fix(server): match the macOS EPERM privacy denial exactly

fix(server): return typed errors for unavailable project folders
2026-09-26 18:47:35 +00:00 · 2026-09-24 19:21:50 +02:00 · 2026-09-24 18:47:08 +02:00
293 changed files with 3465 additions and 8942 deletions
@@ -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 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 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 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": "2.0.16",
      "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": "2.0.16",
      "dependencies": {
        "@corvu/drawer": "catalog:",
        "@dnd-kit/abstract": "0.5.0",
@@ -112,7 +112,7 @@
    },
    "packages/cli": {
      "name": "@opencode/cli",
-      "version": "2.0.18",
+      "version": "2.0.16",
      "bin": {
        "opencode": "./bin/opencode.cjs",
        "opencode2": "./bin/opencode2.cjs",
@@ -135,6 +135,7 @@
        "effect": "catalog:",
        "immer": "11.1.4",
        "jsonc-parser": "3.3.1",
+        "open": "10.1.2",
        "solid-js": "catalog:",
        "tree-sitter-bash": "0.25.0",
        "tree-sitter-powershell": "0.25.10",
@@ -176,7 +177,7 @@
    },
    "packages/client": {
      "name": "@opencode/client",
-      "version": "2.0.18",
+      "version": "2.0.16",
      "dependencies": {
        "@opencode/protocol": "workspace:*",
        "@opencode/schema": "workspace:*",
@@ -202,7 +203,7 @@
    },
    "packages/codemode": {
      "name": "@opencode/codemode",
-      "version": "2.0.18",
+      "version": "2.0.16",
      "dependencies": {
        "acorn": "8.15.0",
        "effect": "catalog:",
@@ -215,7 +216,7 @@
    },
    "packages/console/app": {
      "name": "@opencode/console-app",
-      "version": "2.0.18",
+      "version": "2.0.16",
      "dependencies": {
        "@cloudflare/vite-plugin": "1.15.2",
        "@ibm/plex": "6.4.1",
@@ -251,7 +252,7 @@
    },
    "packages/console/core": {
      "name": "@opencode/console-core",
-      "version": "2.0.18",
+      "version": "2.0.16",
      "dependencies": {
        "@aws-sdk/client-sts": "3.782.0",
        "@jsx-email/render": "1.1.1",
@@ -278,7 +279,7 @@
    },
    "packages/console/function": {
      "name": "@opencode/console-function",
-      "version": "2.0.18",
+      "version": "2.0.16",
      "dependencies": {
        "@openauthjs/openauth": "0.0.0-20250322224806",
        "@opencode/console-core": "workspace:*",
@@ -295,7 +296,7 @@
    },
    "packages/console/mail": {
      "name": "@opencode/console-mail",
-      "version": "2.0.18",
+      "version": "2.0.16",
      "dependencies": {
        "@jsx-email/all": "2.2.3",
        "@jsx-email/cli": "1.4.3",
@@ -319,7 +320,7 @@
    },
    "packages/console/support": {
      "name": "@opencode/console-support",
-      "version": "2.0.18",
+      "version": "2.0.16",
      "dependencies": {
        "@cloudflare/vite-plugin": "1.15.2",
        "@opencode/console-core": "workspace:*",
@@ -339,7 +340,7 @@
    },
    "packages/core": {
      "name": "@opencode/core",
-      "version": "2.0.18",
+      "version": "2.0.16",
      "dependencies": {
        "@ai-sdk/cohere": "3.0.27",
        "@ai-sdk/gateway": "3.0.104",
@@ -407,7 +408,7 @@
    },
    "packages/desktop": {
      "name": "@opencode/desktop",
-      "version": "2.0.18",
+      "version": "2.0.16",
      "dependencies": {
        "@zip.js/zip.js": "2.7.62",
        "electron-context-menu": "5.0.0",
@@ -456,7 +457,7 @@
    },
    "packages/enterprise": {
      "name": "@opencode/enterprise",
-      "version": "2.0.18",
+      "version": "2.0.16",
      "dependencies": {
        "@hono/standard-validator": "catalog:",
        "@opencode-ai/sdk": "1.18.21",
@@ -493,7 +494,7 @@
    },
    "packages/function": {
      "name": "@opencode/function",
-      "version": "2.0.18",
+      "version": "2.0.16",
      "dependencies": {
        "@octokit/auth-app": "8.0.1",
        "@octokit/rest": "catalog:",
@@ -509,7 +510,7 @@
    },
    "packages/http-recorder": {
      "name": "@opencode/http-recorder",
-      "version": "2.0.18",
+      "version": "2.0.16",
      "dependencies": {
        "@effect/platform-node-shared": "4.0.0-rc.112",
      },
@@ -528,7 +529,7 @@
    },
    "packages/httpapi-codegen": {
      "name": "@opencode/httpapi-codegen",
-      "version": "2.0.18",
+      "version": "2.0.16",
      "dependencies": {
        "effect": "catalog:",
        "prettier": "3.6.2",
@@ -541,7 +542,7 @@
    },
    "packages/latex": {
      "name": "@opencode/latex",
-      "version": "2.0.18",
+      "version": "2.0.16",
      "dependencies": {
        "@opencode/plugin": "workspace:*",
        "@opentui/core": "catalog:",
@@ -555,7 +556,7 @@
    },
    "packages/merman": {
      "name": "@opencode/merman",
-      "version": "2.0.18",
+      "version": "2.0.16",
      "dependencies": {
        "@opencode/plugin": "workspace:*",
        "@opentui/core": "catalog:",
@@ -570,7 +571,7 @@
    },
    "packages/plugin": {
      "name": "@opencode/plugin",
-      "version": "2.0.18",
+      "version": "2.0.16",
      "dependencies": {
        "@ai-sdk/provider": "3.0.8",
        "@opencode/ai": "workspace:*",
@@ -596,8 +597,8 @@
      },
      "peerDependencies": {
        "@opencode/theme": "workspace:*",
-        "@opentui/core": ">=0.5.12",
-        "@opentui/solid": ">=0.5.12",
+        "@opentui/core": ">=0.5.10",
+        "@opentui/solid": ">=0.5.10",
        "solid-js": ">=1.9.0",
      },
      "optionalPeers": [
@@ -609,7 +610,7 @@
    },
    "packages/plugin-browser": {
      "name": "@opencode/plugin-browser",
-      "version": "2.0.18",
+      "version": "2.0.16",
      "dependencies": {
        "@opencode/plugin": "workspace:*",
        "@opencode/schema": "workspace:*",
@@ -639,7 +640,7 @@
    },
    "packages/protocol": {
      "name": "@opencode/protocol",
-      "version": "2.0.18",
+      "version": "2.0.16",
      "dependencies": {
        "@opencode/schema": "workspace:*",
        "effect": "catalog:",
@@ -654,7 +655,7 @@
    },
    "packages/schema": {
      "name": "@opencode/schema",
-      "version": "2.0.18",
+      "version": "2.0.16",
      "dependencies": {
        "@standard-schema/spec": "catalog:",
        "effect": "catalog:",
@@ -678,7 +679,7 @@
    },
    "packages/sdk": {
      "name": "@opencode/sdk",
-      "version": "2.0.18",
+      "version": "2.0.16",
      "dependencies": {
        "@opencode/client": "workspace:*",
        "@opencode/core": "workspace:*",
@@ -699,7 +700,7 @@
    },
    "packages/server": {
      "name": "@opencode/server",
-      "version": "2.0.18",
+      "version": "2.0.16",
      "dependencies": {
        "@effect/platform-node": "catalog:",
        "@effect/platform-node-shared": "catalog:",
@@ -721,7 +722,7 @@
    },
    "packages/session-ui": {
      "name": "@opencode/session-ui",
-      "version": "2.0.18",
+      "version": "2.0.16",
      "dependencies": {
        "@kobalte/core": "catalog:",
        "@opencode/client": "workspace:*",
@@ -756,7 +757,7 @@
    },
    "packages/simulation": {
      "name": "@opencode/simulation",
-      "version": "2.0.18",
+      "version": "2.0.16",
      "dependencies": {
        "@opencode/ai": "workspace:*",
        "@opencode/core": "workspace:*",
@@ -776,7 +777,7 @@
    },
    "packages/stats/app": {
      "name": "@opencode/stats-app",
-      "version": "2.0.18",
+      "version": "2.0.16",
      "dependencies": {
        "@ibm/plex": "6.4.1",
        "@kobalte/core": "catalog:",
@@ -810,7 +811,7 @@
    },
    "packages/stats/core": {
      "name": "@opencode/stats-core",
-      "version": "2.0.18",
+      "version": "2.0.16",
      "dependencies": {
        "@aws-sdk/client-athena": "3.933.0",
        "@planetscale/database": "1.19.0",
@@ -829,7 +830,7 @@
    },
    "packages/stats/server": {
      "name": "@opencode/stats-server",
-      "version": "2.0.18",
+      "version": "2.0.16",
      "dependencies": {
        "@aws-sdk/client-firehose": "3.933.0",
        "@effect/platform-node": "catalog:",
@@ -875,7 +876,7 @@
    },
    "packages/theme": {
      "name": "@opencode/theme",
-      "version": "2.0.18",
+      "version": "2.0.16",
      "dependencies": {
        "@opentui/core": "catalog:",
        "effect": "catalog:",
@@ -889,7 +890,7 @@
    },
    "packages/tui": {
      "name": "@opencode/tui",
-      "version": "2.0.18",
+      "version": "2.0.16",
      "dependencies": {
        "@opencode/client": "workspace:*",
        "@opencode/core": "workspace:*",
@@ -908,6 +909,7 @@
        "effect": "catalog:",
        "fuzzysort": "catalog:",
        "get-east-asian-width": "catalog:",
+        "open": "10.1.2",
        "opentui-spinner": "catalog:",
        "remeda": "catalog:",
        "solid-js": "catalog:",
@@ -923,7 +925,7 @@
    },
    "packages/ui": {
      "name": "@opencode/ui",
-      "version": "2.0.18",
+      "version": "2.0.16",
      "dependencies": {
        "@kobalte/core": "catalog:",
        "@pierre/diffs": "catalog:",
@@ -958,7 +960,7 @@
    },
    "packages/util": {
      "name": "@opencode/util",
-      "version": "2.0.18",
+      "version": "2.0.16",
      "dependencies": {
        "@effect/opentelemetry": "catalog:",
        "@effect/platform-node": "catalog:",
@@ -980,7 +982,6 @@
        "mime-types": "3.0.2",
        "minimatch": "10.2.5",
        "npm-package-arg": "13.0.2",
-        "open": "11.0.4",
        "pacote": "21.5.1",
      },
      "devDependencies": {
@@ -996,7 +997,7 @@
    },
    "packages/web": {
      "name": "@opencode/web",
-      "version": "2.0.18",
+      "version": "2.0.16",
      "dependencies": {
        "@astrojs/cloudflare": "12.6.3",
        "@astrojs/markdown-remark": "6.3.1",
@@ -1037,7 +1038,7 @@
    },
    "services/update": {
      "name": "@opencode/update",
-      "version": "2.0.18",
+      "version": "2.0.16",
      "dependencies": {
        "jose": "6.0.11",
        "semver": "catalog:",
@@ -1097,7 +1098,6 @@
    "@types/node": "catalog:",
    "bun-types": "1.4.2",
    "effect": "catalog:",
-    "open": "11.0.4",
    "solid-js": "catalog:",
  },
  "catalog": {
@@ -1114,9 +1114,9 @@
    "@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",
+    "@opentui/core": "0.5.10",
+    "@opentui/keymap": "0.5.10",
+    "@opentui/solid": "0.5.10",
    "@pierre/diffs": "1.2.10",
    "@playwright/test": "1.59.1",
    "@sentry/solid": "10.71.0",
@@ -2252,27 +2252,27 @@

    "@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@0.5.10", "", { "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": "0.5.10", "@opentui/core-darwin-x64": "0.5.10", "@opentui/core-linux-arm64": "0.5.10", "@opentui/core-linux-arm64-musl": "0.5.10", "@opentui/core-linux-x64": "0.5.10", "@opentui/core-linux-x64-musl": "0.5.10", "@opentui/core-win32-arm64": "0.5.10", "@opentui/core-win32-x64": "0.5.10" }, "peerDependencies": { "web-tree-sitter": "0.25.10" } }, "sha512-C3a2UbmefeAjIxAgm4BqjuSxKT4oqutfvYFwVvUgMxmGRHkNbBc/s7sukV0JgwcxFcV3uMFrXxo+E+BQtvuOiw=="],

-    "@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@0.5.10", "", { "os": "darwin", "cpu": "arm64" }, "sha512-Vyb+nTbhab8ZcRy5gg1loEEGwRcIbjAeVRIBfHBcbFDqmITBOg7x2gqJ+x/TnoOy4uwMhCmICUN2wiyREw3r1Q=="],

-    "@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@0.5.10", "", { "os": "darwin", "cpu": "x64" }, "sha512-tTFLcM7Oj1gTyhm/bUdAt3C6grZdCxPk6+/g2azcZBUlI3/62LwbeRS6HbQKFFmm+1fUmX8cq6kWrtul885mVg=="],

-    "@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@0.5.10", "", { "os": "linux", "cpu": "arm64" }, "sha512-ncJXcgudhBf2GdJyF3xVQN/Ec+1F7GOL+pRrURmgBYSj2v1w6EyoDQFAACtPTK2c3R38W6fvZwL4JSLlm4EFXQ=="],

-    "@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-arm64-musl": ["@opentui/core-linux-arm64-musl@0.5.10", "", { "os": "linux", "cpu": "arm64" }, "sha512-dGMphDKexSdeYqwl0wgoFBP88Ta/cdi1Zc1mk29/ENkSCGz+74zlCHgqTHRNGLmI8W5TfuUtCyktQH11/Z+TBQ=="],

-    "@opentui/core-linux-x64": ["@opentui/core-linux-x64@0.5.12", "", { "os": "linux", "cpu": "x64" }, "sha512-eZiCjEzwbb6qClPPfk32Nha9xmr9obt69Xj0+9SKsXxWLBKkjQEGOMRoh/R9ObaQF4aq8If1xV3VEY0sD9W9vg=="],
+    "@opentui/core-linux-x64": ["@opentui/core-linux-x64@0.5.10", "", { "os": "linux", "cpu": "x64" }, "sha512-5qtYaOgwVycZD1GaGshTRsi0rXPAmVExO03N1JQaHu+NYxK/vXSOc7Bu4QW0sPXx3Sp0SpzpP+FHjXABfoK66g=="],

-    "@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-linux-x64-musl": ["@opentui/core-linux-x64-musl@0.5.10", "", { "os": "linux", "cpu": "x64" }, "sha512-Oj4H9hApuvuTKPWxh4SoZAgGJorR7vbvnrZA/cAkSMAk2VGSoHRRcqeXQbcH8IcdjVZ0KFpv8Zkl/D5Ye+2mew=="],

-    "@opentui/core-win32-arm64": ["@opentui/core-win32-arm64@0.5.12", "", { "os": "win32", "cpu": "arm64" }, "sha512-aLbm6870Ybls6CYL4zMOCImTBPLZHZMUXJFGqMI44lIWxitkAtT6zg5lYA4oRqFRzzryDclxr29+hDgT3p3Blw=="],
+    "@opentui/core-win32-arm64": ["@opentui/core-win32-arm64@0.5.10", "", { "os": "win32", "cpu": "arm64" }, "sha512-A9VhgvTxQoUdZ+8LmUumEng1sQNbj9QQQT3NYG9mSxI54qTANi7vOWNSphMiY6RMVsr22pgm6nUvSSvJXv7Jog=="],

-    "@opentui/core-win32-x64": ["@opentui/core-win32-x64@0.5.12", "", { "os": "win32", "cpu": "x64" }, "sha512-KTwtwpfd2zF9opVh3SyRJYDd1o3Xv4XL8OZb8Zi+CqWUel6Y2IDCiVivCv8fGJt3J7wOIXXtuZI9ZUkLyKJCiQ=="],
+    "@opentui/core-win32-x64": ["@opentui/core-win32-x64@0.5.10", "", { "os": "win32", "cpu": "x64" }, "sha512-u3KHa7kEeWrmKVDRJYpxSGO+g5E9cMGlrmTsPN3GVPHUmQMiREUawLXUvsU8+IHaQnqG3Q5nuE1yf4fPBzS+Qw=="],

-    "@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/keymap": ["@opentui/keymap@0.5.10", "", { "dependencies": { "@opentui/core": "0.5.10" }, "peerDependencies": { "@opentui/react": "0.5.10", "@opentui/solid": "0.5.10", "react": ">=19.2.0", "solid-js": "1.9.12" }, "optionalPeers": ["@opentui/react", "@opentui/solid", "react", "solid-js"] }, "sha512-8vDJF+ltXscSnLEv3rgCa4m7PcoYZeUT9BngugpFCmVoNevbaRtYijjdfiUuLmXfT61lO5QbR6nEhn2RZMK8ow=="],

-    "@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@0.5.10", "", { "dependencies": { "@babel/core": "7.28.0", "@babel/preset-typescript": "7.27.1", "@opentui/core": "0.5.10", "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-KrmMIsHiKBHOABTC0brOwqWm+sGq1ZX2sGCAx6WgtBbE3STMup9n8TAy/6gUYhwcjC9zugT53ytfSVwCwVWZUg=="],

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

@@ -4322,7 +4322,7 @@

    "is-decimal": ["is-decimal@2.0.1", "", {}, "sha512-AAB9hiomQs5DXWcRB1rqsxGUstbRroFOPPVAomNk/3XHR5JyEZChOyTWe2oayKnsSsr/kcGqF+z6yuH6HHpN0A=="],

-    "is-docker": ["is-docker@4.0.0", "", { "bin": { "is-docker": "cli.js" } }, "sha512-LHE+wROyG/Y/0ZnbktRCoTix2c1RhgWaZraMZ8o1Q7zCh0VSrICJQO5oqIIISrcSBtrXv0o233w1IYwsWCjTzA=="],
+    "is-docker": ["is-docker@3.0.0", "", { "bin": { "is-docker": "cli.js" } }, "sha512-eljcgEDlEns/7AXFosB5K/2nCM4P7FQPkGc/DWLy5rmFEWvZayGrik1d9/QIY5nJ4f9YsVvBkA6kJpHn9rISdQ=="],

    "is-document.all": ["is-document.all@1.0.0", "", { "dependencies": { "call-bound": "^1.0.4" } }, "sha512-+XSoyS05OdBbhFuELhgTCpFNHkpBOJqtsZfUFFpe5QTw+9Sjbh8zitxhQkYAo6wV7e1Vb8cAPvpCk9jGam/82g=="],

@@ -4340,8 +4340,6 @@

    "is-hexadecimal": ["is-hexadecimal@2.0.1", "", {}, "sha512-DgZQp241c8oO6cA1SbTEWiXeoxV42vlcJxgH+B3hi1AiqqKruZR3ZGF8In3fj4+/y/7rHvlOZLZtgJ/4ttYGZg=="],

-    "is-in-ssh": ["is-in-ssh@1.0.0", "", {}, "sha512-jYa6Q9rH90kR1vKB6NM7qqd1mge3Fx4Dhw5TVlK1MUBqhEOuCagrEHMevNuCcbECmXZ0ThXkRm+Ymr51HwEPAw=="],
-
    "is-inside-container": ["is-inside-container@1.0.0", "", { "dependencies": { "is-docker": "^3.0.0" }, "bin": { "is-inside-container": "cli.js" } }, "sha512-KIYLCCJghfHZxqjYBE7rEy0OBuTd5xCHS7tHVgvCLkx7StIoaxwNW3hCALgEUjFfeRk+MG/Qxmp/vtETEF3tRA=="],

    "is-map": ["is-map@2.0.3", "", {}, "sha512-1Qed0/Hr2m+YqxnM09CjA2d/i6YZNfF6R2oRAOj36eUdS6qIV/huPJNSEpKbupewFs+ZsJlxsjjPbc0/afW6Lw=="],
@@ -4388,7 +4386,7 @@

    "is-whitespace": ["is-whitespace@0.3.0", "", {}, "sha512-RydPhl4S6JwAyj0JJjshWJEFG6hNye3pZFBRZaTUfZFwGHxzppNaNOVgQuS/E/SlhrApuMXrpnK1EEIXfdo3Dg=="],

-    "is-wsl": ["is-wsl@2.2.0", "", { "dependencies": { "is-docker": "^2.0.0" } }, "sha512-fKzAra0rGJUUBwGBgNkHZuToZcn+TtXHpeCgmkMJMMYx1sQDYaCSyjJBSCa2nH1DGm7s3n1oBnohoVTBaN7Lww=="],
+    "is-wsl": ["is-wsl@3.1.1", "", { "dependencies": { "is-inside-container": "^1.0.0" } }, "sha512-e6rvdUCiQCAuumZslxRJWR/Doq4VpPR82kqclvcS0efgt430SlGIk05vdCN58+VrzgtIcfNODjozVielycD4Sw=="],

    "isarray": ["isarray@1.0.0", "", {}, "sha512-VLghIWNM6ELQzo7zwmcg0NmTVyWKYjvIeM83yjp0wRDTmUnrM678fQbcKBo6n2CJEF0szoG//ytg+TKla89ALQ=="],

@@ -4852,7 +4850,7 @@

    "oniguruma-to-es": ["oniguruma-to-es@4.3.6", "", { "dependencies": { "oniguruma-parser": "^0.12.2", "regex": "^6.1.0", "regex-recursion": "^6.0.2" } }, "sha512-csuQ9x3Yr0cEIs/Zgx/OEt9iBw9vqIunAPQkx19R/fiMq2oGVTgcMqO/V3Ybqefr1TBvosI6jU539ksaBULJyA=="],

-    "open": ["open@11.0.4", "", { "dependencies": { "default-browser": "^5.5.1", "define-lazy-prop": "^3.0.0", "is-in-ssh": "^1.0.0", "is-inside-container": "^1.0.0", "powershell-utils": "^0.2.1", "wsl-utils": "^1.0.0" } }, "sha512-++Zlftm0kVLPmzC06t6epuWmcRMDbI4z5P3NNX979WA/k23+NtSOynEGzsVfZwguKw2mi5umVgnBlJQMwRz4Pg=="],
+    "open": ["open@10.1.2", "", { "dependencies": { "default-browser": "^5.2.1", "define-lazy-prop": "^3.0.0", "is-inside-container": "^1.0.0", "is-wsl": "^3.1.0" } }, "sha512-cxN6aIDPz6rm8hbebcP7vrQNhvRcveZoJU72Y7vskh4oIm+BZwBECnx5nTmrlres1Qapvx27Qo1Auukpf8PKXw=="],

    "openai": ["openai@6.49.0", "", { "peerDependencies": { "@aws-sdk/credential-provider-node": ">=3.972.0 <4", "@smithy/hash-node": ">=4.3.0 <5", "@smithy/signature-v4": ">=5.4.0 <6", "ws": "^8.18.0", "zod": "^3.25 || ^4.0" }, "optionalPeers": ["@aws-sdk/credential-provider-node", "@smithy/hash-node", "@smithy/signature-v4", "ws", "zod"] }, "sha512-aYCc0C6L864eR6WSYIwQGyXriw/nIyZx0ObvhzOEVuk0zoBDpynjSbrionWI7q65B5H8jJX0DXR9snEzM6bfPg=="],

@@ -4996,8 +4994,6 @@

    "postject": ["postject@1.0.0-alpha.6", "", { "dependencies": { "commander": "^9.4.0" }, "bin": { "postject": "dist/cli.js" } }, "sha512-b9Eb8h2eVqNE8edvKdwqkrY6O7kAwmI8kcnBv1NScolYJbo59XUF0noFq+lxbC1yN20bmC0WBEbDC5H/7ASb0A=="],

-    "powershell-utils": ["powershell-utils@0.2.1", "", {}, "sha512-C+y9x90UElAddDZmV4qOx9W53B61PO7cIqWz2dQsWlwswuq4mr8NEwytdGKboYbQlGZ3awrkTeNvcZiZNHnQ8A=="],
-
    "preact": ["preact@11.0.0-beta.0", "", {}, "sha512-IcODoASASYwJ9kxz7+MJeiJhvLriwSb4y4mHIyxdgaRZp6kPUud7xytrk/6GZw8U3y6EFJaRb5wi9SrEK+8+lg=="],

    "preact-render-to-string": ["preact-render-to-string@6.6.5", "", { "peerDependencies": { "preact": ">=10 || >= 11.0.0-0" } }, "sha512-O6MHzYNIKYaiSX3bOw0gGZfEbOmlIDtDfWwN1JJdc/T3ihzRT6tGGSEWE088dWrEDGa1u7101q+6fzQnO9XCPA=="],
@@ -5818,7 +5814,7 @@

    "ws": ["ws@8.21.0", "", { "peerDependencies": { "bufferutil": "^4.0.1", "utf-8-validate": ">=5.0.2" }, "optionalPeers": ["bufferutil", "utf-8-validate"] }, "sha512-Vsp28b7DRcimFQvrqu2Wek3z1iYxDCWqHYB8Qsnk/S4RfaCQzPGPyBNuVjJV3cd6UiKtUtp6sNM77gWvzcCH+g=="],

-    "wsl-utils": ["wsl-utils@1.0.0", "", { "dependencies": { "is-wsl": "^3.1.0", "powershell-utils": "^0.1.0" } }, "sha512-Hl0ZOAs672vg+06kfujwRhoS6/jehvULrlFkuF2dRu6pHgA8U06h3xqNIqNNU1LTXPcedxByAR4GS6pwQK0mgA=="],
+    "wsl-utils": ["wsl-utils@0.1.0", "", { "dependencies": { "is-wsl": "^3.1.0" } }, "sha512-h3Fbisa2nKGPxCpm89Hk33lBLsnaGBvctQopaBSOW/uIs6FTe1ATyAnKFJrzVs9vpGdsTe73WF3V4lIsk4Gacw=="],

    "xdg-basedir": ["xdg-basedir@5.1.0", "", {}, "sha512-GCPAHLvrIH13+c0SuacwvRYj2SxJXQ4kaVTT5xgL3kPrz56XxkF21IGhjSE1+W0aw7gpBWRGXLCPnPby6lSpmQ=="],

@@ -5914,6 +5910,8 @@

    "@astrojs/telemetry/ci-info": ["ci-info@4.4.0", "", {}, "sha512-77PSwercCZU2Fc4sX94eF8k8Pxte6JAwL4/ICZLFjJLqegs7kCuAsqqj/70NQF6TvDpgFjkubQB2FW2ZZddvQg=="],

+    "@astrojs/telemetry/is-docker": ["is-docker@4.0.0", "", { "bin": { "is-docker": "cli.js" } }, "sha512-LHE+wROyG/Y/0ZnbktRCoTix2c1RhgWaZraMZ8o1Q7zCh0VSrICJQO5oqIIISrcSBtrXv0o233w1IYwsWCjTzA=="],
+
    "@aws-crypto/crc32/@aws-sdk/types": ["@aws-sdk/types@3.974.4", "", { "dependencies": { "@smithy/types": "^4.16.1", "tslib": "^2.6.2" } }, "sha512-dSFDNG00MEz0/xl5gxL62giLd1iYyJsTxZ1I1DOj6lC+bbgLB4TRsYClJg3b62dhXT1uATzsTNXPnC+33EJV3A=="],

    "@aws-crypto/crc32c/@aws-sdk/types": ["@aws-sdk/types@3.974.4", "", { "dependencies": { "@smithy/types": "^4.16.1", "tslib": "^2.6.2" } }, "sha512-dSFDNG00MEz0/xl5gxL62giLd1iYyJsTxZ1I1DOj6lC+bbgLB4TRsYClJg3b62dhXT1uATzsTNXPnC+33EJV3A=="],
@@ -6396,6 +6394,8 @@

    "builder-util/js-yaml": ["js-yaml@4.3.1", "", { "dependencies": { "argparse": "^2.0.1" }, "bin": { "js-yaml": "bin/js-yaml.js" } }, "sha512-CY6crGq313MX8GkwvB7tzgp99vjQxY1++5y10/BKN/GUfHqWaOGQMNZkBvqSzsZKWk/ijwHlWzzkLulsGHhjWQ=="],

+    "chrome-launcher/is-wsl": ["is-wsl@2.2.0", "", { "dependencies": { "is-docker": "^2.0.0" } }, "sha512-fKzAra0rGJUUBwGBgNkHZuToZcn+TtXHpeCgmkMJMMYx1sQDYaCSyjJBSCa2nH1DGm7s3n1oBnohoVTBaN7Lww=="],
+
    "chromium-bidi/zod": ["zod@3.25.76", "", {}, "sha512-gzUt/qt81nXsFGKIFcC3YnfEAx5NkunCfnDlvuBSSFS02bcXu4Lmea0AFIUwbLWxWPx3d9p8S5QoaujKcNQxcQ=="],

    "clean-css/source-map": ["source-map@0.6.1", "", {}, "sha512-UjgapumWlbMhkBgzT7Ykc5YXUT46F0iKu8SGXq0bcwP5dz/h0Plj6enJqjz1Zbq2l5WaqYnrVbwWOWMyF3F47g=="],
@@ -6500,10 +6500,6 @@

    "import-in-the-middle/es-module-lexer": ["es-module-lexer@2.3.2", "", {}, "sha512-poHGpORABojJJucnV9KbOavETW8lBVnphkW77ER5/BQ5Fz7oXSoCNek7IH3vR5nRjdsEz926ibFYX8KtLQmdyw=="],

-    "is-inside-container/is-docker": ["is-docker@3.0.0", "", { "bin": { "is-docker": "cli.js" } }, "sha512-eljcgEDlEns/7AXFosB5K/2nCM4P7FQPkGc/DWLy5rmFEWvZayGrik1d9/QIY5nJ4f9YsVvBkA6kJpHn9rISdQ=="],
-
-    "is-wsl/is-docker": ["is-docker@2.2.1", "", { "bin": { "is-docker": "cli.js" } }, "sha512-F+i2BKsFrH66iaUFc0woD8sLy8getkwTwtOBjvs56Cx4CgJDeKQeqfz8wAYiSb8JOprWhHH5p77PbmYCvvUuXQ=="],
-
    "js-beautify/glob": ["glob@10.5.0", "", { "dependencies": { "foreground-child": "^3.1.0", "jackspeak": "^3.1.2", "minimatch": "^9.0.4", "minipass": "^7.1.2", "package-json-from-dist": "^1.0.0", "path-scurry": "^1.11.1" }, "bin": { "glob": "dist/esm/bin.mjs" } }, "sha512-DfXN8DfhJ7NH3Oe7cFmu3NCu1wKbkReJ8TorzSAFbSKrlNaQSKfIzqYqVY8zlbs2NLBbWpRiU52GX2PbaBVNkg=="],

    "js-beautify/nopt": ["nopt@7.2.1", "", { "dependencies": { "abbrev": "^2.0.0" }, "bin": { "nopt": "bin/nopt.js" } }, "sha512-taM24ViiimT/XntxbPyJQzCG+p4EKOpgD3mxFwW38mGjVUrfERQOeY4EDHjdnptttfHuHQXFx+lTP08Q+mLa/w=="],
@@ -6514,6 +6510,8 @@

    "lighthouse/devtools-protocol": ["devtools-protocol@0.0.1663043", "", {}, "sha512-33aOY3ZnBP1dgZsshgaL+/XlsQleiFZgyUaDtdZkEa1nbZhVY1MoDeWjk+wxg25fU924l1ZJfoGNmjjeA/5s1w=="],

+    "lighthouse/open": ["open@8.4.2", "", { "dependencies": { "define-lazy-prop": "^2.0.0", "is-docker": "^2.1.1", "is-wsl": "^2.2.0" } }, "sha512-7x81NCL719oNbsq/3mh+hVrAWmFuEYUqrq/Iw3kUzH8ReypT9QQ0BLoJS7/G9k6N81XjW4qHWtjWwe/9eLy1EQ=="],
+
    "lighthouse/ws": ["ws@7.5.13", "", { "peerDependencies": { "bufferutil": "^4.0.1", "utf-8-validate": "^5.0.2" }, "optionalPeers": ["bufferutil", "utf-8-validate"] }, "sha512-rsKI6xDBFVf4r/x8XyChGK04QR/XHroxs/jUcoWvtEZM8TPU/X/uIY9B1CsSzYws9ZJb/6bbBu7dPhFW00CAoA=="],

    "md-to-react-email/marked": ["marked@7.0.4", "", { "bin": { "marked": "bin/marked.js" } }, "sha512-t8eP0dXRJMtMvBojtkcsA7n48BkauktUKzfkPSCq85ZMTJ0v76Rke4DYz01omYpPTUh4p/f7HePgRo3ebG8+QQ=="],
@@ -6616,6 +6614,8 @@

    "sst/jose": ["jose@5.2.3", "", {}, "sha512-KUXdbctm1uHVL8BYhnyHkgp3zDX5KW8ZhAKVFEfUbU2P8Alpzjb+48hHvjOdQIyPshoblhzsuqOwEEAbtHVirA=="],

+    "storybook/open": ["open@10.2.0", "", { "dependencies": { "default-browser": "^5.2.1", "define-lazy-prop": "^3.0.0", "is-inside-container": "^1.0.0", "wsl-utils": "^0.1.0" } }, "sha512-YgBpdJHPyQ2UE5x+hlSXcnejzAvD0b22U2OuAP+8OnlJT+PjWPxtgmGqKKc+RgTM63U9gN0YzrYc71R2WT/hTA=="],
+
    "storybook-solidjs-vite/semver": ["semver@7.8.1", "", { "bin": { "semver": "bin/semver.js" } }, "sha512-rkVq3IXh+4FDGch+KwzX3aV9W3kO54GyEgpvBzSyctDA6Xtd7RJQV1xmXbeQp5v7+VzLOfVqiutSE6GICgPFvg=="],

    "storybook-solidjs-vite/vite": ["vite@7.1.11", "", { "dependencies": { "esbuild": "^0.25.0", "fdir": "^6.5.0", "picomatch": "^4.0.3", "postcss": "^8.5.6", "rollup": "^4.43.0", "tinyglobby": "^0.2.15" }, "optionalDependencies": { "fsevents": "~2.3.3" }, "peerDependencies": { "@types/node": "^20.19.0 || >=22.12.0", "jiti": ">=1.21.0", "less": "^4.0.0", "lightningcss": "^1.21.0", "sass": "^1.70.0", "sass-embedded": "^1.70.0", "stylus": ">=0.54.8", "sugarss": "^5.0.0", "terser": "^5.16.0", "tsx": "^4.8.1", "yaml": "^2.4.2" }, "optionalPeers": ["@types/node", "jiti", "less", "lightningcss", "sass", "sass-embedded", "stylus", "sugarss", "terser", "tsx", "yaml"], "bin": { "vite": "bin/vite.js" } }, "sha512-uzcxnSDVjAopEUjljkWh8EIrg6tlzrjFUfMcR1EVsRDGwf/ccef0qQPRyOrROwhrTDaApueq+ja+KLPlzR/zdg=="],
@@ -6702,10 +6702,6 @@

    "write-file-atomic/signal-exit": ["signal-exit@4.1.0", "", {}, "sha512-bzyZ1e88w9O1iNJbKnOlvYTrWPDl46O1bG0D3XInv+9tkPrxrN8jUUTiFlDkkmKWgn1M6CfIA13SuGqOa9Korw=="],

-    "wsl-utils/is-wsl": ["is-wsl@3.1.1", "", { "dependencies": { "is-inside-container": "^1.0.0" } }, "sha512-e6rvdUCiQCAuumZslxRJWR/Doq4VpPR82kqclvcS0efgt430SlGIk05vdCN58+VrzgtIcfNODjozVielycD4Sw=="],
-
-    "wsl-utils/powershell-utils": ["powershell-utils@0.1.0", "", {}, "sha512-dM0jVuXJPsDN6DvRpea484tCUaMiXWjuCn++HGTqUWzGDjv5tZkEZldAJ/UMlqRYGFrD/etByo4/xOuC/snX2A=="],
-
    "yaml-language-server/prettier": ["prettier@3.9.6", "", { "bin": { "prettier": "bin/prettier.cjs" } }, "sha512-OpN0zzVdiaiAhxpuuj5efpIS4sY9j7bY6uR5mnj5yPzGkdkjNKSJeUThPb60Jw29QuAZgA4o+/iB49kFiaBX6g=="],

    "yaml-language-server/request-light": ["request-light@0.5.8", "", {}, "sha512-3Zjgh+8b5fhRJBQZoy+zbVKpAQGLyka0MPgW3zruTF4dFFJ8Fqcfu9YsAvi/rvdcaTeWG3MkbZv4WKxAn/84Lg=="],
@@ -7340,6 +7336,8 @@

    "builder-util/js-yaml/argparse": ["argparse@2.0.1", "", {}, "sha512-8+9WqebbFzpX9OR+Wa6O29asIogeRMzcGtAINdpMHHyAg10f05aSFVBbcEqGf/PXw1EjAZ+q2/bEBg3DvurK3Q=="],

+    "chrome-launcher/is-wsl/is-docker": ["is-docker@2.2.1", "", { "bin": { "is-docker": "cli.js" } }, "sha512-F+i2BKsFrH66iaUFc0woD8sLy8getkwTwtOBjvs56Cx4CgJDeKQeqfz8wAYiSb8JOprWhHH5p77PbmYCvvUuXQ=="],
+
    "cliui/string-width/emoji-regex": ["emoji-regex@8.0.0", "", {}, "sha512-MSjYzcWNOA0ewAHpz0MxpYFvwg6yjy1NG3xteoqz644VCo/RPgnr1/GGt+ic3iJTzQ8Eu3TdM14SawnVUmGE6A=="],

    "cliui/strip-ansi/ansi-regex": ["ansi-regex@5.0.1", "", {}, "sha512-quJQXlTSUGL2LH9SUXo8VwsY4soanhgo6LNSm84E1LBcE8s3O0wpdiRzyR9z/ZZJMlMWv37qOOb9pdJlMUEKFQ=="],
@@ -7400,6 +7398,12 @@

    "lazystream/readable-stream/string_decoder": ["string_decoder@1.1.1", "", { "dependencies": { "safe-buffer": "~5.1.0" } }, "sha512-n/ShnvDi6FHbbVfviro+WojiFzv+s8MPMHBczVePfUpDJLwoLT0ht1l4YwBCbi8pJAveEEdnkHyPyTP/mzRfwg=="],

+    "lighthouse/open/define-lazy-prop": ["define-lazy-prop@2.0.0", "", {}, "sha512-Ds09qNh8yw3khSjiJjiUInaGX9xlqZDY7JVryGxdxV7NPeuqQfplOpQ66yJFZut3jLa5zOwkXw1g9EI2uKh4Og=="],
+
+    "lighthouse/open/is-docker": ["is-docker@2.2.1", "", { "bin": { "is-docker": "cli.js" } }, "sha512-F+i2BKsFrH66iaUFc0woD8sLy8getkwTwtOBjvs56Cx4CgJDeKQeqfz8wAYiSb8JOprWhHH5p77PbmYCvvUuXQ=="],
+
+    "lighthouse/open/is-wsl": ["is-wsl@2.2.0", "", { "dependencies": { "is-docker": "^2.0.0" } }, "sha512-fKzAra0rGJUUBwGBgNkHZuToZcn+TtXHpeCgmkMJMMYx1sQDYaCSyjJBSCa2nH1DGm7s3n1oBnohoVTBaN7Lww=="],
+
    "miniflare/sharp/@img/sharp-darwin-arm64": ["@img/sharp-darwin-arm64@0.33.5", "", { "optionalDependencies": { "@img/sharp-libvips-darwin-arm64": "1.0.4" }, "os": "darwin", "cpu": "arm64" }, "sha512-UT4p+iz/2H4twwAoLCqfA9UH5pI6DggwKEGuaPy7nCVQ8ZsiY5PIcrRvD1DzuY3qYL07NtIQcWnBSY/heikIFQ=="],

    "miniflare/sharp/@img/sharp-darwin-x64": ["@img/sharp-darwin-x64@0.33.5", "", { "optionalDependencies": { "@img/sharp-libvips-darwin-x64": "1.0.4" }, "os": "darwin", "cpu": "x64" }, "sha512-fyHac4jIc1ANYGRDxtiqelIbdWkIuQaI84Mv45KvGRRxSAa7o7d1ZKAOBaYbnepLC1WqxfpimdeWfvqqSGwR2Q=="],
@@ -7670,10 +7674,6 @@

    "@astrojs/starlight/@astrojs/mdx/@astrojs/markdown-remark/shiki": ["shiki@3.23.0", "", { "dependencies": { "@shikijs/core": "3.23.0", "@shikijs/engine-javascript": "3.23.0", "@shikijs/engine-oniguruma": "3.23.0", "@shikijs/langs": "3.23.0", "@shikijs/themes": "3.23.0", "@shikijs/types": "3.23.0", "@shikijs/vscode-textmate": "^10.0.2", "@types/hast": "^3.0.4" } }, "sha512-55Dj73uq9ZXL5zyeRPzHQsK7Nbyt6Y10k5s7OjuFZGMhpp4r/rsLBH0o/0fstIzX1Lep9VxefWljK/SKCzygIA=="],

-    "@astrojs/starlight/astro/@astrojs/telemetry/is-docker": ["is-docker@3.0.0", "", { "bin": { "is-docker": "cli.js" } }, "sha512-eljcgEDlEns/7AXFosB5K/2nCM4P7FQPkGc/DWLy5rmFEWvZayGrik1d9/QIY5nJ4f9YsVvBkA6kJpHn9rISdQ=="],
-
-    "@astrojs/starlight/astro/@astrojs/telemetry/is-wsl": ["is-wsl@3.1.1", "", { "dependencies": { "is-inside-container": "^1.0.0" } }, "sha512-e6rvdUCiQCAuumZslxRJWR/Doq4VpPR82kqclvcS0efgt430SlGIk05vdCN58+VrzgtIcfNODjozVielycD4Sw=="],
-
    "@astrojs/starlight/astro/p-queue/p-timeout": ["p-timeout@6.1.4", "", {}, "sha512-MyIV3ZA/PmyBN/ud8vV9XzwTrNtR4jFrObymZYnZqMmW0zA8Z17vnT0rBgFE/TlohB+YCHqXMgZzb3Csp49vqg=="],

    "@astrojs/starlight/astro/sharp/@img/sharp-darwin-arm64": ["@img/sharp-darwin-arm64@0.33.5", "", { "optionalDependencies": { "@img/sharp-libvips-darwin-arm64": "1.0.4" }, "os": "darwin", "cpu": "arm64" }, "sha512-UT4p+iz/2H4twwAoLCqfA9UH5pI6DggwKEGuaPy7nCVQ8ZsiY5PIcrRvD1DzuY3qYL07NtIQcWnBSY/heikIFQ=="],
@@ -8076,10 +8076,6 @@

    "@opencode/web/@astrojs/cloudflare/wrangler/workerd": ["workerd@1.20260708.1", "", { "optionalDependencies": { "@cloudflare/workerd-darwin-64": "1.20260708.1", "@cloudflare/workerd-darwin-arm64": "1.20260708.1", "@cloudflare/workerd-linux-64": "1.20260708.1", "@cloudflare/workerd-linux-arm64": "1.20260708.1", "@cloudflare/workerd-windows-64": "1.20260708.1" }, "bin": { "workerd": "bin/workerd" } }, "sha512-WAK+Kt/VVCSldH2qSr8lx46XCJ4Q+bdlHNaFqUtOHthBEIB8C1N8HVW+VOLrxDoTCk0NGNv0zajnBeQK4JOB9w=="],

