feat(app): show last turn changes in review panel

fix(ai): surface truncated Gemini speech and transcription results (#51379 )
fix(ai): describe speech assets in the format actually sent (#51377 )
2026-09-27 11:07:34 +00:00 · 2026-09-27 15:06:22 +05:30 · 2026-09-27 14:29:36 +05:30 · 2026-09-27 14:16:23 +05:30 · 2026-09-26 23:11:33 -05:00 · 2026-09-26 22:58:28 -05:00
173 changed files with 4755 additions and 1936 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 native compaction mechanisms out of `SessionCompaction`. Plugins register `native` strategies through the `SessionCompaction` editor that turn a prepared request into a replacement window (the built-in `NativeCompactionPlugin` handles `@opencode/ai` compaction operations); later registrations win. Core owns the provider-mode decision, route provenance, the retry policy, overflow recovery, interruption, usage accounting, and checkpoint persistence.
+- Keep provider-specific native compaction mechanisms in `@opencode/ai` behind `LLMClient.compact`. `SessionCompaction` chooses a summary or native compaction from the model's `compaction` setting and owns route provenance, request shrinking, the retry policy, interruption, usage accounting, and checkpoint persistence.
 - Keep delivery vocabulary explicit. Prompts steer by default. At safe step boundaries, steered compaction takes priority up to the first steered move control; other steers retain enqueue order. At an idle boundary, steers take priority; otherwise exactly one queued item delivers before the runner reevaluates continuation. Inbox items may be cancelled or changed between queue and steer before delivery. Promoting new user input resets the selected agent's step allowance; a batch of steers resets it once.
 - One step is one logical LLM call; its durable record covers only the model-visible span. Do not write "provider turn", and do not use bare "turn" for a single call: "turn" is reserved for the future assistant-turn unit containing all steps from prompt promotion until the session would go idle.
 - Keep event replay ownership separate from clustered Session execution ownership.
@@ -32,7 +32,7 @@
    },
    "packages/ai": {
      "name": "@opencode/ai",
-      "version": "2.0.16",
+      "version": "2.0.18",
      "dependencies": {
        "@aws-sdk/credential-providers": "3.1057.0",
        "@opencode/schema": "workspace:*",
@@ -54,7 +54,7 @@
    },
    "packages/app": {
      "name": "@opencode/app",
-      "version": "2.0.16",
+      "version": "2.0.18",
      "dependencies": {
        "@corvu/drawer": "catalog:",
        "@dnd-kit/abstract": "0.5.0",
@@ -112,13 +112,14 @@
    },
    "packages/cli": {
      "name": "@opencode/cli",
-      "version": "2.0.16",
+      "version": "2.0.18",
      "bin": {
        "opencode": "./bin/opencode.cjs",
        "opencode2": "./bin/opencode2.cjs",
      },
      "dependencies": {
        "@agentclientprotocol/sdk": "1.2.1",
+        "@clack/core": "1.0.0-alpha.1",
        "@clack/prompts": "1.0.0-alpha.1",
        "@effect/platform-node": "catalog:",
        "@opencode-ai/pty": "0.1.13",
@@ -135,7 +136,7 @@
        "effect": "catalog:",
        "immer": "11.1.4",
        "jsonc-parser": "3.3.1",
-        "open": "10.1.2",
+        "picocolors": "1.1.1",
        "solid-js": "catalog:",
        "tree-sitter-bash": "0.25.0",
        "tree-sitter-powershell": "0.25.10",
@@ -177,7 +178,7 @@
    },
    "packages/client": {
      "name": "@opencode/client",
-      "version": "2.0.16",
+      "version": "2.0.18",
      "dependencies": {
        "@opencode/protocol": "workspace:*",
        "@opencode/schema": "workspace:*",
@@ -203,7 +204,7 @@
    },
    "packages/codemode": {
      "name": "@opencode/codemode",
-      "version": "2.0.16",
+      "version": "2.0.18",
      "dependencies": {
        "acorn": "8.15.0",
        "effect": "catalog:",
@@ -216,7 +217,7 @@
    },
    "packages/console/app": {
      "name": "@opencode/console-app",
-      "version": "2.0.16",
+      "version": "2.0.18",
      "dependencies": {
        "@cloudflare/vite-plugin": "1.15.2",
        "@ibm/plex": "6.4.1",
@@ -252,7 +253,7 @@
    },
    "packages/console/core": {
      "name": "@opencode/console-core",
-      "version": "2.0.16",
+      "version": "2.0.18",
      "dependencies": {
        "@aws-sdk/client-sts": "3.782.0",
        "@jsx-email/render": "1.1.1",
@@ -279,7 +280,7 @@
    },
    "packages/console/function": {
      "name": "@opencode/console-function",
-      "version": "2.0.16",
+      "version": "2.0.18",
      "dependencies": {
        "@openauthjs/openauth": "0.0.0-20250322224806",
        "@opencode/console-core": "workspace:*",
@@ -296,7 +297,7 @@
    },
    "packages/console/mail": {
      "name": "@opencode/console-mail",
-      "version": "2.0.16",
+      "version": "2.0.18",
      "dependencies": {
        "@jsx-email/all": "2.2.3",
        "@jsx-email/cli": "1.4.3",
@@ -320,7 +321,7 @@
    },
    "packages/console/support": {
      "name": "@opencode/console-support",
-      "version": "2.0.16",
+      "version": "2.0.18",
      "dependencies": {
        "@cloudflare/vite-plugin": "1.15.2",
        "@opencode/console-core": "workspace:*",
@@ -340,7 +341,7 @@
    },
    "packages/core": {
      "name": "@opencode/core",
-      "version": "2.0.16",
+      "version": "2.0.18",
      "dependencies": {
        "@ai-sdk/cohere": "3.0.27",
        "@ai-sdk/gateway": "3.0.104",
@@ -408,7 +409,7 @@
    },
    "packages/desktop": {
      "name": "@opencode/desktop",
-      "version": "2.0.16",
+      "version": "2.0.18",
      "dependencies": {
        "@zip.js/zip.js": "2.7.62",
        "electron-context-menu": "5.0.0",
@@ -457,7 +458,7 @@
    },
    "packages/enterprise": {
      "name": "@opencode/enterprise",
-      "version": "2.0.16",
+      "version": "2.0.18",
      "dependencies": {
        "@hono/standard-validator": "catalog:",
        "@opencode-ai/sdk": "1.18.21",
@@ -494,7 +495,7 @@
    },
    "packages/function": {
      "name": "@opencode/function",
-      "version": "2.0.16",
+      "version": "2.0.18",
      "dependencies": {
        "@octokit/auth-app": "8.0.1",
        "@octokit/rest": "catalog:",
@@ -510,7 +511,7 @@
    },
    "packages/http-recorder": {
      "name": "@opencode/http-recorder",
-      "version": "2.0.16",
+      "version": "2.0.18",
      "dependencies": {
        "@effect/platform-node-shared": "4.0.0-rc.112",
      },
@@ -529,7 +530,7 @@
    },
    "packages/httpapi-codegen": {
      "name": "@opencode/httpapi-codegen",
-      "version": "2.0.16",
+      "version": "2.0.18",
      "dependencies": {
        "effect": "catalog:",
        "prettier": "3.6.2",
@@ -542,7 +543,7 @@
    },
    "packages/latex": {
      "name": "@opencode/latex",
-      "version": "2.0.16",
+      "version": "2.0.18",
      "dependencies": {
        "@opencode/plugin": "workspace:*",
        "@opentui/core": "catalog:",
@@ -556,7 +557,7 @@
    },
    "packages/merman": {
      "name": "@opencode/merman",
-      "version": "2.0.16",
+      "version": "2.0.18",
      "dependencies": {
        "@opencode/plugin": "workspace:*",
        "@opentui/core": "catalog:",
@@ -571,7 +572,7 @@
    },
    "packages/plugin": {
      "name": "@opencode/plugin",
-      "version": "2.0.16",
+      "version": "2.0.18",
      "dependencies": {
        "@ai-sdk/provider": "3.0.8",
        "@opencode/ai": "workspace:*",
@@ -597,8 +598,8 @@
      },
      "peerDependencies": {
        "@opencode/theme": "workspace:*",
-        "@opentui/core": ">=0.5.10",
-        "@opentui/solid": ">=0.5.10",
+        "@opentui/core": ">=0.5.12",
+        "@opentui/solid": ">=0.5.12",
        "solid-js": ">=1.9.0",
      },
      "optionalPeers": [
@@ -610,7 +611,7 @@
    },
    "packages/plugin-browser": {
      "name": "@opencode/plugin-browser",
-      "version": "2.0.16",
+      "version": "2.0.18",
      "dependencies": {
        "@opencode/plugin": "workspace:*",
        "@opencode/schema": "workspace:*",
@@ -640,7 +641,7 @@
    },
    "packages/protocol": {
      "name": "@opencode/protocol",
-      "version": "2.0.16",
+      "version": "2.0.18",
      "dependencies": {
        "@opencode/schema": "workspace:*",
        "effect": "catalog:",
@@ -655,7 +656,7 @@
    },
    "packages/schema": {
      "name": "@opencode/schema",
-      "version": "2.0.16",
+      "version": "2.0.18",
      "dependencies": {
        "@standard-schema/spec": "catalog:",
        "effect": "catalog:",
@@ -679,7 +680,7 @@
    },
    "packages/sdk": {
      "name": "@opencode/sdk",
-      "version": "2.0.16",
+      "version": "2.0.18",
      "dependencies": {
        "@opencode/client": "workspace:*",
        "@opencode/core": "workspace:*",
@@ -700,7 +701,7 @@
    },
    "packages/server": {
      "name": "@opencode/server",
-      "version": "2.0.16",
+      "version": "2.0.18",
      "dependencies": {
        "@effect/platform-node": "catalog:",
        "@effect/platform-node-shared": "catalog:",
@@ -722,7 +723,7 @@
    },
    "packages/session-ui": {
      "name": "@opencode/session-ui",
-      "version": "2.0.16",
+      "version": "2.0.18",
      "dependencies": {
        "@kobalte/core": "catalog:",
        "@opencode/client": "workspace:*",
@@ -757,7 +758,7 @@
    },
    "packages/simulation": {
      "name": "@opencode/simulation",
-      "version": "2.0.16",
+      "version": "2.0.18",
      "dependencies": {
        "@opencode/ai": "workspace:*",
        "@opencode/core": "workspace:*",
@@ -777,7 +778,7 @@
    },
    "packages/stats/app": {
      "name": "@opencode/stats-app",
-      "version": "2.0.16",
+      "version": "2.0.18",
      "dependencies": {
        "@ibm/plex": "6.4.1",
        "@kobalte/core": "catalog:",
@@ -811,7 +812,7 @@
    },
    "packages/stats/core": {
      "name": "@opencode/stats-core",
-      "version": "2.0.16",
+      "version": "2.0.18",
      "dependencies": {
        "@aws-sdk/client-athena": "3.933.0",
        "@planetscale/database": "1.19.0",
@@ -830,7 +831,7 @@
    },
    "packages/stats/server": {
      "name": "@opencode/stats-server",
-      "version": "2.0.16",
+      "version": "2.0.18",
      "dependencies": {
        "@aws-sdk/client-firehose": "3.933.0",
        "@effect/platform-node": "catalog:",
@@ -876,7 +877,7 @@
    },
    "packages/theme": {
      "name": "@opencode/theme",
-      "version": "2.0.16",
+      "version": "2.0.18",
      "dependencies": {
        "@opentui/core": "catalog:",
        "effect": "catalog:",
@@ -890,7 +891,7 @@
    },
    "packages/tui": {
      "name": "@opencode/tui",
-      "version": "2.0.16",
+      "version": "2.0.18",
      "dependencies": {
        "@opencode/client": "workspace:*",
        "@opencode/core": "workspace:*",
@@ -909,7 +910,6 @@
        "effect": "catalog:",
        "fuzzysort": "catalog:",
        "get-east-asian-width": "catalog:",
-        "open": "10.1.2",
        "opentui-spinner": "catalog:",
        "remeda": "catalog:",
        "solid-js": "catalog:",
@@ -925,7 +925,7 @@
    },
    "packages/ui": {
      "name": "@opencode/ui",
-      "version": "2.0.16",
+      "version": "2.0.18",
      "dependencies": {
        "@kobalte/core": "catalog:",
        "@pierre/diffs": "catalog:",
@@ -960,7 +960,7 @@
    },
    "packages/util": {
      "name": "@opencode/util",
-      "version": "2.0.16",
+      "version": "2.0.18",
      "dependencies": {
        "@effect/opentelemetry": "catalog:",
        "@effect/platform-node": "catalog:",
@@ -982,6 +982,7 @@
        "mime-types": "3.0.2",
        "minimatch": "10.2.5",
        "npm-package-arg": "13.0.2",
+        "open": "11.0.4",
        "pacote": "21.5.1",
      },
      "devDependencies": {
@@ -997,7 +998,7 @@
    },
    "packages/web": {
      "name": "@opencode/web",
-      "version": "2.0.16",
+      "version": "2.0.18",
      "dependencies": {
        "@astrojs/cloudflare": "12.6.3",
        "@astrojs/markdown-remark": "6.3.1",
@@ -1038,7 +1039,7 @@
    },
    "services/update": {
      "name": "@opencode/update",
-      "version": "2.0.16",
+      "version": "2.0.18",
      "dependencies": {
        "jose": "6.0.11",
        "semver": "catalog:",
@@ -1098,6 +1099,7 @@
    "@types/node": "catalog:",
    "bun-types": "1.4.2",
    "effect": "catalog:",
+    "open": "11.0.4",
    "solid-js": "catalog:",
  },
  "catalog": {
@@ -1114,9 +1116,9 @@
    "@npmcli/arborist": "9.4.0",
    "@octokit/rest": "22.0.0",
    "@openauthjs/openauth": "0.0.0-20250322224806",
-    "@opentui/core": "0.5.10",
-    "@opentui/keymap": "0.5.10",
-    "@opentui/solid": "0.5.10",
+    "@opentui/core": "0.5.12",
+    "@opentui/keymap": "0.5.12",
+    "@opentui/solid": "0.5.12",
    "@pierre/diffs": "1.2.10",
    "@playwright/test": "1.59.1",
    "@sentry/solid": "10.71.0",
@@ -2252,27 +2254,27 @@

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

-    "@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": ["@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-darwin-arm64": ["@opentui/core-darwin-arm64@0.5.10", "", { "os": "darwin", "cpu": "arm64" }, "sha512-Vyb+nTbhab8ZcRy5gg1loEEGwRcIbjAeVRIBfHBcbFDqmITBOg7x2gqJ+x/TnoOy4uwMhCmICUN2wiyREw3r1Q=="],
+    "@opentui/core-darwin-arm64": ["@opentui/core-darwin-arm64@0.5.12", "", { "os": "darwin", "cpu": "arm64" }, "sha512-YdVnP0tAyerBNl0mIcmQEOotPeZzW1VnSXKBl5cyZ5e6nDd2Y+ui/8eRPpn1oqcamf1NCnzS4ohMgejOvna8Zg=="],

-    "@opentui/core-darwin-x64": ["@opentui/core-darwin-x64@0.5.10", "", { "os": "darwin", "cpu": "x64" }, "sha512-tTFLcM7Oj1gTyhm/bUdAt3C6grZdCxPk6+/g2azcZBUlI3/62LwbeRS6HbQKFFmm+1fUmX8cq6kWrtul885mVg=="],
+    "@opentui/core-darwin-x64": ["@opentui/core-darwin-x64@0.5.12", "", { "os": "darwin", "cpu": "x64" }, "sha512-uRrQJdHmLUSj3PV23QPi3WSimYTTxcXnVouxF6U4xMXlOv4N3SxnHfVwMRQkPqbGOfvVWHeLE6FdK4C+ubU0sQ=="],

-    "@opentui/core-linux-arm64": ["@opentui/core-linux-arm64@0.5.10", "", { "os": "linux", "cpu": "arm64" }, "sha512-ncJXcgudhBf2GdJyF3xVQN/Ec+1F7GOL+pRrURmgBYSj2v1w6EyoDQFAACtPTK2c3R38W6fvZwL4JSLlm4EFXQ=="],
+    "@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-musl": ["@opentui/core-linux-arm64-musl@0.5.10", "", { "os": "linux", "cpu": "arm64" }, "sha512-dGMphDKexSdeYqwl0wgoFBP88Ta/cdi1Zc1mk29/ENkSCGz+74zlCHgqTHRNGLmI8W5TfuUtCyktQH11/Z+TBQ=="],
+    "@opentui/core-linux-arm64-musl": ["@opentui/core-linux-arm64-musl@0.5.12", "", { "os": "linux", "cpu": "arm64" }, "sha512-VZ2sNMw1d/r1SLPjUbOP9LKscKz1CQjID8adTL6gG8Lrrq+mYcIUxutyB+P/eG0J/7oRZLPR6OMt7dUOap6RTg=="],

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

-    "@opentui/core-linux-x64-musl": ["@opentui/core-linux-x64-musl@0.5.10", "", { "os": "linux", "cpu": "x64" }, "sha512-Oj4H9hApuvuTKPWxh4SoZAgGJorR7vbvnrZA/cAkSMAk2VGSoHRRcqeXQbcH8IcdjVZ0KFpv8Zkl/D5Ye+2mew=="],
+    "@opentui/core-linux-x64-musl": ["@opentui/core-linux-x64-musl@0.5.12", "", { "os": "linux", "cpu": "x64" }, "sha512-WWW0hVBoSYZ3D6AgZ4u2Y5/u/IyIq2pDb+4yI3WgJ70Wyt6ofHy+6kRGRgbXFn1p+rPInAHjCXD2v6C7iEKSrA=="],

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

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

-    "@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/keymap": ["@opentui/keymap@0.5.12", "", { "dependencies": { "@opentui/core": "0.5.12" }, "peerDependencies": { "@opentui/react": "0.5.12", "@opentui/solid": "0.5.12", "react": ">=19.2.0", "solid-js": "1.9.12" }, "optionalPeers": ["@opentui/react", "@opentui/solid", "react", "solid-js"] }, "sha512-yWPvJjRhJTRoRSUucQq9Ua8ZW7n/2YQ/j6JxWq5Qekm4WuFiTplEkebR/Aj2/xA8tX68NOE5qv1LrY0Jk3NLNQ=="],

-    "@opentui/solid": ["@opentui/solid@0.5.10", "", { "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=="],
+    "@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=="],

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

@@ -4322,7 +4324,7 @@

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

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

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

@@ -4340,6 +4342,8 @@

    "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=="],
@@ -4386,7 +4390,7 @@

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

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

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

@@ -4850,7 +4854,7 @@

    "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@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=="],
+    "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=="],

    "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=="],

@@ -4994,6 +4998,8 @@

    "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=="],
@@ -5814,7 +5820,7 @@

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

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

@@ -5910,8 +5916,6 @@

    "@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=="],
@@ -6394,8 +6398,6 @@

    "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=="],
@@ -6500,6 +6502,10 @@

    "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=="],
@@ -6510,8 +6516,6 @@

    "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=="],
@@ -6614,8 +6618,6 @@

    "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=="],
@@ -6702,6 +6704,10 @@

    "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=="],
@@ -7336,8 +7342,6 @@

    "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=="],
@@ -7398,12 +7402,6 @@

    "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=="],
@@ -7674,6 +7672,10 @@

    "@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=="],
@@ -8076,6 +8078,10 @@

    "@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=="],
@@ -8216,6 +8222,10 @@

    "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=="],
@@ -8318,6 +8328,10 @@

    "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-+Clo0VPDdruHSoBNvV/wKAM8iR6HJPtB00oa8yl9ujU=",
-    "aarch64-linux": "sha256-4wU5v36GTXjwyt5ls4FH+5G43Ujd+dKVSJR21w3lhbA=",
-    "aarch64-darwin": "sha256-pThjoD6baddQ6biy7k1ByXwGwLAeWe/+w0tcYmt1uWs=",
-    "x86_64-darwin": "sha256-bCBl63CqBiqilb+YdaOLBYYZx/yf47c1aqgDOkgdegg="
+    "x86_64-linux": "sha256-7DgxTpKv6ITKTom0mhlJNPQfdEjtEHK5P8uyCr26HZw=",
+    "aarch64-linux": "sha256-PJxW1Ibfx6oS1neWPSHqzP1Pm1HT9my1TrrHmOb6/no=",
+    "aarch64-darwin": "sha256-VIme5VHfM8JxNiDSOykkr5FytghDLI0FxkhiOXUSyQw=",
+    "x86_64-darwin": "sha256-rQ/j0QkR1vxAq4jgUbr0nY4RDyiLTJqN8q1AfoiEqVQ="
  }
 }
@@ -2,7 +2,7 @@
  "$schema": "https://json.schemastore.org/package.json",
  "name": "opencode",
  "description": "AI-powered development tool",
-  "version": "2.0.16",
+  "version": "2.0.18",
  "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": "0.5.10",
-      "@opentui/keymap": "0.5.10",
-      "@opentui/solid": "0.5.10",
+      "@opentui/core": "0.5.12",
+      "@opentui/keymap": "0.5.12",
+      "@opentui/solid": "0.5.12",
      "@tanstack/solid-virtual": "3.13.37",
      "@shikijs/stream": "4.4.3",
      "@standard-schema/spec": "1.1.0",
@@ -162,6 +162,7 @@
    "@types/node": "catalog:",
    "bun-types": "1.4.2",
    "effect": "catalog:",
+    "open": "11.0.4",
    "solid-js": "catalog:"
  },
  "patchedDependencies": {
@@ -12,9 +12,9 @@

 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.

