(
+        yield* Stream.runCollect(
+          Transcription.stream({ model: openai.transcription("gpt-4o-transcribe-diarize"), audio, diarize: true }),
+        ).pipe(
+          Effect.provide(
+            layer((input) =>
+              observe(calls, input).pipe(
+                Effect.as(input.respond(body, { headers: { "content-type": "text/event-stream" } })),
+              ),
+            ),
+          ),
+        ),
+      )
+
+      const form = yield* formFields(calls[0])
+      expect(form).toMatchObject({
+        model: ["gpt-4o-transcribe-diarize"],
+        response_format: ["diarized_json"],
+        chunking_strategy: ["auto"],
+        stream: ["true"],
+      })
+      const segments = [
+        { text: "Hello", startSeconds: 0.25, endSeconds: 0.7, speaker: "A" },
+        { text: "there.", startSeconds: 0.7, endSeconds: 1.25, speaker: "B" },
+      ]
+      expect(events).toEqual([
+        { type: "segment", segment: segments[0] },
+        { type: "segment", segment: segments[1] },
+        expect.objectContaining({
+          type: "finish",
+          text: "Hello there.",
+          segments,
+          usage: { type: "seconds", seconds: 2 },
+        }),
+      ])
+    }),
+  )
+
+  it.effect("requests whisper-1 segment timestamps as verbose_json", () =>
+    Effect.gen(function* () {
+      const calls: Array<Call> = []
+      const response = yield* Transcription.generate({
+        model: openai.transcription("whisper-1"),
+        audio,
+        timestamps: "segment",
+      }).pipe(
+        Effect.provide(
+          layer((input) =>
+            observe(calls, input).pipe(
+              Effect.as(
+                json(input, {
+                  text: "Hello there.",
+                  language: "English",
+                  duration: 1.25,
+                  segments: [
+                    { id: 0, text: " Hello", start: 0.25, end: 0.7 },
+                    { id: 1, text: " there.", start: 0.7, end: 1.25 },
+                  ],
+                  usage: { type: "duration", seconds: 2 },
+                }),
+              ),
+            ),
+          ),
+        ),
+      )
+
+      const form = yield* formFields(calls[0])
+      expect(form).toMatchObject({
+        model: ["whisper-1"],
+        response_format: ["verbose_json"],
+        "timestamp_granularities[]": ["segment"],
+      })
+      expect(form.stream).toBeUndefined()
+      expect(response).toMatchObject({
+        text: "Hello there.",
+        segments: [
+          { text: "Hello", startSeconds: 0.25, endSeconds: 0.7 },
+          { text: "there.", startSeconds: 0.7, endSeconds: 1.25 },
+        ],
+        language: "english",
+        durationSeconds: 1.25,
+        usage: { type: "seconds", seconds: 2 },
+      })
+    }),
+  )
+
+  it.effect("fails an OpenAI stream that ends without transcript.text.done as incomplete", () =>
+    Effect.gen(function* () {
+      const events: Array<TranscriptionEvent> = []
+      const error = yield* Transcription.stream({ model: openai.transcription("gpt-4o-mini-transcribe"), audio }).pipe(
+        Stream.runForEach((event) => Effect.sync(() => events.push(event))),
+        Effect.flip,
+        Effect.provide(
+          layer((input) =>
+            Effect.succeed(
+              input.respond(sseEvents({ type: "transcript.text.delta", delta: "Hel" }), {
+                headers: { "content-type": "text/event-stream" },
+              }),
+            ),
+          ),
+        ),
+      )
+
+      expect(events).toEqual([{ type: "text-delta", delta: "Hel" }])
+      expect(error.reason).toMatchObject({ _tag: "InvalidProviderOutput", classification: "incomplete-stream" })
+      expect(error.reason.http?.status).toBe(200)
+    }),
+  )
+
+  it.effect("sends a Deepgram URL source as a JSON body and repeats array query parameters", () =>
+    Effect.gen(function* () {
+      const calls: Array<Call> = []
+      const response = yield* Transcription.generate({
+        model: deepgram,
+        audio: Media.url("https://a.test/call.mp3", { mediaType: "audio/mpeg" }),
+        language: "en",
+        providerOptions: { keyterm: ["OpenCode", "Effect"] },
+      }).pipe(
+        Effect.provide(
+          layer((input) =>
+            observe(calls, input).pipe(
+              Effect.as(
+                json(input, {
+                  metadata: { request_id: "dg_1", duration: 2 },
+                  results: { channels: [{ alternatives: [{ transcript: "Hello there." }] }] },
+                }),
+              ),
+            ),
+          ),
+        ),
+      )
+
+      expect(calls).toHaveLength(1)
+      const url = new URL(calls[0].url)
+      expect(url.origin + url.pathname).toBe("https://deepgram.test/v1/listen")
+      expect([...url.searchParams]).toEqual([
+        ["model", "nova-3"],
+        ["smart_format", "true"],
+        ["language", "en"],
+        ["keyterm", "OpenCode"],
+        ["keyterm", "Effect"],
+      ])
+      expect(calls[0].headers.get("content-type")).toBe("application/json")
+      expect(JSON.parse(calls[0].body)).toEqual({ url: "https://a.test/call.mp3" })
+      expect(response).toMatchObject({
+        text: "Hello there.",
+        usage: { type: "seconds", seconds: 2 },
+        providerMetadata: { deepgram: { requestId: "dg_1" } },
+      })
+    }),
+  )
+
+  it.effect("transcribes an AssemblyAI URL source without uploading it first", () =>
+    Effect.gen(function* () {
+      const calls: Array<Call> = []
+      const response = yield* Transcription.generate({
+        model: assemblyai,
+        audio: Media.url("https://a.test/call.mp3", { mediaType: "audio/mpeg" }),
+      }).pipe(
+        Effect.provide(
+          layer((input) =>
+            Effect.gen(function* () {
+              const { call } = yield* observe(calls, input)
+              if (call.method === "POST") return json(input, { id: "tr_1", status: "queued" })
+              return json(input, { id: "tr_1", status: "completed", text: "Hello there.", audio_duration: 2 })
+            }),
+          ),
+        ),
+      )
+
+      expect(calls.map((call) => `${call.method} ${call.url}`)).toEqual([
+        "POST https://assemblyai.test/v2/transcript",
+        "GET https://assemblyai.test/v2/transcript/tr_1",
+        "GET https://assemblyai.test/v2/transcript/tr_1",
+      ])
+      expect(JSON.parse(calls[0].body)).toEqual({
+        audio_url: "https://a.test/call.mp3",
+        speech_models: ["universal-3-5-pro"],
+        language_detection: true,
+      })
+      expect(response).toMatchObject({ text: "Hello there.", usage: { type: "seconds", seconds: 2 } })
+    }),
+  )
+
  it.effect(
    "uploads inline audio to AssemblyAI, resumes polling from a persisted token, and surfaces failed transcripts",
    () =>
@@ -251,6 +462,115 @@ describe("Transcription", () => {
    }),
  )