-    "@opencode/web/astro/@astrojs/telemetry/is-docker": ["is-docker@3.0.0", "", { "bin": { "is-docker": "cli.js" } }, "sha512-eljcgEDlEns/7AXFosB5K/2nCM4P7FQPkGc/DWLy5rmFEWvZayGrik1d9/QIY5nJ4f9YsVvBkA6kJpHn9rISdQ=="],
-
-    "@opencode/web/astro/@astrojs/telemetry/is-wsl": ["is-wsl@3.1.1", "", { "dependencies": { "is-inside-container": "^1.0.0" } }, "sha512-e6rvdUCiQCAuumZslxRJWR/Doq4VpPR82kqclvcS0efgt430SlGIk05vdCN58+VrzgtIcfNODjozVielycD4Sw=="],
-
    "@opencode/web/astro/js-yaml/argparse": ["argparse@2.0.1", "", {}, "sha512-8+9WqebbFzpX9OR+Wa6O29asIogeRMzcGtAINdpMHHyAg10f05aSFVBbcEqGf/PXw1EjAZ+q2/bEBg3DvurK3Q=="],

    "@opencode/web/astro/p-queue/p-timeout": ["p-timeout@6.1.4", "", {}, "sha512-MyIV3ZA/PmyBN/ud8vV9XzwTrNtR4jFrObymZYnZqMmW0zA8Z17vnT0rBgFE/TlohB+YCHqXMgZzb3Csp49vqg=="],
@@ -8220,10 +8216,6 @@

    "archiver-utils/glob/path-scurry/lru-cache": ["lru-cache@10.4.3", "", {}, "sha512-JNAzZcXrCt42VGLuYz0zfAzDfAvJWW6AfYlDBQyDV5DClI2m5sAmK+OIO7s59XfsRsWHp02jAJrRadPRGTt6SQ=="],

-    "astro-expressive-code/astro/@astrojs/telemetry/is-docker": ["is-docker@3.0.0", "", { "bin": { "is-docker": "cli.js" } }, "sha512-eljcgEDlEns/7AXFosB5K/2nCM4P7FQPkGc/DWLy5rmFEWvZayGrik1d9/QIY5nJ4f9YsVvBkA6kJpHn9rISdQ=="],
-
-    "astro-expressive-code/astro/@astrojs/telemetry/is-wsl": ["is-wsl@3.1.1", "", { "dependencies": { "is-inside-container": "^1.0.0" } }, "sha512-e6rvdUCiQCAuumZslxRJWR/Doq4VpPR82kqclvcS0efgt430SlGIk05vdCN58+VrzgtIcfNODjozVielycD4Sw=="],
-
    "astro-expressive-code/astro/js-yaml/argparse": ["argparse@2.0.1", "", {}, "sha512-8+9WqebbFzpX9OR+Wa6O29asIogeRMzcGtAINdpMHHyAg10f05aSFVBbcEqGf/PXw1EjAZ+q2/bEBg3DvurK3Q=="],

    "astro-expressive-code/astro/p-queue/p-timeout": ["p-timeout@6.1.4", "", {}, "sha512-MyIV3ZA/PmyBN/ud8vV9XzwTrNtR4jFrObymZYnZqMmW0zA8Z17vnT0rBgFE/TlohB+YCHqXMgZzb3Csp49vqg=="],
@@ -8326,10 +8318,6 @@

    "temp/rimraf/glob/minimatch": ["minimatch@3.1.5", "", { "dependencies": { "brace-expansion": "^1.1.7" } }, "sha512-VgjWUsnnT6n+NUk6eZq77zeFdpW2LWDzP6zFGrCbHXiYNul5Dzqk2HHQ5uFH2DNW5Xbp8+jVzaeNt94ssEEl4w=="],

-    "toolbeam-docs-theme/astro/@astrojs/telemetry/is-docker": ["is-docker@3.0.0", "", { "bin": { "is-docker": "cli.js" } }, "sha512-eljcgEDlEns/7AXFosB5K/2nCM4P7FQPkGc/DWLy5rmFEWvZayGrik1d9/QIY5nJ4f9YsVvBkA6kJpHn9rISdQ=="],
-
-    "toolbeam-docs-theme/astro/@astrojs/telemetry/is-wsl": ["is-wsl@3.1.1", "", { "dependencies": { "is-inside-container": "^1.0.0" } }, "sha512-e6rvdUCiQCAuumZslxRJWR/Doq4VpPR82kqclvcS0efgt430SlGIk05vdCN58+VrzgtIcfNODjozVielycD4Sw=="],
-
    "toolbeam-docs-theme/astro/js-yaml/argparse": ["argparse@2.0.1", "", {}, "sha512-8+9WqebbFzpX9OR+Wa6O29asIogeRMzcGtAINdpMHHyAg10f05aSFVBbcEqGf/PXw1EjAZ+q2/bEBg3DvurK3Q=="],

    "toolbeam-docs-theme/astro/p-queue/p-timeout": ["p-timeout@6.1.4", "", {}, "sha512-MyIV3ZA/PmyBN/ud8vV9XzwTrNtR4jFrObymZYnZqMmW0zA8Z17vnT0rBgFE/TlohB+YCHqXMgZzb3Csp49vqg=="],
@@ -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-+Clo0VPDdruHSoBNvV/wKAM8iR6HJPtB00oa8yl9ujU=",
+    "aarch64-linux": "sha256-4wU5v36GTXjwyt5ls4FH+5G43Ujd+dKVSJR21w3lhbA=",
+    "aarch64-darwin": "sha256-pThjoD6baddQ6biy7k1ByXwGwLAeWe/+w0tcYmt1uWs=",
+    "x86_64-darwin": "sha256-bCBl63CqBiqilb+YdaOLBYYZx/yf47c1aqgDOkgdegg="
  }
 }
@@ -2,7 +2,7 @@
  "$schema": "https://json.schemastore.org/package.json",
  "name": "opencode",
  "description": "AI-powered development tool",
-  "version": "2.0.18",
+  "version": "2.0.16",
  "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": "0.5.10",
+      "@opentui/keymap": "0.5.10",
+      "@opentui/solid": "0.5.10",
      "@tanstack/solid-virtual": "3.13.37",
      "@shikijs/stream": "4.4.3",
      "@standard-schema/spec": "1.1.0",
@@ -162,7 +162,6 @@
    "@types/node": "catalog:",
    "bun-types": "1.4.2",
    "effect": "catalog:",
-    "open": "11.0.4",
    "solid-js": "catalog:"
  },
  "patchedDependencies": {
@@ -10,11 +10,11 @@

 ## Conventions

-Per-type constructors live on the type, not as top-level re-exports. Use `Message.system(...)`, `Message.user(...)`, `Message.assistant(...)`, `Message.tool(...)`, `Message.media(...)`, `LanguageModel.make(...)`, `ToolDefinition.make(...)`, `ToolCallPart.make(...)`, `ToolResultPart.make(...)`, `ToolChoice.make(...)`, `ToolChoice.named(...)`, `SystemPart.make(...)`, and `GenerationOptions.make(...)` directly. The top-level `LLM` namespace is reserved for request-shaped call APIs: `LLM.request`, `LLM.generate`, `LLM.stream`, and `LLM.generateObject`. `LLM.generate`/`LLM.stream` and Promise `ai.llm.generate`/`ai.llm.stream` accept ergonomic input or an `LLMRequest`; both paths use the same canonical request. Core still builds, logs, replays, and updates that durable `LLMRequest` boundary. Use `LLMRequest.update(...)` when deriving canonical request data; do not add a duplicate `LLM.updateRequest(...)` path.
+Per-type constructors live on the type, not as top-level re-exports. Use `Message.system(...)`, `Message.user(...)`, `Message.assistant(...)`, `Message.tool(...)`, `Message.media(...)`, `LanguageModel.make(...)`, `ToolDefinition.make(...)`, `ToolCallPart.make(...)`, `ToolResultPart.make(...)`, `ToolChoice.make(...)`, `ToolChoice.named(...)`, `SystemPart.make(...)`, and `GenerationOptions.make(...)` directly. The top-level `LLM` namespace is reserved for request-shaped call APIs: `LLM.request`, `LLM.generate`, `LLM.stream`, and `LLM.generateObject`. Use `LLMRequest.update(...)` when deriving canonical request data; do not add a duplicate `LLM.updateRequest(...)` path. Two ways to construct the same thing is one too many.

-Modality namespaces mirror `LLM` exactly: `Image.request`, `Image.generate`, `Image.stream`, and the same for `Video`, `Speech`, and `Transcription`. Common request fields (`images`, `mask`, `n`, `size`, `aspectRatio`, `seed`, `format`) lower natively or fail with a typed `AIError`; provider-native controls always live under `providerOptions`, never under a modality-specific `options` key.
+Modality namespaces mirror `LLM` exactly: `Image.request`, `Image.generate`, `Image.stream` (later `Video`, `Speech`, `Transcription`). Common request fields (`images`, `mask`, `n`, `size`, `aspectRatio`, `seed`, `format`) lower natively or fail with a typed `AIError`; provider-native controls always live under `providerOptions`, never under a modality-specific `options` key.

-Media payloads are always `Media.Asset` (`src/media.ts`). Construct them with `Media.bytes`, `Media.base64`, `Media.url`, `Media.ref`, `Media.fromDataUrl`, or `Media.file`; never introduce a parallel `data: string | Uint8Array` shape. `MediaPart.media`, `ImageRequest.images`/`mask`, `ImageResponse.images`, and the `media` `LLMEvent` all share it. Protocols branch on `asset.source.type` and `asset.kind` and use `ProviderShared.requireInlineMedia` / `inlineRequired` / `mediaUrl` / `mediaReference` and `MediaInput.inlineBytes` / `refID` rather than re-deriving base64 or URL handling.
+Media payloads are always `Media.Asset` (`src/media.ts`). Construct them with `Media.bytes`, `Media.base64`, `Media.url`, `Media.ref`, `Media.fromDataUrl`, or `Media.file`; never introduce a parallel `data: string | Uint8Array` shape. `MediaPart.media`, `ImageRequest.images`/`mask`, `ImageResponse.images`, and the `media` `LLMEvent` all share it. Protocols branch on `asset.source.type` and `asset.kind` and use `ProviderShared.inlineMedia` / `requireInlineMedia` / `mediaUrl` / `MediaInput.refID` rather than re-deriving base64 or URL handling.

 `schema/messages.ts → media.ts → route/executor-service.ts` is an accepted runtime dependency from the schema layer on the executor service tag: `Media.Asset.bytes()` must be able to download `url` sources, and the tag lives in that leaf module precisely so the schema barrel never imports the executor implementation (which imports the schema barrel back). Do not move the tag into `route/executor.ts` or import `route/executor.ts` from `src/schema/*` or `src/media.ts`.

@@ -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`, 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.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`).
+Transcription uses all three kinds (OpenAI and Gemini stream, Deepgram is inline, AssemblyAI is queued): every route carries its `kind` and `TranscriptionClient` dispatches on it. `ImageRoute` is the same union; both clients dispatch through `MediaRoute.dispatch` and models compose through `composeAnyRoute`, and 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

@@ -112,7 +112,7 @@ For providers where the URL is derived from typed inputs (Azure resource name, B

 ### Provider Facades

-Provider-facing APIs are configured facades over route values. Endpoint/auth/resource/API-version setup happens before model selection, and model selectors accept only a model or deployment id. Media models use per-modality selectors on the same facade (`openai.image(id)`, `.speech(id)`, `.transcription(id)`, `google.video(id)`) that mirror `openai.responses(id)`; the one-word overlap with the request namespace is accepted over a second construction path:
+Provider-facing APIs are configured facades over route values. Endpoint/auth/resource/API-version setup happens before model selection, and model selectors accept only a model or deployment id. Media models use per-modality selectors on the same facade (`openai.image(id)`, later `.video` / `.speech` / `.transcription`) that mirror `openai.responses(id)`; the one-word overlap with the request namespace is accepted over a second construction path:

 ```ts
 const openai = OpenAI.configure({ apiKey, baseURL })
@@ -275,7 +275,6 @@ Use this order for every protocol module:
 ### Rules

 - Keep protocol files focused on the protocol. Move provider-specific projection, signing, media normalization, or other bulky transformations into `src/protocols/utils/*`.
- Send `tool.inputSchema` as given. `prepareRequest` applies the tool schema rules (`ToolSchemaProjection.tools`) once per request, including tools in namespaces. A protocol whose API needs a model family's rules for every model declares `sanitizer` instead of transforming schemas itself.
 - Use `Effect.fn("Provider.fromRequest")` for request body construction entrypoints. Use `Effect.fn(...)` for event handlers that yield effects; keep purely synchronous handlers as plain functions returning a `StepResult` that the dispatcher lifts via `Effect.succeed(...)`.
 - Parser state owns terminal information. The state machine records finish reason, usage, and pending tool calls; emit one terminal `finish` event (or `provider-error`) for each completed response. If a provider splits reason and usage across events, merge them in parser state before flushing.
 - Emit exactly one terminal `finish` event for a completed response, normally after a matching `step-finish`. Use `stream.terminal` to stop reading when the provider has a completion sentinel; use `stream.onHalt` when the final event must be flushed after the framed stream ends.
@@ -9,13 +9,15 @@ import { OpenAI } from "@opencode/ai/providers"

 const openai = OpenAI.configure({ apiKey: process.env.OPENAI_API_KEY })

+const request = LLM.request({
+  model: openai.responses("gpt-4o-mini"), // `.chat(...)` selects the Chat Completions API instead
+  system: "You are concise.",
+  prompt: "Say hello in one short sentence.",
+  generation: { maxTokens: 40 },
+})
+
 const program = Effect.gen(function* () {
-  const response = yield* LLM.generate({
-    model: openai.responses("gpt-4o-mini"), // `.chat(...)` selects the Chat Completions API instead
-    system: "You are concise.",
-    prompt: "Say hello in one short sentence.",
-    generation: { maxTokens: 40 },
-  })
+  const response = yield* LLM.generate(request)
  console.log(response.text)
 })

@@ -23,8 +25,7 @@ const program = Effect.gen(function* () {
 await Effect.runPromise(program.pipe(Effect.provide(AIClient.layer)))
 ```

-Run `LLM.stream(...)` instead of `generate` when you want incremental `LLMEvent`s. Both accept input or a prebuilt
-`LLM.request(...)`. The event stream is provider-neutral — same shape across OpenAI Chat, OpenAI Responses,
+Run `LLM.stream(request)` instead of `generate` when you want incremental `LLMEvent`s. The event stream is provider-neutral — same shape across OpenAI Chat, OpenAI Responses,
 Anthropic Messages, Gemini, Bedrock Converse, and any OpenAI-compatible deployment.

 The same configured facade names image, video, speech, and transcription models. `Image.generate` resolves the
@@ -71,11 +72,10 @@ helpers; `ai.file` and `ai.write` load `node:fs/promises` on first use, so no Ef
 import { AI } from "@opencode/ai/promise"

 const ai = AI.make()
-const input = { model: openai.responses("gpt-4o-mini"), prompt: "Say hello." }
-const text = await ai.llm.generate(input)
+const text = await ai.llm.generate({ model: openai.responses("gpt-4o-mini"), prompt: "Say hello." })
 const generated = await ai.image.generate({ model: openai.image("gpt-image-2"), prompt: "A lighthouse" })
 await ai.write(generated.image, "./lighthouse.png") // also ai.file(path), ai.bytes(asset), ai.base64(asset), ai.materialize(asset)
-for await (const event of ai.llm.stream(ai.llm.request(input))) {
+for await (const event of ai.llm.stream({ model: openai.responses("gpt-4o-mini"), prompt: "Stream hello." })) {
  // LLMEvent
 }
 await ai.dispose()
@@ -475,18 +475,18 @@ const program = Effect.gen(function* () {
 Common fields are portable in shape, not in support. Unsupported fields fail with a typed `AIError` before any network
 call rather than being dropped, so check this table before swapping only the `model`:

-| Provider              | `n` | `size`    | `aspectRatio` | `seed` | `format` | `images`                         | `mask`              |
-| --------------------- | --- | --------- | ------------- | ------ | -------- | -------------------------------- | ------------------- |
-| OpenAI                | ✓¹  | ✓         | ✗             | ✗      | ✓        | ✓                                | ✓                   |
-| Google (Gemini)       | 1   | ✗         | ✓             | ✓      | ✗        | ✓ (no public URLs)               | ✗                   |
-| xAI                   | ✓   | ✗         | ✓             | ✗      | ✗        | ✓                                | ✗                   |
-| Z.ai                  | ✗   | ✓         | ✗             | ✗      | ✗        | ✗                                | ✗                   |
-| Meta                  | ✓   | ✓ (hint)  | ✗             | ✗      | ✓        | ✓                                | ✗                   |
-| Black Forest Labs     | 1   | per model | per model     | ✓      | ✓        | per model (1–8)                  | `flux-pro-1.0-fill` |
-| fal                   | ✓   | per model | per model     | ✓      | ✓        | 1 (several on `/edit`, `/multi`) | ✓                   |
-| Replicate             | ✗   | ✗         | ✗             | ✗      | ✗        | ✗ (use `providerOptions`)        | ✗                   |
-| Stability `image`     | 1   | ✗         | ✓             | ✓      | ✓        | 1 (not on `core`)                | ✗                   |
-| Stability `upscale()` | ✗   | ✗         | ✗             | ✓      | ✓        | exactly 1 (required)             | ✗                   |
+| Provider              | `n` | `size`    | `aspectRatio` | `seed` | `format` | `images`                  | `mask`              |
+| --------------------- | --- | --------- | ------------- | ------ | -------- | ------------------------- | ------------------- |
+| OpenAI                | ✓¹  | ✓         | ✗             | ✗      | ✓        | ✓                         | ✓                   |
+| Google (Gemini)       | 1   | ✗         | ✓             | ✓      | ✗        | ✓ (no public URLs)        | ✗                   |
+| xAI                   | ✓   | ✗         | ✓             | ✗      | ✗        | ✓                         | ✗                   |
+| Z.ai                  | ✗   | ✓         | ✗             | ✗      | ✗        | ✗                         | ✗                   |
+| Meta                  | ✓   | ✓ (hint)  | ✗             | ✗      | ✓        | ✓                         | ✗                   |
+| Black Forest Labs     | 1   | per model | per model     | ✓      | ✓        | per model (1–8)           | `flux-pro-1.0-fill` |
+| fal                   | ✓   | per model | per model     | ✓      | ✓        | 1 (several on `/edit`)    | ✓                   |
+| Replicate             | ✗   | ✗         | ✗             | ✗      | ✗        | ✗ (use `providerOptions`) | ✗                   |
+| Stability `image`     | 1   | ✗         | ✓             | ✓      | ✓        | 1 (not on `core`)         | ✗                   |
+| Stability `upscale()` | ✗   | ✗         | ✗             | ✓      | ✓        | exactly 1 (required)      | ✗                   |

 ✓ lowers natively; ✗ fails whenever the field is set (including `n: 1`); `1` means `n > 1` fails. ¹ `Image.stream` on OpenAI generates one image. fal
 rejects `size` and `aspectRatio` together; which one a fal or BFL model takes depends on the model.
@@ -621,7 +621,8 @@ persist the bytes promptly if they must remain available.
 ### Partial images

 OpenAI's GPT image models stream previews. `Image.stream` sends `stream: true` with `partialImages` (0–3, default 2)
-and emits `image-partial` events before each final `image`; `Image.generate` keeps the plain JSON request:
+and emits `image-partial` events before each final `image`; `Image.generate` keeps the plain JSON request.
+`dall-e-*` models do not stream and fail typed:

 ```ts
 import { Stream } from "effect"
@@ -698,7 +699,7 @@ const program = Effect.gen(function* () {
 })
 ```

-The hosted result is represented as a provider-executed tool call and a tool result whose content carries the generated image as a file. Gemini image-capable models instead emit a first-class `media` `LLMEvent` for inline image output (`response.message` then carries a `media` part). Retaining `response.message` preserves the generated image for continuation on both routes.
+The hosted result is represented as a provider-executed tool call and tool result, and the generated image is also emitted as a first-class `media` `LLMEvent` (`response.message` then carries a `media` part). Gemini image-capable models emit the same `media` event for inline image output. Retaining `response.message` preserves the generated image for continuation on both routes.

 ## Video generation

@@ -839,10 +840,9 @@ Provider notes:
 - **OpenAI** streams over SSE (`stream_format: "sse"`), which is also the only place it reports token usage; `tts-1`
  and `tts-1-hd` do not support SSE and stream the raw audio body instead. `pcm` is 24 kHz 16-bit mono. `language`
  and `timestamps` are not supported.
- **Gemini TTS** returns the provider's default output: WAV for Gemini 3.8 TTS `generate`, raw 16-bit PCM
-  (`audio/L16;codec=pcm;rate=24000`) otherwise. `pcm` is the only explicit `format` it accepts, and it fails typed on
-  Gemini 3.8 `generate`; the route never wraps PCM as WAV. Style is directed in the text, so `instructions` and
-  `speed` fail typed. Only `gemini-3.1-flash-tts-preview` and later support streaming. Two-speaker audio goes through
+- **Gemini TTS** returns raw 16-bit PCM only (`audio/L16;codec=pcm;rate=24000`), so any `format` other than `pcm`
+  fails typed; wrap the samples yourself. Style is directed in the text, so `instructions` and `speed` fail typed.
+  Only `gemini-3.1-flash-tts-preview` and later support streaming. Two-speaker audio goes through
  `providerOptions.speechConfig.multiSpeakerVoiceConfig`.
 - **ElevenLabs** requires `voice` (the path voice id) and authenticates with `xi-api-key`. `format` maps to the
  `output_format` query parameter (`mp3_44100_128`, `pcm_24000`, `wav_24000`, `opus_48000_64`);
@@ -936,7 +936,7 @@ const transcript = await generation.await({ poll: { interval: 3_000 } })
 ## Public API

 - **`LLM.request({...})`** — build a provider-neutral `LLMRequest`. Accepts ergonomic inputs (`system: string`, `prompt: string`) that normalize into the canonical Schema classes.
- **`LLM.generate` / `LLM.stream`** — run direct input or an `LLMRequest` through `LLMClient` for one-import use.
+- **`LLM.generate` / `LLM.stream`** — re-exported from `LLMClient` for one-import use.
 - **`Message.user(...)` / `Message.assistant(...)` / `Message.tool(...)`** — message constructors from the canonical schema model.
 - **`LanguageModel.make(...)` / `ToolCallPart.make(...)` / `ToolResultPart.make(...)` / `ToolDefinition.make(...)`** — model and tool-related constructors from the canonical schema model.
 - **`LLMEvent.is.*`** — typed guards (`is.textDelta`, `is.toolCall`, `is.finish`, …) for filtering streams.
@@ -944,7 +944,6 @@ const transcript = await generation.await({ poll: { interval: 3_000 } })
 - **`ImageClient`** — Effect service and layer for image execution, parallel to `LLMClient`.
 - **`Media`** — the shared asset type (`Media.Asset`, `Media.Source`) and constructors used by messages, tool results, and media requests.
 - **`Generation`** — provider-neutral handle for an in-flight media generation (`await`, `refresh`, `cancel`, `events`) used by queued media routes.
- **`Video.request` / `generate` / `stream` / `start` / `resume`** — queued video generation through a provider-neutral request; `VideoClient` is its Effect service and layer.
 - **`Speech.request` / `Speech.generate` / `Speech.stream`** — text-to-speech through a provider-neutral request; `SpeechClient` is its Effect service and layer.
 - **`Transcription.request` / `generate` / `stream` / `start` / `resume`** — speech-to-text over inline, streaming, and queued routes; `TranscriptionClient` is its Effect service and layer.
 - **`AIClient.layer` / `AIClient.layerWith(executor)`** — every modality client plus the request executor in one layer.
@@ -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

@@ -41,7 +40,7 @@ The design below is derived from a survey of the raw provider APIs (OpenAI, Gemi

 ### Model selection

-A model value is built as `OpenAI.configure({ apiKey }).responses("gpt-5")` or `.image("gpt-image-2")`: `configure` fixes credentials, endpoint, and defaults; the selector fixes which of the provider's APIs to hit and binds the typed `providerOptions` generic. Media follows the same shape with one selector per modality — `.image(id)`, `.video(id)`, `.speech(id)`, `.transcription(id)` on the facades that offer each — mirroring `openai.responses(id)`. `Image.request` accepts `ImageModel` only, exactly as `LLM.request` accepts `LanguageModel`.
+A model value is built as `OpenAI.configure({ apiKey }).responses("gpt-5")` or `.image("gpt-image-2")`: `configure` fixes credentials, endpoint, and defaults; the selector fixes which of the provider's APIs to hit and binds the typed `providerOptions` generic. Media follows the same shape with one selector per modality — `openai.image(id)` today, `.video(id)` / `.speech(id)` / `.transcription(id)` as those modalities land — mirroring `openai.responses(id)`. `Image.request` accepts `ImageModel` only, exactly as `LLM.request` accepts `LanguageModel`.

 ```ts
 import { OpenAI, Google } from "@opencode/ai/providers"
@@ -136,12 +135,12 @@ Effect.gen(function* () {
 })
 ```

-`size` and `aspectRatio` are not interchangeable; each route rejects fields it cannot lower — see the portability table
-in the README's Image generation section.
+`size` and `aspectRatio` are not interchangeable; each route rejects fields it cannot lower — see the README's Image
+portability matrix.

 Editing is not a separate function; `images`/`mask` on the request select the edit path in the route (OpenAI `/images/edits`, Gemini multimodal parts, xAI `/images/edits`). Routes that cannot honor `mask` fail with `Unsupported`.

-`ImageRoute` is the inline | stream | queued union, dispatched on `route.kind`, like every modality route. `Image.stream` on a streaming route emits `image-partial` previews before each `image`; on a queued route it emits `generation-queued` / `generation-progress` observations, then the result's `image` and `finish` events.
+`ImageRoute` is the inline | stream | queued union, dispatched on `route.kind`. `Image.stream` on a streaming route emits `image-partial` previews before each `image`; on a queued route it emits `generation-queued` / `generation-progress` observations, then the result's `image` and `finish` events.

 #### Video

@@ -167,8 +166,8 @@ Effect.gen(function* () {

  // Simple: wait for it.
  const response = yield* Video.generate(request, { poll: { interval: "10 seconds", timeout: "10 minutes" } })
-  response.video                                     // Media.Asset: url (expiresAt on Veo and Runway; transient `headers` for Veo downloads)
-  response.usage                                     // credits on Runway; the other three report none (xAI's usage.cost_in_usd_ticks is not decoded)
+  response.video                                     // Media.Asset: url with expiresAt (+ transient `headers` for Veo downloads)
+  response.usage                                     // credits on Runway; the other three report none
  response.notices                                   // Veo raiMediaFilteredReasons → filtered, xAI respect_moderation → moderated
  yield* response.video.materialize()                // pull bytes before the URL expires

@@ -176,7 +175,7 @@ Effect.gen(function* () {
  const generation = yield* Video.start(request)     // Generation<VideoResponse>
  generation.id; generation.status; generation.progress; generation.position; generation.token
  yield* generation.await({ poll })                  // VideoResponse
-  yield* generation.cancel()                         // fal PUT cancel_url, Runway DELETE /tasks/{id}; Veo and xAI succeed without a request
+  yield* generation.cancel()                         // fal PUT cancel_url, Runway DELETE /tasks/{id}; no-op for Veo and xAI

  // Resume from another process. The token is validated against the route's codec and refreshed once. It carries no
  // route identity, so persist the provider and model ID alongside it: `resume` needs the model.
@@ -189,11 +188,10 @@ Effect.gen(function* () {

 Tokens are route-owned JSON: Veo `{ operation }`, xAI `{ requestID }`, Runway `{ taskID }`, fal
 `{ requestID, statusURL, responseURL, cancelURL }` (fal's follow-up URLs are authoritative and absolute). Common-field
-lowering per provider: Veo takes inline media only, rejects `audio: false` and `n > 1`, and requires `frames.first`
-when `frames.last` is set; xAI rejects `n`, `seed`, and `negativePrompt` and routes a `video` input to edits or
-(`providerOptions.mode: "extend"`) extensions; fal rejects `n`, plus `durationSeconds`, `references`, and `frames.last`
-because the field names and enums differ per model; Runway passes `aspectRatio` through as its pixel `ratio` and
-rejects `n`.
+lowering per provider: Veo takes inline media only and rejects `audio: false` and `n > 1`; xAI rejects `seed` and
+`negativePrompt` and routes a `video` input to edits or (`providerOptions.mode: "extend"`) extensions; fal rejects
+`durationSeconds`, `references`, and `frames.last` because the field names and enums differ per model; Runway passes
+`aspectRatio` through as its pixel `ratio` and rejects `n`.

 Deferred: `Video.complete(model, token, webhook)` (finish from a webhook payload without polling) and provider poll
 hints (none of the four providers emit one). Later providers: Luma, Kling, MiniMax, Replicate.
@@ -217,7 +215,7 @@ const request = Speech.request({
 })

