fix(ai): classify Z.ai prompt length, sensitive content, and fair-use errors

fix(ai): classify Z.ai plan and balance limits as quota
fix(ai): read provider error messages from common body layouts (#52014 )
2026-09-30 04:27:37 +00:00 · 2026-09-29 10:53:10 -05:00 · 2026-09-29 10:43:07 -05:00 · 2026-09-29 00:19:20 -05:00 · 2026-09-29 15:09:50 +10:00 · 2026-09-29 00:06:52 -05:00
114 changed files with 1222 additions and 310 deletions
@@ -32,7 +32,7 @@
    },
    "packages/ai": {
      "name": "@opencode/ai",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@aws-sdk/credential-providers": "3.1057.0",
        "@opencode/schema": "workspace:*",
@@ -54,7 +54,7 @@
    },
    "packages/app": {
      "name": "@opencode/app",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@corvu/drawer": "catalog:",
        "@dnd-kit/abstract": "0.5.0",
@@ -112,7 +112,7 @@
    },
    "packages/cli": {
      "name": "@opencode/cli",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "bin": {
        "opencode": "./bin/opencode.cjs",
        "opencode2": "./bin/opencode2.cjs",
@@ -178,7 +178,7 @@
    },
    "packages/client": {
      "name": "@opencode/client",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@opencode/protocol": "workspace:*",
        "@opencode/schema": "workspace:*",
@@ -204,7 +204,7 @@
    },
    "packages/codemode": {
      "name": "@opencode/codemode",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "acorn": "8.15.0",
        "effect": "catalog:",
@@ -217,7 +217,7 @@
    },
    "packages/console/app": {
      "name": "@opencode/console-app",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@cloudflare/vite-plugin": "1.15.2",
        "@ibm/plex": "6.4.1",
@@ -253,7 +253,7 @@
    },
    "packages/console/core": {
      "name": "@opencode/console-core",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@aws-sdk/client-sts": "3.782.0",
        "@jsx-email/render": "1.1.1",
@@ -280,7 +280,7 @@
    },
    "packages/console/function": {
      "name": "@opencode/console-function",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@openauthjs/openauth": "0.0.0-20250322224806",
        "@opencode/console-core": "workspace:*",
@@ -297,7 +297,7 @@
    },
    "packages/console/mail": {
      "name": "@opencode/console-mail",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@jsx-email/all": "2.2.3",
        "@jsx-email/cli": "1.4.3",
@@ -321,7 +321,7 @@
    },
    "packages/console/support": {
      "name": "@opencode/console-support",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@cloudflare/vite-plugin": "1.15.2",
        "@opencode/console-core": "workspace:*",
@@ -341,7 +341,7 @@
    },
    "packages/core": {
      "name": "@opencode/core",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@ai-sdk/cohere": "3.0.27",
        "@ai-sdk/gateway": "3.0.104",
@@ -409,7 +409,7 @@
    },
    "packages/desktop": {
      "name": "@opencode/desktop",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@zip.js/zip.js": "2.7.62",
        "electron-context-menu": "5.0.0",
@@ -439,7 +439,7 @@
        "drizzle-kit": "catalog:",
        "drizzle-orm": "catalog:",
        "effect": "catalog:",
-        "electron": "44.4.3",
+        "electron": "44.4.5",
        "electron-builder": "26.15.7",
        "electron-vite": "6.0.0-beta.1",
        "puppeteer-core": "25.9.0",
@@ -458,7 +458,7 @@
    },
    "packages/enterprise": {
      "name": "@opencode/enterprise",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@hono/standard-validator": "catalog:",
        "@opencode-ai/sdk": "1.18.21",
@@ -495,7 +495,7 @@
    },
    "packages/function": {
      "name": "@opencode/function",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@octokit/auth-app": "8.0.1",
        "@octokit/rest": "catalog:",
@@ -511,7 +511,7 @@
    },
    "packages/http-recorder": {
      "name": "@opencode/http-recorder",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@effect/platform-node-shared": "4.0.0-rc.112",
      },
@@ -530,7 +530,7 @@
    },
    "packages/httpapi-codegen": {
      "name": "@opencode/httpapi-codegen",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "effect": "catalog:",
        "prettier": "3.6.2",
@@ -543,7 +543,7 @@
    },
    "packages/latex": {
      "name": "@opencode/latex",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@opencode/plugin": "workspace:*",
        "@opentui/core": "catalog:",
@@ -557,7 +557,7 @@
    },
    "packages/merman": {
      "name": "@opencode/merman",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@opencode/plugin": "workspace:*",
        "@opentui/core": "catalog:",
@@ -572,7 +572,7 @@
    },
    "packages/plugin": {
      "name": "@opencode/plugin",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@ai-sdk/provider": "3.0.8",
        "@opencode/ai": "workspace:*",
@@ -611,7 +611,7 @@
    },
    "packages/plugin-browser": {
      "name": "@opencode/plugin-browser",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@opencode/plugin": "workspace:*",
        "@opencode/schema": "workspace:*",
@@ -641,7 +641,7 @@
    },
    "packages/protocol": {
      "name": "@opencode/protocol",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@opencode/schema": "workspace:*",
        "effect": "catalog:",
@@ -656,7 +656,7 @@
    },
    "packages/schema": {
      "name": "@opencode/schema",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@standard-schema/spec": "catalog:",
        "effect": "catalog:",
@@ -680,7 +680,7 @@
    },
    "packages/sdk": {
      "name": "@opencode/sdk",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@opencode/client": "workspace:*",
        "@opencode/core": "workspace:*",
@@ -701,7 +701,7 @@
    },
    "packages/server": {
      "name": "@opencode/server",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@effect/platform-node": "catalog:",
        "@effect/platform-node-shared": "catalog:",
@@ -723,7 +723,7 @@
    },
    "packages/session-ui": {
      "name": "@opencode/session-ui",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@kobalte/core": "catalog:",
        "@opencode/client": "workspace:*",
@@ -758,7 +758,7 @@
    },
    "packages/simulation": {
      "name": "@opencode/simulation",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@opencode/ai": "workspace:*",
        "@opencode/core": "workspace:*",
@@ -778,7 +778,7 @@
    },
    "packages/stats/app": {
      "name": "@opencode/stats-app",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@ibm/plex": "6.4.1",
        "@kobalte/core": "catalog:",
@@ -812,7 +812,7 @@
    },
    "packages/stats/core": {
      "name": "@opencode/stats-core",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@aws-sdk/client-athena": "3.933.0",
        "@planetscale/database": "1.19.0",
@@ -831,7 +831,7 @@
    },
    "packages/stats/server": {
      "name": "@opencode/stats-server",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@aws-sdk/client-firehose": "3.933.0",
        "@effect/platform-node": "catalog:",
@@ -877,7 +877,7 @@
    },
    "packages/theme": {
      "name": "@opencode/theme",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@opentui/core": "catalog:",
        "effect": "catalog:",
@@ -891,7 +891,7 @@
    },
    "packages/tui": {
      "name": "@opencode/tui",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@opencode/client": "workspace:*",
        "@opencode/core": "workspace:*",
@@ -925,7 +925,7 @@
    },
    "packages/ui": {
      "name": "@opencode/ui",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@kobalte/core": "catalog:",
        "@pierre/diffs": "catalog:",
@@ -960,7 +960,7 @@
    },
    "packages/util": {
      "name": "@opencode/util",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@effect/opentelemetry": "catalog:",
        "@effect/platform-node": "catalog:",
@@ -998,7 +998,7 @@
    },
    "packages/web": {
      "name": "@opencode/web",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "@astrojs/cloudflare": "12.6.3",
        "@astrojs/markdown-remark": "6.3.1",
@@ -1039,7 +1039,7 @@
    },
    "services/update": {
      "name": "@opencode/update",
-      "version": "2.0.18",
+      "version": "2.0.19",
      "dependencies": {
        "jose": "6.0.11",
        "semver": "catalog:",
@@ -1119,7 +1119,7 @@
    "@opentui/core": "0.5.12",
    "@opentui/keymap": "0.5.12",
    "@opentui/solid": "0.5.12",
-    "@pierre/diffs": "1.2.10",
+    "@pierre/diffs": "1.5.1",
    "@playwright/test": "1.59.1",
    "@sentry/solid": "10.71.0",
    "@sentry/vite-plugin": "5.4.0",
@@ -2530,11 +2530,11 @@

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

    "@puppeteer/browsers/yargs/cliui": ["cliui@9.0.1", "", { "dependencies": { "string-width": "^7.2.0", "strip-ansi": "^7.1.0", "wrap-ansi": "^9.0.0" } }, "sha512-k7ndgKhwoQveBL+/1tqGJYNz097I7WOvwbmmU2AR5+magtbjPWQTS1C5vzGkBC8Ym8UWRzfKUzUUqFLypY4Q+w=="],
@@ -2,7 +2,7 @@
  "$schema": "https://json.schemastore.org/package.json",
  "name": "opencode",
  "description": "AI-powered development tool",
-  "version": "2.0.18",
+  "version": "2.0.19",
  "private": true,
  "type": "module",
  "packageManager": "bun@1.4.2",
@@ -68,7 +68,7 @@
      "@tsconfig/bun": "1.0.9",
      "@cloudflare/workers-types": "4.20251008.0",
      "@openauthjs/openauth": "0.0.0-20250322224806",
-      "@pierre/diffs": "1.2.10",
+      "@pierre/diffs": "1.5.1",
      "opentui-spinner": "0.0.7",
      "@solid-primitives/event-listener": "2.4.6",
      "@solid-primitives/media": "2.3.6",
@@ -1,6 +1,6 @@
 {
  "$schema": "https://json.schemastore.org/package.json",
-  "version": "2.0.18",
+  "version": "2.0.19",
  "name": "@opencode/ai",
  "type": "module",
  "license": "MIT",
@@ -39,6 +39,7 @@ const resolve = (policy: CachePolicy | undefined): CachePolicyObject => {
 // whole policy pass for these — emitting hints would be harmless but pointless.
 const RESPECTS_INLINE_HINTS = new Set([
  "anthropic-messages",
+  "anthropic-compatible-messages",
  "google-vertex-messages",
  "bedrock-converse",
  "openrouter",
@@ -29,6 +29,7 @@ import { JsonObject, knownString, optionalArray, optionalNull, ProviderShared }
 import { classifyProviderFailure } from "../provider-error.js"
 import { effortUpdate, resolveEffortUpdates } from "../effort-updates.js"
 import * as Cache from "./utils/cache.js"
+import { claudeVersion, supportsThinkingBlockBinding, THINKING_BINDING_BETA } from "./utils/claude-model.js"
 import { Lifecycle } from "./utils/lifecycle.js"
 import { ToolStream } from "./utils/tool-stream.js"

@@ -988,22 +989,6 @@ const lowerMessages = Effect.fn("AnthropicMessages.lowerMessages")(function* (
  return messages
 })

-// Accept gateway namespaces and Vertex suffixes without treating a snapshot date as a minor version.
-const claudeVersion = (id: string) => {
-  const match = /(?:^|[./])claude-(?<family>[a-z]+)-(?<major>\d+)(?:[.-](?<minor>\d{1,2}))?(?:$|[-:@])/.exec(
-    id.toLowerCase(),
-  )?.groups
-  if (!match) return undefined
-  return { family: match.family, major: Number(match.major), minor: Number(match.minor ?? 0) }
-}
-
-const supportsThinkingBlockBinding = (model: LLMRequest["model"]) => {
-  const override = model.compatibility?.supportsThinkingBlockBinding
-  if (override !== undefined) return override
-  const version = claudeVersion(model.id)
-  return version !== undefined && (version.major > 5 || (version.major === 5 && version.minor >= 1))
-}
-
 const supportsEffortUpdates = (model: LLMRequest["model"]) => {
  const override = model.compatibility?.supportsEffortUpdates
  if (override !== undefined) return override
@@ -1652,8 +1637,7 @@ function requiredBetaHeaders(body: Pick<AnthropicMessagesBody, "messages" | "con
    betas.push("mid-conversation-output-config-2026-07-01")

