refactor(core): isolate session MCP registry behind a session view

feat(acp): register MCP servers per session
feat(core): session-scoped MCP servers
2026-10-25 10:00:48 +08:00 · 2026-09-30 20:15:17 +05:30 · 2026-09-30 19:45:26 +05:30 · 2026-09-30 19:45:25 +05:30 · 2026-09-30 09:20:26 -04:00 · 2026-09-30 18:36:56 +05:30
445 changed files with 14679 additions and 4069 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: ${{ !cancelled() && 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 }}
@@ -184,7 +184,7 @@ const table = sqliteTable("session", {
 - Keep `SessionRunner`, model resolution, tool registry, permissions, and filesystem Location-scoped. Omitted `Location.workspaceID` means implicit-local placement; explicit workspace identity remains reserved for future placement semantics.
 - Preserve one explicit `llm.stream(request)` call per Physical Attempt and reload projected history before durable continuation. A logical Step may use generic pre-output retries, one full-context retry after continuation rejection, incomplete-stream continuation, or one overflow-compaction rebuild. Generic retries retain the logical step number and do not consume another agent-step allowance. Do not delegate orchestration to an in-memory tool loop.
 - Keep local Session drains process-local until clustering is implemented. `SessionRunCoordinator` joins explicit same-Session resumes, coalesces prompt wakeups, and allows different Sessions to run concurrently. A write-ahead execution claim marks a process-local busy period for restart recovery: terminal completion, failure, or user interruption releases it, while shutdown interruption and process death preserve it. Startup recovery resumes claimed top-level Sessions with durable per-execution attempt accounting. The claim is a recovery marker, not clustered ownership, fencing, or an exactly-once guarantee.
- Keep native compaction mechanisms out of `SessionCompaction`. Plugins register `native` strategies through the `SessionCompaction` editor that turn a prepared request into a replacement window (the built-in `NativeCompactionPlugin` handles `@opencode/ai` compaction operations); later registrations win. Core owns the provider-mode decision, route provenance, the retry policy, overflow recovery, interruption, usage accounting, and checkpoint persistence.
+- Keep provider-specific native compaction mechanisms in `@opencode/ai` behind `LLMClient.compact`. `SessionCompaction` chooses a summary or native compaction from the model's `compaction` setting and owns route provenance, request shrinking, the retry policy, interruption, usage accounting, and checkpoint persistence.
 - Keep delivery vocabulary explicit. Prompts steer by default. At safe step boundaries, steered compaction takes priority up to the first steered move control; other steers retain enqueue order. At an idle boundary, steers take priority; otherwise exactly one queued item delivers before the runner reevaluates continuation. Inbox items may be cancelled or changed between queue and steer before delivery. Promoting new user input resets the selected agent's step allowance; a batch of steers resets it once.
 - One step is one logical LLM call; its durable record covers only the model-visible span. Do not write "provider turn", and do not use bare "turn" for a single call: "turn" is reserved for the future assistant-turn unit containing all steps from prompt promotion until the session would go idle.
 - Keep event replay ownership separate from clustered Session execution ownership.
@@ -32,7 +32,7 @@
    },
    "packages/ai": {
      "name": "@opencode/ai",
-      "version": "2.0.18",
+      "version": "2.0.20",
      "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": "2.0.20",
      "dependencies": {
        "@corvu/drawer": "catalog:",
        "@dnd-kit/abstract": "0.5.0",
@@ -112,13 +112,14 @@
    },
    "packages/cli": {
      "name": "@opencode/cli",
-      "version": "2.0.18",
+      "version": "2.0.20",
      "bin": {
        "opencode": "./bin/opencode.cjs",
        "opencode2": "./bin/opencode2.cjs",
      },
      "dependencies": {
        "@agentclientprotocol/sdk": "1.2.1",
+        "@clack/core": "1.0.0-alpha.1",
        "@clack/prompts": "1.0.0-alpha.1",
        "@effect/platform-node": "catalog:",
        "@opencode-ai/pty": "0.1.13",
@@ -135,6 +136,7 @@
        "effect": "catalog:",
        "immer": "11.1.4",
        "jsonc-parser": "3.3.1",
+        "picocolors": "1.1.1",
        "solid-js": "catalog:",
        "tree-sitter-bash": "0.25.0",
        "tree-sitter-powershell": "0.25.10",
@@ -176,7 +178,7 @@
    },
    "packages/client": {
      "name": "@opencode/client",
-      "version": "2.0.18",
+      "version": "2.0.20",
      "dependencies": {
        "@opencode/protocol": "workspace:*",
        "@opencode/schema": "workspace:*",
@@ -202,7 +204,7 @@
    },
    "packages/codemode": {
      "name": "@opencode/codemode",
-      "version": "2.0.18",
+      "version": "2.0.20",
      "dependencies": {
        "acorn": "8.15.0",
        "effect": "catalog:",
@@ -215,7 +217,7 @@
    },
    "packages/console/app": {
      "name": "@opencode/console-app",
-      "version": "2.0.18",
+      "version": "2.0.20",
      "dependencies": {
        "@cloudflare/vite-plugin": "1.15.2",
        "@ibm/plex": "6.4.1",
@@ -251,7 +253,7 @@
    },
    "packages/console/core": {
      "name": "@opencode/console-core",
-      "version": "2.0.18",
+      "version": "2.0.20",
      "dependencies": {
        "@aws-sdk/client-sts": "3.782.0",
        "@jsx-email/render": "1.1.1",
@@ -278,7 +280,7 @@
    },
    "packages/console/function": {
      "name": "@opencode/console-function",
-      "version": "2.0.18",
+      "version": "2.0.20",
      "dependencies": {
        "@openauthjs/openauth": "0.0.0-20250322224806",
        "@opencode/console-core": "workspace:*",
@@ -295,7 +297,7 @@
    },
    "packages/console/mail": {
      "name": "@opencode/console-mail",
-      "version": "2.0.18",
+      "version": "2.0.20",
      "dependencies": {
        "@jsx-email/all": "2.2.3",
        "@jsx-email/cli": "1.4.3",
@@ -319,7 +321,7 @@
    },
    "packages/console/support": {
      "name": "@opencode/console-support",
-      "version": "2.0.18",
+      "version": "2.0.20",
      "dependencies": {
        "@cloudflare/vite-plugin": "1.15.2",
        "@opencode/console-core": "workspace:*",
@@ -339,7 +341,7 @@
    },
    "packages/core": {
      "name": "@opencode/core",
-      "version": "2.0.18",
+      "version": "2.0.20",
      "dependencies": {
        "@ai-sdk/cohere": "3.0.27",
        "@ai-sdk/gateway": "3.0.104",
@@ -375,6 +377,7 @@
        "https-proxy-agent": "7.0.6",
        "ignore": "7.0.5",
        "immer": "11.1.4",
+        "jose": "6.0.11",
        "jsonc-parser": "3.3.1",
        "mime-types": "3.0.2",
        "tree-sitter-bash": "0.25.0",
@@ -407,7 +410,7 @@
    },
    "packages/desktop": {
      "name": "@opencode/desktop",
-      "version": "2.0.18",
+      "version": "2.0.20",
      "dependencies": {
        "@zip.js/zip.js": "2.7.62",
        "electron-context-menu": "5.0.0",
@@ -437,7 +440,7 @@
        "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",
@@ -456,7 +459,7 @@
    },
    "packages/enterprise": {
      "name": "@opencode/enterprise",
-      "version": "2.0.18",
+      "version": "2.0.20",
      "dependencies": {
        "@hono/standard-validator": "catalog:",
        "@opencode-ai/sdk": "1.18.21",
@@ -493,7 +496,7 @@
    },
    "packages/function": {
      "name": "@opencode/function",
-      "version": "2.0.18",
+      "version": "2.0.20",
      "dependencies": {
        "@octokit/auth-app": "8.0.1",
        "@octokit/rest": "catalog:",
@@ -509,7 +512,7 @@
    },
    "packages/http-recorder": {
      "name": "@opencode/http-recorder",
-      "version": "2.0.18",
+      "version": "2.0.20",
      "dependencies": {
        "@effect/platform-node-shared": "4.0.0-rc.112",
      },
@@ -528,7 +531,7 @@
    },
    "packages/httpapi-codegen": {
      "name": "@opencode/httpapi-codegen",
-      "version": "2.0.18",
+      "version": "2.0.20",
      "dependencies": {
        "effect": "catalog:",
        "prettier": "3.6.2",
@@ -541,7 +544,7 @@
    },
    "packages/latex": {
      "name": "@opencode/latex",
-      "version": "2.0.18",
+      "version": "2.0.20",
      "dependencies": {
        "@opencode/plugin": "workspace:*",
        "@opentui/core": "catalog:",
@@ -555,7 +558,7 @@
    },
    "packages/merman": {
      "name": "@opencode/merman",
-      "version": "2.0.18",
+      "version": "2.0.20",
      "dependencies": {
        "@opencode/plugin": "workspace:*",
        "@opentui/core": "catalog:",
@@ -570,7 +573,7 @@
    },
    "packages/plugin": {
      "name": "@opencode/plugin",
-      "version": "2.0.18",
+      "version": "2.0.20",
      "dependencies": {
        "@ai-sdk/provider": "3.0.8",
        "@opencode/ai": "workspace:*",
@@ -596,8 +599,8 @@
      },
      "peerDependencies": {
        "@opencode/theme": "workspace:*",
-        "@opentui/core": ">=0.5.12",
-        "@opentui/solid": ">=0.5.12",
+        "@opentui/core": ">=0.5.13",
+        "@opentui/solid": ">=0.5.13",
        "solid-js": ">=1.9.0",
      },
      "optionalPeers": [
@@ -609,7 +612,7 @@
    },
    "packages/plugin-browser": {
      "name": "@opencode/plugin-browser",
-      "version": "2.0.18",
+      "version": "2.0.20",
      "dependencies": {
        "@opencode/plugin": "workspace:*",
        "@opencode/schema": "workspace:*",
@@ -639,7 +642,7 @@
    },
    "packages/protocol": {
      "name": "@opencode/protocol",
-      "version": "2.0.18",
+      "version": "2.0.20",
      "dependencies": {
        "@opencode/schema": "workspace:*",
        "effect": "catalog:",
@@ -654,7 +657,7 @@
    },
    "packages/schema": {
      "name": "@opencode/schema",
-      "version": "2.0.18",
+      "version": "2.0.20",
      "dependencies": {
        "@standard-schema/spec": "catalog:",
        "effect": "catalog:",
@@ -678,7 +681,7 @@
    },
    "packages/sdk": {
      "name": "@opencode/sdk",
-      "version": "2.0.18",
+      "version": "2.0.20",
      "dependencies": {
        "@opencode/client": "workspace:*",
        "@opencode/core": "workspace:*",
@@ -699,7 +702,7 @@
    },
    "packages/server": {
      "name": "@opencode/server",
-      "version": "2.0.18",
+      "version": "2.0.20",
      "dependencies": {
        "@effect/platform-node": "catalog:",
        "@effect/platform-node-shared": "catalog:",
@@ -721,7 +724,7 @@
    },
    "packages/session-ui": {
      "name": "@opencode/session-ui",
-      "version": "2.0.18",
+      "version": "2.0.20",
      "dependencies": {
        "@kobalte/core": "catalog:",
        "@opencode/client": "workspace:*",
@@ -756,7 +759,7 @@
    },
    "packages/simulation": {
      "name": "@opencode/simulation",
-      "version": "2.0.18",
+      "version": "2.0.20",
      "dependencies": {
        "@opencode/ai": "workspace:*",
        "@opencode/core": "workspace:*",
@@ -776,7 +779,7 @@
    },
    "packages/stats/app": {
      "name": "@opencode/stats-app",
-      "version": "2.0.18",
+      "version": "2.0.20",
      "dependencies": {
        "@ibm/plex": "6.4.1",
        "@kobalte/core": "catalog:",
@@ -810,7 +813,7 @@
    },
    "packages/stats/core": {
      "name": "@opencode/stats-core",
-      "version": "2.0.18",
+      "version": "2.0.20",
      "dependencies": {
        "@aws-sdk/client-athena": "3.933.0",
        "@planetscale/database": "1.19.0",
@@ -829,7 +832,7 @@
    },
    "packages/stats/server": {
      "name": "@opencode/stats-server",
-      "version": "2.0.18",
+      "version": "2.0.20",
      "dependencies": {
        "@aws-sdk/client-firehose": "3.933.0",
        "@effect/platform-node": "catalog:",
@@ -875,7 +878,7 @@
    },
    "packages/theme": {
      "name": "@opencode/theme",
-      "version": "2.0.18",
+      "version": "2.0.20",
      "dependencies": {
        "@opentui/core": "catalog:",
        "effect": "catalog:",
@@ -889,7 +892,7 @@
    },
    "packages/tui": {
      "name": "@opencode/tui",
-      "version": "2.0.18",
+      "version": "2.0.20",
      "dependencies": {
        "@opencode/client": "workspace:*",
        "@opencode/core": "workspace:*",
@@ -923,7 +926,7 @@
    },
    "packages/ui": {
      "name": "@opencode/ui",
-      "version": "2.0.18",
+      "version": "2.0.20",
      "dependencies": {
        "@kobalte/core": "catalog:",
        "@pierre/diffs": "catalog:",
@@ -958,7 +961,7 @@
    },
    "packages/util": {
      "name": "@opencode/util",
-      "version": "2.0.18",
+      "version": "2.0.20",
      "dependencies": {
        "@effect/opentelemetry": "catalog:",
        "@effect/platform-node": "catalog:",
@@ -996,7 +999,7 @@
    },
    "packages/web": {
      "name": "@opencode/web",
-      "version": "2.0.18",
+      "version": "2.0.20",
      "dependencies": {
        "@astrojs/cloudflare": "12.6.3",
        "@astrojs/markdown-remark": "6.3.1",
@@ -1037,7 +1040,7 @@
    },
    "services/update": {
      "name": "@opencode/update",
-      "version": "2.0.18",
+      "version": "2.0.20",
      "dependencies": {
        "jose": "6.0.11",
        "semver": "catalog:",
@@ -1114,10 +1117,10 @@
    "@npmcli/arborist": "9.4.0",
    "@octokit/rest": "22.0.0",
    "@openauthjs/openauth": "0.0.0-20250322224806",
-    "@opentui/core": "0.5.12",
-    "@opentui/keymap": "0.5.12",
-    "@opentui/solid": "0.5.12",
-    "@pierre/diffs": "1.2.10",
+    "@opentui/core": "0.5.13",
+    "@opentui/keymap": "0.5.13",
+    "@opentui/solid": "0.5.13",
+    "@pierre/diffs": "1.5.1",
    "@playwright/test": "1.59.1",
    "@sentry/solid": "10.71.0",
    "@sentry/vite-plugin": "5.4.0",
@@ -2252,27 +2255,25 @@