 const response = yield* Speech.generate(request)   // SpeechResponse: audio: Media.Asset, timestamps?, usage?, providerMetadata?
-yield* Speech.stream(request)                      // Stream<SpeechEvent>: generation-queued | generation-progress | audio-delta { chunk } | timestamps { items } | finish { audio, usage? }
+yield* Speech.stream(request)                      // Stream<SpeechEvent>: audio-delta { chunk } | timestamps { items } | finish { audio, usage? }
 ```

 Execution is `MediaProtocol.stream` for every provider: one request whose body is framed and folded by a `step`
@@ -243,12 +241,10 @@ name→id resolution. Multi-speaker (Gemini `speechConfig.multiSpeakerVoiceConfi
 `opus_48000_64`, Cartesia `{ container, encoding, sample_rate }`, Deepgram `encoding`+`container`) and declares the
 asset's media type rather than sniffing, because headerless PCM can look like an MPEG frame sync. Headerless PCM
 always carries `info.encoding`, `info.sampleRate`, and `info.channels`; its media type is the provider's declaration
-(Gemini `audio/L16;codec=pcm;rate=24000`, Deepgram's `content-type`) or `audio/pcm`. Gemini's asset follows the
-provider's declared type: WAV for Gemini 3.8 TTS `generate`, headerless PCM otherwise. The route never wraps PCM as WAV,
-so `pcm` is the only explicit `format` it accepts, and not on Gemini 3.8 `generate`. Every `format` value a route cannot
-produce (unknown to it, a container on Cartesia SSE, WAV on an ElevenLabs stream, anything but `pcm` on Gemini, `pcm` on
-Gemini 3.8 `generate`) fails the same way as an unsupported field: `UnsupportedOperation` with
-`operation: "media.format"`.
+(Gemini `audio/L16;codec=pcm;rate=24000`, Deepgram's `content-type`) or `audio/pcm`. Gemini returns PCM only, so any
+other `format` is rejected rather than wrapped as WAV by the route. Every `format` value a route cannot produce (unknown
+to it, a container on Cartesia SSE, WAV on an ElevenLabs stream, anything but PCM on Gemini) fails the same way as an
+unsupported field: `UnsupportedOperation` with `operation: "media.format"`.

 **Timestamps.** `timestamps: true` on the request asks for alignment. ElevenLabs selects the `with-timestamps`
 endpoints (character-level, NDJSON when streaming); Cartesia sets `add_timestamps` on `/tts/sse` (word-level; a
@@ -281,7 +277,7 @@ 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,                                     // expected count, hint only (AssemblyAI)
  providerOptions: { known_speaker_names: ["agent"] },
 })

@@ -295,11 +291,10 @@ yield* Transcription.resume(model, token)
 Transcription is the first modality whose providers span all three protocol kinds, and it needed no fourth kind.
 Every `MediaRoute` now carries its `kind`; `TranscriptionRoute` is the union of the inline, stream, and queued routes;
 `TranscriptionModel.fromRoute` is overloaded per protocol kind (arity picks the overload: `<Options>`,
-`<Options, Frame, State>`, `<Options, Token>`) and composes through the shared `composeRoute` (`src/media-model.ts`),
-which picks `MediaRoute.inline` / `stream` / `queued`; and `TranscriptionClient`, like every modality client, is
-`MediaClient.make` (`src/media-client.ts`), which dispatches on `route.kind`. `generate` on a queued route is `start`
-then `await`; `stream` on an inline route is the response as a single `finish`, and on a queued route it is the status
-observations followed by `finish`. `start` / `resume` on a non-queued route fail with `UnsupportedOperation` (`transcription.start`). The
+`<Options, Frame, State>`, `<Options, Token>`) and composes through `MediaRoute.inline` / `stream` / `queued`; and
+`TranscriptionClient` dispatches on `route.kind`. `generate` on a queued route is `start` then `await`; `stream` on an
+inline route is the response as a single `finish`, and on a queued route it is the status observations followed by
+`finish`. `start` / `resume` on a non-queued route fail with `UnsupportedOperation` (`transcription.start`). The
 `finish` event carries the whole transcript (text, segments, words, language, duration, usage), so the stream route's
 `collect` is just "take `finish`".

@@ -314,12 +309,11 @@ Settled rules:
  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.
+  cross-provider speaker model. `speakers` is a hint; only AssemblyAI (`speakers_expected`) accepts it.
 - **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.
+  ISO code on most routes, `english` from whisper-1, `en_us` from AssemblyAI. 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.
@@ -329,7 +323,7 @@ Settled rules:

 | Provider | Kind | Audio input | `timestamps` | `diarize` | Unsupported | Usage |
 |---|---|---|---|---|---|---|
-| 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` |
+| OpenAI | stream (`stream: true` in `stream` mode) | multipart `file` (inline only) | `whisper-1` (`verbose_json`); diarize model: `segment` | `gpt-4o-transcribe-diarize` (`diarized_json`) | `speakers`; `prompt` on the diarize model; streaming on `whisper-1` | `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`) |
 | AssemblyAI | queued (upload → submit → poll) | `/v2/upload` then `audio_url`, or a URL | words always; `segment` → `speaker_labels` | `speaker_labels` | — | `seconds` (`audio_duration`) |
@@ -359,7 +353,7 @@ GenerationAwaitOptions = { poll?: Poll }
 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`.
+`Generation` is not video-specific. Image routes on BFL, fal, and Replicate are queued; `Image.start` exists for them. A route declares itself `inline` or `queued`; `generate` on a queued route is `start` then `await`.

 ### Usage

@@ -395,8 +389,7 @@ for await (const event of generation.events({ poll: { interval: 10_000 } })) {
 const video = await generation.await({ poll: { interval: 10_000 }, signal })
 const resumed = await ai.video.resume(model, JSON.parse(saved)) // persist provider + model ID with the token

-const request = ai.llm.request({ model, prompt })
-const text = await ai.llm.generate(request)
+const text = await ai.llm.generate({ model, prompt })
 for await (const event of ai.llm.stream(request)) { … }

 await ai.dispose()
@@ -406,15 +399,14 @@ Streams become `AsyncIterable` via `Stream.toAsyncIterable`. `AIError` is thrown

 ### Providers

-Existing facades gain per-modality selectors; the modality routes each facade provides (*italics* are not
-implemented):
+Existing facades gain per-modality selectors; the modality routes each facade provides:

 | Facade | llm | image | video | speech | transcription | other |
 |---|---|---|---|---|---|---|
-| `OpenAI` | responses (default), chat | Images API (stream) | *Sora skipped (decision 8)* | ✓ | ✓ | |
+| `OpenAI` | responses (default), chat | Images API (stream) | Sora (deprecated 2026-09-24) | ✓ | ✓ | |
 | `Google` | Gemini | Gemini-native | Veo | Gemini TTS | `gemini-3.5-transcribe` | |
 | `XAI` | ✓ | ✓ | ✓ | | | |
-| `ElevenLabs` | | | | ✓ | *Scribe (pending)* | *soundEffect, music (phase 5)* |
+| `ElevenLabs` | | | | ✓ | Scribe | soundEffect, music |
 | `Cartesia` | | | | ✓ | | |
 | `Deepgram` | | | | Aura | ✓ | |
 | `Fal` | | ✓ (queued) | ✓ | | | |
@@ -423,11 +415,11 @@ implemented):
 | `Replicate` | | ✓ (queued) | | | | |
 | `Stability` | | `image` (inline), `upscale()` (queued) | | | | |
 | `Runway` | | | ✓ | | | |
-| `Luma`, `Kling`, `MiniMax` | | *deferred* | *deferred* | | | |
+| `Luma`, `Kling`, `MiniMax` | | per provider | | | | |

 New facades follow the existing one-file-per-provider rule. The facade selector is the public path for media models; modality-specific package entrypoints (for example `@opencode/ai/providers/openai/images`) are deferred until Core has a modality-aware model resolver.

-`ImageModel<Options>` gives typed `providerOptions` per model; `VideoModel`, `SpeechModel`, and `TranscriptionModel` follow the same generic. As with `LanguageModel`, the route type does not carry `Options`, so `ImageModel<OpenAIImageOptions>` is an `ImageModel` and client methods take plain `ImageRequestFor`. They share an internal `MediaModel` base class (ids, route, `http` overlays) that is not part of the public exports; `Generation` and the promise client work with the concrete modality models.
+`ImageModel<Options>` gives typed `providerOptions` per model; `VideoModel`, `SpeechModel`, and `TranscriptionModel` follow the same generic. They share an internal `MediaModel` base class (ids, route, `http` overlays) that is not part of the public exports; `Generation` and the promise client work with the concrete modality models.

 ### Routes and protocols

@@ -1,6 +1,6 @@
 {
  "$schema": "https://json.schemastore.org/package.json",
-  "version": "2.0.18",
+  "version": "2.0.16",
  "name": "@opencode/ai",
  "type": "module",
  "license": "MIT",
@@ -53,8 +53,6 @@ export type Event = Observation | { readonly type: "generation-finished"; readon

 const TERMINAL: ReadonlySet<Status> = new Set(["completed", "failed", "cancelled", "expired"])

-export const isTerminal = (status: Status) => TERMINAL.has(status)
-
 export class Generation<Response> {
  readonly id: string
  readonly status: Status
@@ -83,7 +81,7 @@ export class Generation<Response> {
  }

  get terminal() {
-    return isTerminal(this.status)
+    return TERMINAL.has(this.status)
  }

  refresh(): Effect.Effect<Generation<Response>, AIError> {
@@ -111,10 +109,9 @@ export class Generation<Response> {
  }

  /**
-   * Status observations as a stream, ending after the first terminal observation. Each poll and each sleep between polls
-   * is bounded by the time remaining until `poll.timeout`, so a hung status request or a long interval fails the stream at
-   * the deadline instead of stalling it. (`Stream.interruptWhen` would express this directly but deadlocks under
-   * `TestClock` when the source completes while the timer sleeps.)
+   * Status observations as a stream, ending after the first terminal observation. Each poll is bounded by the time
+   * remaining until `poll.timeout`, so a hung status request fails the stream instead of stalling it. (`Stream.interruptWhen`
+   * would express this directly but deadlocks under `TestClock` when the source completes while the timer sleeps.)
   */
  events(options?: AwaitOptions): Stream.Stream<Event, AIError> {
    if (this.terminal) return Stream.make(this.event())
@@ -123,26 +120,17 @@ 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),
-                    }),
-                  ),
+              this.refresh().pipe(
+                Effect.timeoutOrElse({
+                  duration: Duration.millis(Math.max(0, deadline - now)),
+                  orElse: () => this.timeoutError(timeout),
+                }),
+              ),
            ),
          )
-          const schedule = this.schedule(options?.poll).pipe(
-            Schedule.modifyDelay((meta) =>
-              Effect.succeed(Duration.min(meta.duration, Duration.millis(Math.max(0, deadline - meta.now)))),
-            ),
-          )
-          return Stream.fromEffectSchedule(refresh, schedule).pipe(
+          return Stream.fromEffectSchedule(refresh, this.schedule(options?.poll)).pipe(
            Stream.takeUntil((generation) => generation.terminal),
            Stream.map((generation) => generation.event()),
          )
@@ -1,30 +1,99 @@
-import { Context } from "effect"
-import { MediaClient } from "./media-client.js"
+import { Context, Effect, Layer, Stream } from "effect"
+import type { AwaitOptions, Generation } from "./generation.js"
+import { RequestExecutor } from "./route/executor.js"
+import { MediaRoute } from "./route/media.js"
+import type { AIError } from "./schema/index.js"
 import {
-  ImageOutputEvent,
-  ImageFinishEvent,
+  responseEvents,
  type ImageEvent,
+  type ImageModel,
+  type ImageOptions,
  type ImageRequestFor,
  type ImageResponse,
 } from "./image.js"

-export type Interface = MediaClient.Interface<ImageRequestFor, ImageEvent, ImageResponse>
+export interface Interface {
+  readonly generate: <Options extends ImageOptions>(
+    request: ImageRequestFor<Options>,
+    options?: AwaitOptions,
+  ) => Effect.Effect<ImageResponse, AIError>
+  readonly stream: <Options extends ImageOptions>(
+    request: ImageRequestFor<Options>,
+    options?: AwaitOptions,
+  ) => Stream.Stream<ImageEvent, AIError>
+  readonly start: <Options extends ImageOptions>(
+    request: ImageRequestFor<Options>,
+  ) => Effect.Effect<Generation<ImageResponse>, AIError>
+  readonly resume: <Options extends ImageOptions>(
+    model: ImageModel<Options>,
+    token: unknown,
+  ) => Effect.Effect<Generation<ImageResponse>, AIError>
+}

 export class ImageClientService extends Context.Service<ImageClientService, Interface>()("@opencode/ImageClient") {}
 export const Service = ImageClientService
 export type Service = ImageClientService

+export const generate = <Options extends ImageOptions>(
+  request: ImageRequestFor<Options>,
+  options?: AwaitOptions,
+): Effect.Effect<ImageResponse, AIError, Service> =>
+  Effect.gen(function* () {
+    const client = yield* Service
+    return yield* client.generate(request, options)
+  })
+
+export const stream = <Options extends ImageOptions>(
+  request: ImageRequestFor<Options>,
+  options?: AwaitOptions,
+): Stream.Stream<ImageEvent, AIError, Service> =>
+  Stream.unwrap(
+    Effect.gen(function* () {
+      const client = yield* Service
+      return client.stream(request, options)
+    }),
+  )
+
+export const start = <Options extends ImageOptions>(
+  request: ImageRequestFor<Options>,
+): Effect.Effect<Generation<ImageResponse>, AIError, Service> =>
+  Effect.gen(function* () {
+    const client = yield* Service
+    return yield* client.start(request)
+  })
+
+export const resume = <Options extends ImageOptions>(
+  model: ImageModel<Options>,
+  token: unknown,
+): Effect.Effect<Generation<ImageResponse>, AIError, Service> =>
+  Effect.gen(function* () {
+    const client = yield* Service
+    return yield* client.resume(model, token)
+  })
+
+export const layer: Layer.Layer<Service, never, RequestExecutor.Service> = Layer.effect(
+  Service,
+  Effect.gen(function* () {
+    const executor = yield* RequestExecutor.Service
+    const dispatch = MediaRoute.dispatch<ImageEvent, ImageResponse>({
+      modality: "image",
+      execute: executor.execute,
+      responseEvents,
+    })
+    return Service.of({
+      start: (request) => dispatch.start(request.model.route, request),
+      resume: (model, token) => dispatch.resume(model.route, model, token),
+      generate: (request, options) => dispatch.generate(request.model.route, request, options),
+      stream: (request, options) => dispatch.stream(request.model.route, request, options),
+    })
+  }),
+)
+
 export const ImageClient = {
  Service,
-  ...MediaClient.make(Service, {
-    modality: "image",
-    responseEvents: (response: ImageResponse) => [
-      ...response.images.map((image, index) => ImageOutputEvent.make({ index, image })),
-      ImageFinishEvent.make({
-        usage: response.usage,
-        notices: response.notices,
-        providerMetadata: response.providerMetadata,
-      }),
-    ],
-  }),
+  layer,
+  generate,
+  stream,
+  start,
+  resume,
 } as const
@@ -1,8 +1,9 @@
 import { Effect, Schema, Stream } from "effect"
 import { Generation, ProgressEvent, QueuedEvent, type AwaitOptions } from "./generation.js"
 import { Media } from "./media.js"
-import { MediaModel, composeRoute, tryRequest } from "./media-model.js"
+import { MediaModel, composeAnyRoute, tryRequest } from "./media-model.js"
 import { MediaRoute } from "./route/media.js"
+import type { MediaProtocol } from "./route/media-protocol.js"
 import { AIError, HttpOptions, MediaUsage, ProviderMetadata, type OpenString } from "./schema/index.js"
 import { ImageClient, Service } from "./image-client.js"

@@ -10,39 +11,75 @@ import { ImageClient, Service } from "./image-client.js"
 // Model
 // ---------------------------------------------------------------------------

-export type ImageOptions = MediaModel.Options
+export type ImageOptions = Record<string, unknown>

-export type ImageRoute = MediaRoute.AnyRoute<ImageRequestFor, ImageEvent, ImageResponse>
+export type ImageRoute<Options extends ImageOptions = ImageOptions> = MediaRoute.AnyRoute<
+  ImageRequestFor<Options>,
+  ImageEvent,
+  ImageResponse
+>

-export class ImageModel<Options extends ImageOptions = ImageOptions> extends MediaModel<ImageRoute, Options> {
+export class ImageModel<Options extends ImageOptions = ImageOptions> extends MediaModel<ImageRoute<Options>, Options> {
  declare protected readonly _ImageModel: void

+  static make<Options extends ImageOptions = ImageOptions>(input: MediaModel.Input<ImageRoute<Options>>) {
+    return new ImageModel<Options>(input)
+  }
+
  /** The number of type arguments selects the kind: `<Options>`, `<Options, Frame, State>`, or `<Options, Token>`. */
  static fromRoute<Options extends ImageOptions>(
-    route: MediaModel.InlineRouteInput<ImageRequestFor<Options>, ImageResponse>,
+    route: ImageModel.InlineRouteInput<Options>,
    input: MediaRoute.ModelInput,
  ): ImageModel<Options>
  static fromRoute<Options extends ImageOptions, Frame, State>(
-    route: MediaModel.StreamRouteInput<ImageRequestFor<Options>, ImageEvent, Frame, State>,
+    route: ImageModel.StreamRouteInput<Options, Frame, State>,
    input: MediaRoute.ModelInput,
  ): ImageModel<Options>
  static fromRoute<Options extends ImageOptions, Token>(
-    route: MediaModel.QueuedRouteInput<ImageRequestFor<Options>, ImageResponse, Token>,
+    route: ImageModel.QueuedRouteInput<Options, Token>,
    input: MediaRoute.ModelInput,
  ): ImageModel<Options>
  static fromRoute<Options extends ImageOptions, Frame, State, Token>(
-    route: MediaModel.AnyRouteInput<ImageRequestFor<Options>, ImageEvent, ImageResponse, Frame, State, Token>,
+    route: ImageModel.RouteInput<Options, Frame, State, Token>,
    input: MediaRoute.ModelInput,
  ) {
    return new ImageModel<Options>({
      id: input.id,
      provider: route.protocol.provider,
      http: input.http,
-      route: composeRoute(route, input, collectResponse) as ImageRoute,
+      route: composeAnyRoute(route, input, collectResponse),
    })
  }
 }

+export namespace ImageModel {
+  export type InlineRouteInput<Options extends ImageOptions = ImageOptions> = MediaModel.RouteInput<
+    ImageRequestFor<Options>,
+    MediaProtocol.Inline<ImageRequestFor<Options>, ImageResponse>
+  >
+
+  export type StreamRouteInput<
+    Options extends ImageOptions = ImageOptions,
+    Frame = unknown,
+    State = unknown,
+  > = MediaModel.RouteInput<
+    MediaProtocol.Addressed<ImageRequestFor<Options>>,
+    MediaProtocol.Streamed<ImageRequestFor<Options>, ImageEvent, Frame, State>
+  >
+
+  export type QueuedRouteInput<Options extends ImageOptions = ImageOptions, Token = unknown> = MediaModel.RouteInput<
+    ImageRequestFor<Options>,
+    MediaProtocol.Queued<ImageRequestFor<Options>, ImageResponse, Token>
+  >
+
+  export type RouteInput<
+    Options extends ImageOptions = ImageOptions,
+    Frame = unknown,
+    State = unknown,
+    Token = unknown,
+  > = MediaModel.AnyRouteInput<ImageRequestFor<Options>, ImageEvent, ImageResponse, Frame, State, Token>
+}
+
 export const ImageModelSchema = Schema.declare((value): value is ImageModel => value instanceof ImageModel, {
  expected: "Image.Model",
 })
@@ -153,6 +190,15 @@ export const ImageEvent = Object.assign(imageEventTagged, {
 })
 export type ImageEvent = Schema.Schema.Type<typeof imageEventTagged>

+export const responseEvents = (response: ImageResponse): ReadonlyArray<ImageEvent> => [
+  ...response.images.map((image, index) => ImageOutputEvent.make({ index, image })),
+  ImageFinishEvent.make({
+    usage: response.usage,
+    notices: response.notices,
+    providerMetadata: response.providerMetadata,
+  }),
+]
+
 const collectResponse = (events: ReadonlyArray<ImageEvent>): Effect.Effect<ImageResponse> => {
  const finish = events.find(ImageEvent.is.finish)
  // Every image protocol's `finish` emits the terminal event or fails, so a completed stream always has one.
@@ -186,31 +232,36 @@ export function request(input: ImageRequest | ImageRequestInput) {
 const requestEffect = (input: ImageRequest | ImageRequestInput) => tryRequest(() => request(input))

 export function generate<const Model extends ImageModel>(
-  input: ImageRequest | ImageRequestInput<Model>,
+  input: ImageRequestInput<Model>,
  options?: AwaitOptions,
 ): Effect.Effect<ImageResponse, AIError, Service>
+export function generate(input: ImageRequest, options?: AwaitOptions): Effect.Effect<ImageResponse, AIError, Service>
 export function generate(input: ImageRequest | ImageRequestInput, options?: AwaitOptions) {
  return requestEffect(input).pipe(Effect.flatMap((request) => ImageClient.generate(request, options)))
 }

 export function stream<const Model extends ImageModel>(
-  input: ImageRequest | ImageRequestInput<Model>,
+  input: ImageRequestInput<Model>,
  options?: AwaitOptions,
 ): Stream.Stream<ImageEvent, AIError, Service>
+export function stream(input: ImageRequest, options?: AwaitOptions): Stream.Stream<ImageEvent, AIError, Service>
 export function stream(input: ImageRequest | ImageRequestInput, options?: AwaitOptions) {
  return Stream.unwrap(requestEffect(input).pipe(Effect.map((request) => ImageClient.stream(request, options))))
 }

 /** Inline and streaming routes fail with `UnsupportedOperation`. */
 export function start<const Model extends ImageModel>(
-  input: ImageRequest | ImageRequestInput<Model>,
+  input: ImageRequestInput<Model>,
 ): Effect.Effect<Generation<ImageResponse>, AIError, Service>
+export function start(input: ImageRequest): Effect.Effect<Generation<ImageResponse>, AIError, Service>
 export function start(input: ImageRequest | ImageRequestInput) {
  return requestEffect(input).pipe(Effect.flatMap((request) => ImageClient.start(request)))
 }

-export const resume = (model: ImageModel, token: unknown): Effect.Effect<Generation<ImageResponse>, AIError, Service> =>
-  ImageClient.resume(model, token)
+export const resume = <Options extends ImageOptions>(
+  model: ImageModel<Options>,
+  token: unknown,
+): Effect.Effect<Generation<ImageResponse>, AIError, Service> => ImageClient.resume(model, token)

 export const Image = {
  request,
@@ -1,6 +1,5 @@
-import { Effect, JsonSchema, Schema, Stream } from "effect"
-import { tryRequest } from "./media-model.js"
-import { LLMClient, Service, type StreamOptions } from "./route/client.js"
+import { Effect, JsonSchema, Schema } from "effect"
+import { LLMClient, Service } from "./route/client.js"
 import {
  GenerationOptions,
  HttpOptions,
@@ -36,26 +35,9 @@ export type RequestInput<SelectedLanguageModel extends LanguageModel = LanguageM
  readonly http?: HttpOptions.Input
 }

-export function generate<const Model extends LanguageModel>(
-  input: RequestInput<Model>,
-  options?: StreamOptions,
-): Effect.Effect<LLMResponse, AIError, Service>
-export function generate(input: LLMRequest, options?: StreamOptions): Effect.Effect<LLMResponse, AIError, Service>
-export function generate(input: RequestInput | LLMRequest, options?: StreamOptions) {
-  return requestEffect(input).pipe(Effect.flatMap((request) => LLMClient.generate(request, options)))
-}
+export const generate = LLMClient.generate

-export function stream<const Model extends LanguageModel>(
-  input: RequestInput<Model>,
-  options?: StreamOptions,
-): Stream.Stream<LLMEvent, AIError, Service>
-export function stream(input: LLMRequest, options?: StreamOptions): Stream.Stream<LLMEvent, AIError, Service>
-export function stream(input: RequestInput | LLMRequest, options?: StreamOptions) {
-  return Stream.unwrap(requestEffect(input).pipe(Effect.map((request) => LLMClient.stream(request, options))))
-}
-
-const requestEffect = (input: RequestInput | LLMRequest) =>
-  input instanceof LLMRequest ? Effect.succeed(input) : tryRequest(() => request(input))
+export const stream = LLMClient.stream

 export const request = <const SelectedLanguageModel extends LanguageModel>(
  input: RequestInput<SelectedLanguageModel>,
@@ -1,77 +0,0 @@
-import { type Context, Effect, Layer, Stream } from "effect"
-import { resultEvents, type AwaitOptions, type Generation, type Observation } from "./generation.js"
-import { RequestExecutor } from "./route/executor.js"
-import type { MediaRoute } from "./route/media.js"
-import { AIError, UnsupportedOperationError } from "./schema/index.js"
-
-/** A media request whose model carries the route that executes it. */
-export interface RoutedRequest<Self extends MediaRoute.MediaRequest, Event, Response> extends MediaRoute.MediaRequest {
-  readonly model: MediaRoute.MediaRequest["model"] & { readonly route: MediaRoute.AnyRoute<Self, Event, Response> }
-}
-
-/** `start` and `resume` fail with `UnsupportedOperation` on inline and stream routes. */
-export interface Interface<Req extends RoutedRequest<Req, Event, Response>, Event, Response> {
-  readonly generate: (request: Req, options?: AwaitOptions) => Effect.Effect<Response, AIError>
-  readonly stream: (request: Req, options?: AwaitOptions) => Stream.Stream<Event | Observation, AIError>
-  readonly start: (request: Req) => Effect.Effect<Generation<Response>, AIError>
-  readonly resume: (model: Req["model"], token: unknown) => Effect.Effect<Generation<Response>, AIError>
-}
-
-/** One modality's layer and service accessors, dispatching each request on its route's `kind`. */
-export const make = <Self, Req extends RoutedRequest<Req, Event, Response>, Event, Response>(
-  service: Context.Service<Self, Interface<Req, Event, Response>>,
-  input: {
-    readonly modality: string
-    /** A completed response expanded into the streaming event shape. */
-    readonly responseEvents: (response: Response) => ReadonlyArray<Event>
-  },
-) => ({
-  layer: Layer.effect(
-    service,
-    Effect.gen(function* () {
-      const executor = yield* RequestExecutor.Service
-      const notQueued = (route: MediaRoute.AnyRoute<Req, Event, Response>, operation: string) =>
-        new AIError({
-          reason: new UnsupportedOperationError({
-            operation: `${input.modality}.${operation}`,
-            provider: route.provider,
-            route: route.id,
-            message: `${route.provider}/${route.id} is not a queued route; use generate or stream`,
-          }),
-        })
-      const start = (request: Req) => {
-        const route = request.model.route
-        if (route.kind !== "queued") return Effect.fail(notQueued(route, "start"))
-        return route.start(request, executor.execute)
-      }
-      return service.of({
-        start,
-        resume: (model, token) => {
-          if (model.route.kind !== "queued") return Effect.fail(notQueued(model.route, "resume"))
-          return model.route.resume(model, token, executor.execute)
-        },
-        generate: (request, options) => {
-          const route = request.model.route
-          if (route.kind !== "queued") return route.generate(request, executor.execute)
-          return start(request).pipe(Effect.flatMap((generation) => generation.await(options)))
-        },
-        stream: (request, options) => {
-          const route = request.model.route
-          if (route.kind === "stream") return route.stream(request, executor.execute)
-          if (route.kind === "queued")
-            return Stream.unwrap(
-              start(request).pipe(Effect.map((generation) => resultEvents(generation, input.responseEvents, options))),
-            )
-          return Stream.fromIterableEffect(Effect.map(route.generate(request, executor.execute), input.responseEvents))
-        },
-      })
-    }),
-  ),
-  generate: (request: Req, options?: AwaitOptions) => service.use((client) => client.generate(request, options)),
-  stream: (request: Req, options?: AwaitOptions) =>
-    Stream.unwrap(service.useSync((client) => client.stream(request, options))),
-  start: (request: Req) => service.use((client) => client.start(request)),
-  resume: (model: Req["model"], token: unknown) => service.use((client) => client.resume(model, token)),
-})
-
-export * as MediaClient from "./media-client.js"
@@ -6,13 +6,11 @@ import { AIError, HttpOptions, InvalidRequestError, ModelID, ProviderID } from "

 /**
 * What every media model carries: ids, the configured route, and deployment `http` overlays. Modality classes
- * (`ImageModel`, `VideoModel`, `SpeechModel`, `TranscriptionModel`) extend it with their route type and a nominal
- * marker so one cannot stand in for the other in requests.
+ * (`ImageModel`, `VideoModel`, `SpeechModel`) extend it with their route type and a nominal marker so one cannot stand
+ * in for the other in requests.
 */
 export class MediaModel<Route, Options> {
-  // As with `LanguageModel`, the route type is erased over `Options`; `fromRoute` and the constructor trust that the
-  // route accepts every request this model's `Options` admit.
-  declare protected readonly _Options: Options
+  declare protected readonly _Options: (options: Options) => Options
  readonly id: ModelID
  readonly provider: ProviderID
  readonly route: Route
@@ -27,8 +25,6 @@ export class MediaModel<Route, Options> {
 }

 export namespace MediaModel {
-  export type Options = Record<string, unknown>
-
  export interface Input<Route> {
    readonly id: string | ModelID
    readonly provider: string | ProviderID
@@ -45,56 +41,48 @@ export namespace MediaModel {
    readonly headers?: Record<string, string>
  }

-  export type InlineRouteInput<Request extends MediaRoute.MediaRequest, Response> = RouteInput<
-    Request,
-    MediaProtocol.Inline<Request, Response>
-  >
-
-  export type StreamRouteInput<Request extends MediaRoute.MediaRequest, Event, Frame, State> = RouteInput<
-    MediaProtocol.Addressed<Request>,
-    MediaProtocol.Streamed<Request, Event, Frame, State>
-  >
-
-  export type QueuedRouteInput<Request extends MediaRoute.MediaRequest, Response, Token> = RouteInput<
-    Request,
-    MediaProtocol.Queued<Request, Response, Token>
-  >
-
  export type AnyRouteInput<Request extends MediaRoute.MediaRequest, Event, Response, Frame, State, Token> =
-    | InlineRouteInput<Request, Response>
-    | StreamRouteInput<Request, Event, Frame, State>
-    | QueuedRouteInput<Request, Response, Token>
+    | RouteInput<Request, MediaProtocol.Inline<Request, Response>>
+    | RouteInput<MediaProtocol.Addressed<Request>, MediaProtocol.Streamed<Request, Event, Frame, State>>
+    | RouteInput<Request, MediaProtocol.Queued<Request, Response, Token>>
 }

 /** Compose a protocol route input with one deployment through `MediaRoute.inline`, `queued`, or `stream`. */
-export const composeRoute = <Request extends MediaRoute.MediaRequest, Event, Response, Frame, State, Token>(
+export const composeRoute = <Request extends MediaRoute.MediaRequest, Protocol, Route>(
+  compose: (input: MediaRoute.Composition<Request> & { readonly protocol: Protocol }) => Route,
+  route: MediaModel.RouteInput<Request, Protocol>,
+  input: MediaRoute.ModelInput,
+): Route =>
+  compose({
+    protocol: route.protocol,
+    endpoint: Endpoint.path(route.path, { baseURL: input.baseURL ?? route.baseURL }),
+    auth: input.auth,
+    headers:
+      route.headers === undefined && input.headers === undefined ? undefined : { ...route.headers, ...input.headers },
+  })
+
+export const composeAnyRoute = <Request extends MediaRoute.MediaRequest, Event, Response, Frame, State, Token>(
  route: MediaModel.AnyRouteInput<Request, Event, Response, Frame, State, Token>,
  input: MediaRoute.ModelInput,
  collect: (events: ReadonlyArray<Event>) => Effect.Effect<Response, AIError>,
 ): MediaRoute.AnyRoute<Request, Event, Response> => {
-  if (isStreamInput(route)) return MediaRoute.stream({ ...composition(route, input), collect })
-  if (isQueuedInput(route)) return MediaRoute.queued(composition(route, input))
-  return MediaRoute.inline(composition(route, input))
+  if (isStreamInput(route))
+    return composeRoute((composition) => MediaRoute.stream({ ...composition, collect }), route, input)
+  if (isQueuedInput(route)) return composeRoute(MediaRoute.queued, route, input)
+  return composeRoute(MediaRoute.inline, route, input)
 }

-const composition = <Request extends MediaRoute.MediaRequest, Protocol>(
-  route: MediaModel.RouteInput<Request, Protocol>,
-  input: MediaRoute.ModelInput,
-): MediaRoute.Composition<Request> & { readonly protocol: Protocol } => ({
-  protocol: route.protocol,
-  endpoint: Endpoint.path(route.path, { baseURL: input.baseURL ?? route.baseURL }),
-  auth: input.auth,
-  headers:
-    route.headers === undefined && input.headers === undefined ? undefined : { ...route.headers, ...input.headers },
-})
-
 const isStreamInput = <Request extends MediaRoute.MediaRequest, Event, Response, Frame, State, Token>(
  route: MediaModel.AnyRouteInput<Request, Event, Response, Frame, State, Token>,
-): route is MediaModel.StreamRouteInput<Request, Event, Frame, State> => route.protocol.kind === "stream"
+): route is MediaModel.RouteInput<
+  MediaProtocol.Addressed<Request>,
+  MediaProtocol.Streamed<Request, Event, Frame, State>
+> => route.protocol.kind === "stream"

 const isQueuedInput = <Request extends MediaRoute.MediaRequest, Event, Response, Frame, State, Token>(
  route: MediaModel.AnyRouteInput<Request, Event, Response, Frame, State, Token>,
-): route is MediaModel.QueuedRouteInput<Request, Response, Token> => route.protocol.kind === "queued"
+): route is MediaModel.RouteInput<Request, MediaProtocol.Queued<Request, Response, Token>> =>
+  route.protocol.kind === "queued"

 /** Lift a synchronous Schema-class constructor into a typed `InvalidRequest` failure. */
 export const tryRequest = <A>(make: () => A): Effect.Effect<A, AIError> =>
@@ -1,22 +1,23 @@
 import { Effect, Layer, ManagedRuntime, Stream } from "effect"
 import { AIClient } from "./ai-client.js"
 import type { AwaitOptions, Event, Generation, Snapshot } from "./generation.js"
-import { Image, type ImageModel, type ImageRequest, type ImageRequestInput } from "./image.js"
+import { Image, ImageModel, ImageRequest, type ImageOptions, type ImageRequestInput } from "./image.js"
 import { LLM } from "./index.js"
 import { Media } from "./media.js"
 import { tryRequest } from "./media-model.js"
 import { RequestExecutor } from "./route/executor.js"
 import { AIError, InvalidRequestError, LanguageModel, LLMRequest } from "./schema/index.js"
 import type { RequestInput } from "./llm.js"
-import { Speech, type SpeechModel, type SpeechRequest, type SpeechRequestInput } from "./speech.js"
+import { Speech, SpeechModel, SpeechRequest, type SpeechRequestInput } from "./speech.js"
 import {
  Transcription,
-  type TranscriptionModel,
-  type TranscriptionRequest,
+  TranscriptionModel,
+  TranscriptionRequest,
+  type TranscriptionOptions,
  type TranscriptionRequestInput,
 } from "./transcription.js"
 import { fileMediaType } from "./utils/media-type.js"
-import { Video, type VideoModel, type VideoRequest, type VideoRequestInput } from "./video.js"
+import { Video, VideoModel, VideoRequest, type VideoOptions, type VideoRequestInput } from "./video.js"

 /**
 * Promise-first entrypoint for scripts and non-Effect callers. One `ManagedRuntime` hosts the LLM, image, video, speech,
@@ -92,8 +93,17 @@ export const make = (options: Options = {}) => {
    cancel: (options) => run(generation.cancel(), options),
  })

+  // The typed `generate`/`stream` overloads take a concrete input or a request, not the union; normalize once here.
  const llmRequest = (input: RequestInput | LLMRequest) =>
    input instanceof LLMRequest ? Effect.succeed(input) : tryRequest(() => LLM.request(input))
+  const imageRequest = (input: ImageRequestInput | ImageRequest) =>
+    input instanceof ImageRequest ? input : Image.request(input)
+  const videoRequest = (input: VideoRequestInput | VideoRequest) =>
+    input instanceof VideoRequest ? input : Video.request(input)
+  const speechRequest = (input: SpeechRequestInput | SpeechRequest) =>
+    input instanceof SpeechRequest ? input : Speech.request(input)
+  const transcriptionRequest = (input: TranscriptionRequestInput | TranscriptionRequest) =>
+    input instanceof TranscriptionRequest ? input : Transcription.request(input)

  return {
    run,
@@ -145,58 +155,61 @@ export const make = (options: Options = {}) => {
      generate: <const Model extends ImageModel>(
        input: ImageRequestInput<Model> | ImageRequest,
        options?: AwaitOptions & RunOptions,
-      ) => run(Image.generate(input, { poll: options?.poll }), options),
+      ) => run(Image.generate(imageRequest(input), { poll: options?.poll }), options),
      stream: <const Model extends ImageModel>(
        input: ImageRequestInput<Model> | ImageRequest,
        options?: AwaitOptions & RunOptions,
-      ) => iterate(Image.stream(input, { poll: options?.poll }), options),
+      ) => iterate(Image.stream(imageRequest(input), { poll: options?.poll }), options),
      start: <const Model extends ImageModel>(input: ImageRequestInput<Model> | ImageRequest, options?: RunOptions) =>
-        run(Image.start(input), options).then(handle),
-      resume: (model: ImageModel, token: unknown, options?: RunOptions) =>
+        run(Image.start(imageRequest(input)), options).then(handle),
+      resume: <Options extends ImageOptions>(model: ImageModel<Options>, token: unknown, options?: RunOptions) =>
        run(Image.resume(model, token), options).then(handle),
    },
    video: {
      request: Video.request,
      start: <const Model extends VideoModel>(input: VideoRequestInput<Model> | VideoRequest, options?: RunOptions) =>
-        run(Video.start(input), options).then(handle),
+        run(Video.start(videoRequest(input)), options).then(handle),
      generate: <const Model extends VideoModel>(
        input: VideoRequestInput<Model> | VideoRequest,
        options?: AwaitOptions & RunOptions,
-      ) => run(Video.generate(input, { poll: options?.poll }), options),
-      resume: (model: VideoModel, token: unknown, options?: RunOptions) =>
+      ) => run(Video.generate(videoRequest(input), { poll: options?.poll }), options),
+      resume: <Options extends VideoOptions>(model: VideoModel<Options>, token: unknown, options?: RunOptions) =>
        run(Video.resume(model, token), options).then(handle),
      stream: <const Model extends VideoModel>(
        input: VideoRequestInput<Model> | VideoRequest,
        options?: AwaitOptions & RunOptions,
-      ) => iterate(Video.stream(input, { poll: options?.poll }), options),
+      ) => iterate(Video.stream(videoRequest(input), { poll: options?.poll }), options),
    },
    speech: {
      request: Speech.request,
      generate: <const Model extends SpeechModel>(
        input: SpeechRequestInput<Model> | SpeechRequest,
        options?: RunOptions,
-      ) => run(Speech.generate(input), options),
+      ) => run(Speech.generate(speechRequest(input)), options),
      stream: <const Model extends SpeechModel>(
        input: SpeechRequestInput<Model> | SpeechRequest,
        options?: RunOptions,
-      ) => iterate(Speech.stream(input), options),
+      ) => iterate(Speech.stream(speechRequest(input)), options),
    },
    transcription: {
      request: Transcription.request,
      generate: <const Model extends TranscriptionModel>(
        input: TranscriptionRequestInput<Model> | TranscriptionRequest,
        options?: AwaitOptions & RunOptions,
-      ) => run(Transcription.generate(input, { poll: options?.poll }), options),
+      ) => run(Transcription.generate(transcriptionRequest(input), { poll: options?.poll }), options),
      stream: <const Model extends TranscriptionModel>(
        input: TranscriptionRequestInput<Model> | TranscriptionRequest,
        options?: AwaitOptions & RunOptions,
-      ) => iterate(Transcription.stream(input, { poll: options?.poll }), options),
+      ) => iterate(Transcription.stream(transcriptionRequest(input), { poll: options?.poll }), options),
      start: <const Model extends TranscriptionModel>(
        input: TranscriptionRequestInput<Model> | TranscriptionRequest,
        options?: RunOptions,
-      ) => run(Transcription.start(input), options).then(handle),
-      resume: (model: TranscriptionModel, token: unknown, options?: RunOptions) =>
-        run(Transcription.resume(model, token), options).then(handle),
+      ) => run(Transcription.start(transcriptionRequest(input)), options).then(handle),
+      resume: <Options extends TranscriptionOptions>(
+        model: TranscriptionModel<Options>,
+        token: unknown,
+        options?: RunOptions,
+      ) => run(Transcription.resume(model, token), options).then(handle),
    },
    dispose: () => runtime.dispose(),
  }
@@ -70,11 +70,7 @@ export const protocol = Protocol.make({
      return {
        ...(yield* OpenAIChat.protocol.body.from(req)),
        enable_thinking: opts.enableThinking,
-        // Alibaba also rejects an explicit budget that is not below `max_completion_tokens`.
-        thinking_budget:
-          opts.thinkingBudget === undefined
-            ? undefined
-            : ProviderShared.fitThinkingBudget(opts.thinkingBudget, req.generation?.maxTokens),
+        thinking_budget: opts.thinkingBudget,
        preserve_thinking: opts.preserveThinking,
        clear_thinking: opts.clearThinking,
        thinking: opts.thinking,
@@ -26,21 +26,18 @@ export const protocol = Protocol.make({
    from: Effect.fn("AlibabaMessages.fromRequest")(function* (req) {
      const opts = yield* ProviderShared.validateWith(Schema.decodeUnknownEffect(Options))(req.providerOptions ?? {})
      // Model Studio accepts enabled thinking without Anthropic's mandatory token budget.
-      const body = yield* AnthropicMessages.protocol.body.from(
-        LLMRequest.update(req, {
-          providerOptions: { ...req.providerOptions, thinking: undefined },
-        }),
-      )
-      const budget = opts.thinking?.budgetTokens ?? opts.thinking?.budget_tokens
      return {
-        ...body,
+        ...(yield* AnthropicMessages.protocol.body.from(
+          LLMRequest.update(req, {
+            providerOptions: { ...req.providerOptions, thinking: undefined },
+          }),
+        )),
        thinking:
          opts.thinking === undefined
            ? undefined
            : {
                type: opts.thinking.type,
-                budget_tokens:
-                  budget === undefined ? undefined : ProviderShared.fitThinkingBudget(budget, body.max_tokens),
+                budget_tokens: opts.thinking.budgetTokens ?? opts.thinking.budget_tokens,
              },
      }
    }),
@@ -18,6 +18,7 @@ import {
  type CacheHint,
  type FinishReasonDetails,
  type FinishReason,
+  type JsonSchema,