+  it.effect("rejects ElevenLabs prompts, webhooks, per-channel transcripts, and untimed diarization", () =>
+    Effect.gen(function* () {
+      const errors = yield* Effect.all(
+        [
+          Transcription.generate({ model: elevenlabs, audio, prompt: "OpenCode" }),
+          Transcription.generate({ model: elevenlabs, audio, providerOptions: { webhook: true } }),
+          Transcription.generate({ model: elevenlabs, audio, http: { body: { use_multi_channel: true } } }),
+          Transcription.generate({
+            model: elevenlabs,
+            audio,
+            diarize: true,
+            providerOptions: { timestamps_granularity: "none" },
+          }),
+          Transcription.generate({
+            model: elevenlabs,
+            audio: Media.ref("file_1", { provider: "elevenlabs", mediaType: "audio/mpeg" }),
+          }),
+        ].map((effect) => Effect.flip(effect)),
+      )
+      expect(errors.map((error) => [error.reason._tag, "operation" in error.reason && error.reason.operation])).toEqual(
+        [
+          ["UnsupportedOperation", "media.prompt"],
+          ["UnsupportedOperation", "transcription.webhook"],
+          ["UnsupportedOperation", "transcription.multichannel"],
+          ["UnsupportedOperation", "media.timestamps"],
+          ["InvalidRequest", false],
+        ],
+      )
+    }).pipe(Effect.provide(layer(() => Effect.die("an unsupported request reached the network")))),
+  )
+
+  it.effect("sends ElevenLabs URL audio as source_url and groups diarized words into speaker turns", () =>
+    Effect.gen(function* () {
+      const calls: Array<Call> = []
+      const token = (text: string, type: string, start: number, end: number, speaker_id?: string) => ({
+        text,
+        type,
+        start,
+        end,
+        speaker_id,
+        logprob: 0,
+      })
+      const response = yield* Transcription.generate({
+        model: elevenlabs,
+        audio: Media.url("https://a.test/call.mp3"),
+        language: "en",
+        speakers: 2,
+        providerOptions: { keyterms: ["OpenCode", "Scribe"], tag_audio_events: true, diarize: false },
+      }).pipe(
+        Effect.provide(
+          layer((input) =>
+            observe(calls, input).pipe(
+              Effect.as(
+                json(input, {
+                  language_code: "ENG",
+                  text: "Ready? (laughs) Yes. Go",
+                  words: [
+                    token("Ready?", "word", 0, 0.5, "speaker_0"),
+                    token(" ", "spacing", 0.5, 0.6, "speaker_0"),
+                    token("(laughs)", "audio_event", 0.6, 1, "speaker_0"),
+                    token(" ", "spacing", 1, 1.1, "speaker_0"),
+                    token("Yes.", "word", 1.2, 1.5, "speaker_1"),
+                    token(" ", "spacing", 1.5, 1.6, "speaker_1"),
+                    token("Go", "word", 1.6, 1.9, "speaker_0"),
+                  ],
+                  transcription_id: "tr_1",
+                  audio_duration_secs: 2,
+                }),
+              ),
+            ),
+          ),
+        ),
+      )
+
+      // `observe` re-encodes the FormData with a new boundary, so read the boundary from the sent body.
+      const boundary = /^--(\S+)/.exec(calls[0].body)?.[1]
+      const form = yield* Effect.promise(() =>
+        new Response(calls[0].body, {
+          headers: { "content-type": `multipart/form-data; boundary=${boundary}` },
+        }).formData(),
+      )
+      expect(calls[0].url).toBe("https://elevenlabs.test/v1/speech-to-text")
+      expect(calls[0].headers.get("xi-api-key")).toBe("test")
+      expect(Array.from(form.entries())).toEqual([
+        ["model_id", "scribe_v2"],
+        ["source_url", "https://a.test/call.mp3"],
+        ["language_code", "en"],
+        ["diarize", "true"],
+        ["num_speakers", "2"],
+        ["keyterms", "OpenCode"],
+        ["keyterms", "Scribe"],
+        ["tag_audio_events", "true"],
+      ])
+      expect(response.segments).toEqual([
+        { text: "Ready?", startSeconds: 0, endSeconds: 0.5, speaker: "speaker_0" },
+        { text: "Yes.", startSeconds: 1.2, endSeconds: 1.5, speaker: "speaker_1" },
+        { text: "Go", startSeconds: 1.6, endSeconds: 1.9, speaker: "speaker_0" },
+      ])
+      expect(response.words?.map((word) => [word.text, word.speaker, word.confidence])).toEqual([
+        ["Ready?", "speaker_0", 1],
+        ["Yes.", "speaker_1", 1],
+        ["Go", "speaker_0", 1],
+      ])
+      expect(response.language).toBe("eng")
+      expect(response.usage).toEqual({ type: "seconds", seconds: 2 })
+      expect(response.providerMetadata).toEqual({ elevenlabs: { transcriptionId: "tr_1" } })
+    }),
+  )
+
  it.effect("rejects reading an AssemblyAI result before the transcript finishes", () =>
    Effect.gen(function* () {
      const generation = yield* Transcription.resume(assemblyai, { transcriptID: "tr_1" })
@@ -1,9 +1,10 @@
 import { describe, expect } from "bun:test"
-import { Effect, Layer, Stream } from "effect"
-import { Media, Video, VideoClient, type GenerationEvent } from "../src/index.js"
+import { Effect, Fiber, Layer, Stream } from "effect"
+import * as TestClock from "effect/testing/TestClock"
+import { Media, Video, VideoClient, type GenerationEvent, type VideoEvent } from "../src/index.js"
 import { Fal, Google, Runway, XAI } from "../src/providers.js"
 import { it } from "./lib/effect.js"
-import { dynamicResponse, json, observe, settle, type Call } from "./lib/http.js"
+import { dynamicResponse, json, observe, settle, type Call, type HandlerInput } from "./lib/http.js"

 const layer = (handler: Parameters<typeof dynamicResponse>[0]) =>
  VideoClient.layer.pipe(Layer.provideMerge(dynamicResponse(handler)))
@@ -162,27 +163,39 @@ describe("Video / Google Veo", () => {
    ),
  )