-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.
+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.

-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.
+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.

 `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`.

@@ -98,7 +98,7 @@ 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`, each addressed by a route-owned `token` whose `Schema.Codec` makes it serializable. `MediaRoute.inline` and `MediaRoute.queued` compose the two kinds with `Endpoint` and `Auth`; the queued route decodes the token once at the boundary (`start` output or `resume` input) and closes over it in a token-free `GenerationRoute` (`status`/`result`/`cancel` are plain Effects), so `Generation` never sees the token's shape and only carries the encoded JSON for persistence. Polls reuse the route's auth and deployment headers plus the request's `http` overlay after `start`, and resolve relative paths against the route base URL (provider-issued absolute URLs such as fal's `status_url` pass through). `result` is always its own GET even when the provider returns output inside the status document, so `Generation.await` behaves the same after `start` and after `resume`. `PollContext.auth` carries only what `Auth` added or changed so protocols can hand download credentials to output assets as transient `Media.Asset.headers` (Veo) — never part of `source` or JSON. Status strings map through a per-protocol `STATUS` table via `MediaProtocol.status`; terminal generations without output fail through `output.ended` / `output.contentPolicy` with the provider document on `reason.body`. `GenerationAwaitOptions` (`AwaitOptions` in `src/generation.ts`, `{ poll?: Poll }`) is the one options type for `await`, `events`, `Video.generate`, and `Video.stream`.
+`MediaProtocol.queued` is the submit-then-poll kind every video route uses: `start` (body + decode into `{ token, snapshot }`), `status`, `result`, and optional `cancel` (with `activeOnly` when the provider's cancel endpoint deletes finished work, as Runway's does: the route refreshes status first and skips terminal generations), each addressed by a route-owned `token` whose `Schema.Codec` makes it serializable. `MediaRoute.inline` and `MediaRoute.queued` compose the two kinds with `Endpoint` and `Auth`; the queued route decodes the token once at the boundary (`start` output or `resume` input) and closes over it in a token-free `GenerationRoute` (`status`/`result`/`cancel` are plain Effects), so `Generation` never sees the token's shape and only carries the encoded JSON for persistence. Polls reuse the route's auth and deployment headers plus the request's `http` overlay after `start`, and resolve relative paths against the route base URL (provider-issued absolute URLs such as fal's `status_url` pass through). `result` is always its own GET even when the provider returns output inside the status document, so `Generation.await` behaves the same after `start` and after `resume`. `PollContext.auth` carries only what `Auth` added or changed so protocols can hand download credentials to output assets as transient `Media.Asset.headers` (Veo) — never part of `source` or JSON. Status strings map through a per-protocol `STATUS` table via `MediaProtocol.status`; terminal generations without output fail through `output.ended` / `output.contentPolicy` with the provider document on `reason.body`. `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.

@@ -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)`, later `.video` / `.speech` / `.transcription`) 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)`, `.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:

 ```ts
 const openai = OpenAI.configure({ apiKey, baseURL })
@@ -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`)    | ✓                   |
-| 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`, `/multi`) | ✓                   |
+| 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.
@@ -621,8 +621,7 @@ 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.
-`dall-e-*` models do not stream and fail typed:
+and emits `image-partial` events before each final `image`; `Image.generate` keeps the plain JSON request:

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

-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.
+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.

 ## Video generation

@@ -840,9 +839,10 @@ 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 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
+- **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
  `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`);
@@ -944,6 +944,7 @@ 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.
@@ -1,6 +1,7 @@
 # Media generation in `@opencode/ai` — public API direction

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

 ## Goal

@@ -40,7 +41,7 @@ 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 — `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`.
+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`.

 ```ts
 import { OpenAI, Google } from "@opencode/ai/providers"
@@ -135,8 +136,8 @@ Effect.gen(function* () {
 })
 ```

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

 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`.

@@ -166,8 +167,8 @@ 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 with expiresAt (+ transient `headers` for Veo downloads)
-  response.usage                                     // credits on Runway; the other three report none
+  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.notices                                   // Veo raiMediaFilteredReasons → filtered, xAI respect_moderation → moderated
  yield* response.video.materialize()                // pull bytes before the URL expires

@@ -175,7 +176,7 @@ 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}; no-op for Veo and xAI
+  yield* generation.cancel()                         // fal PUT cancel_url, Runway DELETE /tasks/{id}; Veo and xAI succeed without a request

  // 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.
@@ -188,10 +189,11 @@ 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 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`.
+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`.

 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.
@@ -241,10 +243,12 @@ 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 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"`.
+(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"`.

 **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
@@ -277,7 +281,7 @@ const request = Transcription.request({
  language: "en",                                  // provider-native passthrough
  timestamps: "segment",                           // none | segment | word
  diarize: true,
-  speakers: 2,                                     // expected count, hint only (AssemblyAI)
+  speakers: 2,                                     // exact speaker count (AssemblyAI only)
  providerOptions: { known_speaker_names: ["agent"] },
 })

@@ -291,10 +295,11 @@ 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 `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
+`<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
 `finish` event carries the whole transcript (text, segments, words, language, duration, usage), so the stream route's
 `collect` is just "take `finish`".

@@ -309,11 +314,12 @@ 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 a hint; only AssemblyAI (`speakers_expected`) accepts it.
+  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.
 - **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, `english` from whisper-1, `en_us` from AssemblyAI. Deepgram and AssemblyAI assume English
-  unless asked to detect, so a missing `language` enables their detection.
+  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.
 - **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.
@@ -323,7 +329,7 @@ Settled rules:

 | Provider | Kind | Audio input | `timestamps` | `diarize` | Unsupported | Usage |
 |---|---|---|---|---|---|---|
-| 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` |
+| OpenAI | stream (`stream: true` in `stream` mode; `whisper-1` ignores `stream`, so it emits only `finish`) | multipart `file` (inline only) | `whisper-1` (`verbose_json`); diarize model: `segment` | `gpt-4o-transcribe-diarize` (`diarized_json`) | `speakers`; `prompt` on the diarize model | `tokens` or `seconds` |
 | Gemini | stream (`generateContent` / `streamGenerateContent`) | `inlineData` or Gemini Files `fileData` | `audioTranscriptionConfig.wordTimestamp` | `audioTranscriptionConfig.diarization` | `prompt`, `speakers` | `tokens` |
 | Deepgram | inline | raw body, or JSON `{ url }` | words always; `segment` → `utterances` | `diarize_model=latest` + `utterances` | `prompt`, `speakers` | `seconds` (`metadata.duration`) |
 | AssemblyAI | queued (upload → submit → poll) | `/v2/upload` then `audio_url`, or a URL | words always; `segment` → `speaker_labels` | `speaker_labels` | — | `seconds` (`audio_duration`) |
@@ -353,7 +359,7 @@ GenerationAwaitOptions = { poll?: Poll }
 Poll = { interval?: Duration; timeout?: Duration }
 ```

-`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`.
+`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`.

 ### Usage

@@ -400,14 +406,15 @@ Streams become `AsyncIterable` via `Stream.toAsyncIterable`. `AIError` is thrown

 ### Providers

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

 | Facade | llm | image | video | speech | transcription | other |
 |---|---|---|---|---|---|---|
-| `OpenAI` | responses (default), chat | Images API (stream) | Sora (deprecated 2026-09-24) | ✓ | ✓ | |
+| `OpenAI` | responses (default), chat | Images API (stream) | *Sora skipped (decision 8)* | ✓ | ✓ | |
 | `Google` | Gemini | Gemini-native | Veo | Gemini TTS | `gemini-3.5-transcribe` | |
 | `XAI` | ✓ | ✓ | ✓ | | | |
-| `ElevenLabs` | | | | ✓ | Scribe | soundEffect, music |
+| `ElevenLabs` | | | | ✓ | *Scribe (pending)* | *soundEffect, music (phase 5)* |
 | `Cartesia` | | | | ✓ | | |
 | `Deepgram` | | | | Aura | ✓ | |
 | `Fal` | | ✓ (queued) | ✓ | | | |
@@ -416,7 +423,7 @@ Existing facades gain per-modality selectors; the modality routes each facade pr
 | `Replicate` | | ✓ (queued) | | | | |
 | `Stability` | | `image` (inline), `upscale()` (queued) | | | | |
 | `Runway` | | | ✓ | | | |
-| `Luma`, `Kling`, `MiniMax` | | per provider | | | | |
+| `Luma`, `Kling`, `MiniMax` | | *deferred* | *deferred* | | | |

 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.

@@ -1,6 +1,6 @@
 {
  "$schema": "https://json.schemastore.org/package.json",
-  "version": "2.0.16",
+  "version": "2.0.18",
  "name": "@opencode/ai",
  "type": "module",
  "license": "MIT",
@@ -53,6 +53,8 @@ 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
@@ -81,7 +83,7 @@ export class Generation<Response> {
  }

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

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

  /**
-   * 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.)
+   * 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.)
   */
  events(options?: AwaitOptions): Stream.Stream<Event, AIError> {
    if (this.terminal) return Stream.make(this.event())
@@ -120,17 +123,26 @@ 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) =>
-              this.refresh().pipe(
-                Effect.timeoutOrElse({
-                  duration: Duration.millis(Math.max(0, deadline - now)),
-                  orElse: () => this.timeoutError(timeout),
-                }),
-              ),
+              now >= deadline
+                ? this.timeoutError(timeout)
+                : this.refresh().pipe(
+                    Effect.timeoutOrElse({
+                      duration: Duration.millis(deadline - now),
+                      orElse: () => this.timeoutError(timeout),
+                    }),
+                  ),
            ),
          )
-          return Stream.fromEffectSchedule(refresh, this.schedule(options?.poll)).pipe(
+          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(
            Stream.takeUntil((generation) => generation.terminal),
            Stream.map((generation) => generation.event()),
          )
@@ -110,8 +110,11 @@ 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, require speaker labels.
-        speaker_labels: request.diarize === true || request.timestamps === "segment" ? true : undefined,
+        // 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,
        speakers_expected: request.speakers,
      },
      request.providerOptions,
@@ -155,8 +158,7 @@ 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 ? "" : `: ${error}`}`)
-  if (status !== "completed")
-    return yield* output.invalid(`${route.name} transcript ${context.token.transcriptID} has not finished`)
+  if (status !== "completed") return yield* output.pending(context.token.transcriptID)
  const duration = transcript.audio_duration ?? undefined
  return new TranscriptionResponse({
    text: transcript.text ?? "",
@@ -31,13 +31,21 @@ export type Request = ImageRequestFor<BlackForestLabsImageOptions>
 // 2. Token and response schemas
 // ---------------------------------------------------------------------------

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

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

@@ -169,14 +181,16 @@ 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 ${document.status}`)
-  if (status !== "completed" || document.result === undefined || document.result === null)
+  if (status !== "completed") return yield* output.pending(context.token.id)
+  if (document.result === undefined || document.result === null)
    return yield* output.invalid(`${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:
-      document.cost === undefined || document.cost === null ? undefined : { type: "credits", credits: document.cost },
+    usage: cost === undefined ? undefined : { type: "credits", credits: cost },
    providerMetadata: {
      bfl: { id: context.token.id, seed: seed ?? undefined, prompt: prompt ?? undefined, ...rest },
    },
@@ -67,6 +67,9 @@ 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 &&
@@ -86,24 +89,32 @@ const fromRequest = Effect.fn("DeepgramSpeech.fromRequest")(function* (request:
 // 6. Stream parsing
 // ---------------------------------------------------------------------------

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

 const finish = (state: State, context: MediaProtocol.ResponseContext<Request>) => {
  const headers = context.http.headers
  const mediaType = headers["content-type"]
  const format = audioFormat(context.request)
-  const encoding = HEADERLESS_ENCODINGS[format.encoding ?? ""]
+  const headerless = HEADERLESS_ENCODINGS[format.encoding ?? ""]
+  const container = format.container ?? (headerless === undefined ? undefined : "wav")
  const requestID = headers["dg-request-id"]
  const modelName = headers["dg-model-name"]
  return SpeechStream.finish(route, state, {
-    ...(format.container === "none" && encoding !== undefined
-      ? SpeechStream.pcm(encoding, SpeechStream.sampleRate(mediaType), mediaType)
+    ...(container === "none" && headerless !== undefined
+      ? SpeechStream.pcm(
+          headerless.encoding,
+          SpeechStream.sampleRate(mediaType) ?? context.request.providerOptions?.sampleRate ?? headerless.sampleRate,
+          mediaType,
+        )
      : // Deepgram's default encoding is MP3; WAV is a container around any encoding.
-        { mediaType, info: { format: format.container === "wav" ? "wav" : (format.encoding ?? "mp3") } }),
+        { mediaType, info: { format: container === "wav" ? "wav" : (format.encoding ?? "mp3") } }),
    usage: SpeechStream.headerUsage("characters", headers["dg-char-count"]),
    providerMetadata:
      requestID === undefined && modelName === undefined
@@ -117,7 +128,7 @@ const finish = (state: State, context: MediaProtocol.ResponseContext<Request>) =
 // ---------------------------------------------------------------------------

 export const protocol = MediaProtocol.stream<Request, SpeechEvent, Uint8Array, State>(route, {
-  unsupported: ["voice", "language", "instructions", "timestamps"],
+  unsupported: ["voice", "language", "instructions"],
  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)/.test(model)) return "aspect_ratio"
+  if (/^fal-ai\/(nano-banana|flux-pro\/(v1\.1-ultra|kontext))/.test(model)) return "aspect_ratio"
  if (model.startsWith("fal-ai/flux")) return "image_size"
  return undefined
 }
@@ -63,20 +63,24 @@ 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 && !isEdit(id))
+  if ((request.images?.length ?? 0) > 1 && !takesImageList(id))
    return Effect.fail(
-      route.unsupported("media.images", `${id} takes one image_url; use an /edit endpoint for several images`),
+      route.unsupported(
+        "media.images",
+        `${id} takes one image_url; use an /edit or /multi endpoint for several images`,
+      ),
    )
  return Effect.void
 }

-// `/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")
+// `/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")

 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 edit = isEdit(request.model.id)
+  const list = takesImageList(request.model.id)
  return MediaProtocol.json(
    mergeJsonRecords(
      {
@@ -86,8 +90,8 @@ 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: edit && images.length > 0 ? images : undefined,
-        image_url: edit ? undefined : images[0],
+        image_urls: list && images.length > 0 ? images : undefined,
+        image_url: list ? undefined : images[0],
        mask_url: request.mask === undefined ? undefined : yield* FalQueue.mediaUrl(request.mask, route.name),
      },
      request.providerOptions,
@@ -112,12 +116,14 @@ 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) =>
-      Media.url(image.url, {
-        mediaType: image.content_type ?? undefined,
-        info: { width: image.width ?? undefined, height: image.height ?? undefined },
-      }),
-    ),
+    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 })
+      )
+    }),
    notices:
      flagged.length === 0
        ? undefined
@@ -526,19 +526,7 @@ const mapFinishReason = (finishReason: string | undefined, hasToolCalls: boolean
  if (finishReason === undefined) return hasToolCalls ? "tool-calls" : "unknown"
  if (finishReason === "STOP") return hasToolCalls ? "tool-calls" : "stop"
  if (finishReason === "MAX_TOKENS") return "length"
-  if (
-    finishReason === "IMAGE_SAFETY" ||
-    finishReason === "RECITATION" ||
-    finishReason === "SAFETY" ||
-    finishReason === "BLOCKLIST" ||
-    finishReason === "PROHIBITED_CONTENT" ||
-    finishReason === "SPII" ||
-    finishReason === "MODEL_ARMOR" ||
-    finishReason === "IMAGE_PROHIBITED_CONTENT" ||
-    finishReason === "IMAGE_RECITATION" ||
-    finishReason === "LANGUAGE"
-  )
-    return "content-filter"
+  if (GeminiGenerateContent.contentFiltered(finishReason)) return "content-filter"
  if (
    finishReason === "MALFORMED_FUNCTION_CALL" ||
    finishReason === "UNEXPECTED_TOOL_CALL" ||
@@ -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(
-      "image.n",
+      "media.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) =>
@@ -56,10 +56,18 @@ 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 returns raw PCM; request format "pcm" or omit it, then wrap the samples yourself`,
+      `${route.name} only accepts raw PCM as an explicit format; omit it to accept the provider's default output`,
    )
  const voiceName = SpeechStream.voiceID(request.voice)
  return MediaProtocol.json(
@@ -94,16 +102,29 @@ const step = Effect.fn("GoogleSpeech.step")(function* (state: State, frame: stri
    part.inlineData === undefined ? [] : [part.inlineData],
  )
  const next: State = { ...GeminiGenerateContent.track(state, chunk), mimeType: state.mimeType ?? audio[0]?.mimeType }
-  return [next, audio.flatMap((part) => SpeechStream.delta(next, part.data)[1])] as const
+  const events = audio.flatMap((part) => SpeechStream.delta(next, part.data)[1])
+  const withheld = next.chunks.length === 0 ? GeminiGenerateContent.withheld(route.name, chunk, frame) : undefined
+  if (withheld !== undefined) return yield* withheld
+  return [next, events] as const
 })

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

@@ -112,7 +133,7 @@ const finish = (state: State) => {
 // ---------------------------------------------------------------------------

 export const protocol = MediaProtocol.stream<Request, SpeechEvent, string, State>(route, {
-  unsupported: ["instructions", "speed", "timestamps"],
+  unsupported: ["instructions", "speed"],
  body: { from: fromRequest },
  frames: (bytes, context) => GeminiGenerateContent.frames(bytes, context.request.mode),
  initial: () => ({ chunks: [] }),
@@ -154,6 +154,9 @@ const step = Effect.fn("GoogleTranscription.step")(function* (state: State, fram
    .filter((item) => item.length > 0)
    .join(" ")
  const delta = text.length === 0 || state.text.length === 0 ? text : ` ${text}`
+  const withheld =
+    state.text.length + delta.length === 0 ? GeminiGenerateContent.withheld(route.name, chunk, frame) : undefined
+  if (withheld !== undefined) return yield* withheld
  const events: ReadonlyArray<TranscriptionEvent> = [
    ...(delta.length === 0 ? [] : [TranscriptionTextDeltaEvent.make({ delta })]),
    ...segments.map((segment) => TranscriptionSegmentEvent.make({ segment })),
@@ -169,6 +172,7 @@ const finish = (state: State) => {
      segments: state.segments.length === 0 ? undefined : state.segments,
      words: state.words.length === 0 ? undefined : state.words,
      usage: GeminiGenerateContent.usage(state.usage),
+      notices: GeminiGenerateContent.notices(route.name, state),
      providerMetadata: GeminiGenerateContent.providerMetadata(state),
    }),
  ])
@@ -149,8 +149,7 @@ const decodeResult = Effect.fn("GoogleVideo.decodeResult")(function* (
  const output = yield* decodeOperation(response)
  const operation = output.value
  const status = statusOf(operation)
-  if (status === "running")
-    return yield* output.invalid(`${route.name} operation ${context.token.operation} has not finished`)
+  if (status === "running") return yield* output.pending(context.token.operation)
  if (status === "failed")
    return yield* output.ended(
      "failed",
@@ -48,15 +48,17 @@ const Usage = Schema.Struct({
  output_tokens_details: Schema.optional(Schema.Record(Schema.String, Schema.Unknown)),
 })

-const OpenAIImageResponse = Schema.Struct({
-  data: Schema.Array(
-    Schema.Struct({
-      b64_json: Schema.optional(Schema.String),
-      url: Schema.optional(Schema.String),
-      revised_prompt: Schema.optional(Schema.String),
-    }),
-  ),
+/** 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,
  usage: Schema.optional(Usage),
 })

@@ -69,11 +71,13 @@ 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),
  }),
@@ -92,6 +96,9 @@ 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
 }

@@ -110,10 +117,6 @@ 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}`),
@@ -194,21 +197,34 @@ const usage = (value: Schema.Schema.Type<typeof Usage> | undefined): MediaUsage
        details: { openai: value },
      }

-const eventImage = (frame: string, label: string, data: string, format: string) =>
+/** `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+)$/)
+  return match ? { format, width: Number(match[1]), height: Number(match[2]) } : { format }
+}
+
+const eventImage = (frame: string, label: string, data: string, format: string, size: string | undefined) =>
  MediaInput.decodedAsset((message, cause) => route.frameError(message, frame, cause), label, data, `image/${format}`, {
-    info: { format },
+    info: info(format, size),
  })

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

@@ -237,7 +257,17 @@ 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 } } }),
+    ImageFinishEvent.make({
+      usage: state.usage,
+      providerMetadata: {
+        openai: {
+          outputFormat: state.format,
+          size: state.size,
+          quality: state.quality,
+          background: state.background,
+        },
+      },
+    }),
  ])
 }

