refactor(core): clarify Session factory construction

test(core): exercise ID-bound Session operations
refactor(core): isolate Session admission and controls
2026-08-28 20:46:14 +00:00 · 2026-08-28 16:29:17 -04:00 · 2026-08-28 16:10:40 -04:00 · 2026-08-28 16:08:37 -04:00 · 2026-08-28 19:43:12 +00:00 · 2026-08-28 15:43:06 -04:00
512 changed files with 25550 additions and 14728 deletions
@@ -1,5 +0,0 @@
---
-"@opencode-ai/core": patch
---
-
-Preserve prompt cache prefixes when sessions move between locations with unchanged instructions.
@@ -1,5 +0,0 @@
---
-"@opencode-ai/core": patch
---
-
-Fix OpenCode Console device authorization URLs when the server returns an origin-rooted verification path.
@@ -0,0 +1,5 @@
+---
+"@opencode-ai/core": patch
+---
+
+Correct directory page headings when the read offset is zero.
@@ -1,5 +0,0 @@
---
-"@opencode-ai/core": patch
---
-
-Propagate fatal Git ignore-check errors during index refresh so best-effort snapshot capture returns unavailable instead of treating the check as having no matches.
@@ -1,5 +0,0 @@
---
-"@opencode-ai/core": patch
---
-
-Prompt and synthetic inbox ID reuse is now idempotent: reusing an ID within the same Session succeeds and returns the first admission, ignoring the retried payload, metadata, and delivery mode. Previously reuse with a differing payload failed with a conflict. Cross-Session and cross-type reuse still fail, and control items keep their operation-specific conflict behavior.
@@ -1,5 +0,0 @@
---
-"@opencode-ai/core": patch
---
-
-Rename the write, patch, and question tool formatting helpers from `toModelOutput` to `toModelContent` to match the result field they populate. Direct imports of these helpers must use the new name; generated content and declared machine output are unchanged.
@@ -1,5 +0,0 @@
---
-"@opencode-ai/core": minor
---
-
-Rename ModelResolver.supported to ModelResolver.hasPackage. Consumers of the old export must update the name; the predicate remains Boolean(model.package), checking only whether a catalog model declares a provider package, not whether it can be loaded. Default-model selection behavior is unchanged.
@@ -1,5 +0,0 @@
---
-"@opencode-ai/core": patch
---
-
-Nested AGENTS.md instructions are re-injected after compaction. Previously the in-memory dedup claim outlived the synthetic message that compaction dropped from model-visible history, so nested instructions were silently lost for the rest of the process lifetime. The claim now only guards in-flight loads; the synthetic message metadata in durable history is the sole lasting ledger, so any history truncation (compaction, revert) self-heals on the next read in that subtree.
@@ -1,5 +0,0 @@
---
-"@opencode-ai/plugin": patch
---
-
-Derive Promise plugin API request and response conversion from the canonical protocol schemas.
@@ -1,8 +0,0 @@
---
-"@opencode-ai/core": minor
-"@opencode-ai/schema": minor
-"@opencode-ai/protocol": minor
-"@opencode-ai/client": minor
---
-
-Remove the unused question request API and use session forms for question tool interactions.
@@ -1,5 +0,0 @@
---
-"@opencode-ai/core": patch
---
-
-Include both paths of renamed files in new snapshot change lists so undo restores the original file instead of only deleting the renamed file.
@@ -1,5 +0,0 @@
---
-"@opencode-ai/core": patch
---
-
-Apply shared Session model-request preparation to transient generation.
@@ -1,9 +0,0 @@
---
-"@opencode-ai/core": minor
-"@opencode-ai/schema": minor
-"@opencode-ai/protocol": minor
-"@opencode-ai/client": minor
---
-
-Add an opt-in portable shell permission scanner. Opaque commands use normal shell authorization without inferring
-external directories, while the default tree-sitter path remains unchanged.
@@ -1,10 +0,0 @@
---
-"@opencode-ai/core": patch
---
-
-Make the experimental portable shell scanner authoritative, with no Tree-sitter
-fallback. Scan common Bash and PowerShell control flow, heredocs, functions,
-expressions, quoting, and substitutions natively. Preserve existing redirect and
-declaration permission matching, and make PowerShell saved approvals cover the
-original command spelling. Parser failures remain visible without changing the
-permission engine. The default Tree-sitter path is unchanged.