-  it.effect("surfaces an operation error as a failed generation with the provider body", () =>
-    Effect.gen(function* () {
-      const failure = {
-        name: operation,
-        done: true,
-        error: { code: 3, message: "Prompt violates policy", status: "INVALID_ARGUMENT" },
-      }
-      const error = yield* Video.generate({ model, prompt: "nope" }).pipe(
-        Effect.flip,
-        Effect.provide(
-          layer((input) =>
-            Effect.succeed(input.request.method === "POST" ? json(input, { name: operation }) : json(input, failure)),
-          ),
-        ),
-      )
-      expect(error.reason._tag).toBe("ProviderInternal")
-      expect(error.message).toBe("Google Veo operation failed: Prompt violates policy")
-      expect(error.reason.body).toBe(JSON.stringify(failure))
-      expect(error.reason.http?.status).toBe(200)
-    }),
-  )
+  for (const terminal of [
+    { error: { code: 3, message: "Prompt violates policy", status: "INVALID_ARGUMENT" }, tag: "InvalidRequest" },
+    { error: { code: 9, message: "Unsupported resolution", status: "FAILED_PRECONDITION" }, tag: "InvalidRequest" },
+    { error: { code: 11, message: "Duration out of range", status: "OUT_OF_RANGE" }, tag: "InvalidRequest" },
+    { error: { code: 7, message: "Permission denied", status: "PERMISSION_DENIED" }, tag: "Authentication" },
+    { error: { code: 16, message: "Invalid credentials", status: "UNAUTHENTICATED" }, tag: "Authentication" },
+    { error: { code: 8, message: "Quota exceeded", status: "RESOURCE_EXHAUSTED" }, tag: "RateLimit" },
+    { error: { code: 13, message: "Internal error", status: "INTERNAL" }, tag: "ProviderInternal" },
+    { error: { code: 14, message: "Service unavailable", status: "UNAVAILABLE" }, tag: "ProviderInternal" },
+    { error: { message: "Something broke" }, tag: "ProviderInternal" },
+  ]) {
+    it.effect(
+      `surfaces ${terminal.error.status ?? "an uncoded"} operation error as ${terminal.tag} with the provider body`,
+      () =>
+        Effect.gen(function* () {
+          const failure = { name: operation, done: true, error: terminal.error }
+          const error = yield* Video.generate({ model, prompt: "nope" }).pipe(
+            Effect.flip,
+            Effect.provide(
+              layer((input) =>
+                Effect.succeed(
+                  input.request.method === "POST" ? json(input, { name: operation }) : json(input, failure),
+                ),
+              ),
+            ),
+          )
+          expect(error.reason._tag).toBe(terminal.tag)
+          expect(error.message).toBe(`Google Veo operation failed: ${terminal.error.message}`)
+          expect(error.reason.body).toBe(JSON.stringify(failure))
+          expect(error.reason.http?.status).toBe(200)
+        }),
+    )
+  }

  it.effect("reports fully filtered output as a content policy failure", () =>
    Effect.gen(function* () {
@@ -332,12 +345,37 @@ describe("Video / xAI", () => {
  for (const terminal of [
    {
      body: { status: "failed", error: { code: "invalid_argument", message: "Prompt cannot be empty." } },
-      tag: "ProviderInternal",
+      tag: "InvalidRequest",
      message: "xAI Video generation failed (invalid_argument): Prompt cannot be empty.",
    },
+    {
+      body: { status: "failed", error: { code: "failed_precondition", message: "Extension is not supported." } },
+      tag: "InvalidRequest",
+      message: "xAI Video generation failed (failed_precondition): Extension is not supported.",
+    },
+    {
+      body: { status: "failed", error: { code: "permission_denied", message: "Team lacks access." } },
+      tag: "Authentication",
+      message: "xAI Video generation failed (permission_denied): Team lacks access.",
+    },
+    {
+      body: { status: "failed", error: { code: "service_unavailable", message: "Overloaded." } },
+      tag: "ProviderInternal",
+      message: "xAI Video generation failed (service_unavailable): Overloaded.",
+    },
+    {
+      body: { status: "failed", error: { code: "internal_error", message: "Generation failed." } },
+      tag: "ProviderInternal",
+      message: "xAI Video generation failed (internal_error): Generation failed.",
+    },
+    {
+      body: { status: "failed", error: { code: "constructor", message: "Future code." } },
+      tag: "ProviderInternal",
+      message: "xAI Video generation failed (constructor): Future code.",
+    },
    { body: { status: "expired" }, tag: "InvalidRequest", message: "xAI Video request req_1 expired" },
  ]) {
-    it.effect(`surfaces ${terminal.body.status} generations with the provider body`, () =>
+    it.effect(`surfaces ${terminal.body.error?.code ?? terminal.body.status} generations with the provider body`, () =>
      Effect.gen(function* () {
        const error = yield* Video.generate({ model, prompt: "x" }).pipe(Effect.flip)
        expect(error.reason._tag).toBe(terminal.tag)
@@ -542,6 +580,45 @@ describe("Video / fal", () => {
    ),
  )