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

-// Only GPT-6 Astra accepts `configuration_update`, and never alongside automatic `context_management` compaction.
+// 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.
 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$/i.test(request.model.id)
+  return /(?:^|\/)gpt-6-(?:astra|sol|luna)$/i.test(request.model.id)
 }

 const nativeImageToolInput = (tool: ToolDefinition) => {
@@ -60,7 +60,17 @@ interface State extends SpeechStream.Audio {
 // `sse` is not supported for `tts-1` or `tts-1-hd`; those models stream the raw audio body instead.
 const supportsSse = (model: string) => !/^tts-1(-hd)?(-|$)/.test(model)

+const FORMATS = new Set(["mp3", "opus", "aac", "flac", "wav", "pcm"])
+
 const fromRequest = Effect.fn("OpenAISpeech.fromRequest")(function* (request: MediaProtocol.Addressed<Request>) {
+  // Not in `unsupported`: that list would also reject `timestamps: false`, which asks for nothing.
+  if (request.timestamps === true)
+    return yield* route.unsupported("media.timestamps", `${route.name} does not return timestamps`)
+  if (request.format !== undefined && !FORMATS.has(request.format))
+    return yield* route.unsupported(
+      "media.format",
+      `${route.name} supports the mp3, opus, aac, flac, wav, and pcm formats, not "${request.format}"`,
+    )
  return MediaProtocol.json(
    mergeJsonRecords(
      {
@@ -109,7 +119,9 @@ const onEvent = Effect.fn("OpenAISpeech.onEvent")(function* (state: State, frame

 const finish = (state: State, context: MediaProtocol.ResponseContext<Request>) => {
  if (isSse(context.body) && !state.done) return Effect.fail(route.incomplete())
-  const format = context.request.format ?? "mp3"
+  // The sent body reflects `providerOptions` and `http.body` overrides of `format`.
+  const sent = context.body.type === "json" ? context.body.value.response_format : undefined
+  const format = typeof sent === "string" ? sent : "mp3"
  return SpeechStream.finish(route, state, {
    ...(format === "pcm" ? SpeechStream.pcm("pcm_s16le", PCM_SAMPLE_RATE) : SpeechStream.container(format)),
    usage: state.usage,
@@ -121,7 +133,7 @@ const finish = (state: State, context: MediaProtocol.ResponseContext<Request>) =
 // ---------------------------------------------------------------------------

 export const protocol = MediaProtocol.stream<Request, SpeechEvent, string | Uint8Array, State>(route, {
-  unsupported: ["language", "timestamps"],
+  unsupported: ["language"],
  body: { from: fromRequest },
  frames: (bytes, context) => (isSse(context.body) ? Framing.sse.frame(bytes) : bytes),
  initial: () => ({ chunks: [], done: false }),
@@ -1,8 +1,9 @@
 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 { mergeJsonRecords, type MediaUsage } from "../schema/index.js"
+import { AIError, mergeJsonRecords, type MediaUsage } from "../schema/index.js"
 import {
  TranscriptionFinishEvent,
  TranscriptionModel,
@@ -59,6 +60,9 @@ 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 }),
 ])
@@ -75,14 +79,23 @@ 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)

@@ -118,10 +131,12 @@ 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)
@@ -173,7 +188,7 @@ 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: request.mode === "stream" ? true : undefined,
+      stream: streamsEvents(request) ? true : undefined,
    },
    {
      overlay: mergeJsonRecords(request.providerOptions, request.http?.body),
@@ -196,7 +211,15 @@ 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: ${event.message ?? event.error?.message ?? "unknown error"}`,
+        rawBody: frame,
+      }),
+    })
  if (event.type === "transcript.text.done") return [{ ...state, transcript: event }, []] as const
  if (event.type === "transcript.text.delta")
    return [state, event.delta.length === 0 ? [] : [TranscriptionTextDeltaEvent.make({ delta: event.delta })]] as const
@@ -246,7 +269,7 @@ export const protocol = MediaProtocol.stream<Request, TranscriptionEvent, Frame,
  unsupported: ["speakers"],
  body: { from: fromRequest },
  frames: (bytes, context) =>
-    context.request.mode === "stream"
+    streamsEvents(context.request)
      ? Framing.sse.frame(bytes)
      : Framing.document.frame(bytes).pipe(Stream.map((document) => ({ document }))),
  initial: () => ({ segments: [] }),
@@ -132,8 +132,7 @@ const decodeResult = Effect.fn("ReplicateImages.decodeResult")(function* (
      status,
      `${route.name} prediction ${context.token.id} ${prediction.status}${typeof prediction.error === "string" ? `: ${prediction.error}` : ""}`,
    )
-  if (status !== "completed")
-    return yield* output.invalid(`${route.name} prediction ${context.token.id} has not finished`)
+  if (status !== "completed") return yield* output.pending(context.token.id)
  if (prediction.data_removed === true)
    return yield* output.ended("expired", `${route.name} removed the output of prediction ${context.token.id}`)
  if (!isOutput(prediction.output))
@@ -141,8 +141,7 @@ const decodeResult = Effect.fn("RunwayVideo.decodeResult")(function* (
  }
  if (status === "cancelled")
    return yield* output.ended("cancelled", `${route.name} task ${context.token.taskID} was cancelled`)
-  if (status !== "completed")
-    return yield* output.invalid(`${route.name} task ${context.token.taskID} has not finished`)
+  if (status !== "completed") return yield* output.pending(context.token.taskID)
  const urls = task.output ?? []
  if (urls.length === 0) return yield* output.invalid(`${route.name} task succeeded without any output`)
  return new VideoResponse({
@@ -171,7 +170,7 @@ 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 },
+  cancel: { method: "DELETE", path: taskPath, activeOnly: true },
 })

 const startPath = (request: Request) => {
@@ -175,7 +175,7 @@ const decodeUpscaleResult = Effect.fn("StabilityImages.decodeUpscaleResult")(fun
 ) {
  if (response.status === 202) {
    const output = yield* upscaleRoute.text(response)
-    return yield* output.invalid(`${upscaleRoute.name} upscale ${context.token.id} has not finished`)
+    return yield* output.pending(context.token.id)
  }
  return yield* decodeUpscaleImage(response)
 })
@@ -72,6 +72,44 @@ export const blocked = (name: string, chunk: Chunk, frame: string) => {
  })
 }

+const CONTENT_FILTER_REASONS = new Set([
+  "IMAGE_SAFETY",
+  "RECITATION",
+  "SAFETY",
+  "BLOCKLIST",
+  "PROHIBITED_CONTENT",
+  "SPII",
+  "MODEL_ARMOR",
+  "IMAGE_PROHIBITED_CONTENT",
+  "IMAGE_RECITATION",
+  "LANGUAGE",
+])
+
+/** Finish reasons for which Gemini stops output on safety or policy grounds. */
+export const contentFiltered = (finishReason: string | undefined) =>
+  finishReason !== undefined && CONTENT_FILTER_REASONS.has(finishReason)
+
+/** Callers check that the response produced no output: a policy stop after output is a partial result instead. */
+export const withheld = (name: string, chunk: Chunk, frame: string) => {
+  const finishReason = chunk.candidates?.[0]?.finishReason
+  if (!contentFiltered(finishReason)) return undefined
+  return new AIError({
+    reason: new ContentPolicyError({ message: `${name} withheld its output (${finishReason})`, body: frame }),
+  })
+}
+
+/** Any finish reason other than `STOP` means the output may be cut short, so it is surfaced rather than dropped. */
+export const notices = (name: string, state: Metadata): ReadonlyArray<Media.Notice> | undefined =>
+  state.finishReason === undefined || state.finishReason === "STOP"
+    ? undefined
+    : [
+        {
+          type: contentFiltered(state.finishReason) ? "filtered" : "other",
+          message: `${name} finished with ${state.finishReason}`,
+          providerMetadata: { google: { finishReason: state.finishReason } },
+        },
+      ]
+
 export const usage = (usage: UsageMetadata | undefined): MediaUsage | undefined =>
  usage === undefined
    ? undefined
@@ -85,6 +85,7 @@ export const finish = (
    readonly mediaType: string | undefined
    readonly info?: Media.Info
    readonly usage?: MediaUsage
+    readonly notices?: ReadonlyArray<Media.Notice>
    readonly providerMetadata?: ProviderMetadata
    readonly detail?: string
  },
@@ -97,6 +98,7 @@ export const finish = (
    SpeechFinishEvent.make({
      audio: Media.bytes(concatBytes(state.chunks), output.mediaType, { info: output.info }),
      usage: output.usage,
+      notices: output.notices,
      providerMetadata: output.providerMetadata,
    }),
  ])
@@ -101,7 +101,8 @@ const decodeResponse = Effect.fn("XAIImages.decodeResponse")(function* (
  )
  if (images.length === 0) return yield* output.invalid(`${route.name} returned no images`)
  const usage = ProviderShared.isRecord(decoded.usage) ? decoded.usage : undefined
-  // xAI reports image counts rather than tokens, seconds, or credits; the raw record stays in provider metadata.
+  // xAI reports a USD cost (`cost_in_usd_ticks`) rather than tokens, seconds, or credits; the raw record stays in
+  // provider metadata.
  return new ImageResponse({
    images,
    providerMetadata: usage === undefined ? undefined : { xai: { usage } },
@@ -136,8 +136,7 @@ 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.invalid(`${route.name} request ${context.token.requestID} has not finished`)
+  if (status === "running") return yield* output.pending(context.token.requestID)
  if (status === "failed") {
    const code = decoded.error?.code ?? undefined
    const message = decoded.error?.message ?? undefined
@@ -1,7 +1,6 @@
-import { Effect, Schema } from "effect"
+import { Duration, 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"
@@ -9,6 +8,7 @@ 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: decoded.data.map((item) => Media.url(item.url)),
+    images: yield* Effect.forEach(decoded.data, (item) => MediaProtocol.expiringUrl(item.url, OUTPUT_RETENTION)),
    // Z.ai reports applied content filters alongside a successful result; surface them instead of dropping them.
    notices:
      filters.length === 0
@@ -137,6 +137,11 @@ 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
  }
 }

@@ -195,7 +200,8 @@ 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); `contentPolicy` is a moderated result.
+   * 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.
   */
  const text = Effect.fn("MediaProtocol.text")(function* (response: HttpClientResponse.HttpClientResponse) {
    const http = context(response)
@@ -224,6 +230,14 @@ 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 ${id} has not finished; await it before reading the result`,
+            body,
+            http,
+          }),
+        }),
      contentPolicy: (message: string) => new AIError({ reason: new ContentPolicyError({ message, body, http }) }),
    }
  })
@@ -285,9 +299,8 @@ export const status = <Table extends Record<string, Status>>(
  raw: string,
  output: Output,
 ): Effect.Effect<Status, AIError> => {
-  const normalized: Status | undefined = table[raw]
-  if (normalized === undefined) return Effect.fail(output.invalid(`Unknown generation status "${raw}"`))
-  return Effect.succeed(normalized)
+  if (!Object.hasOwn(table, raw)) return Effect.fail(output.invalid(`Unknown generation status "${raw}"`))
+  return Effect.succeed(table[raw])
 }

 /** 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 } from "../generation.js"
+import { Generation, isTerminal } from "../generation.js"
 import type { Media } from "../media.js"
 import {
  AIError,
@@ -164,14 +164,19 @@ 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: poll(protocol.status),
+      status,
      result: poll(protocol.result),
      cancel:
-        cancel === undefined
-          ? undefined
-          : transport.call(cancel.method, cancel.path(token), http, execute).pipe(Effect.asVoid),
+        send !== undefined && cancel?.activeOnly
+          ? status.pipe(Effect.flatMap((snapshot) => (isTerminal(snapshot.status) ? Effect.void : send)))
+          : send,
    }
  }

@@ -380,7 +385,11 @@ const encode = (body: MediaProtocol.Body | undefined, headers: Headers.Headers)
  }
 }

-/** Common fields are never silently dropped: a present field the protocol declared unsupported fails typed. */
+/**
+ * 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.
+ */
 const rejectUnsupported = <Request extends object>(
  route: string,
  provider: ProviderID,
@@ -351,10 +351,34 @@ 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}`, () =>
@@ -23,6 +23,7 @@ import { Provider as ProviderSubpath } from "@opencode/ai/provider"
 import {
  AssemblyAI,
  Baseten,
+  BlackForestLabs,
  Cartesia,
  CloudflareAIGateway,
  CloudflareWorkersAI,
@@ -32,14 +33,18 @@ import {
  Fal,
  Fireworks,
  Google,
+  Meta,
  OpenCodeZen,
  OpenAI,
  OpenAICompatible,
  OpenRouter,
+  Replicate,
  Runway,
+  Stability,
  TypeSafeAI,
  VercelAIGateway,
  XAI,
+  ZAI,
 } from "@opencode/ai/providers"
 import {
  OpenAIChat,
@@ -151,8 +156,34 @@ 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")
@@ -97,6 +97,26 @@ 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")
@@ -78,8 +78,11 @@ describe("Image", () => {
        mediaType: "image/webp",
      })
      expect(yield* response.image.bytes()).toEqual(Uint8Array.from([1, 2, 3]))
-      expect(response.image.providerMetadata).toEqual({ openai: { revisedPrompt: "A precise robot" } })
+      expect(response.image.info).toEqual({ format: "webp", width: 2048, height: 2048 })
      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(
@@ -107,8 +110,11 @@ describe("Image", () => {
                })
                return input.respond(
                  JSON.stringify({
-                    data: [{ b64_json: "AQID", revised_prompt: "A precise robot" }, { b64_json: "BAUG" }],
+                    data: [{ b64_json: "AQID" }, { 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" } },
@@ -144,6 +150,7 @@ 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" })
    }),
  )

@@ -725,6 +732,7 @@ 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,
@@ -735,7 +743,6 @@ 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({
@@ -749,9 +756,9 @@ 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],
@@ -761,6 +768,80 @@ 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",
@@ -768,6 +849,56 @@ 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"), {
@@ -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 { Media, Message } from "../src/index.js"
+import { AIError, Media, Message } from "../src/index.js"
 import { it } from "./lib/effect.js"
 import { dynamicResponse, scriptedResponses } from "./lib/http.js"

@@ -161,6 +161,56 @@ 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
@@ -33,6 +33,8 @@ 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 },
  )
@@ -29,7 +29,11 @@ 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" },
+      })
    }),
  )

@@ -76,8 +80,13 @@ 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 })
-      expect(events.find(ImageEvent.is.finish)?.usage).toMatchObject({ type: "tokens" })
+      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" },
+      })
    }),
  )
 })
@@ -44,7 +44,12 @@ 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) })
+      expect(finish.usage).toMatchObject({
+        type: "tokens",
+        input: expect.any(Number),
+        output: expect.any(Number),
+        details: { openai: { input_token_details: { audio_tokens: expect.any(Number) } } },
+      })
    }),
  )

@@ -32,7 +32,12 @@ describe("Z.ai Images", () => {

      expect(response.images).toHaveLength(1)
      expect(response.image.mediaType).toBe("application/octet-stream")
-      expect(response.image.source).toEqual({ type: "url", url: "https://cdn.z.ai/generated.png" })
+      // 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.notices).toEqual([
        {
          type: "moderated",
@@ -28,15 +28,94 @@ 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) } }] },
+                  finishReason: "STOP",
+                },
+              ],
+            }),
+            "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("describes OpenAI audio in the format the request body actually asked for", () =>
+    Effect.gen(function* () {
+      const [pcm, wav] = yield* Effect.all([
+        Speech.generate({ model: openai, text: "Hi", format: "mp3", providerOptions: { response_format: "pcm" } }),
+        Speech.generate({ model: openai, text: "Hi", http: { body: { response_format: "wav" } } }),
+      ]).pipe(Effect.provide(respond("\u0001\u0002", "application/octet-stream")))
+      expect(pcm.audio.mediaType).toBe("audio/pcm")
+      expect(pcm.audio.info).toEqual({ format: "pcm", encoding: "pcm_s16le", sampleRate: 24000, channels: 1 })
+      expect(wav.audio.mediaType).toBe("audio/wav")
+      expect(wav.audio.info?.format).toBe("wav")
+    }),
+  )
+
+  it.effect("describes Deepgram raw encodings in their default WAV container", () =>
+    Effect.gen(function* () {
+      const response = yield* Speech.generate({ model: deepgram, text: "Hi", providerOptions: { encoding: "mulaw" } })
+      expect(response.audio.mediaType).toBe("audio/wav")
+      expect(response.audio.info?.format).toBe("wav")
+    }).pipe(Effect.provide(respond("RIFF....WAVEfmt ", "audio/wav"))),
+  )
+
+  it.effect("always gives headerless Deepgram PCM a sample rate", () =>
+    Effect.gen(function* () {
+      const [requested, defaulted] = yield* Effect.all([
+        Speech.generate({
+          model: deepgram,
+          text: "Hi",
+          providerOptions: { encoding: "mulaw", container: "none", sampleRate: 16000 },
+        }),
+        Speech.generate({ model: deepgram, text: "Hi", providerOptions: { encoding: "alaw", container: "none" } }),
+      ]).pipe(Effect.provide(respond("\u0001\u0002", "audio/basic")))
+      expect(requested.audio.info).toEqual({ format: "pcm", encoding: "pcm_mulaw", sampleRate: 16000, channels: 1 })
+      expect(defaulted.audio.info).toEqual({ format: "pcm", encoding: "pcm_alaw", sampleRate: 8000, channels: 1 })
+    }),
+  )
+
+  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(
        [
          Speech.generate({ model: openai, text: "Hi", timestamps: true }),
+          Speech.generate({ model: openai, text: "Hi", format: "ogg" }),
          Speech.generate({ model: google, text: "Hi", format: "mp3" }),
          Speech.generate({ model: google, text: "Hi", instructions: "Warm." }),
          collect(Speech.stream({ model: elevenlabs, text: "Hi", voice, format: "wav" })),
@@ -48,16 +127,57 @@ describe("Speech", () => {
        [
          ["UnsupportedOperation", "media.timestamps"],
          ["UnsupportedOperation", "media.format"],
+          ["UnsupportedOperation", "media.format"],
          ["UnsupportedOperation", "media.instructions"],
          ["UnsupportedOperation", "media.format"],
          ["UnsupportedOperation", "media.format"],
          ["UnsupportedOperation", "media.voice"],
        ],
      )
-      expect(errors[1].reason).toMatchObject({ provider: "google", route: "google-speech" })
+      expect(errors[1].reason).toMatchObject({ provider: "openai", route: "openai-speech" })
+      expect(errors[2].reason).toMatchObject({ provider: "google", route: "google-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" } }] },
+            finishReason: "STOP",
+          },
+        ],
+      })
+      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!" })
@@ -88,6 +208,38 @@ describe("Speech", () => {
    }),
  )

+  it.effect("surfaces Gemini speech that ended without STOP instead of returning it as complete", () =>
+    Effect.gen(function* () {
+      const document = (finishReason?: string) =>
+        JSON.stringify({
+          candidates: [
+            {
+              content: { parts: [{ inlineData: { mimeType: "audio/L16;codec=pcm;rate=24000", data: "AQI=" } }] },
+              finishReason,
+            },
+          ],
+        })
+      const withheld = JSON.stringify({ candidates: [{ finishReason: "SAFETY" }] })
+      const generate = (body: string) =>
+        Speech.generate({ model: google, text: "Hi" }).pipe(Effect.provide(respond(body, "application/json")))
+
+      const truncated = yield* generate(document()).pipe(Effect.flip)
+      const partial = yield* generate(document("MAX_TOKENS"))
+      const policy = yield* generate(withheld).pipe(Effect.flip)
+
+      expect(truncated.reason).toMatchObject({ _tag: "InvalidProviderOutput", classification: "incomplete-stream" })
+      expect(yield* partial.audio.bytes()).toEqual(Uint8Array.from([1, 2]))
+      expect(partial.notices).toEqual([
+        {
+          type: "other",
+          message: "Google Speech finished with MAX_TOKENS",
+          providerMetadata: { google: { finishReason: "MAX_TOKENS" } },
+        },
+      ])
+      expect(policy.reason).toMatchObject({ _tag: "ContentPolicy", body: withheld })
+    }),
+  )
+
  it.effect("parses ElevenLabs timestamped records split across network chunks", () =>
    Effect.gen(function* () {
      const record = (bytes: ReadonlyArray<number>, character: string, start: number) =>
@@ -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 } from "./lib/http.js"
+import { dynamicResponse, json, observe, type Call } from "./lib/http.js"

 const layer = (handler: Parameters<typeof dynamicResponse>[0]) =>
  TranscriptionClient.layer.pipe(Layer.provideMerge(dynamicResponse(handler)))
@@ -25,7 +25,6 @@ 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" }),
@@ -53,7 +52,6 @@ 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"],
@@ -70,6 +68,67 @@ 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",
    () =>
@@ -171,4 +230,76 @@ 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" },
+            }),
+          ),
+        ),
+      ),
+    ),
+  )
+
+  it.effect("surfaces Gemini transcripts that ended without STOP instead of returning them as complete", () =>
+    Effect.gen(function* () {
+      const document = (finishReason?: string) =>
+        JSON.stringify({
+          candidates: [{ content: { parts: [{ audioTranscription: { text: "Hello" } }] }, finishReason }],
+        })
+      const withheld = JSON.stringify({ candidates: [{ finishReason: "SAFETY" }] })
+      const generate = (body: string) =>
+        Transcription.generate({ model: google, audio }).pipe(
+          Effect.provide(
+            layer((input) => Effect.succeed(input.respond(body, { headers: { "content-type": "application/json" } }))),
+          ),
+        )
+
+      const truncated = yield* generate(document()).pipe(Effect.flip)
+      const partial = yield* generate(document("MAX_TOKENS"))
+      const policy = yield* generate(withheld).pipe(Effect.flip)
+
+      expect(truncated.reason).toMatchObject({ _tag: "InvalidProviderOutput", classification: "incomplete-stream" })
+      expect(partial.text).toBe("Hello")
+      expect(partial.notices).toEqual([
+        {
+          type: "other",
+          message: "Google Transcription finished with MAX_TOKENS",
+          providerMetadata: { google: { finishReason: "MAX_TOKENS" } },
+        },
+      ])
+      expect(policy.reason).toMatchObject({ _tag: "ContentPolicy", body: withheld })
+    }),
+  )
 })
@@ -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 with the API version header, polls the task, and reports credits", () =>
+  it.effect("submits image_to_video, polls the task, reports credits, and keeps the finished task on cancel", () =>
    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 input.respond(null, { status: 204 })
+              if (call.method === "DELETE") return yield* Effect.die("cancel deleted a finished Runway task")
              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 })
@@ -653,6 +653,32 @@ 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}`,
      ])
    }),
@@ -812,3 +838,55 @@ 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" }))))),
+  )
+})
@@ -39,6 +39,30 @@ test("restores review mode and selected file per session", async ({ page }) => {
  await expectSelectedFile(page, "gamma.ts")
 })