    "@opentelemetry/semantic-conventions": ["@opentelemetry/semantic-conventions@1.43.0", "", {}, "sha512-eSYWTm620tTk45EKSedaUL8MFYI8hW164hIXsgIHyxu3VobUB3fFCu5t0hQby6OoWRPsG1KkKUG2M5UadiLiVg=="],

-    "@opentui/core": ["@opentui/core@0.5.12", "", { "dependencies": { "bun-ffi-structs": "0.3.1", "diff": "9.0.0", "marked": "17.0.1", "string-width": "7.2.0", "strip-ansi": "7.1.2" }, "optionalDependencies": { "@opentui/core-darwin-arm64": "0.5.12", "@opentui/core-darwin-x64": "0.5.12", "@opentui/core-linux-arm64": "0.5.12", "@opentui/core-linux-arm64-musl": "0.5.12", "@opentui/core-linux-x64": "0.5.12", "@opentui/core-linux-x64-musl": "0.5.12", "@opentui/core-win32-arm64": "0.5.12", "@opentui/core-win32-x64": "0.5.12" }, "peerDependencies": { "web-tree-sitter": "0.25.10" } }, "sha512-ZXBE5gmvdovmV8zJQrOQf6E44v1tJRDEgrM2MYhEglzgXZ+smIUp95O8zeRYGsuIzQIiMPMgQqKtTJuzvAb7BQ=="],
+    "@opentui/core": ["@opentui/core@0.5.13", "", { "dependencies": { "bun-ffi-structs": "0.3.1", "diff": "9.0.0", "marked": "17.0.1", "string-width": "7.2.0", "strip-ansi": "7.1.2" }, "optionalDependencies": { "@opentui/core-darwin-arm64": "0.5.13", "@opentui/core-darwin-x64": "0.5.13", "@opentui/core-linux-arm64": "0.5.13", "@opentui/core-linux-arm64-musl": "0.5.13", "@opentui/core-linux-x64": "0.5.13", "@opentui/core-linux-x64-musl": "0.5.13", "@opentui/core-win32-arm64": "0.5.13", "@opentui/core-win32-x64": "0.5.13" }, "peerDependencies": { "web-tree-sitter": "0.25.10" } }, "sha512-3XNXJx3J9I+Ce170oh7GJ3leBZZA7QYv4OAhwiMCPQtKMkhy3Wra99NM26HXcEGme0zjkkJLownwLLnxuc0U/Q=="],

-    "@opentui/core-darwin-arm64": ["@opentui/core-darwin-arm64@0.5.12", "", { "os": "darwin", "cpu": "arm64" }, "sha512-YdVnP0tAyerBNl0mIcmQEOotPeZzW1VnSXKBl5cyZ5e6nDd2Y+ui/8eRPpn1oqcamf1NCnzS4ohMgejOvna8Zg=="],
+    "@opentui/core-darwin-arm64": ["@opentui/core-darwin-arm64@0.5.13", "", { "os": "darwin", "cpu": "arm64" }, "sha512-5X9U2v5qn4+vKj31zpn0RMoBV3Q9ttdM4t5KN41NPg6XgtIOZgKwox5yOsvBaiQ1KGbuk5wMvXCxfWJ30Mj/nw=="],

-    "@opentui/core-darwin-x64": ["@opentui/core-darwin-x64@0.5.12", "", { "os": "darwin", "cpu": "x64" }, "sha512-uRrQJdHmLUSj3PV23QPi3WSimYTTxcXnVouxF6U4xMXlOv4N3SxnHfVwMRQkPqbGOfvVWHeLE6FdK4C+ubU0sQ=="],
+    "@opentui/core-darwin-x64": ["@opentui/core-darwin-x64@0.5.13", "", { "os": "darwin", "cpu": "x64" }, "sha512-9IgQHLKSn3quVsU0gibkRjOPegv1QH4573KWYXQNDmSxBXw84Nd1mDNsbK9f72SblAILhOCYK685pmk3X/z0Ig=="],

-    "@opentui/core-linux-arm64": ["@opentui/core-linux-arm64@0.5.12", "", { "os": "linux", "cpu": "arm64" }, "sha512-XeKhuIaEtgipvuPHbl4qPOBj+Ut+2zObmsxMVM1jDcjz/FatG9PGeGQPx1G1SnvH2AgpT4K+eCu7DUF0+yIqoQ=="],
+    "@opentui/core-linux-arm64": ["@opentui/core-linux-arm64@0.5.13", "", { "os": "linux", "cpu": "arm64" }, "sha512-jMXGEpB/2Ch/IR0QzYBM5eCr1tUzicxoTP1AbMCbOduJXcGRCHTWqIdQIgRErwPF92gBcDIs4JugSn/Jd0Ki7g=="],

-    "@opentui/core-linux-arm64-musl": ["@opentui/core-linux-arm64-musl@0.5.12", "", { "os": "linux", "cpu": "arm64" }, "sha512-VZ2sNMw1d/r1SLPjUbOP9LKscKz1CQjID8adTL6gG8Lrrq+mYcIUxutyB+P/eG0J/7oRZLPR6OMt7dUOap6RTg=="],
+    "@opentui/core-linux-x64": ["@opentui/core-linux-x64@0.5.13", "", { "os": "linux", "cpu": "x64" }, "sha512-7ytcKy7pQxvQer3PADGYNK+HRhSDyhZvp475GRBEhlBJIdhdL8PNU6hjd2R1dnieifiW7Mpc4EiC1kGKe69gYg=="],