+  for (const failure of [
+    {
+      name: "a COMPLETED status carrying an error",
+      status: { status: "COMPLETED", error: "Invalid input", error_type: "ValidationError" },
+      result: { status: 422, body: { detail: [{ loc: ["body", "prompt"], msg: "Invalid input" }] } },
+      tag: "InvalidRequest",
+    },
+    {
+      name: "a failing response_url",
+      status: { status: "COMPLETED" },
+      result: { status: 500, body: { detail: "Internal error" } },
+      tag: "ProviderInternal",
+    },
+  ]) {
+    it.effect(`fails await for ${failure.name} with the response_url body and HTTP context`, () =>
+      Effect.gen(function* () {
+        // A transient 500 on the result fetch is retried first; the body and HTTP context survive the final failure.
+        const fiber = yield* Effect.forkChild(Video.generate({ model, prompt: "x" }).pipe(Effect.flip))
+        yield* TestClock.adjust("5 minutes")
+        const error = yield* Fiber.join(fiber)
+        expect(error.reason._tag).toBe(failure.tag)
+        expect(error.reason.body).toBe(JSON.stringify(failure.result.body))
+        expect(error.reason.http).toMatchObject({ url: urls.response, status: failure.result.status })
+      }).pipe(
+        Effect.provide(
+          layer((input) =>
+            Effect.succeed(
+              input.request.method === "POST"
+                ? json(input, submitted)
+                : input.request.url === urls.response
+                  ? json(input, failure.result.body, { status: failure.result.status })
+                  : json(input, failure.status),
+            ),
+          ),
+        ),
+      ),
+    )
+  }
+
  it.effect("rejects model-specific common fields and points at providerOptions", () =>
    Effect.gen(function* () {
      const errors = yield* Effect.forEach(
@@ -729,6 +806,11 @@ describe("Video / Runway", () => {
      tag: "ProviderInternal",
      message: "Runway task failed (INTERNAL.BAD_OUTPUT.CODE01): Something broke",
    },
+    {
+      body: { status: "FAILED", failure: "Unsupported dimensions", failureCode: "ASSET.INVALID" },
+      tag: "InvalidRequest",
+      message: "Runway task failed (ASSET.INVALID): Unsupported dimensions",
+    },
    { body: { status: "CANCELLED" }, tag: "InvalidRequest", message: "Runway task task_1 was cancelled" },
  ]) {
    it.effect(`surfaces ${terminal.body.failureCode ?? terminal.body.status} with the task body`, () =>
@@ -818,6 +900,39 @@ describe("Video / Runway", () => {
    }),
  )

+  it.effect("streams the observations of a failed task and then fails with the task body", () =>
+    Effect.gen(function* () {
+      const calls: Array<Call> = []
+      const events: Array<VideoEvent> = []
+      const failed = { status: "FAILED", failure: "Something broke", failureCode: "INTERNAL.BAD_OUTPUT.CODE01" }
+      const program = Video.stream({ model, prompt: "x" }, { poll: { interval: "1 second" } }).pipe(
+        Stream.runForEach((event) => Effect.sync(() => events.push(event))),
+        Effect.flip,
+      )
+      const error = yield* settle(program, 3).pipe(
+        Effect.provide(
+          layer((input) =>
+            Effect.gen(function* () {
+              const { call, nth } = yield* observe(calls, input)
+              if (call.method === "POST") return json(input, { id: "task_1" })
+              if (nth === 1) return json(input, { status: "PENDING" })
+              if (nth === 2) return json(input, { status: "RUNNING", progress: 0.5 })
+              return json(input, failed)
+            }),
+          ),
+        ),
+      )
+      expect(events).toEqual([
+        { type: "generation-queued", id: "task_1", position: undefined },
+        { type: "generation-progress", id: "task_1", progress: 0.5 },
+      ])
+      expect(error.reason._tag).toBe("ProviderInternal")
+      expect(error.message).toBe("Runway task failed (INTERNAL.BAD_OUTPUT.CODE01): Something broke")
+      expect(error.reason.body).toBe(JSON.stringify(failed))
+      expect(error.reason.http?.status).toBe(200)
+    }),
+  )
+
  it.effect("fails a stream with a Timeout reason once polling passes the poll deadline", () =>
    Effect.gen(function* () {
      const program = Video.stream(
@@ -839,6 +954,169 @@ describe("Video / Runway", () => {
  )
 })