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

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

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

 const encodeRedactedContent = (chunks: ReadonlyArray<Uint8Array>) => Encoding.encodeBase64(concatBytes(chunks))
@@ -605,10 +627,9 @@ const step = (state: ParserState, event: BedrockEvent) =>
      const index = event.contentBlockDelta.contentBlockIndex
      const reasoning = event.contentBlockDelta.delta.reasoningContent
      const events: LLMEvent[] = []
-      const redactedChunks = yield* (() => {
+      const redactedChunk = yield* (() => {
        if (reasoning.redactedContent === undefined) return Effect.succeed(undefined)
        return Effect.fromResult(Encoding.decodeBase64(reasoning.redactedContent)).pipe(
-          Effect.map((chunk) => [...(state.reasoningRedactedContent[index] ?? []), chunk]),
          Effect.mapError((cause) =>
            ProviderShared.eventError(
              ADAPTER,
@@ -619,17 +640,21 @@ const step = (state: ParserState, event: BedrockEvent) =>
          ),
        )
      })()
-      const redactedData = redactedChunks === undefined ? reasoning.data : encodeRedactedContent(redactedChunks)
+      const redactedChunks = state.reasoningRedactedContent[index] ?? []
+      if (redactedChunk !== undefined) redactedChunks.push(redactedChunk)
      const metadata = (() => {
        if (reasoning.signature) return providerMetadata(state.providerMetadataKey, { signature: reasoning.signature })
-        if (redactedData !== undefined) return providerMetadata(state.providerMetadataKey, { redactedData })
+        if (redactedChunk === undefined && reasoning.data !== undefined)
+          return providerMetadata(state.providerMetadataKey, { redactedData: reasoning.data })
      })()
      const lifecycle = (() => {
-        if (reasoning.text === undefined && metadata === undefined) return state.lifecycle
-        return Lifecycle.reasoningDelta(state.lifecycle, events, `reasoning-${index}`, reasoning.text ?? "", metadata)
+        if (reasoning.text !== undefined || metadata !== undefined)
+          return Lifecycle.reasoningDelta(state.lifecycle, events, `reasoning-${index}`, reasoning.text ?? "", metadata)
+        if (redactedChunk !== undefined) return Lifecycle.reasoningStart(state.lifecycle, events, `reasoning-${index}`)
+        return state.lifecycle
      })()
      const reasoningRedactedContent = (() => {
-        if (redactedChunks !== undefined) return { ...state.reasoningRedactedContent, [index]: redactedChunks }
+        if (redactedChunk !== undefined) return { ...state.reasoningRedactedContent, [index]: redactedChunks }
        if (reasoning.data === undefined) return state.reasoningRedactedContent
        return Object.fromEntries(
          Object.entries(state.reasoningRedactedContent).filter(([key]) => key !== String(index)),
@@ -765,7 +790,19 @@ const onHalt = (state: ParserState): ReadonlyArray<LLMEvent> => {
    return state.finishReason.normalized
  })()
  const events: LLMEvent[] = []
-  Lifecycle.finish(state.lifecycle, events, {
+  const lifecycle = Object.entries(state.reasoningRedactedContent).reduce((current, [index, chunks]) => {
+    const signature = state.reasoningSignatures[Number(index)]
+    return Lifecycle.reasoningEnd(
+      current,
+      events,
+      `reasoning-${index}`,
+      providerMetadata(
+        state.providerMetadataKey,
+        signature ? { signature } : { redactedData: encodeRedactedContent(chunks) },
+      ),
+    )
+  }, state.lifecycle)
+  Lifecycle.finish(lifecycle, events, {
    reason: {
      ...state.finishReason,
      normalized,
@@ -0,0 +1,19 @@
+import type { LLMRequest } from "../../schema/index.js"
+
+export const THINKING_BINDING_BETA = "thinking-binding-controls-2026-08-01"
+
+// Accept gateway namespaces and Vertex suffixes without treating a snapshot date as a minor version.
+export const claudeVersion = (id: string) => {
+  const match = /(?:^|[./])claude-(?<family>[a-z]+)-(?<major>\d+)(?:[.-](?<minor>\d{1,2}))?(?:$|[-:@])/.exec(
+    id.toLowerCase(),
+  )?.groups
+  if (!match) return undefined
+  return { family: match.family, major: Number(match.major), minor: Number(match.minor ?? 0) }
+}
+
+export const supportsThinkingBlockBinding = (model: LLMRequest["model"]) => {
+  const override = model.compatibility?.supportsThinkingBlockBinding
+  if (override !== undefined) return override
+  const version = claudeVersion(model.id)
+  return version !== undefined && (version.major > 5 || (version.major === 5 && version.minor >= 1))
+}
@@ -1,4 +1,4 @@
-import { Option, Schema } from "effect"
+import { Option, Schema, SchemaGetter } from "effect"
 import {
  AuthenticationError,
  ContentPolicyError,
@@ -33,7 +33,8 @@ const patterns = [
  /context[_ ]length[_ ]exceeded/i,
  /context length is only \d+ tokens/i,
  /input length.*exceeds.*context length/i,
-  /prompt too long; exceeded (?:max )?context length/i,
+  // Z.ai code 1261 arrives as `Prompt too long` or `Prompt 超长`.
+  /prompt (?:too long|超长)/i,
  /too large for model with \d+ maximum context length/i,
  /prompt has [\d,]+ tokens?, but the configured context size is [\d,]+ tokens?/i,
  /model_context_window_exceeded/i,
@@ -109,7 +110,8 @@ const QUOTA_CODES = new Set([
  "freeusagelimiterror",
  "creditlimitexceeded",
 ])
-const AUTH_CODES = new Set(["authentication_error", "permission_error"])
+// Google reports an invalid API key as HTTP 400 INVALID_ARGUMENT with this `details[].reason`.
+const AUTH_CODES = new Set(["authentication_error", "permission_error", "api_key_invalid"])
 const SERVER_CODES = new Set([
  "api_error",
  "internal_error",
@@ -144,16 +146,53 @@ const CONTENT_POLICY_CODES = new Set([
 const GATEWAY_CODE_LABEL = /^[^:\n]+: \[([A-Za-z0-9_.-]+)\]/
 const RATE_LIMIT_TEXT = /rate increased too quickly|rate[-_\s]?limit|too[_\s]?many[_\s]?requests/i
 // Only consulted on 429, where throttles and account caps share a status.
-const QUOTA_TEXT = /insufficient[-_\s]?quota|quota[-_\s]?exceeded|budget exceeded|usage limit/i
+// Z.ai reports balance, plan expiry, plan limits, plan model access, and fair-use restrictions on 429.
+const QUOTA_TEXT =
+  /insufficient[-_\s]?(?:quota|balance)|quota[-_\s]?exceeded|budget exceeded|usage limit|limit exhausted|package has expired|plan does not yet include|fair usage policy/i
 // Policy rejections without a dedicated code, matched against the provider's own
 // explanation only. OpenAI reuses `invalid_prompt` for usage-policy rejections while
 // Bedrock Mantle reuses it for schema validation; Anthropic reports blocked output
 // under `invalid_request_error`.
 const CONTENT_POLICY_TEXT =
-  /violating our usage policy|blocked by content filtering policy|content[-_\s]?policy|rejected as a result of our safety system/i
+  /violating our usage policy|blocked by content filtering policy|content[-_\s]?policy|rejected as a result of our safety system|detected potentially unsafe or sensitive content/i
 const SERVER_ERROR_TEXT =
  /\b(?:try again|(?:please |you can )?retry (?:the |this |your )?request|try (?:the |this |your )?request again|(?:currently |temporarily )?at capacity|overloaded|temporarily unavailable|service[-_\s]?unavailable|(?:server|internal)[-_\s]?error|server (?:is )?busy|provider returned (?:an )?error|resource[-_\s]?exhausted|upstream (?:connect|connection|request)|request buffer limit while retrying upstream)\b/i

+const Message = Schema.String.check(Schema.isPattern(/\S/))
+
+const messageAt = <Fields extends Schema.Struct.Fields>(
+  fields: Fields,
+  message: (body: Schema.Struct<Fields>["Type"]) => string,
+) =>
+  Schema.Struct(fields).pipe(
+    Schema.decodeTo(Schema.String, {
+      decode: SchemaGetter.transform(message),
+      encode: SchemaGetter.forbidden(() => "Provider error messages are decode-only"),
+    }),
+  )
+
+// Common error body layouts that carry a human-readable message, in priority order.
+// Provider-specific layouts belong in their protocol.
+const decodeMessage = Schema.decodeUnknownOption(
+  Schema.fromJsonString(
+    Schema.Union([
+      messageAt({ error: Schema.Struct({ message: Message }) }, (body) => body.error.message),
+      messageAt({ error: Message }, (body) => body.error),
+      messageAt({ message: Message }, (body) => body.message),
+      // AWS services
+      messageAt({ Message: Message }, (body) => body.Message),
+      // RFC 9457 problem details
+      messageAt({ detail: Message }, (body) => body.detail),
+      messageAt(
+        { errors: Schema.NonEmptyArray(Schema.Struct({ message: Message })) },
+        (body) => body.errors[0].message,
+      ),
+    ]),
+  ),
+)
+
+export const providerErrorMessage = (body: string) => Option.getOrUndefined(decodeMessage(body))
+
 export interface ProviderFailure {
  readonly message: string
  readonly status?: number | undefined
@@ -259,6 +298,10 @@ function providerCodes(value: unknown) {
    error?.type,
    error?.status,
    error?.error_type,
+    // Google `google.rpc.ErrorInfo` details carry the specific reason.
+    ...(Array.isArray(error?.details)
+      ? error.details.map((detail) => (isRecord(detail) ? detail.reason : undefined))
+      : []),
    inner?.code,
    metadata?.error_type,
    responseError?.code,
@@ -28,7 +28,8 @@ export type Settings = ProviderPackage.Settings &
    readonly provider?: string
  }

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

 const auth = (input: ProviderAuthOption<"optional">) => {
  if ("auth" in input && input.auth) return input.auth
@@ -43,7 +44,7 @@ export const configure = (input: Config) => {
      message: "Anthropic-compatible providers require a baseURL",
    })
  const { provider: _, baseURL, apiKey: _apiKey, auth: _auth, ...rest } = input
-  const route = AnthropicMessages.route.with({
+  const route = (provider === "anthropic" ? AnthropicMessages.route : compatibleRoute).with({
    ...rest,
    provider,
    endpoint: { baseURL },
@@ -35,13 +35,13 @@ const RESPONSES_WEBSOCKET_ROTATE_AFTER_MS = 24 * 60 * 1000

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

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

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

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

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

 const statusError = (response: HttpClientResponse.HttpClientResponse) =>
@@ -3,7 +3,7 @@ import { Effect } from "effect"
 import { CacheHint, LLM, Message } from "../src/index.js"
 import { Auth } from "../src/route.js"
 import { compileRequest } from "../src/route/client.js"
-import { AmazonBedrock, GoogleVertexMessages } from "../src/providers.js"
+import { AmazonBedrock, AnthropicCompatible, GoogleVertexMessages } from "../src/providers.js"
 import * as AnthropicMessages from "../src/protocols/anthropic-messages.js"
 import * as Gemini from "../src/protocols/gemini.js"
 import * as OpenAIChat from "../src/protocols/openai-chat.js"
@@ -107,6 +107,26 @@ describe("applyCachePolicy", () => {
    }),
  )

+  it.effect("'auto' emits Anthropic cache markers on Anthropic-compatible routes", () =>
+    Effect.gen(function* () {
+      const prepared = yield* compileRequest(
+        LLM.request({
+          model: AnthropicCompatible.configure({ apiKey: "test", baseURL: "https://messages.example.test/v1" }).model(
+            "compatible",
+          ),
+          system: "You are concise.",
+          prompt: "hi",
+        }),
+      )
+
+      expect(prepared.route).toBe("anthropic-compatible-messages")
+      expect(prepared.body).toMatchObject({
+        system: [{ type: "text", text: "You are concise.", cache_control: { type: "ephemeral" } }],
+        messages: [{ role: "user", content: [{ type: "text", text: "hi", cache_control: { type: "ephemeral" } }] }],
+      })
+    }),
+  )
+
  it.effect("'auto' is a no-op on OpenAI (implicit caching protocol)", () =>
    Effect.gen(function* () {
      const prepared = yield* compileRequest(
@@ -273,10 +273,56 @@ describe("RequestExecutor", () => {
      expectAIError(error)
      expect(error.reason).toMatchObject({ _tag: "InvalidRequest" })
      expect("classification" in error.reason ? error.reason.classification : undefined).toBeUndefined()
-      expect(error.message).toBe("Provider request failed with HTTP 400")
+      expect(error.message).toBe("Provider request failed with HTTP 400: invalid parameter")
    }).pipe(Effect.provide(fixedResponse("invalid parameter", { status: 400 }))),
  )

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

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

@@ -154,8 +154,8 @@ describe("public exports", () => {
    expect(XAI.model).toBeFunction()
    expect(XAI.provider.responses).toBe(XAI.responses)
    expect(XAI.provider.chat).toBe(XAI.chat)
-    expect(XAI.configure({ apiKey: "fixture" }).responses("grok-4.3").route.id).toBe("openai-responses")
-    expect(XAI.configure({ apiKey: "fixture" }).chat("grok-4.3").route.id).toBe("openai-compatible-chat")
+    expect(XAI.configure({ apiKey: "fixture" }).responses("grok-4.3").route.id).toBe("xai-responses")
+    expect(XAI.configure({ apiKey: "fixture" }).chat("grok-4.3").route.id).toBe("xai-chat")
    expect(OpenAI.configure({ apiKey: "fixture" }).image("gpt-image-2").route.id).toBe("openai-images")
    expect(OpenAI.provider.image).toBe(OpenAI.image)
    expect(Google.configure({ apiKey: "fixture" }).image("imagen-4.0-generate-001").route.id).toBe("google-images")
@@ -0,0 +1,34 @@
+{
+  "version": 1,
+  "metadata": {
+    "tags": [
+      "prefix:bedrock-converse-thinking-binding",
+      "provider:amazon-bedrock",
+      "protocol:bedrock-converse",
+      "reasoning"
+    ],
+    "name": "bedrock-converse-thinking-binding/accepts-the-default-binding-with-no-thinking-configured",
+    "recordedAt": "2026-09-28T23:09:14.527Z"
+  },
+  "interactions": [
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://bedrock-runtime.us-east-1.amazonaws.com/model/global.anthropic.claude-opus-5-5/converse-stream",
+        "headers": {
+          "content-type": "application/json"
+        },
+        "body": "{\"modelId\":\"global.anthropic.claude-opus-5-5\",\"messages\":[{\"role\":\"user\",\"content\":[{\"text\":\"Say hello.\"}]}],\"system\":[{\"text\":\"Reply with the single word 'Hello'.\"}],\"inferenceConfig\":{\"maxTokens\":1024},\"additionalModelRequestFields\":{\"thinking\":{\"type\":\"adaptive\",\"block_binding\":{\"prefix_mismatch_behavior\":\"drop_block\"}},\"anthropic_beta\":[\"thinking-binding-controls-2026-08-01\"]}}"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "application/vnd.amazon.eventstream"
+        },
+        "body": "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",
+        "bodyEncoding": "base64"
+      }
+    }
+  ]
+}
@@ -1,6 +1,6 @@
 import { describe, expect, test } from "bun:test"
 import { isContextOverflow } from "../src/index.js"
-import { classifyProviderFailure } from "../src/provider-error.js"
+import { classifyProviderFailure, providerErrorMessage } from "../src/provider-error.js"

 describe("provider error classification", () => {
  test("classifies provider token limit messages as context overflow", () => {
@@ -282,6 +282,86 @@ describe("provider error classification", () => {
    ).toEqual(Array(6).fill("QuotaExceeded"))
  })

+  test("classifies Z.ai plan and balance limits as quota rather than throttling", () => {
+    const zai = (code: string, message: string) => ({ error: { code, message } })
+    const cases = [
+      zai("1113", "Insufficient balance or no resource package. Please recharge."),
+      zai("1308", "Usage limit reached for 5 hours. Your limit will reset at 2026-10-01 00:00:00"),
+      zai(
+        "1309",
+        "Your GLM Coding Plan package has expired and is temporarily unavailable. You can resume using it after renewing the subscription on the official website.",
+      ),
+      zai("1310", "Weekly/Monthly Limit Exhausted. Your limit will reset at 2026-10-01 00:00:00"),
+      zai("1311", "Your current subscription plan does not yet include access to glm-5"),
+      zai("1314", "Your enterprise package has expired. Please contact your enterprise administrator."),
+      zai(
+        "1313",
+        "Your account's current usage pattern does not comply with the Fair Usage Policy, and your request frequency has been limited. For details, please refer to the Subscription Service Agreement. To restore access, please submit a request.",
+      ),
+      // Z.ai's Anthropic-compatible endpoint wraps the code and request ID into the message.
+      {
+        type: "error",
+        error: {
+          type: "rate_limit_error",
+          code: "1309",
+          message:
+            "[1309][Your GLM Coding Plan package has expired and is temporarily unavailable. You can resume using it after renewing the subscription on the official website.][20260929132151e73af01340d54b58]",
+        },
+      },
+    ]
+    expect(
+      cases.map(
+        (body) =>
+          classifyProviderFailure({ message: body.error.message, status: 429, rawBody: JSON.stringify(body) })._tag,
+      ),
+    ).toEqual(Array(cases.length).fill("QuotaExceeded"))
+  })
+
+  test("classifies Z.ai prompt length rejections as context overflow", () => {
+    const cases = [
+      { error: { code: "1261", message: "Prompt 超长" } },
+      { error: { code: "1261", message: "Prompt too long" } },
+      {
+        type: "error",
+        error: { type: "invalid_request_error", code: "1261", message: "[1261][Prompt too long][2026092913]" },
+      },
+    ]
+    expect(
+      cases.map((body) => {
+        const reason = classifyProviderFailure({
+          message: body.error.message,
+          status: 400,
+          rawBody: JSON.stringify(body),
+        })
+        return reason._tag === "InvalidRequest" ? reason.classification : reason._tag
+      }),
+    ).toEqual(["context-overflow", "context-overflow", "context-overflow"])
+  })
+
+  test("classifies Z.ai sensitive content rejections as content policy", () => {
+    const message =
+      "System detected potentially unsafe or sensitive content in input or generation. Please avoid using prompts that may generate sensitive content. Thank you for your cooperation."
+    expect(
+      classifyProviderFailure({
+        message,
+        status: 400,
+        rawBody: JSON.stringify({ error: { code: "1301", message } }),
+      })._tag,
+    ).toBe("ContentPolicy")
+  })
+
+  test("keeps Z.ai throttling and overload retryable", () => {
+    expect(
+      [
+        { error: { code: "1302", message: "Rate limit reached for requests" } },
+        { error: { code: "1305", message: "The service may be temporarily overloaded, please try again later" } },
+      ].map(
+        (body) =>
+          classifyProviderFailure({ message: body.error.message, status: 429, rawBody: JSON.stringify(body) })._tag,
+      ),
+    ).toEqual(["RateLimit", "RateLimit"])
+  })
+
  test("does not let substituted server codes make a 4xx retryable", () => {
    const openai = { error: { type: "server_error", message: "Upstream request failed: Model is unavailable." } }
    const anthropic = {
@@ -355,6 +435,32 @@ describe("provider error rawBody classification", () => {
    }
  })