-    "@opentui/core-linux-x64": ["@opentui/core-linux-x64@0.5.12", "", { "os": "linux", "cpu": "x64" }, "sha512-eZiCjEzwbb6qClPPfk32Nha9xmr9obt69Xj0+9SKsXxWLBKkjQEGOMRoh/R9ObaQF4aq8If1xV3VEY0sD9W9vg=="],
+    "@opentui/core-linux-x64-musl": ["@opentui/core-linux-x64-musl@0.5.13", "", { "os": "linux", "cpu": "x64" }, "sha512-C2ZC7WA7YH/GS+rJnbeVGe6Kxeor0aTD2qcS6l32KmN4XuY7TXm192XJMfxxnKaTA6oKp3mW27ezolJKUcGtMw=="],

-    "@opentui/core-linux-x64-musl": ["@opentui/core-linux-x64-musl@0.5.12", "", { "os": "linux", "cpu": "x64" }, "sha512-WWW0hVBoSYZ3D6AgZ4u2Y5/u/IyIq2pDb+4yI3WgJ70Wyt6ofHy+6kRGRgbXFn1p+rPInAHjCXD2v6C7iEKSrA=="],
+    "@opentui/core-win32-arm64": ["@opentui/core-win32-arm64@0.5.13", "", { "os": "win32", "cpu": "arm64" }, "sha512-IB6eLh6I/gYXrJ0AYxZpD+Dr+yfZJck0ZfLnIapbD+fykaT0umOtvc/BL+CtlC/aSc7jpe0q4eXdn6XIA8HtLw=="],

-    "@opentui/core-win32-arm64": ["@opentui/core-win32-arm64@0.5.12", "", { "os": "win32", "cpu": "arm64" }, "sha512-aLbm6870Ybls6CYL4zMOCImTBPLZHZMUXJFGqMI44lIWxitkAtT6zg5lYA4oRqFRzzryDclxr29+hDgT3p3Blw=="],
+    "@opentui/core-win32-x64": ["@opentui/core-win32-x64@0.5.13", "", { "os": "win32", "cpu": "x64" }, "sha512-FCucDN8A4iFDPdwqLK99ISs42pcbcObkxhN1jtsnmcYM9/Ptron7Hhapx2ObQWYjSrJNnntmfZQd2ewpE8YqTQ=="],

-    "@opentui/core-win32-x64": ["@opentui/core-win32-x64@0.5.12", "", { "os": "win32", "cpu": "x64" }, "sha512-KTwtwpfd2zF9opVh3SyRJYDd1o3Xv4XL8OZb8Zi+CqWUel6Y2IDCiVivCv8fGJt3J7wOIXXtuZI9ZUkLyKJCiQ=="],
+    "@opentui/keymap": ["@opentui/keymap@0.5.13", "", { "dependencies": { "@opentui/core": "0.5.13" }, "peerDependencies": { "@opentui/react": "0.5.13", "@opentui/solid": "0.5.13", "react": ">=19.2.0", "solid-js": "1.9.12" }, "optionalPeers": ["@opentui/react", "@opentui/solid", "react", "solid-js"] }, "sha512-bbpQ5N8000CuvVDhptGuHxUE92sivChjUjLkvYT1VnLlDTiGbQ4mPsHfnqsaEokc7O7jBcoJXJQsLxw7rO/qkg=="],

-    "@opentui/keymap": ["@opentui/keymap@0.5.12", "", { "dependencies": { "@opentui/core": "0.5.12" }, "peerDependencies": { "@opentui/react": "0.5.12", "@opentui/solid": "0.5.12", "react": ">=19.2.0", "solid-js": "1.9.12" }, "optionalPeers": ["@opentui/react", "@opentui/solid", "react", "solid-js"] }, "sha512-yWPvJjRhJTRoRSUucQq9Ua8ZW7n/2YQ/j6JxWq5Qekm4WuFiTplEkebR/Aj2/xA8tX68NOE5qv1LrY0Jk3NLNQ=="],
-
-    "@opentui/solid": ["@opentui/solid@0.5.12", "", { "dependencies": { "@babel/core": "7.28.0", "@babel/preset-typescript": "7.27.1", "@opentui/core": "0.5.12", "babel-plugin-module-resolver": "5.0.2", "babel-preset-solid": "1.9.12", "entities": "7.0.1", "s-js": "^0.4.9" }, "peerDependencies": { "solid-js": "1.9.12" } }, "sha512-hAiVlVMtT7AkHGblKwcW1YAuXtxkSy1XSf/RRc4j3IlG3mTNX0bhJdnGOo3Xw14EqeZMp41Mcp5WzHAzMm/DzA=="],
+    "@opentui/solid": ["@opentui/solid@0.5.13", "", { "dependencies": { "@babel/core": "7.28.0", "@babel/preset-typescript": "7.27.1", "@opentui/core": "0.5.13", "babel-plugin-module-resolver": "5.0.2", "babel-preset-solid": "1.9.12", "entities": "7.0.1", "s-js": "^0.4.9" }, "peerDependencies": { "solid-js": "1.9.12" } }, "sha512-MGMYQYeoZNn9uq3zsLPqq/G+nBQXgGwpylsrYux0nJ+C+6oflDEE6t8huSTZaAUizC/3WG8sVSVFutczeRbnPg=="],

    "@oslojs/asn1": ["@oslojs/asn1@1.0.0", "", { "dependencies": { "@oslojs/binary": "1.0.0" } }, "sha512-zw/wn0sj0j0QKbIXfIlnEcTviaCzYOY3V5rAyjR6YtOByFtJiT574+8p9Wlach0lZH9fddD4yb9laEAIl4vXQA=="],

@@ -2528,11 +2529,11 @@

    "@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=="],

@@ -3868,7 +3869,7 @@

    "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=="],

@@ -6256,11 +6257,7 @@

    "@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=="],

@@ -7158,8 +7155,6 @@

    "@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": {
@@ -1,8 +1,8 @@
 {
  "nodeModules": {
-    "x86_64-linux": "sha256-9gJjhes2ueYckAgdeGlPwZcaIDdwB3ZnqK/XHHXhWNs=",
-    "aarch64-linux": "sha256-Sy5YXYM9tKevIITdV++bP35SJNaFCQVKwlNJRbWsD1Q=",
-    "aarch64-darwin": "sha256-wiXHjKXm2VIFvalwITpSiRHaFZEWc8UJIqjQyc/0f0s=",
-    "x86_64-darwin": "sha256-r/mnhdNbnPIJOY3qvtuY6GQ7ed1Nauq65X+8uERhdP8="
+    "x86_64-linux": "sha256-7DgxTpKv6ITKTom0mhlJNPQfdEjtEHK5P8uyCr26HZw=",
+    "aarch64-linux": "sha256-PJxW1Ibfx6oS1neWPSHqzP1Pm1HT9my1TrrHmOb6/no=",
+    "aarch64-darwin": "sha256-VIme5VHfM8JxNiDSOykkr5FytghDLI0FxkhiOXUSyQw=",
+    "x86_64-darwin": "sha256-rQ/j0QkR1vxAq4jgUbr0nY4RDyiLTJqN8q1AfoiEqVQ="
  }
 }
@@ -2,7 +2,7 @@
  "$schema": "https://json.schemastore.org/package.json",
  "name": "opencode",
  "description": "AI-powered development tool",
-  "version": "2.0.18",
+  "version": "2.0.20",
  "private": true,
  "type": "module",
  "packageManager": "bun@1.4.2",
@@ -52,9 +52,9 @@
      "@octokit/rest": "22.0.0",
      "@hono/standard-validator": "0.2.0",
      "@hono/zod-validator": "0.4.2",
-      "@opentui/core": "0.5.12",
-      "@opentui/keymap": "0.5.12",
-      "@opentui/solid": "0.5.12",
+      "@opentui/core": "0.5.13",
+      "@opentui/keymap": "0.5.13",
+      "@opentui/solid": "0.5.13",
      "@tanstack/solid-virtual": "3.13.37",
      "@shikijs/stream": "4.4.3",
      "@standard-schema/spec": "1.1.0",
@@ -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": "2.0.20",
  "name": "@opencode/ai",
  "type": "module",
  "license": "MIT",
@@ -38,12 +38,30 @@ 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",
 ])

+// OpenRouter upstreams other than Anthropic and Alibaba Qwen cache without breakpoints. Gemini uses only the last
+// breakpoint, so a conversation-tail breakpoint writes a new cache every step and costs more than none. Qwen ignores
+// breakpoints on tool definitions and caches tools with the system prompt.
+const openRouterPolicy = (modelID: string): CachePolicyObject => {
+  // `~anthropic/claude-sonnet-latest` style IDs are OpenRouter aliases for the latest model in a family.
+  const id = modelID.replace(/^~/, "")
+  if (id.startsWith("anthropic/")) return AUTO
+  if (id.startsWith("qwen/")) return { system: true, messages: { tail: 1 } }
+  return NONE
+}
+
 const makeHint = (ttlSeconds: number | undefined): CacheHint =>
  ttlSeconds !== undefined ? new CacheHint({ type: "ephemeral", ttlSeconds }) : new CacheHint({ type: "ephemeral" })

@@ -149,9 +167,10 @@ const countHints = (request: LLMRequest) =>

 export const applyCachePolicy = (request: LLMRequest): LLMRequest => {
  if (!RESPECTS_INLINE_HINTS.has(request.model.route.id)) return request
-  if (request.model.route.id === "openrouter" && (request.cache === undefined || request.cache === "auto"))
-    return request
-  const policy = resolve(request.cache)
+  const policy =
+    request.model.route.id === "openrouter" && (request.cache === undefined || request.cache === "auto")
+      ? openRouterPolicy(request.model.id)
+      : resolve(request.cache)
  if (!policy.tools && !policy.system && !policy.messages) return request

  const hint = makeHint(policy.ttlSeconds)
@@ -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"

@@ -988,22 +989,6 @@ 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
@@ -1652,8 +1637,7 @@ 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 !== "disabled" && 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,
@@ -89,24 +89,32 @@ const fromRequest = Effect.fn("DeepgramSpeech.fromRequest")(function* (request:
 // 6. Stream parsing
 // ---------------------------------------------------------------------------