@@ -1,5 +0,0 @@
---
-"@opencode-ai/core": patch
---
-
-Use parent directory names for SKILL.md IDs so individually downloaded skills do not overwrite each other.
@@ -1,5 +0,0 @@
---
-"@opencode-ai/core": patch
---
-
-Simplify interrupt continuation: the steer-scoped resume decision now lives in SessionExecution as a post-cleanup inbox check, and the run coordinator drops its continuation state machine. Wakes arriving during cancellation cleanup now restart a normal full drain, and interrupting an idle session with continue now resumes pending steering input. Recovery-applied moves now end with the same full wake as inbox-admitted moves, retrying any stranded inbox work at the new location. Interrupting with continue now also resumes a next-in-line control item: between-turn manual compaction and moves run under any drain scope, while queued prompts remain parked.
@@ -1,6 +0,0 @@
---
-"@opencode-ai/client": patch
-"@opencode-ai/plugin": patch
---
-
-Add form reply and cancellation operations that reconcile terminal forms in the local TUI projection.
@@ -1,5 +0,0 @@
---
-"@opencode-ai/core": patch
---
-
-Title generation and compaction summaries now build their model requests through the shared session request boundary, gaining unsupported-media filtering and image bounds while explicitly opting out of session context hooks: plugins that shape the agent conversation do not observe title or compaction requests. Title requests gain the fork-aware session prompt cache key, and compaction summaries in forked sessions reuse the fork root's prompt cache key instead of the fork's own.
@@ -1,6 +0,0 @@
---
-"@opencode-ai/plugin": patch
-"@opencode-ai/core": patch
---
-
-Add transport-neutral Session model request hooks and provider-scoped hook registration so eligible OpenAI Responses requests can prefer WebSocket without bypassing HTTP-only middleware.
@@ -41,11 +41,5 @@
    // Warn when spreading non-plain objects (Headers, class instances, etc.)
    "typescript/no-misused-spread": "warn"
  },
-  "options": {
-    "typeAware": true
-  },
-  "options": {
-    "typeAware": true
-  },
  "ignorePatterns": ["**/node_modules", "**/dist", "**/.build", "**/.sst", "**/*.d.ts", "**/sdk.gen.ts"]
 }
@@ -2,7 +2,7 @@
 exact = true
 # Only install newly resolved package versions published at least 3 days ago.
 minimumReleaseAge = 259200
-minimumReleaseAgeExcludes = ["@ai-sdk/amazon-bedrock", "@ai-sdk/anthropic", "@brendonovich/vite-plugin-opencode", "@opencode-ai/sdk", "@opencode-ai/pty", "@opencode-ai/pty-darwin-arm64", "@opencode-ai/pty-darwin-x64", "@opencode-ai/pty-linux-arm64-gnu", "@opencode-ai/pty-linux-arm64-musl", "@opencode-ai/pty-linux-x64-gnu", "@opencode-ai/pty-linux-x64-musl", "@opentui/core", "@opentui/core-darwin-arm64", "@opentui/core-darwin-x64", "@opentui/core-linux-arm64", "@opentui/core-linux-arm64-musl", "@opentui/core-linux-x64", "@opentui/core-linux-x64-musl", "@opentui/core-win32-arm64", "@opentui/core-win32-x64", "@opentui/keymap", "@opentui/solid", "opentui-spinner", "gitlab-ai-provider", "opencode-gitlab-auth", "@ff-labs/fff-node", "@ff-labs/fff-bun", "@ff-labs/fff-bin-darwin-arm64", "@ff-labs/fff-bin-darwin-x64", "@ff-labs/fff-bin-linux-arm64-gnu", "@ff-labs/fff-bin-linux-arm64-musl", "@ff-labs/fff-bin-linux-x64-gnu", "@ff-labs/fff-bin-linux-x64-musl", "@ff-labs/fff-bin-win32-arm64", "@ff-labs/fff-bin-win32-x64", "@pierre/diffs", "@pierre/theming", "app-builder-lib", "dmg-builder", "electron-builder", "electron-publish", "blume"]