  type MediaPart,
  type ProviderMetadata,
  type ProviderOptions,
@@ -30,13 +31,13 @@ import { classifyProviderFailure } from "../provider-error.js"
 import { effortUpdate, resolveEffortUpdates } from "../effort-updates.js"
 import * as Cache from "./utils/cache.js"
 import { Lifecycle } from "./utils/lifecycle.js"
+import { ToolSchemaProjection } from "./utils/tool-schema.js"
 import { ToolStream } from "./utils/tool-stream.js"

 const ADAPTER = "anthropic-messages"
 export const DEFAULT_BASE_URL = "https://api.anthropic.com/v1"
 export const PATH = "/messages"
 export const DEFAULT_MAX_TOKENS = 32_000
-const MIN_THINKING_BUDGET = 1_024
 const DEFAULT_EFFORT = "high"

 const SSE_EVENTS = new Set([
@@ -523,10 +524,10 @@ const redactedDataFromMetadata = (metadata: ProviderMetadata | undefined, key: s
  return typeof provider.redactedData === "string" ? provider.redactedData : undefined
 }

-const lowerTool = (breakpoints: Cache.Breakpoints, tool: ToolDefinition): AnthropicTool => ({
+const lowerTool = (breakpoints: Cache.Breakpoints, tool: ToolDefinition, inputSchema: JsonSchema): AnthropicTool => ({
  name: tool.name,
  description: tool.description,
-  input_schema: tool.inputSchema,
+  input_schema: inputSchema,
  cache_control: cacheControl(breakpoints, tool.cache),
 })

@@ -1026,15 +1027,6 @@ const applyThinkingBindingDefault = (model: LLMRequest["model"], thinking: Anthr
  }
 }

-// Anthropic also requires an explicit thinking budget below `max_tokens` and at or above its minimum.
-const fitThinking = (thinking: AnthropicThinking | undefined, maxTokens: number) =>
-  thinking?.type === "enabled"
-    ? {
-        ...thinking,
-        budget_tokens: ProviderShared.fitThinkingBudget(thinking.budget_tokens, maxTokens, MIN_THINKING_BUDGET),
-      }
-    : thinking
-
 const fromRequest = Effect.fn("AnthropicMessages.fromRequest")(function* (request: LLMRequest) {
  const options = yield* decodeOptions(request.providerOptions ?? {})
  const management = options.contextManagement
@@ -1047,7 +1039,12 @@ const fromRequest = Effect.fn("AnthropicMessages.fromRequest")(function* (reques
  // over-mark we keep their tool hints and shed the message-tail ones first.
  const breakpoints = Cache.newBreakpoints(ANTHROPIC_BREAKPOINT_CAP)
  const flattened = ProviderShared.flattenToolRequest(updates.request)
-  const tools = flattened.tools.length === 0 ? undefined : flattened.tools.map((tool) => lowerTool(breakpoints, tool))
+  const tools =
+    flattened.tools.length === 0
+      ? undefined
+      : flattened.tools.map((tool) =>
+          lowerTool(breakpoints, tool, ToolSchemaProjection.modelCompatibility(tool.inputSchema, request.model)),
+        )
  // Anthropic rejects tool_choice when tools are absent; "none" is only meaningful with tools present.
  const toolChoice = tools === undefined || !request.toolChoice ? undefined : yield* lowerToolChoice(request.toolChoice)
  const systemParts = request.system.filter((part) => part.text.length > 0)
@@ -1067,7 +1064,6 @@ const fromRequest = Effect.fn("AnthropicMessages.fromRequest")(function* (reques
  }
  const output_config =
    updates.effort === undefined && format === undefined ? undefined : { effort: updates.effort, format }
-  const maxTokens = generation?.maxTokens ?? DEFAULT_MAX_TOKENS
  const body = {
    model: request.model.id,
    system,
@@ -1075,12 +1071,12 @@ const fromRequest = Effect.fn("AnthropicMessages.fromRequest")(function* (reques
    tools,
    tool_choice: toolChoice,
    stream: true as const,
-    max_tokens: maxTokens,
+    max_tokens: generation?.maxTokens ?? DEFAULT_MAX_TOKENS,
    temperature: generation?.temperature,
    top_p: generation?.topP,
    top_k: generation?.topK,
    stop_sequences: generation?.stop,
-    thinking: applyThinkingBindingDefault(request.model, fitThinking(options.thinking, maxTokens)),
+    thinking: applyThinkingBindingDefault(request.model, options.thinking),
    output_config,
    // top-level passthrough per SDK MessageCreateParamsBase:4638,4643,4649,4654,4670
    cache_control: options.cache_control ?? options.cacheControl,
@@ -110,11 +110,8 @@ const fromRequest = Effect.fn("AssemblyAITranscription.fromRequest")(function* (
        language_code: request.language,
        language_detection: request.language === undefined ? true : undefined,
        prompt: request.prompt,
-        // Turn-level `utterances`, the only segments AssemblyAI returns, and `speakers_expected` require speaker labels.
-        speaker_labels:
-          request.diarize === true || request.timestamps === "segment" || request.speakers !== undefined
-            ? true
-            : undefined,
+        // Turn-level `utterances`, the only segments AssemblyAI returns, require speaker labels.
+        speaker_labels: request.diarize === true || request.timestamps === "segment" ? true : undefined,
        speakers_expected: request.speakers,
      },
      request.providerOptions,
@@ -158,7 +155,8 @@ const decodeResult = Effect.fn("AssemblyAITranscription.decodeResult")(function*
  const error = transcript.error ?? undefined
  if (status === "failed")
    return yield* output.ended("failed", `${route.name} transcription failed${error === undefined ? "" : `: ${error}`}`)
-  if (status !== "completed") return yield* output.pending(context.token.transcriptID)
+  if (status !== "completed")
+    return yield* output.invalid(`${route.name} transcript ${context.token.transcriptID} has not finished`)
  const duration = transcript.audio_duration ?? undefined
  return new TranscriptionResponse({
    text: transcript.text ?? "",
@@ -9,6 +9,7 @@ import {
  type CacheHint,
  type FinishReason,
  type FinishReasonDetails,
+  type JsonSchema,
  type LLMRequest,
  type LanguageModel,
  type ProviderMetadata,
@@ -25,6 +26,7 @@ import { BedrockCache } from "./utils/bedrock-cache.js"
 import { BedrockMedia } from "./utils/bedrock-media.js"
 import { Lifecycle } from "./utils/lifecycle.js"
 import { MistralToolID } from "./utils/mistral-tool-id.js"
+import { ToolSchemaProjection } from "./utils/tool-schema.js"
 import { ToolStream } from "./utils/tool-stream.js"
 import { concatBytes } from "../utils/bytes.js"

@@ -219,18 +221,22 @@ type BedrockEvent = Schema.Schema.Type<typeof BedrockEvent>
 // =============================================================================
 // Request Lowering
 // =============================================================================
-const lowerToolSpec = (tool: ToolDefinition): BedrockToolSpec => ({
+const lowerToolSpec = (tool: ToolDefinition, inputSchema: JsonSchema): BedrockToolSpec => ({
  toolSpec: {
    name: tool.name,
    ...(tool.description.trim().length > 0 ? { description: tool.description } : {}),
-    inputSchema: { json: tool.inputSchema },
+    inputSchema: { json: inputSchema },
  },
 })

-const lowerTools = (breakpoints: BedrockCache.Breakpoints, tools: ReadonlyArray<ToolDefinition>): BedrockTool[] => {
+const lowerTools = (
+  model: LanguageModel,
+  breakpoints: BedrockCache.Breakpoints,
+  tools: ReadonlyArray<ToolDefinition>,
+): BedrockTool[] => {
  const result: BedrockTool[] = []
  for (const tool of tools) {
-    result.push(lowerToolSpec(tool))
+    result.push(lowerToolSpec(tool, ToolSchemaProjection.modelCompatibility(tool.inputSchema, model)))
    const cachePoint = BedrockCache.block(breakpoints, tool.cache)
    if (cachePoint) result.push(cachePoint)
  }
@@ -435,39 +441,19 @@ const isHighReasoningEffort = Schema.is(
  }),
 )

-const Options = Schema.Struct({
-  thinking: Schema.optional(Schema.Struct({ type: Schema.Literal("enabled"), budgetTokens: Schema.Number })),
-})
-export type OptionsInput = typeof Options.Type
-const decodeOptions = ProviderShared.validateWith(Schema.decodeUnknownEffect(Options))
-// Claude on Bedrock requires the thinking budget below `maxTokens`, with a minimum of 1,024.
-const MIN_THINKING_BUDGET = 1_024
-
 const fromRequest = Effect.fn("BedrockConverse.fromRequest")(function* (request: LLMRequest) {
  const toolChoice = request.toolChoice ? yield* lowerToolChoice(request.toolChoice) : undefined
  const flattened = ProviderShared.flattenToolRequest(request)
  const generation = request.generation
-  const options = yield* decodeOptions(request.providerOptions ?? {})
  const maxTokens =
    isNova2(request.model) && isHighReasoningEffort(request.http?.body) ? undefined : generation?.maxTokens
-  const thinking =
-    options.thinking === undefined
-      ? undefined
-      : {
-          type: "enabled",
-          budget_tokens: ProviderShared.fitThinkingBudget(
-            options.thinking.budgetTokens,
-            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)
  const toolConfig = (() => {
    if (flattened.tools.length === 0) return undefined
    return {
-      tools: lowerTools(breakpoints, flattened.tools),
+      tools: lowerTools(request.model, breakpoints, flattened.tools),
      // Converse has no native "none". Keep definitions stable for prompt
      // caching and omit only the unsupported choice.
      toolChoice,
@@ -501,15 +487,9 @@ const fromRequest = Effect.fn("BedrockConverse.fromRequest")(function* (request:
    system,
    inferenceConfig,
    toolConfig,
-    // Converse's base inferenceConfig has no topK or thinking; Anthropic/Nova accept them
-    // as model-specific fields, so they go through additionalModelRequestFields.
-    additionalModelRequestFields:
-      generation?.topK === undefined && thinking === undefined
-        ? undefined
-        : {
-            ...(generation?.topK === undefined ? {} : { top_k: generation.topK }),
-            ...(thinking === undefined ? {} : { thinking }),
-          },
+    // Converse's base inferenceConfig has no topK; Anthropic/Nova accept it
+    // as a model-specific field, so it goes through additionalModelRequestFields.
+    additionalModelRequestFields: generation?.topK === undefined ? undefined : { top_k: generation.topK },
  }
 })

@@ -31,21 +31,13 @@ export type Request = ImageRequestFor<BlackForestLabsImageOptions>
 // 2. Token and response schemas
 // ---------------------------------------------------------------------------

-/**
- * Regional clusters answer on different hosts, so the returned `polling_url` is followed verbatim. BFL reports the
- * credit cost on submit, so it rides on the token; it is optional so tokens persisted before it existed still decode.
- */
-export const Token = Schema.Struct({
-  id: Schema.String,
-  pollingURL: Schema.String,
-  cost: Schema.optionalKey(Schema.Number),
-})
+/** Regional clusters answer on different hosts, so the returned `polling_url` is followed verbatim. */
+export const Token = Schema.Struct({ id: Schema.String, pollingURL: Schema.String })
 export type Token = Schema.Schema.Type<typeof Token>

 const StartResponse = Schema.Struct({
  id: Schema.String,
  polling_url: Schema.String,
-  cost: optionalNull(Schema.Number),
 })

 const Result = Schema.Struct({
@@ -153,11 +145,7 @@ const fromRequest = Effect.fn("BlackForestLabsImages.fromRequest")(function* (re
 // ---------------------------------------------------------------------------

 const decodeStart = route.decodeStarted(StartResponse, (value) => ({
-  token: {
-    id: value.id,
-    pollingURL: value.polling_url,
-    ...(value.cost === undefined || value.cost === null ? {} : { cost: value.cost }),
-  },
+  token: { id: value.id, pollingURL: value.polling_url },
  snapshot: { id: value.id, status: "queued" },
 }))

@@ -181,16 +169,14 @@ const decodeResult = Effect.fn("BlackForestLabsImages.decodeResult")(function* (
  if (isModerated(document.status)) return yield* output.contentPolicy(`${route.name} moderated the generation`)
  if (status === "failed" || status === "expired")
    return yield* output.ended(status, `${route.name} generation ${context.token.id} ended with ${document.status}`)
-  if (status !== "completed") return yield* output.pending(context.token.id)
-  if (document.result === undefined || document.result === null)
+  if (status !== "completed" || document.result === undefined || document.result === null)
    return yield* output.invalid(`${route.name} generation ${context.token.id} has no result`)
  const { sample, seed, prompt, ...rest } = document.result
-  // A settled `cost` on the result supersedes the submit-time cost carried on the token.
-  const cost = document.cost ?? context.token.cost
  return new ImageResponse({
    // `sample` is a signed URL that expires 10 minutes after the result is ready, so it is downloaded now.
    images: [yield* context.materialize(Media.url(sample))],
-    usage: cost === undefined ? undefined : { type: "credits", credits: cost },
+    usage:
+      document.cost === undefined || document.cost === null ? undefined : { type: "credits", credits: document.cost },
    providerMetadata: {
      bfl: { id: context.token.id, seed: seed ?? undefined, prompt: prompt ?? undefined, ...rest },
    },
@@ -67,9 +67,6 @@ const queryParameters = (request: Request) => {
 }

 const fromRequest = Effect.fn("DeepgramSpeech.fromRequest")(function* (request: 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[request.format] === undefined &&
@@ -120,7 +117,7 @@ const finish = (state: State, context: MediaProtocol.ResponseContext<Request>) =
 // ---------------------------------------------------------------------------

 export const protocol = MediaProtocol.stream<Request, SpeechEvent, Uint8Array, State>(route, {
-  unsupported: ["voice", "language", "instructions"],
+  unsupported: ["voice", "language", "instructions", "timestamps"],
  body: { from: fromRequest },
  frames: (bytes) => bytes,
  initial: () => ({ chunks: [] }),
@@ -49,7 +49,7 @@ const QueueResult = Schema.StructWithRest(
 // ---------------------------------------------------------------------------

 const sizing = (model: string) => {
-  if (/^fal-ai\/(nano-banana|flux-pro\/(v1\.1-ultra|kontext))/.test(model)) return "aspect_ratio"
+  if (/^fal-ai\/(nano-banana|flux-pro\/v1\.1-ultra)/.test(model)) return "aspect_ratio"
  if (model.startsWith("fal-ai/flux")) return "image_size"
  return undefined
 }
@@ -63,24 +63,20 @@ const validate = (request: Request) => {
    return Effect.fail(route.unsupported("media.size", `${id} sizes by aspectRatio`))
  if (request.aspectRatio !== undefined && field === "image_size")
    return Effect.fail(route.unsupported("media.aspectRatio", `${id} sizes by size (image_size)`))
-  if ((request.images?.length ?? 0) > 1 && !takesImageList(id))
+  if ((request.images?.length ?? 0) > 1 && !isEdit(id))
    return Effect.fail(
-      route.unsupported(
-        "media.images",
-        `${id} takes one image_url; use an /edit or /multi endpoint for several images`,
-      ),
+      route.unsupported("media.images", `${id} takes one image_url; use an /edit endpoint for several images`),
    )
  return Effect.void
 }

-// `/edit` and `/multi` (Kontext) endpoints take an `image_urls` list; image-to-image, fill, and Ultra take one
-// `image_url` (beside `mask_url`).
-const takesImageList = (model: string) => model.endsWith("/edit") || model.endsWith("/multi")
+// `/edit` endpoints take an `image_urls` list; image-to-image, fill, and Ultra take one `image_url` (beside `mask_url`).
+const isEdit = (model: string) => model.endsWith("/edit")

 const fromRequest = Effect.fn("FalImages.fromRequest")(function* (request: Request) {
  yield* validate(request)
  const images = yield* Effect.forEach(request.images ?? [], (image) => FalQueue.mediaUrl(image, route.name))
-  const list = takesImageList(request.model.id)
+  const edit = isEdit(request.model.id)
  return MediaProtocol.json(
    mergeJsonRecords(
      {
@@ -90,8 +86,8 @@ const fromRequest = Effect.fn("FalImages.fromRequest")(function* (request: Reque
        image_size: request.size === undefined ? undefined : MediaInput.dimensions(request.size),
        aspect_ratio: request.aspectRatio,
        output_format: request.format,
-        image_urls: list && images.length > 0 ? images : undefined,
-        image_url: list ? undefined : images[0],
+        image_urls: edit && images.length > 0 ? images : undefined,
+        image_url: edit ? undefined : images[0],
        mask_url: request.mask === undefined ? undefined : yield* FalQueue.mediaUrl(request.mask, route.name),
      },
      request.providerOptions,
@@ -116,14 +112,12 @@ const decodeResult = Effect.fn("FalImages.decodeResult")(function* (
  // With the safety checker on, flagged images come back blacked out rather than omitted.
  const flagged = (has_nsfw_concepts ?? []).flatMap((value, index) => (value ? [index] : []))
  return new ImageResponse({
-    images: images.map((image) => {
-      const info = { width: image.width ?? undefined, height: image.height ?? undefined }
-      // `sync_mode: true` returns data URIs instead of hosted URLs.
-      return (
-        Media.parseDataUrl(image.url, { info }) ??
-        Media.url(image.url, { mediaType: image.content_type ?? undefined, info })
-      )
-    }),
+    images: images.map((image) =>
+      Media.url(image.url, {
+        mediaType: image.content_type ?? undefined,
+        info: { width: image.width ?? undefined, height: image.height ?? undefined },
+      }),
+    ),
    notices:
      flagged.length === 0
        ? undefined
@@ -11,6 +11,7 @@ import {
  Usage,
  type FinishReason,
  type LLMRequest,
+  type LanguageModel,
  type MediaPart,
  type ProviderMetadata,
  type ProviderOptions,
@@ -23,12 +24,11 @@ import { Media } from "../media.js"
 import { JsonObject, knownString, lenient, optionalArray, optionalNull, ProviderShared } from "./shared.js"
 import { GeminiGenerateContent } from "./utils/gemini-generate-content.js"
 import { Lifecycle } from "./utils/lifecycle.js"
+import { ToolSchemaProjection } from "./utils/tool-schema.js"

 const ADAPTER = "gemini"
 // Google documents this sentinel for replaying Gemini 3 function calls after their original signature was lost.
 const SKIP_THOUGHT_SIGNATURE_VALIDATOR = "skip_thought_signature_validator"
-// Gemini 2.5 rejects a budget under the model's minimum: 512 on Flash-Lite, the highest, and 128 on Pro.
-const MIN_THINKING_BUDGET = 512
 export const DEFAULT_BASE_URL = "https://generativelanguage.googleapis.com/v1beta"

 // Gemini 3 rejects replayed function calls without a thought signature. Google's SDKs avoid that in normal chats by
@@ -268,11 +268,12 @@ interface ParserState {
 // =============================================================================
 // Request Lowering
 // =============================================================================
-// Tool schemas go in `parametersJsonSchema`, which accepts standard JSON Schema.
-const lowerTool = (tool: ToolDefinition) => ({
+// Tool schemas go in `parametersJsonSchema`, which accepts standard JSON Schema. Gemini's schema
+// rules are this API's default, including for tuned endpoints whose IDs do not name Gemini.
+const lowerTool = (tool: ToolDefinition, model: LanguageModel) => ({
  name: tool.name,
  description: tool.description,
-  parametersJsonSchema: tool.inputSchema,
+  parametersJsonSchema: ToolSchemaProjection.modelCompatibility(tool.inputSchema, model, "gemini"),
 })

 const lowerToolConfig = (toolChoice: NonNullable<LLMRequest["toolChoice"]>) =>
@@ -451,22 +452,10 @@ const fromRequest = Effect.fn("Gemini.fromRequest")(function* (request: LLMReque
    presencePenalty: generation?.presencePenalty,
    seed: generation?.seed,
    stopSequences: generation?.stop,
-    // Gemini accepts a budget above `maxOutputTokens`, but thinking then leaves the answer empty.
    thinkingConfig:
      options.thinkingConfig === undefined
        ? undefined
-        : {
-            ...options.thinkingConfig,
-            includeThoughts: options.thinkingConfig.includeThoughts ?? true,
-            thinkingBudget:
-              options.thinkingConfig.thinkingBudget === undefined
-                ? undefined
-                : ProviderShared.fitThinkingBudget(
-                    options.thinkingConfig.thinkingBudget,
-                    generation?.maxTokens,
-                    MIN_THINKING_BUDGET,
-                  ),
-          },
+        : { ...options.thinkingConfig, includeThoughts: options.thinkingConfig.includeThoughts ?? true },
  }

  return {
@@ -479,7 +468,7 @@ const fromRequest = Effect.fn("Gemini.fromRequest")(function* (request: LLMReque
    tools: hasTools
      ? [
          {
-            functionDeclarations: flattened.tools.map(lowerTool),
+            functionDeclarations: flattened.tools.map((tool) => lowerTool(tool, request.model)),
          },
        ]
      : undefined,
@@ -815,8 +804,6 @@ export const protocol = Protocol.make({
    schema: GeminiBody,
    from: fromRequest,
  },
-  // Gemini's schema rules are this API's default, including for tuned endpoints whose IDs do not name Gemini.
-  sanitizer: "gemini",
  stream: {
    event: Protocol.jsonEvent(GeminiEvent),
    initial: (request) => ({
@@ -101,7 +101,7 @@ const generationConfig = (request: Request) => {
 const fromRequest = Effect.fn("GoogleImages.fromRequest")(function* (request: Request) {
  if (request.n !== undefined && request.n > 1)
    return yield* route.unsupported(
-      "media.n",
+      "image.n",
      `${route.name} generates one image per request; call it once per image instead of n=${request.n}`,
    )
  const parts = yield* Effect.forEach(request.images ?? [], (image) =>
@@ -56,18 +56,10 @@ interface State extends SpeechStream.Audio, GeminiGenerateContent.Metadata {
 // ---------------------------------------------------------------------------

 const fromRequest = Effect.fn("GoogleSpeech.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", `${route.name} does not return timestamps`)
-  if (request.format === "pcm" && request.mode === "generate" && /^gemini-3\.8-.*-tts(?:-|$)/.test(request.model.id))
-    return yield* route.unsupported(
-      "media.format",
-      `${route.name} returns WAV by default for Gemini 3.8 TTS unary requests; omit the format to accept it`,
-    )
  if (request.format !== undefined && request.format !== "pcm")
    return yield* route.unsupported(
      "media.format",
-      `${route.name} only accepts raw PCM as an explicit format; omit it to accept the provider's default output`,
+      `${route.name} only returns raw PCM; request format "pcm" or omit it, then wrap the samples yourself`,
    )
  const voiceName = SpeechStream.voiceID(request.voice)
  return MediaProtocol.json(
@@ -105,18 +97,10 @@ const step = Effect.fn("GoogleSpeech.step")(function* (state: State, frame: stri
  return [next, audio.flatMap((part) => SpeechStream.delta(next, part.data)[1])] as const
 })

-const finish = (state: State, context: MediaProtocol.ResponseContext<Request>) => {
+const finish = (state: State) => {
  const sampleRate = SpeechStream.sampleRate(state.mimeType) ?? DEFAULT_SAMPLE_RATE
-  const output =
-    state.mimeType?.split(";")[0]?.toLowerCase() === "audio/wav"
-      ? SpeechStream.container("wav", sampleRate)
-      : SpeechStream.pcm("pcm_s16le", sampleRate, state.mimeType ?? `audio/L16;codec=pcm;rate=${sampleRate}`)
-  if (context.request.format === "pcm" && output.info.format !== "pcm")
-    return Effect.fail(
-      route.frameError(`Google Speech returned ${output.info.format} instead of the requested raw PCM`),
-    )
  return SpeechStream.finish(route, state, {
-    ...output,
+    ...SpeechStream.pcm("pcm_s16le", sampleRate, state.mimeType ?? `audio/L16;codec=pcm;rate=${sampleRate}`),
    usage: GeminiGenerateContent.usage(state.usage),
    providerMetadata: GeminiGenerateContent.providerMetadata(state),
    detail: state.finishReason === undefined ? undefined : `finish reason: ${state.finishReason}`,
@@ -128,7 +112,7 @@ const finish = (state: State, context: MediaProtocol.ResponseContext<Request>) =
 // ---------------------------------------------------------------------------

 export const protocol = MediaProtocol.stream<Request, SpeechEvent, string, State>(route, {
-  unsupported: ["instructions", "speed"],
+  unsupported: ["instructions", "speed", "timestamps"],
  body: { from: fromRequest },
  frames: (bytes, context) => GeminiGenerateContent.frames(bytes, context.request.mode),
  initial: () => ({ chunks: [] }),
@@ -149,7 +149,8 @@ const decodeResult = Effect.fn("GoogleVideo.decodeResult")(function* (
  const output = yield* decodeOperation(response)
  const operation = output.value
  const status = statusOf(operation)
-  if (status === "running") return yield* output.pending(context.token.operation)
+  if (status === "running")
+    return yield* output.invalid(`${route.name} operation ${context.token.operation} has not finished`)
  if (status === "failed")
    return yield* output.ended(
      "failed",
@@ -5,6 +5,7 @@ import { LLMEvent, LLMRequest, Message, ToolResultPart } from "../schema/index.j
 import { OpenResponses } from "./open-responses.js"
 import { JsonObject, optionalArray, optionalNull, ProviderShared } from "./shared.js"
 import { ResponsesHostedTools } from "./utils/responses-hosted-tools.js"
+import { ToolSchemaProjection } from "./utils/tool-schema.js"
 import { detectMediaType } from "../utils/media-type.js"

 const ADAPTER = "meta-responses"
@@ -102,7 +103,12 @@ const fromRequest = Effect.fn("MetaResponses.fromRequest")(function* (request: L
        ? undefined
        : yield* Effect.forEach(projected.tools, (tool) =>
            Effect.gen(function* () {
-              if (tool.native === undefined) return yield* OpenResponses.lowerTool(NAME, tool)
+              if (tool.native === undefined)
+                return yield* OpenResponses.lowerTool(
+                  NAME,
+                  tool,
+                  ToolSchemaProjection.modelCompatibility(tool.inputSchema, request.model),
+                )
              return yield* ProviderShared.validateWith(Schema.decodeUnknownEffect(NativeTool))(tool.native.meta)
            }),
          ),
@@ -13,6 +13,7 @@ import {
  UnknownProviderError,
  Usage,
  type FinishReasonDetails,
+  type JsonSchema,
  type LLMRequest,
  type MediaPart,
  type ToolCallPart,
@@ -22,6 +23,7 @@ import { classifyProviderFailure } from "../provider-error.js"
 import { JsonObject, optionalArray, optionalNull, ProviderShared } from "./shared.js"
 import { Lifecycle } from "./utils/lifecycle.js"
 import { MistralToolID } from "./utils/mistral-tool-id.js"
+import { ToolSchemaProjection } from "./utils/tool-schema.js"
 import { ToolStream } from "./utils/tool-stream.js"

 const ADAPTER = "mistral-chat"
@@ -366,9 +368,9 @@ const lowerMessages = Effect.fn("MistralChat.lowerMessages")(function* (request:
  return messages
 })

-const lowerTool = (tool: ToolDefinition): MistralTool => ({
+const lowerTool = (tool: ToolDefinition, inputSchema: JsonSchema): MistralTool => ({
  type: "function",
-  function: { name: tool.name, description: tool.description, parameters: tool.inputSchema, strict: false },
+  function: { name: tool.name, description: tool.description, parameters: inputSchema, strict: false },
 })

 export const fromRequest = Effect.fn("MistralChat.fromRequest")(function* (request: LLMRequest) {
@@ -394,7 +396,12 @@ export const fromRequest = Effect.fn("MistralChat.fromRequest")(function* (reque
  return {
    model: request.model.id,
    messages: yield* lowerMessages(flattened.request),
-    tools: flattened.tools.length > 0 ? flattened.tools.map(lowerTool) : undefined,
+    tools:
+      flattened.tools.length > 0
+        ? flattened.tools.map((tool) =>
+            lowerTool(tool, ToolSchemaProjection.modelCompatibility(tool.inputSchema, request.model)),
+          )
+        : undefined,
    tool_choice: toolChoice,
    stream: true as const,
    max_tokens: request.generation?.maxTokens,
@@ -8,6 +8,7 @@ import {
  ProviderInternalError,
  Usage,
  type FinishReason,
+  type JsonSchema,
  type LLMRequest,
  type MediaPart,
  type ProviderMetadata,
@@ -23,6 +24,7 @@ import { classifyProviderFailure } from "../provider-error.js"
 import { effortUpdate } from "../effort-updates.js"
 import { OpenResponsesOptions } from "./utils/open-responses-options.js"
 import { Lifecycle } from "./utils/lifecycle.js"
+import { ToolSchemaProjection } from "./utils/tool-schema.js"
 import { ToolStream } from "./utils/tool-stream.js"

 const ADAPTER = "open-responses"
@@ -441,24 +443,23 @@ interface ReasoningStreamItem {
 // =============================================================================
 // Request Lowering
 // =============================================================================
-export const lowerTool = Effect.fn("OpenResponses.lowerTool")(function* (protocolName: string, tool: ToolDefinition) {
+export const lowerTool = Effect.fn("OpenResponses.lowerTool")(function* (
+  protocolName: string,
+  tool: ToolDefinition,
+  inputSchema: JsonSchema,
+) {
  if (tool.native !== undefined)
    return yield* ProviderShared.invalidRequest(`${protocolName} does not support provider-native tool ${tool.name}`)
  return {
    type: "function" as const,
    name: tool.name,
    description: tool.description,
-    parameters: tool.inputSchema,
+    parameters: inputSchema,
    // The common tool definition does not currently express Responses strict-schema policy.
    strict: false,
  }
 })

-export const lowerTools = (tools: ReadonlyArray<ToolDefinition>, adapter: ProviderAdapter) =>
-  Effect.forEach(tools, (tool) =>
-    tool.native !== undefined && adapter.nativeTool ? adapter.nativeTool(tool.native) : lowerTool(adapter.name, tool),
-  )
-
 export const lowerToolChoice = (protocolName: string, toolChoice: NonNullable<LLMRequest["toolChoice"]>) =>
  ProviderShared.matchToolChoice(protocolName, toolChoice, {
    auto: () => "auto" as const,
@@ -820,7 +821,14 @@ export const fromRequestWithAdapter = Effect.fn("OpenResponses.fromRequestWithAd
  return {
    ...(yield* lowerConversation(projected.request, adapter)),
    ...lowerGeneration(request),
-    tools: projected.tools.length === 0 ? undefined : yield* lowerTools(projected.tools, adapter),
+    tools:
+      projected.tools.length === 0
+        ? undefined
+        : yield* Effect.forEach(projected.tools, (tool) =>
+            tool.native !== undefined && adapter.nativeTool
+              ? adapter.nativeTool(tool.native)
+              : lowerTool(adapter.name, tool, ToolSchemaProjection.modelCompatibility(tool.inputSchema, request.model)),
+          ),
    tool_choice:
      allowedToolChoice(request) ??
      (request.toolChoice ? yield* lowerToolChoice(adapter.name, request.toolChoice) : undefined),
@@ -17,6 +17,7 @@ import {
  type FinishReason,
  type FinishReasonDetails,
  type CacheHint,
+  type JsonSchema,
  type LLMRequest,
  type MediaPart,
  type ReasoningPart,
@@ -28,6 +29,7 @@ import { classifyProviderFailure } from "../provider-error.js"
 import { isRecord, JsonObject, optionalArray, optionalNull, ProviderShared } from "./shared.js"
 import { OpenAIOptions } from "./utils/openai-options.js"
 import { Lifecycle } from "./utils/lifecycle.js"
+import { ToolSchemaProjection } from "./utils/tool-schema.js"
 import { ToolStream } from "./utils/tool-stream.js"

 const ADAPTER = "openai-chat"
@@ -328,12 +330,17 @@ interface LoweringOptions {
  readonly toolCallID?: (id: string) => string
 }

-const lowerTool = (tool: ToolDefinition, options: LoweringOptions, supportsStrictMode: boolean): OpenAIChatTool => ({
+const lowerTool = (
+  tool: ToolDefinition,
+  inputSchema: JsonSchema,
+  options: LoweringOptions,
+  supportsStrictMode: boolean,
+): OpenAIChatTool => ({
  type: "function",
  function: {
    name: tool.name,
    description: tool.description,
-    parameters: tool.inputSchema,
+    parameters: inputSchema,
    ...(supportsStrictMode ? { strict: false } : {}),
  },
  cache_control: options.cacheControl?.(tool.cache),
@@ -818,7 +825,14 @@ export const fromRequest = Effect.fn("OpenAIChat.fromRequest")(function* (
        ? hasHistory
          ? []
          : undefined
-        : flattened.tools.map((tool) => lowerTool(tool, options, supportsStrictMode)),
+        : flattened.tools.map((tool) =>
+            lowerTool(
+              tool,
+              ToolSchemaProjection.modelCompatibility(tool.inputSchema, request.model),
+              options,
+              supportsStrictMode,
+            ),
+          ),
    tool_choice: hasActiveTools && request.toolChoice ? yield* lowerToolChoice(request.toolChoice) : undefined,
    stream: true as const,
    ...(supportsUsageInStreaming ? { stream_options: { include_usage: true } } : {}),
@@ -48,17 +48,15 @@ const Usage = Schema.Struct({
  output_tokens_details: Schema.optional(Schema.Record(Schema.String, Schema.Unknown)),
 })

-/** What the provider actually rendered; it can differ from the request when `auto` or a default applied. */
-const Settings = {
-  output_format: Schema.optional(Schema.String),
-  size: Schema.optional(Schema.String),
-  quality: Schema.optional(Schema.String),
-  background: Schema.optional(Schema.String),
-}
-
 const OpenAIImageResponse = Schema.Struct({
-  data: Schema.Array(Schema.Struct({ b64_json: Schema.String })),
-  ...Settings,
+  data: Schema.Array(
+    Schema.Struct({
+      b64_json: Schema.optional(Schema.String),
+      url: Schema.optional(Schema.String),
+      revised_prompt: Schema.optional(Schema.String),
+    }),
+  ),
+  output_format: Schema.optional(Schema.String),
  usage: Schema.optional(Usage),
 })

@@ -71,13 +69,11 @@ const StreamEvent = Schema.Union([
    type: Schema.Literals(["image_generation.partial_image", "image_edit.partial_image"]),
    b64_json: Schema.String,
    partial_image_index: Schema.Number,
-    ...Settings,
    output_format: Schema.String,
  }),
  Schema.Struct({
    type: Schema.Literals(["image_generation.completed", "image_edit.completed"]),
    b64_json: Schema.String,
-    ...Settings,
    output_format: Schema.String,
    usage: Schema.optional(Usage),
  }),
@@ -96,9 +92,6 @@ type Frame = string | { readonly document: string; readonly requested: string |
 interface State {
  readonly completed: number
  readonly format?: string
-  readonly size?: string
-  readonly quality?: string
-  readonly background?: string
  readonly usage?: MediaUsage
 }

@@ -117,6 +110,10 @@ const nativeOptions = (options: OpenAIImageOptions | undefined) => {

 const streamOptions = (request: MediaProtocol.Addressed<Request>) => {
  if (request.mode !== "stream") return Effect.succeed(undefined)
+  if (request.model.id.startsWith("dall-e"))
+    return Effect.fail(
+      route.unsupported("media.stream", `${request.model.id} does not stream; use Image.generate or a GPT image model`),
+    )
  if (request.n !== undefined && request.n > 1)
    return Effect.fail(
      route.unsupported("media.n", `${route.name} streams one image; use Image.generate for n=${request.n}`),
@@ -197,34 +194,21 @@ const usage = (value: Schema.Schema.Type<typeof Usage> | undefined): MediaUsage
        details: { openai: value },
      }

-/** `size` echoes the rendered `WIDTHxHEIGHT`; `auto` or any other value leaves the dimensions unknown. */
-const info = (format: string, size: string | undefined): Media.Info => {
-  const match = size?.match(/^(\d+)x(\d+)$/)
-  return match ? { format, width: Number(match[1]), height: Number(match[2]) } : { format }
-}
-
-const eventImage = (frame: string, label: string, data: string, format: string, size: string | undefined) =>
+const eventImage = (frame: string, label: string, data: string, format: string) =>
  MediaInput.decodedAsset((message, cause) => route.frameError(message, frame, cause), label, data, `image/${format}`, {
-    info: info(format, size),
+    info: { format },
  })

 const onEvent = Effect.fn("OpenAIImages.onEvent")(function* (state: State, frame: string) {
  const event = yield* decodeEvent(frame)
  const format = event.output_format
  if ("partial_image_index" in event) {
-    const image = yield* eventImage(frame, `${route.name} partial image`, event.b64_json, format, event.size)
+    const image = yield* eventImage(frame, `${route.name} partial image`, event.b64_json, format)
    return [state, [ImagePartialEvent.make({ index: event.partial_image_index, image })]] as const
  }
-  const image = yield* eventImage(frame, `${route.name} result ${state.completed}`, event.b64_json, format, event.size)
+  const image = yield* eventImage(frame, `${route.name} result ${state.completed}`, event.b64_json, format)
  return [
-    {
-      completed: state.completed + 1,
-      format,
-      size: event.size,
-      quality: event.quality,
-      background: event.background,
-      usage: usage(event.usage),
-    },
+    { ...state, completed: state.completed + 1, format, usage: usage(event.usage) },
    [ImageOutputEvent.make({ index: state.completed, image })],
  ] as const
 })
@@ -235,20 +219,16 @@ const onDocument = Effect.fn("OpenAIImages.onDocument")(function* (frame: Exclud
    Effect.mapError((cause) => invalid(`${route.name} returned an invalid response`, cause)),
  )
  const format = decoded.output_format ?? frame.requested ?? "png"
+  const mediaType = `image/${format}`
  const images = yield* Effect.forEach(decoded.data, (item, index) =>
-    MediaInput.decodedAsset(invalid, `${route.name} result ${index}`, item.b64_json, `image/${format}`, {
-      info: info(format, decoded.size),
+    MediaInput.imageOutput(invalid, `${route.name} result ${index}`, item, mediaType, {
+      info: { format },
+      providerMetadata:
+        item.revised_prompt === undefined ? undefined : { openai: { revisedPrompt: item.revised_prompt } },
    }),
  )
  if (images.length === 0) return yield* invalid(`${route.name} returned no images`)
-  const state: State = {
-    completed: images.length,
-    format,
-    size: decoded.size,
-    quality: decoded.quality,
-    background: decoded.background,
-    usage: usage(decoded.usage),
-  }
+  const state: State = { completed: images.length, format, usage: usage(decoded.usage) }
  return [state, images.map((image, index) => ImageOutputEvent.make({ index, image }))] as const
 })

@@ -257,17 +237,7 @@ const step = (state: State, frame: Frame) => (typeof frame === "string" ? onEven
 const finish = (state: State) => {
  if (state.completed === 0) return Effect.fail(route.incomplete())
  return Effect.succeed([
-    ImageFinishEvent.make({
-      usage: state.usage,
-      providerMetadata: {
-        openai: {
-          outputFormat: state.format,
-          size: state.size,
-          quality: state.quality,
-          background: state.background,
-        },
-      },
-    }),
+    ImageFinishEvent.make({ usage: state.usage, providerMetadata: { openai: { outputFormat: state.format } } }),
  ])
 }

@@ -5,12 +5,20 @@ import { Auth } from "../route/auth.js"
 import { Endpoint } from "../route/endpoint.js"
 import { Protocol } from "../route/protocol.js"
 import { HttpTransport } from "../route/transport/index.js"
-import { LLMRequest, type ToolDefinition, type ToolEntry } from "../schema/index.js"
+import {
+  LLMRequest,
+  mergeJsonRecords,
+  type JsonSchema,
+  type LanguageModel,
+  type ToolDefinition,
+  type ToolEntry,
+} from "../schema/index.js"
 import { resolveEffortUpdates } from "../effort-updates.js"
 import { OpenResponses } from "./open-responses.js"
 import { OpenResponsesOptions } from "./utils/open-responses-options.js"
 import { JsonObject, optionalArray, optionalNull, ProviderShared } from "./shared.js"
 import { ResponsesHostedTools } from "./utils/responses-hosted-tools.js"
+import { ToolSchemaProjection } from "./utils/tool-schema.js"
 import { OpenResponsesChannel } from "./open-responses-channel.js"
 import { ResponsesCompaction } from "./utils/responses-compaction.js"
 import { ResponsesCheckpoint } from "./utils/responses-checkpoint.js"
@@ -135,6 +143,11 @@ export const CompactionTrigger = Schema.Struct({ type: Schema.Literal("compactio
 const CheckpointBody = Schema.Struct({
  ...OpenAIResponsesBody.fields,
  input: Schema.Array(Schema.Union([OpenAIResponsesInputItem, CompactionTrigger])),
+  store: Schema.Literal(false),
+  prompt_cache_retention: optionalNull(Schema.String),
+  prompt_cache_options: optionalNull(
+    Schema.Struct({ mode: Schema.optional(Schema.String), ttl: Schema.optional(Schema.String) }),
+  ),
 })

 const adapter = {
@@ -143,14 +156,12 @@ const adapter = {
  restoreHostedToolItem: (item: unknown) => (Schema.is(OpenAIResponsesHostedToolItem)(item) ? item : undefined),
 } satisfies OpenResponses.ProviderAdapter

-// GPT-6 Astra, Sol, and Luna accept `configuration_update` only in standard mode (not `reasoning.mode: "pro"` or
-// `-pro` slugs), and never alongside automatic `context_management` compaction.
+// Only GPT-6 Astra accepts `configuration_update`, and never alongside automatic `context_management` compaction.
 const supportsEffortUpdates = (request: LLMRequest) => {
  if (request.providerOptions?.contextManagement !== undefined) return false
-  if (Schema.is(Schema.Struct({ mode: Schema.Literal("pro") }))(request.http?.body?.reasoning)) return false
  const override = request.model.compatibility?.supportsEffortUpdates
  if (override !== undefined) return override
-  return /(?:^|\/)gpt-6-(?:astra|sol|luna)$/i.test(request.model.id)
+  return /(?:^|\/)gpt-6-astra$/i.test(request.model.id)
 }

 const nativeImageToolInput = (tool: ToolDefinition) => {
@@ -163,19 +174,20 @@ const nativeImageTool = (tool: ToolDefinition) => {
  return Schema.is(OpenAIResponsesImageGenerationTool)(native) ? native : undefined
 }

-const lowerTool = Effect.fn("OpenAIResponses.lowerTool")(function* (tool: ToolDefinition) {
+const lowerTool = Effect.fn("OpenAIResponses.lowerTool")(function* (tool: ToolDefinition, inputSchema: JsonSchema) {
  const native = nativeImageToolInput(tool)
  if (native !== undefined) {
    if (Schema.is(OpenAIResponsesImageGenerationTool)(native)) return native
    return yield* ProviderShared.invalidRequest("OpenAI Responses image generation tool options are invalid")
  }
-  return yield* OpenResponses.lowerTool(NAME, tool)
+  return yield* OpenResponses.lowerTool(NAME, tool, inputSchema)
 })

 // Native namespaces hold only function tools, so deeper levels flatten into
 // the leaf names the same way non-native protocols flatten the whole tree.
-const lowerToolEntry = Effect.fn("OpenAIResponses.lowerToolEntry")(function* (tool: ToolEntry) {
-  if (tool.type === "tool") return yield* lowerTool(tool)
+const lowerToolEntry = Effect.fn("OpenAIResponses.lowerToolEntry")(function* (tool: ToolEntry, model: LanguageModel) {
+  if (tool.type === "tool")
+    return yield* lowerTool(tool, ToolSchemaProjection.modelCompatibility(tool.inputSchema, model))
  // OpenAI requires a namespace description; fall back to a generic one so a
  // missing description never blocks the request.
  return {