+test("shows and restores last turn changes from the session diff", async ({ page }) => {
+  await setup(page)
+  await page.route(`**/api/session/${sessionA}/diff**`, (route) =>
+    route.fulfill({
+      status: 200,
+      contentType: "application/json",
+      body: JSON.stringify({ data: [diff("src/delta.ts")] }),
+    }),
+  )
+  await page.goto(sessionHref(sessionA))
+  await expectSessionTitle(page, titleA)
+  await page.getByRole("button", { name: "Toggle review" }).click()
+
+  await page.getByRole("button", { name: "Git changes" }).click()
+  await page.getByRole("option", { name: "Last turn changes" }).click()
+  await expect(page.getByRole("button", { name: "Last turn changes" })).toBeVisible()
+  await expectSelectedFile(page, "delta.ts")
+
+  await page.reload()
+  await expectSessionTitle(page, titleA)
+  await expect(page.getByRole("button", { name: "Last turn changes" })).toBeVisible()
+  await expectSelectedFile(page, "delta.ts")
+})
+
 for (const tab of ["Context", "Open file", "README.md"]) {
  test(`restores the selected ${tab} pane tab after switching sessions and reloading`, async ({ page }) => {
    await setup(page)
@@ -1,5 +1,5 @@
 import { expect, test, type Page } from "@playwright/test"
-import type { OpenCodeEvent, SessionMessageInfo } from "@opencode/client/promise"
+import type { OpenCodeEvent, SessionInboxInfo, SessionMessageInfo } from "@opencode/client/promise"
 import { base64Encode } from "@opencode/util/encode"
 import { mockOpenCodeServer } from "../utils/mock-server"
 import { expectAppVisible } from "../utils/waits"
@@ -14,7 +14,12 @@ type InboxRow = {
  sessionID: string
  time: { created: number }
  type: "user"
-  payload: { text: string; metadata?: Record<string, unknown> }
+  payload: {
+    text: string
+    metadata?: Record<string, unknown>
+    files?: Extract<SessionInboxInfo, { type: "user" }>["payload"]["files"]
+    agents?: Extract<SessionInboxInfo, { type: "user" }>["payload"]["agents"]
+  }
  delivery: "steer" | "queue"
 }

@@ -29,7 +34,7 @@ function createQueueMock(seed: string[], messages: SessionMessageInfo[] = []) {
  }))
  const events: OpenCodeEvent[] = []
  const prompts: Record<string, unknown>[] = []
-  const changes: { inboxID: string; action: "cancel" | "steer" }[] = []
+  const changes: { inboxID: string; action: "cancel" | "steer" | "queue" }[] = []
  const log: string[] = []
  let sequence = 0
  const emit = <Type extends OpenCodeEvent["type"]>(
@@ -234,6 +239,108 @@ 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": "2.0.16",
+  "version": "2.0.18",
  "description": "",
  "type": "module",
  "exports": {
@@ -47,6 +47,7 @@ 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.
@@ -168,6 +168,7 @@ function ComposerStory(props: {
              alternate: () => props.alternate,
              editing: () => undefined,
              confirmEdit() {},
+              undoing: () => false,
              cancelEdit() {},
              editFirst: () => false,
            }
@@ -16,6 +16,7 @@ export function Composer(props: {
  class?: string
  model: ComposerModel
  borderUnderlay?: boolean
+  readOnly?: boolean
  suggestionBoundary?: () => HTMLElement | undefined
 }) {
  const dialog = useDialog()
@@ -27,6 +28,7 @@ export function Composer(props: {
      <ComposerEditor
        controller={props.model}
        borderUnderlay={props.borderUnderlay}
+        readOnly={props.readOnly}
        class={props.class}
        modelControlsVisible={!props.model.model.loading}
        attachKeybind={command.keybindParts("file.attach")}
@@ -371,6 +371,7 @@ export function createComposerModel(adapter: ComposerAdapter, options?: { queue?
        onSubmit: (submitOptions) => {
          if (!available()) return
          const queue = options?.queue
+          if (queue?.undoing()) return
          // Confirming an edit re-admits the queued prompt instead of sending
          // the composer value as a new prompt. Enter keeps it queued in
          // place; the alternate action sends it as a steer.
@@ -86,6 +86,7 @@ export function createHomeSessionsController(home: HomeController) {
      sessions: indexedSessions,
      projectDirectories,
      projects: home.project.list,
+      resolveProject: (session) => home.server.focusedContext()?.projects.forSession(session),
    }),
  )
  const records = createMemo(() => allRecords().slice(0, HOME_SESSION_LIMIT))
@@ -291,6 +292,7 @@ export function createHomeSessionsController(home: HomeController) {
          sessions: () => [result],
          projectDirectories,
          projects: home.project.list,
+          resolveProject: ctx.projects.forSession,
        })[0]
      },
      create: home.project.openNewSession,
@@ -18,6 +18,7 @@ export function buildHomeSessionRecords(input: {
  sessions: () => SessionInfo[]
  projectDirectories: () => string[] | undefined
  projects: () => LocalProject[]
+  resolveProject?: (session: SessionInfo) => LocalProject | undefined
 }) {
  const selected = input.projectDirectories()
  const directories = selected ? new Set(selected.map(pathKey)) : undefined
@@ -27,11 +28,12 @@ export function buildHomeSessionRecords(input: {
  return [...new Map(sessions.map((session) => [session.id, session] as const)).values()]
    .sort(compareSessionTime)
    .map((session) => {
-      const project = homeProjectForSession(session, input.projects()) ?? {
-        id: session.projectID,
-        worktree: session.location.directory,
-        expanded: false,
-      }
+      const project = input.resolveProject?.(session) ??
+        homeProjectForSession(session, input.projects()) ?? {
+          id: session.projectID,
+          worktree: session.location.directory,
+          expanded: false,
+        }
      return { session, project, projectName: displayName(project) }
    })
 }
@@ -874,6 +874,9 @@ export const dict = {
  "session.queue.send": "Send",
  "session.queue.steerTooltip": "Send without interrupting",
  "session.queue.remove": "Remove",
+  "session.queue.undo": "Undo",
+  "session.queue.undoShell": "Leave shell mode before undoing a queued prompt",
+  "session.queue.undoUnavailable": "Edit this prompt in the queue to preserve its file context",
  "session.queue.reorder": "Reorder queued prompt",
  "session.queue.attachments.one": "{{count}} attachment",
  "session.queue.attachments.other": "{{count}} attachments",
@@ -18,6 +18,8 @@ import { showToast } from "@/shell/notifications/toast"
 import { formatServerError } from "./errors"
 import { useSettings } from "@/settings/model"
 import { timelinePreset } from "@opencode/session-ui/timeline/detail"
+import type { SessionInfo } from "@opencode/client/promise"
+import { resolveProjectForSession, resolveSessionDetailsProject } from "@/shell/layout/helpers"

 export const { use: useGlobal, provider: GlobalProvider } = createSimpleContext({
  name: "Global",
@@ -180,6 +182,13 @@ function createServerController(
  }

  const projectsList = createMemo(() => projects.list().map(enrich))
+  const forSession = (session: SessionInfo) => {
+    const project = resolveProjectForSession(session, projectsList(), sync.data.project)
+    if (!project) return
+    return "expanded" in project ? project : { ...project, expanded: false }
+  }
+  const detailsForSession = (session: SessionInfo) =>
+    resolveSessionDetailsProject(session, projectsList(), sync.data.project)
  const recentlyClosedList = createMemo(() => {
    const known = new Set(sync.data.project.map((project) => pathKey(project.worktree)))
    return projects
@@ -200,6 +209,8 @@ function createServerController(
    projects: {
      ...projects,
      list: projectsList,
+      forSession,
+      detailsForSession,
      resolve: enrich,
      recentlyClosed: recentlyClosedList,
    },
@@ -175,6 +175,18 @@ function SessionQueueRow(props: { queue: SessionQueueView; id: string; index: nu
                  {props.queue.working() ? language.t("session.queue.steer") : language.t("session.queue.send")}
                </Button>
              </Tooltip>
+              <Tooltip placement="top" value={language.t("session.queue.undo")}>
+                <IconButton
+                  data-action="session-queue-undo"
+                  type="button"
+                  size="small"
+                  variant="ghost-muted"
+                  icon={<Icon name="arrow-down-to-line" />}
+                  disabled={props.queue.busy()}
+                  aria-label={language.t("session.queue.undo")}
+                  onClick={() => props.queue.undo(props.id)}
+                />
+              </Tooltip>
            </Show>
            <Tooltip placement="top" value={language.t("session.queue.remove")}>
              <IconButton
@@ -1,6 +1,6 @@
 import { describe, expect, test } from "bun:test"
 import type { SessionInboxInfo } from "@opencode/client/promise"
-import { queuedPromptAttachments, queuedPromptRows } from "./queue"
+import { queuedPromptAttachments, queuedPromptUndoDraft, queuedPromptRows } from "./queue"

 const queued = [
  {
@@ -104,3 +104,43 @@ describe("queuedPromptAttachments", () => {
    expect(queuedPromptAttachments(item)).toEqual([])
  })
 })
+
+describe("queuedPromptUndoDraft", () => {
+  test("keeps full text, structured mentions, and inline images", () => {
+    const item = {
+      ...queued[0],
+      payload: {
+        text: "inspect @main.ts with @build",
+        files: [
+          {
+            data: "aGk=",
+            mime: "text/plain",
+            source: { type: "uri" as const, uri: "file:///repo/main.ts" },
+            name: "main.ts",
+            mention: { start: 8, end: 16, text: "@main.ts" },
+          },
+          { data: "aGk=", mime: "image/png", source: { type: "inline" as const }, name: "shot.png" },
+        ],
+        agents: [{ name: "build", mention: { start: 22, end: 28, text: "@build" } }],
+      },
+    } satisfies SessionInboxInfo
+    expect(queuedPromptUndoDraft(item)).toMatchObject([
+      { type: "text", content: "inspect " },
+      { type: "file", content: "@main.ts", url: "data:text/plain;base64,aGk=" },
+      { type: "text", content: " with " },
+      { type: "agent", content: "@build", name: "build" },
+      { type: "image", filename: "shot.png" },
+    ])
+  })
+
+  test("does not drop hidden file context", () => {
+    const item = {
+      ...queued[0],
+      payload: {
+        text: "inspect this",
+        files: [{ data: "aGk=", mime: "text/plain", source: { type: "uri" as const, uri: "file:///repo/main.ts" } }],
+      },
+    } satisfies SessionInboxInfo
+    expect(queuedPromptUndoDraft(item)).toBeUndefined()
+  })
+})
@@ -3,10 +3,11 @@ import { createStore } from "solid-js/store"
 import { useMutation } from "@tanstack/solid-query"
 import type { SessionInboxInfo } from "@opencode/client/promise"
 import { SessionMessage } from "@opencode/schema/session-message"
+import { Skill } from "@opencode/schema/skill"
 import type { ComposerDelivery } from "@/composer/adapter"
 import type { ComposerStateTarget } from "@/composer/submission-state"
 import type { ImageAttachmentPart, PathAttachmentPart, Prompt } from "@/composer/state"
-import { clonePrompt, isAttachment, promptLength } from "@/composer/prompt-parts"
+import { appendPrompt, clonePrompt, isAttachment, promptLength } from "@/composer/prompt-parts"
 import { buildPromptRequest } from "@/composer/request"
 import { blobDataUrl, createLegacyBlobReference } from "@/runtime/persistence/drafts"
 import { readPromptPresentation } from "@/composer/comment-note"
@@ -42,6 +43,7 @@ export function createSessionQueue(input: {
    mutationFn: async (
      change:
        | { type: "reorder"; inboxIDs: string[] }
+        | { type: "undo"; item: QueuedPrompt; prompt: Prompt }
        | {
            type: "edit"
            inboxIDs: string[]
@@ -54,6 +56,16 @@ export function createSessionQueue(input: {
          },
    ) => {
      if (change.type === "reorder") return rewrite(change.inboxIDs)
+      if (change.type === "undo") {
+        await server.api.session.inbox.cancel({ sessionID: input.sessionID, inboxID: change.item.id })
+        const draft = input.draft.current()
+        const prompt = promptLength(draft)
+          ? appendPrompt(draft, change.prompt)
+          : [...change.prompt, ...draft.filter(isAttachment)]
+        input.draft.set(prompt, promptLength(prompt))
+        input.restoreFocus(promptLength(prompt))
+        return
+      }
      const replacement = await editedPromptInput(
        input.sessionID,
        location().directory,
@@ -139,6 +151,21 @@ export function createSessionQueue(input: {
    if (state.editing?.id === id) cancelEdit()
    return server.api.session.inbox.cancel({ sessionID: input.sessionID, inboxID: id }).catch(() => notify())
  }
+  const undo = (id: string) => {
+    if (mutation.isPending || state.editing) return
+    const item = queued().find((entry) => entry.id === id)
+    if (!item) return
+    if (input.draft.mode.current() !== "normal") {
+      showToast({ title: language.t("session.queue.undoShell") })
+      return
+    }
+    const prompt = queuedPromptUndoDraft(item)
+    if (!prompt) {
+      showToast({ title: language.t("session.queue.undoUnavailable") })
+      return
+    }
+    mutation.mutate({ type: "undo", item, prompt })
+  }
  const reorder = (inboxIDs: string[]) => {
    if (mutation.isPending) return Promise.resolve()
    return mutation.mutateAsync({ type: "reorder", inboxIDs }).catch(() => undefined)
@@ -226,9 +253,11 @@ export function createSessionQueue(input: {
    editFirst,
    rows,
    busy: () => mutation.isPending,
+    undoing: () => mutation.isPending && mutation.variables?.type === "undo",
    working: input.working,
    steer,
    remove,
+    undo,
    edit,
    reorder,
  }
@@ -239,7 +268,7 @@ export type SessionQueue = ReturnType<typeof createSessionQueue>
 // The slice of the queue the panel renders and drives.
 export type SessionQueueView = Pick<
  SessionQueue,
-  "rows" | "editing" | "working" | "busy" | "steer" | "remove" | "edit" | "reorder"
+  "rows" | "editing" | "working" | "busy" | "steer" | "remove" | "undo" | "edit" | "reorder"
 >

 export function queuedPromptRows(items: QueuedPrompt[], replacement?: { original: string; replacement: string }) {
@@ -249,7 +278,8 @@ export function queuedPromptRows(items: QueuedPrompt[], replacement?: { original
    .map((item) => ({
      id: item.id,
      text: queuedPromptText(item),
-      attachments: (item.payload.files?.length ?? 0) + (readPromptPresentation(item.payload.metadata)?.attachments.length ?? 0),
+      attachments:
+        (item.payload.files?.length ?? 0) + (readPromptPresentation(item.payload.metadata)?.attachments.length ?? 0),
    }))
 }

@@ -287,6 +317,88 @@ export function queuedPromptAttachments(item: QueuedPrompt): (ImageAttachmentPar
  ]
 }

+// Use the full model-visible text so comment notes and path references remain
+// in the draft. Convert mentioned files, agents, and skills back into editor
+// parts; a detached draft cannot represent non-mentioned file context.
+export function queuedPromptUndoDraft(item: QueuedPrompt): Prompt | undefined {
+  if (
+    item.payload.files?.some((file) => !isComposerAttachment(file) && !file.mention) ||
+    item.payload.agents?.some((agent) => !agent.mention) ||
+    item.payload.skills?.some((skill) => !skill.mention)
+  )
+    return
+  const text = item.payload.text
+  const references = [
+    ...(item.payload.files ?? []).flatMap((file) =>
+      file.mention
+        ? [
+            {
+              type: "file" as const,
+              content: file.mention.text,
+              start: file.mention.start,
+              end: file.mention.end,
+              path: file.name ?? file.mention.text.replace(/^@/, ""),
+              filename: file.name,
+              mime: file.mime,
+              url: `data:${file.mime};base64,${file.data}`,
+            },
+          ]
+        : [],
+    ),
+    ...(item.payload.agents ?? []).flatMap((agent) =>
+      agent.mention
+        ? [
+            {
+              type: "agent" as const,
+              content: agent.mention.text,
+              start: agent.mention.start,
+              end: agent.mention.end,
+              name: agent.name,
+            },
+          ]
+        : [],
+    ),
+    ...(item.payload.skills ?? []).flatMap((skill) =>
+      skill.mention
+        ? [
+            {
+              type: "skill" as const,
+              content: skill.mention.text,
+              start: skill.mention.start,
+              end: skill.mention.end,
+              id: Skill.ID.make(skill.id),
+              name: Skill.Name.make(skill.name),
+            },
+          ]
+        : [],
+    ),
+  ].sort((left, right) => left.start - right.start)
+  if (
+    references.some(
+      (part, index) =>
+        part.start < (references[index - 1]?.end ?? 0) || text.slice(part.start, part.end) !== part.content,
+    )
+  )
+    return
+  const parts: Prompt = references.flatMap((part, index) => {
+    const start = references[index - 1]?.end ?? 0
+    return [
+      ...(part.start > start
+        ? [{ type: "text" as const, content: text.slice(start, part.start), start, end: part.start }]
+        : []),
+      part,
+    ]
+  })
+  const start = references.at(-1)?.end ?? 0
+  return [
+    ...parts,
+    ...(text.length > start || !parts.length
+      ? [{ type: "text" as const, content: text.slice(start), start, end: text.length }]
+      : []),
+    ...queuedPromptAttachments(item).filter((part) => part.type === "image"),
+  ]
+}
+
 function isComposerAttachment(file: NonNullable<QueuedPrompt["payload"]["files"]>[number]) {
  return !file.mention && file.source.type === "inline"
 }
@@ -224,7 +224,12 @@ export function ActiveSessionComposerRegion(props: {
        <div class="relative">
          <SessionQueuePanel queue={props.model.queue} />
          <div class="relative z-10">
-            <Composer model={props.model.composer} borderUnderlay suggestionBoundary={props.suggestionBoundary} />
+            <Composer
+              model={props.model.composer}
+              borderUnderlay
+              readOnly={props.model.queue.undoing()}
+              suggestionBoundary={props.suggestionBoundary}
+            />
          </div>
        </div>
      }
@@ -21,7 +21,6 @@ import { reviewDiffDirectory, reviewDiffNeedsLoad, reviewRootDirectory } from ".
 import type { DiffStyle } from "./review-tab"

 export type ChangeMode = "git" | "branch" | "turn"
-type VcsMode = "git" | "branch"