+minimumReleaseAgeExcludes = ["@ai-sdk/amazon-bedrock", "@ai-sdk/anthropic", "@brendonovich/vite-plugin-opencode", "@opencode-ai/sdk", "@opencode-ai/pty", "@opencode-ai/pty-darwin-arm64", "@opencode-ai/pty-darwin-x64", "@opencode-ai/pty-linux-arm64-gnu", "@opencode-ai/pty-linux-arm64-musl", "@opencode-ai/pty-linux-x64-gnu", "@opencode-ai/pty-linux-x64-musl", "@opentui/core", "@opentui/core-darwin-arm64", "@opentui/core-darwin-x64", "@opentui/core-linux-arm64", "@opentui/core-linux-arm64-musl", "@opentui/core-linux-x64", "@opentui/core-linux-x64-musl", "@opentui/core-win32-arm64", "@opentui/core-win32-x64", "@opentui/keymap", "@opentui/solid", "opentui-spinner", "gitlab-ai-provider", "opencode-gitlab-auth", "@ff-labs/fff-node", "@ff-labs/fff-bun", "@ff-labs/fff-bin-darwin-arm64", "@ff-labs/fff-bin-darwin-x64", "@ff-labs/fff-bin-linux-arm64-gnu", "@ff-labs/fff-bin-linux-arm64-musl", "@ff-labs/fff-bin-linux-x64-gnu", "@ff-labs/fff-bin-linux-x64-musl", "@ff-labs/fff-bin-win32-arm64", "@ff-labs/fff-bin-win32-x64", "@pierre/diffs", "@pierre/theming", "app-builder-lib", "dmg-builder", "electron", "electron-builder", "electron-publish", "blume", "mermaid"]

 [test]
 root = "./do-not-run-tests-from-root"
@@ -63,7 +63,8 @@ new sst.cloudflare.StaticSite("WebApp", {
  domain: "app." + domain,
  path: "packages/app",
  build: {
-    command: "bun turbo build",
+    // Preserve Sentry credentials and run source-map uploads on every deployment.
+    command: "bun run build",
    output: "./dist",
  },
 })
@@ -4,7 +4,7 @@
  bun,
  nodejs,
  darwin,
-  electron_41,
+  callPackage,
  makeWrapper,
  writableTmpDirAsHomeHook,
  autoPatchelfHook,
@@ -13,7 +13,7 @@
  opencode,
 }:
 let
-  electron = electron_41;
+  electron = callPackage ./electron.nix { };
 in
 stdenv.mkDerivation (finalAttrs: {
  pname = "opencode-desktop";
@@ -48,7 +48,7 @@ stdenv.mkDerivation (finalAttrs: {
    desktopName = "OpenCode";
    exec = "opencode-desktop %U";
    icon = "ai.opencode.desktop";
-    # Electron 41 derives X11 WM_CLASS from app.name.
+    # Electron derives X11 WM_CLASS from app.name.
    startupWMClass = "OpenCode";
    categories = [ "Development" ];
  });
@@ -67,12 +67,10 @@ stdenv.mkDerivation (finalAttrs: {
    # https://github.com/electron/electron/issues/31121
    # mac builds use a .app bundle which doesnt have this issue
    + lib.optionalString stdenv.isLinux ''
-      BASE_PATH=packages/desktop
-      FILES=(src/main/windows.ts)
-      for file in "''${FILES[@]}"; do
-        substituteInPlace $BASE_PATH/$file \
-          --replace-fail "process.resourcesPath" "'$out/opt/opencode-desktop/resources'"
-      done
+      substituteInPlace \
+        packages/desktop/src/main/windows/appearance.ts \
+        packages/desktop/src/main/service/desktop-cli.ts \
+        --replace-fail "process.resourcesPath" "'$out/opt/opencode-desktop/resources'"
    '';

  preBuild = ''
@@ -0,0 +1,13 @@
+{ callPackage, path }:
+let
+  version = (builtins.fromJSON (builtins.readFile ../packages/desktop/package.json)).devDependencies.electron;
+in
+(callPackage (path + "/pkgs/development/tools/electron/binary/generic.nix") { }) version {
+  # Electron 42.10.1 SHASUMS256.txt; update with the desktop package version.