-const HEADERLESS_ENCODINGS: Readonly<Record<string, SpeechStream.PcmEncoding>> = {
-  linear16: "pcm_s16le",
-  mulaw: "pcm_mulaw",
-  alaw: "pcm_alaw",
+/** Deepgram wraps raw encodings in WAV unless `container` is `none`, and defaults their sample rate per encoding. */
+const HEADERLESS_ENCODINGS: Readonly<
+  Record<string, { readonly encoding: SpeechStream.PcmEncoding; readonly sampleRate: number }>
+> = {
+  linear16: { encoding: "pcm_s16le", sampleRate: 24000 },
+  mulaw: { encoding: "pcm_mulaw", sampleRate: 8000 },
+  alaw: { encoding: "pcm_alaw", sampleRate: 8000 },
 }

 const finish = (state: State, context: MediaProtocol.ResponseContext<Request>) => {
  const headers = context.http.headers
  const mediaType = headers["content-type"]
  const format = audioFormat(context.request)
-  const encoding = HEADERLESS_ENCODINGS[format.encoding ?? ""]
+  const headerless = HEADERLESS_ENCODINGS[format.encoding ?? ""]
+  const container = format.container ?? (headerless === undefined ? undefined : "wav")
  const requestID = headers["dg-request-id"]
  const modelName = headers["dg-model-name"]
  return SpeechStream.finish(route, state, {
-    ...(format.container === "none" && encoding !== undefined
-      ? SpeechStream.pcm(encoding, SpeechStream.sampleRate(mediaType), mediaType)
+    ...(container === "none" && headerless !== undefined
+      ? SpeechStream.pcm(
+          headerless.encoding,
+          SpeechStream.sampleRate(mediaType) ?? context.request.providerOptions?.sampleRate ?? headerless.sampleRate,
+          mediaType,
+        )
      : // Deepgram's default encoding is MP3; WAV is a container around any encoding.
-        { mediaType, info: { format: format.container === "wav" ? "wav" : (format.encoding ?? "mp3") } }),
+        { mediaType, info: { format: container === "wav" ? "wav" : (format.encoding ?? "mp3") } }),
    usage: SpeechStream.headerUsage("characters", headers["dg-char-count"]),
    providerMetadata:
      requestID === undefined && modelName === undefined
@@ -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
@@ -526,19 +526,7 @@ const mapFinishReason = (finishReason: string | undefined, hasToolCalls: boolean
  if (finishReason === undefined) return hasToolCalls ? "tool-calls" : "unknown"
  if (finishReason === "STOP") return hasToolCalls ? "tool-calls" : "stop"
  if (finishReason === "MAX_TOKENS") return "length"
-  if (
-    finishReason === "IMAGE_SAFETY" ||
-    finishReason === "RECITATION" ||
-    finishReason === "SAFETY" ||
-    finishReason === "BLOCKLIST" ||
-    finishReason === "PROHIBITED_CONTENT" ||
-    finishReason === "SPII" ||
-    finishReason === "MODEL_ARMOR" ||
-    finishReason === "IMAGE_PROHIBITED_CONTENT" ||
-    finishReason === "IMAGE_RECITATION" ||
-    finishReason === "LANGUAGE"
-  )
-    return "content-filter"
+  if (GeminiGenerateContent.contentFiltered(finishReason)) return "content-filter"
  if (
    finishReason === "MALFORMED_FUNCTION_CALL" ||
    finishReason === "UNEXPECTED_TOOL_CALL" ||
@@ -102,10 +102,14 @@ const step = Effect.fn("GoogleSpeech.step")(function* (state: State, frame: stri
    part.inlineData === undefined ? [] : [part.inlineData],
  )
  const next: State = { ...GeminiGenerateContent.track(state, chunk), mimeType: state.mimeType ?? audio[0]?.mimeType }
-  return [next, audio.flatMap((part) => SpeechStream.delta(next, part.data)[1])] as const
+  const events = audio.flatMap((part) => SpeechStream.delta(next, part.data)[1])
+  const withheld = next.chunks.length === 0 ? GeminiGenerateContent.withheld(route.name, chunk, frame) : undefined
+  if (withheld !== undefined) return yield* withheld
+  return [next, events] as const
 })

 const finish = (state: State, context: MediaProtocol.ResponseContext<Request>) => {
+  if (state.finishReason === undefined) return Effect.fail(route.incomplete())
  const sampleRate = SpeechStream.sampleRate(state.mimeType) ?? DEFAULT_SAMPLE_RATE
  const output =
    state.mimeType?.split(";")[0]?.toLowerCase() === "audio/wav"
@@ -118,8 +122,9 @@ const finish = (state: State, context: MediaProtocol.ResponseContext<Request>) =
  return SpeechStream.finish(route, state, {
    ...output,
    usage: GeminiGenerateContent.usage(state.usage),
+    notices: GeminiGenerateContent.notices(route.name, state),
    providerMetadata: GeminiGenerateContent.providerMetadata(state),
-    detail: state.finishReason === undefined ? undefined : `finish reason: ${state.finishReason}`,
+    detail: `finish reason: ${state.finishReason}`,
  })
 }

@@ -154,6 +154,9 @@ const step = Effect.fn("GoogleTranscription.step")(function* (state: State, fram
    .filter((item) => item.length > 0)
    .join(" ")
  const delta = text.length === 0 || state.text.length === 0 ? text : ` ${text}`
+  const withheld =
+    state.text.length + delta.length === 0 ? GeminiGenerateContent.withheld(route.name, chunk, frame) : undefined
+  if (withheld !== undefined) return yield* withheld
  const events: ReadonlyArray<TranscriptionEvent> = [
    ...(delta.length === 0 ? [] : [TranscriptionTextDeltaEvent.make({ delta })]),
    ...segments.map((segment) => TranscriptionSegmentEvent.make({ segment })),
@@ -169,6 +172,7 @@ const finish = (state: State) => {
      segments: state.segments.length === 0 ? undefined : state.segments,
      words: state.words.length === 0 ? undefined : state.words,
      usage: GeminiGenerateContent.usage(state.usage),
+      notices: GeminiGenerateContent.notices(route.name, state),
      providerMetadata: GeminiGenerateContent.providerMetadata(state),
    }),
  ])
@@ -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) {
@@ -426,6 +426,7 @@ interface ActiveContent {
  readonly type: "text" | "reasoning"
  readonly id: string
  readonly thinking?: MistralThinkingContent
+  readonly thinkingUnits?: MistralThinkingUnit[]
 }

 export interface ParserState {
@@ -502,8 +503,8 @@ const closeActive = (state: ParserState, events: LLMEvent[]) => {
          state.lifecycle,
          events,
          state.active.id,
-          thinkingMetadata(state.active.thinking ?? { type: "thinking", thinking: [] }),
-          thinkingText(state.active.thinking?.thinking ?? []),
+          thinkingMetadata({ ...state.active.thinking, type: "thinking", thinking: state.active.thinkingUnits ?? [] }),
+          thinkingText(state.active.thinkingUnits ?? []),
        )
  return { ...state, lifecycle, active: undefined }
 }
@@ -524,20 +525,23 @@ const appendThinking = (state: ParserState, events: LLMEvent[], part: MistralOut
  const current = state.active?.type === "reasoning" ? state : closeActive(state, events)
  const units = thinkingUnits(part.thinking)
  const active = current.active ?? { type: "reasoning" as const, id: `reasoning-${current.nextContent}` }
+  // Keep native units out of streamed events until the block is complete.
+  const accumulated = active.thinkingUnits ?? []
+  accumulated.push(...units)
  const thinking = {
    ...active.thinking,
    ...part,
    type: "thinking" as const,
-    thinking: [...(active.thinking?.thinking ?? []), ...units],
+    thinking: [],
  }
  const text = thinkingText(units)
  return {
    ...current,
    lifecycle:
      text.length > 0
-        ? Lifecycle.reasoningDelta(current.lifecycle, events, active.id, text, thinkingMetadata(thinking))
-        : Lifecycle.reasoningStart(current.lifecycle, events, active.id, thinkingMetadata(thinking)),
-    active: { ...active, thinking },
+        ? Lifecycle.reasoningDelta(current.lifecycle, events, active.id, text)
+        : Lifecycle.reasoningStart(current.lifecycle, events, active.id),
+    active: { ...active, thinking, thinkingUnits: accumulated },
    nextContent: current.active ? current.nextContent : current.nextContent + 1,
  }
 }
@@ -20,7 +20,6 @@ import {
  type LLMRequest,
  type MediaPart,
  type ReasoningPart,
-  type TextPart,
  type ToolCallPart,
  type ToolDefinition,
 } from "../schema/index.js"
@@ -45,6 +44,7 @@ const OpenAIChatCacheControl = Schema.Struct({
  type: Schema.Literal("ephemeral"),
  ttl: Schema.optional(Schema.String),
 })
+type OpenAIChatCacheControl = Schema.Schema.Type<typeof OpenAIChatCacheControl>

 const OpenAIChatFunction = Schema.Struct({
  name: Schema.String,
@@ -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>