+// ---------------------------------------------------------------------------
+// Transient read failures
+// ---------------------------------------------------------------------------
+
+describe("Video / transient read failures", () => {
+  const model = Runway.configure({ apiKey: "test", baseURL: "https://runway.test/v1" }).video("gen4.5")
+  const succeeded = { id: "task_1", status: "SUCCEEDED", output: ["https://runway.test/out.mp4"] }
+  const failure = (input: HandlerInput, status: number, headers?: Record<string, string>) =>
+    json(input, { error: `HTTP ${status}` }, { status, headers })
+  const methods = (calls: ReadonlyArray<Call>) => calls.map((call) => call.method)
+
+  it.effect("retries a 503 status poll and a 503 result read, then returns the result", () =>
+    Effect.gen(function* () {
+      const calls: Array<Call> = []
+      const response = yield* settle(
+        Video.generate({ model, prompt: "x" }, { poll: { interval: "1 second" } }),
+        5,
+      ).pipe(
+        Effect.provide(
+          layer((input) =>
+            Effect.gen(function* () {
+              const { call, nth } = yield* observe(calls, input)
+              if (call.method === "POST") return json(input, { id: "task_1" })
+              // 1: status fails, 2: status succeeds, 3: result fails, 4: result succeeds.
+              if (nth === 1 || nth === 3) return failure(input, 503)
+              return json(input, succeeded)
+            }),
+          ),
+        ),
+      )
+      expect(response.video.source).toMatchObject({ type: "url", url: "https://runway.test/out.mp4" })
+      expect(methods(calls)).toEqual(["POST", "GET", "GET", "GET", "GET"])
+    }),
+  )
+
+  it.effect("waits for a 429 retry-after before polling again", () =>
+    Effect.gen(function* () {
+      const calls: Array<Call> = []
+      const fiber = yield* Effect.forkChild(
+        Video.generate({ model, prompt: "x" }, { poll: { interval: "1 second" } }).pipe(
+          Effect.provide(
+            layer((input) =>
+              Effect.gen(function* () {
+                const { call, nth } = yield* observe(calls, input)
+                if (call.method === "POST") return json(input, { id: "task_1" })
+                if (nth === 1) return failure(input, 429, { "retry-after": "10" })
+                return json(input, succeeded)
+              }),
+            ),
+          ),
+        ),
+      )
+      yield* TestClock.adjust("9 seconds")
+      expect(methods(calls)).toEqual(["POST", "GET"])
+      yield* TestClock.adjust("1 second")
+      yield* Fiber.join(fiber)
+      expect(methods(calls)).toEqual(["POST", "GET", "GET", "GET"])
+    }),
+  )
+
+  it.effect("fails a 400 status poll without retrying", () =>
+    Effect.gen(function* () {
+      const calls: Array<Call> = []
+      const error = yield* Video.generate({ model, prompt: "x" }).pipe(
+        Effect.flip,
+        Effect.provide(
+          layer((input) =>
+            Effect.gen(function* () {
+              const { call } = yield* observe(calls, input)
+              return call.method === "POST" ? json(input, { id: "task_1" }) : failure(input, 400)
+            }),
+          ),
+        ),
+      )
+      expect(error.reason._tag).toBe("InvalidRequest")
+      expect(methods(calls)).toEqual(["POST", "GET"])
+    }),
+  )
+
+  it.effect("stops retrying at poll.timeout with a Timeout reason", () =>
+    Effect.gen(function* () {
+      const calls: Array<Call> = []
+      const error = yield* settle(
+        Video.generate({ model, prompt: "x" }, { poll: { interval: "1 second", timeout: "5 seconds" } }).pipe(
+          Effect.flip,
+        ),
+        6,
+      ).pipe(
+        Effect.provide(
+          layer((input) =>
+            Effect.gen(function* () {
+              const { call } = yield* observe(calls, input)
+              return call.method === "POST" ? json(input, { id: "task_1" }) : failure(input, 503)
+            }),
+          ),
+        ),
+      )
+      expect(error.reason._tag).toBe("Timeout")
+      expect(calls.filter((call) => call.method === "GET").length).toBeGreaterThan(1)
+    }),
+  )
+
+  it.effect("bounds a streamed result read's retries by poll.timeout", () =>
+    Effect.gen(function* () {
+      const calls: Array<Call> = []
+      const error = yield* settle(
+        Video.stream({ model, prompt: "x" }, { poll: { interval: "1 second", timeout: "5 seconds" } }).pipe(
+          Stream.runCollect,
+          Effect.flip,
+        ),
+        6,
+      ).pipe(
+        Effect.provide(
+          layer((input) =>
+            Effect.gen(function* () {
+              const { call, nth } = yield* observe(calls, input)
+              if (call.method === "POST") return json(input, { id: "task_1" })
+              return nth === 1 ? json(input, succeeded) : failure(input, 503)
+            }),
+          ),
+        ),
+      )
+      expect(error.reason._tag).toBe("Timeout")
+      expect(calls.filter((call) => call.method === "GET").length).toBeGreaterThan(2)
+    }),
+  )
+
+  it.effect("never retries a failed submit", () =>
+    Effect.gen(function* () {
+      const calls: Array<Call> = []
+      const error = yield* Video.generate({ model, prompt: "x" }).pipe(
+        Effect.flip,
+        Effect.provide(layer((input) => observe(calls, input).pipe(Effect.map(() => failure(input, 503))))),
+      )
+      expect(error.reason._tag).toBe("ProviderInternal")
+      expect(methods(calls)).toEqual(["POST"])
+    }),
+  )
+
+  it.effect("never retries a failed cancel", () =>
+    Effect.gen(function* () {
+      const calls: Array<Call> = []
+      const error = yield* Effect.gen(function* () {
+        const generation = yield* Video.start({ model, prompt: "x" })
+        return yield* generation.cancel().pipe(Effect.flip)
+      }).pipe(
+        Effect.provide(
+          layer((input) =>
+            Effect.gen(function* () {
+              const { call } = yield* observe(calls, input)
+              if (call.method === "POST") return json(input, { id: "task_1" })
+              if (call.method === "DELETE") return failure(input, 503)
+              return json(input, { id: "task_1", status: "RUNNING" })
+            }),
+          ),
+        ),
+      )
+      expect(error.reason._tag).toBe("ProviderInternal")
+      expect(methods(calls)).toEqual(["POST", "GET", "DELETE"])
+    }),
+  )
+})
+
 // ---------------------------------------------------------------------------
 // Shared queued behavior
 // ---------------------------------------------------------------------------
@@ -878,6 +1156,123 @@ describe("Video / queued result", () => {
    )
  }