+  test("classifies Google invalid API keys as authentication failures", () => {
+    const rawBody = JSON.stringify({
+      error: {
+        code: 400,
+        message: "API key not valid. Please pass a valid API key.",
+        status: "INVALID_ARGUMENT",
+        details: [
+          {
+            "@type": "type.googleapis.com/google.rpc.ErrorInfo",
+            reason: "API_KEY_INVALID",
+            domain: "googleapis.com",
+          },
+          {
+            "@type": "type.googleapis.com/google.rpc.LocalizedMessage",
+            locale: "en-US",
+            message: "API key not valid. Please pass a valid API key.",
+          },
+        ],
+      },
+    })
+    expect(
+      classifyProviderFailure({ message: "API key not valid. Please pass a valid API key.", status: 400, rawBody })
+        ._tag,
+    ).toBe("Authentication")
+  })
+
  test("classifies overflow signals buried in the raw payload when the summary is vague", () => {
    const reason = classifyProviderFailure({
      message: "Request failed",
@@ -370,3 +476,42 @@ describe("provider error rawBody classification", () => {
    ).toBe("QuotaExceeded")
  })
 })
+
+describe("provider error messages", () => {
+  test("reads messages from common error body layouts", () => {
+    expect(
+      [
+        '{"error":{"message":"Invalid API Key","type":"invalid_request_error"}}',
+        '{"code":"invalid-argument","error":"Incorrect API key provided."}',
+        '{"message":"1 validation error detected"}',
+        '{"Message":"Invalid API Key format: Must start with pre-defined prefix"}',
+        '{"type":"about:blank","title":"Gone","status":410,"detail":"The model has reached its end of life"}',
+        '{"result":null,"success":false,"errors":[{"code":10000,"message":"Authentication error"}]}',
+      ].map(providerErrorMessage),
+    ).toEqual([
+      "Invalid API Key",
+      "Incorrect API key provided.",
+      "1 validation error detected",
+      "Invalid API Key format: Must start with pre-defined prefix",
+      "The model has reached its end of life",
+      "Authentication error",
+    ])
+  })
+
+  test("prefers the nested error message over a top-level message", () => {
+    expect(providerErrorMessage('{"message":"Bad Request","error":{"message":"model not found"}}')).toBe(
+      "model not found",
+    )
+  })
+
+  test("ignores blank, non-string, and non-JSON messages", () => {
+    expect(
+      [
+        '{"error":{"message":"  "}}',
+        '{"message":{"detail":[{"msg":"too high"}]}}',
+        '{"errors":[]}',
+        "invalid parameter",
+      ].map(providerErrorMessage),
+    ).toEqual([undefined, undefined, undefined, undefined])
+  })
+})
@@ -300,7 +300,9 @@ describe("provider package entrypoints", () => {
    })

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

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

@@ -0,0 +1,103 @@
+import { describe, expect } from "bun:test"
+import { Effect } from "effect"
+import { LLM, LLMRequest, Message } from "../../src/index.js"
+import { LLMClient } from "../../src/route.js"
+import { AmazonBedrock } from "../../src/providers.js"
+import { recordedTests } from "../recorded-test.js"
+
+const RECORDING_REGION = process.env.BEDROCK_RECORDING_REGION ?? "us-east-1"
+
+// Claude Opus 5.5 enforces the conversation-prefix check on Bedrock, so a changed system prompt is a real
+// mismatch. Override with BEDROCK_BINDING_MODEL_ID for another model that enforces it.
+const modelID = process.env.BEDROCK_BINDING_MODEL_ID ?? "global.anthropic.claude-opus-5-5"
+
+// Mirrors the "high" variant, so the recording covers the real overlay and default merge.
+const model = (blockBinding?: { readonly prefix_mismatch_behavior: string }) =>
+  AmazonBedrock.model(modelID, {
+    apiKey: process.env.AWS_BEARER_TOKEN_BEDROCK ?? "fixture",
+    region: RECORDING_REGION,
+    body: {
+      additionalModelRequestFields: {
+        thinking: { type: "adaptive", display: "summarized", ...(blockBinding ? { block_binding: blockBinding } : {}) },
+        output_config: { effort: "high" },
+      },
+    },
+  })
+
+const question = "How many positive integers below 5000 have exactly 12 positive divisors? Reply with the number only."
+
+const first = LLM.request({
+  id: "recorded_bedrock_thinking_binding_first",
+  model: model(),
+  system: "You are a concise assistant.",
+  prompt: question,
+  cache: "none",
+  generation: { maxTokens: 12_000 },
+})
+
+const recorded = recordedTests({
+  prefix: "bedrock-converse-thinking-binding",
+  provider: "amazon-bedrock",
+  protocol: "bedrock-converse",
+  requires: ["AWS_BEARER_TOKEN_BEDROCK"],
+})
+
+describe("Bedrock Converse thinking binding recorded", () => {
+  recorded.effect.with("accepts the default binding with no thinking configured", { tags: ["reasoning"] }, () =>
+    Effect.gen(function* () {
+      const response = yield* LLMClient.generate(
+        LLM.request({
+          id: "recorded_bedrock_thinking_binding_default",
+          model: AmazonBedrock.model(modelID, {
+            apiKey: process.env.AWS_BEARER_TOKEN_BEDROCK ?? "fixture",
+            region: RECORDING_REGION,
+          }),
+          system: "Reply with the single word 'Hello'.",
+          prompt: "Say hello.",
+          cache: "none",
+          generation: { maxTokens: 1_024 },
+        }),
+      )
+
+      expect(response.finishReason?.normalized).toBe("stop")
+      expect(response.text).toMatch(/hello/i)
+    }),
+  )
+
+  recorded.effect.with(
+    "keeps a session working after the system prompt changes",
+    { tags: ["reasoning"] },
+    () =>
+      Effect.gen(function* () {
+        const turn = yield* LLMClient.generate(first)
+        // The signed thinking block is what Bedrock binds to the first system prompt.
+        expect(turn.message.content.some((part) => part.type === "reasoning")).toBe(true)
+
+        // Replay the assistant turn under a different system prompt, as a prompt rebuild or compaction would.
+        const next = LLMRequest.update(first, {
+          id: "recorded_bedrock_thinking_binding_next",
+          system: [{ type: "text", text: "You are a concise assistant. Today is Monday." }],
+          messages: [
+            ...first.messages,
+            Message.assistant(turn.message.content),
+            Message.user("Now double it. Reply with the number only."),
+          ],
+        })
+
+        const bound = yield* LLMClient.generate(next)
+        expect(bound.finishReason?.normalized).toBe("stop")
+        expect(bound.text).toMatch(/\d/)
+
+        // The same replay is rejected when the caller asks for the default `error` behavior, proving the check is
+        // enforced and that the default `drop_block` is what let the request above through.
+        const rejected = yield* LLMClient.generate(
+          LLMRequest.update(next, {
+            id: "recorded_bedrock_thinking_binding_error",
+            model: model({ prefix_mismatch_behavior: "error" }),
+          }),
+        ).pipe(Effect.flip)
+        expect(rejected.message).toContain("bound to a different conversation")
+      }),
+    60_000,
+  )
+})
@@ -0,0 +1,100 @@
+import { describe, expect } from "bun:test"
+import { Effect } from "effect"
+import { GenerationOptions, LanguageModel, LLM } from "../../src/index.js"
+import { compileRequest } from "../../src/route/client.js"
+import { AmazonBedrock } from "../../src/providers.js"
+import { it } from "../lib/effect.js"
+
+const binding = { prefix_mismatch_behavior: "drop_block" }
+const beta = ["thinking-binding-controls-2026-08-01"]
+
+const bedrock = (id: string, settings: Parameters<typeof AmazonBedrock.model>[1] = {}) =>
+  AmazonBedrock.model(id, { baseURL: "https://bedrock-runtime.test", apiKey: "test-bearer", ...settings })
+
+const fields = (model: LanguageModel, generation?: GenerationOptions) =>
+  compileRequest(
+    LLM.request({ id: "req_1", model, system: "You are concise.", prompt: "Say hello.", cache: "none", generation }),
+  ).pipe(Effect.map((prepared) => prepared.body.additionalModelRequestFields))
+
+describe("Bedrock Converse thinking block binding", () => {
+  for (const id of [
+    "global.anthropic.claude-fable-5-1",
+    "us.anthropic.claude-fable-5-1-v1:0",
+    "anthropic.claude-fable-5.1",
+    "anthropic.claude-mythos-5-1",
+    "us.anthropic.claude-opus-5-5",
+    "global.anthropic.claude-sonnet-5-5",
+    "anthropic.claude-opus-6",
+  ]) {
+    it.effect(`defaults adaptive thinking to drop_block with the beta for ${id}`, () =>
+      Effect.gen(function* () {
+        expect(yield* fields(bedrock(id))).toEqual({
+          thinking: { type: "adaptive", block_binding: binding },
+          anthropic_beta: beta,
+        })
+      }),
+    )
+  }
+
+  for (const id of [
+    "global.anthropic.claude-opus-5",
+    "us.anthropic.claude-sonnet-5",
+    "global.anthropic.claude-fable-5",
+    "anthropic.claude-fable-5-v1:0",
+    "global.anthropic.claude-opus-4-8",
+    "us.anthropic.claude-opus-4-5-20251101-v1:0",
+    "us.anthropic.claude-haiku-4-5-20251001-v1:0",
+    "anthropic.claude-3-5-sonnet-20241022-v2:0",
+    "us.amazon.nova-2-lite-v1:0",
+  ]) {
+    it.effect(`leaves ${id} untouched`, () =>
+      Effect.gen(function* () {
+        expect(yield* fields(bedrock(id))).toBeUndefined()
+      }),
+    )
+  }
+
+  it.effect("binds a manual thinking budget and keeps top_k", () =>
+    Effect.gen(function* () {
+      expect(
+        yield* fields(
+          bedrock("global.anthropic.claude-fable-5-1", { thinking: { type: "enabled", budgetTokens: 4_000 } }),
+          GenerationOptions.make({ maxTokens: 64_000, topK: 40 }),
+        ),
+      ).toEqual({
+        top_k: 40,
+        thinking: { type: "enabled", budget_tokens: 4_000, block_binding: binding },
+        anthropic_beta: beta,
+      })
+    }),
+  )
+
+  it.effect("does not bind disabled thinking", () =>
+    Effect.gen(function* () {
+      expect(
+        yield* fields(
+          bedrock("global.anthropic.claude-fable-5-1", {
+            body: { additionalModelRequestFields: { thinking: { type: "disabled" } } },
+          }),
+        ),
+      ).toBeUndefined()
+    }),
+  )
+
+  it.effect("honors the compatibility override in both directions", () =>
+    Effect.gen(function* () {
+      const arn = "arn:aws:bedrock:us-east-1:123456789012:application-inference-profile/abc123"
+      expect(yield* fields(bedrock(arn))).toBeUndefined()
+      expect(
+        yield* fields(LanguageModel.update(bedrock(arn), { compatibility: { supportsThinkingBlockBinding: true } })),
+      ).toEqual({ thinking: { type: "adaptive", block_binding: binding }, anthropic_beta: beta })
+      expect(
+        yield* fields(
+          LanguageModel.update(bedrock("global.anthropic.claude-fable-5-1"), {
+            compatibility: { supportsThinkingBlockBinding: false },
+          }),
+        ),
+      ).toBeUndefined()
+    }),
+  )
+})
@@ -1301,11 +1301,11 @@ describe("Bedrock Converse route", () => {
          ),
        ),
      )
-      expect(response.events.filter((event) => event.type === "reasoning-delta" && event.text === "").at(-1)).toEqual({
-        type: "reasoning-delta",
+      expect(response.events.filter((event) => event.type === "reasoning-delta")).toEqual([])
+      expect(response.events.find((event) => event.type === "reasoning-start")).toEqual({
+        type: "reasoning-start",
        id: "reasoning-0",
-        text: "",
-        providerMetadata: { bedrock: { redactedData } },
+        providerMetadata: undefined,
      })
      expect(response.events.find((event) => event.type === "reasoning-end")).toEqual({
        type: "reasoning-end",
@@ -1383,6 +1383,13 @@ describe("Bedrock Converse route", () => {
        ),
      )

+      expect(response.events.filter((event) => event.type === "reasoning-delta")).toEqual([])
+      expect(response.events.find((event) => event.type === "reasoning-end")).toEqual({
+        type: "reasoning-end",
+        id: "reasoning-0",
+        providerMetadata: { bedrock: { redactedData: "AQID" } },
+        text: undefined,
+      })
      expect(response.message.content).toEqual([
        { type: "reasoning", text: "", providerMetadata: { bedrock: { redactedData: "AQID" } } },
      ])
@@ -56,7 +56,9 @@ describe("xAI Responses route", () => {
      expect(XAIResponses.protocol.body).not.toBe(OpenAIResponses.protocol.body)

      const prepared = yield* compileRequest(LLM.request({ model, prompt: "Hello" }))
+      expect(prepared.route).toBe("xai-responses")
      expect(prepared.protocol).toBe("xai-responses")
+      expect(prepared.model.route.providerMetadataKey).toBe("xai")
      expect(prepared.body.store).toBe(false)
      expect(prepared.body.include).toEqual(["reasoning.encrypted_content"])
    }),
@@ -298,3 +300,14 @@ describe("xAI Responses route", () => {
    }),
  )
 })
+
+it.effect("names the xAI Chat route separately from its OpenAI Chat protocol", () =>
+  Effect.gen(function* () {
+    const prepared = yield* compileRequest(
+      LLM.request({ model: XAI.configure({ apiKey: "test" }).chat("grok-4.6"), prompt: "Hello" }),
+    )
+    expect(prepared.route).toBe("xai-chat")
+    expect(prepared.protocol).toBe("openai-chat")
+    expect(prepared.model.route.providerMetadataKey).toBe("xai")
+  }),
+)
@@ -1,6 +1,6 @@
 {
  "name": "@opencode/app",
-  "version": "2.0.18",
+  "version": "2.0.19",
  "description": "",
  "type": "module",
  "exports": {
@@ -1,7 +1,7 @@
 {
  "$schema": "https://json.schemastore.org/package.json",
  "name": "@opencode/cli",
-  "version": "2.0.18",
+  "version": "2.0.19",
  "type": "module",
  "license": "MIT",
  "bin": {
@@ -164,6 +164,7 @@ export async function runNonInteractivePrompt(input: Input) {
      if (!formAlreadySettled(error)) throw error
    }
    formCancelled = true
+    if (input.compatibility !== "v1") process.exitCode = 1
  }

  const consume = async () => {
@@ -309,6 +309,7 @@ async function capture(input: Parameters<typeof run>[0]) {