@@ -112,18 +121,15 @@ 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 OpenAIChatTextContent = Schema.Struct({
+  type: Schema.Literal("text"),
+  text: Schema.String,
+  cache_control: Schema.optional(OpenAIChatCacheControl),
+})
+type OpenAIChatTextContent = Schema.Schema.Type<typeof OpenAIChatTextContent>

 const OpenAIChatUserContent = Schema.Union([
-  Schema.Struct({
-    type: Schema.Literal("text"),
-    text: Schema.String,
-    cache_control: Schema.optional(OpenAIChatCacheControl),
-  }),
+  OpenAIChatTextContent,
  Schema.Struct({
    type: Schema.Literal("image_url"),
    image_url: Schema.Struct({ url: Schema.String }),
@@ -133,6 +139,7 @@ const OpenAIChatUserContent = Schema.Union([
    file: Schema.Struct({ filename: Schema.String, file_data: Schema.String }),
  }),
 ])
+type OpenAIChatUserContent = Schema.Schema.Type<typeof OpenAIChatUserContent>

 const OpenAIChatMessage = Schema.Union([
  Schema.Struct({
@@ -146,21 +153,19 @@ const OpenAIChatMessage = Schema.Union([
  Schema.StructWithRest(
    Schema.Struct({
      role: Schema.Literal("assistant"),
-      content: Schema.NullOr(Schema.String),
+      content: Schema.NullOr(Schema.Union([Schema.String, Schema.Array(OpenAIChatTextContent)])),
      tool_calls: optionalArray(OpenAIChatAssistantToolCall),
      reasoning_content: Schema.optional(Schema.String),
      reasoning: Schema.optional(Schema.String),
      reasoning_text: Schema.optional(Schema.String),
      reasoning_details: Schema.optional(Schema.Unknown),
-      cache_control: Schema.optional(OpenAIChatCacheControl),
    }),
    [Schema.Record(Schema.String, Schema.Unknown)],
  ),
  Schema.Struct({
    role: Schema.Literal("tool"),
    tool_call_id: Schema.String,
-    content: Schema.String,
-    cache_control: Schema.optional(OpenAIChatCacheControl),
+    content: Schema.Union([Schema.String, Schema.Array(OpenAIChatTextContent)]),
  }),
 ]).pipe(Schema.toTaggedUnion("role"))
 type OpenAIChatMessage = Schema.Schema.Type<typeof OpenAIChatMessage>
@@ -242,6 +247,7 @@ 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 +300,7 @@ interface PendingToolDelta {
  readonly id?: string
  readonly name?: string
  readonly input: string
+  readonly extraContent?: Schema.Schema.Type<typeof ExtraContent>
 }

 export interface ParserState {
@@ -322,9 +329,7 @@ export interface ParserState {
 // OpenAI Chat wire format. Keep provider quirks here instead of leaking native
 // fields into `LLMRequest`.
 interface LoweringOptions {
-  readonly cacheControl?: (
-    cache: CacheHint | undefined,
-  ) => Schema.Schema.Type<typeof OpenAIChatCacheControl> | undefined
+  readonly cacheControl?: (cache: CacheHint | undefined) => OpenAIChatCacheControl | undefined
  readonly toolCallID?: (id: string) => string
 }

@@ -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) {
@@ -406,7 +415,7 @@ const lowerUserMessage = Effect.fn("OpenAIChat.lowerUserMessage")(function* (
  message: OpenAIChatRequestMessage,
  options: LoweringOptions,
 ) {
-  const content: Array<Schema.Schema.Type<typeof OpenAIChatUserContent>> = []
+  const content: OpenAIChatUserContent[] = []
  for (const part of message.content) {
    if (part.type === "text") {
      content.push({ type: "text", text: part.text, cache_control: options.cacheControl?.(part.cache) })
@@ -432,14 +441,14 @@ const lowerAssistantMessage = Effect.fn("OpenAIChat.lowerAssistantMessage")(func
  requireReasoning: boolean,
  options: LoweringOptions & { readonly providerMetadataKey: string },
 ) {
-  const content: TextPart[] = []
+  const content: OpenAIChatTextContent[] = []
  const reasoning: ReasoningPart[] = []
  const toolCalls: OpenAIChatAssistantToolCall[] = []
  for (const part of message.content) {
    if (!ProviderShared.supportsContent(part, ["text", "reasoning", "tool-call"]))
      return yield* ProviderShared.unsupportedContent("OpenAI Chat", "assistant", ["text", "reasoning", "tool-call"])
    if (part.type === "text") {
-      content.push(part)
+      content.push({ type: "text", text: part.text, cache_control: options.cacheControl?.(part.cache) })
      continue
    }
    if (part.type === "reasoning") {
@@ -477,14 +486,15 @@ const lowerAssistantMessage = Effect.fn("OpenAIChat.lowerAssistantMessage")(func
    if (reasoning.length === 0) return nativeReasoning ?? (requireReasoning ? "" : undefined)
    return text
  })()
-  const cached = message.content.findLast((part) => "cache" in part && part.cache !== undefined)
-  const cacheControl = options.cacheControl?.(cached && "cache" in cached ? cached.cache : undefined)
  const result = {
    role: "assistant" as const,
-    content: content.length > 0 ? content.map((part) => part.text).join("") : toolCalls.length > 0 ? null : "",
+    content: (() => {
+      if (content.some((part) => part.cache_control !== undefined)) return content
+      if (content.length === 0 && toolCalls.length > 0) return null
+      return content.map((part) => part.text).join("")
+    })(),
    ...(toolCalls.length > 0 ? { tool_calls: toolCalls } : {}),
    ...(details !== undefined ? { reasoning_details: details } : {}),
-    ...(cacheControl !== undefined ? { cache_control: cacheControl } : {}),
  }
  if (field === undefined || reasoningText === undefined) return result
  return { ...result, [field]: reasoningText }
@@ -495,33 +505,38 @@ const lowerToolMessages = Effect.fn("OpenAIChat.lowerToolMessages")(function* (
  options: LoweringOptions,
 ) {
  const messages: OpenAIChatMessage[] = []
-  const attachments: Array<Schema.Schema.Type<typeof OpenAIChatUserContent>> = []
+  const attachments: OpenAIChatUserContent[] = []
  for (const part of message.content) {
    if (!ProviderShared.supportsContent(part, ["tool-result"]))
      return yield* ProviderShared.unsupportedContent("OpenAI Chat", "tool", ["tool-result"])
    if (part.result.type !== "content") {
-      messages.push({
-        role: "tool",
-        tool_call_id: options.toolCallID?.(part.id) ?? part.id,
-        content: ProviderShared.toolResultText(part),
-        cache_control: options.cacheControl?.(part.cache),
-      })
+      messages.push(
+        toolMessage(
+          options.toolCallID?.(part.id) ?? part.id,
+          ProviderShared.toolResultText(part),
+          options.cacheControl?.(part.cache),
+        ),
+      )
      continue
    }
    const content: ReadonlyArray<Tool.Content> = part.result.value
    const text = content.filter((item) => item.type === "text").map((item) => item.text)
-    messages.push({
-      role: "tool",
-      tool_call_id: options.toolCallID?.(part.id) ?? part.id,
-      content: text.join("\n"),
-      cache_control: options.cacheControl?.(part.cache),
-    })
+    messages.push(
+      toolMessage(options.toolCallID?.(part.id) ?? part.id, text.join("\n"), options.cacheControl?.(part.cache)),
+    )
    const files = content.filter((item) => item.type === "file")
    attachments.push(...(yield* Effect.forEach(files, (item) => lowerMedia(ProviderShared.toolFileMedia(item)))))
  }
  return { messages, attachments }
 })

+// Chat cache breakpoints belong on text content parts, not on the message itself.
+const toolMessage = (toolCallID: string, text: string, cacheControl: OpenAIChatCacheControl | undefined) => ({
+  role: "tool" as const,
+  tool_call_id: toolCallID,
+  content: cacheControl === undefined ? text : [{ type: "text" as const, text, cache_control: cacheControl }],
+})
+
 const lowerMessage = Effect.fn("OpenAIChat.lowerMessage")(function* (
  message: OpenAIChatRequestMessage,
  reasoningField: string | undefined,
@@ -580,7 +595,7 @@ const lowerMessages = Effect.fn("OpenAIChat.lowerMessages")(function* (request:
    if (requireAssistantAfterTool && messages.at(-1)?.role === "tool")
      messages.push({ role: "assistant", content: "Done." })
  }
-  const pendingAttachments: Array<Schema.Schema.Type<typeof OpenAIChatUserContent>> = []
+  const pendingAttachments: OpenAIChatUserContent[] = []
  const flushAttachments = () => {
    if (pendingAttachments.length === 0) return
    bridgeTools()
@@ -590,24 +605,25 @@ const lowerMessages = Effect.fn("OpenAIChat.lowerMessages")(function* (request:
    if (message.role === "user") bridgeTools()
    if (message.role === "system") {
      const part = yield* ProviderShared.wrappedSystemUpdate("OpenAI Chat", message)
+      const cacheControl = options.cacheControl?.(part.cache)
      if (pendingAttachments.length > 0) {
        messages.push({
          role: "user",
          content: [
            ...pendingAttachments.splice(0),
-            { type: "text", text: part.text, cache_control: options.cacheControl?.(part.cache) },
+            { type: "text", text: part.text, cache_control: cacheControl },
          ],
        })
        continue
      }
      const previous = messages.at(-1)
      if (previous?.role === "user" && typeof previous.content === "string")
-        messages[messages.length - 1] = options.cacheControl?.(part.cache)
+        messages[messages.length - 1] = cacheControl
          ? {
              role: "user",
              content: [
                { type: "text", text: previous.content },
-                { type: "text", text: part.text, cache_control: options.cacheControl(part.cache) },
+                { type: "text", text: part.text, cache_control: cacheControl },
              ],
            }
          : { role: "user", content: `${previous.content}\n${part.text}` }
@@ -616,15 +632,15 @@ const lowerMessages = Effect.fn("OpenAIChat.lowerMessages")(function* (request:
          role: "user",
          content: [
            ...previous.content,
-            { type: "text", text: part.text, cache_control: options.cacheControl?.(part.cache) },
+            { type: "text", text: part.text, cache_control: cacheControl },
          ],
        }
      else
        messages.push(
-          options.cacheControl?.(part.cache)
+          cacheControl
            ? {
                role: "user",
-                content: [{ type: "text", text: part.text, cache_control: options.cacheControl(part.cache) }],
+                content: [{ type: "text", text: part.text, cache_control: cacheControl }],
              }
            : { role: "user", content: part.text },
        )
@@ -721,7 +737,9 @@ 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 +1132,13 @@ 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 +1150,12 @@ 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))
@@ -60,10 +60,17 @@ interface State extends SpeechStream.Audio {
 // `sse` is not supported for `tts-1` or `tts-1-hd`; those models stream the raw audio body instead.
 const supportsSse = (model: string) => !/^tts-1(-hd)?(-|$)/.test(model)