 export function createSessionReview(input: {
  session: SessionModel
@@ -64,15 +63,13 @@ export function createSessionReview(input: {
    ) {
      list.push("branch")
    }
+    // Turn diffs compare session snapshots, which the server only captures in Git projects.
+    if (project?.vcs === "git" && input.session.identity.sessionID()) list.push("turn")
    return list
  })
  const mobileChanges = createMemo(
    () => !input.session.isDesktop() && !input.screen.terminal.open() && state.mobileTab === "changes",
  )
-  const vcsMode = createMemo<VcsMode | undefined>(() => {
-    const value = mode()
-    return value === "git" || value === "branch" ? value : undefined
-  })
  const vcsKey = createMemo(
    () =>
      [
@@ -90,22 +87,28 @@ export function createSessionReview(input: {
          (input.session.tabs.activeTab() === "review" || !!input.session.tabs.activeFileTab()))
      : mobileChanges(),
  )
-  const vcsQuery = createQuery(() => {
-    const value = vcsMode()
+  const turnKey = createMemo(() => [server.scope, "session-turn", input.session.identity.sessionID()] as const)
+  const diffQuery = createQuery(() => {
+    const value = mode()
+    const sessionID = input.session.identity.sessionID()
+    const turn = value === "turn"
    return {
-      queryKey: [...vcsKey(), value] as const,
+      queryKey: turn ? turnKey() : ([...vcsKey(), value] as const),
      enabled: server.connection.status() === "connected" && wantsReview() && !!input.session.project()?.vcs,
      refetchOnMount: "always" as const,
-      refetchOnWindowFocus: true,
-      queryFn: value
-        ? () =>
+      // A finished turn's diff is immutable and expensive, so only the idle transition refreshes it.
+      refetchOnWindowFocus: !turn,
+      queryFn: turn
+        ? sessionID
+          ? () => server.api.session.diff({ sessionID })
+          : skipToken
+        : () =>
            server.api.vcs
              .diff({
                location: { directory: location().directory },
                mode: value === "git" ? "working" : value,
              })
-              .then((result) => result.data)
-        : skipToken,
+              .then((result) => result.data),
    }
  })
  const detailsQuery = createQuery(() => ({
@@ -136,16 +139,13 @@ export function createSessionReview(input: {
    on(
      () => input.screen.review.open() || mobileChanges(),
      (open, previous) => {
-        if (!open || previous || !input.screen.files.open() || vcsQuery.isFetching) return
+        if (!open || previous || !input.screen.files.open() || diffQuery.isFetching) return
        refresh()
      },
      { defer: true },
    ),
  )
-  const diffs = () => {
-    if (mode() === "git" || mode() === "branch") return vcsQuery.isFetched ? (vcsQuery.data ?? []) : []
-    return []
-  }
+  const diffs = () => (diffQuery.isFetched ? (diffQuery.data ?? []) : [])
  const activeFile = () => {
    const list = diffs()
    const selected = selectedFile()
@@ -155,17 +155,12 @@ export function createSessionReview(input: {
  const count = () => diffs().length
  const hasChanges = () => count() > 0
  const ready = () => {
-    // A project without VCS never enables vcsQuery, so its status stays "pending" forever.
+    // A project without VCS never enables diffQuery, so its status stays "pending" forever.
    const project = input.session.project()
    if (project && !project.vcs) return true
-    if (mode() === "git" || mode() === "branch") return !vcsQuery.isPending
-    return true
+    return !diffQuery.isPending
  }
  const loadDiff = async (path: string, version?: number): Promise<FileDiffInfo | undefined> => {
-    const value = vcsMode()
-    if (!value) return undefined
-    const root = reviewRootDirectory(input.session.project()?.worktree ?? location().directory)
-    const directory = reviewDiffDirectory(root, path)
    const source = diffs().find((diff) => diff.file === path)
    const valid = (diff: FileDiffInfo | undefined): FileDiffInfo | undefined => {
      if (!diff || !source) return undefined
@@ -173,6 +168,26 @@ export function createSessionReview(input: {
      if (reviewDiffNeedsLoad(diff)) return undefined
      return diff
    }
+    const value = mode()
+    // Full-file patches past the server's output budget come back empty; bounded context usually fits.
+    if (value === "turn") {
+      const sessionID = input.session.identity.sessionID()
+      if (!sessionID) return undefined
+      return queryClient
+        .fetchQuery({
+          queryKey: [...turnKey(), "bounded", version] as const,
+          staleTime: Number.POSITIVE_INFINITY,
+          retry: 2,
+          queryFn: () => server.api.session.diff({ sessionID, context: 3 }),
+        })
+        .then((result) => valid(result.find((diff) => diff.file === path)))
+        .catch((error) => {
+          console.debug("[session-review] failed to load bounded turn diff", { path, error })
+          return undefined
+        })
+    }
+    const root = reviewRootDirectory(input.session.project()?.worktree ?? location().directory)
+    const directory = reviewDiffDirectory(root, path)
    const request = (scope: string, context?: number) =>
      queryClient
        .fetchQuery({
@@ -357,6 +372,7 @@ export function createSessionReview(input: {
      (next, previous) => {
        if (next !== "idle" || previous === undefined || previous === "idle") return
        refresh()
+        void queryClient.invalidateQueries({ queryKey: turnKey() })
      },
      { defer: true },
    ),
@@ -402,7 +418,7 @@ export function createSessionReview(input: {
      open: () => state.detailsOpen,
      setOpen: (open: boolean) => setState("detailsOpen", open),
    },
-    diffVersion: () => vcsQuery.dataUpdatedAt,
+    diffVersion: () => diffQuery.dataUpdatedAt,
    diffStyle: {
      current: layout.review.diffStyle,
      set: (style: DiffStyle) => layout.review.setDiffStyle(style),
@@ -252,7 +252,6 @@ function ReviewTitle(props: { review: SessionReviewModel }) {

 function ReviewEmpty(props: { review: SessionReviewModel; loadingClass: string }) {
  const language = useLanguage()
-  const loading = () => (props.review.mode() === "git" || props.review.mode() === "branch") && !props.review.ready()
  const noGit = () => props.review.noGit()
  const text = () => {
    if (props.review.mode() === "git") return language.t("session.review.noUncommittedChanges")
@@ -261,7 +260,7 @@ function ReviewEmpty(props: { review: SessionReviewModel; loadingClass: string }
  }
  return (
    <Switch>
-      <Match when={loading()}>
+      <Match when={!props.review.ready()}>
        <div class={props.loadingClass}>{language.t("session.review.loadingChanges")}</div>
      </Match>
      <Match when={noGit()}>
@@ -285,11 +284,10 @@ function ReviewEmpty(props: { review: SessionReviewModel; loadingClass: string }

 function ReviewPanelEmpty(props: { review: SessionReviewModel }) {
  const language = useLanguage()
-  const loading = () => (props.review.mode() === "git" || props.review.mode() === "branch") && !props.review.ready()
  const noGit = () => props.review.noGit()
  return (
    <Switch>
-      <Match when={loading()}>
+      <Match when={!props.review.ready()}>
        <div class="px-6 py-4 text-text-weak">{language.t("session.review.loadingChanges")}</div>
      </Match>
      <Match when={noGit()}>
@@ -14,7 +14,6 @@ import { createStore } from "solid-js/store"
 import { ResizeHandle } from "@opencode/ui/resize-handle"
 import { MessageTimeline } from "@/session/timeline/message-timeline"
 import { useServer } from "@/runtime/server/current"
-import { projectForSession } from "@/shell/layout/helpers"
 import { ComposerDropzone } from "@/composer/dropzone"
 import type { SessionModel } from "@/session/model"
 import { SESSION_PANEL_WIDTH_MIN } from "@/session/session-panel-width"
@@ -66,7 +65,7 @@ function SessionScreenContent(props: { session: SessionModel; browser: ReturnTyp
  const server = useServer()
  const detailsProject = createMemo(() => {
    const info = session.data.info()
-    return info ? projectForSession(info, server.ctx.sync.data.project) : undefined
+    return info ? server.ctx.projects.detailsForSession(info) : undefined
  })
  const isDesktop = session.isDesktop
  const btw = createSessionBtw(session)
@@ -12,7 +12,7 @@ import { useServer } from "@/runtime/server/current"
 import { ServerConnection } from "@/runtime/server/registry"
 import { useLanguage } from "@/runtime/i18n/language"
 import { usePlatform } from "@/runtime/platform/platform"
-import { displayName, errorMessage, getProjectAvatarSource, projectForSession } from "@/shell/layout/helpers"
+import { displayName, errorMessage, getProjectAvatarSource } from "@/shell/layout/helpers"
 import { getProjectAvatarVariant, useLayout, type LocalProject } from "@/shell/state/layout"
 import { tabKey, useTabs } from "@/shell/tabs/tabs"
 import { useSettingsSurface } from "@/settings/surface"
@@ -319,11 +319,8 @@ export function SessionIdentityHeader(props: { sessionID: string; session?: Sess
      : sessionTitle(props.session?.title ?? (parentID() ? undefined : info()?.title)),
  )
  const project = createMemo(() => {
+    if (props.session) return server.ctx.projects.forSession(props.session)
    const projects = server.ctx.projects.list()
-    if (props.session)
-      return (
-        projectForSession(props.session, projects) ?? projectForSession(props.session, server.ctx.sync.data.project)
-      )
    const value = directory()
    if (!value) return undefined
    const key = pathKey(value)
@@ -1,7 +1,7 @@
 import { DiffChanges } from "@opencode/ui/diff-changes"
 import { Icon } from "@opencode/ui/icon"
 import { getFilename } from "@opencode/util/path"
-import { createMemo, Show, type JSX } from "solid-js"
+import { createMemo, Show } from "solid-js"
 import { useLanguage } from "@/runtime/i18n/language"
 import type { Project } from "@/runtime/server/types"
 import { useSettings } from "@/settings/model"
@@ -16,7 +16,6 @@ export function SessionSummaryPanel(props: {
  shown?: boolean
  mobile?: boolean
  project: Project
-  avatar?: JSX.Element
  directory: string
  local: boolean
  branch?: string
@@ -44,7 +43,7 @@ export function SessionSummaryPanel(props: {
  return (
    <div data-component="session-summary-panel" data-mobile={props.mobile || undefined}>
      <div>
-        <ProjectSummaryCard project={props.project} avatar={props.avatar}>
+        <ProjectSummaryCard project={props.project}>
          <SessionWorkspaceMenu
            eligible={props.moveEligible}
            sessionID={props.sessionID}
@@ -1,16 +1,14 @@
 import { Icon } from "@opencode/ui/icon"
-import { ProjectAvatar } from "@opencode/ui/project-avatar"
-import { createUniqueId, Show, type ParentProps, type JSX } from "solid-js"
+import { createUniqueId, Show, type ParentProps } from "solid-js"
 import type { Project } from "@/runtime/server/types"
 import { useSettings } from "@/settings/model"
-import { displayName, getProjectAvatarSource } from "@/shell/layout/helpers"
-import { getProjectAvatarVariant } from "@/shell/state/layout"
+import { displayName } from "@/shell/layout/helpers"
+import { ProjectIcon } from "@/shell/layout/project-icon"
 import "./summary.css"

 export function ProjectSummaryCard(
  props: ParentProps<{
    project: Pick<Project, "name" | "worktree" | "icon"> & { id?: string }
-    avatar?: JSX.Element
  }>,
 ) {
  const settings = useSettings()
@@ -26,13 +24,7 @@ export function ProjectSummaryCard(
        aria-controls={contentID}
        onClick={() => settings.sessionSummary.setProjectExpanded(!expanded())}
      >
-        {props.avatar ?? (
-          <ProjectAvatar
-            fallback={displayName(props.project)}
-            src={getProjectAvatarSource(props.project.id, props.project.icon)}
-            variant={getProjectAvatarVariant(props.project.icon?.color)}
-          />
-        )}
+        <ProjectIcon project={props.project} />
        <span dir="auto" class="session-summary-label">
          {displayName(props.project)}
        </span>
@@ -31,7 +31,6 @@ import { getReadyMarkdown, preloadMarkdown } from "@opencode/session-ui/markdown
 import { createTimelineController, type TimelineController, type TimelineSessionSource } from "./controller"
 import { createTimelineVirtualizer } from "./virtualizer"
 import { containsDirectory, isWorkspaceDirectory } from "@/workspaces/paths"
-import { projectForSession } from "@/shell/layout/helpers"
 import { parseCommentNote, readPromptPresentation } from "@/composer/comment-note"
 import { useCommand } from "@/shell/commands/command"
 import { SessionAncestorTrail, SessionProjectMenu, SessionTitleHeader } from "../session-identity-header"
@@ -143,14 +142,14 @@ function MessageTimelineView(
    const session = props.session.data.info()
    const projects = server.ctx.sync.data.project
    return session
-      ? projectForSession(session, projects)
+      ? server.ctx.projects.detailsForSession(session)
      : projects.find((item) => containsDirectory(item.worktree, sessionDirectory()))
  })
  const workspaceSession = createMemo(() => isWorkspaceDirectory(project(), sessionDirectory()))
-  const avatarProject = createMemo(() => {
+  const headerProject = createMemo(() => {
    const session = props.session.data.info()
    if (!session) return
-    return projectForSession(session, server.ctx.projects.list()) ?? project()
+    return server.ctx.projects.forSession(session)
  })
  createEffect(() => {
    const directory = project()?.worktree
@@ -408,7 +407,7 @@ function MessageTimelineView(
              <div class="flex items-center gap-1 min-w-0 flex-1">
                <div class="flex items-center gap-0.5 min-w-0 flex-1 w-full">
                  <SessionProjectMenu
-                    project={avatarProject()}
+                    project={headerProject()}
                    directory={sessionDirectory()}
                    workspace={workspaceSession()}
                  />
@@ -11,7 +11,7 @@ import { useLayout, type LocalProject } from "@/shell/state/layout"
 import { ServerConnection } from "@/runtime/server/registry"
 import { useServerSDK } from "@/runtime/server/client"
 import { useTabs } from "@/shell/tabs/tabs"
-import { displayName, projectForSession } from "@/shell/layout/helpers"
+import { displayName, resolveProjectForSession } from "@/shell/layout/helpers"
 import { createSessionTabs } from "@/session/helpers"
 import { useSessionLayout } from "@/session/session-layout"
 import { useServer } from "@/runtime/server/current"
@@ -253,9 +253,7 @@ export function createServerSessionEntries(props: {
    })
    if (current.signal.aborted) return []
    const opened = props.opened()
-    const openedByID = new Map(opened.flatMap((project) => (project.id ? [[project.id, project] as const] : [])))
    const stored = props.stored().map((project) => ({ ...project, expanded: false }))
-    const storedByID = new Map(stored.map((project) => [project.id, project] as const))
    return Promise.all([
      props.load(search, current.signal).then(
        (result) => result.data,
@@ -271,8 +269,7 @@ export function createServerSessionEntries(props: {
      [...new Map([...exact, ...listed].map((session) => [session.id, session] as const)).values()]
        .filter((session) => !session.time.archived)
        .map((session) => {
-          const project =
-            projectForSession(session, opened, openedByID) ?? projectForSession(session, stored, storedByID)
+          const project = resolveProjectForSession(session, opened, stored)
          return {
            id: `session:${props.server}:${session.id}`,
            type: "session" as const,
@@ -50,6 +50,17 @@ export const childSessionOnPath = (sessions: SessionInfo[] | undefined, rootID:
 export const displayName = (project: { name?: string; worktree: string }) =>
  project.name || getFilename(project.worktree) || project.worktree

+type ProjectAppearance = {
+  name?: string
+  worktree: string
+  icon?: { color?: string; url?: string; override?: string }
+}
+
+function withProjectAppearance<T extends ProjectAppearance>(metadata: T, appearance?: ProjectAppearance) {
+  if (!appearance || appearance === metadata) return metadata
+  return { ...metadata, name: displayName(appearance), icon: appearance.icon }
+}
+
 export function toggleHomeProjectSelection(
  current: HomeProjectSelection | undefined,
  server: ServerConnection.Key,
@@ -97,11 +108,59 @@ export function getProjectAvatarSource(id?: string, icon?: { color?: string; url
 export function projectForSession<T extends { id?: string; worktree: string; sandboxes?: string[] }>(
  session: SessionInfo,
  projects: T[],
-  byID: Map<string, T> = new Map(projects.flatMap((project) => (project.id ? [[project.id, project] as const] : []))),
 ) {
-  const direct = byID.get(session.projectID)
-  if (direct) return direct
-  return projects.find((project) => isProjectDirectory(project, session.location.directory))
+  const matching = projects.filter((project) => project.id === session.projectID)
+  if (matching.length === 1) return matching[0]
+  if (matching.length > 1) {
+    const directory = pathKey(session.location.directory)
+    const exact =
+      matching.find((project) => pathKey(project.worktree) === directory) ??
+      matching.find((project) => project.sandboxes?.some((sandbox) => pathKey(sandbox) === directory))
+    if (exact) return exact
+    return (
+      matching
+        .filter((project) => isProjectDirectory(project, session.location.directory))
+        .sort((a, b) => b.worktree.length - a.worktree.length)[0] ?? matching.at(-1)
+    )
+  }
+  const directory = pathKey(session.location.directory)
+  const exact =
+    projects.find((project) => pathKey(project.worktree) === directory) ??
+    projects.find((project) => project.sandboxes?.some((sandbox) => pathKey(sandbox) === directory))
+  if (exact) return exact
+  return projects
+    .filter((project) => isProjectDirectory(project, session.location.directory))
+    .sort((a, b) => b.worktree.length - a.worktree.length)[0]
+}
+
+export function resolveProjectForSession<
+  T extends { id?: string; worktree: string; sandboxes?: string[] },
+  U extends { id?: string; worktree: string; sandboxes?: string[] },
+>(session: SessionInfo, opened: T[], stored: U[]) {
+  const current = projectForSession(session, opened)
+  if (current?.id === session.projectID) {
+    const unresolved = opened.find(
+      (project) => !project.id && pathKey(project.worktree) === pathKey(session.location.directory),
+    )
+    if (!unresolved) return current
+    const canonical = projectForSession(session, stored)
+    if (canonical?.id === session.projectID && pathKey(canonical.worktree) === pathKey(unresolved.worktree))
+      return unresolved
+    return current
+  }
+  const synced = projectForSession(session, stored)
+  if (synced?.id !== session.projectID) return current ?? synced
+  if (current && !current.id && pathKey(current.worktree) === pathKey(session.location.directory)) return current
+  return synced
+}
+
+export function resolveSessionDetailsProject<
+  T extends ProjectAppearance & { id?: string; sandboxes?: string[] },
+  U extends ProjectAppearance & { id?: string; sandboxes?: string[] },
+>(session: SessionInfo, opened: T[], stored: U[]) {
+  const metadata = projectForSession(session, stored)
+  if (!metadata) return
+  return withProjectAppearance(metadata, resolveProjectForSession(session, opened, stored))
 }

 export const errorMessage = (err: unknown, fallback: string) => {
@@ -4,7 +4,7 @@ import { displayName, getProjectAvatarSource } from "@/shell/layout/helpers"
 import { getProjectAvatarVariant, type LocalProject } from "@/shell/state/layout"