+  const veoOperation = "models/veo-3.1/operations/op_1"
+  const falURLs = {
+    status: "https://queue.fal.test/fal-ai/veo3.1/requests/r1/status",
+    response: "https://queue.fal.test/fal-ai/veo3.1/requests/r1",
+    cancel: "https://queue.fal.test/fal-ai/veo3.1/requests/r1/cancel",
+  }
+  for (const queued of [
+    {
+      model: Google.configure({ apiKey: "test", baseURL: "https://google.test/v1beta" }).video("veo-3.1"),
+      submitted: { name: veoOperation },
+      token: { operation: veoOperation },
+      submitURL: "https://google.test/v1beta/models/veo-3.1:predictLongRunning",
+      statusURL: `https://google.test/v1beta/${veoOperation}`,
+      resultURL: `https://google.test/v1beta/${veoOperation}`,
+      running: { name: veoOperation, done: false },
+      done: {
+        name: veoOperation,
+        done: true,
+        response: { generateVideoResponse: { generatedSamples: [{ video: { uri: "https://google.test/out.mp4" } }] } },
+      },
+      result: undefined,
+      url: "https://google.test/out.mp4",
+    },
+    {
+      model: XAI.configure({ apiKey: "test", baseURL: "https://xai.test/v1" }).video("grok-imagine-video-1.5"),
+      submitted: { request_id: "req_1" },
+      token: { requestID: "req_1" },
+      submitURL: "https://xai.test/v1/videos/generations",
+      statusURL: "https://xai.test/v1/videos/req_1",
+      resultURL: "https://xai.test/v1/videos/req_1",
+      running: { status: "pending", progress: 40 },
+      done: { status: "done", video: { url: "https://vidgen.x.ai/out.mp4", respect_moderation: true } },
+      result: undefined,
+      url: "https://vidgen.x.ai/out.mp4",
+    },
+    {
+      model: Fal.configure({ apiKey: "test", baseURL: "https://queue.fal.test" }).video("fal-ai/veo3.1"),
+      submitted: {
+        request_id: "r1",
+        status_url: falURLs.status,
+        response_url: falURLs.response,
+        cancel_url: falURLs.cancel,
+      },
+      token: { requestID: "r1", statusURL: falURLs.status, responseURL: falURLs.response, cancelURL: falURLs.cancel },
+      submitURL: "https://queue.fal.test/fal-ai/veo3.1",
+      statusURL: falURLs.status,
+      resultURL: falURLs.response,
+      running: { status: "IN_PROGRESS" },
+      done: { status: "COMPLETED" },
+      result: { video: { url: "https://v3.fal.media/out.mp4" } },
+      url: "https://v3.fal.media/out.mp4",
+    },
+  ]) {
+    it.effect(`resumes a ${queued.model.provider} generation from a JSON round-tripped token`, () =>
+      Effect.gen(function* () {
+        const calls: Array<Call> = []
+        const response = yield* Effect.gen(function* () {
+          const started = yield* Video.start({ model: queued.model, prompt: "x" })
+          const resumed = yield* Video.resume(queued.model, JSON.parse(JSON.stringify(started.token)))
+          expect(resumed.status).toBe("running")
+          expect(resumed.token).toEqual(queued.token)
+          return yield* resumed.await()
+        }).pipe(
+          Effect.provide(
+            layer((input) =>
+              Effect.gen(function* () {
+                const { call, nth } = yield* observe(calls, input)
+                if (call.method === "POST") return json(input, queued.submitted)
+                if (call.url === queued.resultURL && queued.result !== undefined) return json(input, queued.result)
+                return json(input, nth === 1 ? queued.running : queued.done)
+              }),
+            ),
+          ),
+        )
+        expect(response.video.source).toEqual(expect.objectContaining({ type: "url", url: queued.url }))
+        expect(calls.map((call) => `${call.method} ${call.url}`)).toEqual([
+          `POST ${queued.submitURL}`,
+          `GET ${queued.statusURL}`,
+          `GET ${queued.statusURL}`,
+          `GET ${queued.resultURL}`,
+        ])
+      }),
+    )
+  }
+
+  for (const queued of [
+    {
+      model: Google.configure({ apiKey: "test", baseURL: "https://google.test/v1beta" }).video("veo-3.1"),
+      submitted: { name: veoOperation },
+    },
+    {
+      model: XAI.configure({ apiKey: "test", baseURL: "https://xai.test/v1" }).video("grok-imagine-video-1.5"),
+      submitted: { request_id: "req_1" },
+    },
+  ]) {
+    it.effect(`cancels a ${queued.model.provider} generation without sending a request`, () =>
+      Effect.gen(function* () {
+        const calls: Array<Call> = []
+        yield* Effect.gen(function* () {
+          const generation = yield* Video.start({ model: queued.model, prompt: "x" })
+          yield* generation.cancel()
+        }).pipe(
+          Effect.provide(
+            layer((input) =>
+              Effect.gen(function* () {
+                const { call } = yield* observe(calls, input)
+                if (call.method !== "POST") return yield* Effect.die(`cancel sent ${call.method} ${call.url}`)
+                return json(input, queued.submitted)
+              }),
+            ),
+          ),
+        )
+        expect(calls.map((call) => call.method)).toEqual(["POST"])
+      }),
+    )
+  }
+
  it.effect("rejects a status that only matches an inherited property", () =>
    Effect.gen(function* () {
      const error = yield* Video.resume(
@@ -1,6 +1,6 @@
 {
  "name": "@opencode/app",
-  "version": "2.0.18",
+  "version": "2.0.19",
  "description": "",
  "type": "module",
  "exports": {
@@ -1,7 +1,7 @@
 {
  "$schema": "https://json.schemastore.org/package.json",
  "name": "@opencode/cli",
-  "version": "2.0.18",
+  "version": "2.0.19",
  "type": "module",
  "license": "MIT",
  "bin": {
@@ -51,7 +51,7 @@ const Root = Spec.make(typeof OPENCODE_CLI_NAME === "string" ? OPENCODE_CLI_NAME
    ),
    session: Flag.string("session").pipe(
      Flag.withAlias("s"),
-      Flag.withDescription("Session ID to continue"),
+      Flag.withDescription("Session ID to continue, or to create if it does not exist"),
      Flag.optional,
    ),
    prompt: Flag.string("prompt").pipe(Flag.withDescription("Prompt to use"), Flag.optional),
@@ -328,7 +328,7 @@ const Root = Spec.make(typeof OPENCODE_CLI_NAME === "string" ? OPENCODE_CLI_NAME
        ),
        session: Flag.string("session").pipe(
          Flag.withAlias("s"),
-          Flag.withDescription("Session ID to continue"),
+          Flag.withDescription("Session ID to continue, or to create if it does not exist"),
          Flag.optional,
        ),
        fork: Flag.boolean("fork").pipe(
@@ -368,7 +368,7 @@ const Root = Spec.make(typeof OPENCODE_CLI_NAME === "string" ? OPENCODE_CLI_NAME
        ),
        session: Flag.string("session").pipe(
          Flag.withAlias("s"),
-          Flag.withDescription("Session ID to continue"),
+          Flag.withDescription("Session ID to continue, or to create if it does not exist"),
          Flag.optional,
        ),
        fork: Flag.boolean("fork").pipe(
@@ -11,6 +11,10 @@ import { UpdatePreflight } from "../../services/update-preflight"
 import { Npm } from "@opencode/util/npm"
 import { OPENCODE_ARTIFACT, OPENCODE_CHANNEL, OPENCODE_VERSION } from "../../version"
 import { Env } from "../../env"
+import { Service } from "@opencode/client/effect/service"
+import { OpenCode } from "@opencode/client/promise"
+import { findSession } from "../../session-target"
+import { errorMessage } from "../../util/error"

 export default Runtime.handler(Commands, (input) =>
  Effect.gen(function* () {
@@ -46,6 +50,15 @@ export default Runtime.handler(Commands, (input) =>
        Effect.promise(() => preflight.fail("OpenCode update could not start the new background service")),
      ),
    )
+    const session = Option.getOrUndefined(input.session)
+    // A missing --session ID becomes the ID of the session the first prompt creates.
+    const sessionExists =
+      session !== undefined &&
+      (yield* Effect.tryPromise({
+        try: () =>
+          findSession(OpenCode.make({ baseUrl: server.endpoint.url, headers: Service.headers(server.endpoint) }), session),
+        catch: (cause) => new Error(errorMessage(cause)),
+      })) !== undefined
    const updater = yield* Updater.Service
    let installing: string | undefined
    const updateListeners = new Set<(version: string) => void>()
@@ -81,7 +94,8 @@ export default Runtime.handler(Commands, (input) =>
      },
      args: {
        continue: input.continue,
-        sessionID: Option.getOrUndefined(input.session),
+        sessionID: sessionExists ? session : undefined,
+        newSessionID: sessionExists ? undefined : session,
        prompt: Option.getOrUndefined(input.prompt),
        auto: input.auto || input.yolo || input.dangerouslySkipPermissions,
      },
@@ -135,6 +135,7 @@ export async function runNonInteractivePrompt(input: Input) {
  const replyPermission = async (request: { id: string; action: string; resources: ReadonlyArray<string> }) => {
    if (!input.auto) {
      permissionRejected = true
+      if (input.compatibility !== "v1") process.exitCode = 1
      UI.println(
        UI.Style.TEXT_WARNING_BOLD + "!",
        UI.Style.TEXT_NORMAL +
@@ -163,6 +164,7 @@ export async function runNonInteractivePrompt(input: Input) {
      if (!formAlreadySettled(error)) throw error
    }
    formCancelled = true
+    if (input.compatibility !== "v1") process.exitCode = 1
  }