@@ -183,13 +195,11 @@ const lowerToolEntry = Effect.fn("OpenAIResponses.lowerToolEntry")(function* (to
    name: tool.name,
    description: tool.description ?? `Tools in the ${tool.name} namespace.`,
    tools: yield* Effect.forEach(ProviderShared.flattenTools(tool.tools), (leaf) =>
-      OpenResponses.lowerTool(NAME, leaf),
+      OpenResponses.lowerTool(NAME, leaf, ToolSchemaProjection.modelCompatibility(leaf.inputSchema, model)),
    ),
  }
 })

-const lowerTools = (request: LLMRequest) => Effect.forEach(request.tools, lowerToolEntry)
-
 const lowerToolChoice = (toolChoice: NonNullable<LLMRequest["toolChoice"]>, tools: ReadonlyArray<ToolEntry>) =>
  ProviderShared.matchToolChoice(NAME, toolChoice, {
    auto: () => "auto" as const,
@@ -213,7 +223,10 @@ const fromRequest = Effect.fn("OpenAIResponses.fromRequest")(function* (request:
    ...(yield* OpenResponses.lowerConversation(updates.request, adapter)),
    ...OpenResponses.lowerGeneration(request, { ...options, reasoningEffort: updates.effort }),
    context_management: management?.map((edit) => ({ type: edit.type, compact_threshold: edit.compactThreshold })),
-    tools: request.tools.length === 0 ? undefined : yield* lowerTools(request),
+    tools:
+      request.tools.length === 0
+        ? undefined
+        : yield* Effect.forEach(request.tools, (tool) => lowerToolEntry(tool, request.model)),
    tool_choice:
      request.tools.length === 0
        ? undefined
@@ -225,6 +238,7 @@ const fromRequest = Effect.fn("OpenAIResponses.fromRequest")(function* (request:
 const checkpointBody = {
  schema: CheckpointBody,
  from: Effect.fn("OpenAIResponses.checkpointBody")(function* (request: LLMRequest) {
+    const native = yield* fromRequest(LLMRequest.update(request, { toolChoice: undefined }))
    const overlay = request.http?.body
    // Complete history is required for stateless replay and SSE recovery. Raw input overrides bypass that contract.
    if (
@@ -235,13 +249,18 @@ const checkpointBody = {
      return yield* ProviderShared.invalidRequest(
        "Trigger compaction requires complete canonical history, not an input or continuation override",
      )
-    if (overlay?.stream !== undefined && overlay.stream !== true)
-      return yield* ProviderShared.invalidRequest("Trigger compaction requires a streamed response")
-    const native = yield* fromRequest(request)
-    return {
-      ...native,
-      input: [...native.input, { type: "compaction_trigger" as const }],
-    }
+    return yield* ProviderShared.validateWith(Schema.decodeUnknownEffect(CheckpointBody))({
+      ...mergeJsonRecords(native, overlay),
+      input: [...native.input, { type: "compaction_trigger" }],
+      stream: true,
+      store: false,
+      parallel_tool_calls: true,
+      tool_choice: undefined,
+      context_management: undefined,
+      text: undefined,
+      max_output_tokens: undefined,
+      max_tool_calls: undefined,
+    })
  }),
 }

@@ -323,10 +342,7 @@ export const transport = channelTransport({
 })

 export const route = Route.make({
-  compact: {
-    endpoint: ResponsesCompaction.make(adapter, lowerTools),
-    trigger: ResponsesCheckpoint.make(checkpointBody),
-  },
+  compact: { endpoint: ResponsesCompaction.make(adapter), trigger: ResponsesCheckpoint.make(checkpointBody) },
  id: ADAPTER,
  provider: "openai",
  providerMetadataKey: "openai",
@@ -61,9 +61,6 @@ interface State extends SpeechStream.Audio {
 const supportsSse = (model: string) => !/^tts-1(-hd)?(-|$)/.test(model)

 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`)
  return MediaProtocol.json(
    mergeJsonRecords(
      {
@@ -124,7 +121,7 @@ const finish = (state: State, context: MediaProtocol.ResponseContext<Request>) =
 // ---------------------------------------------------------------------------

 export const protocol = MediaProtocol.stream<Request, SpeechEvent, string | Uint8Array, State>(route, {
-  unsupported: ["language"],
+  unsupported: ["language", "timestamps"],
  body: { from: fromRequest },
  frames: (bytes, context) => (isSse(context.body) ? Framing.sse.frame(bytes) : bytes),
  initial: () => ({ chunks: [], done: false }),
@@ -1,9 +1,8 @@
 import { Effect, Schema, Stream } from "effect"
-import { classifyProviderFailure } from "../provider-error.js"
 import { Framing } from "../route/framing.js"
 import { MediaProtocol } from "../route/media-protocol.js"
 import { MediaRoute } from "../route/media.js"
-import { AIError, mergeJsonRecords, type MediaUsage } from "../schema/index.js"
+import { mergeJsonRecords, type MediaUsage } from "../schema/index.js"
 import {
  TranscriptionFinishEvent,
  TranscriptionModel,
@@ -60,9 +59,6 @@ const Usage = Schema.Union([
    input_tokens: Schema.optional(Schema.Number),
    output_tokens: Schema.optional(Schema.Number),
    total_tokens: Schema.optional(Schema.Number),
-    input_token_details: Schema.optional(
-      Schema.Struct({ audio_tokens: Schema.optional(Schema.Number), text_tokens: Schema.optional(Schema.Number) }),
-    ),
  }),
  Schema.Struct({ type: Schema.Literal("duration"), seconds: Schema.Number }),
 ])
@@ -79,23 +75,14 @@ const transcriptFields = {
  usage: Schema.optional(Usage),
 }

-/** OpenAI may add stream event types; frames outside `EVENT_TYPES` are ignored. */
-const EventType = Schema.Struct({ type: Schema.String })
 const Event = Schema.Union([
  Schema.Struct({ type: Schema.Literal("transcript.text.delta"), delta: Schema.String }),
  Schema.Struct({ type: Schema.Literal("transcript.text.segment"), ...Segment.fields }),
  Schema.Struct({ type: Schema.Literal("transcript.text.done"), ...transcriptFields }),
-  Schema.Struct({
-    type: Schema.Literal("error"),
-    message: Schema.optional(Schema.String),
-    error: Schema.optional(Schema.Struct({ message: Schema.optional(Schema.String) })),
-  }),
 ])
-const EVENT_TYPES = new Set(["transcript.text.delta", "transcript.text.segment", "transcript.text.done", "error"])
 const Transcript = Schema.Struct(transcriptFields)
 type Transcript = Schema.Schema.Type<typeof Transcript>

-const decodeEventType = route.decodeFrame(EventType)
 const decodeEvent = route.decodeFrame(Event)
 const decodeTranscript = route.decodeFrame(Transcript)

@@ -131,12 +118,10 @@ const capabilities = (model: string): Capabilities => {
  return TRANSCRIBE
 }

-/** whisper-1 ignores `stream`, so its `stream` mode sends a plain request and emits only `finish`. */
-const streamsEvents = (request: MediaProtocol.Addressed<Request>) =>
-  request.mode === "stream" && capabilities(request.model.id).stream
-
 const validate = (request: MediaProtocol.Addressed<Request>, model: Capabilities) => {
  const id = request.model.id
+  if (request.mode === "stream" && !model.stream)
+    return Effect.fail(route.unsupported("media.stream", `${id} does not stream; use Transcription.generate`))
  if (request.diarize === true && !model.diarize)
    return Effect.fail(route.unsupported("media.diarize", `${id} does not diarize; use gpt-4o-transcribe-diarize`))
  if (request.prompt !== undefined && model.diarize)
@@ -188,7 +173,7 @@ const fromRequest = Effect.fn("OpenAITranscription.fromRequest")(function* (requ
      timestamp_granularities: responseFormat === "verbose_json" ? [request.timestamps] : undefined,
      // Diarizing audio longer than 30 seconds requires a chunking strategy.
      chunking_strategy: model.diarize ? "auto" : undefined,
-      stream: streamsEvents(request) ? true : undefined,
+      stream: request.mode === "stream" ? true : undefined,
    },
    {
      overlay: mergeJsonRecords(request.providerOptions, request.http?.body),
@@ -211,15 +196,7 @@ const segment = (value: Schema.Schema.Type<typeof Segment>): TranscriptionSegmen
 })

 const onEvent = Effect.fn("OpenAITranscription.onEvent")(function* (state: State, frame: string) {
-  if (!EVENT_TYPES.has((yield* decodeEventType(frame)).type)) return [state, []] as const
  const event = yield* decodeEvent(frame)
-  if (event.type === "error")
-    return yield* new AIError({
-      reason: classifyProviderFailure({
-        message: `${route.name} stream failed: ${event.message ?? event.error?.message ?? "unknown error"}`,
-        rawBody: frame,
-      }),
-    })
  if (event.type === "transcript.text.done") return [{ ...state, transcript: event }, []] as const
  if (event.type === "transcript.text.delta")
    return [state, event.delta.length === 0 ? [] : [TranscriptionTextDeltaEvent.make({ delta: event.delta })]] as const
@@ -269,7 +246,7 @@ export const protocol = MediaProtocol.stream<Request, TranscriptionEvent, Frame,
  unsupported: ["speakers"],
  body: { from: fromRequest },
  frames: (bytes, context) =>
-    streamsEvents(context.request)
+    context.request.mode === "stream"
      ? Framing.sse.frame(bytes)
      : Framing.document.frame(bytes).pipe(Stream.map((document) => ({ document }))),
  initial: () => ({ segments: [] }),
@@ -132,7 +132,8 @@ const decodeResult = Effect.fn("ReplicateImages.decodeResult")(function* (
      status,
      `${route.name} prediction ${context.token.id} ${prediction.status}${typeof prediction.error === "string" ? `: ${prediction.error}` : ""}`,
    )
-  if (status !== "completed") return yield* output.pending(context.token.id)
+  if (status !== "completed")
+    return yield* output.invalid(`${route.name} prediction ${context.token.id} has not finished`)
  if (prediction.data_removed === true)
    return yield* output.ended("expired", `${route.name} removed the output of prediction ${context.token.id}`)
  if (!isOutput(prediction.output))
@@ -141,7 +141,8 @@ const decodeResult = Effect.fn("RunwayVideo.decodeResult")(function* (
  }
  if (status === "cancelled")
    return yield* output.ended("cancelled", `${route.name} task ${context.token.taskID} was cancelled`)
-  if (status !== "completed") return yield* output.pending(context.token.taskID)
+  if (status !== "completed")
+    return yield* output.invalid(`${route.name} task ${context.token.taskID} has not finished`)
  const urls = task.output ?? []
  if (urls.length === 0) return yield* output.invalid(`${route.name} task succeeded without any output`)
  return new VideoResponse({
@@ -170,7 +171,7 @@ export const protocol = MediaProtocol.queued<Request, VideoResponse, Token>(rout
  start: { body: { from: fromRequest }, decode: decodeStart },
  status: { path: taskPath, decode: decodeStatus },
  result: { path: taskPath, decode: decodeResult },
-  cancel: { method: "DELETE", path: taskPath, activeOnly: true },
+  cancel: { method: "DELETE", path: taskPath },
 })

 const startPath = (request: Request) => {
@@ -110,14 +110,6 @@ export const sumTokens = (...values: ReadonlyArray<number | undefined>): number
  return values.reduce((acc: number, value) => acc + (value ?? 0), 0)
 }

-/**
- * Caps an explicit thinking budget at half the output limit. Thinking counts against the output limit, so a budget
- * near it leaves the answer, a tool call, or a summary without room. Smaller budgets, special values such as `-1` and
- * `0`, and requests without an output limit pass through unchanged.
- */
-export const fitThinkingBudget = (budget: number, maxTokens: number | undefined, minimum = 1) =>
-  maxTokens === undefined || budget <= maxTokens / 2 ? budget : Math.max(minimum, Math.floor(maxTokens / 2))
-
 export const eventError = (route: string, message: string, body?: string, cause?: unknown) =>
  new AIError({
    reason: new InvalidProviderOutputError({ route, message, body, cause }),
@@ -175,7 +175,7 @@ const decodeUpscaleResult = Effect.fn("StabilityImages.decodeUpscaleResult")(fun
 ) {
  if (response.status === 202) {
    const output = yield* upscaleRoute.text(response)
-    return yield* output.pending(context.token.id)
+    return yield* output.invalid(`${upscaleRoute.name} upscale ${context.token.id} has not finished`)
  }
  return yield* decodeUpscaleImage(response)
 })
@@ -1,7 +1,7 @@
 import { Effect, Schema, Stream } from "effect"
 import { Route, type RouteBody, type TriggerCompactOperation } from "../../route/client.js"
 import { Protocol } from "../../route/protocol.js"
-import { CompactionCheckpointResponse, LLMEvent, LLMRequest } from "../../schema/index.js"
+import { CompactionCheckpointResponse, HttpOptions, LLMEvent, LLMRequest } from "../../schema/index.js"
 import { OpenResponses } from "../open-responses.js"
 import { ProviderShared } from "../shared.js"

@@ -109,8 +109,12 @@ export const make = <Body>(body: RouteBody<Body>): TriggerCompactOperation =>
      transport: source.transport,
    })
    const native = yield* body.from(request)
-    const prepared = yield* route.prepareTransport(native, request, options)
-    yield* route.streamPrepared(prepared, request, { http: executor }, options).pipe(Stream.runDrain)
+    // The body builder already applied and validated overlays. Do not let transport reapply them.
+    const preparedRequest = LLMRequest.update(request, {
+      http: request.http === undefined ? undefined : new HttpOptions({ ...request.http, body: undefined }),
+    })
+    const prepared = yield* route.prepareTransport(native, preparedRequest, options)
+    yield* route.streamPrepared(prepared, preparedRequest, { http: executor }, options).pipe(Stream.runDrain)
    if (!result) return yield* ProviderShared.eventError(source.id, "Compaction response ended without a checkpoint")
    return result
  })
@@ -19,18 +19,12 @@ import { OpenResponses } from "../open-responses.js"
 import { JsonObject, optionalNull, ProviderShared } from "../shared.js"
 import { Media } from "../../media.js"

-// /compact has a smaller wire contract than /responses; keep the request controls it accepts.
 const Body = Schema.Struct({
  model: Schema.String,
  input: Schema.Array(Schema.Unknown),
  instructions: optionalNull(Schema.String),
  previous_response_id: optionalNull(Schema.String),
  service_tier: optionalNull(Schema.String),
-  reasoning: Schema.optional(JsonObject),
-  text: Schema.optional(JsonObject),
-  include: OpenResponses.coreFields.include,
-  parallel_tool_calls: OpenResponses.coreFields.parallel_tool_calls,
-  tools: Schema.optional(Schema.Array(JsonObject)),
  prompt_cache_key: optionalNull(Schema.String),
  prompt_cache_retention: optionalNull(Schema.String),
  prompt_cache_options: optionalNull(
@@ -80,27 +74,17 @@ const Response = Schema.Struct({
  usage: Schema.optional(Schema.StructWithRest(OpenResponses.OpenResponsesUsage, [JsonObject])),
 })

-export const make = (
-  adapter: OpenResponses.ProviderAdapter,
-  lowerTools: (request: LLMRequest) => Effect.Effect<ReadonlyArray<Record<string, unknown>>, AIError>,
-): CompactOperation =>
+export const make = (adapter: OpenResponses.ProviderAdapter): CompactOperation =>
  Effect.fn("ResponsesCompaction.execute")(function* (request, executor, options) {
    const route = request.model.route
    // The standalone compaction endpoint rejects histories containing configuration updates.
    const native = yield* OpenResponses.lowerConversation(stripEffortUpdates(request), adapter)
-    const generation = OpenResponses.lowerGeneration(request)
-    const tools = request.tools.length === 0 ? undefined : yield* lowerTools(request)
    const body = yield* ProviderShared.validateWith(Schema.decodeUnknownEffect(Body))(
      mergeJsonRecords(
        {
          ...native,
-          service_tier: generation.service_tier,
-          reasoning: generation.reasoning,
-          text: generation.text,
-          include: generation.include,
-          parallel_tool_calls: generation.parallel_tool_calls,
-          tools,
-          prompt_cache_key: generation.prompt_cache_key,
+          service_tier: request.providerOptions?.serviceTier,
+          prompt_cache_key: ProviderShared.promptCacheKey(request),
        },
        request.http?.body,
      ),
@@ -1,4 +1,4 @@
-import { ToolDefinition, type JsonSchema, type LanguageModel, type LLMRequest } from "../../schema/index.js"
+import type { JsonSchema, LanguageModel, LanguageModelSanitizerCompatibility } from "../../schema/index.js"
 import { isRecord } from "../../utils/record.js"
 import { GeminiJsonSchema } from "./gemini-json-schema.js"

@@ -70,13 +70,13 @@ const objectRoot = (schema: JsonSchema): JsonSchema => {
 // Otherwise the protocol's own default applies (the Gemini API always uses Gemini's rules), then the
 // model name selects the family's rules so models reached through gateways and OpenAI-compatible
 // endpoints get the same handling.
-const modelCompatibility = (schema: JsonSchema, model: LanguageModel): JsonSchema => {
+const modelCompatibility = (
+  schema: JsonSchema,
+  model: LanguageModel,
+  protocolDefault?: LanguageModelSanitizerCompatibility,
+): JsonSchema => {
  const root = objectRoot(schema)
-  switch (
-    model.compatibility?.sanitizer ??
-    model.route.sanitizer ??
-    MODEL_NAMES.find(([name]) => name.test(model.id))?.[1]
-  ) {
+  switch (model.compatibility?.sanitizer ?? protocolDefault ?? MODEL_NAMES.find(([name]) => name.test(model.id))?.[1]) {
    case "gemini":
      return gemini(root)
    case "moonshot":
@@ -87,18 +87,10 @@ const modelCompatibility = (schema: JsonSchema, model: LanguageModel): JsonSchem
  }
 }

-// Applied once to every request before any protocol builds its body, including tools in namespaces.
-const tools = (entries: LLMRequest["tools"], model: LanguageModel): LLMRequest["tools"] =>
-  entries.map((tool) =>
-    tool.type === "tool"
-      ? new ToolDefinition({ ...tool, inputSchema: modelCompatibility(tool.inputSchema, model) })
-      : { ...tool, tools: tools(tool.tools, model) },
-  )
-
 export const ToolSchemaProjection = {
  gemini,
+  modelCompatibility,
  moonshot,
  openAI,
  responses,
-  tools,
 } as const
@@ -101,8 +101,7 @@ const decodeResponse = Effect.fn("XAIImages.decodeResponse")(function* (
  )
  if (images.length === 0) return yield* output.invalid(`${route.name} returned no images`)
  const usage = ProviderShared.isRecord(decoded.usage) ? decoded.usage : undefined
-  // xAI reports a USD cost (`cost_in_usd_ticks`) rather than tokens, seconds, or credits; the raw record stays in
-  // provider metadata.
+  // xAI reports image counts rather than tokens, seconds, or credits; the raw record stays in provider metadata.
  return new ImageResponse({
    images,
    providerMetadata: usage === undefined ? undefined : { xai: { usage } },
@@ -50,8 +50,7 @@ const fromRequest = Effect.fn("XAIResponses.fromRequest")(function* (request: LL
      operation: "in-band-compaction",
      provider: request.model.provider,
      route: request.model.route.id,
-      message:
-        "xAI requires explicit compaction through LLMClient.compact; automatic context management is not supported",
+      message: "xAI requires explicit compaction through LLMClient.compact; automatic context management is not supported",
    })
  return yield* decodeBody(yield* OpenResponses.fromRequestWithAdapter(request, adapter))
 })
@@ -94,8 +93,6 @@ export const protocol = Protocol.make({
  },
 })

-export const compact = ResponsesCompaction.make(adapter, (request) =>
-  OpenResponses.lowerTools(ProviderShared.flattenTools(request.tools), adapter),
-)
+export const compact = ResponsesCompaction.make(adapter)

 export * as XAIResponses from "./xai-responses.js"
@@ -136,7 +136,8 @@ const decodeResult = Effect.fn("XAIVideo.decodeResult")(function* (
  const output = yield* decodeVideoStatus(response)
  const decoded = output.value
  const status = yield* MediaProtocol.status(STATUS, decoded.status, output)
-  if (status === "running") return yield* output.pending(context.token.requestID)
+  if (status === "running")
+    return yield* output.invalid(`${route.name} request ${context.token.requestID} has not finished`)
  if (status === "failed") {
    const code = decoded.error?.code ?? undefined
    const message = decoded.error?.message ?? undefined
@@ -1,6 +1,7 @@
-import { Duration, Effect, Schema } from "effect"
+import { Effect, Schema } from "effect"
 import type { HttpClientResponse } from "effect/unstable/http"
 import { ImageModel, ImageResponse, type ImageRequestFor } from "../image.js"
+import { Media } from "../media.js"
 import { MediaProtocol } from "../route/media-protocol.js"
 import { MediaRoute } from "../route/media.js"
 import { mergeJsonRecords, type OpenString } from "../schema/index.js"
@@ -8,7 +9,6 @@ import { mergeJsonRecords, type OpenString } from "../schema/index.js"
 const route = MediaProtocol.identity({ id: "zai-images", name: "Z.ai Images", provider: "zai" })
 export const DEFAULT_BASE_URL = "https://api.z.ai/api/paas/v4"
 export const PATH = "/images/generations"
-const OUTPUT_RETENTION = Duration.days(30)

 // ---------------------------------------------------------------------------
 // 1. Public model input
@@ -76,7 +76,7 @@ const decodeResponse = Effect.fn("ZAIImages.decodeResponse")(function* (
  const filters = decoded.content_filter ?? []
  return new ImageResponse({
    // Z.ai returns only URLs and no content type; the media type resolves when the asset is materialized.
-    images: yield* Effect.forEach(decoded.data, (item) => MediaProtocol.expiringUrl(item.url, OUTPUT_RETENTION)),
+    images: decoded.data.map((item) => Media.url(item.url)),
    // Z.ai reports applied content filters alongside a successful result; surface them instead of dropping them.
    notices:
      filters.length === 0
@@ -80,13 +80,7 @@ const SERVER_CODES = new Set([
  "slow_down",
  "serviceunavailableexception",
 ])
-// `invalid_request` is the Vercel AI Gateway's code for an upstream request rejection.
-const INVALID_REQUEST_CODES = new Set([
-  "invalid_prompt",
-  "invalid_request",
-  "invalid_request_error",
-  "validationexception",
-])
+const INVALID_REQUEST_CODES = new Set(["invalid_prompt", "invalid_request_error", "validationexception"])
 // Azure OpenAI reports `content_filter` with `innererror.code` ResponsibleAIPolicyViolation.
 // OpenRouter tags provider failures with a typed `error_type`; its Responses skin also
 // emits `image_content_policy_violation` as the native code.
@@ -31,7 +31,6 @@ export interface Settings extends ProviderPackage.Settings {
  readonly profile?: string
  readonly region?: string
  readonly topP?: number
-  readonly thinking?: BedrockConverse.OptionsInput["thinking"]
 }
 export const routes = [BedrockConverse.route]

@@ -72,7 +71,6 @@ export const model: ProviderPackage.Definition<Settings>["model"] = (modelID, se
    generation: settings.topP === undefined ? undefined : { topP: settings.topP },
    headers: settings.headers === undefined ? undefined : { ...settings.headers },
    http: settings.body === undefined ? undefined : { body: { ...settings.body } },
-    providerOptions: settings.thinking === undefined ? undefined : { thinking: settings.thinking },
    profile: settings.profile,
    region: settings.region,
  }).model(modelID)
@@ -32,7 +32,10 @@ const openAIProviderOptions = (options: OpenAIOptionsInput | undefined): Provide
  return result
 }

-export const gpt5DefaultOptions = (modelID: string): ProviderOptions | undefined => {
+export const gpt5DefaultOptions = (
+  modelID: string,
+  options: { readonly textVerbosity?: boolean } = {},
+): ProviderOptions | undefined => {
  const id = modelID.toLowerCase()
  if (!id.includes("gpt-5") || id.includes("gpt-5-chat") || id.includes("gpt-5-pro")) return undefined
  return openAIProviderOptions({
@@ -44,19 +47,27 @@ export const gpt5DefaultOptions = (modelID: string): ProviderOptions | undefined
    // this, callers using the default model facade get reasoning summaries
    // they cannot replay statelessly.
    include: ["reasoning.encrypted_content"],
+    textVerbosity:
+      options.textVerbosity === true && id.includes("gpt-5.") && !id.includes("codex") && !id.includes("-chat")
+        ? "low"
+        : undefined,
  })
 }

-export const openAIDefaultOptions = (modelID: string): ProviderOptions | undefined =>
-  mergeProviderOptions(openAIProviderOptions({ store: false }), gpt5DefaultOptions(modelID))
+export const openAIDefaultOptions = (
+  modelID: string,
+  options: { readonly textVerbosity?: boolean } = {},
+): ProviderOptions | undefined =>
+  mergeProviderOptions(openAIProviderOptions({ store: false }), gpt5DefaultOptions(modelID, options))

 export const withOpenAIOptions = <Options extends { readonly providerOptions?: OpenAIProviderOptionsInput }>(
  modelID: string,
  options: Options,
+  defaults: { readonly textVerbosity?: boolean } = {},
 ): Omit<Options, "providerOptions"> & { readonly providerOptions?: ProviderOptions } => {
  return {
    ...options,
-    providerOptions: mergeProviderOptions(openAIDefaultOptions(modelID), options.providerOptions),
+    providerOptions: mergeProviderOptions(openAIDefaultOptions(modelID, defaults), options.providerOptions),
  }
 }

@@ -100,7 +100,7 @@ export const configure = (input: Config = {}) => {
  const modelDefaults = defaults(input)
  const responses = (id: string | ModelID) =>
    responsesRoute
-      .with(withOpenAIOptions(id, modelDefaults))
+      .with(withOpenAIOptions(id, modelDefaults, { textVerbosity: true }))
      .model<OpenAIProviderOptionsInput>({ id })
  const chat = (id: string | ModelID) =>
    chatRoute.with(withOpenAIOptions(id, modelDefaults)).model<OpenAIProviderOptionsInput>({
@@ -8,7 +8,7 @@ import type { ProviderPackage } from "../provider-package.js"
 import { SystemOne } from "../experimental/system-one.js"
 import { OpenAIChat } from "../protocols/openai-chat.js"
 import { newBreakpoints, ttlBucket } from "../protocols/utils/cache.js"
-import { isRecord, ProviderShared } from "../protocols/shared.js"
+import { isRecord } from "../protocols/shared.js"

 export const id = ProviderID.make("openrouter")
 const baseURL = "https://openrouter.ai/api/v1"
@@ -123,7 +123,7 @@ export const protocol = Protocol.make({
          return {
            ...body,
            messages,
-            ...bodyOptions(request.providerOptions, request.generation?.maxTokens),
+            ...bodyOptions(request.providerOptions),
          } as OpenRouterBody
        }),
      ),
@@ -143,14 +143,7 @@ const cacheControl = () => {
  }
 }

-// OpenRouter forwards `reasoning.max_tokens` as the upstream thinking budget. Upstreams such as Anthropic and Alibaba
-// reject one that is not below the output limit; 1,024 is Anthropic's minimum budget.
-const fitReasoning = (reasoning: Record<string, unknown>, maxTokens: number | undefined) =>
-  typeof reasoning.max_tokens === "number"
-    ? { ...reasoning, max_tokens: ProviderShared.fitThinkingBudget(reasoning.max_tokens, maxTokens, 1_024) }
-    : reasoning
-
-const bodyOptions = (input: unknown, maxTokens: number | undefined) => {
+const bodyOptions = (input: unknown) => {
  const openrouter = isRecord(input) ? input : {}
  const { usage, models, provider, plugins, web_search_options, debug, user, reasoning, promptCacheKey, ...options } =
    openrouter
@@ -169,7 +162,7 @@ const bodyOptions = (input: unknown, maxTokens: number | undefined) => {
    ...(isRecord(web_search_options) ? { web_search_options } : {}),
    ...(isRecord(debug) ? { debug } : {}),
    ...(typeof user === "string" ? { user } : {}),
-    ...(isRecord(reasoning) ? { reasoning: fitReasoning(reasoning, maxTokens) } : {}),
+    ...(isRecord(reasoning) ? { reasoning } : {}),
  }
 }

@@ -11,8 +11,7 @@ import { applyEffortUpdates } from "../effort-updates.js"
 import { normalizeToolHistory } from "../tool-history.js"
 import { sanitizeSurrogates } from "../utils/sanitize.js"
 import * as ProviderShared from "../protocols/shared.js"
-import { ToolSchemaProjection } from "../protocols/utils/tool-schema.js"
-import type { LanguageModelSanitizerCompatibility, ProtocolID, ProviderOptions } from "../schema/index.js"
+import type { ProtocolID, ProviderOptions } from "../schema/index.js"
 import {
  AIError,
  CompactionResponse,
@@ -58,7 +57,6 @@ export interface Route<
  readonly defaults: RouteDefaults
  readonly body: RouteBody<Body>
  readonly supportsEffortUpdates?: (request: LLMRequest) => boolean
-  readonly sanitizer?: LanguageModelSanitizerCompatibility
  readonly with: {
    <Next extends CompactionOperations | undefined>(
      patch: RoutePatch<Body, Prepared> & { readonly compact: Next },
@@ -390,7 +388,6 @@ function makeFromTransport<Body, Prepared, Frame, Event, State>(
      defaults: routeInput.defaults ?? {},
      body: protocol.body,
      supportsEffortUpdates: protocol.supportsEffortUpdates,
-      sanitizer: protocol.sanitizer,
      with: (patch: RoutePatch<Body, Prepared>) => {
        const { compact, id, provider, providerMetadataKey, auth, transport, endpoint, ...defaults } = patch
        return build({
@@ -562,9 +559,7 @@ const prepareRequest = (request: LLMRequest) => {
      tool.type === "tool" ? tool : { ...tool, tools: dedupe(tool.tools) },
    )
  const resolved = applyCachePolicy(
-    applyEffortUpdates(
-      LLMRequest.update(sanitized, { tools: ToolSchemaProjection.tools(dedupe(sanitized.tools), sanitized.model) }),
-    ),
+    applyEffortUpdates(LLMRequest.update(sanitized, { tools: dedupe(sanitized.tools) })),
  )
  const headers = resolved.model.route.headers?.({ request: resolved })
  return headers === undefined
@@ -137,11 +137,6 @@ export interface Queued<Request, Response, Token> {
  readonly cancel?: {
    readonly method: AuthInput["method"]
    readonly path: (token: Token) => string
-    /**
-     * Fetch a fresh status first and skip the call for terminal generations, for providers whose cancel endpoint
-     * destroys finished work (Runway's `DELETE /v1/tasks/{id}` deletes completed tasks and their outputs).
-     */
-    readonly activeOnly?: boolean
  }
 }

@@ -200,8 +195,7 @@ 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.
+   * provider-side, `cancelled`/`expired` mean the result will never exist); `contentPolicy` is a moderated result.
   */
  const text = Effect.fn("MediaProtocol.text")(function* (response: HttpClientResponse.HttpClientResponse) {
    const http = context(response)
@@ -230,14 +224,6 @@ export const identity = (input: { readonly id: string; readonly name: string; re
              ? new ProviderInternalError({ message, body, http })
              : new InvalidRequestError({ message, body, http }),
        }),
-      pending: (id: string) =>
-        new AIError({
-          reason: new InvalidRequestError({
-            message: `${input.name} generation ${id} has not finished; await it before reading the result`,
-            body,
-            http,
-          }),
-        }),
      contentPolicy: (message: string) => new AIError({ reason: new ContentPolicyError({ message, body, http }) }),
    }
  })
@@ -299,8 +285,9 @@ export const status = <Table extends Record<string, Status>>(
  raw: string,
  output: Output,
 ): Effect.Effect<Status, AIError> => {
-  if (!Object.hasOwn(table, raw)) return Effect.fail(output.invalid(`Unknown generation status "${raw}"`))
-  return Effect.succeed(table[raw])
+  const normalized: Status | undefined = table[raw]
+  if (normalized === undefined) return Effect.fail(output.invalid(`Unknown generation status "${raw}"`))
+  return Effect.succeed(normalized)
 }

 /** A `url` asset whose provider-declared retention window starts now. */
@@ -5,7 +5,7 @@ import { Endpoint } from "./endpoint.js"
 import { RequestExecutorService, type Interface } from "./executor-service.js"
 import { RequestExecutor } from "./executor.js"
 import { MediaProtocol } from "./media-protocol.js"
-import { Generation, isTerminal } from "../generation.js"
+import { Generation, resultEvents, type AwaitOptions, type Observation } from "../generation.js"
 import type { Media } from "../media.js"
 import {
  AIError,
@@ -52,7 +52,7 @@ export const deployment = (
 // ---------------------------------------------------------------------------

 /** One request, one response. */
-export interface InlineRoute<Request extends MediaRequest, Response> {
+export interface Route<Request extends MediaRequest, Response> {
  readonly kind: "inline"
  readonly id: string
  readonly provider: ProviderID
@@ -86,7 +86,7 @@ export interface StreamRoute<Request extends MediaRequest, Event, Response> {
 }

 export type AnyRoute<Request extends MediaRequest, Event, Response> =
-  | InlineRoute<Request, Response>
+  | Route<Request, Response>
  | StreamRoute<Request, Event, Response>
  | QueuedRoute<Request, Response>

@@ -119,7 +119,7 @@ export interface StreamInput<Request extends MediaRequest, Event, Response, Fram
 */
 export const inline = <Request extends MediaRequest, Response>(
  input: InlineInput<Request, Response>,
-): InlineRoute<Request, Response> => {
+): Route<Request, Response> => {
  const transport = makeTransport(input)
  return {
    kind: "inline",
@@ -164,19 +164,14 @@ export const queued = <Request extends MediaRequest, Response, Token>(
      transport
        .call("GET", operation.path(token), http, execute)
        .pipe(Effect.flatMap((sent) => operation.decode(sent.response, { token, auth: sent.auth, materialize })))
-    const status = poll(protocol.status)
    const cancel = protocol.cancel
-    const send =
-      cancel === undefined
-        ? undefined
-        : transport.call(cancel.method, cancel.path(token), http, execute).pipe(Effect.asVoid)
    return {
-      status,
+      status: poll(protocol.status),
      result: poll(protocol.result),
      cancel:
-        send !== undefined && cancel?.activeOnly
-          ? status.pipe(Effect.flatMap((snapshot) => (isTerminal(snapshot.status) ? Effect.void : send)))
-          : send,
+        cancel === undefined
+          ? undefined
+          : transport.call(cancel.method, cancel.path(token), http, execute).pipe(Effect.asVoid),
    }
  }

@@ -272,6 +267,59 @@ export const stream = <Request extends MediaRequest, Event, Response, Frame, Sta
  }
 }

+export const dispatch = <Event, Response>(input: {
+  readonly modality: string
+  readonly execute: Execute
+  readonly responseEvents: (response: Response) => ReadonlyArray<Event>
+}) => {
+  const notQueued = (route: { readonly provider: ProviderID; readonly id: string }, operation: string) =>
+    new AIError({
+      reason: new UnsupportedOperationError({
+        operation: `${input.modality}.${operation}`,
+        provider: route.provider,
+        route: route.id,
+        message: `${route.provider}/${route.id} is not a queued route; use generate or stream`,
+      }),
+    })
+  const start = <Request extends MediaRequest>(route: AnyRoute<Request, Event, Response>, request: Request) => {
+    if (route.kind !== "queued") return Effect.fail(notQueued(route, "start"))
+    return route.start(request, input.execute)
+  }
+  return {
+    start,
+    resume: <Request extends MediaRequest>(
+      route: AnyRoute<Request, Event, Response>,
+      model: MediaRequest["model"],
+      token: unknown,
+    ) => {
+      if (route.kind !== "queued") return Effect.fail(notQueued(route, "resume"))
+      return route.resume(model, token, input.execute)
+    },
+    generate: <Request extends MediaRequest>(
+      route: AnyRoute<Request, Event, Response>,
+      request: Request,
+      options?: AwaitOptions,
+    ) => {
+      if (route.kind !== "queued") return route.generate(request, input.execute)
+      return start(route, request).pipe(Effect.flatMap((generation) => generation.await(options)))
+    },
+    stream: <Request extends MediaRequest>(
+      route: AnyRoute<Request, Event, Response>,
+      request: Request,
+      options?: AwaitOptions,
+    ): Stream.Stream<Event | Observation, AIError> => {
+      if (route.kind === "stream") return route.stream(request, input.execute)
+      if (route.kind === "queued")
+        return Stream.unwrap(
+          start(route, request).pipe(
+            Effect.map((generation) => resultEvents(generation, input.responseEvents, options)),
+          ),
+        )
+      return Stream.fromIterableEffect(Effect.map(route.generate(request, input.execute), input.responseEvents))
+    },
+  }
+}
+
 // ---------------------------------------------------------------------------
 // Transport plumbing shared by every kind
 // ---------------------------------------------------------------------------
@@ -385,11 +433,7 @@ const encode = (body: MediaProtocol.Body | undefined, headers: Headers.Headers)
  }
 }

-/**
- * Common fields are never silently dropped: a present field the protocol declared unsupported fails typed. `false`
- * counts as present because some booleans mean something when false (video `audio`); protocols reject opt-in
- * booleans such as speech `timestamps` with `=== true` in `body.from` instead of listing them.
- */
+/** Common fields are never silently dropped: a present field the protocol declared unsupported fails typed. */
 const rejectUnsupported = <Request extends object>(
  route: string,
  provider: ProviderID,
@@ -1,5 +1,5 @@
 import { Schema, type Effect } from "effect"
-import type { AIError, LanguageModelSanitizerCompatibility, LLMEvent, LLMRequest, ProtocolID } from "../schema/index.js"
+import type { AIError, LLMEvent, LLMRequest, ProtocolID } from "../schema/index.js"

 /**
 * The semantic API contract of one model server family.
@@ -43,8 +43,6 @@ export interface Protocol<Body, Frame, Event, State> {
  readonly stream: ProtocolStream<Frame, Event, State>
  /** Whether `body.from` lowers `Message.effort(...)` markers; wrappers around another `body.from` must forward it. */
  readonly supportsEffortUpdates?: (request: LLMRequest) => boolean
-  /** Tool schema sanitizer for every model on this protocol unless the model's compatibility sets one; wrappers around another `body.from` must forward it. */
-  readonly sanitizer?: LanguageModelSanitizerCompatibility
 }

 export interface ProtocolBody<Body> {
@@ -1,31 +1,53 @@
-import { Context } from "effect"
-import { MediaClient } from "./media-client.js"
-import {
-  SpeechTimestampsEvent,
-  SpeechFinishEvent,
-  type SpeechEvent,
-  type SpeechRequestFor,
-  type SpeechResponse,
-} from "./speech.js"
+import { Context, Effect, Layer, Stream } from "effect"
+import { RequestExecutor } from "./route/executor.js"
+import type { AIError } from "./schema/index.js"
+import type { SpeechEvent, SpeechOptions, SpeechRequestFor, SpeechResponse } from "./speech.js"

-export type Interface = MediaClient.Interface<SpeechRequestFor, SpeechEvent, SpeechResponse>
+export interface Interface {
+  readonly generate: <Options extends SpeechOptions>(
+    request: SpeechRequestFor<Options>,
+  ) => Effect.Effect<SpeechResponse, AIError>
+  readonly stream: <Options extends SpeechOptions>(
+    request: SpeechRequestFor<Options>,
+  ) => Stream.Stream<SpeechEvent, AIError>
+}

 export class SpeechClientService extends Context.Service<SpeechClientService, Interface>()("@opencode/SpeechClient") {}
 export const Service = SpeechClientService
 export type Service = SpeechClientService

+export const generate = <Options extends SpeechOptions>(
+  request: SpeechRequestFor<Options>,
+): Effect.Effect<SpeechResponse, AIError, Service> =>
+  Effect.gen(function* () {
+    const client = yield* Service
+    return yield* client.generate(request)
+  })
+
+export const stream = <Options extends SpeechOptions>(
+  request: SpeechRequestFor<Options>,
+): Stream.Stream<SpeechEvent, AIError, Service> =>
+  Stream.unwrap(
+    Effect.gen(function* () {
+      const client = yield* Service
+      return client.stream(request)
+    }),
+  )
+
+export const layer: Layer.Layer<Service, never, RequestExecutor.Service> = Layer.effect(
+  Service,
+  Effect.gen(function* () {
+    const executor = yield* RequestExecutor.Service
+    return Service.of({
+      generate: (request) => request.model.route.generate(request, executor.execute),
+      stream: (request) => request.model.route.stream(request, executor.execute),
+    })
+  }),
+)
+
 export const SpeechClient = {
  Service,
-  ...MediaClient.make(Service, {
-    modality: "speech",
-    responseEvents: (response: SpeechResponse) => [
-      ...(response.timestamps === undefined ? [] : [SpeechTimestampsEvent.make({ items: response.timestamps })]),
-      SpeechFinishEvent.make({
-        audio: response.audio,
-        usage: response.usage,
-        notices: response.notices,
-        providerMetadata: response.providerMetadata,
-      }),
-    ],
-  }),
+  layer,
+  generate,
+  stream,
 } as const
@@ -1,8 +1,8 @@
 import { Effect, Schema, Stream } from "effect"
-import { ProgressEvent, QueuedEvent } from "./generation.js"
 import { Media } from "./media.js"
 import { MediaModel, composeRoute, tryRequest } from "./media-model.js"
 import { MediaRoute } from "./route/media.js"
+import type { MediaProtocol } from "./route/media-protocol.js"
 import { AIError, HttpOptions, MediaUsage, ProviderMetadata, type OpenString } from "./schema/index.js"
 import { SpeechClient, Service } from "./speech-client.js"

@@ -10,39 +10,53 @@ import { SpeechClient, Service } from "./speech-client.js"
 // Model
 // ---------------------------------------------------------------------------

-export type SpeechOptions = MediaModel.Options
+export type SpeechOptions = Record<string, unknown>

-export type SpeechRoute = MediaRoute.AnyRoute<SpeechRequestFor, SpeechEvent, SpeechResponse>
+export type SpeechRoute<Options extends SpeechOptions = SpeechOptions> = MediaRoute.StreamRoute<
+  SpeechRequestFor<Options>,
+  SpeechEvent,
+  SpeechResponse
+>

-export class SpeechModel<Options extends SpeechOptions = SpeechOptions> extends MediaModel<SpeechRoute, Options> {
+export class SpeechModel<Options extends SpeechOptions = SpeechOptions> extends MediaModel<
+  SpeechRoute<Options>,
+  Options
+> {
  declare protected readonly _SpeechModel: void

-  /** The number of type arguments selects the kind: `<Options>`, `<Options, Frame, State>`, or `<Options, Token>`. */
-  static fromRoute<Options extends SpeechOptions>(
-    route: MediaModel.InlineRouteInput<SpeechRequestFor<Options>, SpeechResponse>,
-    input: MediaRoute.ModelInput,
-  ): SpeechModel<Options>
-  static fromRoute<Options extends SpeechOptions, Frame, State>(
-    route: MediaModel.StreamRouteInput<SpeechRequestFor<Options>, SpeechEvent, Frame, State>,
-    input: MediaRoute.ModelInput,
-  ): SpeechModel<Options>
-  static fromRoute<Options extends SpeechOptions, Token>(
-    route: MediaModel.QueuedRouteInput<SpeechRequestFor<Options>, SpeechResponse, Token>,
-    input: MediaRoute.ModelInput,
-  ): SpeechModel<Options>
-  static fromRoute<Options extends SpeechOptions, Frame, State, Token>(
-    route: MediaModel.AnyRouteInput<SpeechRequestFor<Options>, SpeechEvent, SpeechResponse, Frame, State, Token>,
+  static make<Options extends SpeechOptions = SpeechOptions>(input: MediaModel.Input<SpeechRoute<Options>>) {
+    return new SpeechModel<Options>(input)
+  }
+