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

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

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

  test("V1 JSON output flushes step_start before an unrelated step failure", async () => {
@@ -1,7 +1,7 @@
 {
  "$schema": "https://json.schemastore.org/package.json",
  "name": "@opencode/client",
-  "version": "2.0.18",
+  "version": "2.0.19",
  "type": "module",
  "license": "MIT",
  "repository": {
@@ -1,7 +1,7 @@
 {
  "$schema": "https://json.schemastore.org/package.json",
  "name": "@opencode/codemode",
-  "version": "2.0.18",
+  "version": "2.0.19",
  "description": "Effect-native confined code execution over schema-described tools",
  "type": "module",
  "license": "MIT",
@@ -1,6 +1,6 @@
 {
  "name": "@opencode/console-app",
-  "version": "2.0.18",
+  "version": "2.0.19",
  "type": "module",
  "license": "MIT",
  "scripts": {
@@ -1,7 +1,7 @@
 {
  "$schema": "https://json.schemastore.org/package.json",
  "name": "@opencode/console-core",
-  "version": "2.0.18",
+  "version": "2.0.19",
  "private": true,
  "type": "module",
  "license": "MIT",
@@ -1,6 +1,6 @@
 {
  "name": "@opencode/console-function",
-  "version": "2.0.18",
+  "version": "2.0.19",
  "$schema": "https://json.schemastore.org/package.json",
  "private": true,
  "type": "module",
@@ -1,6 +1,6 @@
 {
  "name": "@opencode/console-mail",
-  "version": "2.0.18",
+  "version": "2.0.19",
  "dependencies": {
    "@jsx-email/all": "2.2.3",
    "@jsx-email/cli": "1.4.3",
@@ -1,6 +1,6 @@
 {
  "name": "@opencode/console-support",
-  "version": "2.0.18",
+  "version": "2.0.19",
  "type": "module",
  "license": "MIT",
  "scripts": {
@@ -1,6 +1,6 @@
 {
  "$schema": "https://json.schemastore.org/package.json",
-  "version": "2.0.18",
+  "version": "2.0.19",
  "name": "@opencode/core",
  "type": "module",
  "license": "MIT",
@@ -2,13 +2,12 @@ export * as InstructionBuiltIns from "./builtins.js"

 import { makeLocationNode } from "@opencode/util/effect/app-node"
 import { Context, DateTime, Effect, Layer, Schema } from "effect"
-import type { Session } from "@opencode/schema/session"
 import { Global } from "@opencode/util/global"
 import { Location } from "../location.js"
 import { Instructions } from "./index.js"

 export interface Interface {
-  readonly load: (sessionID: Session.ID) => Effect.Effect<Instructions.List>
+  readonly load: () => Effect.Effect<Instructions.List>
 }

 export class Service extends Context.Service<Service, Interface>()("@opencode/InstructionBuiltIns") {}
@@ -19,16 +18,24 @@ const layer = Layer.effect(
    const global = yield* Global.Service
    const location = yield* Location.Service
    return Service.of({
-      load: (sessionID) =>
+      load: () =>
        Effect.succeed(
          Instructions.combine([
+            Instructions.make({
+              key: Instructions.Key.make("core/date"),
+              codec: Schema.toCodecJson(Schema.String),
+              read: DateTime.nowAsDate.pipe(Effect.map((date) => date.toDateString())),
+              render: {
+                initial: (date) => `Today's date: ${date}`,
+                changed: (_previous, date) => `Today's date is now: ${date}`,
+              },
+            }),
            Instructions.make({
              key: Instructions.Key.make("core/environment"),
              codec: Schema.toCodecJson(Schema.String),
              read: Effect.sync(() =>
                [
                  "<env>",
-                  `  Current conversation session ID: ${sessionID}`,
                  `  Working directory: ${location.directory}`,
                  `  Workspace root folder: ${location.project.directory}`,
                  `  Is directory a git repo: ${location.vcs?.type === "git" ? "yes" : "no"}`,
@@ -44,15 +51,6 @@ const layer = Layer.effect(
                  ["The environment you are running in is now:", environment].join("\n"),
              },
            }),
-            Instructions.make({
-              key: Instructions.Key.make("core/date"),
-              codec: Schema.toCodecJson(Schema.String),
-              read: DateTime.nowAsDate.pipe(Effect.map((date) => date.toDateString())),
-              render: {
-                initial: (date) => `Today's date: ${date}`,
-                changed: (_previous, date) => `Today's date is now: ${date}`,
-              },
-            }),
          ]),
        ),
    })
@@ -1,55 +1,62 @@
 import { Effect } from "effect"
+import { isArrayNonEmpty } from "effect/Array"
 import { define } from "@opencode/plugin/effect/plugin"
 import { Form } from "@opencode/schema/form"
 import { Provider } from "../../provider.js"
-import { iife } from "../../util/iife.js"
 import { configuredSettings } from "./configured.js"

 const providerID = Provider.ID.make("cloudflare-ai-gateway")

+const accountIdField = Form.StringField.make({
+  type: "string",
+  key: "accountId",
+  title: "Enter your Cloudflare Account ID",
+  placeholder: "e.g. 1234567890abcdef1234567890abcdef",
+  required: true,
+})
+
+const gatewayIdField = Form.StringField.make({
+  type: "string",
+  key: "gatewayId",
+  title: "Enter your Cloudflare AI Gateway ID",
+  placeholder: "e.g. my-gateway",
+  required: true,
+})
+
 export const CloudflareAIGatewayPlugin = define({
  id: "opencode.provider.cloudflare.ai.gateway",
  effect: Effect.fn(function* (ctx) {
+    const accountId = process.env.CLOUDFLARE_ACCOUNT_ID
+    const gatewayId = process.env.CLOUDFLARE_GATEWAY_ID
    const configured = yield* configuredSettings(providerID)
-    const form = iife(() => {
-      if (typeof configured?.baseURL === "string") return
-      const accountId = process.env.CLOUDFLARE_ACCOUNT_ID || stringOption(configured ?? {}, "accountId")
-      const gatewayId =
-        process.env.CLOUDFLARE_GATEWAY_ID ||
-        stringOption(configured ?? {}, "gatewayId") ||
-        stringOption(configured ?? {}, "gateway")
-      if (accountId && gatewayId) return
-      const accountIdForm = Form.StringField.make({
-        type: "string",
-        key: "accountId",
-        title: "Enter your Cloudflare Account ID",
-        placeholder: "e.g. 1234567890abcdef1234567890abcdef",
-        required: true,
-      })
-      const gatewayIdForm = Form.StringField.make({
-        type: "string",
-        key: "gatewayId",
-        title: "Enter your Cloudflare AI Gateway ID",
-        placeholder: "e.g. my-gateway",
-        required: true,
-      })
-      if (accountId) return Form.Fields.make([gatewayIdForm])
-      if (gatewayId) return Form.Fields.make([accountIdForm])
-      return Form.Fields.make([accountIdForm, gatewayIdForm])
-    })
+    const fields =
+      typeof configured?.baseURL === "string"
+        ? []
+        : [
+            ...(accountId || typeof configured?.accountId === "string" ? [] : [accountIdField]),
+            ...(gatewayId || typeof configured?.gatewayId === "string" ? [] : [gatewayIdField]),
+          ]
    yield* ctx.integration.transform((editor) => {
      editor.method.update({
        integrationID: providerID,
        method: {
          type: "key",
          label: "Gateway API token",
-          form,
+          form: isArrayNonEmpty(fields) ? Form.Fields.make(fields) : undefined,
        },
      })
    })
+    yield* ctx.provider.transform((evt) => {
+      const item = evt.get(providerID)
+      if (!item || (!accountId && !gatewayId)) return
+      evt.update(item.provider.id, (provider) => {
+        if (typeof provider.settings?.baseURL === "string") return
+        provider.settings = {
+          ...(accountId ? { accountId } : {}),
+          ...(gatewayId ? { gatewayId } : {}),
+          ...provider.settings,
+        }
+      })
+    })
  }),
 })
-
-function stringOption(options: Record<string, unknown>, key: string) {
-  return typeof options[key] === "string" ? options[key] : undefined
-}
@@ -50,7 +50,7 @@ export const CloudflareWorkersAIPlugin = define({
 })

 function resolveAccountId(options: Record<string, unknown>) {
-  return process.env.CLOUDFLARE_ACCOUNT_ID ?? stringOption(options, "accountId")
+  return stringOption(options, "accountId") ?? process.env.CLOUDFLARE_ACCOUNT_ID
 }

 function workersEndpoint(accountId: string) {
@@ -11,6 +11,7 @@ import { Model } from "../../model.js"
 import { Agent } from "../../agent.js"
 import { define } from "@opencode/plugin/effect/plugin"
 import { Provider } from "../../provider.js"
+import { SessionAffinity } from "../../session/affinity.js"
 import type { PluginInternal } from "../internal.js"

 const clientID = "Ov23li8tweQw6odWQebz"
@@ -272,7 +273,7 @@ export const GithubCopilotPlugin = define({
            .pipe(Effect.orElseSucceed(() => undefined))
          const interaction = interactionType(evt.kind, session?.parentID !== undefined)
          evt.headers["X-Interaction-Type"] = interaction
-          evt.headers["X-Interaction-Id"] = evt.sessionID
+          evt.headers["X-Interaction-Id"] = session ? SessionAffinity.get(session) : evt.sessionID
          if (interaction !== "conversation-agent") evt.headers["x-initiator"] = "agent"
        }),
      { providerID: Provider.ID.githubCopilot },
@@ -9,6 +9,7 @@ import { Bus } from "../../bus.js"
 import { Integration } from "../../integration.js"
 import { OauthCallbackPage } from "../../oauth/page.js"
 import { Provider } from "../../provider.js"
+import { SessionAffinity } from "../../session/affinity.js"
 import type { PluginInternal } from "../internal.js"

 const clientID = "app_EMoamEEZ73f0CkXaXp7hrann"
@@ -299,12 +300,16 @@ export const OpenAIPlugin = define({
    yield* ctx.session.hook(
      "model.request",
      (evt) =>
-        Effect.sync(() => {
+        Effect.gen(function* () {
          if (!chatgpt) return
          if (evt.baseURL && URL.canParse(evt.baseURL) && new URL(evt.baseURL).origin === "https://api.openai.com")
            evt.baseURL = codexBaseURL
+          const session = yield* ctx.session
+            .get({ sessionID: evt.sessionID })
+            .pipe(Effect.orElseSucceed(() => undefined))
          evt.headers.originator = "opencode"
-          evt.headers["session-id"] = evt.sessionID
+          // ChatGPT routes its prompt cache on this header, so children share the parent's.
+          evt.headers["session-id"] = session ? SessionAffinity.get(session) : evt.sessionID
        }),
      { providerID: Provider.ID.openai },
    )
@@ -0,0 +1,8 @@
+export * as SessionAffinity from "./affinity.js"
+
+import type { SessionSchema } from "./schema.js"
+
+// TODO: Should the `model.request` hook expose affinity so plugins stop deriving it from `ctx.session.get`?
+/** The Session ID that groups model requests for provider cache routing: children share the parent's, forks the fork source's. */
+export const get = (session: Pick<SessionSchema.Info, "id" | "parentID" | "fork">) =>
+  session.parentID ?? session.fork?.sessionID ?? session.id
@@ -132,7 +132,7 @@ const layer = Layer.effect(
      const loaded = yield* Effect.all(
        {
          tools: registry.snapshot(permissions),
-          builtins: builtins.load(sessionID),
+          builtins: builtins.load(),
          discovery: discovery.load(),
          skills: skillInstructions.load(permissions),
          references: referenceInstructions.load(),
@@ -144,13 +144,16 @@ const layer = Layer.effect(
      return {
        session,
        agent: { ...agent, info: agent.info },
+        // Ordered from most to least shared across sessions so the baseline stays a reusable
+        // prompt-cache prefix: user-level catalog and guidance, then project instructions, then
+        // the date and environment, which vary by day and directory.
        instructions: Instructions.combine([
-          loaded.builtins,
          CodeModeInstructions.make(loaded.tools.codeModeCatalog),
-          loaded.discovery,
-          loaded.skills,
-          loaded.references,
          loaded.mcp,
+          loaded.references,
+          loaded.skills,
+          loaded.discovery,
+          loaded.builtins,
          loaded.entries,
        ]),
        tools: loaded.tools,
@@ -31,6 +31,7 @@ import { Permission } from "../permission.js"
 import { PluginHooks } from "../plugin/hooks.js"
 import { QuestionTool } from "../tool/plugin/question.js"
 import { Tool } from "../tool.js"
+import { SessionAffinity } from "./affinity.js"
 import { SessionModelTransport } from "./model-transport.js"
 import { SessionProviderContext } from "./provider-context.js"
 import { SessionRunnerModel } from "./runner/model.js"
@@ -46,6 +47,8 @@ const IMAGE_REMOVED =
 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
+// No reply needs more, however much the model allows.
+const OUTPUT_TOKEN_MAX = 256_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.
@@ -87,7 +90,7 @@ const outputLimit = (
  kind: "primary" | "compaction",
  inputTokens?: Input["inputTokens"],
 ) => {
-  const model = limit.output > 0 ? limit.output : OUTPUT_TOKEN_FALLBACK
+  const model = Math.min(limit.output > 0 ? limit.output : OUTPUT_TOKEN_FALLBACK, OUTPUT_TOKEN_MAX)
  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))
@@ -268,7 +271,7 @@ export const layer = Layer.effect(
      const entries = Object.entries(shaped.options)
      const generation = Object.fromEntries(entries.filter(([k]) => GENERATION_KEYS.has(k))) as GenerationOptionsFields
      const providerOptions = Object.fromEntries(entries.filter(([k]) => !GENERATION_KEYS.has(k)))
-      const affinity = session.parentID ?? session.fork?.sessionID ?? session.id
+      const affinity = SessionAffinity.get(session)
      const base = LLM.request({
        model: model.model,
        http: {
@@ -207,6 +207,10 @@ export const Plugin = {
                },
                (invocation) =>
                  Effect.gen(function* () {
+                    invocation.env.AGENT = "1"
+                    invocation.env.OPENCODE = "1"
+                    invocation.env.AI_AGENT ||= "opencode"
+                    invocation.env.OPENCODE_SESSION_ID = context.sessionID
                    finalTimeout = yield* prepare(invocation, context)
                  }),
              )
@@ -88,6 +88,11 @@ const responsesEffort = (effort: string): Overlay => ({
  settings: { reasoningEffort: effort, reasoningSummary: "auto", include: ENCRYPTED_REASONING },
 })

+const xaiResponses: Protocol = (_, support) => {
+  if (support.type !== "effort") return []
+  return efforts(support.values ?? EFFORTS, responsesEffort)
+}
+
 const cloudflareAIGateway: Protocol = (model, support) => {
  const id = modelID(model)
  if (id.startsWith("openai/")) return openaiResponses(model, support)
@@ -557,7 +562,7 @@ const PROTOCOLS: Readonly<Record<string, Protocol>> = {
  "@opencode/ai/providers/mistral": openaiChat,
  "@opencode/ai/providers/moonshot/chat": moonshotChat,
  "@opencode/ai/providers/togetherai": openaiChat,
-  "@opencode/ai/providers/xai": openaiChat,
+  "@opencode/ai/providers/xai": xaiResponses,
  "@opencode/ai/providers/zai/chat": zaiChat,
  "@opencode/ai/providers/zai-coding-plan/chat": zaiChat,