 type ProjectIconProps = Omit<ProjectAvatarProps, "fallback" | "src" | "variant"> & {
-  project: LocalProject
+  project: Pick<LocalProject, "id" | "name" | "worktree" | "icon">
  fallback?: string
  icon?: LocalProject["icon"]
 }
@@ -9,7 +9,7 @@ import { Menu } from "@opencode/ui/menu"
 import { useGlobal, useServerCtx } from "@/runtime/server/runtime"
 import { useLanguage } from "@/runtime/i18n/language"
 import { ServerConnection, serverName, useServers } from "@/runtime/server/registry"
-import { displayName, projectForSession } from "@/shell/layout/helpers"
+import { displayName } from "@/shell/layout/helpers"
 import { SessionTabAvatar } from "@/shell/layout/session-tab-avatar"
 import { SessionProgressIndicatorV2 } from "@opencode/session-ui/v2/session-progress-indicator-v2"
 import type { SessionInfo } from "@opencode/client/promise"
@@ -57,7 +57,7 @@ export function TabNavItem(props: {
  const project = createMemo(() => {
    const session = props.session
    if (!session) return
-    return projectForSession(session, serverCtx()?.projects.list() ?? [])
+    return serverCtx()?.projects.forSession(session)
  })
  const title = createMemo(() => {
    const session = props.session
@@ -29,7 +29,6 @@ import { MobileDrawer, MobileDrawerContent, MobileDrawerLabel, MobileDrawerTrigg
 import { sessionTabTitle } from "./tab-title"
 import { SessionTabAvatar } from "@/shell/layout/session-tab-avatar"
 import { SessionProgressIndicatorV2 } from "@opencode/session-ui/v2/session-progress-indicator-v2"
-import { projectForSession } from "@/shell/layout/helpers"
 import { useSettingsDialog } from "@/settings/command"
 import { updaterAction } from "@/shell/updates/action"
 import type { UpdaterState } from "@/shell/updates/types"
@@ -441,7 +440,7 @@ export function Titlebar(props: {
              const value = session()
              if (!tab || !value) return
              const conn = global.servers.list().find((item) => ServerConnection.key(item) === tab.server)
-              return projectForSession(value, conn ? global.ensureServerCtx(conn).projects.list() : [])
+              return conn ? global.ensureServerCtx(conn).projects.forSession(value) : undefined
            })
            const currentTitle = () => {
              const tab = currentTab()
@@ -1,7 +1,7 @@
 {
  "$schema": "https://json.schemastore.org/package.json",
  "name": "@opencode/cli",
-  "version": "2.0.16",
+  "version": "2.0.18",
  "type": "module",
  "license": "MIT",
  "bin": {
@@ -25,6 +25,7 @@
  },
  "dependencies": {
    "@agentclientprotocol/sdk": "1.2.1",
+    "@clack/core": "1.0.0-alpha.1",
    "@clack/prompts": "1.0.0-alpha.1",
    "@effect/platform-node": "catalog:",
    "@opencode/client": "workspace:*",
@@ -41,7 +42,7 @@
    "effect": "catalog:",
    "immer": "11.1.4",
    "jsonc-parser": "3.3.1",
-    "open": "10.1.2",
+    "picocolors": "1.1.1",
    "solid-js": "catalog:",
    "tree-sitter-bash": "0.25.0",
    "tree-sitter-powershell": "0.25.10",
@@ -142,10 +142,10 @@ const Root = Spec.make(typeof OPENCODE_CLI_NAME === "string" ? OPENCODE_CLI_NAME
      ],
    }),
    Spec.make("auth", {
-      description: "manage AI providers and credentials",
+      description: "manage integrations and credentials",
      commands: [
        Spec.make("list", {
-          description: "list providers and credentials",
+          description: "list integrations and credentials",
          params: {
            ...ServerParams,
            format: Flag.choice("format", ["default", "json"]).pipe(
@@ -155,7 +155,7 @@ const Root = Spec.make(typeof OPENCODE_CLI_NAME === "string" ? OPENCODE_CLI_NAME
          },
        }),
        Spec.make("login", {
-          description: "log in to a provider",
+          description: "connect an integration",
          params: {
            ...ServerParams,
            target: Argument.string("target").pipe(
@@ -228,7 +228,9 @@ const Root = Spec.make(typeof OPENCODE_CLI_NAME === "string" ? OPENCODE_CLI_NAME
        }),
        Spec.make("auth", {
          description: "Authenticate with an OAuth-capable remote MCP server",
-          params: { name: Argument.string("name").pipe(Argument.withDescription("Name of the MCP server")) },
+          params: {
+            name: Argument.string("name").pipe(Argument.withDescription("Name of the MCP server"), Argument.optional),
+          },
        }),
        Spec.make("logout", {
          description: "Remove stored OAuth credentials for an MCP server",
@@ -1,8 +1,9 @@
-import { autocomplete, intro, log, outro, select, spinner, text } from "@clack/prompts"
+import { intro, log, outro, select, spinner, text } from "@clack/prompts"
 import { Effect, Option } from "effect"
 import type { FormAnswer, IntegrationInfo, OpenCodeClient } from "@opencode/client"
 import { Commands } from "../../commands"
 import { Runtime } from "../../../framework/runtime"
+import { selectIntegration, type IntegrationChoice } from "../../../ui/integration-picker"
 import { handlePromptErrors, openUrl, prompt, requireInteractive } from "../../../ui/prompt"
 import { answerForm, secret } from "./form"
 import {
@@ -21,10 +22,8 @@ const integrationPriority = new Map([
  ["opencode", 1],
  ["openai", 2],
  ["github-copilot", 3],
-  ["google", 4],
-  ["anthropic", 5],
-  ["openrouter", 6],
-  ["vercel", 7],
+  ["anthropic", 4],
+  ["google", 5],
 ])

 export default Runtime.handler(
@@ -74,30 +73,35 @@ const findIntegration = Effect.fn("cli.auth.login.integration")(function* (clien
  }
  const integrations = yield* loadIntegrations(client)
  if (target) return yield* resolveIntegration(integrations, target)
-  const available = integrations
+  const choices = loginChoices(integrations)
+  if (choices.length === 0) return yield* Effect.fail(new Error("No authentication integrations are available"))
+  const id = yield* prompt<string>(() => selectIntegration(choices))
+  return yield* resolveIntegration(integrations, id)
+})
+
+export function loginChoices(integrations: IntegrationInfo[]): IntegrationChoice[] {
+  return integrations
    .filter((integration) => connectMethods(integration).length > 0)
    .toSorted(
      (a, b) =>
+        Number(b.metadata?.source === "mcp") - Number(a.metadata?.source === "mcp") ||
        (integrationPriority.get(a.id) ?? integrationPriority.size) -
          (integrationPriority.get(b.id) ?? integrationPriority.size) ||
        a.name.localeCompare(b.name) ||
        a.id.localeCompare(b.id),
    )
-  if (available.length === 0) return yield* Effect.fail(new Error("No authentication integrations are available"))
-  const id = yield* prompt<string>(() =>
-    autocomplete({
-      message: "Select integration",
-      maxItems: 8,
-      options: available.map((integration) => {
-        const option = { value: integration.id, label: integration.name, hint: integration.id }
-        if (integration.connections.length > 0) return { ...option, hint: "connected" }
-        if (integration.id === "opencode") return { ...option, hint: "recommended" }
-        return option
-      }),
-    }),
-  )
-  return yield* resolveIntegration(available, id)
-})
+    .map((integration) => ({
+      value: integration.id,
+      label: integration.name,
+      category:
+        integration.metadata?.source === "mcp"
+          ? "MCP"
+          : integrationPriority.has(integration.id)
+            ? "Popular"
+            : "Services",
+      connected: integration.connections.length > 0,
+    }))
+}

 const chooseMethod = Effect.fn("cli.auth.login.method")(function* (methods: ConnectMethod[], target?: string) {
  if (target) return yield* resolveMethod(methods, target)
@@ -143,17 +147,18 @@ const keyLogin = Effect.fn("cli.auth.login.key")(function* (
  )
 })

-const oauthLogin = Effect.fn("cli.auth.login.oauth")(function* (
+export const oauthLogin = Effect.fn("cli.auth.login.oauth")(function* (
  client: OpenCodeClient,
  integration: IntegrationInfo,
  method: Extract<ConnectMethod, { type: "oauth" }>,
  answer?: FormAnswer,
+  label?: string,
 ) {
  const progress = spinner()
  progress.start("Starting authorization...")
  const started = yield* request((signal) =>
    client.integration.oauth.connect(
-      { integrationID: integration.id, methodID: method.id, answer, location },
+      { integrationID: integration.id, methodID: method.id, answer, label, location },
      { signal },
    ),
  ).pipe(Effect.tapCause(() => Effect.sync(() => progress.stop("Authentication failed", 1))))
@@ -190,16 +195,14 @@ const oauthLogin = Effect.fn("cli.auth.login.oauth")(function* (
    return
  }

-  const waiting = spinner()
-  waiting.start("Waiting for authorization...")
-  const status = yield* waitForOAuth(client, integration.id, attempt.attemptID).pipe(
-    Effect.tapCause(() => Effect.sync(() => waiting.stop("Authentication failed", 1))),
-  )
+  // Clack's spinner captures Ctrl+C and exits the process directly, which would skip the finalizer that
+  // cancels the attempt. Waits that can last minutes use plain log lines so Ctrl+C interrupts normally.
+  log.step("Waiting for authorization...")
+  const status = yield* waitForOAuth(client, integration.id, attempt.attemptID)
  if (status.status === "complete") {
-    waiting.stop(`Connected to ${integration.name}`)
+    log.success(`Connected to ${integration.name}`)
    return
  }
-  waiting.stop("Authentication failed", 1)
  if (status.status === "failed") yield* Effect.fail(new Error(status.message))
  yield* Effect.fail(new Error("Authorization expired"))
 })
@@ -226,14 +229,21 @@ const commandLogin = Effect.fn("cli.auth.login.command")(function* (
      ),
    ).pipe(Effect.ignore),
  )
-  const status = yield* waitForCommand(client, integration.id, started.data.attemptID, (message) =>
-    progress.message(message.trim() || "Waiting for authentication command..."),
-  ).pipe(Effect.tapCause(() => Effect.sync(() => progress.stop("Authentication failed", 1))))
+  progress.stop("Authentication command started")
+  // The status message accumulates the command's stderr; print each completed line once.
+  let printed = 0
+  log.step("Waiting for authentication command...")
+  const status = yield* waitForCommand(client, integration.id, started.data.attemptID, (message) => {
+    const end = message.lastIndexOf("\n") + 1
+    if (end <= printed) return
+    const output = message.slice(printed, end).trim()
+    printed = end
+    if (output) log.message(output)
+  })
  if (status.status === "complete") {
-    progress.stop(`Connected to ${integration.name}`)
+    log.success(`Connected to ${integration.name}`)
    return
  }
-  progress.stop("Authentication failed", 1)
  if (status.status === "failed") yield* Effect.fail(new Error(status.message))
  yield* Effect.fail(new Error("Authentication expired"))
 })
@@ -1,65 +1,109 @@
-import { EOL } from "node:os"
-import { Effect } from "effect"
-import {
-  OpenCode,
-  type IntegrationAttemptStatus,
-  type IntegrationOAuthMethod,
-  type OpenCodeClient,
-} from "@opencode/client"
+import { confirm, intro, log, outro } from "@clack/prompts"
+import { Effect, Option } from "effect"
+import { OpenCode, type IntegrationInfo, type IntegrationOAuthMethod, type McpServer } from "@opencode/client"
 import { Commands } from "../../commands"
 import { Runtime } from "../../../framework/runtime"
 import { Service } from "@opencode/client/effect/service"
 import { ServiceConfig } from "../../../services/service-config"
-import { resolveIntegration } from "./resolve"
+import { selectIntegration, type IntegrationChoice } from "../../../ui/integration-picker"
+import { handlePromptErrors, prompt, requireInteractive } from "../../../ui/prompt"
+import { answerForm } from "../auth/form"
+import { oauthLogin } from "../auth/login"
+import { loadIntegrations, request } from "../auth/shared"

 const location = { directory: process.cwd() }

 export default Runtime.handler(
  Commands.commands.mcp.commands.auth,
-  Effect.fn("cli.mcp.auth")(function* (input) {
-    const endpoint = yield* Service.ensure(yield* ServiceConfig.options())
-    const client = OpenCode.make({ baseUrl: endpoint.url, headers: Service.headers(endpoint) })
-
-    const integration = yield* resolveIntegration(client, input.name, location)
-    if (!integration)
-      return yield* Effect.fail(new Error(`MCP server "${input.name}" is not an OAuth-capable remote server`))
-    const method = integration.methods.find(
-      (candidate): candidate is IntegrationOAuthMethod => candidate.type === "oauth",
-    )
-    if (!method)
-      return yield* Effect.fail(new Error(`MCP server "${input.name}" is not an OAuth-capable remote server`))
-
-    const started = yield* Effect.promise(() =>
-      client.integration.oauth.connect({ integrationID: integration.id, methodID: method.id, location }),
-    )
-    const attempt = started.data
-    if (attempt.mode === "code")
-      return yield* Effect.fail(new Error("This server requires manual code entry, which the CLI does not support"))
-
-    process.stdout.write(attempt.instructions + EOL + attempt.url + EOL)
-
-    const result = yield* poll(client, integration.id, attempt.attemptID)
-    if (result.status === "complete") {
-      process.stdout.write(`Authenticated with ${input.name}` + EOL)
-      return
-    }
-    const reason = result.status === "failed" ? `: ${result.message}` : ""
-    return yield* Effect.fail(new Error(`Authentication ${result.status}${reason}`))
-  }),
+  Effect.fn("cli.mcp.auth")((input) => authenticate(Option.getOrUndefined(input.name)).pipe(handlePromptErrors)),
 )

-const poll = (
-  client: OpenCodeClient,
-  integrationID: string,
-  attemptID: string,
-): Effect.Effect<Exclude<IntegrationAttemptStatus, { status: "pending" }>> =>
-  Effect.gen(function* () {
-    const status = yield* Effect.promise(() =>
-      client.integration.oauth.status({ integrationID, attemptID, location }),
-    ).pipe(Effect.map((result) => result.data))
-    if (status.status === "pending") {
-      yield* Effect.sleep("1 second")
-      return yield* poll(client, integrationID, attemptID)
+const authenticate = Effect.fn("cli.mcp.auth.run")(function* (name?: string) {
+  if (!name) yield* requireInteractive("Pass an MCP server name when running without an interactive terminal")
+  intro("Authenticate an MCP server")
+  const endpoint = yield* Service.ensure(yield* ServiceConfig.options())
+  const client = OpenCode.make({ baseUrl: endpoint.url, headers: Service.headers(endpoint) })
+  const integrations = yield* loadIntegrations(client)
+  const servers = yield* request((signal) => client.mcp.list({ location }, { signal }))
+  const choices = mcpAuthChoices(servers.data, integrations)
+  if (!name && choices.length === 0) {
+    log.warn("No OAuth-capable MCP servers configured")
+    log.info(
+      `Remote MCP servers support OAuth by default. Add one with \`opencode mcp add\` or in opencode.json:\n${exampleConfig}`,
+    )
+    outro("Done")
+    return
+  }
+
+  const server = name ? servers.data.find((item) => item.name === name) : undefined
+  if (name && !server) return yield* Effect.fail(new Error(`MCP server not found: ${name}`))
+  const integrationID = server
+    ? server.integrationID
+    : yield* prompt<string>(() => selectIntegration(choices, "MCP server"))
+  const integration = integrations.find((item) => item.id === integrationID)
+  const method = integration?.methods.find(
+    (candidate): candidate is IntegrationOAuthMethod => candidate.type === "oauth",
+  )
+  if (!integration || !method)
+    return yield* Effect.fail(new Error(`MCP server "${name}" is not an OAuth-capable remote server`))
+
+  if (integration.connections.length > 0) {
+    const status = servers.data.find((item) => item.integrationID === integration.id)?.status.status
+    if (status === "needs_auth") log.warn(`${integration.name} has expired credentials. Re-authenticating...`)
+    if (status !== "needs_auth" && process.stdin.isTTY && process.stdout.isTTY) {
+      const again = yield* prompt<boolean>(() =>
+        confirm({ message: `${integration.name} already has valid credentials. Re-authenticate?` }),
+      )
+      if (!again) {
+        outro("Cancelled")
+        return
+      }
    }
-    return status
-  })
+  }
+
+  // Re-authenticating replaces the previous sign-in rather than adding an account. The new credential
+  // keeps the active one's label, and the old ones are only removed once it is stored, so a failed
+  // attempt keeps them.
+  const previous = integration.connections.filter((connection) => connection.type === "credential")
+  yield* oauthLogin(client, integration, method, yield* answerForm(method.form), previous[0]?.label)
+  yield* Effect.forEach(
+    previous,
+    (connection) => request((signal) => client.credential.remove({ credentialID: connection.id }, { signal })),
+    { discard: true },
+  )
+  outro("Done")
+})
+
+const exampleConfig = `
+  "mcp": {
+    "my-server": {
+      "type": "remote",
+      "url": "https://example.com/mcp"
+    }
+  }`
+
+// Choices carry the server-owned integration ID so provider integrations with colliding names never match.
+export function mcpAuthChoices(servers: McpServer[], integrations: IntegrationInfo[]): IntegrationChoice[] {
+  const byID = new Map(integrations.map((integration) => [integration.id, integration]))
+  return servers
+    .flatMap((server) => {
+      const integration = server.integrationID ? byID.get(server.integrationID) : undefined
+      if (!integration?.methods.some((method) => method.type === "oauth")) return []
+      return [
+        {
+          value: integration.id,
+          label: server.name,
+          category: "MCP" as const,
+          connected: integration.connections.length > 0,
+          hint: statusHint(server.status),
+        },
+      ]
+    })
+    .toSorted((a, b) => a.label.localeCompare(b.label) || a.value.localeCompare(b.value))
+}
+
+function statusHint(status: McpServer["status"]) {
+  if (status.status === "needs_auth") return "needs authentication"
+  if (status.status === "failed" || status.status === "disabled") return status.status
+  return undefined
+}
@@ -0,0 +1,67 @@
+import { AutocompletePrompt } from "@clack/core"
+import { S_BAR, S_BAR_END, S_RADIO_ACTIVE, S_RADIO_INACTIVE, symbol } from "@clack/prompts"
+import color from "picocolors"
+
+export type IntegrationChoice = {
+  value: string
+  label: string
+  category: "MCP" | "Popular" | "Services"
+  connected: boolean
+  hint?: string
+}
+
+export async function selectIntegration(choices: IntegrationChoice[], kind = "integration") {
+  const result = await new AutocompletePrompt<IntegrationChoice>({
+    options: choices,
+    filter: (search, choice) =>
+      [choice.label, choice.value, choice.category].some((value) => value.toLowerCase().includes(search.toLowerCase())),
+    validate: (value) => (value ? undefined : `Select an ${kind}`),
+    render() {
+      const title = `${color.gray(S_BAR)}\n${symbol(this.state)}  Select ${kind}`
+      if (this.state === "submit") {
+        const choice = choices.find((item) => item.value === this.value)
+        return `${title}\n${color.gray(S_BAR)}  ${color.dim(choice?.label ?? "")}`
+      }
+      if (this.state === "cancel")
+        return `${title}\n${color.gray(S_BAR)}  ${color.strikethrough(color.dim(this.userInput))}`
+
+      // Leave room for the category headings as well as Clack's title and footer.
+      const maxItems = Math.min(8, Math.max(2, (process.stdout.rows ?? 24) - 14 - Number(this.state === "error")))
+      const compact = (process.stdout.rows ?? 24) < 18
+      const start = Math.min(
+        Math.max(0, this.cursor - Math.min(2, maxItems - 1)),
+        Math.max(0, this.filteredOptions.length - maxItems),
+      )
+      const visible = this.filteredOptions.slice(start, start + maxItems)
+      const rows = visible.flatMap((choice, index) => [
+        ...(index === 0 || visible[index - 1].category !== choice.category
+          ? [...(compact ? [] : [`${color.cyan(S_BAR)}  `]), `${color.cyan(S_BAR)}  ${color.bold(choice.category)}`]
+          : []),
+        `${color.cyan(S_BAR)}  ${start + index === this.cursor ? color.green(S_RADIO_ACTIVE) : color.dim(S_RADIO_INACTIVE)} ${
+          start + index === this.cursor ? choice.label : color.dim(choice.label)
+        }${choice.connected ? ` ${color.green("✓")}` : ""}${choice.hint ? ` ${color.dim(`(${choice.hint})`)}` : ""}`,
+      ])
+      return [
+        title,
+        `${color.cyan(S_BAR)}  ${color.dim("Search:")} ${this.isNavigating ? color.dim(this.userInput) : this.userInputWithCursor}`,
+        ...(visible.length === 0 && this.userInput
+          ? [`${color.cyan(S_BAR)}  ${color.yellow(`No ${kind}s found`)}`]
+          : []),
+        ...(this.state === "error" && visible.length > 0
+          ? [`${color.yellow(S_BAR)}  ${color.yellow(this.error)}`]
+          : []),
+        ...(start > 0 ? [`${color.cyan(S_BAR)}  ${color.dim("…")}`] : []),
+        ...rows,
+        ...(start + maxItems < this.filteredOptions.length ? [`${color.cyan(S_BAR)}  ${color.dim("…")}`] : []),
+        `${color.cyan(S_BAR)}  ${color.dim(
+          (process.stdout.columns ?? 80) < 50
+            ? "↑/↓ navigate • Enter select"
+            : "↑/↓ to select • Enter: confirm • Type: to search",
+        )}`,
+        color.cyan(S_BAR_END),
+      ].join("\n")
+    },
+  }).prompt()
+  if (typeof result === "string" || typeof result === "symbol") return result
+  throw new Error(`No ${kind} selected`)
+}
@@ -16,12 +16,13 @@ export function requireInteractive(message: string) {
 }

 export const openUrl = Effect.fn("cli.prompt.open-url")(function* (url: string) {
-  const { default: open } = yield* Effect.promise(() => import("open"))
-  yield* Effect.promise(() => open(url)).pipe(Effect.ignore)
+  const browser = yield* Effect.promise(() => import("@opencode/util/open"))
+  yield* Effect.promise(() => browser.openUrl(url)).pipe(Effect.ignore)
 })

 export function handlePromptErrors<A, E, R>(effect: Effect.Effect<A, E, R>) {
  return effect.pipe(
+    Effect.onInterrupt(() => Effect.sync(() => cancel("Cancelled"))),
    Effect.catchIf(
      (error) => error === cancelled,
      () =>
@@ -0,0 +1,30 @@
+import { expect, test } from "bun:test"
+import type { IntegrationInfo } from "@opencode/client"
+import { loginChoices } from "../src/commands/handlers/auth/login"
+
+const integration = (value: Partial<IntegrationInfo> & Pick<IntegrationInfo, "id" | "name">): IntegrationInfo => ({
+  methods: [{ type: "key" }],
+  connections: [],
+  ...value,
+})
+
+test("groups the CLI choices like /connect while keeping stable login IDs", () => {
+  expect(
+    loginChoices([
+      integration({ id: "mistral", name: "Mistral" }),
+      integration({ id: "openai", name: "OpenAI" }),
+      integration({ id: "linear", name: "Linear", metadata: { source: "mcp" } }),
+      integration({ id: "github", name: "GitHub", metadata: { source: "mcp" } }),
+      integration({ id: "opencode", name: "OpenCode Console" }),
+      integration({ id: "opencode-go", name: "OpenCode Go", connections: [{ type: "env", name: "GO_KEY" }] }),
+      integration({ id: "unused", name: "Unused", methods: [{ type: "env", names: ["UNUSED_KEY"] }] }),
+    ]),
+  ).toEqual([
+    { value: "github", label: "GitHub", category: "MCP", connected: false },
+    { value: "linear", label: "Linear", category: "MCP", connected: false },
+    { value: "opencode-go", label: "OpenCode Go", category: "Popular", connected: true },
+    { value: "opencode", label: "OpenCode Console", category: "Popular", connected: false },
+    { value: "openai", label: "OpenAI", category: "Popular", connected: false },
+    { value: "mistral", label: "Mistral", category: "Services", connected: false },
+  ])
+})
@@ -20,12 +20,12 @@ describe("auth command", () => {
    expect(auth.stdout).toContain("list")
    expect(auth.stdout).toContain("login")
    expect(auth.stdout).toContain("logout")
-    expect(auth.stdout).toContain("manage AI providers and credentials")
-    expect(auth.stdout).toContain("list providers and credentials")
-    expect(auth.stdout).toContain("log in to a provider")
+    expect(auth.stdout).toContain("manage integrations and credentials")
+    expect(auth.stdout).toContain("list integrations and credentials")
+    expect(auth.stdout).toContain("connect an integration")
    expect(auth.stdout).toContain("log out of a saved account")
    expect(auth.stdout).toContain("switch the active account for an integration")
-    expect(auth.stdout).not.toContain("connect")
+    expect(auth.stdout).not.toMatch(/^  connect\s/m)
    expect(list.exitCode).toBe(0)
    expect(list.stdout).toContain("opencode auth list [flags]")
    expect(list.stdout).toContain("--format")
@@ -216,7 +216,8 @@ describe("auth command", () => {
    expect(requests).toContainEqual({ method: "DELETE", path: `${endpoint}/con_oauth` })
  })