+  /** Compose a streaming speech protocol with its canonical path into a model for one deployment. */
+  static fromRoute<Options extends SpeechOptions = SpeechOptions, Frame = unknown, State = unknown>(
+    route: SpeechModel.RouteInput<Options, Frame, State>,
    input: MediaRoute.ModelInput,
  ) {
    return new SpeechModel<Options>({
      id: input.id,
      provider: route.protocol.provider,
      http: input.http,
-      route: composeRoute(route, input, collectResponse) as SpeechRoute,
+      route: composeRoute(
+        (composition) => MediaRoute.stream({ ...composition, collect: collectResponse }),
+        route,
+        input,
+      ),
    })
  }
 }

+export namespace SpeechModel {
+  export type RouteInput<
+    Options extends SpeechOptions = SpeechOptions,
+    Frame = unknown,
+    State = unknown,
+  > = MediaModel.RouteInput<
+    MediaProtocol.Addressed<SpeechRequestFor<Options>>,
+    MediaProtocol.Streamed<SpeechRequestFor<Options>, SpeechEvent, Frame, State>
+  >
+}
+
 export const SpeechModelSchema = Schema.declare((value): value is SpeechModel => value instanceof SpeechModel, {
  expected: "Speech.Model",
 })
@@ -134,17 +148,11 @@ export const SpeechFinishEvent = Schema.Struct({
  providerMetadata: Schema.optional(ProviderMetadata),
 }).annotate({ identifier: "Speech.Event.Finish" })

-const speechEventTagged = Schema.Union([
-  QueuedEvent,
-  ProgressEvent,
-  SpeechAudioDeltaEvent,
-  SpeechTimestampsEvent,
-  SpeechFinishEvent,
-]).pipe(Schema.toTaggedUnion("type"))
+const speechEventTagged = Schema.Union([SpeechAudioDeltaEvent, SpeechTimestampsEvent, SpeechFinishEvent]).pipe(
+  Schema.toTaggedUnion("type"),
+)
 export const SpeechEvent = Object.assign(speechEventTagged, {
  is: {
-    generationQueued: speechEventTagged.guards["generation-queued"],
-    generationProgress: speechEventTagged.guards["generation-progress"],
    audioDelta: speechEventTagged.guards["audio-delta"],
    timestamps: speechEventTagged.guards.timestamps,
    finish: speechEventTagged.guards.finish,
@@ -187,15 +195,17 @@ export function request(input: SpeechRequest | SpeechRequestInput) {
 const requestEffect = (input: SpeechRequest | SpeechRequestInput) => tryRequest(() => request(input))

 export function generate<const Model extends SpeechModel>(
-  input: SpeechRequest | SpeechRequestInput<Model>,
+  input: SpeechRequestInput<Model>,
 ): Effect.Effect<SpeechResponse, AIError, Service>
+export function generate(input: SpeechRequest): Effect.Effect<SpeechResponse, AIError, Service>
 export function generate(input: SpeechRequest | SpeechRequestInput) {
  return requestEffect(input).pipe(Effect.flatMap((request) => SpeechClient.generate(request)))
 }

 export function stream<const Model extends SpeechModel>(
-  input: SpeechRequest | SpeechRequestInput<Model>,
+  input: SpeechRequestInput<Model>,
 ): Stream.Stream<SpeechEvent, AIError, Service>
+export function stream(input: SpeechRequest): Stream.Stream<SpeechEvent, AIError, Service>
 export function stream(input: SpeechRequest | SpeechRequestInput) {
  return Stream.unwrap(requestEffect(input).pipe(Effect.map((request) => SpeechClient.stream(request))))
 }
@@ -1,13 +1,34 @@
-import { Context } from "effect"
-import { MediaClient } from "./media-client.js"
+import { Context, Effect, Layer, Stream } from "effect"
+import type { AwaitOptions, Generation } from "./generation.js"
+import { RequestExecutor } from "./route/executor.js"
+import { MediaRoute } from "./route/media.js"
+import type { AIError } from "./schema/index.js"
 import {
-  TranscriptionFinishEvent,
+  responseEvents,
  type TranscriptionEvent,
+  type TranscriptionModel,
+  type TranscriptionOptions,
  type TranscriptionRequestFor,
  type TranscriptionResponse,
 } from "./transcription.js"

-export type Interface = MediaClient.Interface<TranscriptionRequestFor, TranscriptionEvent, TranscriptionResponse>
+export interface Interface {
+  readonly generate: <Options extends TranscriptionOptions>(
+    request: TranscriptionRequestFor<Options>,
+    options?: AwaitOptions,
+  ) => Effect.Effect<TranscriptionResponse, AIError>
+  readonly stream: <Options extends TranscriptionOptions>(
+    request: TranscriptionRequestFor<Options>,
+    options?: AwaitOptions,
+  ) => Stream.Stream<TranscriptionEvent, AIError>
+  readonly start: <Options extends TranscriptionOptions>(
+    request: TranscriptionRequestFor<Options>,
+  ) => Effect.Effect<Generation<TranscriptionResponse>, AIError>
+  readonly resume: <Options extends TranscriptionOptions>(
+    model: TranscriptionModel<Options>,
+    token: unknown,
+  ) => Effect.Effect<Generation<TranscriptionResponse>, AIError>
+}

 export class TranscriptionClientService extends Context.Service<TranscriptionClientService, Interface>()(
  "@opencode/TranscriptionClient",
@@ -15,10 +36,66 @@ export class TranscriptionClientService extends Context.Service<TranscriptionCli
 export const Service = TranscriptionClientService
 export type Service = TranscriptionClientService

+export const generate = <Options extends TranscriptionOptions>(
+  request: TranscriptionRequestFor<Options>,
+  options?: AwaitOptions,
+): Effect.Effect<TranscriptionResponse, AIError, Service> =>
+  Effect.gen(function* () {
+    const client = yield* Service
+    return yield* client.generate(request, options)
+  })
+
+export const stream = <Options extends TranscriptionOptions>(
+  request: TranscriptionRequestFor<Options>,
+  options?: AwaitOptions,
+): Stream.Stream<TranscriptionEvent, AIError, Service> =>
+  Stream.unwrap(
+    Effect.gen(function* () {
+      const client = yield* Service
+      return client.stream(request, options)
+    }),
+  )
+
+export const start = <Options extends TranscriptionOptions>(
+  request: TranscriptionRequestFor<Options>,
+): Effect.Effect<Generation<TranscriptionResponse>, AIError, Service> =>
+  Effect.gen(function* () {
+    const client = yield* Service
+    return yield* client.start(request)
+  })
+
+export const resume = <Options extends TranscriptionOptions>(
+  model: TranscriptionModel<Options>,
+  token: unknown,
+): Effect.Effect<Generation<TranscriptionResponse>, AIError, Service> =>
+  Effect.gen(function* () {
+    const client = yield* Service
+    return yield* client.resume(model, token)
+  })
+
+export const layer: Layer.Layer<Service, never, RequestExecutor.Service> = Layer.effect(
+  Service,
+  Effect.gen(function* () {
+    const executor = yield* RequestExecutor.Service
+    const dispatch = MediaRoute.dispatch<TranscriptionEvent, TranscriptionResponse>({
+      modality: "transcription",
+      execute: executor.execute,
+      responseEvents,
+    })
+    return Service.of({
+      start: (request) => dispatch.start(request.model.route, request),
+      resume: (model, token) => dispatch.resume(model.route, model, token),
+      generate: (request, options) => dispatch.generate(request.model.route, request, options),
+      stream: (request, options) => dispatch.stream(request.model.route, request, options),
+    })
+  }),
+)
+
 export const TranscriptionClient = {
  Service,
-  ...MediaClient.make(Service, {
-    modality: "transcription",
-    responseEvents: (response: TranscriptionResponse) => [TranscriptionFinishEvent.make({ ...response })],
-  }),
+  layer,
+  generate,
+  stream,
+  start,
+  resume,
 } as const
@@ -1,8 +1,9 @@
 import { Effect, Schema, Stream } from "effect"
 import { Generation, ProgressEvent, QueuedEvent, type AwaitOptions } from "./generation.js"
 import { Media } from "./media.js"
-import { MediaModel, composeRoute, tryRequest } from "./media-model.js"
+import { MediaModel, composeAnyRoute, tryRequest } from "./media-model.js"
 import { MediaRoute } from "./route/media.js"
+import type { MediaProtocol } from "./route/media-protocol.js"
 import { AIError, HttpOptions, MediaUsage, ProviderMetadata } from "./schema/index.js"
 import { TranscriptionClient, Service } from "./transcription-client.js"

@@ -10,49 +11,90 @@ import { TranscriptionClient, Service } from "./transcription-client.js"
 // Model
 // ---------------------------------------------------------------------------

-export type TranscriptionOptions = MediaModel.Options
+export type TranscriptionOptions = Record<string, unknown>

-export type TranscriptionRoute = MediaRoute.AnyRoute<TranscriptionRequestFor, TranscriptionEvent, TranscriptionResponse>
+export type TranscriptionRoute<Options extends TranscriptionOptions = TranscriptionOptions> = MediaRoute.AnyRoute<
+  TranscriptionRequestFor<Options>,
+  TranscriptionEvent,
+  TranscriptionResponse
+>

 export class TranscriptionModel<Options extends TranscriptionOptions = TranscriptionOptions> extends MediaModel<
-  TranscriptionRoute,
+  TranscriptionRoute<Options>,
  Options
 > {
  declare protected readonly _TranscriptionModel: void

+  static make<Options extends TranscriptionOptions = TranscriptionOptions>(
+    input: MediaModel.Input<TranscriptionRoute<Options>>,
+  ) {
+    return new TranscriptionModel<Options>(input)
+  }
+
  /** The number of type arguments selects the kind: `<Options>`, `<Options, Frame, State>`, or `<Options, Token>`. */
  static fromRoute<Options extends TranscriptionOptions>(
-    route: MediaModel.InlineRouteInput<TranscriptionRequestFor<Options>, TranscriptionResponse>,
+    route: TranscriptionModel.InlineRouteInput<Options>,
    input: MediaRoute.ModelInput,
  ): TranscriptionModel<Options>
  static fromRoute<Options extends TranscriptionOptions, Frame, State>(
-    route: MediaModel.StreamRouteInput<TranscriptionRequestFor<Options>, TranscriptionEvent, Frame, State>,
+    route: TranscriptionModel.StreamRouteInput<Options, Frame, State>,
    input: MediaRoute.ModelInput,
  ): TranscriptionModel<Options>
  static fromRoute<Options extends TranscriptionOptions, Token>(
-    route: MediaModel.QueuedRouteInput<TranscriptionRequestFor<Options>, TranscriptionResponse, Token>,
+    route: TranscriptionModel.QueuedRouteInput<Options, Token>,
    input: MediaRoute.ModelInput,
  ): TranscriptionModel<Options>
  static fromRoute<Options extends TranscriptionOptions, Frame, State, Token>(
-    route: MediaModel.AnyRouteInput<
-      TranscriptionRequestFor<Options>,
-      TranscriptionEvent,
-      TranscriptionResponse,
-      Frame,
-      State,
-      Token
-    >,
+    route: TranscriptionModel.RouteInput<Options, Frame, State, Token>,
    input: MediaRoute.ModelInput,
  ) {
    return new TranscriptionModel<Options>({
      id: input.id,
      provider: route.protocol.provider,
      http: input.http,
-      route: composeRoute(route, input, collectResponse) as TranscriptionRoute,
+      route: composeAnyRoute(route, input, collectResponse),
    })
  }
 }

+export namespace TranscriptionModel {
+  export type InlineRouteInput<Options extends TranscriptionOptions = TranscriptionOptions> = MediaModel.RouteInput<
+    TranscriptionRequestFor<Options>,
+    MediaProtocol.Inline<TranscriptionRequestFor<Options>, TranscriptionResponse>
+  >
+
+  export type StreamRouteInput<
+    Options extends TranscriptionOptions = TranscriptionOptions,
+    Frame = unknown,
+    State = unknown,
+  > = MediaModel.RouteInput<
+    MediaProtocol.Addressed<TranscriptionRequestFor<Options>>,
+    MediaProtocol.Streamed<TranscriptionRequestFor<Options>, TranscriptionEvent, Frame, State>
+  >
+
+  export type QueuedRouteInput<
+    Options extends TranscriptionOptions = TranscriptionOptions,
+    Token = unknown,
+  > = MediaModel.RouteInput<
+    TranscriptionRequestFor<Options>,
+    MediaProtocol.Queued<TranscriptionRequestFor<Options>, TranscriptionResponse, Token>
+  >
+
+  export type RouteInput<
+    Options extends TranscriptionOptions = TranscriptionOptions,
+    Frame = unknown,
+    State = unknown,
+    Token = unknown,
+  > = MediaModel.AnyRouteInput<
+    TranscriptionRequestFor<Options>,
+    TranscriptionEvent,
+    TranscriptionResponse,
+    Frame,
+    State,
+    Token
+  >
+}
+
 export const TranscriptionModelSchema = Schema.declare(
  (value): value is TranscriptionModel => value instanceof TranscriptionModel,
  { expected: "Transcription.Model" },
@@ -170,6 +212,10 @@ export const TranscriptionEvent = Object.assign(transcriptionEventTagged, {
 })
 export type TranscriptionEvent = Schema.Schema.Type<typeof transcriptionEventTagged>

+export const responseEvents = (response: TranscriptionResponse): ReadonlyArray<TranscriptionEvent> => [
+  TranscriptionFinishEvent.make({ ...response }),
+]
+
 const collectResponse = (events: ReadonlyArray<TranscriptionEvent>): Effect.Effect<TranscriptionResponse> => {
  const finish = events.find(TranscriptionEvent.is.finish)
  // Every transcription protocol's `finish` emits the terminal event or fails, so a completed stream always has one.
@@ -197,7 +243,11 @@ export function request(input: TranscriptionRequest | TranscriptionRequestInput)
 const requestEffect = (input: TranscriptionRequest | TranscriptionRequestInput) => tryRequest(() => request(input))

 export function generate<const Model extends TranscriptionModel>(
-  input: TranscriptionRequest | TranscriptionRequestInput<Model>,
+  input: TranscriptionRequestInput<Model>,
+  options?: AwaitOptions,
+): Effect.Effect<TranscriptionResponse, AIError, Service>
+export function generate(
+  input: TranscriptionRequest,
  options?: AwaitOptions,
 ): Effect.Effect<TranscriptionResponse, AIError, Service>
 export function generate(input: TranscriptionRequest | TranscriptionRequestInput, options?: AwaitOptions) {
@@ -205,7 +255,11 @@ export function generate(input: TranscriptionRequest | TranscriptionRequestInput
 }

 export function stream<const Model extends TranscriptionModel>(
-  input: TranscriptionRequest | TranscriptionRequestInput<Model>,
+  input: TranscriptionRequestInput<Model>,
+  options?: AwaitOptions,
+): Stream.Stream<TranscriptionEvent, AIError, Service>
+export function stream(
+  input: TranscriptionRequest,
  options?: AwaitOptions,
 ): Stream.Stream<TranscriptionEvent, AIError, Service>
 export function stream(input: TranscriptionRequest | TranscriptionRequestInput, options?: AwaitOptions) {
@@ -214,14 +268,15 @@ export function stream(input: TranscriptionRequest | TranscriptionRequestInput,

 /** Inline and streaming routes fail with `UnsupportedOperation`. */
 export function start<const Model extends TranscriptionModel>(
-  input: TranscriptionRequest | TranscriptionRequestInput<Model>,
+  input: TranscriptionRequestInput<Model>,
 ): Effect.Effect<Generation<TranscriptionResponse>, AIError, Service>
+export function start(input: TranscriptionRequest): Effect.Effect<Generation<TranscriptionResponse>, AIError, Service>
 export function start(input: TranscriptionRequest | TranscriptionRequestInput) {
  return requestEffect(input).pipe(Effect.flatMap((request) => TranscriptionClient.start(request)))
 }

-export const resume = (
-  model: TranscriptionModel,
+export const resume = <Options extends TranscriptionOptions>(
+  model: TranscriptionModel<Options>,
  token: unknown,
 ): Effect.Effect<Generation<TranscriptionResponse>, AIError, Service> => TranscriptionClient.resume(model, token)

@@ -1,30 +1,98 @@
-import { Context } from "effect"
-import { MediaClient } from "./media-client.js"
+import { Context, Effect, Layer, Stream } from "effect"
+import { resultEvents, type AwaitOptions, type Generation } from "./generation.js"
+import { RequestExecutor } from "./route/executor.js"
+import type { AIError } from "./schema/index.js"
 import {
-  VideoOutputEvent,
-  VideoFinishEvent,
+  responseEvents,
  type VideoEvent,
+  type VideoModel,
+  type VideoOptions,
  type VideoRequestFor,
  type VideoResponse,
 } from "./video.js"

-export type Interface = MediaClient.Interface<VideoRequestFor, VideoEvent, VideoResponse>
+export interface Interface {
+  readonly start: <Options extends VideoOptions>(
+    request: VideoRequestFor<Options>,
+  ) => Effect.Effect<Generation<VideoResponse>, AIError>
+  readonly resume: <Options extends VideoOptions>(
+    model: VideoModel<Options>,
+    token: unknown,
+  ) => Effect.Effect<Generation<VideoResponse>, AIError>
+  readonly generate: <Options extends VideoOptions>(
+    request: VideoRequestFor<Options>,
+    options?: AwaitOptions,
+  ) => Effect.Effect<VideoResponse, AIError>
+  readonly stream: <Options extends VideoOptions>(
+    request: VideoRequestFor<Options>,
+    options?: AwaitOptions,
+  ) => Stream.Stream<VideoEvent, AIError>
+}

 export class VideoClientService extends Context.Service<VideoClientService, Interface>()("@opencode/VideoClient") {}
 export const Service = VideoClientService
 export type Service = VideoClientService

+export const start = <Options extends VideoOptions>(
+  request: VideoRequestFor<Options>,
+): Effect.Effect<Generation<VideoResponse>, AIError, Service> =>
+  Effect.gen(function* () {
+    const client = yield* Service
+    return yield* client.start(request)
+  })
+
+export const resume = <Options extends VideoOptions>(
+  model: VideoModel<Options>,
+  token: unknown,
+): Effect.Effect<Generation<VideoResponse>, AIError, Service> =>
+  Effect.gen(function* () {
+    const client = yield* Service
+    return yield* client.resume(model, token)
+  })
+
+export const generate = <Options extends VideoOptions>(
+  request: VideoRequestFor<Options>,
+  options?: AwaitOptions,
+): Effect.Effect<VideoResponse, AIError, Service> =>
+  Effect.gen(function* () {
+    const client = yield* Service
+    return yield* client.generate(request, options)
+  })
+
+export const stream = <Options extends VideoOptions>(
+  request: VideoRequestFor<Options>,
+  options?: AwaitOptions,
+): Stream.Stream<VideoEvent, AIError, Service> =>
+  Stream.unwrap(
+    Effect.gen(function* () {
+      const client = yield* Service
+      return client.stream(request, options)
+    }),
+  )
+
+export const layer: Layer.Layer<Service, never, RequestExecutor.Service> = Layer.effect(
+  Service,
+  Effect.gen(function* () {
+    const executor = yield* RequestExecutor.Service
+    const start = <Options extends VideoOptions>(request: VideoRequestFor<Options>) =>
+      request.model.route.start(request, executor.execute)
+    return Service.of({
+      start,
+      resume: (model, token) => model.route.resume(model, token, executor.execute),
+      generate: (request, options) => start(request).pipe(Effect.flatMap((generation) => generation.await(options))),
+      stream: (request, options) =>
+        Stream.unwrap(
+          start(request).pipe(Effect.map((generation) => resultEvents(generation, responseEvents, options))),
+        ),
+    })
+  }),
+)
+
 export const VideoClient = {
  Service,
-  ...MediaClient.make(Service, {
-    modality: "video",
-    responseEvents: (response: VideoResponse) => [
-      ...response.videos.map((video, index) => VideoOutputEvent.make({ index, video })),
-      VideoFinishEvent.make({
-        usage: response.usage,
-        notices: response.notices,
-        providerMetadata: response.providerMetadata,
-      }),
-    ],
-  }),
+  layer,
+  start,
+  resume,
+  generate,
+  stream,
 } as const
@@ -3,6 +3,7 @@ import { Generation, ProgressEvent, QueuedEvent, type AwaitOptions } from "./gen
 import { Media } from "./media.js"
 import { MediaModel, composeRoute, tryRequest } from "./media-model.js"
 import { MediaRoute } from "./route/media.js"
+import type { MediaProtocol } from "./route/media-protocol.js"
 import { AIError, HttpOptions, MediaUsage, ProviderMetadata, type OpenString } from "./schema/index.js"
 import { VideoClient, Service } from "./video-client.js"

@@ -10,39 +11,41 @@ import { VideoClient, Service } from "./video-client.js"
 // Model
 // ---------------------------------------------------------------------------

-export type VideoOptions = MediaModel.Options
+export type VideoOptions = Record<string, unknown>

-export type VideoRoute = MediaRoute.AnyRoute<VideoRequestFor, VideoEvent, VideoResponse>
+export type VideoRoute<Options extends VideoOptions = VideoOptions> = MediaRoute.QueuedRoute<
+  VideoRequestFor<Options>,
+  VideoResponse
+>

-export class VideoModel<Options extends VideoOptions = VideoOptions> extends MediaModel<VideoRoute, Options> {
+export class VideoModel<Options extends VideoOptions = VideoOptions> extends MediaModel<VideoRoute<Options>, Options> {
  declare protected readonly _VideoModel: void

-  /** The number of type arguments selects the kind: `<Options>`, `<Options, Frame, State>`, or `<Options, Token>`. */
-  static fromRoute<Options extends VideoOptions>(
-    route: MediaModel.InlineRouteInput<VideoRequestFor<Options>, VideoResponse>,
-    input: MediaRoute.ModelInput,
-  ): VideoModel<Options>
-  static fromRoute<Options extends VideoOptions, Frame, State>(
-    route: MediaModel.StreamRouteInput<VideoRequestFor<Options>, VideoEvent, Frame, State>,
-    input: MediaRoute.ModelInput,
-  ): VideoModel<Options>
-  static fromRoute<Options extends VideoOptions, Token>(
-    route: MediaModel.QueuedRouteInput<VideoRequestFor<Options>, VideoResponse, Token>,
-    input: MediaRoute.ModelInput,
-  ): VideoModel<Options>
-  static fromRoute<Options extends VideoOptions, Frame, State, Token>(
-    route: MediaModel.AnyRouteInput<VideoRequestFor<Options>, VideoEvent, VideoResponse, Frame, State, Token>,
+  static make<Options extends VideoOptions = VideoOptions>(input: MediaModel.Input<VideoRoute<Options>>) {
+    return new VideoModel<Options>(input)
+  }
+
+  /** Compose a queued video protocol with its canonical start path into a model for one deployment. */
+  static fromRoute<Options extends VideoOptions = VideoOptions, Token = unknown>(
+    route: VideoModel.RouteInput<Options, Token>,
    input: MediaRoute.ModelInput,
  ) {
    return new VideoModel<Options>({
      id: input.id,
      provider: route.protocol.provider,
      http: input.http,
-      route: composeRoute(route, input, collectResponse) as VideoRoute,
+      route: composeRoute(MediaRoute.queued, route, input),
    })
  }
 }

+export namespace VideoModel {
+  export type RouteInput<Options extends VideoOptions = VideoOptions, Token = unknown> = MediaModel.RouteInput<
+    VideoRequestFor<Options>,
+    MediaProtocol.Queued<VideoRequestFor<Options>, VideoResponse, Token>
+  >
+}
+
 export const VideoModelSchema = Schema.declare((value): value is VideoModel => value instanceof VideoModel, {
  expected: "Video.Model",
 })
@@ -146,19 +149,15 @@ export const VideoEvent = Object.assign(videoEventTagged, {
 })
 export type VideoEvent = Schema.Schema.Type<typeof videoEventTagged>

-const collectResponse = (events: ReadonlyArray<VideoEvent>): Effect.Effect<VideoResponse> => {
-  const finish = events.find(VideoEvent.is.finish)
-  // A streaming video protocol's `finish` emits the terminal event or fails, so a completed stream always has one.
-  if (finish === undefined) return Effect.die(new Error("The video stream completed without a finish event"))
-  return Effect.succeed(
-    new VideoResponse({
-      videos: events.filter(VideoEvent.is.video).map((event) => event.video),
-      usage: finish.usage,
-      notices: finish.notices,
-      providerMetadata: finish.providerMetadata,
-    }),
-  )
-}
+/** A completed response expanded into the streaming event shape. */
+export const responseEvents = (response: VideoResponse): ReadonlyArray<VideoEvent> => [
+  ...response.videos.map((video, index) => VideoOutputEvent.make({ index, video })),
+  VideoFinishEvent.make({
+    usage: response.usage,
+    notices: response.notices,
+    providerMetadata: response.providerMetadata,
+  }),
+]

 // ---------------------------------------------------------------------------
 // Request-shaped call API
@@ -179,28 +178,33 @@ export function request(input: VideoRequest | VideoRequestInput) {
 const requestEffect = (input: VideoRequest | VideoRequestInput) => tryRequest(() => request(input))

 export function start<const Model extends VideoModel>(
-  input: VideoRequest | VideoRequestInput<Model>,
+  input: VideoRequestInput<Model>,
 ): Effect.Effect<Generation<VideoResponse>, AIError, Service>
+export function start(input: VideoRequest): Effect.Effect<Generation<VideoResponse>, AIError, Service>
 export function start(input: VideoRequest | VideoRequestInput) {
  return requestEffect(input).pipe(Effect.flatMap((request) => VideoClient.start(request)))
 }

 export function generate<const Model extends VideoModel>(
-  input: VideoRequest | VideoRequestInput<Model>,
+  input: VideoRequestInput<Model>,
  options?: AwaitOptions,
 ): Effect.Effect<VideoResponse, AIError, Service>
+export function generate(input: VideoRequest, options?: AwaitOptions): Effect.Effect<VideoResponse, AIError, Service>
 export function generate(input: VideoRequest | VideoRequestInput, options?: AwaitOptions) {
  return requestEffect(input).pipe(Effect.flatMap((request) => VideoClient.generate(request, options)))
 }

 /** Rebuild a generation handle from a persisted `Generation.token`, refreshing its status once. */
-export const resume = (model: VideoModel, token: unknown): Effect.Effect<Generation<VideoResponse>, AIError, Service> =>
-  VideoClient.resume(model, token)
+export const resume = <Options extends VideoOptions>(
+  model: VideoModel<Options>,
+  token: unknown,
+): Effect.Effect<Generation<VideoResponse>, AIError, Service> => VideoClient.resume(model, token)

 export function stream<const Model extends VideoModel>(
-  input: VideoRequest | VideoRequestInput<Model>,
+  input: VideoRequestInput<Model>,
  options?: AwaitOptions,
 ): Stream.Stream<VideoEvent, AIError, Service>
+export function stream(input: VideoRequest, options?: AwaitOptions): Stream.Stream<VideoEvent, AIError, Service>
 export function stream(input: VideoRequest | VideoRequestInput, options?: AwaitOptions) {
  return Stream.unwrap(requestEffect(input).pipe(Effect.map((request) => VideoClient.stream(request, options))))
 }
@@ -351,34 +351,10 @@ describe("OpenAI Responses effort updates", () => {
    }),
  )

-  it.effect("strips markers when the body overlay selects pro reasoning mode", () =>
-    Effect.gen(function* () {
-      const prepared = yield* compileRequest(
-        LLM.request({
-          model: OpenAI.configure({ apiKey: "fixture", http: { body: { reasoning: { mode: "pro" } } } }).responses(
-            "gpt-6-sol",
-          ),
-          messages: conversation,
-          providerOptions: { reasoningEffort: "low" },
-        }),
-      )
-
-      expect(updates(prepared.body)).toEqual([])
-      expect(prepared.body.reasoning).toEqual({ effort: "low" })
-    }),
-  )
-
  for (const [id, supported] of [
    ["gpt-6-astra", true],
    ["openai/gpt-6-astra", true],
-    ["gpt-6-sol", true],
-    ["openai/gpt-6-sol", true],
-    ["gpt-6-luna", true],
-    ["openai/gpt-6-luna", true],
    ["gpt-6-astra-2026-09-01", false],
-    ["gpt-6-sol-pro", false],
-    ["gpt-6-luna-pro", false],
-    ["gpt-6-sol-fast", false],
    ["gpt-5.6-sol", false],
  ] as const) {
    it.effect(`${supported ? "lowers" : "strips"} markers for ${id}`, () =>
@@ -23,7 +23,6 @@ import { Provider as ProviderSubpath } from "@opencode/ai/provider"
 import {
  AssemblyAI,
  Baseten,
-  BlackForestLabs,
  Cartesia,
  CloudflareAIGateway,
  CloudflareWorkersAI,
@@ -33,18 +32,14 @@ import {
  Fal,
  Fireworks,
  Google,
-  Meta,
  OpenCodeZen,
  OpenAI,
  OpenAICompatible,
  OpenRouter,
-  Replicate,
  Runway,
-  Stability,
  TypeSafeAI,
  VercelAIGateway,
  XAI,
-  ZAI,
 } from "@opencode/ai/providers"
 import {
  OpenAIChat,
@@ -59,19 +54,6 @@ import { TestLLM } from "@opencode/ai/testing"
 import { Evaluation, EvaluationClient } from "@opencode/ai/experimental"

 describe("public exports", () => {
-  test("modality, provider, and protocol entrypoints load first in a fresh process", async () => {
-    const results = await Promise.all(
-      ["image", "video", "speech", "transcription", "providers", "protocols"].map(async (entry) => {
-        const child = Bun.spawn(
-          [process.execPath, "-e", `await import(${JSON.stringify(`${import.meta.dir}/../src/${entry}.ts`)})`],
-          { stderr: "pipe" },
-        )
-        return { entry, exitCode: await child.exited, stderr: await new Response(child.stderr).text() }
-      }),
-    )
-    expect(results.filter((result) => result.exitCode !== 0)).toEqual([])
-  })
-
  test("root exposes app-facing runtime APIs", () => {
    expect(LLM.request).toBeFunction()
    expect(LLMClient.Service).toBeFunction()
@@ -156,34 +138,8 @@ describe("public exports", () => {
    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(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")
-    expect(Google.provider.image).toBe(Google.image)
-    expect(XAI.configure({ apiKey: "fixture" }).image("grok-imagine-image").route.id).toBe("xai-images")
-    expect(XAI.provider.image).toBe(XAI.image)
-    expect(Fal.configure({ apiKey: "fixture" }).image("fal-ai/flux/dev").route.id).toBe("fal-images")
-    expect(Fal.provider.image).toBe(Fal.image)
-    expect(BlackForestLabs.configure({ apiKey: "fixture" }).image("flux-2-pro").route.id).toBe("bfl-images")
-    expect(BlackForestLabs.provider.image).toBe(BlackForestLabs.image)
-    expect(Replicate.configure({ apiKey: "fixture" }).image("black-forest-labs/flux-schnell").route.id).toBe(
-      "replicate-images",
-    )
-    expect(Replicate.provider.image).toBe(Replicate.image)
-    expect(Stability.configure({ apiKey: "fixture" }).image("sd3.5-large").route.id).toBe("stability-images")
-    expect(Stability.provider.image).toBe(Stability.image)
-    expect(Stability.configure({ apiKey: "fixture" }).upscale().route.id).toBe("stability-upscale")
-    expect(Stability.provider.upscale).toBe(Stability.upscale)
-    expect(Meta.configure({ apiKey: "fixture" }).image("muse-image").route.id).toBe("meta-images")
-    expect(Meta.provider.image).toBe(Meta.image)
-    expect(ZAI.configure({ apiKey: "fixture" }).image("glm-image").route.id).toBe("zai-images")
-    expect(ZAI.provider.image).toBe(ZAI.image)
    expect(XAI.configure({ apiKey: "fixture" }).video("grok-imagine-video-1.5").route.id).toBe("xai-video")
-    expect(XAI.provider.video).toBe(XAI.video)
-    expect(Google.configure({ apiKey: "fixture" }).video("veo-3.1-generate-preview").route.id).toBe("google-video")
-    expect(Google.provider.video).toBe(Google.video)
    expect(Fal.configure({ apiKey: "fixture" }).video("fal-ai/veo3.1").route.id).toBe("fal-video")
-    expect(Fal.provider.video).toBe(Fal.video)
    expect(Runway.configure({ apiKey: "fixture" }).video("gen4.5").route.id).toBe("runway-video")
    expect(Runway.provider.video).toBe(Runway.video)
    expect(OpenAI.configure({ apiKey: "fixture" }).speech("gpt-4o-mini-tts").route.id).toBe("openai-speech")
@@ -30,7 +30,7 @@
        {
          "direction": "client",
          "kind": "text",
-          "body": "{\"type\":\"response.create\",\"model\":\"gpt-5.5\",\"input\":[{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"What is the weather in Paris?\"}]}],\"instructions\":\"Call get_weather once, then reply exactly: Paris is sunny.\",\"tools\":[{\"type\":\"function\",\"name\":\"get_weather\",\"description\":\"Get current weather for a city.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false},\"strict\":false}],\"store\":false,\"include\":[\"reasoning.encrypted_content\"],\"reasoning\":{\"effort\":\"medium\",\"summary\":\"auto\"},\"max_output_tokens\":50}"
+          "body": "{\"type\":\"response.create\",\"model\":\"gpt-5.5\",\"input\":[{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"What is the weather in Paris?\"}]}],\"instructions\":\"Call get_weather once, then reply exactly: Paris is sunny.\",\"tools\":[{\"type\":\"function\",\"name\":\"get_weather\",\"description\":\"Get current weather for a city.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false},\"strict\":false}],\"store\":false,\"include\":[\"reasoning.encrypted_content\"],\"reasoning\":{\"effort\":\"medium\",\"summary\":\"auto\"},\"text\":{\"verbosity\":\"low\"},\"max_output_tokens\":50}"
        },
        {
          "direction": "server",
@@ -525,7 +525,7 @@
        {
          "direction": "client",
          "kind": "text",
-          "body": "{\"type\":\"response.create\",\"model\":\"gpt-5.5\",\"input\":[{\"type\":\"function_call_output\",\"call_id\":\"call_hejtTYDa1IfLyNIzb3fq9gJs\",\"output\":\"{\\\"temperature\\\":22,\\\"condition\\\":\\\"sunny\\\"}\"}],\"instructions\":\"Call get_weather once, then reply exactly: Paris is sunny.\",\"tools\":[{\"type\":\"function\",\"name\":\"get_weather\",\"description\":\"Get current weather for a city.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false},\"strict\":false}],\"store\":false,\"include\":[\"reasoning.encrypted_content\"],\"reasoning\":{\"effort\":\"medium\",\"summary\":\"auto\"},\"max_output_tokens\":50,\"previous_response_id\":\"resp_0d9a44b6df400533016aa8c8e36de887d1be260913d131b2ca\"}"
+          "body": "{\"type\":\"response.create\",\"model\":\"gpt-5.5\",\"input\":[{\"type\":\"function_call_output\",\"call_id\":\"call_hejtTYDa1IfLyNIzb3fq9gJs\",\"output\":\"{\\\"temperature\\\":22,\\\"condition\\\":\\\"sunny\\\"}\"}],\"instructions\":\"Call get_weather once, then reply exactly: Paris is sunny.\",\"tools\":[{\"type\":\"function\",\"name\":\"get_weather\",\"description\":\"Get current weather for a city.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false},\"strict\":false}],\"store\":false,\"include\":[\"reasoning.encrypted_content\"],\"reasoning\":{\"effort\":\"medium\",\"summary\":\"auto\"},\"text\":{\"verbosity\":\"low\"},\"max_output_tokens\":50,\"previous_response_id\":\"resp_0d9a44b6df400533016aa8c8e36de887d1be260913d131b2ca\"}"
        },
        {
          "direction": "server",
@@ -30,7 +30,7 @@
        {
          "direction": "client",
          "kind": "text",
-          "body": "{\"type\":\"response.create\",\"model\":\"gpt-5.5\",\"input\":[{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"Reply exactly: Alpha.\"}]}],\"instructions\":\"Follow the user's exact reply instruction.\",\"store\":false,\"include\":[\"reasoning.encrypted_content\"],\"reasoning\":{\"effort\":\"medium\",\"summary\":\"auto\"},\"max_output_tokens\":30}"
+          "body": "{\"type\":\"response.create\",\"model\":\"gpt-5.5\",\"input\":[{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"Reply exactly: Alpha.\"}]}],\"instructions\":\"Follow the user's exact reply instruction.\",\"store\":false,\"include\":[\"reasoning.encrypted_content\"],\"reasoning\":{\"effort\":\"medium\",\"summary\":\"auto\"},\"text\":{\"verbosity\":\"low\"},\"max_output_tokens\":30}"
        },
        {
          "direction": "server",
@@ -109,7 +109,7 @@
        {
          "direction": "client",
          "kind": "text",
-          "body": "{\"type\":\"response.create\",\"model\":\"gpt-5.5\",\"input\":[{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"Reply exactly: Alpha.\"}]},{\"type\":\"reasoning\",\"id\":\"rs_0a6277dd90b94da1016aa8c946e33487d1b725d8e9dc874d82\",\"summary\":[],\"encrypted_content\":\"gAAAAABqqMlHtG6yltzgW_UjUcYxvl2hoMkk7cSEH5SJMe9CR5gKIaCwCh4peUo8XZrd-EU-tPCXthv7JzHxYXGVG1fIgTJ7BjBoOh-jgd_oGlyCHj2jVPj7nVoB763tZHdyw_ovL3V7GpJ6VeLGIsRGqNTnBz47ZuKikTKrbTDupn6fT2wOM_69zwdg4-UVnoF2J9E_jIS0E5XRtRwOidqANl61HCwo7LV-Ut1aqCbXb-59vkrVGWPxD_8n4smf7Qjywc0FCH9zwuEDX4cPdqj3MmjvYPrn0jand9LKkAy9rblaKFJSQfVuritbHrdQrnF7hLxu7QCpehOzNXOkpNEqTmXnAZjfMc53hq-ahH6_KoyYlZpompwyGPngFeI2fKRqP8rlpDilD1BHBsh-bl7kXzI8HQ_jameXwPZ1La6gjtFkThXp53BD6BOx11SB9Nypqolu2at5rR32UYcGrYeGtTu-HmYGp0oHVFkHumTNuHKmGXV14dI9swgryfygLhX8EAJrWrjm3e8rvAkHKpAZ0IkmlCcp15UCFDKNeS560fQVRaKXWnQ7m0Ih3C1xG0ifJ89j27c8GHo1kAhEJk-lSB1-FZr9Ls_w7N772kmZ2a7LLswu3kNW78kPas_CtcOnBOHwE1DhcVh5YpxwNftOHZnK1v8NPNF8EWqio4ArZy1thMCzH5zXBNcFzgd8tePMFukBblSP8QGQoVYRqTne2sFoOZXjslXnDvEe-Ycj8X38zWgRiwAk7guOloFC7Se36KCDP357773Vah86gWCt55mSEyhVW_GF1oTuHvJ18GZsXcyN21scF1PSr8YaCM_jR7ZkU1GYXbQK2Y4oTAV9XDptQA5YzEREnn7muC_6v5ZTAglZF1lhn9Q0NwmylZEAXJdSGHaqXt1Hv-vQlprA_9m22vrreBOTLPnVK946J8absKrwfe-jK_1n_9YQR43uwH8XwFBFND0c4lICCQGbxwM8pX4ACWR0c19aORCYm-M5FrJsxmG29_aDVNhcvkoQ3mlP7ITQeqzkrjfytSwLb2BYpXYZKjEHNfV9j3JoxJobUkK5hrxXBhTvZzbVBnE0LSXQNwR-JAcOliP_jXBEeQ-28B-aGW8TI1vEP2i260QKgzOzPC-pOoFp0-vCvxojNO0kE16ECVTLfDNLNGSMZs9vekdLJP2akBp6PsUXsQUTbWO_wr1E2oNU7ctfMRxoh-yP0ZW2_xz_NjE72O5LF_6zuDVV7Q==\"},{\"type\":\"message\",\"id\":\"msg_0a6277dd90b94da1016aa8c947253887d184c150fcbcbcd8da\",\"role\":\"assistant\",\"content\":[{\"type\":\"output_text\",\"text\":\"Alpha.\"}],\"phase\":\"final_answer\",\"status\":\"completed\"},{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"Reply exactly: Beta.\"}]}],\"instructions\":\"Follow the user's exact reply instruction.\",\"store\":false,\"include\":[\"reasoning.encrypted_content\"],\"reasoning\":{\"effort\":\"medium\",\"summary\":\"auto\"},\"max_output_tokens\":30}"
+          "body": "{\"type\":\"response.create\",\"model\":\"gpt-5.5\",\"input\":[{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"Reply exactly: Alpha.\"}]},{\"type\":\"reasoning\",\"id\":\"rs_0a6277dd90b94da1016aa8c946e33487d1b725d8e9dc874d82\",\"summary\":[],\"encrypted_content\":\"gAAAAABqqMlHtG6yltzgW_UjUcYxvl2hoMkk7cSEH5SJMe9CR5gKIaCwCh4peUo8XZrd-EU-tPCXthv7JzHxYXGVG1fIgTJ7BjBoOh-jgd_oGlyCHj2jVPj7nVoB763tZHdyw_ovL3V7GpJ6VeLGIsRGqNTnBz47ZuKikTKrbTDupn6fT2wOM_69zwdg4-UVnoF2J9E_jIS0E5XRtRwOidqANl61HCwo7LV-Ut1aqCbXb-59vkrVGWPxD_8n4smf7Qjywc0FCH9zwuEDX4cPdqj3MmjvYPrn0jand9LKkAy9rblaKFJSQfVuritbHrdQrnF7hLxu7QCpehOzNXOkpNEqTmXnAZjfMc53hq-ahH6_KoyYlZpompwyGPngFeI2fKRqP8rlpDilD1BHBsh-bl7kXzI8HQ_jameXwPZ1La6gjtFkThXp53BD6BOx11SB9Nypqolu2at5rR32UYcGrYeGtTu-HmYGp0oHVFkHumTNuHKmGXV14dI9swgryfygLhX8EAJrWrjm3e8rvAkHKpAZ0IkmlCcp15UCFDKNeS560fQVRaKXWnQ7m0Ih3C1xG0ifJ89j27c8GHo1kAhEJk-lSB1-FZr9Ls_w7N772kmZ2a7LLswu3kNW78kPas_CtcOnBOHwE1DhcVh5YpxwNftOHZnK1v8NPNF8EWqio4ArZy1thMCzH5zXBNcFzgd8tePMFukBblSP8QGQoVYRqTne2sFoOZXjslXnDvEe-Ycj8X38zWgRiwAk7guOloFC7Se36KCDP357773Vah86gWCt55mSEyhVW_GF1oTuHvJ18GZsXcyN21scF1PSr8YaCM_jR7ZkU1GYXbQK2Y4oTAV9XDptQA5YzEREnn7muC_6v5ZTAglZF1lhn9Q0NwmylZEAXJdSGHaqXt1Hv-vQlprA_9m22vrreBOTLPnVK946J8absKrwfe-jK_1n_9YQR43uwH8XwFBFND0c4lICCQGbxwM8pX4ACWR0c19aORCYm-M5FrJsxmG29_aDVNhcvkoQ3mlP7ITQeqzkrjfytSwLb2BYpXYZKjEHNfV9j3JoxJobUkK5hrxXBhTvZzbVBnE0LSXQNwR-JAcOliP_jXBEeQ-28B-aGW8TI1vEP2i260QKgzOzPC-pOoFp0-vCvxojNO0kE16ECVTLfDNLNGSMZs9vekdLJP2akBp6PsUXsQUTbWO_wr1E2oNU7ctfMRxoh-yP0ZW2_xz_NjE72O5LF_6zuDVV7Q==\"},{\"type\":\"message\",\"id\":\"msg_0a6277dd90b94da1016aa8c947253887d184c150fcbcbcd8da\",\"role\":\"assistant\",\"content\":[{\"type\":\"output_text\",\"text\":\"Alpha.\"}],\"phase\":\"final_answer\",\"status\":\"completed\"},{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"Reply exactly: Beta.\"}]}],\"instructions\":\"Follow the user's exact reply instruction.\",\"store\":false,\"include\":[\"reasoning.encrypted_content\"],\"reasoning\":{\"effort\":\"medium\",\"summary\":\"auto\"},\"text\":{\"verbosity\":\"low\"},\"max_output_tokens\":30}"
        },
        {
          "direction": "server",
@@ -30,7 +30,7 @@
        {
          "direction": "client",
          "kind": "text",
-          "body": "{\"type\":\"response.create\",\"model\":\"gpt-5.5\",\"input\":[{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"Reply exactly: Ready.\"}]}],\"instructions\":\"Follow the user's exact reply instruction.\",\"store\":false,\"include\":[\"reasoning.encrypted_content\"],\"reasoning\":{\"effort\":\"medium\",\"summary\":\"auto\"},\"max_output_tokens\":30}"
+          "body": "{\"type\":\"response.create\",\"model\":\"gpt-5.5\",\"input\":[{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"Reply exactly: Ready.\"}]}],\"instructions\":\"Follow the user's exact reply instruction.\",\"store\":false,\"include\":[\"reasoning.encrypted_content\"],\"reasoning\":{\"effort\":\"medium\",\"summary\":\"auto\"},\"text\":{\"verbosity\":\"low\"},\"max_output_tokens\":30}"
        },
        {
          "direction": "server",
@@ -109,7 +109,7 @@
        {
          "direction": "client",
          "kind": "text",
-          "body": "{\"type\":\"response.create\",\"model\":\"gpt-5.5\",\"input\":[{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"Reply exactly: Recovered.\"}]}],\"instructions\":\"Follow the user's exact reply instruction.\",\"store\":false,\"include\":[\"reasoning.encrypted_content\"],\"reasoning\":{\"effort\":\"medium\",\"summary\":\"auto\"},\"max_output_tokens\":30,\"previous_response_id\":\"resp_01cc0cda24c36acf016aa8ca3c1d3c87d1853283f43675e411\"}"
+          "body": "{\"type\":\"response.create\",\"model\":\"gpt-5.5\",\"input\":[{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"Reply exactly: Recovered.\"}]}],\"instructions\":\"Follow the user's exact reply instruction.\",\"store\":false,\"include\":[\"reasoning.encrypted_content\"],\"reasoning\":{\"effort\":\"medium\",\"summary\":\"auto\"},\"text\":{\"verbosity\":\"low\"},\"max_output_tokens\":30,\"previous_response_id\":\"resp_01cc0cda24c36acf016aa8ca3c1d3c87d1853283f43675e411\"}"
        },
        {
          "direction": "server",
@@ -119,7 +119,7 @@
        {
          "direction": "client",
          "kind": "text",
-          "body": "{\"type\":\"response.create\",\"model\":\"gpt-5.5\",\"input\":[{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"Reply exactly: Ready.\"}]},{\"type\":\"reasoning\",\"id\":\"rs_01cc0cda24c36acf016aa8ca3ced8c87d1a14c5c6a2ced8544\",\"summary\":[],\"encrypted_content\":\"gAAAAABqqMo9M9B15LsV1CLsXpNJpI08GiwCAK97hTheQ2s1lAkKgARMs1HIIXVeAr-tbUq88yN51fiQE8HvGwdF9ZcNI6bZle8D2PS7m8O7UE7C1Z_HX_fz2f0pRHyRfWpVAT2gYQWIDeZu6UdgxbKPBW0lXWzlk_relHG5x6nXkYzZoEeVasqavWoyMMSX7cexe-IYJh6e_3DgRpOchueS8Z-70P0w5R83Ea7UXZQNhMA0yDEYu_td2PmE2Pd2PUTOB3mxF2pb1z7-2t6S0UryhHx0az7Gh2eT60GGUqz9CIZzNE_FX--tszeuO0eI92Cen5tirOUHBTyyDqE0eG26DRl_p_U-xDZwaQONbtYbvkvrj-G7FA2oZXxjJPHuQZsNgBslXS-H0KT1lx3Y8XJ9QMVjFLFaucFG64wCmXPfCH8dYtX_YqfYQR4lwNfiSbyJEX2oDvTVVD_aCJ9NRo7c0aCTtmKBvr6fvvAy3MAFxAp_Sm2nMx4P5GYO4qAmJDByywKw-VK1vHlv3NRmVsAgbArIFgm-axoCs2PLpvZjDqeQGPavaq8zKWTyZYqBsEzKZUtGOZfYjD4mud0Z08I4i2H4K-L00ccVauode3548ZipOIuslbhJxonQXsF6TFdW2Hj8E5JjoEr5IbmwHyI0PBcDWW5AmkjHLwr9v08mFppRoD-2wzPAd5igROAuUbvJhiQd2A-uOaohwMjdpFxrjyUqgGTlI5g7tmI1ceeQWms0bKm8Pd0wIqVM3Nq6YvV7XfEyeogfRMVUQezr_lES42ZMVAoKBSFzMysDwCFkhVNVclcTUpcUUbVp21FChG7Ag-xuq8Cl6OGLA8nWX1C0aCf2HNa-n3dkYr1DtUziurh1MD-UIs5jdGiq3ptrc0VaVZwNdD4jVfAoHB_Ws7GiISXuclfpqsG3DTJEfzlbukI1vxXrt3FArsHiQvQjW5UM7gGel32M6p8AlXRxnez9PgIuU1WrtBUJetk7m39AZwp_aqbqC-AJ-MF70xP1VJZwFN-GeNL3VZsRHePFG4h7Pj---CCZRGlmzuE1-b-sIE7Bn_gbue_qHFMZJhAY55MO25vfZbSoLWHZCGmLMjJVHOYCPoy6l7zyxNmoIcC58QILNWal31KLCDmCsASmZC-xQRjyFwt-kvLbvk38Dc02IKcP3ujhf6WRRr1A0hh1K-gXmv_XI_MUFDcOVIjjhB-rXgjWSCoKfaKI9GCIsb9mnNaBq65BWg==\"},{\"type\":\"message\",\"id\":\"msg_01cc0cda24c36acf016aa8ca3d4a0087d1950121aed4802434\",\"role\":\"assistant\",\"content\":[{\"type\":\"output_text\",\"text\":\"Ready.\"}],\"phase\":\"final_answer\",\"status\":\"completed\"},{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"Reply exactly: Recovered.\"}]}],\"instructions\":\"Follow the user's exact reply instruction.\",\"store\":false,\"include\":[\"reasoning.encrypted_content\"],\"reasoning\":{\"effort\":\"medium\",\"summary\":\"auto\"},\"max_output_tokens\":30}"