@@ -8,7 +8,6 @@ import { FSUtil } from "@opencode/util/fs-util"
 import { Global } from "@opencode/util/global"
 import { AbsolutePath } from "@opencode/core/schema"
 import { InstructionBuiltIns } from "@opencode/core/instructions/builtins"
-import { SessionSchema } from "@opencode/core/session/schema"
 import { location } from "../fixture/location"
 import { testEffect } from "../lib/effect"
 import { readInitial, readUpdate } from "../lib/instructions"
@@ -16,7 +15,6 @@ import { readInitial, readUpdate } from "../lib/instructions"
 const directory = AbsolutePath.make(FSUtil.resolve("/repo/packages/core"))
 const projectDirectory = AbsolutePath.make(FSUtil.resolve("/repo"))
 const timestamp = Date.parse("2026-06-03T12:00:00.000Z")
-const sessionID = SessionSchema.ID.make("ses_builtin_test")
 const temporary = os.tmpdir()
 const localDate = (time: number) => new Date(time).toDateString()
 const locationLayer = Layer.succeed(
@@ -40,21 +38,20 @@ describe("InstructionBuiltIns", () => {
    Effect.gen(function* () {
      yield* TestClock.setTime(timestamp)
      const context = yield* InstructionBuiltIns.Service
-      const initialized = yield* readInitial(yield* context.load(sessionID))
+      const initialized = yield* readInitial(yield* context.load())

      expect(initialized.text).toBe(
        [
+          `Today's date: ${localDate(timestamp)}`,
+          "",
          "Here is some useful information about the environment you are running in:",
          "<env>",
-          `  Current conversation session ID: ${sessionID}`,
          `  Working directory: ${directory}`,
          `  Workspace root folder: ${projectDirectory}`,
          "  Is directory a git repo: yes",
          `  Platform: ${process.platform}`,
          `  Prefer ${temporary} over generic system temporary directories such as /tmp; it is pre-created and approved for external access.`,
          "</env>",
-          "",
-          `Today's date: ${localDate(timestamp)}`,
        ].join("\n"),
      )
    }),
@@ -64,10 +61,10 @@ describe("InstructionBuiltIns", () => {
    Effect.gen(function* () {
      yield* TestClock.setTime(timestamp)
      const context = yield* InstructionBuiltIns.Service
-      const initialized = yield* readInitial(yield* context.load(sessionID))
+      const initialized = yield* readInitial(yield* context.load())

      yield* TestClock.setTime(timestamp + 24 * 60 * 60 * 1000)
-      const refreshed = yield* readUpdate(yield* context.load(sessionID), initialized)
+      const refreshed = yield* readUpdate(yield* context.load(), initialized)

      expect(refreshed.text).toBe(`Today's date is now: ${localDate(timestamp + 24 * 60 * 60 * 1000)}`)
    }),
@@ -77,10 +74,10 @@ describe("InstructionBuiltIns", () => {
    Effect.gen(function* () {
      yield* TestClock.setTime(timestamp)
      const context = yield* InstructionBuiltIns.Service
-      const initialized = yield* readInitial(yield* context.load(sessionID))
+      const initialized = yield* readInitial(yield* context.load())

      yield* TestClock.setTime(timestamp + 60 * 60 * 1000)
-      expect((yield* readUpdate(yield* context.load(sessionID), initialized)).changed).toBe(false)
+      expect((yield* readUpdate(yield* context.load(), initialized)).changed).toBe(false)
    }),
  )
 })
@@ -9,6 +9,7 @@ import { Credential } from "@opencode/core/credential"
 import { Integration } from "@opencode/core/integration"
 import { Compatibility, ID, Info, Model, VariantID } from "@opencode/core/model"
 import { Provider } from "@opencode/core/provider"
+import { Variant } from "@opencode/core/variant"
 import { ModelResolver } from "@opencode/core/model-resolver"
 import { AISDK } from "@opencode/core/aisdk"
 import { Npm } from "@opencode/util/npm"
@@ -580,6 +581,29 @@ describe("ModelResolver", () => {
    }),
  )

+  it.effect("sends xAI Responses effort variants with reasoning summaries", () =>
+    Effect.gen(function* () {
+      const base = model("@opencode/ai/providers/xai", { providerID: Provider.ID.make("xai"), modelID: "grok-4.6" })
+      const catalog = Info.make({
+        ...base,
+        variants: Variant.resolve(base, [{ type: "effort", values: ["low", "high"] }]),
+      })
+      const resolved = yield* ModelResolver.resolveModel(
+        catalog,
+        VariantID.make("high"),
+        Credential.Key.make({ type: "key", key: "secret" }),
+      )
+      const prepared = yield* compileRequest(LLM.request({ model: resolved, prompt: "Hello" }))
+
+      expect(resolved.route.id).toBe("xai-responses")
+      expect(prepared.body).toMatchObject({
+        reasoning: { effort: "high", summary: "auto" },
+        include: ["reasoning.encrypted_content"],
+      })
+      expect(prepared.body).not.toHaveProperty("reasoning_effort")
+    }),
+  )
+
  it.effect("overlays selected OpenAI-compatible variant bodies", () =>
    Effect.gen(function* () {
      const catalog = model(Provider.aisdk("@ai-sdk/openai-compatible"), {
@@ -1282,7 +1306,7 @@ describe("ModelResolver", () => {
        reasoningEffort: "high",
      })
      expect(String(mistral.provider)).toBe("test-provider")
-      expect(xai.route.id).toBe("openai-responses")
+      expect(xai.route.id).toBe("xai-responses")
      expect(xai.route.defaults.providerOptions).toEqual({
        reasoningEffort: "high",
        store: false,
@@ -1059,7 +1059,7 @@ describe("ModelsDevPlugin", () => {
      expect(grok?.variants).toEqual(
        ["low", "medium", "high"].map((id) => ({
          id: Model.VariantID.make(id),
-          settings: { reasoningEffort: id },
+          settings: { reasoningEffort: id, reasoningSummary: "auto", include: ["reasoning.encrypted_content"] },
        })),
      )

@@ -4,11 +4,19 @@ import { Integration } from "@opencode/core/integration"
 import { Plugin } from "@opencode/core/plugin"
 import { PluginHost } from "@opencode/core/plugin/host"
 import { CloudflareAIGatewayPlugin } from "@opencode/core/plugin/provider/cloudflare-ai-gateway"
+import { Provider } from "@opencode/core/provider"
 import { withEnv } from "../fixture/env"
 import { testEffect } from "../lib/effect"
 import { PluginTestLayer } from "./fixture"

 const it = testEffect(PluginTestLayer)
+const providerID = Provider.ID.make("cloudflare-ai-gateway")
+
+const seed = Effect.fn(function* (fn: (provider: Provider.MutableInfo) => void) {
+  const catalog = yield* Provider.Service
+  yield* catalog.transform((catalog) => catalog.update(providerID, fn))
+  return catalog
+})

 const addPlugin = Effect.fn(function* () {
  const plugin = yield* Plugin.Service
@@ -46,4 +54,55 @@ describe("CloudflareAIGatewayPlugin", () => {
      }),
    ),
  )
+
+  it.effect("requests only the gateway ID when the environment provides the account ID", () =>
+    withEnv({ CLOUDFLARE_ACCOUNT_ID: "account", CLOUDFLARE_GATEWAY_ID: undefined }, () =>
+      Effect.gen(function* () {
+        yield* addPlugin()
+        const integrations = yield* Integration.Service
+        expect((yield* integrations.get(Integration.ID.make("cloudflare-ai-gateway")))?.methods).toContainEqual({
+          type: "key",
+          label: "Gateway API token",
+          form: [expect.objectContaining({ type: "string", key: "gatewayId", required: true })],
+        })
+      }),
+    ),
+  )
+
+  it.effect("gives the provider its environment account and gateway IDs", () =>
+    withEnv({ CLOUDFLARE_ACCOUNT_ID: "account", CLOUDFLARE_GATEWAY_ID: "gateway" }, () =>
+      Effect.gen(function* () {
+        const catalog = yield* seed(() => {})
+        yield* addPlugin()
+        expect((yield* catalog.get(providerID))?.settings).toEqual({ accountId: "account", gatewayId: "gateway" })
+      }),
+    ),
+  )
+
+  it.effect("prefers configured IDs over environment IDs", () =>
+    withEnv({ CLOUDFLARE_ACCOUNT_ID: "env-account", CLOUDFLARE_GATEWAY_ID: "env-gateway" }, () =>
+      Effect.gen(function* () {
+        const catalog = yield* seed((provider) => {
+          provider.settings = { accountId: "configured-account", gatewayId: "configured-gateway" }
+        })
+        yield* addPlugin()
+        expect((yield* catalog.get(providerID))?.settings).toEqual({
+          accountId: "configured-account",
+          gatewayId: "configured-gateway",
+        })
+      }),
+    ),
+  )
+
+  it.effect("leaves a configured endpoint URL untouched", () =>
+    withEnv({ CLOUDFLARE_ACCOUNT_ID: "account", CLOUDFLARE_GATEWAY_ID: "gateway" }, () =>
+      Effect.gen(function* () {
+        const catalog = yield* seed((provider) => {
+          provider.settings = { baseURL: "https://proxy.example/v1" }
+        })
+        yield* addPlugin()
+        expect((yield* catalog.get(providerID))?.settings).toEqual({ baseURL: "https://proxy.example/v1" })
+      }),
+    ),
+  )
 })
@@ -119,7 +119,7 @@ describe("CloudflareWorkersAIPlugin", () => {
    ),
  )

-  it.effect("uses env account ID over configured account ID", () =>
+  it.effect("uses configured account ID over env account ID", () =>
    withEnv({ CLOUDFLARE_ACCOUNT_ID: "env-acct" }, () =>
      Effect.gen(function* () {
        const catalog = yield* seed((provider) => {
@@ -129,7 +129,7 @@ describe("CloudflareWorkersAIPlugin", () => {
        yield* addPlugin()
        expect(required(yield* catalog.get(providerID))).toMatchObject({
          package: "aisdk:test-provider",
-          settings: { baseURL: "https://api.cloudflare.com/client/v4/accounts/env-acct/ai/v1" },
+          settings: { baseURL: "https://api.cloudflare.com/client/v4/accounts/configured-acct/ai/v1" },
        })
      }),
    ),
@@ -183,10 +183,11 @@ describe("GithubCopilotPlugin", () => {
  it.effect("classifies child-session steps as subagent interactions", () =>
    Effect.gen(function* () {
      yield* addPlugin()
-      const event = yield* modelRequest((yield* sessions()).child, "primary")
+      const ids = yield* sessions()
+      const event = yield* modelRequest(ids.child, "primary")
      expect(event.headers).toEqual({
        "X-Interaction-Type": "conversation-subagent",
-        "X-Interaction-Id": event.sessionID,
+        "X-Interaction-Id": ids.parent,
        "x-initiator": "agent",
      })
    }),
@@ -207,10 +208,11 @@ describe("GithubCopilotPlugin", () => {
  it.effect("classifies compaction requests by kind rather than agent", () =>
    Effect.gen(function* () {
      yield* addPlugin()
-      const event = yield* modelRequest((yield* sessions()).child, "compaction", "build")
+      const ids = yield* sessions()
+      const event = yield* modelRequest(ids.child, "compaction", "build")
      expect(event.headers).toEqual({
        "X-Interaction-Type": "conversation-compaction",
-        "X-Interaction-Id": event.sessionID,
+        "X-Interaction-Id": ids.parent,
        "x-initiator": "agent",
      })
    }),
@@ -1,6 +1,6 @@
 import { Money } from "@opencode/schema/money"
 import { Agent } from "@opencode/schema/agent"
-import { Session } from "@opencode/schema/session"
+import { Session } from "@opencode/core/session"
 import { OpenAIResponses } from "@opencode/ai/protocols/openai-responses"
 import { describe, expect } from "bun:test"
 import { ConfigProvider, DateTime, Effect } from "effect"
@@ -41,10 +41,14 @@ function required<T>(value: T | undefined): T {
  return value
 }

-const request = Effect.fn(function* (providerID: Provider.ID, baseURL: string) {
+const request = Effect.fn(function* (
+  providerID: Provider.ID,
+  baseURL: string,
+  sessionID = Session.ID.make("ses_test"),
+) {
  const hooks = yield* PluginHooks.Service
  const event = yield* hooks.trigger("session", "model.request", {
-    sessionID: Session.ID.make("ses_test"),
+    sessionID,
    agent: Agent.ID.make("build"),
    model: Model.Ref.make({ providerID, id: Model.ID.make("gpt-5.5") }),
    kind: "primary",
@@ -156,6 +160,12 @@ describe("OpenAIPlugin", () => {
      expect(custom.headers).not.toHaveProperty("originator")
      expect(proxy.baseURL).toBe("https://proxy.example/v1?region=us")
      expect(proxy.headers).toMatchObject({ originator: "opencode", "session-id": "ses_test" })
+      const sessions = yield* Session.Service
+      const location = yield* Location.Service
+      const parent = yield* sessions.create({ location: { directory: location.directory } })
+      const child = yield* sessions.create({ parentID: parent.id })
+      const childRequest = yield* request(Provider.ID.openai, "https://api.openai.com/v1", child.id)
+      expect(childRequest.headers).toMatchObject({ "session-id": parent.id })
      const eligible = required(yield* models.get(Provider.ID.openai, Model.ID.make("gpt-5.5")))
      expect(eligible.package).toBe("@opencode/ai/providers/openai")
      expect(eligible.headers).toMatchObject({ originator: "opencode", "chatgpt-account-id": "acct_123" })
@@ -236,7 +236,7 @@ const setup = Effect.gen(function* () {
    db,
    bus,
    session,
-    instructions: yield* instructionBuiltIns.load(sessionID),
+    instructions: yield* instructionBuiltIns.load(),
    instances: Instance.Service.of({
      // Generation only exercises the Location's model context.
      provide: () =>
@@ -87,7 +87,7 @@ import { permissionLayer } from "./lib/permission"
 import { agentHost, modelHost, host, noProviders } from "./plugin/host"
 import { CodeModeInstructions } from "@opencode/core/codemode/instructions"