+const FORMATS = new Set(["mp3", "opus", "aac", "flac", "wav", "pcm"])
+
 const fromRequest = Effect.fn("OpenAISpeech.fromRequest")(function* (request: MediaProtocol.Addressed<Request>) {
  // Not in `unsupported`: that list would also reject `timestamps: false`, which asks for nothing.
  if (request.timestamps === true)
    return yield* route.unsupported("media.timestamps", `${route.name} does not return timestamps`)
+  if (request.format !== undefined && !FORMATS.has(request.format))
+    return yield* route.unsupported(
+      "media.format",
+      `${route.name} supports the mp3, opus, aac, flac, wav, and pcm formats, not "${request.format}"`,
+    )
  return MediaProtocol.json(
    mergeJsonRecords(
      {
@@ -112,7 +119,9 @@ const onEvent = Effect.fn("OpenAISpeech.onEvent")(function* (state: State, frame

 const finish = (state: State, context: MediaProtocol.ResponseContext<Request>) => {
  if (isSse(context.body) && !state.done) return Effect.fail(route.incomplete())
-  const format = context.request.format ?? "mp3"
+  // The sent body reflects `providerOptions` and `http.body` overrides of `format`.
+  const sent = context.body.type === "json" ? context.body.value.response_format : undefined
+  const format = typeof sent === "string" ? sent : "mp3"
  return SpeechStream.finish(route, state, {
    ...(format === "pcm" ? SpeechStream.pcm("pcm_s16le", PCM_SAMPLE_RATE) : SpeechStream.container(format)),
    usage: state.usage,
@@ -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))
+}
@@ -72,6 +72,44 @@ export const blocked = (name: string, chunk: Chunk, frame: string) => {
  })
 }

+const CONTENT_FILTER_REASONS = new Set([
+  "IMAGE_SAFETY",
+  "RECITATION",
+  "SAFETY",
+  "BLOCKLIST",
+  "PROHIBITED_CONTENT",
+  "SPII",
+  "MODEL_ARMOR",
+  "IMAGE_PROHIBITED_CONTENT",
+  "IMAGE_RECITATION",
+  "LANGUAGE",
+])
+
+/** Finish reasons for which Gemini stops output on safety or policy grounds. */
+export const contentFiltered = (finishReason: string | undefined) =>
+  finishReason !== undefined && CONTENT_FILTER_REASONS.has(finishReason)
+
+/** Callers check that the response produced no output: a policy stop after output is a partial result instead. */
+export const withheld = (name: string, chunk: Chunk, frame: string) => {
+  const finishReason = chunk.candidates?.[0]?.finishReason
+  if (!contentFiltered(finishReason)) return undefined
+  return new AIError({
+    reason: new ContentPolicyError({ message: `${name} withheld its output (${finishReason})`, body: frame }),
+  })
+}
+
+/** Any finish reason other than `STOP` means the output may be cut short, so it is surfaced rather than dropped. */
+export const notices = (name: string, state: Metadata): ReadonlyArray<Media.Notice> | undefined =>
+  state.finishReason === undefined || state.finishReason === "STOP"
+    ? undefined
+    : [
+        {
+          type: contentFiltered(state.finishReason) ? "filtered" : "other",
+          message: `${name} finished with ${state.finishReason}`,
+          providerMetadata: { google: { finishReason: state.finishReason } },
+        },
+      ]
+
 export const usage = (usage: UsageMetadata | undefined): MediaUsage | undefined =>
  usage === undefined
    ? undefined
@@ -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"
@@ -85,6 +85,7 @@ export const finish = (
    readonly mediaType: string | undefined
    readonly info?: Media.Info
    readonly usage?: MediaUsage
+    readonly notices?: ReadonlyArray<Media.Notice>
    readonly providerMetadata?: ProviderMetadata
    readonly detail?: string
  },
@@ -97,6 +98,7 @@ export const finish = (
    SpeechFinishEvent.make({
      audio: Media.bytes(concatBytes(state.chunks), output.mediaType, { info: output.info }),
      usage: output.usage,
+      notices: output.notices,
      providerMetadata: output.providerMetadata,
    }),
  ])
@@ -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,
@@ -16,6 +16,8 @@ import {
 const patterns = [
  /prompt is too long/i,
  /input is too long for requested model/i,
+  // Cloudflare Workers AI reports this as HTTP 413.
+  /exceeded this model context window limit/i,
  /exceeds the context window/i,
  /exceeds (?:the )?(?:model'?s )?maximum context length(?: of [\d,]+ tokens?|\s*\([\d,]+\))/i,
  /input token count.*exceeds the maximum/i,
@@ -58,6 +60,47 @@ 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 +111,8 @@ 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 +157,41 @@ 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 +297,10 @@ 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\":\"EpcDCpQDAWkUfRM325TAUtfFiOeQIEWn/TsCU9oi2js4VPHFeeLfAu+2k8PJm0fN/OaF0y4ovau7S9QIAsuOPI2w2aIyQ2kMGj1XvUyRTvz30DOZgtq1km6W6YGzZyyTCNSeBcpwtJtziHZVVWq9xEI/HHB8Ta1Ot215xnFyDL7iUGEwgGu45/mInpk+SOCYBy9biDddpDxcDi14BGoleArY9XEFAzYLxXssl7HMWjpfee5095im7gD125Nripq1Jf3nGY/2TxqjgQAdJpQybwct63p74O1szGHQxrkBt7AwphDgbOWtLpUP/QJBRdl8qhrozqRe611NQ6V5lMSwpO7OhQ/IDRtWMwOyrrKblZfmMnnPl2/9xDfZRsYnfmWq+7PeAptJl1cDRlMBKhj5iRn31xvN43EiuvWwWPsSndiWvxrMvVBd89TR4u0+z0pYCYZcsFkYKFlPA7pZsdnh6CON24AA5WUkO4dQNoqYdik6aO5hE9jLHG5FHTdr0W69qgPNozbxnO0ptRcOtkGpB9xYUVoTxcSXXZE=\"}},\"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"
+      }
+    }
+  ]
+}
@@ -4,7 +4,7 @@
    "model": "anthropic/claude-sonnet-4.6",
    "tags": ["prefix:openai-compatible-chat", "provider:openrouter", "protocol:openai-chat", "reasoning"],
    "name": "openrouter-reasoning",
-    "recordedAt": "2026-07-18T11:28:39.267Z"
+    "recordedAt": "2026-09-29T16:19:02.835Z"
  },
  "interactions": [
    {
@@ -15,14 +15,14 @@
        "headers": {
          "content-type": "application/json"
        },
-        "body": "{\"model\":\"anthropic/claude-sonnet-4.6\",\"messages\":[{\"role\":\"system\",\"content\":\"Think through the arithmetic, then reply with only the final integer.\"},{\"role\":\"user\",\"content\":\"What is 173 multiplied by 219?\"}],\"stream\":true,\"stream_options\":{\"include_usage\":true},\"temperature\":0,\"reasoning\":{\"max_tokens\":1024},\"max_completion_tokens\":1536,\"store\":false,\"usage\":{\"include\":true}}"
+        "body": "{\"model\":\"anthropic/claude-sonnet-4.6\",\"messages\":[{\"role\":\"system\",\"content\":[{\"type\":\"text\",\"text\":\"Think through the arithmetic, then reply with only the final integer.\",\"cache_control\":{\"type\":\"ephemeral\"}}]},{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is 173 multiplied by 219?\",\"cache_control\":{\"type\":\"ephemeral\"}}]}],\"stream\":true,\"stream_options\":{\"include_usage\":true},\"store\":false,\"max_completion_tokens\":1536,\"temperature\":0,\"usage\":{\"include\":true},\"reasoning\":{\"max_tokens\":1024}}"
      },
      "response": {
        "status": 200,
        "headers": {
          "content-type": "text/event-stream"
        },