  const consume = async () => {
@@ -493,7 +495,8 @@ export async function runNonInteractivePrompt(input: Input) {
      if (event.type === "session.execution.interrupted") {
        if (input.compatibility === "v1" && (permissionRejected || formCancelled)) return
        if (event.data.reason === "user" && interrupted) process.exitCode = 130
-        if (event.data.reason !== "user" && !emittedError) {
+        // A declined tool call ends the step with an interruption; it was already reported above.
+        if (event.data.reason !== "user" && !emittedError && !permissionRejected && !formCancelled) {
          emittedError = true
          process.exitCode = 1
          const error = { type: "aborted" as const, message: `Session interrupted: ${event.data.reason}` }
@@ -620,7 +623,9 @@ export async function runNonInteractivePrompt(input: Input) {
        UI.error(item.state.error.message)
      }

-      if (message.error && !emittedError) {
+      // A declined tool call ends its step with an interrupted-step error that is
+      // only a consequence of our own rejection; it was already reported above.
+      if (message.error && !emittedError && !permissionRejected && !formCancelled) {
        emittedError = true
        process.exitCode = 1
        if (!emit("error", timestamp, { error: message.error })) UI.error(message.error.message)
@@ -63,6 +63,7 @@ export async function resolveSessionTarget(input: {
    (await input.client.session
      .create(
        {
+          id: input.session,
          agent: prepared.agent,
          model: prepared.model,
          location: { directory: location.directory },
@@ -101,14 +102,11 @@ async function selectSession(input: {
  fork?: boolean
  signal?: AbortSignal
 }) {
-  const explicit = input.session
-    ? await input.client.session.get({ sessionID: input.session }, ...requestOptions(input.signal)).catch((error) => {
-        if (error && typeof error === "object" && "_tag" in error && error._tag === "SessionNotFoundError")
-          return undefined
-        throw error
-      })
-    : undefined
-  if (input.session && !explicit) throw new Error("Session not found")
+  const explicit = input.session ? await findSession(input.client, input.session, input.signal) : undefined
+  if (input.session && !explicit) {
+    if (input.fork) throw new Error("Session not found")
+    return { session: undefined }
+  }
  if (explicit)
    return {
      session: input.fork
@@ -133,6 +131,13 @@ async function selectSession(input: {
  }
 }

+export function findSession(client: OpenCodeClient, sessionID: string, signal?: AbortSignal) {
+  return client.session.get({ sessionID }, ...requestOptions(signal)).catch((error) => {
+    if (error && typeof error === "object" && "_tag" in error && error._tag === "SessionNotFoundError") return undefined
+    throw error
+  })
+}
+
 async function latestSession(
  client: OpenCodeClient,
  location: LocationGetOutput,
@@ -309,6 +309,7 @@ async function capture(input: Parameters<typeof run>[0]) {

 afterEach(() => {
  mock.restore()
+  process.exitCode = 0
 })

 describe("runNonInteractivePrompt", () => {
@@ -433,6 +434,7 @@ describe("runNonInteractivePrompt", () => {
    expect(sdk.form.list).toHaveBeenCalledWith({
      location: { directory: "/work tree" },
    })
+    expect(process.exitCode).toBe(1)
  })

  test("attach mode cancels only session-owned forms", async () => {
@@ -448,6 +450,7 @@ describe("runNonInteractivePrompt", () => {
      { sessionID: "global", formID: "frm_pending_global" },
      expect.anything(),
    )
+    expect(process.exitCode).toBe(1)
  })