-  test("settles the OAuth spinner when status polling fails", async () => {
+  test("reports OAuth status polling failures and cancels the attempt", async () => {
+    let cancelled = false
    using server = authServer((request, url) => {
      if (url.pathname === "/api/integration") {
        return Response.json(
@@ -245,6 +246,7 @@ describe("auth command", () => {
        return new Response("Unavailable", { status: 500 })
      }
      if (url.pathname === "/api/integration/openai/connect/oauth/con_oauth" && request.method === "DELETE") {
+        cancelled = true
        return new Response(null, { status: 204 })
      }
      return new Response("Not found", { status: 404 })
@@ -252,8 +254,10 @@ describe("auth command", () => {

    const result = await cli(["auth", "login", "openai", "--server", server.url.toString()])
    expect(result.exitCode).toBe(1)
-    expect(result.stdout).toContain("Authentication failed")
+    expect(result.stdout).toContain("Waiting for authorization...")
+    expect(result.stdout).toContain("UnexpectedStatus: 500")
    expect(result.stdout).toContain("Failed")
+    expect(cancelled).toBe(true)
    expect(result.stdout).not.toContain("\n    at ")
  })

@@ -0,0 +1,62 @@
+import { expect, test } from "bun:test"
+import path from "node:path"
+import type { IntegrationInfo, McpServer } from "@opencode/client"
+import { mcpAuthChoices } from "../src/commands/handlers/mcp/auth"
+
+const server = (
+  name: string,
+  integrationID?: string,
+  status: McpServer["status"] = { status: "pending" },
+): McpServer => ({ name, integrationID, status })
+
+const integration = (id: string, methods: IntegrationInfo["methods"], connected = false): IntegrationInfo => ({
+  id,
+  name: id,
+  methods,
+  connections: connected ? [{ type: "credential", method: "oauth", id: "cred_1", label: "Work" }] : [],
+})
+
+test("offers only OAuth-capable MCP servers by their server identity", () => {
+  expect(
+    mcpAuthChoices(
+      [
+        server("Linear", "mcp_linear", { status: "needs_auth", error: "expired" }),
+        server("Local"),
+        server("API key only", "mcp_key"),
+        server("GitHub", "mcp_github"),
+        server("Sentry", "mcp_sentry", { status: "failed", error: "boom" }),
+        server("Unresolved", "mcp_missing"),
+      ],
+      [
+        integration("mcp_linear", [{ type: "oauth", id: "login", label: "Linear" }], true),
+        integration("mcp_github", [{ type: "oauth", id: "login", label: "GitHub" }]),
+        integration("mcp_sentry", [{ type: "oauth", id: "login", label: "Sentry" }]),
+        integration("mcp_key", [{ type: "key" }]),
+        integration("Linear", [{ type: "oauth", id: "login", label: "A provider with a colliding name" }]),
+      ],
+    ),
+  ).toEqual([
+    { value: "mcp_github", label: "GitHub", category: "MCP", connected: false, hint: undefined },
+    { value: "mcp_linear", label: "Linear", category: "MCP", connected: true, hint: "needs authentication" },
+    { value: "mcp_sentry", label: "Sentry", category: "MCP", connected: false, hint: "failed" },
+  ])
+})
+
+test("mcp auth accepts an optional server name and rejects no-name noninteractive calls before connecting", async () => {
+  const cli = (args: string[]) =>
+    Bun.spawn([process.execPath, "run", "src/index.ts", "mcp", "auth", ...args], {
+      cwd: path.join(import.meta.dir, ".."),
+      stdout: "pipe",
+      stderr: "pipe",
+    })
+  const help = cli(["--help"])
+  expect(await new Response(help.stdout).text()).toContain("opencode mcp auth [flags] [<name>]")
+  expect(await help.exited).toBe(0)
+
+  const missing = cli([])
+  expect(await new Response(missing.stdout).text()).toContain(
+    "Pass an MCP server name when running without an interactive terminal",
+  )
+  expect(await new Response(missing.stderr).text()).toBe("")
+  expect(await missing.exited).toBe(1)
+})
@@ -1,7 +1,7 @@
 {
  "$schema": "https://json.schemastore.org/package.json",
  "name": "@opencode/client",
-  "version": "2.0.16",
+  "version": "2.0.18",
  "type": "module",
  "license": "MIT",
  "repository": {
@@ -1,7 +1,7 @@
 {
  "$schema": "https://json.schemastore.org/package.json",
  "name": "@opencode/codemode",
-  "version": "2.0.16",
+  "version": "2.0.18",
  "description": "Effect-native confined code execution over schema-described tools",
  "type": "module",
  "license": "MIT",
@@ -1,6 +1,6 @@
 {
  "name": "@opencode/console-app",
-  "version": "2.0.16",
+  "version": "2.0.18",
  "type": "module",
  "license": "MIT",
  "scripts": {
@@ -1,7 +1,7 @@
 {
  "$schema": "https://json.schemastore.org/package.json",
  "name": "@opencode/console-core",
-  "version": "2.0.16",
+  "version": "2.0.18",
  "private": true,
  "type": "module",
  "license": "MIT",
@@ -1,6 +1,6 @@
 {
  "name": "@opencode/console-function",
-  "version": "2.0.16",
+  "version": "2.0.18",
  "$schema": "https://json.schemastore.org/package.json",
  "private": true,
  "type": "module",
@@ -1,6 +1,6 @@
 {
  "name": "@opencode/console-mail",
-  "version": "2.0.16",
+  "version": "2.0.18",
  "dependencies": {
    "@jsx-email/all": "2.2.3",
    "@jsx-email/cli": "1.4.3",
@@ -1,6 +1,6 @@
 {
  "name": "@opencode/console-support",
-  "version": "2.0.16",
+  "version": "2.0.18",
  "type": "module",
  "license": "MIT",
  "scripts": {
@@ -1,6 +1,6 @@
 {
  "$schema": "https://json.schemastore.org/package.json",
-  "version": "2.0.16",
+  "version": "2.0.18",
  "name": "@opencode/core",
  "type": "module",
  "license": "MIT",
@@ -18,7 +18,7 @@ export const Plugin = define({
        editor.configure({
          ...(entry.info.compaction.auto === undefined ? {} : { auto: entry.info.compaction.auto }),
          ...(entry.info.compaction.buffer === undefined ? {} : { buffer: entry.info.compaction.buffer }),
-          ...(entry.info.compaction.keep?.tokens === undefined ? {} : { tokens: entry.info.compaction.keep.tokens }),
+          ...(entry.info.compaction.keep?.tokens === undefined ? {} : { keep: entry.info.compaction.keep.tokens }),
        })
      }
    })
@@ -197,6 +197,8 @@ export const provider = (options: Options): OAuthClientProvider => {
    saveTokens: (tokens) => options.store.saveTokens(tokens),
    redirectToAuthorization: (url) => {
      if (!redirect) throw refuse("user authorization")
+      if (url.protocol !== "http:" && url.protocol !== "https:")
+        throw new Error(`MCP server "${options.config.url}" returned a ${url.protocol} authorization URL; only http and https are supported`)
      return redirect.open(url)
    },
    ...(options.invalidate ? { invalidateCredentials: options.invalidate } : {}),
@@ -1,29 +0,0 @@
-export * as NativeCompactionPlugin from "./compaction.js"
-
-import { LLMClient, Message } from "@opencode/ai"
-import { define } from "@opencode/plugin/effect/plugin"
-import { Effect } from "effect"
-import { SessionCompaction } from "../session/compaction.js"
-import type { PluginInternal } from "./internal.js"
-
-export const Plugin = define({
-  id: "opencode.compaction.native",
-  effect: Effect.fn("NativeCompactionPlugin")(function* () {
-    const llm = yield* LLMClient.Service
-    const compaction = yield* SessionCompaction.Service
-    yield* compaction.transform((editor) => {
-      editor.native((input) => {
-        const request = input.request
-        if (LLMClient.canCompact(request, { mechanism: "trigger" }))
-          return Effect.gen(function* () {
-            const retained = yield* input.retained
-            const result = yield* llm.compact(request, { ...input.options, mechanism: "trigger" })
-            return { replacement: [...retained, Message.assistant(result.checkpoint)], usage: result.usage }
-          })
-        if (LLMClient.canCompact(request))
-          return llm.compact(request, { mechanism: "endpoint", http: input.options.http })
-        return undefined
-      })
-    })
-  }),
-} satisfies PluginInternal.InternalPlugin)
@@ -88,7 +88,6 @@ import { WriteTool } from "../tool/plugin/write.js"
 import { AgentPlugin } from "./agent.js"
 import BrowserPlugin from "@opencode/plugin-browser"
 import { CommandPlugin } from "./command.js"
-import { NativeCompactionPlugin } from "./compaction.js"
 import { IdentityPlugin } from "./identity.js"
 import { PlanPlugin } from "./plan.js"
 import { ModelsDevPlugin } from "./models-dev.js"
@@ -225,7 +224,6 @@ const pre = [
  SkillPlugin.Plugin,
  VcsHgPlugin.Plugin,
  ModelsDevPlugin,
-  NativeCompactionPlugin.Plugin,
  ...ProviderPlugins,
  ...WebSearchPlugins,
  PatchTool.Plugin,
@@ -1,5 +1,5 @@
 import type { IntegrationOAuthMethodRegistration } from "@opencode/plugin/effect/integration"
-import type { SessionRequestKind } from "@opencode/plugin/effect/session"
+import type { SessionRequestKind, SessionTitle } from "@opencode/plugin/effect/session"
 import { Effect, Option, Schema, Semaphore, Stream } from "effect"
 import { IntegrationConnection } from "../../integration/connection.js"
 import { Credential } from "../../credential.js"
@@ -8,6 +8,7 @@ import { CopilotModels } from "../../github-copilot/models.js"
 import { App } from "../../app.js"
 import { Integration } from "../../integration.js"
 import { Model } from "../../model.js"
+import { Agent } from "../../agent.js"
 import { define } from "@opencode/plugin/effect/plugin"
 import { Provider } from "../../provider.js"
 import type { PluginInternal } from "../internal.js"
@@ -162,6 +163,7 @@ export const GithubCopilotPlugin = define({
    const loading = Semaphore.makeUnsafe(1)
    const loaded: {
      baseURL?: string
+      token?: string
      models?: CopilotModels.Snapshot
      connection?: Effect.Success<ReturnType<typeof ctx.integration.connection.active>>
    } = {}
@@ -173,6 +175,7 @@ export const GithubCopilotPlugin = define({
        : undefined
      if (credential?.type !== "oauth") {
        loaded.baseURL = undefined
+        loaded.token = undefined
        loaded.models = undefined
        loaded.connection = undefined
        return
@@ -200,6 +203,7 @@ export const GithubCopilotPlugin = define({
      )
        return
      loaded.baseURL = url
+      loaded.token = credential.refresh
      loaded.models = remote
      loaded.connection = connection
    })
@@ -273,6 +277,29 @@ export const GithubCopilotPlugin = define({
        }),
      { providerID: Provider.ID.githubCopilot },
    )
+    // GitHub's integration guide designates session naming as a utility scenario served by
+    // free, rate-limited utility models. Any failure leaves the result unset so the normal
+    // billable title path still runs.
+    yield* ctx.session.hook(
+      "title",
+      (evt) =>
+        Effect.gen(function* () {
+          if (evt.model.providerID !== Provider.ID.githubCopilot) return
+          if (!loaded.baseURL || !loaded.token || !loaded.models) return
+          const agent = yield* ctx.agent.get({ agentID: Agent.ID.make("title") }).pipe(Effect.orElseSucceed(() => undefined))
+          if (agent?.data.model) return
+          const model = utilityTitleModels.find((id) => loaded.models?.has(id))
+          if (!model) return
+          evt.result = yield* utilityTitle(
+            { baseURL: loaded.baseURL, token: loaded.token, model, app: ctx.app },
+            evt,
+          ).pipe(
+            Effect.tapError((cause) => Effect.logDebug("Copilot utility title failed", { model, cause })),
+            Effect.orElseSucceed(() => undefined),
+          )
+        }),
+      { providerID: Provider.ID.githubCopilot },
+    )
    yield* ctx.session.hook(
      "http.request",
      (evt) =>
@@ -369,6 +396,70 @@ function request(url: string, init: RequestInit) {

 type Fetch = (input: Parameters<typeof fetch>[0], init?: RequestInit) => Promise<Response>

+// Matches the Copilot client: gpt-4o-mini is the "small utility" model; when an account
+// lacks it the request falls through to the regular title path instead of another guess.
+export const utilityTitleModels = ["gpt-4o-mini"]
+
+const UtilityCompletion = Schema.Struct({
+  choices: Schema.Array(Schema.Struct({ message: Schema.Struct({ content: Schema.NullOr(Schema.String) }) })),
+})
+const decodeUtilityCompletion = Schema.decodeUnknownEffect(Schema.fromJsonString(UtilityCompletion))
+
+// This issues its own /chat/completions call instead of steering core's title request.
+// The `session.title` hook exposes `model` read-only, so pointing core at another model
+// would mean widening that contract and re-resolving inside SessionModelRequest; rewriting
+// the body in `http.request` is worse still, since the endpoint (/responses for GPT-5,
+// /v1/messages for Claude) is fixed before that hook runs and gpt-4o-mini only serves
+// /chat/completions. Utility titles are Copilot-specific, stateless, non-streaming, and
+// free, so a small request here costs less than a core seam. Trade-offs: no session
+// usage record for the title step (the call bills nothing) and no `http.*` hook visibility.
+export function utilityTitle(
+  input: { baseURL: string; token: string; model: string; app: App.Info; fetch?: Fetch },
+  request: Pick<SessionTitle, "sessionID" | "system" | "messages" | "options">,
+) {
+  const send = input.fetch ?? fetch
+  const text = (parts: ReadonlyArray<{ type: string; text?: string | null }>) =>
+    parts.flatMap((part) => (part.type === "text" && typeof part.text === "string" ? [part.text] : [])).join("\n")
+  const messages = [
+    ...(request.system.length ? [{ role: "system", content: text(request.system) }] : []),
+    ...request.messages.map((message) => ({ role: message.role, content: text(message.content) })),
+  ]
+  return Effect.tryPromise({
+    try: async (signal) => {
+      const response = await send(`${input.baseURL}/chat/completions`, {
+        method: "POST",
+        signal,
+        headers: {
+          Authorization: `Bearer ${input.token}`,
+          "Content-Type": "application/json",
+          "User-Agent": App.useragent(input.app),
+          "X-GitHub-Api-Version": apiVersion,
+          "Openai-Intent": "conversation-edits",
+          "X-Interaction-Type": "agent-session-name-generation",
+          "X-Interaction-Id": request.sessionID,
+          "x-initiator": "agent",
+        },
+        body: JSON.stringify({
+          model: input.model,
+          messages,
+          stream: false,
+          ...(typeof request.options.maxTokens === "number" ? { max_tokens: request.options.maxTokens } : {}),
+        }),
+      })
+      if (!response.ok) throw new Error(`Utility title request failed: ${response.status}`)
+      return response.text()
+    },
+    catch: (cause) => cause,
+  }).pipe(
+    Effect.timeout("20 seconds"),
+    Effect.flatMap(decodeUtilityCompletion),
+    Effect.flatMap((completion) => {
+      const title = completion.choices[0]?.message.content?.trim()
+      return title ? Effect.succeed(title) : Effect.fail(new Error("Utility title response was empty"))
+    }),
+  )
+}
+
 export function copilotFetch(token: string | undefined, upstream: Fetch | undefined, app: App.Info): Fetch {
  const send = upstream ?? fetch
  return async (input, init) => {
@@ -1,5 +1,6 @@
 import type { IntegrationOAuthMethodRegistration } from "@opencode/plugin/effect/integration"
 import { define } from "@opencode/plugin/effect/plugin"
+import type { SessionRequest } from "@opencode/plugin/effect/session"
 import { Deferred, Effect, Option, Schema, Semaphore, Stream } from "effect"
 import type { Server } from "node:http"
 import { App } from "../../app.js"
@@ -307,6 +308,13 @@ export const OpenAIPlugin = define({
        }),
      { providerID: Provider.ID.openai },
    )
+    // The ChatGPT backend rejects a requested output limit, and OpenAI counts one against rate limits.
+    const omitOutputLimit = (evt: SessionRequest) =>
+      Effect.sync(() => {
+        delete evt.options.maxTokens
+      })
+    for (const name of ["context", "compaction"] as const)
+      yield* ctx.session.hook(name, omitOutputLimit, { providerID: Provider.ID.openai })
    const refresh = () => loading.withPermit(load().pipe(Effect.andThen(ctx.provider.reload())))
    yield* bus.subscribe(Credential.Event.Switched).pipe(
      Stream.filter((event) => event.data.integrationID === Integration.ID.make("openai")),
@@ -13,6 +13,7 @@ import { Provider } from "../../provider.js"
 import { WebSearch } from "../../websearch.js"
 import { ConfigPolicy } from "@opencode/schema/config/policy"
 import { ConfigProvider } from "@opencode/schema/config/provider"
+import { Mcp } from "@opencode/schema/mcp"
 import { Money } from "@opencode/schema/money"

 const defaultServer = "https://opencode.ai/console"
@@ -23,6 +24,15 @@ const RemoteResponse = Schema.Struct({
  websearch: Schema.Struct({
    providerID: WebSearch.ID,
  }).pipe(Schema.optional),
+  // MCP servers by name, in the same shape as a remote server in local config. Only remote servers are
+  // accepted so the Console can never make the client run a command. `auth: "console"` asks the client
+  // to attach its own Console credential to that server's requests.
+  mcp: Schema.Struct({
+    servers: Schema.Record(
+      Schema.String,
+      Schema.Struct({ ...Mcp.RemoteConfig.fields, auth: Schema.Literal("console").pipe(Schema.optional) }),
+    ),
+  }).pipe(Schema.optional),
  // Organization policy compiled for the authenticated caller; omitted when there is none.
  experimental: Schema.Struct({
    policies: Schema.Array(ConfigPolicy.Info).pipe(Schema.optional),
@@ -134,19 +144,25 @@ export const OpencodePlugin = define<HttpClient.HttpClient | Bus.Service | Manag
      config: typeof RemoteResponse.Type | undefined
      connection: ActiveConnection
      organization: string | undefined
-    } = { config: undefined, connection: undefined, organization: undefined }
+      // Console MCP servers carry the credential in their headers, so a rotated token changes the snapshot.
+      mcp:
+        | { servers: NonNullable<typeof RemoteResponse.Type.mcp>["servers"]; headers: Record<string, string> }
+        | undefined
+    } = { config: undefined, connection: undefined, organization: undefined, mcp: undefined }

    const load = Effect.fn("OpencodePlugin.load")(function* () {
      const connection = yield* ctx.integration.connection.active("opencode")
-      if (!connection) return { config: undefined, connection, organization: undefined }
+      if (!connection) return { config: undefined, connection, organization: undefined, mcp: undefined }
      return yield* ctx.integration.connection.resolve(connection).pipe(
        Effect.flatMap((credential) => {
-          if (!credential) return Effect.succeed({ config: undefined, connection, organization: undefined })
+          if (!credential)
+            return Effect.succeed({ config: undefined, connection, organization: undefined, mcp: undefined })
          return fetchConfig(http, credential).pipe(
            Effect.map((config) => ({
              config,
              connection,
              organization: typeof credential.metadata?.orgName === "string" ? credential.metadata.orgName : undefined,
+              mcp: config?.mcp && { servers: config.mcp.servers, headers: credentialHeaders(credential) },
            })),
          )
        }),
@@ -156,8 +172,8 @@ export const OpencodePlugin = define<HttpClient.HttpClient | Bus.Service | Manag
            // would lift organization policy while personal credentials keep working.
            Effect.as(
              IntegrationConnection.key(connection) === IntegrationConnection.key(snapshot.connection)
-                ? { config: snapshot.config, connection, organization: snapshot.organization }
-                : { config: undefined, connection, organization: undefined },
+                ? { config: snapshot.config, connection, organization: snapshot.organization, mcp: snapshot.mcp }
+                : { config: undefined, connection, organization: undefined, mcp: undefined },
            ),
          ),
        ),
@@ -337,10 +353,24 @@ export const OpencodePlugin = define<HttpClient.HttpClient | Bus.Service | Manag
      editor.default.set(descriptor.providerID)
    })