-        "body": ": OPENROUTER PROCESSING\n\n: OPENROUTER PROCESSING\n\ndata: {\"id\":\"gen-1784374117-AXXPsQRoclZeQGx2uHeK\",\"object\":\"chat.completion.chunk\",\"created\":1784374117,\"model\":\"anthropic/claude-sonnet-4.6\",\"provider\":\"Anthropic\",\"choices\":[{\"index\":0,\"delta\":{\"content\":\"\",\"role\":\"assistant\",\"reasoning\":\"173\",\"reasoning_details\":[{\"type\":\"reasoning.text\",\"text\":\"173\",\"format\":\"anthropic-claude-v1\",\"index\":0}]},\"finish_reason\":null,\"native_finish_reason\":null}]}\n\n: OPENROUTER PROCESSING\n\ndata: {\"id\":\"gen-1784374117-AXXPsQRoclZeQGx2uHeK\",\"object\":\"chat.completion.chunk\",\"created\":1784374117,\"model\":\"anthropic/claude-sonnet-4.6\",\"provider\":\"Anthropic\",\"choices\":[{\"index\":0,\"delta\":{\"content\":\"\",\"role\":\"assistant\",\"reasoning\":\" × 219\\n\\n173 × 200 = 34,600\\n173 × 19 = 173 × 20 - 173 = 3,460 - 173 = 3,287\",\"reasoning_details\":[{\"type\":\"reasoning.text\",\"text\":\" × 219\\n\\n173 × 200 = 34,600\\n173 × 19 = 173 × 20 - 173 = 3,460 - 173 = 3,287\",\"format\":\"anthropic-claude-v1\",\"index\":0}]},\"finish_reason\":null,\"native_finish_reason\":null}]}\n\ndata: {\"id\":\"gen-1784374117-AXXPsQRoclZeQGx2uHeK\",\"object\":\"chat.completion.chunk\",\"created\":1784374117,\"model\":\"anthropic/claude-sonnet-4.6\",\"provider\":\"Anthropic\",\"choices\":[{\"index\":0,\"delta\":{\"content\":\"\",\"role\":\"assistant\",\"reasoning\":\"\\n\\n34,600 + 3,287 = 37,887\",\"reasoning_details\":[{\"type\":\"reasoning.text\",\"text\":\"\\n\\n34,600 + 3,287 = 37,887\",\"format\":\"anthropic-claude-v1\",\"index\":0}]},\"finish_reason\":null,\"native_finish_reason\":null}]}\n\ndata: {\"id\":\"gen-1784374117-AXXPsQRoclZeQGx2uHeK\",\"object\":\"chat.completion.chunk\",\"created\":1784374117,\"model\":\"anthropic/claude-sonnet-4.6\",\"provider\":\"Anthropic\",\"choices\":[{\"index\":0,\"delta\":{\"content\":\"\",\"role\":\"assistant\",\"reasoning_details\":[{\"type\":\"reasoning.text\",\"signature\":\"EtgCCosBCA8YAipA0W4viH3kgBs43Cl5ewwVBPXTQElvzfbA2TLF4iSbKy9ZZDCSDjjAlF3Bs4ELEnP3vrrTuTioC6OB380lXQdyIDIRY2xhdWRlLXNvbm5ldC00LTY4AEIIdGhpbmtpbmdaJDRjMGYwNDZmLTI1ZmQtNDVmYi1iZmIzLWEwOGE4ZTI0OWNhNxIMMiUlJC3x/5p5PuTwGgwlc8eipZyoM94BHwMiMO45uQx/ymeOjbugi7RDVPZ4jZXSIiEbVi2CD7zPjAK5fFQoVGP1HD55v9CER823JCp6Dg5Xb7Lrk6NUd1XN2KTKrttK7mATE+IBrDTFmor/1cNeg+9gjIbxM/jn/6L5HPmh3/esEVu24Q0IGLZVoE7cTgGgxsrceKMD71Jp2XQgIWD8ltsPfWw3gSc4p+z18UuPN6LuR0mHHENTnClHrAPnOrxbDIl4ZwZgMX8YAQ==\",\"format\":\"anthropic-claude-v1\",\"index\":0}]},\"finish_reason\":null,\"native_finish_reason\":null}]}\n\ndata: {\"id\":\"gen-1784374117-AXXPsQRoclZeQGx2uHeK\",\"object\":\"chat.completion.chunk\",\"created\":1784374117,\"model\":\"anthropic/claude-sonnet-4.6\",\"provider\":\"Anthropic\",\"choices\":[{\"index\":0,\"delta\":{\"content\":\"37887\",\"role\":\"assistant\"},\"finish_reason\":null,\"native_finish_reason\":null}]}\n\ndata: {\"id\":\"gen-1784374117-AXXPsQRoclZeQGx2uHeK\",\"object\":\"chat.completion.chunk\",\"created\":1784374117,\"model\":\"anthropic/claude-sonnet-4.6\",\"provider\":\"Anthropic\",\"choices\":[{\"index\":0,\"delta\":{\"content\":\"\",\"role\":\"assistant\",\"reasoning\":null},\"finish_reason\":\"stop\",\"native_finish_reason\":\"end_turn\"}]}\n\ndata: {\"id\":\"gen-1784374117-AXXPsQRoclZeQGx2uHeK\",\"object\":\"chat.completion.chunk\",\"created\":1784374117,\"model\":\"anthropic/claude-sonnet-4.6\",\"provider\":\"Anthropic\",\"service_tier\":\"default\",\"choices\":[{\"index\":0,\"delta\":{\"content\":\"\",\"role\":\"assistant\"},\"finish_reason\":\"stop\",\"native_finish_reason\":\"end_turn\"}],\"usage\":{\"prompt_tokens\":61,\"completion_tokens\":80,\"total_tokens\":141,\"cost\":0.001383,\"is_byok\":false,\"prompt_tokens_details\":{\"cached_tokens\":0,\"cache_write_tokens\":0,\"audio_tokens\":0,\"video_tokens\":0},\"cache_creation\":{\"ephemeral_5m_input_tokens\":0,\"ephemeral_1h_input_tokens\":0},\"cost_details\":{\"upstream_inference_cost\":0.001383,\"upstream_inference_prompt_cost\":0.000183,\"upstream_inference_completions_cost\":0.0012},\"completion_tokens_details\":{\"reasoning_tokens\":29,\"image_tokens\":0,\"audio_tokens\":0}}}\n\ndata: [DONE]\n\n"
+        "body": "data: {\"id\":\"gen-1790698739-Acm5E9n2uVTO14sqrick\",\"object\":\"chat.completion.chunk\",\"created\":1790698739,\"model\":\"anthropic/claude-sonnet-4.6\",\"provider\":\"Claude Platform on AWS\",\"choices\":[{\"index\":0,\"delta\":{\"content\":\"\",\"role\":\"assistant\",\"reasoning\":\"173\",\"reasoning_details\":[{\"type\":\"reasoning.text\",\"text\":\"173\",\"format\":\"anthropic-claude-v1\",\"index\":0}]},\"finish_reason\":null,\"native_finish_reason\":null}]}\n\n: OPENROUTER PROCESSING\n\ndata: {\"id\":\"gen-1790698739-Acm5E9n2uVTO14sqrick\",\"object\":\"chat.completion.chunk\",\"created\":1790698739,\"model\":\"anthropic/claude-sonnet-4.6\",\"provider\":\"Claude Platform on AWS\",\"choices\":[{\"index\":0,\"delta\":{\"content\":\"\",\"role\":\"assistant\",\"reasoning\":\" × 219\\n\\n173 × 200 = 34,600\\n173 × 19 = 173 × 20 - 173 = 3,460 - 173 = 3,287\\n\\n34,600 + 3,287 = 37,887\",\"reasoning_details\":[{\"type\":\"reasoning.text\",\"text\":\" × 219\\n\\n173 × 200 = 34,600\\n173 × 19 = 173 × 20 - 173 = 3,460 - 173 = 3,287\\n\\n34,600 + 3,287 = 37,887\",\"format\":\"anthropic-claude-v1\",\"index\":0}]},\"finish_reason\":null,\"native_finish_reason\":null}]}\n\ndata: {\"id\":\"gen-1790698739-Acm5E9n2uVTO14sqrick\",\"object\":\"chat.completion.chunk\",\"created\":1790698739,\"model\":\"anthropic/claude-sonnet-4.6\",\"provider\":\"Claude Platform on AWS\",\"choices\":[{\"index\":0,\"delta\":{\"content\":\"\",\"role\":\"assistant\",\"reasoning_details\":[{\"type\":\"reasoning.text\",\"signature\":\"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.eyJlbmRwb2ludF9zbHVnIjoiYW50aHJvcGljL2NsYXVkZS00LjYtc29ubmV0LTIwMjYwMjE3fGNsYXVkZS1vbi1hd3MifQ\",\"format\":\"anthropic-claude-v1\",\"index\":0}]},\"finish_reason\":null,\"native_finish_reason\":null}]}\n\ndata: {\"id\":\"gen-1790698739-Acm5E9n2uVTO14sqrick\",\"object\":\"chat.completion.chunk\",\"created\":1790698739,\"model\":\"anthropic/claude-sonnet-4.6\",\"provider\":\"Claude Platform on AWS\",\"choices\":[{\"index\":0,\"delta\":{\"content\":\"37\",\"role\":\"assistant\"},\"finish_reason\":null,\"native_finish_reason\":null}]}\n\ndata: {\"id\":\"gen-1790698739-Acm5E9n2uVTO14sqrick\",\"object\":\"chat.completion.chunk\",\"created\":1790698739,\"model\":\"anthropic/claude-sonnet-4.6\",\"provider\":\"Claude Platform on AWS\",\"choices\":[{\"index\":0,\"delta\":{\"content\":\"887\",\"role\":\"assistant\"},\"finish_reason\":null,\"native_finish_reason\":null}]}\n\ndata: {\"id\":\"gen-1790698739-Acm5E9n2uVTO14sqrick\",\"object\":\"chat.completion.chunk\",\"created\":1790698739,\"model\":\"anthropic/claude-sonnet-4.6\",\"provider\":\"Claude Platform on AWS\",\"choices\":[{\"index\":0,\"delta\":{\"content\":\"\",\"role\":\"assistant\",\"reasoning\":null},\"finish_reason\":\"stop\",\"native_finish_reason\":\"end_turn\"}]}\n\ndata: {\"id\":\"gen-1790698739-Acm5E9n2uVTO14sqrick\",\"object\":\"chat.completion.chunk\",\"created\":1790698739,\"model\":\"anthropic/claude-sonnet-4.6\",\"provider\":\"Claude Platform on AWS\",\"service_tier\":\"default\",\"choices\":[{\"index\":0,\"delta\":{\"content\":\"\",\"role\":\"assistant\"},\"finish_reason\":\"stop\",\"native_finish_reason\":\"end_turn\"}],\"usage\":{\"prompt_tokens\":61,\"completion_tokens\":80,\"total_tokens\":141,\"cost\":0.001383,\"is_byok\":false,\"prompt_tokens_details\":{\"cached_tokens\":0,\"cache_write_tokens\":0,\"audio_tokens\":0,\"video_tokens\":0},\"cost_details\":{\"upstream_inference_cost\":0.001383,\"upstream_inference_prompt_cost\":0.000183,\"upstream_inference_completions_cost\":0.0012},\"completion_tokens_details\":{\"reasoning_tokens\":73,\"image_tokens\":0,\"audio_tokens\":0}}}\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 +355,43 @@ describe("provider error rawBody classification", () => {
    }
  })