-const emptyCodeMode = `\n\n${CodeModeInstructions.render({ total: 0, shown: 0, namespaces: [] })}`
+const emptyCodeMode = `${CodeModeInstructions.render({ total: 0, shown: 0, namespaces: [] })}\n\n`
 type ToolBarrier = {
  readonly count: number
  readonly started: Deferred.Deferred<void>
@@ -128,6 +128,7 @@ const undersizedContextModel = testModel("undersized-context", { context: 1, out
 const recoveryModel = testModel("recovery", { context: 200_000, output: 1_000 })
 const fittedOutputModel = testModel("fitted-output", { context: 100_000, output: 64_000 })
 const smallWindowModel = testModel("small-window", { context: 64_000, output: 16_000 })
+const largeOutputModel = testModel("large-output", { context: 1_000_000, output: 1_000_000 })

 test("calculates step cost using the matching context tier", () => {
  expect(
@@ -1874,8 +1875,8 @@ describe("SessionRunnerLLM", () => {
    yield* s.runPrompt("Second")

    expect(s.requests.map((request) => request.system.map((part) => part.text))).toEqual([
-      [defaultSystem, fakeIdentity, "Initial context\n\nBuild skills"],
-      [defaultSystem, fakeIdentity, "Initial context\n\nBuild skills"],
+      [defaultSystem, fakeIdentity, "Build skills\n\nInitial context"],
+      [defaultSystem, fakeIdentity, "Build skills\n\nInitial context"],
    ])
    expect(systemTexts(s.requests[1])).toContainEqual(expect.stringContaining("Reviewer skills"))
  })
@@ -1897,7 +1898,7 @@ describe("SessionRunnerLLM", () => {
    yield* s.runPrompt("First")

    expect(s.requests.map((request) => request.system.map((part) => part.text))).toEqual([
-      [defaultSystem, fakeIdentity, "Initial context\n\nBuild skills"],
+      [defaultSystem, fakeIdentity, "Build skills\n\nInitial context"],
    ])
  })

@@ -3424,6 +3425,14 @@ describe("SessionRunnerLLM", () => {
    expect(s.requests[1]?.generation?.maxTokens).toBeGreaterThan(100_000 - 50_000 - 200)
  })

+  scenario("caps the output limit a large model advertises", function* (s) {
+    s.currentModel = largeOutputModel
+    yield* s.llm.push(TestLLM.text("Answer", "text-large-output"))
+    yield* s.runPrompt("Question")
+
+    expect(s.requests[0]?.generation?.maxTokens).toBe(256_000)
+  })
+
  scenario("gives the summary its full output limit when the conversation overshot the threshold", function* (s) {
    // The conversation overshot the threshold, so the prepared summary request exceeds the budget and `deliver`
    // shrinks it before sending. The output limit must follow the budget, not the oversized prepared request.
@@ -956,6 +956,59 @@ describe("ShellTool", () => {
    { timeout: 15_000 },
  )

+  productionIt.live(
+    "identifies agent shell commands without inheriting a stale session ID",
+    () =>
+      Effect.acquireUseRelease(
+        Effect.promise(() => tmpdir()),
+        (tmp) => {
+          reset()
+          return withSession(tmp.path, (registry) =>
+            Effect.gen(function* () {
+              const sessions = yield* Session.Service
+              yield* sessions.environment({
+                sessionID,
+                variables: { AGENT: "0", OPENCODE: "0", AI_AGENT: "", OPENCODE_SESSION_ID: "stale" },
+              })
+              const command = isWindows
+                ? '[Console]::Out.Write("$env:AGENT|$env:OPENCODE|$env:AI_AGENT|$env:OPENCODE_SESSION_ID")'
+                : 'printf %s "$AGENT|$OPENCODE|$AI_AGENT|$OPENCODE_SESSION_ID"'
+              const settled = yield* executeTool(registry, call({ command }))
+
+              expect(settled.status).toBe("completed")
+              expect(settled.content?.[0]).toEqual({ type: "text", text: `1|1|opencode|${sessionID}` })
+            }),
+          )
+        },
+        (tmp) => Effect.promise(() => tmp[Symbol.asyncDispose]().then(() => undefined)),
+      ),
+    { timeout: 15_000 },
+  )
+
+  productionIt.live(
+    "preserves an outer AI_AGENT marker in agent shell commands",
+    () =>
+      Effect.acquireUseRelease(
+        Effect.promise(() => tmpdir()),
+        (tmp) => {
+          reset()
+          return withSession(tmp.path, (registry) =>
+            Effect.gen(function* () {
+              const sessions = yield* Session.Service
+              yield* sessions.environment({ sessionID, variables: { AI_AGENT: "outer-agent" } })
+              const command = isWindows ? '[Console]::Out.Write($env:AI_AGENT)' : 'printf %s "$AI_AGENT"'
+              const settled = yield* executeTool(registry, call({ command }))
+
+              expect(settled.status).toBe("completed")
+              expect(settled.content?.[0]).toEqual({ type: "text", text: "outer-agent" })
+            }),
+          )
+        },
+        (tmp) => Effect.promise(() => tmp[Symbol.asyncDispose]().then(() => undefined)),
+      ),
+    { timeout: 15_000 },
+  )
+
  it.live("resolves a relative workdir from the active Location", () =>
    Effect.acquireUseRelease(
      Effect.promise(() => tmpdir()),
@@ -126,6 +126,26 @@ test("spells Cloudflare AI Gateway variants for their upstream routes", () => {
  ])
 })

+test("spells xAI Responses variants with catalog effort levels", () => {
+  const supports: Variant.Support[] = [{ type: "effort", values: ["low", "medium", "high", "xhigh"] }]
+  expect(resolve(model("@opencode/ai/providers/xai", "grok-4.6"), supports)).toEqual(
+    ["low", "medium", "high", "xhigh"].map((effort) => ({
+      id: effort,
+      settings: { reasoningEffort: effort, reasoningSummary: "auto", include: ["reasoning.encrypted_content"] },
+    })),
+  )
+  expect(resolve(model("@opencode/ai/providers/xai", "grok-4.3"), [{ type: "effort", values: ["none", "low"] }])).toEqual([
+    {
+      id: "none",
+      settings: { reasoningEffort: "none", reasoningSummary: "auto", include: ["reasoning.encrypted_content"] },
+    },
+    { id: "low", settings: { reasoningEffort: "low", reasoningSummary: "auto", include: ["reasoning.encrypted_content"] } },
+  ])
+  expect(resolve(model("@opencode/ai/providers/xai", "grok-4.6"), [{ type: "effort" }]).map((item) => item.id)).toEqual([
+    "low", "medium", "high",
+  ])
+})
+
 test("spells Chat Completions variants for direct providers", () => {
  expect(
    resolve(model("@opencode/ai/providers/deepseek", "deepseek-v4-flash"), [
@@ -1,7 +1,7 @@
 {
  "name": "@opencode/desktop",
  "private": true,
-  "version": "2.0.18",
+  "version": "2.0.19",
  "type": "module",
  "license": "MIT",
  "homepage": "https://opencode.ai",
@@ -53,7 +53,7 @@
    "drizzle-kit": "catalog:",
    "drizzle-orm": "catalog:",
    "effect": "catalog:",
-    "electron": "44.4.3",
+    "electron": "44.4.5",
    "electron-builder": "26.15.7",
    "electron-vite": "6.0.0-beta.1",
    "puppeteer-core": "25.9.0",
@@ -44,7 +44,14 @@ const connect = Effect.fn("BackgroundService.connect")(function* (mode: "initial
          ? path.join(app.getPath("userData"), "opencode", "service-local.json")
          : undefined,
      version,
-      command: [...cli.command, "serve", "--service", ...(isolated ? ["--hostname", "0.0.0.0", "--port", "0"] : [])],
+      // A fixed port makes a second contender fail to bind and back off; port 0 never collides, so two
+      // services could boot against the same database.
+      command: [
+        ...cli.command,
+        "serve",
+        "--service",
+        ...(isolated ? ["--hostname", "0.0.0.0", "--port", String(0x0c0c)] : []),
+      ],
      onStart: (reason, previousVersion) =>
        runFork(Effect.logInfo("v2 CLI background service starting", { reason, previousVersion })),
    })
@@ -1,6 +1,6 @@
 {
  "name": "@opencode/enterprise",
-  "version": "2.0.18",
+  "version": "2.0.19",
  "private": true,
  "type": "module",
  "license": "MIT",
@@ -1,6 +1,6 @@
 {
  "name": "@opencode/function",
-  "version": "2.0.18",
+  "version": "2.0.19",
  "$schema": "https://json.schemastore.org/package.json",
  "private": true,
  "type": "module",
@@ -1,6 +1,6 @@
 {
  "$schema": "https://json.schemastore.org/package.json",
-  "version": "2.0.18",
+  "version": "2.0.19",
  "name": "@opencode/http-recorder",
  "description": "Record and replay Effect HTTP and WebSocket traffic with deterministic cassettes",
  "type": "module",
@@ -1,7 +1,7 @@
 {
  "$schema": "https://json.schemastore.org/package.json",
  "name": "@opencode/httpapi-codegen",
-  "version": "2.0.18",
+  "version": "2.0.19",
  "private": true,
  "type": "module",
  "exports": {
@@ -1,7 +1,7 @@
 {
  "$schema": "https://json.schemastore.org/package.json",
  "name": "@opencode/latex",
-  "version": "2.0.18",
+  "version": "2.0.19",
  "private": true,
  "type": "module",
  "exports": {
@@ -1,7 +1,7 @@
 {
  "$schema": "https://json.schemastore.org/package.json",
  "name": "@opencode/merman",
-  "version": "2.0.18",
+  "version": "2.0.19",
  "private": true,
  "type": "module",
  "exports": {
@@ -1,7 +1,7 @@
 {
  "$schema": "https://json.schemastore.org/package.json",
  "name": "@opencode/plugin-browser",
-  "version": "2.0.18",
+  "version": "2.0.19",
  "description": "OpenCode's desktop browser plugin",
  "type": "module",
  "license": "MIT",
@@ -1,7 +1,7 @@
 {
  "$schema": "https://json.schemastore.org/package.json",
  "name": "@opencode/plugin",
-  "version": "2.0.18",
+  "version": "2.0.19",
  "type": "module",
  "license": "MIT",
  "scripts": {
@@ -1,7 +1,7 @@
 {
  "$schema": "https://json.schemastore.org/package.json",
  "name": "@opencode/protocol",
-  "version": "2.0.18",
+  "version": "2.0.19",
  "type": "module",
  "license": "MIT",
  "repository": {
@@ -1,7 +1,7 @@
 {
  "$schema": "https://json.schemastore.org/package.json",
  "name": "@opencode/schema",
-  "version": "2.0.18",
+  "version": "2.0.19",
  "type": "module",
  "license": "MIT",
  "repository": {
@@ -1,6 +1,6 @@
 {
  "$schema": "https://json.schemastore.org/package.json",
-  "version": "2.0.18",
+  "version": "2.0.19",
  "name": "@opencode/sdk",
  "type": "module",
  "license": "MIT",
@@ -1,7 +1,7 @@
 {
  "$schema": "https://json.schemastore.org/package.json",
  "name": "@opencode/server",
-  "version": "2.0.18",
+  "version": "2.0.19",
  "type": "module",
  "license": "MIT",
  "repository": {
@@ -13,10 +13,7 @@ for (const split of [false, true]) {
      await expect(additions).toHaveText(["select-text"])
      await expect(root.locator('[data-line-type="context"] [data-diff-span]')).toHaveCount(0)
      await expect(root.locator('[data-line-type="change-deletion"] [data-diff-span]')).toHaveText([
-        '"http" in',
-        "? error.reason.",
-        "response?.",
-        ": undefined",
+        '"http" in error.reason ? error.reason.http?.response?.headers["x-should-retry"] : undefined',
      ])
      await expect(additions).not.toHaveCSS("background-color", "rgba(0, 0, 0, 0)")
    })
@@ -27,8 +24,7 @@ for (const split of [false, true]) {
      const root = await mount("components-session-review--large-file", { args: { split, source } })
      const line = root.locator('[data-line][data-line-type="change-addition"]')
      await expect(line).toHaveText("export const value = 'after'")
-      // Plain first paint is not proof that the worker kept inline diffs disabled.
-      await expect(line.locator('[style*="--syntax-"]')).not.toHaveCount(0)
+      await expect(line.locator('[style*="--syntax-"]')).toHaveCount(0)
      await expect(root.locator("[data-diff-span]")).toHaveCount(0)
    })
  }
@@ -1,7 +1,7 @@
 import { expect, story } from "../../storybook/playwright/story"

 // Moved from packages/app/e2e/regression/session-timeline-notices.spec.ts
-story("renders the moved location notice in its compact timeline style", async ({ mount, page }) => {
+story("renders the moved location notice as a timeline divider", async ({ mount, page }) => {
  const directory = `/Users/usrnk1/Developer/opencode/${"nested-directory/".repeat(24)}session`
  await page.setViewportSize({ width: 480, height: 720 })
  const timeline = await mount("current-session-timeline-rows--conversation", { args: { scenario: "location" } })
@@ -14,12 +14,10 @@ story("renders the moved location notice in its compact timeline style", async (
  await expect(value).toHaveText(directory)
  await expect(notice).not.toContainText("·")
  await expect(notice.locator("svg")).toHaveCount(0)
-  await expect(notice).toHaveCSS("height", "28px")
-  await expect(notice).toHaveCSS("gap", "8px")
-  await expect(notice).toHaveCSS("padding-top", "4px")
-  await expect(notice).toHaveCSS("padding-bottom", "4px")
+  await expect(notice).toHaveCSS("padding-top", "8px")
+  await expect(notice).toHaveCSS("padding-bottom", "8px")
  await expect(label).toHaveCSS("font-size", "13px")
-  await expect(label).toHaveCSS("font-weight", "530")
+  await expect(label).toHaveCSS("font-weight", "440")
  await expect(label).toHaveCSS("line-height", "16px")
  await expect(label).toHaveCSS("color", "rgb(128, 128, 128)")
  await expect(value).toHaveCSS("font-size", "13px")
@@ -1,6 +1,6 @@
 {
  "name": "@opencode/session-ui",
-  "version": "2.0.18",
+  "version": "2.0.19",
  "private": true,
  "type": "module",
  "license": "MIT",
@@ -13,7 +13,7 @@ test("renders large diffs as plain text without changing ordinary highlighting",
  await page.goto("/")
  await page.waitForFunction(() => !!window.highlighting)
  const ordinary = await page.evaluate(() => window.highlighting.mount(1))
-  expect(ordinary.options).toMatchObject({ lineDiffType: "word-alt", maxLineDiffLength: 1000, tokenizeMaxLineLength: 1000 })
+  expect(ordinary.options).toMatchObject({ lineDiffType: "word-line", maxLineDiffLength: 1000, tokenizeMaxLineLength: 1000 })
  expect(ordinary.syntaxSpans).toBeGreaterThan(0)
  await expect(page.locator('[data-line="11"][data-line-type="change-addition"]')).toContainText("status: 201")
 })
@@ -80,7 +80,7 @@ async function mount(revision: number) {
  const offset = messages.length
  const start = performance.now()
  active = normalize({ ...input, additions: large ? 120 : 12, deletions: large ? 120 : 12 })
-  const pool = getWorkerPool(large ? "none" : "word-alt")!
+  const pool = getWorkerPool(large ? "none" : "word-line")!
  let firstReady = 0
  let rendered = 0
  let finish!: (value: Measurement) => void
@@ -128,7 +128,7 @@ async function mount(revision: number) {

 export const highlighting = {
  mount,
-  configure(options: Partial<WorkerRenderingOptions>) { return getWorkerPool(large ? "none" : "word-alt")!.setRenderOptions(options) },
+  configure(options: Partial<WorkerRenderingOptions>) { return getWorkerPool(large ? "none" : "word-line")!.setRenderOptions(options) },
  unmount() { dispose?.(); dispose = undefined; host.scrollTop = 0 },
  contents() { return active && { before: text(active, "deletions"), after: text(active, "additions") } },
  input: { before, after: inputs.map((input) => input.after) },
@@ -16,7 +16,7 @@ import {
 import { acquireVirtualizer, virtualMetrics } from "../pierre/virtualizer"
 import { File, type DiffFileProps, type FileProps } from "./file"