  test("V1 JSON output flushes step_start before an unrelated step failure", async () => {
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
nexxeln	8a7a5526a1	fix(ai): support Sonnet 5.5 Messages request shapes	2026-09-29 08:39:07 +00:00
opencode-agent[bot]andrekram1-node	b30c4d00d1	fix(ai): enable explicit caching on more message protocol routes (#51981 ) Co-authored-by: rekram1-node <rekram1-node@users.noreply.github.com>	2026-09-29 00:50:08 -05:00
Aiden Cline	6712cc4c2c	fix(core): turn off Workers AI thinking through the chat template (#52017 )	2026-09-29 00:45:17 -05:00
Aiden Cline	2aaa265cdc	fix(ai): read provider error messages from common body layouts (#52014 )	2026-09-29 00:19:20 -05:00
Luke Parker	ff72659a47	fix(desktop): give isolated dev service a fixed port (#52013 )	2026-09-29 15:09:50 +10:00
Aiden Cline	14af33d53d	fix(ai): show provider error bodies when no message is recognized (#51978 )	2026-09-29 00:06:52 -05:00
Luke Parker	a604b7f773	fix(ui): calm diff word highlights with @pierre/diffs 1.5.1 (#51236 )	2026-09-29 14:58:24 +10:00
Luke Parker	41d4a9c45c	fix(session-ui): render moved notice as a timeline divider (#52009 )	2026-09-29 14:58:13 +10:00
Luke Parker	293d60a89f	chore(desktop): bump electron to 44.4.5 (#52005 )	2026-09-29 14:50:04 +10:00
Aiden Cline	34a8938dc7	fix(ai): bind Bedrock Claude thinking blocks by default (#51959 )	2026-09-28 23:38:20 -05:00
Aiden Cline	36ef6cc216	fix(ai): finalize Bedrock redacted reasoning at block end (#51999 )	2026-09-28 23:37:51 -05:00
opencode	f02c30eb55	sync release versions for v2.0.19	2026-09-29 04:31:02 +00:00
Aiden Cline	ca084b2430	fix(ai): give provider routes distinct IDs (#51976 )	2026-09-28 19:55:06 -05:00
Aiden Cline	3740ec311b	feat(core): align shell tool environment with agent conventions (#51975 )	2026-09-28 19:53:53 -05:00
opencode-agent[bot]andrekram1-node	35bd8ac442	test(core): update xAI variant expectations for Responses (#51977 ) Co-authored-by: rekram1-node <rekram1-node@users.noreply.github.com>	2026-09-28 19:48:35 -05:00
Aiden Cline	1fc05ca590	fix(core): share affinity in provider session headers (#51931 )	2026-09-28 19:30:24 -05:00
Aiden Cline	bda798b167	fix(core): drop session ID and order instructions for prompt-cache reuse (#51960 )	2026-09-28 19:29:28 -05:00
Aiden Cline	3babae35c0	fix(core): fall back to Cloudflare environment IDs when not configured (#51963 )	2026-09-28 19:28:03 -05:00
Aiden Cline	3ab5c1433c	fix(core): request xAI reasoning summaries on Responses variants (#51964 )	2026-09-28 19:11:48 -05:00
Aiden Cline	49437a25b1	fix(ai): classify invalid Google API keys as authentication errors (#51950 )	2026-09-28 18:49:29 -05:00
Aiden Cline	49403a554f	feat(core): cap requested output tokens at 256k (#51962 )	2026-09-28 18:49:05 -05:00
opencode-agent[bot]andrekram1-node	87d6f93409	test(cli): isolate run exit codes between tests (#51955 ) Co-authored-by: rekram1-node <rekram1-node@users.noreply.github.com>	2026-09-28 19:16:01 -04:00
Frank	97d4eaa2ba	zen: jev privacy policy	2026-09-28 19:01:46 -04:00
Kit Langton	7827dbe396	fix(tui): deduplicate projects in the open picker (#51924 )	2026-09-28 18:13:00 -04:00
James Long	5f9ced439b	fix(cli): drop misleading interruption errors after declined prompts in run (#51948 )	2026-09-28 17:58:04 -04:00
Aiden Cline	8c1ce954d0	fix(tui): wait for agent and model before auto-submitting --prompt (#51938 )	2026-09-28 15:41:14 -05:00
ARH Alireza Haghdoost Claude Opus 5.5 Aiden Cline	07338c5d48	feat(cli): create the session when --session names one that does not exist (#51405 ) Co-authored-by: Alireza Haghdoost <haghdoost@uber.com> Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Co-authored-by: Aiden Cline <aidenpcline@gmail.com>	2026-09-28 15:09:03 -05:00
James Long	46e53e3f2b	fix(ai): expose evaluation confidence (#51930 )	2026-09-28 15:24:21 -04:00
Aiden Cline	6cf442b545	fix(core): share child session affinity headers (#51923 )	2026-09-28 13:31:17 -05:00
opencode-agent[bot]andrekram1-node	f20f5b68ee	chore(release): announce V2 releases in Discord (#51880 ) Co-authored-by: rekram1-node <rekram1-node@users.noreply.github.com>	2026-09-28 12:30:55 -05:00
SebastianandOpenCode Agent	96dd9f77a9	fix(core): attribute one-shot generation requests (#48358 ) Co-authored-by: OpenCode Agent <opencode-agent[bot]@users.noreply.github.com>	2026-09-28 11:55:14 -05:00
opencode-agent[bot]	dd786c62af	chore(core): refresh bundled models.dev snapshot	2026-09-28 12:23:50 +00:00
Frank	87c402a124	docs(go): simplify v2 usage limit explanation	2026-09-28 07:39:42 -04:00
Frank	7076a878a4	docs(www): document Go Plus (#51834 )	2026-09-28 07:25:37 -04:00
Frank	45b91eed82	docs(go): sync v2 model list with v1 (#51837 )	2026-09-28 11:23:40 +00:00
Niels Kootstra	39e1ce55bc	fix(core): reject relative path segments in repository hosts (#51577 )	2026-09-28 10:14:35 +05:30
opencode-agent[bot]andrekram1-node	d9f54392ba	fix(tui): distinguish background shell from interrupted command (#51769 ) Co-authored-by: rekram1-node <rekram1-node@users.noreply.github.com>	2026-09-27 23:01:00 -05:00
Aiden Cline	d73396ab3d	fix(ai): preserve Gemini thought signatures on OpenAI Chat tool calls (#51768 )	2026-09-27 22:57:22 -05:00
Jérôme BenoitandTest User	0caae608a2	chore(nix): update nixpkgs for Bun 1.4 (#50221 ) Co-authored-by: Test User <test@test.com>	2026-09-27 21:34:52 -05:00
Kit Langton	96f23508be	refactor(core): remove unused project discovery option (#51729 )	2026-09-27 15:05:46 -07:00
Kit Langton	28bb0a7158	refactor(core): drop forwarding shim modules (#51670 )	2026-09-27 14:47:19 -07:00
DS	3d109828ff	fix(tui): truncate btw question preview (#51713 )	2026-09-27 21:05:20 +02:00
Shoubhit Dash	c0d49f101c	feat(ai): retry transient failures on queued generation reads (#51635 )	2026-09-27 19:47:25 +05:30
Shoubhit Dash	be2446e188	feat(ai): add ElevenLabs Scribe transcription route (#51641 )	2026-09-27 19:34:36 +05:30
Shoubhit Dash	107966eddd	fix(ai): reject and throw with signal.reason on abort (#51633 )	2026-09-27 19:24:45 +05:30
Kit Langton	f5e580cde1	chore(core): remove dead modules and exports (#51667 )	2026-09-27 06:38:43 -07:00
Shoubhit Dash	4428a77acd	fix(ai): classify terminal generation failures by provider error code (#51632 )	2026-09-27 18:44:21 +05:30
opencode-agent[bot]	01eb18144b	chore(core): refresh bundled models.dev snapshot	2026-09-27 12:19:33 +00:00
Shoubhit Dash	01208048dc	test(ai): cover queued media failures, resume, cancel, and transcription sources (#51626 )	2026-09-27 17:43:24 +05:30
Shoubhit Dash	995f76cb63	feat(tui): add last turn source to diff viewer (#51639 )	2026-09-27 17:39:41 +05:30