+  test("classifies Workers AI context window rejections as context overflow despite HTTP 413", () => {
+    const message =
+      "AiError: Ai: The estimated number of input and maximum output tokens (900047) exceeded this model context window limit (32000). (17851589-f2e6-405d-b67c-5550e52ee1c1)"
+    const reason = classifyProviderFailure({
+      message,
+      status: 413,
+      rawBody: JSON.stringify({ errors: [{ message, code: 5021 }], success: false, result: {}, messages: [] }),
+    })
+    expect(reason._tag === "InvalidRequest" ? reason.classification : reason._tag).toBe("context-overflow")
+  })
+
+  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 +407,42 @@ 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" } })
  })

@@ -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"))
@@ -303,7 +303,8 @@ describe("Mistral Chat", () => {
          fixedResponse(
            sseEvents(
              chunk({ content: [{ type: "thinking", thinking: [], marker: "empty" }] }),
-              chunk({ content: [{ type: "thinking", thinking: [{ type: "text", text: "Consider" }] }] }),
+              chunk({ content: [{ type: "thinking", thinking: [{ type: "text", text: "Con" }] }] }),
+              chunk({ content: [{ type: "thinking", thinking: [{ type: "text", text: "sider" }], closed: true }] }),
              chunk({ content: [{ type: "text", text: "Answer" }] }),
              chunk({}, "stop"),
            ),
@@ -313,6 +314,11 @@ describe("Mistral Chat", () => {

      expect(response.reasoning).toBe("Consider")
      expect(response.text).toBe("Answer")
+      expect(response.events.find(LLMEvent.is.reasoningStart)?.providerMetadata).toBeUndefined()
+      expect(response.events.filter(LLMEvent.is.reasoningDelta).map((event) => [event.text, event.providerMetadata])).toEqual([
+        ["Con", undefined],
+        ["sider", undefined],
+      ])
      expect(response.message.content).toEqual([
        {
          type: "reasoning",
@@ -321,8 +327,12 @@ describe("Mistral Chat", () => {
            mistral: {
              thinking: {
                type: "thinking",
-                thinking: [{ type: "text", text: "Consider" }],
+                thinking: [
+                  { type: "text", text: "Con" },
+                  { type: "text", text: "sider" },
+                ],
                marker: "empty",
+                closed: true,
              },
            },
          },
@@ -337,8 +347,12 @@ describe("Mistral Chat", () => {
          content: [
            {
              type: "thinking",
-              thinking: [{ type: "text", text: "Consider" }],
+              thinking: [
+                { type: "text", text: "Con" },
+                { type: "text", text: "sider" },
+              ],
              marker: "empty",
+              closed: true,
            },
            { type: "text", text: "Answer" },
          ],
@@ -357,6 +371,8 @@ describe("Mistral Chat", () => {
          ),
        ),
      )
+      expect(response.events.find(LLMEvent.is.reasoningStart)?.providerMetadata).toBeUndefined()
+      expect(response.events.filter(LLMEvent.is.reasoningDelta)).toEqual([])
      expect(response.message.content).toEqual([
        {
          type: "reasoning",
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
Shoubhit Dash	6b61e05776	refactor(core): isolate session MCP registry behind a session view	2026-09-30 20:15:17 +05:30
Shoubhit Dash	704ef1c693	feat(acp): register MCP servers per session	2026-09-30 19:45:26 +05:30
Shoubhit Dash	2f0a2b607d	feat(core): session-scoped MCP servers	2026-09-30 19:45:25 +05:30
James Long	02c3891d9b	feat(core): let form cancellation carry a message (#52137 )	2026-09-30 09:20:26 -04:00
Shoubhit Dash	1844c11104	fix(acp): follow server defaults and refresh the session catalog (#52286 )	2026-09-30 18:36:56 +05:30
opencode-agent[bot]	c0285b457a	chore(core): refresh bundled models.dev snapshot	2026-09-30 12:25:26 +00:00
opencode-agent[bot]	ffa4c4c730	feat(app): open referenced session IDs from markdown (#52231 ) Co-authored-by: Brendonovich <14191578+Brendonovich@users.noreply.github.com>	2026-09-30 15:39:30 +08:00
Luke Parker	01efd22b2a	feat(desktop): comment on page elements from the in-app browser (#52217 )	2026-09-30 16:52:42 +10:00
opencode-agent[bot]	dd68d6eb79	fix(app): select new-session project by resolved ID (#52230 ) Co-authored-by: Brendonovich <14191578+Brendonovich@users.noreply.github.com>	2026-09-30 14:34:05 +08:00
Simon Klee	1243d09dbc	tui: update OpenTUI to 0.5.13 (#52233 )	2026-09-30 06:13:28 +00:00
Aiden Cline	a80a00011d	fix(ai): classify Workers AI context window rejections as context overflow (#52128 )	2026-09-29 23:49:03 -05:00
opencode-agent[bot]	bf97a0443f	fix(app): alert only for open session tabs (#52204 ) Co-authored-by: Brendonovich <14191578+Brendonovich@users.noreply.github.com>	2026-09-30 03:55:01 +00:00
Luke Parker	67b14e9191	feat(session-ui): keep open Used group header sticky (#52210 )	2026-09-30 13:46:40 +10:00
Luke Parker	1b02abcfab	feat(session-ui): group adjacent reads into one row (#52207 )	2026-09-30 12:54:40 +10:00
Aiden Cline	74dbc509d7	fix(ai): place prompt cache breakpoints on OpenRouter Anthropic and Qwen requests (#52110 )	2026-09-29 18:07:49 -05:00
Aiden Cline	760f87fab1	fix(core): pass through Copilot Responses settings (#52182 )	2026-09-29 17:52:53 -05:00
opencode-agent[bot]	df51166711	fix(ci): run V2 Discord notification after skipped build jobs (#52012 ) Co-authored-by: rekram1-node <rekram1-node@users.noreply.github.com>	2026-09-29 16:22:16 -05:00
opencode	8d8a7bc844	sync release versions for v2.0.20	2026-09-29 21:08:02 +00:00
opencode-agent[bot]	a2fc1968be	fix(stats): match document background to page theme (#52169 )	2026-09-29 15:59:22 -05:00
Aiden Cline	c2a39ac592	fix(core): stop promising a ChatGPT usage reset (#52168 )	2026-09-29 15:50:09 -05:00
Aiden Cline	4deda18037	fix(app): align ChatGPT usage copy and links (#52163 )	2026-09-29 15:18:45 -05:00
Aiden Cline	0f83038253	fix(core): align ChatGPT token sharing with updated partner guide (#52162 )	2026-09-29 15:11:58 -05:00
Dax	4c33a253aa	feat(cli): add auth export and auth import commands (#52139 )	2026-09-29 16:09:01 -04:00
opencode-agent[bot]	135995d4fc	test: stabilize V2 CI test suites (#52159 ) Co-authored-by: rekram1-node <rekram1-node@users.noreply.github.com> Co-authored-by: jlongster <17031+jlongster@users.noreply.github.com>	2026-09-29 14:54:11 -05:00
Aiden Cline	4d9090790b	feat(core): add separate ChatGPT token-sharing OAuth method (#52147 )	2026-09-29 14:48:51 -05:00
Aiden Cline	621a5b0706	feat(app): show ChatGPT token-sharing guidance (#52160 )	2026-09-29 14:45:59 -05:00
Aiden Cline	16ef62c851	feat(app): show ChatGPT usage limit dialog (#52153 )	2026-09-29 14:38:48 -05:00
Aiden Cline	b694d2bf26	fix(core): explain ChatGPT token-sharing errors (#52158 )	2026-09-29 14:25:01 -05:00
Aiden Cline	89d37a0f6d	fix(core): restrict database files to their owner (#52150 )	2026-09-29 14:18:40 -05:00
James Long	bc5ff1cfd9	fix(cli): answer subagent asks in run and keep parallel rejections continuing (#52146 )	2026-09-29 15:03:06 -04:00
Aiden Cline	c14a1f5acf	feat(core): preserve provider response body in session errors (#52136 )	2026-09-29 13:32:09 -05:00
Frank	7db941a892	docs(console): add GPT 6.1 Sol to model list	2026-09-29 14:28:47 -04:00
James Long	83fafda63a	feat(cli): continue run after rejecting a permission ask (#51968 )	2026-09-29 14:26:20 -04:00
opencode-agent[bot]	a565ea8c74	feat(cli): allow disabling the background service (#52107 ) Co-authored-by: jlongster <17031+jlongster@users.noreply.github.com>	2026-09-29 13:32:38 -04:00
Aiden Cline	3126808e0e	fix(ai): defer Mistral thinking metadata until block end (#52008 )	2026-09-29 11:38:06 -05:00
opencode-agent[bot]	948047a8ca	fix(tui): use disclosure icon for low activity errors (#52097 ) Co-authored-by: thdxr <826656+thdxr@users.noreply.github.com>	2026-09-29 11:10:32 -04:00
opencode-agent[bot]	0f931d3939	chore(core): refresh bundled models.dev snapshot	2026-09-29 12:22:53 +00:00
Kit Langton	7ef4a1a56e	feat(tui): show recently closed tabs in new session menu	2026-09-29 03:35:31 -07:00
Victor Navarro	b29dab3231	fix(core): drop SSO link from Console sign-in error (#52062 )	2026-09-29 12:04:27 +02:00
Victor Navarro	d76f968c60	feat(core): tell users how to sign back in to OpenCode Console (#51847 )	2026-09-29 10:58:45 +02:00
opencode-agent[bot]	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]	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]	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	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]	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
Sebastian	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]	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 Benoit	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
Shoubhit Dash	c33de198e3	fix(ai): surface truncated Gemini speech and transcription results (#51379 )	2026-09-27 14:29:36 +05:30
Shoubhit Dash	24224bcb57	fix(ai): describe speech assets in the format actually sent (#51377 )	2026-09-27 14:16:23 +05:30
Aiden Cline	7913c8db59	feat(core): log provider rejections that trigger overflow compaction (#51582 )	2026-09-26 23:11:33 -05:00
Aiden Cline	d9987ef9c8	feat(core): fit output limits to the context window (#51271 )	2026-09-26 22:58:28 -05:00
Jack	f0ed4f67df	docs: list LongCat 2.5 Preview Free in V2 Console (#51487 )	2026-09-26 21:20:36 +08:00
opencode-agent[bot]	2109d68d39	chore(core): refresh bundled models.dev snapshot	2026-09-26 12:18:22 +00:00
Filip	cefb2968e2	fix(cli): cancel auth attempts on ctrl+c (#51484 )	2026-09-26 11:59:17 +00:00
opencode-agent[bot]	00d179015f	chore: update nix node_modules hashes	2026-09-26 10:01:15 +00:00
opencode-agent[bot]	1d4e1233e5	feat(cli): share grouped auth picker with MCP auth (#51006 ) Co-authored-by: rekram1-node <rekram1-node@users.noreply.github.com> Co-authored-by: thdxr <thdxr@users.noreply.github.com> Co-authored-by: rekram1-node <63023139+rekram1-node@users.noreply.github.com> Co-authored-by: Filip Hejmowski <fhejmowski@simplito.com>	2026-09-26 11:42:04 +02:00
opencode-agent[bot]	d14f20b46e	fix(tui): capitalize OpenCode web search provider (#49023 ) Co-authored-by: vimtor <36263538+vimtor@users.noreply.github.com> Co-authored-by: Victor Navarro <vn4varro@gmail.com>	2026-09-26 09:36:20 +00:00
opencode-agent[bot]	37049a5a13	fix(tui): skip model selection after MCP connection (#51448 ) Co-authored-by: rekram1-node <rekram1-node@users.noreply.github.com>	2026-09-26 00:00:25 -05:00
Aiden Cline	a64bc3616e	refactor(core): cleanup session compaction (#51447 )	2026-09-26 00:00:11 -05:00