+    yield* ctx.mcp.transform((editor) => {
+      const mcp = snapshot.mcp
+      if (!mcp) return
+      for (const [name, server] of Object.entries(mcp.servers)) {
+        // A server the user configured under the same name wins.
+        if (editor.get(name)) continue
+        const { auth, ...config } = server
+        editor.set(name, auth === "console" ? { ...config, headers: { ...config.headers, ...mcp.headers } } : config)
+      }
+    })
+
    const apply = Effect.fn("OpencodePlugin.apply")(function* (next: typeof snapshot) {
      snapshot = next
      yield* publish(next)
-      yield* Effect.all([ctx.provider.reload(), ctx.websearch.reload()], { concurrency: 2, discard: true })
+      yield* Effect.all([ctx.provider.reload(), ctx.websearch.reload(), ctx.mcp.reload()], {
+        concurrency: 3,
+        discard: true,
+      })
    })
    const refresh = () => loading.withPermit(load().pipe(Effect.andThen(apply)))
    yield* bus.subscribe(Credential.Event.Switched).pipe(
@@ -364,15 +394,11 @@ export const OpencodePlugin = define<HttpClient.HttpClient | Bus.Service | Manag
 })

 function fetchConfig(http: HttpClient.HttpClient, value: Credential.Value) {
-  const metadata = value.metadata
-  const orgID = typeof metadata?.orgID === "string" ? metadata.orgID : undefined
-  const token = value.type === "oauth" ? value.access : value.key
  return http
    .execute(
      HttpClientRequest.get(`${serverUrl(value)}/api/v2/config`).pipe(
        HttpClientRequest.acceptJson,
-        HttpClientRequest.bearerToken(token),
-        HttpClientRequest.setHeaders(orgID ? { "x-org-id": orgID } : {}),
+        HttpClientRequest.setHeaders(credentialHeaders(value)),
      ),
    )
    .pipe(
@@ -385,6 +411,14 @@ function fetchConfig(http: HttpClient.HttpClient, value: Credential.Value) {
    )
 }

+function credentialHeaders(value: Credential.Value): Record<string, string> {
+  const orgID = value.metadata?.orgID
+  return {
+    authorization: `Bearer ${value.type === "oauth" ? value.access : value.key}`,
+    ...(typeof orgID === "string" ? { "x-org-id": orgID } : {}),
+  }
+}
+
 function serverUrl(value: Credential.Value) {
  return typeof value.metadata?.server === "string" ? value.metadata.server : defaultServer
 }
@@ -44,6 +44,14 @@ const IMAGE_BYTES_TARGET = 15 * 1024 * 1024 // 15 MiB
 const IMAGE_REMOVED =
  "[This image was removed to reduce the request size and is no longer visible. Do not make claims about its contents from memory. If needed, retrieve it again with an available tool or ask the user to attach it again.]"
 const GENERATION_KEYS = new Set(Object.keys(GenerationOptions.fields))
+// Used when the catalog has no output limit for the model.
+const OUTPUT_TOKEN_FALLBACK = 32_000
+// A summary never needs more, and a request asking for more cannot be shrunk to fit a window the catalog overstates.
+const SUMMARY_OUTPUT_MAX = 32_000
+// Prompt text is estimated at about 4 characters per token, which can run low on dense text such as code.
+const ESTIMATE_ERROR = 0.15
+// Never ask for less; only reachable with automatic compaction off, since it keeps the window from filling this far.
+const OUTPUT_TOKEN_MIN = 1_024

 /** Tool errors, plus the user declining a permission or dismissing a question. */
 export type ExecuteError = Tool.Error | Permission.DeclinedError | QuestionTool.CancelledError
@@ -69,6 +77,21 @@ export interface Input {
  readonly toolChoice?: LLM.RequestInput["toolChoice"]
  /** Only the durable runner may use a stateful WebSocket. */
  readonly webSocket?: "session"
+  /** Prompt size, measured by the provider or estimated. The default output limit leaves room for it. */
+  readonly inputTokens?: { readonly measured: number; readonly estimated: number }
+}
+
+/** The default output limit: the catalog limit, fitted to the room the prompt leaves in the context window. */
+const outputLimit = (
+  limit: Model.Info["limit"],
+  kind: "primary" | "compaction",
+  inputTokens?: Input["inputTokens"],
+) => {
+  const model = limit.output > 0 ? limit.output : OUTPUT_TOKEN_FALLBACK
+  const requested = kind === "compaction" ? Math.min(model, SUMMARY_OUTPUT_MAX) : model
+  if (inputTokens === undefined || limit.context <= 0) return requested
+  const room = limit.context - inputTokens.measured - Math.ceil(inputTokens.estimated * (1 + ESTIMATE_ERROR))
+  return Math.min(requested, Math.max(OUTPUT_TOKEN_MIN, room))
 }

 export const baseTranscript = (input: {
@@ -218,8 +241,19 @@ export const layer = Layer.effect(
      const given = new Map(
        tools.definitions.map((t) => [{ description: t.description, input: { ...t.inputSchema } }, t] as const),
      )
+      // Hooks see the default output limit and may change or remove it. Titles and generate keep the provider default,
+      // because their reasoning is hard to budget.
      const shaped = yield* shape(
-        { sessionID: session.id, model: model.ref, system: input.system, messages: input.messages, options: {} },
+        {
+          sessionID: session.id,
+          model: model.ref,
+          system: input.system,
+          messages: input.messages,
+          options:
+            kind === "primary" || kind === "compaction"
+              ? { maxTokens: outputLimit(model.limit, kind, input.inputTokens) }
+              : {},
+        },
        Object.fromEntries(Array.from(given, ([d, t]) => [t.name, d])),
      )
      // Match by identity first, then by key. Entries matching neither were invented by a
@@ -2,7 +2,7 @@ export * as SessionProviderContext from "./provider-context.js"

 import { Message } from "@opencode/ai"
 import { SessionProviderContext } from "@opencode/schema/session-provider-context"
-import { Schema } from "effect"
+import { Predicate, Schema } from "effect"
 import { isDeepStrictEqual } from "node:util"
 import { Hash } from "@opencode/util/hash"
 import type { SessionMessage } from "./message.js"
@@ -54,5 +54,31 @@ export const encode = (provenance: Provenance, replacement: ReadonlyArray<Messag
  messages: Schema.decodeSync(Schema.fromJsonString(Schema.Json))(JSON.stringify(replacement)),
 })

-export const decode = (context: Info) => Schema.decodeUnknownSync(messages)(context.messages)
-export const validate = (context: Info) => Schema.decodeUnknownEffect(messages)(context.messages)
+export const decode = (context: Info) => Schema.decodeUnknownSync(messages)(upgradeLegacyMedia(context.messages))
+export const validate = (context: Info) => Schema.decodeUnknownEffect(messages)(upgradeLegacyMedia(context.messages))
+
+/**
+ * Before 2.0.15, version-1 checkpoints stored mediaType/data directly on media parts. Core only built
+ * those parts from prompt attachments, whose data the Prompt schema guarantees is base64.
+ */
+function upgradeLegacyMedia(input: Info["messages"]) {
+  if (!Array.isArray(input)) return input
+  return input.map((message: unknown) => {
+    if (!Predicate.isObject(message) || !Array.isArray(message.content)) return message
+    return {
+      ...message,
+      content: message.content.map((part: unknown) => {
+        if (
+          !Predicate.isObject(part) ||
+          part.type !== "media" ||
+          part.media !== undefined ||
+          typeof part.mediaType !== "string" ||
+          typeof part.data !== "string"
+        )
+          return part
+        const { mediaType, data, ...rest } = part
+        return { ...rest, media: { source: { type: "base64", data, mediaType } } }
+      }),
+    }
+  })
+}
@@ -20,6 +20,7 @@ import { SessionSchema } from "../schema.js"
 import { SessionStore } from "../store.js"
 import { SessionMessageTable } from "../sql.js"
 import { SessionTitle } from "../title.js"
+import { toSessionError } from "../to-session-error.js"
 import { DrainResult, Service, type Interface } from "./index.js"
 import { Snapshot } from "../../snapshot.js"
 import { makeLocationNode } from "@opencode/util/effect/app-node"
@@ -109,39 +110,39 @@ const layer = Layer.effect(
              if (pending?.type === "move")
                return DrainResult.Moved({ continuation: continuing ? { step } : undefined })
              if (pending?.type === "compaction") {
-                const session = yield* store.get(sessionID)
-                if (!session) return yield* Effect.die(new Error(`Session not found: ${sessionID}`))
                const compacted = yield* restore(
                  Effect.gen(function* () {
-                    return yield* compaction.compactManual({
-                      session,
-                      resolveContext: (session) =>
-                        Effect.gen(function* () {
-                          const selected = yield* context.select(session.id)
-                          const model = yield* context.resolveModel(selected.session)
-                          // Preview updates without admitting them after the already-delivered compaction marker.
-                          const history = yield* SessionHistory.preview(
-                            db,
-                            session.id,
-                            selected.instructions,
-                            SessionProviderContext.provenance(model) ?? "local",
-                          )
-                          return {
-                            session: selected.session,
-                            agent: selected.agent,
-                            tools: selected.tools,
-                            model,
-                            initial: history.initial,
-                            messages: history.messages,
-                            instructionUpdate: history.instructionUpdate,
-                          }
-                        }),
-                      prepare: context.request.compaction,
-                      messages: yield* store.context(sessionID),
+                    const selected = yield* context.select(sessionID)
+                    const model = yield* context.resolveModel(selected.session)
+                    // Preview updates without admitting them after the already-delivered compaction marker.
+                    const history = yield* SessionHistory.preview(
+                      db,
+                      sessionID,
+                      selected.instructions,
+                      SessionProviderContext.provenance(model) ?? "local",
+                    )
+                    return yield* compaction.compact({
+                      reason: "manual",
                      inputID: pending.id,
-                      started: true,
+                      context: {
+                        session: selected.session,
+                        agent: selected.agent,
+                        tools: selected.tools,
+                        model,
+                        initial: history.initial,
+                        messages: history.messages,
+                      },
                    })
-                  }),
+                  }).pipe(
+                    Effect.catch((error) =>
+                      bus.publish(SessionEvent.Compaction.Failed, {
+                        sessionID,
+                        reason: "manual",
+                        inputID: pending.id,
+                        error: toSessionError(error),
+                      }),
+                    ),
+                  ),
                ).pipe(Effect.exit)
                if (Exit.isFailure(compacted)) {
                  yield* bus.publish(SessionEvent.Compaction.Failed, {
@@ -213,14 +214,9 @@ const layer = Layer.effect(
        // Reuse boundary preparation once; retries refresh context without delivering more input.
        const loaded = initial ?? (yield* prepareContext(sessionID).pipe(Effect.flatMap(context.load)))
        initial = undefined
-        const compactionInput = {
-          context: loaded,
-          prepare: context.request.compaction,
-        }
-        if (compaction.required({ messages: loaded.messages, resolved: loaded.model, context: loaded })) {
-          const result = yield* compaction.compact(compactionInput)
-          if (result.status !== "completed") return yield* new StepFailedError({ error: result.error })
-          if (result.recoveredOverflow) recoverOverflow = false
+        const compacted = yield* compaction.compact({ reason: "auto", context: loaded })
+        if (compacted.status === "failed") return yield* new StepFailedError({ error: compacted.error })
+        if (compacted.status === "completed") {
          assistantMessageID = SessionMessage.ID.create()
          continue
        }
@@ -244,6 +240,7 @@ const layer = Layer.effect(
          // Keep tool definitions on the final Step to preserve the provider's cached prefix.
          toolChoice: stepLimitReached ? "none" : undefined,
          webSocket: "session",
+          inputTokens: SessionCompaction.estimatePrompt(loaded),
        })
        const outcome = yield* steps.attempt({
          isLocationClosed: lifecycle.isClosed,
@@ -263,9 +260,9 @@ const layer = Layer.effect(
            }),
          recoverContinuation,
          recoverOverflow: Effect.suspend(() =>
-            recoverOverflow && compaction.enabled()
+            recoverOverflow
              ? compaction
-                  .compact({ ...compactionInput, overflow: true })
+                  .compact({ reason: "overflow", context: loaded })
                  .pipe(Effect.map((result) => result.status === "completed"))
              : Effect.succeed(false),
          ),
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
Shoubhit Dash	5c1e7ca00f	feat(app): show last turn changes in review panel	2026-09-27 15:06:22 +05:30
Shoubhit Dash	c33de198e3	fix(ai): surface truncated Gemini speech and transcription results (#51379 )	2026-09-27 14:29:36 +05:30
Shoubhit Dash	24224bcb57	fix(ai): describe speech assets in the format actually sent (#51377 )	2026-09-27 14:16:23 +05:30
Aiden Cline	7913c8db59	feat(core): log provider rejections that trigger overflow compaction (#51582 )	2026-09-26 23:11:33 -05:00
Aiden Cline	d9987ef9c8	feat(core): fit output limits to the context window (#51271 )	2026-09-26 22:58:28 -05:00
Jack	f0ed4f67df	docs: list LongCat 2.5 Preview Free in V2 Console (#51487 )	2026-09-26 21:20:36 +08:00
opencode-agent[bot]	2109d68d39	chore(core): refresh bundled models.dev snapshot	2026-09-26 12:18:22 +00:00
Filip	cefb2968e2	fix(cli): cancel auth attempts on ctrl+c (#51484 )	2026-09-26 11:59:17 +00:00
opencode-agent[bot]	00d179015f	chore: update nix node_modules hashes	2026-09-26 10:01:15 +00:00
opencode-agent[bot]rekram1-node thdxr rekram1-node Filip Hejmowski	1d4e1233e5	feat(cli): share grouped auth picker with MCP auth (#51006 ) Co-authored-by: rekram1-node <rekram1-node@users.noreply.github.com> Co-authored-by: thdxr <thdxr@users.noreply.github.com> Co-authored-by: rekram1-node <63023139+rekram1-node@users.noreply.github.com> Co-authored-by: Filip Hejmowski <fhejmowski@simplito.com>	2026-09-26 11:42:04 +02:00
opencode-agent[bot]vimtor Victor Navarro	d14f20b46e	fix(tui): capitalize OpenCode web search provider (#49023 ) Co-authored-by: vimtor <36263538+vimtor@users.noreply.github.com> Co-authored-by: Victor Navarro <vn4varro@gmail.com>	2026-09-26 09:36:20 +00:00
opencode-agent[bot]andrekram1-node	37049a5a13	fix(tui): skip model selection after MCP connection (#51448 ) Co-authored-by: rekram1-node <rekram1-node@users.noreply.github.com>	2026-09-26 00:00:25 -05:00
Aiden Cline	a64bc3616e	refactor(core): cleanup session compaction (#51447 )	2026-09-26 00:00:11 -05:00
opencode	39021dfd67	sync release versions for v2.0.18	2026-09-25 23:57:39 +00:00
opencode-agent[bot]	709ddc0d79	chore: update nix node_modules hashes	2026-09-25 23:23:45 +00:00
Kit LangtonandAiden Cline	041885d838	fix(core): decode legacy media in compaction checkpoints (#51409 ) Co-authored-by: Aiden Cline <aidenpcline@gmail.com>	2026-09-25 18:08:16 -05:00
Aiden Cline	29ce49db0f	refactor(util): share a browser opener across cli, tui, and core (#51412 )	2026-09-25 18:00:32 -05:00
opencode	00738c5b2d	sync release versions for v2.0.17	2026-09-25 21:09:12 +00:00
Aiden Cline	6ec8ca920f	feat(core): name Copilot sessions with the free utility model (#51237 )	2026-09-25 14:53:16 -05:00
Shoubhit Dash	6585bb7105	fix(ai): keep OpenAI image output settings and Z.ai URL expiry (#51380 )	2026-09-25 22:51:46 +05:30
Shoubhit Dash	f954688fbb	fix(ai): harden OpenAI transcription stream parsing (#51378 )	2026-09-25 22:51:22 +05:30
Shoubhit Dash	1463dabde9	fix(ai): tighten media error consistency (#51374 )	2026-09-25 22:46:04 +05:30
Shoubhit Dash	29ea6ee05b	test(ai): cover media facade selectors and url asset edges (#51376 )	2026-09-25 22:37:20 +05:30
Shoubhit Dash	b170904731	docs(ai): describe transcription speakers as a constraint (#51382 )	2026-09-25 22:36:02 +05:30
Shoubhit Dash	88e1fa9304	fix(ai): accept timestamps: false on speech routes without timestamps (#51375 )	2026-09-25 22:33:59 +05:30
opencode-agent[bot]andvimtor	ff1bf315ed	docs(www): hide Console Usage API documentation (#51358 ) Co-authored-by: vimtor <36263538+vimtor@users.noreply.github.com>	2026-09-25 19:01:48 +02:00
Shoubhit Dash	144ce00e00	fix(ai): bound generation event poll sleep by the deadline (#51372 )	2026-09-25 22:31:35 +05:30
Shoubhit Dash	ad504094f0	fix(ai): never delete a finished Runway task on cancel (#51373 )	2026-09-25 22:24:16 +05:30
Shoubhit Dash	bad6834a3e	fix(ai): size fal Kontext by aspect ratio and decode sync_mode data URIs (#51371 )	2026-09-25 22:23:14 +05:30
Shoubhit Dash	0c4bbc3cd1	feat(ai): keep prompt cache across effort switches on GPT-6 Sol and Luna (#51339 )	2026-09-25 22:15:23 +05:30
Shoubhit Dash	ae7dd82126	fix(ai): report Black Forest Labs submit cost as image usage (#51370 )	2026-09-25 22:13:55 +05:30
Shoubhit Dash	65d5123ead	fix(ai): enable AssemblyAI speaker labels when speakers is set (#51369 )	2026-09-25 22:11:44 +05:30
Shoubhit Dash	4eb46a8885	fix(core): revert always-thinking variants for Claude Opus 5.5 (#51359 )	2026-09-25 22:03:12 +05:30
Jack	1986e92842	docs(go): show permanent DeepSeek $60 allowance (#51363 )	2026-09-26 00:17:08 +08:00
Shoubhit Dash	14fc63ba9e	fix(core): keep thinking on for Claude Opus 5.5 variants (#51338 )	2026-09-25 18:32:41 +05:30
opencode-agent[bot]andnexxeln	c34ffa117e	fix(ai): preserve Gemini 3.8 TTS WAV output (#51300 ) Co-authored-by: nexxeln <95541290+nexxeln@users.noreply.github.com>	2026-09-25 18:11:36 +05:30
opencode-agent[bot]vimtor vimtor	beeb14e910	feat(prompt): undo queued prompts back into the input (#51124 ) Co-authored-by: vimtor <36263538+vimtor@users.noreply.github.com> Co-authored-by: vimtor <vn4varro@gmail.com>	2026-09-25 14:36:29 +02:00
opencode-agent[bot]	aae42e2e75	chore(core): refresh bundled models.dev snapshot	2026-09-25 12:21:04 +00:00
opencode-agent[bot]vimtor vimtor	cc9011c1ae	fix(tui): virtualize large added-file diffs (#51122 ) Co-authored-by: vimtor <36263538+vimtor@users.noreply.github.com> Co-authored-by: vimtor <vn4varro@gmail.com>	2026-09-25 13:51:00 +02:00
Victor Navarro	6cd938e1e9	feat(core): register Console-hosted MCP servers (#51325 )	2026-09-25 13:16:04 +02:00
Jack	7de6b3fc15	docs(console): document Qwen3.8 Max (#51320 )	2026-09-25 19:13:45 +08:00
opencode-agent[bot]	c1c9a13993	chore: update nix node_modules hashes	2026-09-25 08:37:39 +00:00
Simon Klee	917d904f18	tui: update OpenTUI v0.5.12 (#50567 )	2026-09-25 08:17:14 +00:00
opencode-agent[bot]andBrendonovich	ee5b67eb84	fix(app): unify session project icon resolution (#51288 ) Co-authored-by: Brendonovich <14191578+Brendonovich@users.noreply.github.com>	2026-09-25 07:47:12 +00:00
Aiden Cline	048a47e89e	docs: focus compaction page on user-facing behavior (#51270 )	2026-09-25 00:21:17 -05:00