-type DiffPreload<T> = PreloadMultiFileDiffResult<T> | PreloadFileDiffResult<T>
+type DiffPreload<T> = PreloadMultiFileDiffResult<T, undefined> | PreloadFileDiffResult<T, undefined>

 type SSRDiffFileProps<T> = DiffFileProps<T> & {
  preloadedDiff: DiffPreload<T>
@@ -119,7 +119,7 @@ function DiffSSRViewer<T>(props: SSRDiffFileProps<T>) {
    // @ts-expect-error private field required for hydration
    fileDiffInstance.fileContainer = fileDiffRef
    fileDiffInstance.hydrate(
-      local.fileDiff
+      local.fileDiff || !local.before || !local.after
        ? {
            fileDiff: local.fileDiff,
            lineAnnotations: annotations,
@@ -128,12 +128,11 @@ function DiffSSRViewer<T>(props: SSRDiffFileProps<T>) {
            prerenderedHTML: local.preloadedDiff.prerenderedHTML,
          }
        : {
-            oldFile: local.before
-              ? { ...local.before, contents: typeof local.before.contents === "string" ? local.before.contents : "" }
-              : local.before,
-            newFile: local.after
-              ? { ...local.after, contents: typeof local.after.contents === "string" ? local.after.contents : "" }
-              : local.after,
+            oldFile: {
+              ...local.before,
+              contents: typeof local.before.contents === "string" ? local.before.contents : "",
+            },
+            newFile: { ...local.after, contents: typeof local.after.contents === "string" ? local.after.contents : "" },
            lineAnnotations: annotations,
            fileContainer: fileDiffRef,
            containerWrapper: container,
@@ -75,17 +75,17 @@ export type FileSearchControl = {
  register: (handle: FileSearchHandle | null) => void
 }

-export type TextFileProps<T = {}> = FileOptions<T> &
+export type TextFileProps<T = {}> = FileOptions<T, undefined> &
  SharedProps<T> & {
    mode: "text"
    file: FileContents
    annotations?: LineAnnotation<T>[]
-    preloadedDiff?: PreloadMultiFileDiffResult<T>
+    preloadedDiff?: PreloadMultiFileDiffResult<T, undefined>
  }

-type DiffPreload<T> = PreloadMultiFileDiffResult<T> | PreloadFileDiffResult<T>
+type DiffPreload<T> = PreloadMultiFileDiffResult<T, undefined> | PreloadFileDiffResult<T, undefined>

-type DiffBaseProps<T> = FileDiffOptions<T> &
+type DiffBaseProps<T> = FileDiffOptions<T, undefined> &
  SharedProps<T> & {
    mode: "diff"
    annotations?: DiffLineAnnotation<T>[]
@@ -957,7 +957,7 @@ function DiffViewer<T>(props: DiffFileProps<T>) {
  let instance: FileDiff<T> | undefined
  let instanceVirtualizer: Virtualizer | undefined
  let instanceWorkerPool: ReturnType<typeof getWorkerPool>
-  let instanceVirtualHunkSeparators: FileDiffOptions<T>["hunkSeparators"] | undefined
+  let instanceVirtualHunkSeparators: FileDiffOptions<T, undefined>["hunkSeparators"] | undefined
  let instanceFileDiff: FileDiffMetadata | undefined
  let instanceBefore: FileContents | undefined
  let instanceAfter: FileContents | undefined
@@ -1066,7 +1066,7 @@ function DiffViewer<T>(props: DiffFileProps<T>) {
    lineDiffType: "none",
    maxLineDiffLength: 0,
    tokenizeMaxLineLength: 1,
-  } satisfies Pick<FileDiffOptions<T>, "lineDiffType" | "maxLineDiffLength" | "tokenizeMaxLineLength">
+  } satisfies Pick<FileDiffOptions<T, undefined>, "lineDiffType" | "maxLineDiffLength" | "tokenizeMaxLineLength">

  const lineCallbacks = createLineCallbacks({
    viewer,
@@ -1076,7 +1076,7 @@ function DiffViewer<T>(props: DiffFileProps<T>) {
    onLineNumberSelectionEnd: (range) => local.onLineNumberSelectionEnd?.(range),
  })

-  const options = createMemo<FileDiffOptions<T>>(() => {
+  const options = createMemo<FileDiffOptions<T, undefined>>(() => {
    const base = {
      ...createDefaultOptions(props.diffStyle),
      ...others,
@@ -1112,7 +1112,7 @@ function DiffViewer<T>(props: DiffFileProps<T>) {
  createEffect(() => {
    const opts = options()
    // Worker render options override per-viewer options, including the large-file fallback.
-    const workerPool = getWorkerPool(large() ? "none" : "word-alt")
+    const workerPool = getWorkerPool(large() ? "none" : "word-line")
    const virtualizer = virtuals.get()
    const beforeContents = typeof local.before?.contents === "string" ? local.before.contents : ""
    const afterContents = typeof local.after?.contents === "string" ? local.after.contents : ""
@@ -64,12 +64,12 @@ export type SessionReviewCommentActions = {
 export type SessionReviewFocus = { file: string; id: string }

 type RawReviewDiff = (PresentationFileDiff | FileDiffInfo) & {
-  preloaded?: PreloadMultiFileDiffResult<unknown>
+  preloaded?: PreloadMultiFileDiffResult<unknown, undefined>
 }
 type ReviewDiff = ((PresentationFileDiff & { file: string }) | FileDiffInfo) & {
-  preloaded?: PreloadMultiFileDiffResult<unknown>
+  preloaded?: PreloadMultiFileDiffResult<unknown, undefined>
 }
-type Item = ViewDiff & { preloaded?: PreloadMultiFileDiffResult<unknown> }
+type Item = ViewDiff & { preloaded?: PreloadMultiFileDiffResult<unknown, undefined> }

 function diff(value: unknown): value is ReviewDiff {
  if (!value || typeof value !== "object" || Array.isArray(value)) return false
@@ -1,7 +1,25 @@
 import { ProviderIcon } from "@opencode/ui/provider-icon"
+import { Tooltip } from "@opencode/ui/tooltip"
 import { Show } from "solid-js"

-export function TimelineSeparator(props: { label: string; providerID?: string; variant?: string }) {
+export function TimelineSeparator(props: {
+  label: string
+  value?: string
+  tooltip?: string
+  providerID?: string
+  variant?: string
+}) {
+  const label = () => (
+    <bdi
+      data-slot="session-timeline-notice-label"
+      dir="auto"
+      class="block truncate"
+      classList={{ "shrink-0": !!props.value }}
+      title={props.tooltip ? undefined : props.label}
+    >
+      {props.label}
+    </bdi>
+  )
  return (
    <div class="flex h-8 w-full items-center gap-3 text-v2-text-text-faint">
      <span class="h-px min-w-0 flex-1 bg-v2-border-border-strong" />
@@ -10,9 +28,26 @@ export function TimelineSeparator(props: { label: string; providerID?: string; v
          {(providerID) => <ProviderIcon id={providerID()} class="text-v2-icon-icon-faint" aria-hidden="true" />}
        </Show>
        <span class="flex min-w-0 items-center gap-1.5">
-          <bdi dir="auto" class="truncate" title={props.label}>
-            {props.label}
-          </bdi>
+          <Show when={props.tooltip} fallback={label()}>
+            {(tooltip) => (
+              <Tooltip
+                appearance="compact"
+                placement="top"
+                value={tooltip()}
+                class={props.value ? "min-w-0 shrink-0" : "min-w-0"}
+                triggerTabIndex={0}
+              >
+                {label()}
+              </Tooltip>
+            )}
+          </Show>
+          <Show when={props.value}>
+            {(value) => (
+              <bdi data-slot="session-timeline-notice-value" dir="ltr" class="min-w-0 truncate" title={value()}>
+                {value()}
+              </bdi>
+            )}
+          </Show>
          <Show when={props.variant && props.variant !== "default" ? props.variant : undefined}>
            {(variant) => (
              <>
@@ -32,7 +32,7 @@ type Data = {
    [sessionID: string]: FileDiffInfo[]
  }
  session_diff_preload?: {
-    [sessionID: string]: PreloadMultiFileDiffResult<unknown>[]
+    [sessionID: string]: PreloadMultiFileDiffResult<unknown, undefined>[]
  }
 }

@@ -2,7 +2,7 @@ import { DiffLineAnnotation, FileContents, FileDiffOptions, type SelectedLineRan
 import { ComponentProps } from "solid-js"
 import { lineCommentStyles } from "../components/line-comment-styles"

-export type DiffProps<T = {}> = FileDiffOptions<T> & {
+export type DiffProps<T = {}> = FileDiffOptions<T, undefined> & {
  before: FileContents
  after: FileContents
  annotations?: DiffLineAnnotation<T>[]
@@ -17,6 +17,11 @@ export type DiffProps<T = {}> = FileDiffOptions<T> & {
 const unsafeCSS = `
 :host {
  --diffs-bg: var(--opencode-diffs-bg, var(--color-background-stronger));
+  /* Pierre mixes 15% in dark mode, which makes collapsed rows read as highlighted. */
+  --diffs-bg-separator-override: light-dark(
+    color-mix(in lab, var(--diffs-bg) 98%, var(--diffs-mixer)),
+    color-mix(in lab, var(--diffs-bg) 95%, var(--diffs-mixer))
+  );
 }

 [data-diff],
@@ -138,15 +143,15 @@ const unsafeCSS = `
 }

@media (max-width: 767px) {
-  /* File annotations share the code column; reclaim the measured number gutter. */
-  [data-file] [data-line-annotation] {
-    margin-inline-start: calc(-1 * var(--diffs-column-number-width, 0px));
-    z-index: 4;
+  /* File annotations share the code column; reclaim the number gutter. Pierre only measures column widths for
+     scrolling files with annotations, so derive the gutter from the code grid width instead. */
+  [data-file][data-overflow='wrap'] [data-code] {
+    container-type: inline-size;
  }

-  [data-file] [data-annotation-content] {
-    width: var(--diffs-column-width, auto);
-    inset-inline-start: 0;
+  [data-file][data-overflow='wrap'] [data-line-annotation] {
+    margin-inline-start: calc(100% - 100cqi);
+    z-index: 4;
  }
 }

@@ -198,7 +203,7 @@ ${lineCommentStyles}

 `

-export function createDefaultOptions<T>(style: FileDiffOptions<T>["diffStyle"]) {
+export function createDefaultOptions<T>(style: FileDiffOptions<T, undefined>["diffStyle"]) {
  return {
    theme: "OpenCode",
    themeType: "system",
@@ -210,7 +215,7 @@ export function createDefaultOptions<T>(style: FileDiffOptions<T>["diffStyle"])
    disableBackground: false,
    expansionLineCount: 20,
    hunkSeparators: "line-info-basic",
-    lineDiffType: "word-alt",
+    lineDiffType: "word-line",
    maxLineDiffLength: 1000,
    maxLineLengthForHighlighting: 1000,
    disableFileHeader: true,
@@ -8,7 +8,7 @@ export function workerFactory(): Worker {
  return new Worker(ShikiWorkerUrl, { type: "module" })
 }

-function createPool(lineDiffType: "none" | "word-alt") {
+function createPool(lineDiffType: "none" | "word-line") {
  const pool = new WorkerPoolManager(
    {
      workerFactory,
@@ -36,7 +36,7 @@ function createPool(lineDiffType: "none" | "word-alt") {
 let plain: WorkerPoolManager | undefined
 let diff: WorkerPoolManager | undefined

-export function getWorkerPool(lineDiffType: "none" | "word-alt" = "word-alt"): WorkerPoolManager | undefined {
+export function getWorkerPool(lineDiffType: "none" | "word-line" = "word-line"): WorkerPoolManager | undefined {
  if (typeof window === "undefined") return

  if (lineDiffType === "none") {
@@ -44,7 +44,7 @@ export function getWorkerPool(lineDiffType: "none" | "word-alt" = "word-alt"): W
    return plain
  }

-  if (!diff) diff = createPool("word-alt")
+  if (!diff) diff = createPool("word-line")
  return diff
 }

@@ -271,7 +271,12 @@ export namespace Timeline {
            detail,
            new Set(
              messages
-                .filter((message) => message.type === "compaction" || message.type === "model-switched")
+                .filter(
+                  (message) =>
+                    message.type === "compaction" ||
+                    message.type === "model-switched" ||
+                    message.type === "location-switched",
+                )
                .map((message) => message.id),
            ),
          )
@@ -5,6 +5,7 @@ import type {
  SessionMessageInfo,
 } from "@opencode/client/promise"
 import { storyDocument, storyTool } from "../storybook/current-session-scenarios"
+import { timelinePresets } from "./detail"
 import { createTimelineProjection, Timeline, TimelineRow } from "./projection"

 describe("current session timeline rows", () => {
@@ -333,6 +334,39 @@ describe("current session timeline rows", () => {
    ])
  })