+          "body": "{\"type\":\"response.create\",\"model\":\"gpt-5.5\",\"input\":[{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"Reply exactly: Ready.\"}]},{\"type\":\"reasoning\",\"id\":\"rs_01cc0cda24c36acf016aa8ca3ced8c87d1a14c5c6a2ced8544\",\"summary\":[],\"encrypted_content\":\"gAAAAABqqMo9M9B15LsV1CLsXpNJpI08GiwCAK97hTheQ2s1lAkKgARMs1HIIXVeAr-tbUq88yN51fiQE8HvGwdF9ZcNI6bZle8D2PS7m8O7UE7C1Z_HX_fz2f0pRHyRfWpVAT2gYQWIDeZu6UdgxbKPBW0lXWzlk_relHG5x6nXkYzZoEeVasqavWoyMMSX7cexe-IYJh6e_3DgRpOchueS8Z-70P0w5R83Ea7UXZQNhMA0yDEYu_td2PmE2Pd2PUTOB3mxF2pb1z7-2t6S0UryhHx0az7Gh2eT60GGUqz9CIZzNE_FX--tszeuO0eI92Cen5tirOUHBTyyDqE0eG26DRl_p_U-xDZwaQONbtYbvkvrj-G7FA2oZXxjJPHuQZsNgBslXS-H0KT1lx3Y8XJ9QMVjFLFaucFG64wCmXPfCH8dYtX_YqfYQR4lwNfiSbyJEX2oDvTVVD_aCJ9NRo7c0aCTtmKBvr6fvvAy3MAFxAp_Sm2nMx4P5GYO4qAmJDByywKw-VK1vHlv3NRmVsAgbArIFgm-axoCs2PLpvZjDqeQGPavaq8zKWTyZYqBsEzKZUtGOZfYjD4mud0Z08I4i2H4K-L00ccVauode3548ZipOIuslbhJxonQXsF6TFdW2Hj8E5JjoEr5IbmwHyI0PBcDWW5AmkjHLwr9v08mFppRoD-2wzPAd5igROAuUbvJhiQd2A-uOaohwMjdpFxrjyUqgGTlI5g7tmI1ceeQWms0bKm8Pd0wIqVM3Nq6YvV7XfEyeogfRMVUQezr_lES42ZMVAoKBSFzMysDwCFkhVNVclcTUpcUUbVp21FChG7Ag-xuq8Cl6OGLA8nWX1C0aCf2HNa-n3dkYr1DtUziurh1MD-UIs5jdGiq3ptrc0VaVZwNdD4jVfAoHB_Ws7GiISXuclfpqsG3DTJEfzlbukI1vxXrt3FArsHiQvQjW5UM7gGel32M6p8AlXRxnez9PgIuU1WrtBUJetk7m39AZwp_aqbqC-AJ-MF70xP1VJZwFN-GeNL3VZsRHePFG4h7Pj---CCZRGlmzuE1-b-sIE7Bn_gbue_qHFMZJhAY55MO25vfZbSoLWHZCGmLMjJVHOYCPoy6l7zyxNmoIcC58QILNWal31KLCDmCsASmZC-xQRjyFwt-kvLbvk38Dc02IKcP3ujhf6WRRr1A0hh1K-gXmv_XI_MUFDcOVIjjhB-rXgjWSCoKfaKI9GCIsb9mnNaBq65BWg==\"},{\"type\":\"message\",\"id\":\"msg_01cc0cda24c36acf016aa8ca3d4a0087d1950121aed4802434\",\"role\":\"assistant\",\"content\":[{\"type\":\"output_text\",\"text\":\"Ready.\"}],\"phase\":\"final_answer\",\"status\":\"completed\"},{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"Reply exactly: Recovered.\"}]}],\"instructions\":\"Follow the user's exact reply instruction.\",\"store\":false,\"include\":[\"reasoning.encrypted_content\"],\"reasoning\":{\"effort\":\"medium\",\"summary\":\"auto\"},\"text\":{\"verbosity\":\"low\"},\"max_output_tokens\":30}"
        },
        {
          "direction": "server",
@@ -26,7 +26,7 @@
        "headers": {
          "content-type": "application/json"
        },
-        "body": "{\"model\":\"gpt-5.5\",\"input\":[{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"Think briefly, then reply exactly with: Hello!\"}]}],\"instructions\":\"Show concise reasoning when the provider supports visible reasoning summaries.\",\"store\":false,\"include\":[\"reasoning.encrypted_content\"],\"reasoning\":{\"effort\":\"low\",\"summary\":\"auto\"},\"max_output_tokens\":120,\"stream\":true}"
+        "body": "{\"model\":\"gpt-5.5\",\"input\":[{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"Think briefly, then reply exactly with: Hello!\"}]}],\"instructions\":\"Show concise reasoning when the provider supports visible reasoning summaries.\",\"store\":false,\"include\":[\"reasoning.encrypted_content\"],\"reasoning\":{\"effort\":\"low\",\"summary\":\"auto\"},\"text\":{\"verbosity\":\"low\"},\"max_output_tokens\":120,\"stream\":true}"
      },
      "response": {
        "status": 200,
@@ -44,7 +44,7 @@
        "headers": {
          "content-type": "application/json"
        },
-        "body": "{\"model\":\"gpt-5.5\",\"input\":[{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"Think briefly, then reply exactly with: Hello!\"}]},{\"type\":\"reasoning\",\"id\":\"rs_052e7ec551f55289016aa8c8d63eac87d19d6b921611f123e7\",\"summary\":[],\"encrypted_content\":\"gAAAAABqqMjWZ2Eei8_Gf-5FeEFAYp-gSzFL4D4lQBKL_fyyTYXv5iJ-2jql1mOq0wZpqHL8O9MWxebQGW56Ahd-p21qrDD52CyUBqKKlF87eC1d-cTgjXQlFMsPxvwyQeuU6A2l8tanTtJ48sKtzZtHrDuBXZ35u-lONnovjFGMX3Q83xoqG_um_w5rT420TA_SyU4fGt7oiQvOPS1q4PNo97O824oRnI7n_BC1jPYCaJhl2I1rPJg4afuOpjG-u7JcXRD4JPwZdqMa5o2d0uDKHuUYwP25qiPKKDqTTqFka5cDJjZNPF3ZkVHR-cagjZGvMnizXXxgUpPJ9j83gqY4QJLKCkzcaBj9H7mAL-v9yl4I5kn_9_DhpMILs2SZkC8AvIYNgmel3sDV_BG4XZ2JXciZz86ukQ6DwXgQqS4HOB91g-sGHOWMU1ohsZlEvvJBjGkJ_rAdXVMqAbvi2zvE3_NI4sTAGUrIugGJePrQYTe8gqL8f9NsYac6pzHNQL1e_jQNUvp49bu7EsPzCP3KPYVvZCFohDdwe7sMd6wrztrCJwM4CLdAQK61A7sYzU0HyglLtPidmS5QkSmV6U_xgih7JbKnY0oAeCyYw4ADYqdNTi0axmBErh-lbh-XKNG_TnoMa-2IS3X041N8OsDfSdQp3QsAm53fF8seQuLFa27Iaq2etMj3yGeqWVjA-Mae3K34mt2YPGjQ-HbIOMVmYXBLzNr-s2fT35Sp6SDEsFyvzXb0Vij58s1wW5zkuKgaJiroGgkY86NImuaa3_-wpMK3_9O_wwAbRwV4uBCVzT_rY6rDQHR9-VkM0MbGK8drbdtjXwy3KtAzkux4N4g2nadYU0IIIEUNj_JChUFSHC7VRg7L7LpZMgAFGwHmaUyzQt31LyiVix9WFtcKfBgzehoRV6vstln-oBRd-vFjUW-7WLm7R_lFNHQZ0CKUvKCSpQxdIevczpYT0_lQiDU7Rfp1UBBnicndpq4YQwgRppdZX-QHG5IZxxHNWYdIBtn3eO3ooDXmI-rYryyVcFG6VY5xqssf8GgXqgNy84X_SgYfhGmNiPPQTl5wIBa49f1sxAI-7ri1xLr6FJhQMasOoxm_VuZYNkq6NrAXprtKa70cBRpm1wWBNcPdMul4GNMDQatQZRDENcNLe45iMX-HB1YYSvyc-y5rfSJkP4EgKXC-OqcrzxAlRfB3Bm4jOQL_PSsNBbh26CWAdAYSftM88fbnuqZX2w==\"},{\"type\":\"message\",\"role\":\"assistant\",\"content\":[{\"type\":\"output_text\",\"text\":\"Hello!\"}],\"status\":\"completed\"},{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"Now reply exactly with: Done.\"}]}],\"store\":false,\"include\":[\"reasoning.encrypted_content\"],\"reasoning\":{\"effort\":\"low\",\"summary\":\"auto\"},\"max_output_tokens\":40,\"stream\":true}"
+        "body": "{\"model\":\"gpt-5.5\",\"input\":[{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"Think briefly, then reply exactly with: Hello!\"}]},{\"type\":\"reasoning\",\"id\":\"rs_052e7ec551f55289016aa8c8d63eac87d19d6b921611f123e7\",\"summary\":[],\"encrypted_content\":\"gAAAAABqqMjWZ2Eei8_Gf-5FeEFAYp-gSzFL4D4lQBKL_fyyTYXv5iJ-2jql1mOq0wZpqHL8O9MWxebQGW56Ahd-p21qrDD52CyUBqKKlF87eC1d-cTgjXQlFMsPxvwyQeuU6A2l8tanTtJ48sKtzZtHrDuBXZ35u-lONnovjFGMX3Q83xoqG_um_w5rT420TA_SyU4fGt7oiQvOPS1q4PNo97O824oRnI7n_BC1jPYCaJhl2I1rPJg4afuOpjG-u7JcXRD4JPwZdqMa5o2d0uDKHuUYwP25qiPKKDqTTqFka5cDJjZNPF3ZkVHR-cagjZGvMnizXXxgUpPJ9j83gqY4QJLKCkzcaBj9H7mAL-v9yl4I5kn_9_DhpMILs2SZkC8AvIYNgmel3sDV_BG4XZ2JXciZz86ukQ6DwXgQqS4HOB91g-sGHOWMU1ohsZlEvvJBjGkJ_rAdXVMqAbvi2zvE3_NI4sTAGUrIugGJePrQYTe8gqL8f9NsYac6pzHNQL1e_jQNUvp49bu7EsPzCP3KPYVvZCFohDdwe7sMd6wrztrCJwM4CLdAQK61A7sYzU0HyglLtPidmS5QkSmV6U_xgih7JbKnY0oAeCyYw4ADYqdNTi0axmBErh-lbh-XKNG_TnoMa-2IS3X041N8OsDfSdQp3QsAm53fF8seQuLFa27Iaq2etMj3yGeqWVjA-Mae3K34mt2YPGjQ-HbIOMVmYXBLzNr-s2fT35Sp6SDEsFyvzXb0Vij58s1wW5zkuKgaJiroGgkY86NImuaa3_-wpMK3_9O_wwAbRwV4uBCVzT_rY6rDQHR9-VkM0MbGK8drbdtjXwy3KtAzkux4N4g2nadYU0IIIEUNj_JChUFSHC7VRg7L7LpZMgAFGwHmaUyzQt31LyiVix9WFtcKfBgzehoRV6vstln-oBRd-vFjUW-7WLm7R_lFNHQZ0CKUvKCSpQxdIevczpYT0_lQiDU7Rfp1UBBnicndpq4YQwgRppdZX-QHG5IZxxHNWYdIBtn3eO3ooDXmI-rYryyVcFG6VY5xqssf8GgXqgNy84X_SgYfhGmNiPPQTl5wIBa49f1sxAI-7ri1xLr6FJhQMasOoxm_VuZYNkq6NrAXprtKa70cBRpm1wWBNcPdMul4GNMDQatQZRDENcNLe45iMX-HB1YYSvyc-y5rfSJkP4EgKXC-OqcrzxAlRfB3Bm4jOQL_PSsNBbh26CWAdAYSftM88fbnuqZX2w==\"},{\"type\":\"message\",\"role\":\"assistant\",\"content\":[{\"type\":\"output_text\",\"text\":\"Hello!\"}],\"status\":\"completed\"},{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"Now reply exactly with: Done.\"}]}],\"store\":false,\"include\":[\"reasoning.encrypted_content\"],\"reasoning\":{\"effort\":\"low\",\"summary\":\"auto\"},\"text\":{\"verbosity\":\"low\"},\"max_output_tokens\":40,\"stream\":true}"
      },
      "response": {
        "status": 200,
@@ -24,7 +24,7 @@
        "headers": {
          "content-type": "application/json"
        },
-        "body": "{\"model\":\"gpt-5.5\",\"input\":[{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"Think briefly, then reply exactly with: Hello!\"}]}],\"instructions\":\"Show concise reasoning when the provider supports visible reasoning summaries.\",\"store\":false,\"include\":[\"reasoning.encrypted_content\"],\"reasoning\":{\"effort\":\"low\",\"summary\":\"auto\"},\"max_output_tokens\":120,\"stream\":true}"
+        "body": "{\"model\":\"gpt-5.5\",\"input\":[{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"Think briefly, then reply exactly with: Hello!\"}]}],\"instructions\":\"Show concise reasoning when the provider supports visible reasoning summaries.\",\"store\":false,\"include\":[\"reasoning.encrypted_content\"],\"reasoning\":{\"effort\":\"low\",\"summary\":\"auto\"},\"text\":{\"verbosity\":\"low\"},\"max_output_tokens\":120,\"stream\":true}"
      },
      "response": {
        "status": 200,
@@ -25,7 +25,7 @@
        "headers": {
          "content-type": "application/json"
        },
-        "body": "{\"model\":\"gpt-5.5\",\"input\":[{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"What is the weather in Paris?\"}]}],\"instructions\":\"Use the get_weather tool exactly once. After the tool result, reply exactly: Paris is sunny.\",\"tools\":[{\"type\":\"function\",\"name\":\"get_weather\",\"description\":\"Get current weather for a city.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false},\"strict\":false}],\"store\":false,\"include\":[\"reasoning.encrypted_content\"],\"reasoning\":{\"effort\":\"medium\",\"summary\":\"auto\"},\"max_output_tokens\":80,\"stream\":true}"
+        "body": "{\"model\":\"gpt-5.5\",\"input\":[{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"What is the weather in Paris?\"}]}],\"instructions\":\"Use the get_weather tool exactly once. After the tool result, reply exactly: Paris is sunny.\",\"tools\":[{\"type\":\"function\",\"name\":\"get_weather\",\"description\":\"Get current weather for a city.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false},\"strict\":false}],\"store\":false,\"include\":[\"reasoning.encrypted_content\"],\"reasoning\":{\"effort\":\"medium\",\"summary\":\"auto\"},\"text\":{\"verbosity\":\"low\"},\"max_output_tokens\":80,\"stream\":true}"
      },
      "response": {
        "status": 200,
@@ -43,7 +43,7 @@
        "headers": {
          "content-type": "application/json"
        },
-        "body": "{\"model\":\"gpt-5.5\",\"input\":[{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"What is the weather in Paris?\"}]},{\"type\":\"function_call\",\"id\":\"fc_09525c04931d1487016aa8c8d8e12887d193bd327a0f313bd7\",\"call_id\":\"call_p57PJbKe0bX44nj908fpHdRn\",\"name\":\"get_weather\",\"arguments\":\"{\\\"city\\\":\\\"Paris\\\"}\"},{\"type\":\"function_call_output\",\"call_id\":\"call_p57PJbKe0bX44nj908fpHdRn\",\"output\":\"{\\\"temperature\\\":22,\\\"condition\\\":\\\"sunny\\\"}\"}],\"instructions\":\"Use the get_weather tool exactly once. After the tool result, reply exactly: Paris is sunny.\",\"tools\":[{\"type\":\"function\",\"name\":\"get_weather\",\"description\":\"Get current weather for a city.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false},\"strict\":false}],\"store\":false,\"include\":[\"reasoning.encrypted_content\"],\"reasoning\":{\"effort\":\"medium\",\"summary\":\"auto\"},\"max_output_tokens\":80,\"stream\":true}"
+        "body": "{\"model\":\"gpt-5.5\",\"input\":[{\"type\":\"message\",\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"What is the weather in Paris?\"}]},{\"type\":\"function_call\",\"id\":\"fc_09525c04931d1487016aa8c8d8e12887d193bd327a0f313bd7\",\"call_id\":\"call_p57PJbKe0bX44nj908fpHdRn\",\"name\":\"get_weather\",\"arguments\":\"{\\\"city\\\":\\\"Paris\\\"}\"},{\"type\":\"function_call_output\",\"call_id\":\"call_p57PJbKe0bX44nj908fpHdRn\",\"output\":\"{\\\"temperature\\\":22,\\\"condition\\\":\\\"sunny\\\"}\"}],\"instructions\":\"Use the get_weather tool exactly once. After the tool result, reply exactly: Paris is sunny.\",\"tools\":[{\"type\":\"function\",\"name\":\"get_weather\",\"description\":\"Get current weather for a city.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false},\"strict\":false}],\"store\":false,\"include\":[\"reasoning.encrypted_content\"],\"reasoning\":{\"effort\":\"medium\",\"summary\":\"auto\"},\"text\":{\"verbosity\":\"low\"},\"max_output_tokens\":80,\"stream\":true}"
      },
      "response": {
        "status": 200,
@@ -97,26 +97,6 @@ describe("Generation", () => {
    }),
  )

-  it.effect("fails an event stream at the deadline when the poll interval is longer than the timeout", () =>
-    Effect.gen(function* () {
-      const scripted = yield* scriptedRoute(["running"], "never")
-      const generation = new Generation(scripted.route, "t", { id: "gen_1", status: "queued" })
-
-      const fiber = yield* Effect.forkChild(
-        generation
-          .events({ poll: { interval: "30 seconds", timeout: "10 seconds" } })
-          .pipe(Stream.runCollect, Effect.flip),
-      )
-      yield* TestClock.adjust("9 seconds")
-      expect(fiber.pollUnsafe()).toBeUndefined()
-      yield* TestClock.adjust("1 second")
-      const error = yield* Fiber.join(fiber)
-
-      expect(error.reason._tag).toBe("Timeout")
-      expect(yield* Ref.get(scripted.polls)).toBe(1)
-    }),
-  )
-
  it.effect("surfaces the route failure body for failed generations", () =>
    Effect.gen(function* () {
      const scripted = yield* scriptedRoute(["running", "failed"], "unused")
@@ -78,11 +78,8 @@ describe("Image", () => {
        mediaType: "image/webp",
      })
      expect(yield* response.image.bytes()).toEqual(Uint8Array.from([1, 2, 3]))
-      expect(response.image.info).toEqual({ format: "webp", width: 2048, height: 2048 })
+      expect(response.image.providerMetadata).toEqual({ openai: { revisedPrompt: "A precise robot" } })
      expect(response.usage).toMatchObject({ type: "tokens", total: 12 })
-      expect(response.providerMetadata).toEqual({
-        openai: { outputFormat: "webp", size: "2048x2048", quality: "high", background: "opaque" },
-      })
    }).pipe(
      Effect.provide(
        ImageClient.layer.pipe(
@@ -110,11 +107,8 @@ describe("Image", () => {
                })
                return input.respond(
                  JSON.stringify({
-                    data: [{ b64_json: "AQID" }, { b64_json: "BAUG" }],
+                    data: [{ b64_json: "AQID", revised_prompt: "A precise robot" }, { b64_json: "BAUG" }],
                    output_format: "webp",
-                    size: "2048x2048",
-                    quality: "high",
-                    background: "opaque",
                    usage: { input_tokens: 4, output_tokens: 8, total_tokens: 12 },
                  }),
                  { headers: { "content-type": "application/json" } },
@@ -150,7 +144,6 @@ describe("Image", () => {
        ),
      )
      expect(response.image.source).toEqual({ type: "bytes", data: Uint8Array.from([1, 2, 3]), mediaType: "image/png" })
-      expect(response.image.info).toEqual({ format: "png" })
    }),
  )

@@ -732,7 +725,6 @@ describe("Image", () => {
      const errors = yield* Effect.all(
        [
          Image.start({ model: Google.configure({ apiKey: "test" }).image("gemini-3.1-flash-image"), prompt }),
-          Image.generate({ model: Google.configure({ apiKey: "test" }).image("gemini-3.1-flash-image"), prompt, n: 2 }),
          Image.start({
            model: BlackForestLabs.configure({ apiKey: "test" }).image("flux-2-pro"),
            prompt,
@@ -743,6 +735,7 @@ describe("Image", () => {
            prompt,
            size: "512x512",
          }),
+          Stream.runCollect(Image.stream({ model: openai.image("dall-e-3"), prompt })),
          Stream.runCollect(Image.stream({ model: openai.image("gpt-image-2"), prompt, n: 2 })),
          Image.start({ model: replicate, prompt, seed: 7 }),
          Image.start({
@@ -756,9 +749,9 @@ describe("Image", () => {
      expect(errors.map((error) => [error.reason._tag, "operation" in error.reason && error.reason.operation])).toEqual(
        [
          ["UnsupportedOperation", "image.start"],
-          ["UnsupportedOperation", "media.n"],
          ["UnsupportedOperation", "media.aspectRatio"],
          ["UnsupportedOperation", "media.size"],
+          ["UnsupportedOperation", "media.stream"],
          ["UnsupportedOperation", "media.n"],
          ["UnsupportedOperation", "media.seed"],
          ["InvalidRequest", false],
@@ -768,80 +761,6 @@ describe("Image", () => {
    }).pipe(Effect.provide(layer(() => Effect.die("an unsupported request reached the network")))),
  )

-  const falToken = {
-    requestID: "r1",
-    statusURL: "https://queue.fal.test/fal-ai/flux/requests/r1/status",
-    responseURL: "https://queue.fal.test/fal-ai/flux/requests/r1",
-    cancelURL: "https://queue.fal.test/fal-ai/flux/requests/r1/cancel",
-  }
-  const falSubmitted = {
-    request_id: falToken.requestID,
-    status_url: falToken.statusURL,
-    response_url: falToken.responseURL,
-    cancel_url: falToken.cancelURL,
-  }
-  const bodies: Array<unknown> = []
-  it.effect("sizes fal Kontext by aspect ratio and sends several images to /multi", () =>
-    Effect.gen(function* () {
-      const fal = Fal.configure({ apiKey: "test", baseURL: "https://queue.fal.test" })
-      const images = [Media.url("https://example.test/a.png"), Media.url("https://example.test/b.png")]
-      const rejected = yield* Image.start({
-        model: fal.image("fal-ai/flux-pro/kontext"),
-        prompt: "A lighthouse",
-        size: "512x512",
-      }).pipe(Effect.flip)
-      yield* Image.start({
-        model: fal.image("fal-ai/flux-pro/kontext"),
-        prompt: "A lighthouse",
-        images: images.slice(0, 1),
-        aspectRatio: "16:9",
-      })
-      yield* Image.start({ model: fal.image("fal-ai/flux-pro/kontext/max/multi"), prompt: "A lighthouse", images })
-
-      expect(rejected.reason).toMatchObject({ _tag: "UnsupportedOperation", operation: "media.size" })
-      expect(bodies).toEqual([
-        { prompt: "A lighthouse", aspect_ratio: "16:9", image_url: "https://example.test/a.png" },
-        { prompt: "A lighthouse", image_urls: ["https://example.test/a.png", "https://example.test/b.png"] },
-      ])
-    }).pipe(
-      Effect.provide(
-        layer((input) => {
-          bodies.push(JSON.parse(input.text))
-          return Effect.succeed(json(input, falSubmitted))
-        }),
-      ),
-    ),
-  )
-
-  it.effect("decodes fal sync_mode data URIs as inline images", () =>
-    Effect.gen(function* () {
-      const generation = yield* Image.resume(Fal.configure({ apiKey: "test" }).image("fal-ai/flux/schnell"), falToken)
-      const response = yield* generation.await()
-
-      expect(response.images.map((image) => image.source)).toEqual([
-        { type: "base64", data: "AQID", mediaType: "image/png" },
-        { type: "url", url: "https://v3.fal.media/out.jpg", mediaType: "image/jpeg" },
-      ])
-      expect(response.image.info).toEqual({ width: 512, height: 512 })
-      expect(yield* response.image.bytes()).toEqual(Uint8Array.from([1, 2, 3]))
-    }).pipe(
-      Effect.provide(
-        layer((input) =>
-          Effect.succeed(
-            input.request.url === falToken.statusURL
-              ? json(input, { status: "COMPLETED" })
-              : json(input, {
-                  images: [
-                    { url: "data:image/png;base64,AQID", width: 512, height: 512, content_type: "image/png" },
-                    { url: "https://v3.fal.media/out.jpg", width: 512, height: 512, content_type: "image/jpeg" },
-                  ],
-                }),
-          ),
-        ),
-      ),
-    ),
-  )
-
  const moderated = { id: "req_1", status: "Content Moderated" }
  const prediction = {
    id: "p_1",
@@ -849,56 +768,6 @@ describe("Image", () => {
    output: { text: "not an image" },
    urls: { get: "https://replicate.test/p_1", cancel: "https://replicate.test/p_1/cancel" },
  }
-  for (const pending of [
-    {
-      model: BlackForestLabs.configure({ apiKey: "test" }).image("flux-2-pro"),
-      token: { id: "req_1", pollingURL: "https://bfl.test/v1/get_result?id=req_1" },
-      status: 200,
-      body: { id: "req_1", status: "Pending" },
-      message: "Black Forest Labs generation req_1",
-    },
-    {
-      model: Replicate.configure({ apiKey: "test" }).image("owner/model"),
-      token: { id: "p_1", getURL: "https://replicate.test/p_1", cancelURL: "https://replicate.test/p_1/cancel" },
-      status: 200,
-      body: {
-        id: "p_1",
-        status: "processing",
-        urls: { get: "https://replicate.test/p_1", cancel: "https://replicate.test/p_1/cancel" },
-      },
-      message: "Replicate generation p_1",
-    },
-    {
-      model: Stability.configure({ apiKey: "test", baseURL: "https://stability.test" }).upscale(),
-      token: { id: "up_1" },
-      status: 202,
-      body: { id: "up_1", status: "in-progress" },
-      message: "Stability AI generation up_1",
-    },
-  ]) {
-    it.effect(`rejects reading a ${pending.model.provider} result before the generation finishes`, () =>
-      Effect.gen(function* () {
-        const generation = yield* Image.resume(pending.model, pending.token)
-        const error = yield* generation.result().pipe(Effect.flip)
-        expect(error.reason._tag).toBe("InvalidRequest")
-        expect(error.message).toBe(`${pending.message} has not finished; await it before reading the result`)
-        expect(error.reason.body).toBe(JSON.stringify(pending.body))
-        expect(error.reason.http?.status).toBe(pending.status)
-      }).pipe(
-        Effect.provide(
-          layer((input) =>
-            Effect.succeed(
-              input.respond(JSON.stringify(pending.body), {
-                status: pending.status,
-                headers: { "content-type": "application/json" },
-              }),
-            ),
-          ),
-        ),
-      ),
-    )
-  }
-
  it.effect("classifies terminal outcomes the recordings never saw", () =>
    Effect.gen(function* () {
      const bfl = yield* Image.resume(BlackForestLabs.configure({ apiKey: "test" }).image("flux-2-pro"), {
@@ -7,6 +7,7 @@ import {
  type ImageModelOptions,
  type ImageOptions,
  type ImageRequestFor,
+  type ImageRoute,
 } from "../src/index.js"
 import type { Service } from "../src/image-client.js"
 import { Anthropic, BlackForestLabs, Google, OpenAI, Stability, XAI, ZAI } from "../src/providers.js"
@@ -20,7 +21,8 @@ type GoogleLikeOptions = {
  readonly thinkingLevel?: "LOW" | "HIGH"
 } & Record<string, unknown>

-declare const google: ImageModel<GoogleLikeOptions>
+declare const route: ImageRoute<GoogleLikeOptions>
+const google = ImageModel.make<GoogleLikeOptions>({ id: "gemini-image", provider: "google", route })
 // @ts-expect-error Extracted model options retain known provider fields.
 const invalidGoogleOptions: ImageModelOptions<typeof google> = { imageSize: "8K" }
 void invalidGoogleOptions
@@ -150,8 +152,6 @@ Image.generate({ model: zai, prompt: "A lighthouse", providerOptions: { quality:
 Image.generate({ model: zai, prompt: "A lighthouse", providerOptions: { userID: 1 } })

 declare const generic: ImageModel<ImageOptions>
-const widenImage = <Options extends ImageOptions>(model: ImageModel<Options>): ImageModel => model
-void widenImage
 Image.generate({ model: generic, prompt: "A lighthouse", providerOptions: { arbitrary: true } })
 const explicitAsset: Media.Asset = Media.url("https://example.com/image.png")
 void explicitAsset
@@ -6,7 +6,6 @@ import {
  type LanguageModelProviderOptions,
  type ProviderOptions,
 } from "../src/index.js"
-import { ai } from "../src/promise.js"
 import { OpenAIChat } from "../src/protocols.js"

 interface ExampleOptions {
@@ -32,10 +31,6 @@ const generated = LLM.generate(LLM.request({ model, prompt: "Hello" }))
 type GenerateRequirements = Assert<Equal<Requirements<typeof generated>, LLMClientService>>
 const streamed = LLM.stream(LLM.request({ model, prompt: "Hello" }))
 type StreamClientRequirements = Assert<Equal<StreamRequirements<typeof streamed>, LLMClientService>>
-const generatedFromInput = LLM.generate({ model, prompt: "Hello", providerOptions: { mode: "fast" } })
-type InputGenerateRequirements = Assert<Equal<Requirements<typeof generatedFromInput>, LLMClientService>>
-const streamedFromInput = LLM.stream({ model, prompt: "Hello", providerOptions: { mode: "thorough" } })
-type InputStreamRequirements = Assert<Equal<StreamRequirements<typeof streamedFromInput>, LLMClientService>>

 LLM.request({
  model,
@@ -44,11 +39,6 @@ LLM.request({
  providerOptions: { mode: "slow" },
 })

-// @ts-expect-error Direct input keeps the selected model's provider option types.
-LLM.generate({ model, prompt: "Hello", providerOptions: { mode: "slow" } })
-// @ts-expect-error Stream input keeps the selected model's provider option types.
-LLM.stream({ model, prompt: "Hello", providerOptions: { mode: "slow" } })
-
 const generatedObject = LLM.generateObject({
  model,
  prompt: "Hello",
@@ -79,16 +69,5 @@ const options: LanguageModelProviderOptions<typeof model> = { mode: "fast" }
 void (options satisfies LanguageModelProviderOptions<typeof model>)
 void (true satisfies GenerateRequirements)
 void (true satisfies StreamClientRequirements)
-void (true satisfies InputGenerateRequirements)
-void (true satisfies InputStreamRequirements)
 void (true satisfies GenerateObjectRequirements)
 void (true satisfies GenerateDynamicObjectRequirements)
-
-void ai.llm.generate({ model, prompt: "Hello", providerOptions: { mode: "fast" } })
-void ai.llm.stream({ model, prompt: "Hello", providerOptions: { mode: "thorough" } })
-void ai.llm.generate(ai.llm.request({ model, prompt: "Hello" }))
-void ai.llm.stream(ai.llm.request({ model, prompt: "Hello" }))
-// @ts-expect-error Promise direct input keeps the selected model's provider option types.
-void ai.llm.generate({ model, prompt: "Hello", providerOptions: { mode: "slow" } })
-// @ts-expect-error Promise stream input keeps the selected model's provider option types.
-void ai.llm.stream({ model, prompt: "Hello", providerOptions: { mode: "slow" } })
@@ -1,7 +1,6 @@
 import { describe, expect, test } from "bun:test"
-import { Effect, Schema, Stream } from "effect"
-import { CacheHint, LLM, LLMEvent, LLMResponse, ToolEntry, ToolNamespace } from "../src/index.js"
-import { OpenAI } from "../src/providers.js"
+import { Schema } from "effect"
+import { CacheHint, LLM, LLMResponse, ToolEntry, ToolNamespace } from "../src/index.js"
 import * as OpenAIChat from "../src/protocols/openai-chat.js"
 import * as OpenAIResponses from "../src/protocols/openai-responses.js"
 import {
@@ -14,8 +13,6 @@ import {
  ToolDefinition,
  ToolResultPart,
 } from "../src/schema/index.js"
-import { fixedResponse } from "./lib/http.js"
-import { sseEvents } from "./lib/sse.js"

 const chatRoute = OpenAIChat.route
 const responsesRoute = OpenAIResponses.route
@@ -243,26 +240,6 @@ describe("llm constructors", () => {
    expect(request.messages.map((message) => message.role)).toEqual(["user", "system"])
  })

-  test("generates and streams from input or a prebuilt request", async () => {
-    const model = OpenAI.configure({ apiKey: "test", baseURL: "https://openai.test/v1" }).chat("gpt-4o-mini")
-    const layer = fixedResponse(
-      sseEvents({ choices: [{ delta: { content: "Hello" } }] }, { choices: [{ delta: {}, finish_reason: "stop" }] }),
-    )
-    const input = { model, prompt: "Say hello." }
-    const request = LLM.request(input)
-    const generated = await Effect.runPromise(LLM.generate(input).pipe(Effect.provide(layer)))
-    const generatedFromRequest = await Effect.runPromise(LLM.generate(request).pipe(Effect.provide(layer)))
-    expect(generated.text).toBe("Hello")
-    expect(generatedFromRequest.text).toBe(generated.text)
-
-    const streamed = await Effect.runPromise(LLM.stream(input).pipe(Stream.runCollect, Effect.provide(layer)))
-    const streamedFromRequest = await Effect.runPromise(
-      LLM.stream(request).pipe(Stream.runCollect, Effect.provide(layer)),
-    )
-    expect(Array.from(streamed).some(LLMEvent.is.textDelta)).toBe(true)
-    expect(streamedFromRequest).toEqual(streamed)
-  })
-
  test("extracts output text from response events", () => {
    expect(
      LLMResponse.text({
@@ -3,7 +3,7 @@ import { NodeFileSystem } from "@effect/platform-node"
 import { Effect, Ref, Schema } from "effect"
 import { FileSystem } from "effect"
 import { HttpClientRequest } from "effect/unstable/http"
-import { AIError, Media, Message } from "../src/index.js"
+import { Media, Message } from "../src/index.js"
 import { it } from "./lib/effect.js"
 import { dynamicResponse, scriptedResponses } from "./lib/http.js"

@@ -161,56 +161,6 @@ describe("Media", () => {
    }),
  )

-  it.effect("keeps transient url download headers out of toJSON and AssetSchema encoding", () =>
-    Effect.sync(() => {
-      const asset = Media.url("https://cdn.example.test/video.mp4", {
-        mediaType: "video/mp4",
-        expiresAt: 42,
-        headers: { "x-goog-api-key": "secret" },
-      })
-      expect(asset.headers).toEqual({ "x-goog-api-key": "secret" })
-      const source = { type: "url", url: "https://cdn.example.test/video.mp4", mediaType: "video/mp4", expiresAt: 42 }
-
-      expect(asset.toJSON()).not.toHaveProperty("headers")
-      expect(JSON.stringify(asset)).not.toContain("secret")
-      expect(asset.toJSON().source).toEqual(source)
-
-      const encoded = Schema.encodeSync(Media.AssetSchema)(asset)
-      expect(encoded).not.toHaveProperty("headers")
-      expect(encoded.source).toEqual(source)
-
-      const codec = Schema.fromJsonString(Media.AssetSchema)
-      const json = Schema.encodeSync(codec)(asset)
-      expect(json).not.toContain("secret")
-      const restored = Schema.decodeSync(codec)(json)
-      expect(restored).toBeInstanceOf(Media.Asset)
-      expect(restored.source).toEqual(source)
-      expect(restored.expiresAt).toBe(42)
-      expect(restored.headers).toBeUndefined()
-    }),
-  )
-
-  it.effect("fails url downloads with non-2xx status as a typed AIError keeping http and body", () =>
-    Effect.gen(function* () {
-      const body = JSON.stringify({ error: { message: "file expired" } })
-      const error = yield* Media.url("https://cdn.example.test/expired.png")
-        .bytes()
-        .pipe(
-          Effect.flip,
-          Effect.provide(
-            dynamicResponse((input) =>
-              Effect.succeed(input.respond(body, { status: 404, headers: { "content-type": "application/json" } })),
-            ),
-          ),
-        )
-      expect(error).toBeInstanceOf(AIError)
-      expect(error.message).toContain("file expired")
-      expect(error.reason.http?.status).toBe(404)
-      expect(error.reason.http?.url).toBe("https://cdn.example.test/expired.png")
-      expect(error.reason.body).toBe(body)
-    }),
-  )
-
  it.effect("reads files with sniffed media types and writes materialized assets", () =>
    Effect.gen(function* () {
      const fs = yield* FileSystem.FileSystem
@@ -116,32 +116,19 @@ describe("AI promise client", () => {
    const seen: Array<string> = []
    const ai = AI.make({ layer: executor(seen) })

-    const request = ai.llm.request({ model: openai.chat("gpt-4o-mini"), prompt: "Say hello." })
-    const text = await ai.llm.generate(request)
+    const text = await ai.llm.generate({ model: openai.chat("gpt-4o-mini"), prompt: "Say hello." })
    expect(text.text).toBe("Hello world")
-    expect((await ai.llm.generate({ model: openai.chat("gpt-4o-mini"), prompt: "Say hello." })).text).toBe(
-      "Hello world",
-    )

    const image = await ai.image.generate({ model: openai.image("gpt-image-2"), prompt: "A lighthouse" })
    expect(image.image).toBeInstanceOf(Media.Asset)
    expect(image.image.mediaType).toBe("image/png")
    expect(await ai.run(image.image.bytes())).toEqual(Uint8Array.from([1, 2, 3]))
-    const requested = await ai.image.generate(
-      ai.image.request({ model: openai.image("gpt-image-2"), prompt: "A lighthouse" }),
-    )
-    expect(requested.image.mediaType).toBe("image/png")

    const deltas: Array<string> = []
-    for await (const event of ai.llm.stream(request)) {
+    for await (const event of ai.llm.stream({ model: openai.chat("gpt-4o-mini"), prompt: "Say hello." })) {
      if (LLMEvent.is.textDelta(event)) deltas.push(event.text)
    }
    expect(deltas).toEqual(["Hello", " world"])
-    const directDeltas: Array<string> = []
-    for await (const event of ai.llm.stream({ model: openai.chat("gpt-4o-mini"), prompt: "Say hello." })) {
-      if (LLMEvent.is.textDelta(event)) directDeltas.push(event.text)
-    }
-    expect(directDeltas).toEqual(deltas)

    const imageEvents: Array<string> = []
    for await (const event of ai.image.stream({ model: openai.image("gpt-image-2"), prompt: "A lighthouse" })) {
@@ -150,11 +137,8 @@ describe("AI promise client", () => {
    expect(imageEvents).toEqual(["image-partial", "image", "finish"])

    expect(seen).toEqual([
-      "https://openai.test/v1/chat/completions",
      "https://openai.test/v1/chat/completions",
      "https://openai.test/v1/images/generations",
-      "https://openai.test/v1/images/generations",
-      "https://openai.test/v1/chat/completions",
      "https://openai.test/v1/chat/completions",
      "https://openai.test/v1/images/generations",
    ])
@@ -276,27 +260,22 @@ describe("AI promise client", () => {
    const ai = AI.make({ layer: executor([]) })

    const failure = await ai.llm
-      .generate(ai.llm.request({ model: openai.responses("gpt-5"), prompt: "Hello" }))
+      .generate({ model: openai.responses("gpt-5"), prompt: "Hello" })
      .then(() => undefined)
      .catch((error: unknown) => error)
    expect(failure).toBeInstanceOf(AIError)
    expect(failure instanceof AIError && failure.reason.http?.status).toBe(404)

-    const invalidLLM = await ai.llm
-      // @ts-expect-error Invalid input must reject with AIError instead of throwing synchronously.
+    const invalid = await ai.llm
+      // @ts-expect-error Invalid input must reject with AIError, not throw synchronously.
      .generate({ model: openai.responses("gpt-5"), messages: [{ role: "bogus" }] })
      .catch((error: unknown) => error)
-    expect(invalidLLM instanceof AIError && invalidLLM.reason._tag).toBe("InvalidRequest")
-
-    const invalid = await ai.image
-      .generate({ model: openai.image("gpt-image-2"), prompt: "A lighthouse", n: 1.5 })
-      .catch((error: unknown) => error)
    expect(invalid instanceof AIError && invalid.reason._tag).toBe("InvalidRequest")

    const controller = new AbortController()
    controller.abort()
    const aborted = await ai.llm
-      .generate(ai.llm.request({ model: openai.chat("gpt-4o-mini"), prompt: "Hello" }), { signal: controller.signal })
+      .generate({ model: openai.chat("gpt-4o-mini"), prompt: "Hello" }, { signal: controller.signal })
      .then(() => "completed")
      .catch(() => "aborted")
    expect(aborted).toBe("aborted")
@@ -216,33 +216,6 @@ it.effect("Alibaba keeps native reasoning controls and future efforts on their s
  }),
 )

-it.effect("Alibaba fits explicit thinking budgets to half the output limit", () =>
-  Effect.gen(function* () {
-    const provider = Alibaba.configure({ region: "ap-southeast-1", apiKey: "fixture" })
-    const chat = (maxTokens?: number) =>
-      compileRequest(
-        LLM.request({
-          model: provider.chat("qwen3.7-plus"),
-          prompt: "hi",
-          ...(maxTokens === undefined ? {} : { generation: { maxTokens } }),
-          providerOptions: { enableThinking: true, thinkingBudget: 131_071 },
-        }),
-      ).pipe(Effect.map((prepared) => prepared.body.thinking_budget))
-    const messages = yield* compileRequest(
-      LLM.request({
-        model: provider.messages("qwen3.7-plus"),
-        prompt: "hi",
-        generation: { maxTokens: 32_000 },
-        providerOptions: { thinking: { type: "enabled", budgetTokens: 131_071 } },
-      }),
-    )
-
-    expect(yield* chat(32_000)).toBe(16_000)
-    expect(yield* chat()).toBe(131_071)
-    expect(messages.body.thinking).toEqual({ type: "enabled", budget_tokens: 16_000 })
-  }),
-)
-
 it.effect("Alibaba validates malformed options before execution", () =>
  Effect.gen(function* () {
    const provider = Alibaba.configure({ region: "ap-southeast-1", apiKey: "fixture" })
@@ -148,13 +148,11 @@ describe("Anthropic Messages route", () => {
    Effect.gen(function* () {
      const enabled = yield* compileRequest(
        LLMRequest.update(request, {
-          generation: { maxTokens: 4_096 },
          providerOptions: { thinking: { type: "enabled", budgetTokens: 1_024 } },
        }),
      )
      const legacy = yield* compileRequest(
        LLMRequest.update(request, {
-          generation: { maxTokens: 4_096 },
          providerOptions: { thinking: { type: "enabled", budget_tokens: 2_048 } },
        }),
      )
@@ -170,22 +168,6 @@ describe("Anthropic Messages route", () => {
    }),
  )

-  it.effect("fits the thinking budget to half the output limit", () =>
-    Effect.gen(function* () {
-      const thinking = (maxTokens: number) =>
-        compileRequest(
-          LLMRequest.update(request, {
-            generation: { maxTokens },
-            providerOptions: { thinking: { type: "enabled", budgetTokens: 31_999 } },
-          }),
-        ).pipe(Effect.map((prepared) => prepared.body.thinking))
-
-      expect(yield* thinking(64_000)).toEqual({ type: "enabled", budget_tokens: 31_999 })
-      expect(yield* thinking(20_000)).toEqual({ type: "enabled", budget_tokens: 10_000 })
-      expect(yield* thinking(1_500)).toEqual({ type: "enabled", budget_tokens: 1_024 })
-    }),
-  )
-
  it.effect("rejects enabled thinking without a budget", () =>
    Effect.gen(function* () {
      const error = yield* compileRequest(
@@ -244,29 +244,6 @@ describe("Bedrock Converse route", () => {
    }),
  )

-  it.effect("fits a Claude thinking budget below maxTokens", () =>
-    Effect.gen(function* () {
-      const fields = (maxTokens: number, budgetTokens: number, topK?: number) =>
-        compileRequest(
-          LLMRequest.update(baseRequest, {
-            model: AmazonBedrock.model("us.anthropic.claude-haiku-4-5-20251001-v1:0", {
-              baseURL: "https://bedrock-runtime.test",
-              apiKey: "test-bearer",
-              thinking: { type: "enabled", budgetTokens },
-            }),
-            generation: GenerationOptions.make({ maxTokens, topK }),
-          }),
-        ).pipe(Effect.map((prepared) => prepared.body.additionalModelRequestFields))
-
-      expect(yield* fields(64_000, 31_999)).toEqual({ thinking: { type: "enabled", budget_tokens: 31_999 } })
-      expect(yield* fields(20_000, 31_999, 40)).toEqual({
-        top_k: 40,
-        thinking: { type: "enabled", budget_tokens: 10_000 },
-      })
-      expect(yield* fields(1_500, 31_999)).toEqual({ thinking: { type: "enabled", budget_tokens: 1_024 } })
-    }),
-  )
-
  it.effect("omits additionalModelRequestFields when topK is unset", () =>
    Effect.gen(function* () {
      const prepared = yield* compileRequest(baseRequest)
@@ -33,8 +33,6 @@ describe("Black Forest Labs Images recorded", () => {

        expect(response.image.source.type).toBe("bytes")
        expect(dimensions(yield* response.image.bytes())).toEqual({ width: 512, height: 512 })
-        // BFL reports cost on submit only; the Ready result omits it.
-        expect(response.usage).toEqual({ type: "credits", credits: 1.4000000000000001 })
      }),
    { timeout: 15 * 60 * 1000 },
  )
@@ -22,22 +22,21 @@ testEffect(
      expect(body).toMatchObject({
        model: "fixture",
        stream: true,
-        store: true,
+        store: false,
        instructions: "Keep the context",
-        parallel_tool_calls: false,
+        parallel_tool_calls: true,
        prompt_cache_key: "session-key",
        service_tier: "priority",
        reasoning: { effort: "high", summary: "auto" },
-        context_management: [{ type: "compaction" }],
-        max_tool_calls: 1,
-        tool_choice: "required",
-        text: { verbosity: "high", format: { type: "json_object" } },
        prompt_cache_retention: "24h",
        prompt_cache_options: { mode: "session", ttl: "1h" },
        input: [{ role: "user", content: [{ type: "input_text", text: "hello" }] }, { type: "compaction_trigger" }],
      })
      expect(body.tools).toHaveLength(1)
      expect(body.tools[0].name).toBe("lookup")
+      expect(body.tool_choice).toBeUndefined()
+      expect(body.context_management).toBeUndefined()
+      expect(body.text).toBeUndefined()
      expect(body.max_output_tokens).toBeUndefined()
      expect(body.previous_response_id).toBeUndefined()
      return respond(
@@ -58,7 +57,7 @@ testEffect(
      )
    }),
  ),
-).effect("trigger keeps request controls, configured deployment, and supplied subscription headers", () =>
+).effect("trigger uses normal request preparation, configured deployment, and supplied subscription headers", () =>
  Effect.gen(function* () {
    const calls: string[] = []
    const input = LLM.request({
@@ -68,14 +67,12 @@ testEffect(
      promptCacheKey: "session-key",
      tools: [{ name: "lookup", description: "Lookup", inputSchema: { type: "object", properties: {} } }],
      toolChoice: { type: "tool", name: "lookup" },
+      generation: { maxTokens: 1 },
      providerOptions: {
        store: true,
        reasoningEffort: "high",
        reasoningSummary: "auto",
        contextManagement: [{ type: "compaction" }],
-        parallelToolCalls: false,
-        maxToolCalls: 1,
-        textVerbosity: "low",
      },
      http: {
        headers: { "chatgpt-account-id": "fixture-account", "x-codex-beta-features": "remote_compaction_v2" },
@@ -85,7 +82,8 @@ testEffect(
          prompt_cache_retention: "24h",
          prompt_cache_options: { mode: "session", ttl: "1h" },
          store: true,
-          text: { verbosity: "high", format: { type: "json_object" } },
+          stream: false,
+          text: { format: { type: "json_object" } },
          tool_choice: "required",
        },
      },
@@ -116,75 +114,6 @@ testEffect(
  }),
 )

-testEffect(
-  dynamicResponse(({ text, respond }) =>
-    Effect.sync(() => {
-      expect(JSON.parse(text).text).toEqual({ verbosity: "low", format: { type: "json_object" } })
-      return respond(sseEvents({ type: "response.completed", response: { id: "resp_1", output: [checkpoint] } }), {
-        headers: { "content-type": "text/event-stream" },
-      })
-    }),
-  ),
-).effect("keeps explicit verbosity on a trigger checkpoint for prompt cache reuse", () =>
-  LLMClient.compact(
-    LLM.request({
-      model: OpenAI.configure({ apiKey: "fixture" }).responses("gpt-5.5"),
-      prompt: "Hello.",
-      providerOptions: { textVerbosity: "low" },
-      http: { body: { text: { format: { type: "json_object" } } } },
-    }),
-    trigger,
-  ),
-)
-
-testEffect(
-  dynamicResponse(({ text, respond }) =>
-    Effect.sync(() => {