+  test("keeps divider notices outside grouped context rows", () => {
+    const source = [
+      { id: "msg_user", type: "user", text: "move", time: { created: 1 } },
+      {
+        id: "msg_assistant",
+        type: "assistant",
+        agent: "build",
+        model: { id: "model", providerID: "provider" },
+        content: [storyTool("tool_read", "read", "completed", {})],
+        time: { created: 2, completed: 3 },
+      },
+      { id: "msg_moved", type: "location-switched", location: { directory: "/tmp/next" }, time: { created: 4 } },
+      { id: "msg_skill", type: "skill", skill: "review", name: "Review", text: "instructions", time: { created: 5 } },
+    ] satisfies SessionMessageInfo[]
+    const rows = Timeline.constructSessionMessageRows(
+      source,
+      false,
+      { type: "idle" },
+      undefined,
+      false,
+      false,
+      undefined,
+      timelinePresets.find((preset) => preset.id === "compact")!.value,
+    ).rows
+
+    expect(rows.map(TimelineRow.key)).toEqual([
+      "user-message:msg_user",
+      "assistant-part:context:context:msg_assistant:tool_read",
+      "notice:msg_moved",
+      "assistant-part:context:message:msg_skill",
+    ])
+  })
+
  test("keeps assistant errors and retries before later notices", () => {
    const result = Timeline.constructSessionMessageRows(
      [
@@ -5,7 +5,6 @@ import type {
  SessionStatus,
 } from "@opencode/client/promise"
 import { useI18n } from "@opencode/ui/context/i18n"
-import { Tooltip } from "@opencode/ui/tooltip"
 import { For, Show, createMemo, type Accessor, type JSX } from "solid-js"
 import { Dynamic } from "solid-js/web"
 import type { SessionUserActions, SessionUserAttachmentReference, SessionUserComment } from "../actions"
@@ -522,25 +521,12 @@ export function createSessionTimelineRowRenderer(input: {
          }
        >
          {(message) => (
-            <div
-              data-slot="session-timeline-notice"
-              data-type="location-switched"
-              class={`flex h-7 w-full min-w-0 items-center gap-2 py-1 text-[13px] leading-text-compact tracking-[-0.04px] text-v2-text-text-faint ${inset()}`}
-            >
-              <Tooltip
-                appearance="compact"
-                placement="top"
-                value={i18n.t("ui.sessionTimeline.notice.movedTooltip")}
-                class="shrink-0"
-                triggerTabIndex={0}
-              >
-                <bdi data-slot="session-timeline-notice-label" dir="auto" class="font-[530]">
-                  {i18n.t("ui.sessionTimeline.notice.movedTo")}
-                </bdi>
-              </Tooltip>{" "}
-              <bdi data-slot="session-timeline-notice-value" dir="ltr" class="min-w-0 truncate font-[440]">
-                {message().location.directory}
-              </bdi>
+            <div data-slot="session-timeline-notice" data-type="location-switched" class={`w-full py-2 ${inset()}`}>
+              <TimelineSeparator
+                label={i18n.t("ui.sessionTimeline.notice.movedTo")}
+                value={message().location.directory}
+                tooltip={i18n.t("ui.sessionTimeline.notice.movedTooltip")}
+              />
            </div>
          )}
        </Show>
@@ -455,7 +455,7 @@ const MovedLocation = {
  render: () => (
    <CurrentSessionTimelineStory
      title="Moved Session location"
-      description="A changed working directory stays compact, truncates, and exposes its tooltip."
+      description="A changed working directory renders as a timeline divider, truncates, and exposes its tooltip."
      document={{
        ...thinkingDocument,
        status: { type: "idle" },
@@ -1,7 +1,7 @@
 {
  "$schema": "https://json.schemastore.org/package.json",
  "name": "@opencode/simulation",
-  "version": "2.0.18",
+  "version": "2.0.19",
  "type": "module",
  "license": "MIT",
  "repository": {
@@ -1,7 +1,7 @@
 {
  "$schema": "https://json.schemastore.org/package.json",
  "name": "@opencode/stats-app",
-  "version": "2.0.18",
+  "version": "2.0.19",
  "private": true,
  "type": "module",
  "license": "MIT",
@@ -1,7 +1,7 @@
 {
  "$schema": "https://json.schemastore.org/package.json",
  "name": "@opencode/stats-core",
-  "version": "2.0.18",
+  "version": "2.0.19",
  "private": true,
  "type": "module",
  "license": "MIT",
@@ -1,7 +1,7 @@
 {
  "$schema": "https://json.schemastore.org/package.json",
  "name": "@opencode/stats-server",
-  "version": "2.0.18",
+  "version": "2.0.19",
  "private": true,
  "type": "module",
  "license": "MIT",
@@ -1,7 +1,7 @@
 {
  "$schema": "https://json.schemastore.org/package.json",
  "name": "@opencode/theme",
-  "version": "2.0.18",
+  "version": "2.0.19",
  "type": "module",
  "license": "MIT",
  "repository": {
@@ -1,7 +1,7 @@
 {
  "$schema": "https://json.schemastore.org/package.json",
  "name": "@opencode/tui",
-  "version": "2.0.18",
+  "version": "2.0.19",
  "private": true,
  "type": "module",
  "license": "MIT",
@@ -1,6 +1,6 @@
 {
  "name": "@opencode/ui",
-  "version": "2.0.18",
+  "version": "2.0.19",
  "type": "module",
  "license": "MIT",
  "repository": {
@@ -1,7 +1,7 @@
 {
  "$schema": "https://json.schemastore.org/package.json",
  "name": "@opencode/util",
-  "version": "2.0.18",
+  "version": "2.0.19",
  "type": "module",
  "license": "MIT",
  "repository": {
@@ -2,7 +2,7 @@
  "name": "@opencode/web",
  "type": "module",
  "license": "MIT",
-  "version": "2.0.18",
+  "version": "2.0.19",
  "scripts": {
    "dev": "astro dev",
    "dev:remote": "VITE_API_URL=https://api.opencode.ai astro dev",
@@ -283,6 +283,7 @@ https://opencode.ai/zen/v1/models
 - Nemotron 3 Ultra Free (نقاط نهاية NVIDIA المجانية): للاستخدام التجريبي فقط — لا ترسل بيانات شخصية أو سرية. يُسجَّل استخدامك لأغراض أمنية ولتحسين منتجات وخدمات NVIDIA. بيانات الجلسة المُسجَّلة لأغراض التحسين غير مرتبطة بهويتك أو بأي مُعرِّف دائم. لمزيد من المعلومات حول ممارسات معالجة البيانات لدينا، راجع [سياسة الخصوصية](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf). بتفاعلك مع نقطة النهاية هذه، فإنك توافق على جمعنا لهذه المعلومات وتسجيلها واستخدامها وعلى [شروط خدمة النسخة التجريبية من واجهة NVIDIA API](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf).
 - OpenAI APIs: يتم الاحتفاظ بالطلبات لمدة 30 يوما وفقا لـ [OpenAI's Data Policies](https://platform.openai.com/docs/guides/your-data).
 - Anthropic APIs: يتم الاحتفاظ بالطلبات لمدة 30 يوما وفقا لـ [Anthropic's Data Policies](https://docs.anthropic.com/en/docs/claude-code/data-usage).
+- Jev APIs: لا تُستخدم المطالبات والمدخلات الأخرى في التدريب. يُحتفظ بالبيانات وفقًا لـ [سياسة الخصوصية الخاصة بـ TypeSafe AI](https://typesafe.ai/legal/privacy-policy).

 ---

@@ -295,6 +295,7 @@ i ne koriste vaše podatke za treniranje modela, uz sljedeće izuzetke:
 - Nemotron 3 Ultra Free (besplatni NVIDIA endpointi): Samo za probnu upotrebu — nemojte slati lične ili povjerljive podatke. Vaše korištenje se bilježi radi sigurnosti i poboljšanja NVIDIA proizvoda i usluga. Zabilježeni podaci sesije koji se koriste u svrhu poboljšanja nisu povezani s vašim identitetom niti bilo kojim trajnim identifikatorom. Za više informacija o našim praksama obrade podataka pogledajte našu [Politiku privatnosti](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf). Interakcijom s ovim endpointom pristajete na naše prikupljanje, bilježenje i korištenje takvih informacija te na [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf).
 - OpenAI APIs: Requests are retained for 30 days in accordance with [OpenAI's Data Policies](https://platform.openai.com/docs/guides/your-data).
 - Anthropic APIs: Requests are retained for 30 days in accordance with [Anthropic's Data Policies](https://docs.anthropic.com/en/docs/claude-code/data-usage).
+- Jev APIs: Promptovi i drugi ulazni podaci ne koriste se za treniranje modela. Podaci se čuvaju u skladu s [Politikom privatnosti TypeSafe AI](https://typesafe.ai/legal/privacy-policy).

 ---

@@ -293,6 +293,7 @@ Alle vores modeller hostes i US. Vores udbydere følger en nul-opbevaringspoliti
 - Nemotron 3 Ultra Free (gratis NVIDIA-endpoints): Kun til prøvebrug — indsend ikke personlige eller fortrolige data. Din brug logges af sikkerhedshensyn og for at forbedre NVIDIAs produkter og tjenester. De loggede sessionsdata, der bruges til forbedringsformål, er ikke knyttet til din identitet eller nogen vedvarende identifikator. For mere information om vores databehandlingspraksis, se vores [privatlivspolitik](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf). Ved at interagere med dette endpoint giver du samtykke til vores indsamling, registrering og brug af sådanne oplysninger samt [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf).
 - OpenAI APIs: Anmodninger opbevares i 30 dage i overensstemmelse med [OpenAI's Data Policies](https://platform.openai.com/docs/guides/your-data).
 - Anthropic APIs: Anmodninger opbevares i 30 dage i overensstemmelse med [Anthropic's Data Policies](https://docs.anthropic.com/en/docs/claude-code/data-usage).
+- Jev APIs: Prompts og andre input bruges ikke til træning. Data opbevares i overensstemmelse med [TypeSafe AI's privatlivspolitik](https://typesafe.ai/legal/privacy-policy).

 ---

@@ -279,6 +279,7 @@ Alle unsere Modelle werden in den USA gehostet. Unsere Provider folgen einer Zer
 - Nemotron 3 Ultra Free (kostenlose NVIDIA-Endpunkte): Nur für Testzwecke — übermitteln Sie keine personenbezogenen oder vertraulichen Daten. Ihre Nutzung wird zu Sicherheitszwecken und zur Verbesserung der Produkte und Dienste von NVIDIA protokolliert. Die zu Verbesserungszwecken protokollierten Sitzungsdaten sind nicht mit Ihrer Identität oder einem dauerhaften Identifikator verknüpft. Weitere Informationen zu unseren Datenverarbeitungspraktiken finden Sie in unserer [Datenschutzrichtlinie](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf). Durch die Interaktion mit diesem Endpunkt stimmen Sie unserer Erhebung, Aufzeichnung und Nutzung solcher Informationen sowie den [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf) zu.
 - OpenAI APIs: Anfragen werden in Übereinstimmung mit [OpenAI's Data Policies](https://platform.openai.com/docs/guides/your-data) 30 Tage lang gespeichert.
 - Anthropic APIs: Anfragen werden in Übereinstimmung mit [Anthropic's Data Policies](https://docs.anthropic.com/en/docs/claude-code/data-usage) 30 Tage lang gespeichert.
+- Jev APIs: Prompts und andere Eingaben werden nicht für das Training verwendet. Daten werden gemäß der [Datenschutzrichtlinie von TypeSafe AI](https://typesafe.ai/legal/privacy-policy) gespeichert.

 ---

@@ -293,6 +293,7 @@ Todos nuestros modelos están alojados en US. Nuestros proveedores siguen una po
 - Nemotron 3 Ultra Free (endpoints gratuitos de NVIDIA): Solo para uso de prueba — no envíes datos personales ni confidenciales. Tu uso se registra con fines de seguridad y para mejorar los productos y servicios de NVIDIA. Los datos de sesión registrados con fines de mejora no están vinculados a tu identidad ni a ningún identificador persistente. Para obtener más información sobre nuestras prácticas de procesamiento de datos, consulta nuestra [Política de privacidad](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf). Al interactuar con este endpoint, aceptas que recopilemos, registremos y usemos dicha información, así como los [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf).
 - OpenAI APIs: Las solicitudes se conservan durante 30 días de acuerdo con [OpenAI's Data Policies](https://platform.openai.com/docs/guides/your-data).
 - Anthropic APIs: Las solicitudes se conservan durante 30 días de acuerdo con [Anthropic's Data Policies](https://docs.anthropic.com/en/docs/claude-code/data-usage).
+- Jev APIs: Los prompts y otras entradas no se usan para el entrenamiento. Los datos se conservan de acuerdo con la [política de privacidad de TypeSafe AI](https://typesafe.ai/legal/privacy-policy).

 ---

@@ -279,6 +279,7 @@ Tous nos modèles sont hébergés aux US. Nos fournisseurs suivent une politique
 - Nemotron 3 Ultra Free (endpoints NVIDIA gratuits) : Réservé à un usage d'essai — n'envoyez pas de données personnelles ou confidentielles. Votre utilisation est journalisée à des fins de sécurité et pour améliorer les produits et services de NVIDIA. Les données de session journalisées à des fins d'amélioration ne sont pas liées à votre identité ni à un quelconque identifiant persistant. Pour plus d'informations sur nos pratiques de traitement des données, consultez notre [Politique de confidentialité](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf). En interagissant avec cet endpoint, vous consentez à notre collecte, à notre enregistrement et à notre utilisation de ces informations ainsi qu'aux [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf).
 - OpenAI APIs : Les requêtes sont conservées pendant 30 jours conformément à [OpenAI's Data Policies](https://platform.openai.com/docs/guides/your-data).
 - Anthropic APIs : Les requêtes sont conservées pendant 30 jours conformément à [Anthropic's Data Policies](https://docs.anthropic.com/en/docs/claude-code/data-usage).
+- Jev APIs : Les prompts et autres données saisies ne sont pas utilisés pour l'entraînement. Les données sont conservées conformément à la [politique de confidentialité de TypeSafe AI](https://typesafe.ai/legal/privacy-policy).

 ---

--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
Aiden Cline	9b4a372c2a	fix(ai): classify Z.ai prompt length, sensitive content, and fair-use errors	2026-09-29 10:53:10 -05:00
Aiden Cline	d12f89b9c8	fix(ai): classify Z.ai plan and balance limits as quota	2026-09-29 10:43:07 -05:00
Aiden Cline	2aaa265cdc	fix(ai): read provider error messages from common body layouts (#52014 )	2026-09-29 00:19:20 -05:00
Luke Parker	ff72659a47	fix(desktop): give isolated dev service a fixed port (#52013 )	2026-09-29 15:09:50 +10:00
Aiden Cline	14af33d53d	fix(ai): show provider error bodies when no message is recognized (#51978 )	2026-09-29 00:06:52 -05:00
Luke Parker	a604b7f773	fix(ui): calm diff word highlights with @pierre/diffs 1.5.1 (#51236 )	2026-09-29 14:58:24 +10:00
Luke Parker	41d4a9c45c	fix(session-ui): render moved notice as a timeline divider (#52009 )	2026-09-29 14:58:13 +10:00
Luke Parker	293d60a89f	chore(desktop): bump electron to 44.4.5 (#52005 )	2026-09-29 14:50:04 +10:00
Aiden Cline	34a8938dc7	fix(ai): bind Bedrock Claude thinking blocks by default (#51959 )	2026-09-28 23:38:20 -05:00
Aiden Cline	36ef6cc216	fix(ai): finalize Bedrock redacted reasoning at block end (#51999 )	2026-09-28 23:37:51 -05:00
opencode	f02c30eb55	sync release versions for v2.0.19	2026-09-29 04:31:02 +00:00
Aiden Cline	ca084b2430	fix(ai): give provider routes distinct IDs (#51976 )	2026-09-28 19:55:06 -05:00
Aiden Cline	3740ec311b	feat(core): align shell tool environment with agent conventions (#51975 )	2026-09-28 19:53:53 -05:00
opencode-agent[bot]andrekram1-node	35bd8ac442	test(core): update xAI variant expectations for Responses (#51977 ) Co-authored-by: rekram1-node <rekram1-node@users.noreply.github.com>	2026-09-28 19:48:35 -05:00
Aiden Cline	1fc05ca590	fix(core): share affinity in provider session headers (#51931 )	2026-09-28 19:30:24 -05:00
Aiden Cline	bda798b167	fix(core): drop session ID and order instructions for prompt-cache reuse (#51960 )	2026-09-28 19:29:28 -05:00
Aiden Cline	3babae35c0	fix(core): fall back to Cloudflare environment IDs when not configured (#51963 )	2026-09-28 19:28:03 -05:00
Aiden Cline	3ab5c1433c	fix(core): request xAI reasoning summaries on Responses variants (#51964 )	2026-09-28 19:11:48 -05:00
Aiden Cline	49437a25b1	fix(ai): classify invalid Google API keys as authentication errors (#51950 )	2026-09-28 18:49:29 -05:00
Aiden Cline	49403a554f	feat(core): cap requested output tokens at 256k (#51962 )	2026-09-28 18:49:05 -05:00
opencode-agent[bot]andrekram1-node	87d6f93409	test(cli): isolate run exit codes between tests (#51955 ) Co-authored-by: rekram1-node <rekram1-node@users.noreply.github.com>	2026-09-28 19:16:01 -04:00
Frank	97d4eaa2ba	zen: jev privacy policy	2026-09-28 19:01:46 -04:00