-      const body = JSON.parse(text)
-      expect(body.text).toEqual({ verbosity: "high", format: { type: "json_object" } })
-      expect(body.max_output_tokens).toBe(20_000)
-      return respond(sseEvents({ type: "response.completed", response: { id: "resp_1", output: [checkpoint] } }), {
-        headers: { "content-type": "text/event-stream" },
-      })
-    }),
-  ),
-).effect("keeps the effective body-overlay verbosity and text formatting", () =>
-  LLMClient.compact(
-    LLM.request({
-      model: OpenAI.configure({ apiKey: "fixture" }).responses("gpt-5.5"),
-      prompt: "Hello.",
-      generation: { maxTokens: 20_000 },
-      providerOptions: { textVerbosity: "low" },
-      http: { body: { text: { verbosity: "high", format: { type: "json_object" } } } },
-    }),
-    trigger,
-  ),
-)
-
-testEffect(
-  dynamicResponse(({ text, respond }) =>
-    Effect.sync(() => {
-      expect(JSON.parse(text).max_output_tokens).toBe(128)
-      return respond(JSON.stringify({ error: { message: "max_output_tokens must be at least 20000" } }), {
-        status: 400,
-        headers: { "content-type": "application/json" },
-      })
-    }),
-  ),
-).effect("passes configured output limits through and leaves rejection to the provider", () =>
-  Effect.gen(function* () {
-    const error = yield* LLMClient.compact(
-      LLM.request({
-        model: OpenAI.configure({ apiKey: "fixture" }).responses("gpt-5.5"),
-        prompt: "Hello.",
-        generation: { maxTokens: 128 },
-      }),
-      trigger,
-    ).pipe(Effect.flip)
-    expect(error.message).toContain("at least 20000")
-  }),
-)
-
 const idless = { type: "compaction", encrypted_content: "opaque" }
 testEffect(
  fixedResponse(
@@ -255,7 +184,7 @@ testEffect(fixedResponse(sseEvents({ type: "response.output_item.done", item: ch
      expect(error.reason._tag).toBe("InvalidProviderOutput")
    }),
 )
-for (const body of [{ input: [] }, { previous_response_id: "stale" }, { stream: false }]) {
+for (const body of [{ input: [] }, { previous_response_id: "stale" }]) {
  testEffect(dynamicResponse(() => Effect.die("Must reject before sending"))).effect(
    `rejects caller-supplied ${Object.keys(body)[0]} before sending trigger`,
    () =>
@@ -110,16 +110,11 @@ for (const model of [
    dynamicResponse(({ request, text, respond }) =>
      Effect.sync(() => {
        expect(new URL(request.url).pathname).toEndWith("/responses/compact")
-        expect(JSON.parse(text)).toEqual({
-          model: "fixture",
-          input: [item],
-          instructions: "Keep the context",
-          include: ["reasoning.encrypted_content"],
-        })
+        expect(JSON.parse(text)).toEqual({ model: "fixture", input: [item], instructions: "Keep the context" })
        return respond(JSON.stringify({ object: "response.compaction", output: [checkpoint] }))
      }),
    ),
-  ).effect(`${model.provider} validates tools but ignores unrelated unsupported generation settings`, () =>
+  ).effect(`${model.provider} compacts provider-specific history without lowering generation settings`, () =>
    Effect.gen(function* () {
      const request = LLM.request({
        model,
@@ -156,11 +151,6 @@ for (const model of [
      ] as const) {
        const error = yield* LLMClient.generate(candidate).pipe(Effect.flip)
        expect(error.reason._tag).toBe(tag)
-        if (candidate.tools.length > 0) {
-          const compactError = yield* LLMClient.compact(candidate).pipe(Effect.flip)
-          expect(compactError.reason._tag).toBe("InvalidRequest")
-          continue
-        }
        const response = yield* LLMClient.compact(candidate)
        expect(response.replacement[0]?.content[0]?.type).toBe("compaction")
      }
@@ -265,13 +255,6 @@ for (const overlay of [undefined, { service_tier: "priority", prompt_cache_key:
          model: "fixture",
          input: [{ type: "message", role: "user", content: [{ type: "input_text", text: "hello" }] }],
          service_tier: overlay?.service_tier ?? "flex",
-          reasoning: { effort: "low" },
-          text: { verbosity: "low", format: { type: "json_object" } },
-          include: ["reasoning.encrypted_content"],
-          parallel_tool_calls: false,
-          tools: [
-            { type: "function", name: "lookup", description: "Lookup", parameters: { type: "object" }, strict: false },
-          ],
          prompt_cache_key: overlay?.prompt_cache_key ?? "affinity",
          prompt_cache_retention: "24h",
          prompt_cache_options: { mode: "explicit", ttl: "30m" },
@@ -285,20 +268,12 @@ for (const overlay of [undefined, { service_tier: "priority", prompt_cache_key:
        model: OpenAI.configure({ apiKey: "test" }).responses("fixture"),
        prompt: "hello",
        promptCacheKey: "affinity",
-        providerOptions: {
-          serviceTier: "flex",
-          reasoningEffort: "low",
-          textVerbosity: "low",
-          include: ["reasoning.encrypted_content"],
-          parallelToolCalls: false,
-        },
+        providerOptions: { serviceTier: "flex" },
        generation: { maxTokens: 100 },
-        tools: [{ name: "lookup", description: "Lookup", inputSchema: {} }],
        http: {
          body: {
            stream: true,
            store: false,
-            text: { format: { type: "json_object" } },
            prompt_cache_retention: "24h",
            prompt_cache_options: { mode: "explicit", ttl: "30m" },
            ...overlay,
@@ -421,8 +396,6 @@ for (const model of [
            model: model.id,
            input: [{ type: "message", role: "user", content: [{ type: "input_text", text: "original" }] }],
            instructions: "system",
-            include: ["reasoning.encrypted_content"],
-            ...(model.id === "gpt-5.3-codex" ? { reasoning: { effort: "medium", summary: "auto" } } : {}),
          })
          return respond(
            JSON.stringify({
@@ -434,10 +407,7 @@ for (const model of [
          )
        }
        expect(new URL(request.url).pathname.endsWith("/responses")).toBe(true)
-        expect(body.input).toEqual([
-          ...output,
-          { type: "message", role: "user", content: [{ type: "input_text", text: "continue" }] },
-        ])
+        expect(body.input).toEqual([...output, { type: "message", role: "user", content: [{ type: "input_text", text: "continue" }] }])
        return respond(sseEvents({ type: "response.completed", response: { id: "resp_1", output: [] } }), {
          headers: { "content-type": "text/event-stream" },
        })
@@ -90,23 +90,6 @@ describe("Gemini route", () => {
    }),
  )

-  it.effect("fits the thinking budget to half the output limit", () =>
-    Effect.gen(function* () {
-      const thinkingBudget = (budget: number, maxTokens = 32_000) =>
-        compileRequest(
-          LLMRequest.update(request, {
-            generation: { maxTokens },
-            providerOptions: { thinkingConfig: { thinkingBudget: budget } },
-          }),
-        ).pipe(Effect.map((prepared) => prepared.body.generationConfig?.thinkingConfig?.thinkingBudget))
-
-      expect(yield* thinkingBudget(32_768)).toBe(16_000)
-      expect(yield* thinkingBudget(8_000)).toBe(8_000)
-      expect(yield* thinkingBudget(-1)).toBe(-1)
-      expect(yield* thinkingBudget(8_192, 1_000)).toBe(512)
-    }),
-  )
-
  it.effect("forwards standard Gemini generation options", () =>
    Effect.gen(function* () {
      const prepared = yield* compileRequest(
@@ -29,11 +29,7 @@ describe("OpenAI Images recorded", () => {

      expect(response.images).toHaveLength(1)
      expect(response.image.mediaType).toBe("image/jpeg")
-      expect(response.image.info).toEqual({ format: "jpeg", width: 1024, height: 1024 })
      expect((yield* response.image.bytes()).length).toBeGreaterThan(0)
-      expect(response.providerMetadata).toEqual({
-        openai: { outputFormat: "jpeg", size: "1024x1024", quality: "low", background: "opaque" },
-      })
    }),
  )

@@ -80,13 +76,8 @@ describe("OpenAI Images recorded", () => {
      expect(events.map((event) => event.type)).toEqual(["image-partial", "image", "finish"])
      const image = events.find(ImageEvent.is.image)
      expect(image?.image.mediaType).toBe("image/jpeg")
-      expect(image?.image.info).toEqual({ format: "jpeg", width: 1024, height: 1024 })
      expect(dimensions(yield* image!.image.bytes())).toEqual({ width: 1024, height: 1024 })
-      const finish = events.find(ImageEvent.is.finish)
-      expect(finish?.usage).toMatchObject({ type: "tokens" })
-      expect(finish?.providerMetadata).toEqual({
-        openai: { outputFormat: "jpeg", size: "1024x1024", quality: "low", background: "opaque" },
-      })
+      expect(events.find(ImageEvent.is.finish)?.usage).toMatchObject({ type: "tokens" })
    }),
  )
 })
@@ -1945,7 +1945,7 @@ describe("OpenAI Responses route", () => {
      expect(prepared.body.prompt_cache_key).toBe("session_123")
      expect(prepared.body.include).toEqual(["reasoning.encrypted_content"])
      expect(prepared.body.reasoning).toEqual({ effort: "high", summary: "auto" })
-      expect(prepared.body.text).toBeUndefined()
+      expect(prepared.body.text).toEqual({ verbosity: "low" })
      expect(prepared.body.metadata).toEqual({ environment: "test", tenant: "acme" })
      expect(prepared.body.safety_identifier).toBe("user_123")
      expect(prepared.body.stream_options).toEqual({ include_obfuscation: false })
@@ -44,12 +44,7 @@ describe("OpenAI Transcription recorded", () => {
      expect(deltas.length).toBeGreaterThan(1)
      expect(deltas.join("")).toBe(finish.text)
      expect(finish.text).toMatch(TRANSCRIPT)
-      expect(finish.usage).toMatchObject({
-        type: "tokens",
-        input: expect.any(Number),
-        output: expect.any(Number),
-        details: { openai: { input_token_details: { audio_tokens: expect.any(Number) } } },
-      })
+      expect(finish.usage).toMatchObject({ type: "tokens", input: expect.any(Number), output: expect.any(Number) })
    }),
  )

@@ -152,27 +152,6 @@ describe("OpenRouter", () => {
    }),
  )

-  it.effect("fits the reasoning budget to half the output limit", () =>
-    Effect.gen(function* () {
-      const reasoning = (maxTokens: number | undefined, value: Record<string, unknown>) =>
-        compileRequest(
-          LLM.request({
-            model: OpenRouter.configure({ apiKey: "test-key" }).model("qwen/qwen3.8-flash"),
-            cache: "none",
-            prompt: "Hello",
-            ...(maxTokens === undefined ? {} : { generation: { maxTokens } }),
-            providerOptions: { reasoning: value },
-          }),
-        ).pipe(Effect.map((prepared) => prepared.body.reasoning))
-
-      expect(yield* reasoning(32_000, { max_tokens: 131_071 })).toEqual({ max_tokens: 16_000 })
-      expect(yield* reasoning(131_072, { max_tokens: 65_536 })).toEqual({ max_tokens: 65_536 })
-      expect(yield* reasoning(1_500, { max_tokens: 65_536 })).toEqual({ max_tokens: 1_024 })
-      expect(yield* reasoning(undefined, { max_tokens: 131_071 })).toEqual({ max_tokens: 131_071 })
-      expect(yield* reasoning(32_000, { effort: "high" })).toEqual({ effort: "high" })
-    }),
-  )
-
  it.effect("applies OpenRouter payload options from the model helper", () =>
    Effect.gen(function* () {
      const prepared = yield* compileRequest(
@@ -32,12 +32,7 @@ describe("Z.ai Images", () => {

      expect(response.images).toHaveLength(1)
      expect(response.image.mediaType).toBe("application/octet-stream")
-      // Z.ai documents that output URLs expire 30 days after generation; the test clock starts at 0.
-      expect(response.image.source).toEqual({
-        type: "url",
-        url: "https://cdn.z.ai/generated.png",
-        expiresAt: 30 * 24 * 60 * 60 * 1000,
-      })
+      expect(response.image.source).toEqual({ type: "url", url: "https://cdn.z.ai/generated.png" })
      expect(response.notices).toEqual([
        {
          type: "moderated",
@@ -28,49 +28,10 @@ const cartesia = Cartesia.configure({ apiKey: "test", baseURL: "https://cartesia
 const google = Google.configure({ apiKey: "test", baseURL: "https://google.test/v1beta" }).speech(
  "gemini-2.5-flash-preview-tts",
 )
-const google38 = Google.configure({ apiKey: "test", baseURL: "https://google.test/v1beta" }).speech(
-  "gemini-3.8-flash-tts",
-)
-const google38Lite = Google.configure({ apiKey: "test", baseURL: "https://google.test/v1beta" }).speech(
-  "gemini-3.8-flash-lite-tts",
-)
 const deepgram = Deepgram.configure({ apiKey: "test", baseURL: "https://deepgram.test" }).speech("aura-2-thalia-en")
 const voice = "JBFqnCBsd6RMkjVDRZzb"

 describe("Speech", () => {
-  it.effect("preserves Google's WAV output instead of describing it as raw PCM", () =>
-    Effect.gen(function* () {
-      const bytes = new TextEncoder().encode("RIFF....WAVEfmt ")
-      const response = yield* Speech.generate({ model: google38, text: "Hi" }).pipe(
-        Effect.provide(
-          respond(
-            JSON.stringify({
-              candidates: [
-                { content: { parts: [{ inlineData: { mimeType: "audio/wav", data: Encoding.encodeBase64(bytes) } }] } },
-              ],
-            }),
-            "application/json",
-          ),
-        ),
-      )
-      expect(response.audio.mediaType).toBe("audio/wav")
-      expect(response.audio.info?.format).toBe("wav")
-      expect(response.audio.info?.encoding).toBeUndefined()
-      expect(yield* response.audio.bytes()).toEqual(bytes)
-    }),
-  )
-
-  it.effect("rejects raw PCM for Gemini 3.8 unary requests before sending", () =>
-    Effect.gen(function* () {
-      const errors = yield* Effect.all(
-        [google38, google38Lite].map((model) =>
-          Speech.generate({ model, text: "Hi", format: "pcm" }).pipe(Effect.flip),
-        ),
-      ).pipe(Effect.provide(layer(() => Effect.die("An unsupported request reached the network"))))
-      expect(errors.map((error) => error.reason._tag)).toEqual(["UnsupportedOperation", "UnsupportedOperation"])
-    }),
-  )
-
  it.effect("rejects what a provider cannot produce before sending anything", () =>
    Effect.gen(function* () {
      const errors = yield* Effect.all(
@@ -97,42 +58,6 @@ describe("Speech", () => {
    }).pipe(Effect.provide(layer(() => Effect.die("an unsupported request reached the network")))),
  )

-  it.effect("treats timestamps: false as not asking for timestamps on routes that cannot return them", () =>
-    Effect.gen(function* () {
-      const bytes = Uint8Array.from([1, 2, 3])
-      const gemini = JSON.stringify({
-        candidates: [
-          { content: { parts: [{ inlineData: { mimeType: "audio/L16;codec=pcm;rate=24000", data: "AQID" } }] } },
-        ],
-      })
-      const responses = yield* Effect.all([
-        Speech.generate({ model: openai, text: "Hi", timestamps: false }).pipe(
-          Effect.provide(respond(new Blob([bytes]).stream(), "audio/mpeg")),
-        ),
-        Speech.generate({ model: google, text: "Hi", timestamps: false }).pipe(
-          Effect.provide(respond(gemini, "application/json")),
-        ),
-        Speech.generate({ model: deepgram, text: "Hi", timestamps: false }).pipe(
-          Effect.provide(respond(new Blob([bytes]).stream(), "audio/mpeg")),
-        ),
-      ])
-      for (const response of responses) expect(yield* response.audio.bytes()).toEqual(bytes)
-
-      const errors = yield* Effect.all(
-        [openai, google, deepgram].map((model) =>
-          Speech.generate({ model, text: "Hi", timestamps: true }).pipe(Effect.flip),
-        ),
-      ).pipe(Effect.provide(layer(() => Effect.die("an unsupported request reached the network"))))
-      expect(errors.map((error) => [error.reason._tag, "operation" in error.reason && error.reason.operation])).toEqual(
-        [
-          ["UnsupportedOperation", "media.timestamps"],
-          ["UnsupportedOperation", "media.timestamps"],
-          ["UnsupportedOperation", "media.timestamps"],
-        ],
-      )
-    }),
-  )
-
  it.effect("classifies stream failures and keeps the provider payload and HTTP context", () =>
    Effect.gen(function* () {
      const badFrame = JSON.stringify({ type: "speech.audio.delta", audio: "not base64!" })
@@ -1,5 +1,5 @@
 import type { Stream } from "effect"
-import { Speech, SpeechModel, type SpeechEvent, type SpeechOptions } from "../src/index.js"
+import { Speech, type SpeechEvent } from "../src/index.js"
 import { ElevenLabs, OpenAI, Runway } from "../src/providers.js"

 type StreamItem<T> = T extends Stream.Stream<infer A, infer _E, infer _R> ? A : never
@@ -7,8 +7,6 @@ type Equal<A, B> = [A, B] extends [B, A] ? true : false
 type Assert<T extends true> = T

 const elevenlabs = ElevenLabs.configure({ apiKey: "test" }).speech("eleven_flash_v2_5")
-const widenSpeech = <Options extends SpeechOptions>(model: SpeechModel<Options>): SpeechModel => model
-void widenSpeech

 Speech.generate({
  model: elevenlabs,
@@ -5,7 +5,7 @@ import { HttpClientRequest } from "effect/unstable/http"
 import { Media, Transcription, TranscriptionClient } from "../src/index.js"
 import { AssemblyAI, Deepgram, Google, OpenAI } from "../src/providers.js"
 import { it } from "./lib/effect.js"
-import { dynamicResponse, json, observe, type Call } from "./lib/http.js"
+import { dynamicResponse } from "./lib/http.js"

 const layer = (handler: Parameters<typeof dynamicResponse>[0]) =>
  TranscriptionClient.layer.pipe(Layer.provideMerge(dynamicResponse(handler)))
@@ -25,6 +25,7 @@ describe("Transcription", () => {
    Effect.gen(function* () {
      const errors = yield* Effect.all(
        [
+          Stream.runCollect(Transcription.stream({ model: openai.transcription("whisper-1"), audio })),
          Transcription.generate({ model: openai.transcription("gpt-4o-mini-transcribe"), audio, diarize: true }),
          Transcription.generate({ model: openai.transcription("gpt-4o-mini-transcribe"), audio, timestamps: "word" }),
          Transcription.generate({ model: openai.transcription("gpt-4o-transcribe-diarize"), audio, prompt: "Names" }),
@@ -52,6 +53,7 @@ describe("Transcription", () => {
      )
      expect(errors.map((error) => [error.reason._tag, "operation" in error.reason && error.reason.operation])).toEqual(
        [
+          ["UnsupportedOperation", "media.stream"],
          ["UnsupportedOperation", "media.diarize"],
          ["UnsupportedOperation", "media.timestamps"],
          ["UnsupportedOperation", "media.prompt"],
@@ -68,67 +70,6 @@ describe("Transcription", () => {
    }).pipe(Effect.provide(layer(() => Effect.die("an unsupported request reached the network")))),
  )

-  it.effect("ignores unknown OpenAI stream events and fails on an error event with the frame", () =>
-    Effect.gen(function* () {
-      const sse = (...frames: ReadonlyArray<string>) => frames.map((frame) => `data: ${frame}\n\n`).join("")
-      const failure = `{"type":"error","error":{"type":"server_error","code":"server_error","message":"The server had an error"}}`
-      const bodies = [
-        sse(
-          `{"type":"transcript.text.delta","delta":"Hi"}`,
-          `{"type":"transcript.text.future","payload":1}`,
-          `{"type":"transcript.text.done","text":"Hi"}`,
-          "[DONE]",
-        ),
-        sse(`{"type":"transcript.text.delta","delta":"Hi"}`, failure),
-      ]
-      const model = openai.transcription("gpt-4o-mini-transcribe")
-      const program = Effect.gen(function* () {
-        const events = Array.from(yield* Stream.runCollect(Transcription.stream({ model, audio })))
-        const error = yield* Stream.runCollect(Transcription.stream({ model, audio })).pipe(Effect.flip)
-        return { events, error }
-      })
-      const { events, error } = yield* program.pipe(
-        Effect.provide(
-          layer((input) =>
-            Effect.sync(() =>
-              input.respond(bodies.shift() ?? "", { headers: { "content-type": "text/event-stream" } }),
-            ),
-          ),
-        ),
-      )
-
-      expect(events.map((event) => event.type)).toEqual(["text-delta", "finish"])
-      expect(error.reason).toMatchObject({ _tag: "ProviderInternal", body: failure })
-      expect(error.message).toContain("The server had an error")
-    }),
-  )
-
-  it.effect("streams whisper-1 as a single finish from a plain request", () =>
-    Effect.gen(function* () {
-      const bodies: Array<string> = []
-      const events = Array.from(
-        yield* Stream.runCollect(Transcription.stream({ model: openai.transcription("whisper-1"), audio })).pipe(
-          Effect.provide(
-            layer((input) =>
-              Effect.sync(() => {
-                bodies.push(input.text)
-                return input.respond(
-                  JSON.stringify({ text: "Hello there.", usage: { type: "duration", seconds: 2 } }),
-                  { headers: { "content-type": "application/json" } },
-                )
-              }),
-            ),
-          ),
-        ),
-      )
-
-      expect(bodies[0]).not.toContain('name="stream"')
-      expect(events).toEqual([
-        expect.objectContaining({ type: "finish", text: "Hello there.", usage: { type: "seconds", seconds: 2 } }),
-      ])
-    }),
-  )
-
  it.effect(
    "uploads inline audio to AssemblyAI, resumes polling from a persisted token, and surfaces failed transcripts",
    () =>
@@ -230,45 +171,4 @@ describe("Transcription", () => {
        expect(failure.reason).toMatchObject({ _tag: "ProviderInternal", body: failed })
      }),
  )
-
-  it.effect("enables AssemblyAI speaker labels when only an expected speaker count is given", () =>
-    Effect.gen(function* () {
-      const calls: Array<Call> = []
-      yield* Transcription.start({ model: assemblyai, audio: Media.url("https://a.test/call.mp3"), speakers: 2 }).pipe(
-        Effect.provide(
-          layer((input) => observe(calls, input).pipe(Effect.as(json(input, { id: "tr_1", status: "queued" })))),
-        ),
-      )
-      expect(calls.map((call) => JSON.parse(call.body))).toEqual([
-        {
-          audio_url: "https://a.test/call.mp3",
-          speech_models: ["universal-3-5-pro"],
-          language_detection: true,
-          speaker_labels: true,
-          speakers_expected: 2,
-        },
-      ])
-    }),
-  )
-
-  it.effect("rejects reading an AssemblyAI result before the transcript finishes", () =>
-    Effect.gen(function* () {
-      const generation = yield* Transcription.resume(assemblyai, { transcriptID: "tr_1" })
-      const error = yield* generation.result().pipe(Effect.flip)
-      expect(error.reason._tag).toBe("InvalidRequest")
-      expect(error.message).toBe("AssemblyAI generation tr_1 has not finished; await it before reading the result")
-      expect(error.reason.body).toBe(JSON.stringify({ id: "tr_1", status: "processing" }))
-      expect(error.reason.http?.status).toBe(200)
-    }).pipe(
-      Effect.provide(
-        layer((input) =>
-          Effect.succeed(
-            input.respond(JSON.stringify({ id: "tr_1", status: "processing" }), {
-              headers: { "content-type": "application/json" },
-            }),
-          ),
-        ),
-      ),
-    ),
-  )
 })
@@ -1,11 +1,5 @@
 import type { Stream } from "effect"
-import {
-  Media,
-  Transcription,
-  TranscriptionModel,
-  type TranscriptionEvent,
-  type TranscriptionOptions,
-} from "../src/index.js"
+import { Media, Transcription, type TranscriptionEvent } from "../src/index.js"
 import { AssemblyAI, Deepgram, OpenAI } from "../src/providers.js"

 type StreamItem<T> = T extends Stream.Stream<infer A, infer _E, infer _R> ? A : never
@@ -14,10 +8,6 @@ type Assert<T extends true> = T

 const audio = Media.url("https://example.com/call.mp3")
 const deepgram = Deepgram.configure({ apiKey: "test" }).transcription("nova-3")
-const widenTranscription = <Options extends TranscriptionOptions>(
-  model: TranscriptionModel<Options>,
-): TranscriptionModel => model
-void widenTranscription

 Transcription.generate({
  model: deepgram,
@@ -576,7 +576,7 @@ describe("Video / Runway", () => {
  const model = runway.video("gen4.5")
  const taskUrl = "https://runway.test/v1/tasks/task_1"

-  it.effect("submits image_to_video, polls the task, reports credits, and keeps the finished task on cancel", () =>
+  it.effect("submits image_to_video with the API version header, polls the task, and reports credits", () =>
    Effect.gen(function* () {
      const calls: Array<Call> = []
      const program = Effect.gen(function* () {
@@ -624,7 +624,7 @@ describe("Video / Runway", () => {
                return json(input, { id: "task_1", estimatedCost: { credits: 25 } })
              }
              expect(call.url).toBe(taskUrl)
-              if (call.method === "DELETE") return yield* Effect.die("cancel deleted a finished Runway task")
+              if (call.method === "DELETE") return input.respond(null, { status: 204 })
              if (nth === 1) return json(input, { id: "task_1", status: "PENDING", estimatedCost: { credits: 25 } })
              if (nth === 2) return json(input, { id: "task_1", status: "THROTTLED", estimatedCost: { credits: 25 } })
              if (nth === 3) return json(input, { id: "task_1", status: "RUNNING", progress: 0.5 })
@@ -653,32 +653,6 @@ describe("Video / Runway", () => {
        `GET ${taskUrl}`,
        `GET ${taskUrl}`,
        `GET ${taskUrl}`,
-        `GET ${taskUrl}`,
-      ])
-    }),
-  )
-
-  it.effect("cancels a task that is still running", () =>
-    Effect.gen(function* () {
-      const calls: Array<Call> = []
-      yield* Effect.gen(function* () {
-        const generation = yield* Video.start({ model, prompt: "x" })
-        yield* generation.cancel()
-      }).pipe(
-        Effect.provide(
-          layer((input) =>
-            Effect.gen(function* () {
-              const { call } = yield* observe(calls, input)
-              if (call.method === "POST") return json(input, { id: "task_1" })
-              if (call.method === "DELETE") return input.respond(null, { status: 204 })
-              return json(input, { id: "task_1", status: "RUNNING", progress: 0.2 })
-            }),
-          ),
-        ),
-      )
-      expect(calls.map((call) => `${call.method} ${call.url}`)).toEqual([
-        "POST https://runway.test/v1/text_to_video",
-        `GET ${taskUrl}`,
        `DELETE ${taskUrl}`,
      ])
    }),
@@ -838,55 +812,3 @@ describe("Video / Runway", () => {
    }),
  )
 })
-
-// ---------------------------------------------------------------------------
-// Shared queued behavior
-// ---------------------------------------------------------------------------
-
-describe("Video / queued result", () => {
-  for (const pending of [
-    {
-      model: Google.configure({ apiKey: "test", baseURL: "https://google.test/v1beta" }).video("veo-3.1"),
-      token: { operation: "models/veo-3.1/operations/op_1" },
-      body: { name: "models/veo-3.1/operations/op_1", done: false },
-      name: "Google Veo",
-    },
-    {
-      model: XAI.configure({ apiKey: "test", baseURL: "https://xai.test/v1" }).video("grok-imagine-video-1.5"),
-      token: { requestID: "req_1" },
-      body: { status: "pending", progress: 40 },
-      name: "xAI Video",
-    },
-    {
-      model: Runway.configure({ apiKey: "test", baseURL: "https://runway.test/v1" }).video("gen4.5"),
-      token: { taskID: "task_1" },
-      body: { status: "RUNNING", progress: 0.5 },
-      name: "Runway",
-    },
-  ]) {
-    it.effect(`rejects reading a ${pending.model.provider} result before the generation finishes`, () =>
-      Effect.gen(function* () {
-        const generation = yield* Video.resume(pending.model, pending.token)
-        const error = yield* generation.result().pipe(Effect.flip)
-        expect(error.reason._tag).toBe("InvalidRequest")
-        expect(error.message).toBe(
-          `${pending.name} generation ${generation.id} has not finished; await it before reading the result`,
-        )
-        expect(error.reason.body).toBe(JSON.stringify(pending.body))
-        expect(error.reason.http?.status).toBe(200)
-      }).pipe(Effect.provide(layer((input) => Effect.succeed(json(input, pending.body))))),
-    )
-  }
-
-  it.effect("rejects a status that only matches an inherited property", () =>
-    Effect.gen(function* () {
-      const error = yield* Video.resume(
-        XAI.configure({ apiKey: "test", baseURL: "https://xai.test/v1" }).video("grok-imagine-video-1.5"),
-        { requestID: "req_1" },
-      ).pipe(Effect.flip)
-      expect(error.reason._tag).toBe("InvalidProviderOutput")
-      expect(error.message).toBe('Unknown generation status "constructor"')
-      expect(error.reason.body).toBe(JSON.stringify({ status: "constructor" }))
-    }).pipe(Effect.provide(layer((input) => Effect.succeed(json(input, { status: "constructor" }))))),
-  )
-})
@@ -9,6 +9,7 @@ import {
  type VideoModelOptions,
  type VideoOptions,
  type VideoRequestFor,
+  type VideoRoute,
 } from "../src/index.js"
 import type { Service } from "../src/video-client.js"
 import { Anthropic, Fal, Google, OpenAI, Runway, XAI } from "../src/providers.js"
@@ -22,7 +23,8 @@ type VeoLikeOptions = {
  readonly personGeneration?: "allow_all" | "allow_adult"
 } & Record<string, unknown>

-declare const veo: VideoModel<VeoLikeOptions>
+declare const route: VideoRoute<VeoLikeOptions>
+const veo = VideoModel.make<VeoLikeOptions>({ id: "veo", provider: "google", route })
 // @ts-expect-error Extracted model options retain known provider fields.
 const invalidVeoOptions: VideoModelOptions<typeof veo> = { personGeneration: "everyone" }
 void invalidVeoOptions
@@ -97,8 +99,6 @@ Video.generate({ model: google, prompt: "A kitten", durationSeconds: "8s" })
 Video.generate({ model: google, prompt: "A kitten", options: { personGeneration: "allow_all" } })

 declare const generic: VideoModel<VideoOptions>
-const widenVideo = <Options extends VideoOptions>(model: VideoModel<Options>): VideoModel => model
-void widenVideo
 Video.generate({ model: generic, prompt: "A kitten", providerOptions: { arbitrary: true } })

 const request = Video.request({ model: veo, prompt: "A kitten", providerOptions: { personGeneration: "allow_all" } })
@@ -2,7 +2,7 @@ import { DialogProvider } from "@opencode/ui/context/dialog"
 import { Browser } from "@opencode/plugin-browser/rpc"
 import { For, Show } from "solid-js"
 import { createStore } from "solid-js/store"
-import { Portal, render } from "solid-js/web"
+import { render } from "solid-js/web"
 import { LanguageProvider, UiI18nBridge } from "../src/runtime/i18n/language"
 import type { BrowserPaneLayout, BrowserPaneRegistration } from "../src/runtime/platform/browser-pane"
 import type { createSessionBrowser } from "../src/session/browser/model"
@@ -27,12 +27,7 @@ export function mountBrowserPane() {
      loadErrors: {} as Record<string, string | undefined>,
      error: undefined as string | undefined,
      layouts: {} as Record<string, BrowserPaneLayout | undefined>,
-      covered: false,
-      captures: 0,
-      holdCapture: false,
    })
-    // Each capture waits until the fixture releases it, so a spec can observe the pending state.
-    const held: (() => void)[] = []
    const tabs = ["Alpha", "Beta"].map((name) => ({
      id: Browser.TabID.make(`tab_${name === "Alpha" ? "11111111" : "22222222"}-1111-1111-1111-111111111111`),
      title: name,
@@ -49,17 +44,6 @@ export function mountBrowserPane() {
        {
          setLayout: (layout) => setStore("layouts", tab.title, layout),
          command: async () => undefined,
-          capture: async () => {
-            setStore("captures", (count) => count + 1)
-            if (store.holdCapture) await new Promise<void>((resolve) => held.push(resolve))
-            const canvas = new OffscreenCanvas(4, 4)
-            const paint = canvas.getContext("2d")
-            if (paint) {
-              paint.fillStyle = "#3b82f6"
-              paint.fillRect(0, 0, 4, 4)
-            }
-            return canvas.convertToBlob()
-          },
          close: () => undefined,
        },
      ]),
@@ -134,34 +118,12 @@ export function mountBrowserPane() {
            Complete navigation
          </button>
          <button onClick={() => setStore("visible", (visible) => !visible)}>Toggle Review tab</button>
-          <button onClick={() => setStore("holdCapture", true)}>Hold capture</button>
-          <button onClick={() => held.splice(0).forEach((resolve) => resolve())}>Release capture</button>
-          <button onClick={() => setStore("covered", (covered) => !covered)}>Toggle popover</button>
        </nav>
-        <p>Captures: {store.captures}</p>
-        <div style={{ position: "relative", width: "640px", height: "360px", border: "1px solid #555" }}>
+        <div style={{ width: "640px", height: "360px", border: "1px solid #555" }}>
          <Show when={store.mounted}>
            <SessionBrowserPane browser={browser} visible={store.visible} />
          </Show>
        </div>
-        <Show when={store.covered}>
-          {/* Floating content portals into <body> like a menu or hover card over the page. */}
-          <Portal mount={document.body}>
-            <div
-              data-popper-positioner
-              data-testid="fixture-popover"
-              style={{
-                position: "fixed",
-                top: "0",
-                left: "0",
-                width: "320px",
-                height: "480px",
-                "z-index": "1001",
-                "pointer-events": "none",
-              }}
-            />
-          </Portal>
-        </Show>
        <h2 style={{ "font-size": "18px", margin: "20px 0 12px" }}>Native layout recorder</h2>
        <p>The desktop boundary keeps each session's page visible until its registration is hidden.</p>
        <For each={tabs}>
@@ -58,27 +58,6 @@ story("hides the native view immediately while the pane stays mounted", async ({
  await expect(root.getByTestId("native-Alpha")).toHaveAttribute("data-visible", "true")
 })

-story("keeps a still of the page under floating content that covers it", async ({ page }, testInfo) => {
-  const root = page.getByTestId("browser-pane-fixture")
-  const still = root.locator("#browser-panel img")
-  await root.getByRole("button", { name: "Hold capture", exact: true }).click()
-  await root.getByRole("button", { name: "Toggle popover", exact: true }).click()
-  await expect(root.getByText("Captures: 1", { exact: true })).toBeVisible()
-  // The native page stays up until its still is ready, so the pane never shows blank.
-  await expect(root.getByTestId("native-Alpha")).toHaveAttribute("data-visible", "true")
-  await expect(still).toHaveCount(0)
-
-  await root.getByRole("button", { name: "Release capture", exact: true }).click()
-  await expect(root.getByTestId("native-Alpha")).toHaveAttribute("data-visible", "false")
-  await expect(still).toBeVisible()
-  await page.screenshot({ path: testInfo.outputPath("covered.png") })
-
-  await root.getByRole("button", { name: "Toggle popover", exact: true }).click()
-  await expect(root.getByTestId("native-Alpha")).toHaveAttribute("data-visible", "true")
-  await expect(still).toHaveCount(0)
-  await expect(root.getByText("Captures: 1", { exact: true })).toBeVisible()
-})
-
 story("shows the empty state over a blank native page and restores navigation", async ({ page }) => {
  const root = page.getByTestId("browser-pane-fixture")
  await root.getByRole("button", { name: "Blank page", exact: true }).click()
@@ -1,5 +1,5 @@
 import { expect, test, type Page } from "@playwright/test"
-import type { OpenCodeEvent, SessionInboxInfo, SessionMessageInfo } from "@opencode/client/promise"
+import type { OpenCodeEvent, SessionMessageInfo } from "@opencode/client/promise"
 import { base64Encode } from "@opencode/util/encode"
 import { mockOpenCodeServer } from "../utils/mock-server"
 import { expectAppVisible } from "../utils/waits"
@@ -14,12 +14,7 @@ type InboxRow = {
  sessionID: string
  time: { created: number }
  type: "user"
-  payload: {
-    text: string
-    metadata?: Record<string, unknown>
-    files?: Extract<SessionInboxInfo, { type: "user" }>["payload"]["files"]
-    agents?: Extract<SessionInboxInfo, { type: "user" }>["payload"]["agents"]
-  }
+  payload: { text: string; metadata?: Record<string, unknown> }
  delivery: "steer" | "queue"
 }

@@ -34,7 +29,7 @@ function createQueueMock(seed: string[], messages: SessionMessageInfo[] = []) {
  }))
  const events: OpenCodeEvent[] = []
  const prompts: Record<string, unknown>[] = []
-  const changes: { inboxID: string; action: "cancel" | "steer" | "queue" }[] = []
+  const changes: { inboxID: string; action: "cancel" | "steer" }[] = []
  const log: string[] = []
  let sequence = 0
  const emit = <Type extends OpenCodeEvent["type"]>(
@@ -239,108 +234,6 @@ test("editing restores the existing draft and replaces only the original queue p
  expect(mock.log[0]).toBe("prompt:queue")
 })

-test("Undo cancels only the selected queued prompt and focuses the restored input", async ({ page }) => {
-  const mock = createQueueMock(["first queued prompt", "second queued prompt", "third queued prompt"])
-  const view = await openSession(page, mock)
-  await expect(view.rows).toHaveCount(3)
-
-  const row = view.rows.filter({ hasText: "second queued prompt" })
-  const actions = row.locator('[data-slot="session-queue-actions"] button')
-  await expect(actions).toHaveCount(3)
-  expect(
-    await actions.evaluateAll((buttons) =>
-      buttons.map((button) => button.getAttribute("aria-label") ?? button.textContent?.trim()),
-    ),
-  ).toEqual(["Steer", "Undo", "Remove"])
-  const undo = row.getByRole("button", { name: "Undo" })
-  await expect(undo).toHaveText("")
-  await expect(undo.locator("svg use")).toHaveAttribute("href", "#opencode-v2-icon-arrow-down-to-line")
-  await undo.hover()
-  await expect(page.getByRole("tooltip")).toHaveText("Undo")
-  await undo.click()
-  await expect(view.rows.locator('[data-action="session-queue-edit"]')).toHaveText([
-    "first queued prompt",
-    "third queued prompt",
-  ])
-  await expect(view.input).toHaveText("second queued prompt")
-  await expect(view.input).toBeFocused()
-  expect(mock.changes).toEqual([{ inboxID: "inb_seed_2", action: "cancel" }])
-  expect(mock.prompts).toEqual([])
-})
-
-test("Undo appends to an existing draft and restores inline attachments", async ({ page }) => {
-  const mock = createQueueMock(["queued with image"])
-  mock.rows[0].payload.files = [
-    {
-      data: "iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVQIHWP4z8DwHwAFgAI/ScL/nwAAAABJRU5ErkJggg==",
-      mime: "image/png",
-      source: { type: "inline" },
-      name: "shot.png",
-    },
-  ]
-  const view = await openSession(page, mock)
-  await view.input.fill("my draft")
-  await view.rows.getByRole("button", { name: "Undo" }).click()
-  await expect(view.rows).toHaveCount(0)
-  await expect(view.input).toHaveText("my draft\n\nqueued with image")
-  await expect(view.input).toBeFocused()
-  await expect(view.composer.getByRole("img", { name: "shot.png" })).toBeVisible()
-  expect(mock.changes).toEqual([{ inboxID: "inb_seed_1", action: "cancel" }])
-})
-
-test("Undo stays usable with a long queue on a narrow screen", async ({ page }, testInfo) => {
-  await page.setViewportSize({ width: 390, height: 844 })
-  const text = "Review the detailed error report and check every step of the retry path ".repeat(4)
-  const mock = createQueueMock([text, ...Array.from({ length: 6 }, (_, index) => `queued follow-up ${index + 1}`)])
-  const view = await openSession(page, mock)
-  await expect(view.rows).toHaveCount(7)
-  const row = view.rows.filter({ hasText: text })
-  await row.getByRole("button", { name: "Undo" }).hover()
-  await expect(page.getByRole("tooltip")).toHaveText("Undo")
-  await page.screenshot({ path: testInfo.outputPath("undo-narrow-queue.png") })
-  await row.getByRole("button", { name: "Undo" }).click()
-  await expect(view.rows).toHaveCount(6)
-  await expect(view.input).toHaveText(text)
-  await expect(view.input).toBeFocused()
-  expect(mock.changes).toEqual([{ inboxID: "inb_seed_1", action: "cancel" }])
-})
-
-test("Undo preserves mentioned file and agent references on resubmission", async ({ page }) => {
-  const mock = createQueueMock(["inspect @main.ts with @build"])
-  mock.rows[0].payload.files = [
-    {
-      data: "aGk=",
-      mime: "text/plain",
-      source: { type: "uri", uri: "file:///repo/main.ts" },
-      name: "main.ts",
-      mention: { start: 8, end: 16, text: "@main.ts" },
-    },
-  ]
-  mock.rows[0].payload.agents = [{ name: "build", mention: { start: 22, end: 28, text: "@build" } }]
-  const view = await openSession(page, mock)
-  await view.rows.getByRole("button", { name: "Undo" }).click()
-  await expect(view.input).toHaveText("inspect @main.ts with @build")
-  await view.input.press("Enter")
-  await expect.poll(() => mock.prompts.length).toBe(1)
-  expect(mock.prompts[0].files).toMatchObject([
-    { uri: "data:text/plain;base64,aGk=", mention: { text: "@main.ts", start: 8, end: 16 } },
-  ])
-  expect(mock.prompts[0].agents).toMatchObject([{ name: "build", mention: { text: "@build" } }])
-})
-
-test("Undo does not discard hidden file context", async ({ page }) => {
-  const mock = createQueueMock(["inspect this file"])
-  mock.rows[0].payload.files = [
-    { data: "aGk=", mime: "text/plain", source: { type: "uri", uri: "file:///repo/main.ts" }, name: "main.ts" },
-  ]
-  const view = await openSession(page, mock)
-  await view.rows.getByRole("button", { name: "Undo" }).click()
-  await expect(page.getByText("Edit this prompt in the queue to preserve its file context")).toBeVisible()
-  await expect(view.rows).toHaveCount(1)
-  await expect(view.input).toHaveText("")
-  expect(mock.changes).toEqual([])
-})
-
 for (const delivery of ["steer", "queue"] as const) {
  test(`keeps finished tools above a pending ${delivery === "queue" ? "queue-to-steer" : "steer"} follow-up`, async ({
    page,
@@ -1,6 +1,6 @@
 {
  "name": "@opencode/app",
-  "version": "2.0.18",
+  "version": "2.0.16",
  "description": "",
  "type": "module",
  "exports": {
@@ -47,7 +47,6 @@ export type ComposerDelivery = "steer" | "queue"
 // is loaded in the editor.
 export type ComposerQueue = {
  count: Accessor<number>
-  undoing: Accessor<boolean>
  // Delivery a plain submit uses right now.
  delivery: Accessor<ComposerDelivery>
  // Delivery offered on Mod+Enter and the toolbar hint button; undefined hides the hint.
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
OpeOginni	eb15a9b789	fix(server): match the macOS EPERM privacy denial exactly	2026-09-24 19:21:50 +02:00
OpeOginni	d74adc2beb	fix(server): return typed errors for unavailable project folders	2026-09-24 18:47:08 +02:00