+  aarch64-linux = "20e68d6c4e47f3ebf59de7c6b1f8b8bec6a6ebda6a451132f9b465f3f13ce467";
+  x86_64-linux = "2452b27112d92387471fa2488aafac85d79ea3f2ee1216c0abd5150d6c12362b";
+  aarch64-darwin = "ac7194a3dfd81930ba35355c01620262c1254752859b42dcb8f4b9e4d174a871";
+  x86_64-darwin = "4489aba55477a0082266cb690db1c829503ba3338048599d8fd243953df37dab";
+  # fetchzip hashes the unpacked headers, not the release tarball.
+  headers = "sha256-4eUy3BZVvxTl7KUOsxio7769lL6ag/ecbeK+qLURWMI=";
+}
@@ -1,8 +1,8 @@
 {
  "nodeModules": {
-    "x86_64-linux": "sha256-agxF1Ab8P84tijHvw7jaG+9UZm/dJZhHw8CGNlQQqYc=",
-    "aarch64-linux": "sha256-Kg6CkhoEEsb+ZOGPN/rnNoirLdGSyQl6HU/Fy8t9Mqs=",
-    "aarch64-darwin": "sha256-SnxBpmcfPL2p3OYmSuG5Y/aFW8PeEOLhfQrxAs/53fs=",
-    "x86_64-darwin": "sha256-Dnxl1EcfiE7/rlHmPkko0BKc6hHVk6rQ/2h/PWuLfNo="
+    "x86_64-linux": "sha256-EtUp4pHl9TyPtRrLGvk/X7kd2LuIxNxCpUwF5aLtzN4=",
+    "aarch64-linux": "sha256-m0j/pMZCguclR3/T9JmzCfi11YzmIvBFyR2bVhIO37Y=",
+    "aarch64-darwin": "sha256-nqefk68ZTUfNU15q1WkXaGsFzPNwOjCtMHpp6WrpNqM=",
+    "x86_64-darwin": "sha256-syD7hX62E4yCDV/wux1QKw4q/zZr24f99Y2mmzMJo6o="
  }
 }
@@ -39,24 +39,24 @@
      "packages/stats/*"
    ],
    "catalog": {
-      "@effect/opentelemetry": "4.0.0-rc.111",
-      "@effect/platform-node": "4.0.0-rc.111",
-      "@effect/platform-node-shared": "4.0.0-rc.111",
-      "@effect/sql-sqlite-bun": "4.0.0-rc.111",
+      "@effect/opentelemetry": "4.0.0-rc.112",
+      "@effect/platform-node": "4.0.0-rc.112",
+      "@effect/platform-node-shared": "4.0.0-rc.112",
+      "@effect/sql-sqlite-bun": "4.0.0-rc.112",
      "@npmcli/arborist": "9.4.0",
      "@types/bun": "1.3.13",
      "@types/cross-spawn": "6.0.6",
      "@octokit/rest": "22.0.0",
      "@hono/standard-validator": "0.2.0",
      "@hono/zod-validator": "0.4.2",
-      "@opentui/core": "0.5.8",
-      "@opentui/keymap": "0.5.8",
-      "@opentui/solid": "0.5.8",
+      "@opentui/core": "0.5.9",
+      "@opentui/keymap": "0.5.9",
+      "@opentui/solid": "0.5.9",
      "@tanstack/solid-virtual": "3.13.37",
-      "@shikijs/stream": "4.2.0",
+      "@shikijs/stream": "4.4.3",
      "@standard-schema/spec": "1.1.0",
      "ulid": "3.0.1",
-      "@kobalte/core": "0.13.11",
+      "@kobalte/core": "0.13.13",
      "@corvu/drawer": "0.2.4",
      "@types/luxon": "3.7.1",
      "@types/node": "24.12.2",
@@ -67,13 +67,16 @@
      "@openauthjs/openauth": "0.0.0-20250322224806",
      "@pierre/diffs": "1.2.10",
      "opentui-spinner": "0.0.7",
-      "@solid-primitives/storage": "4.3.3",
+      "@solid-primitives/event-listener": "2.4.6",
+      "@solid-primitives/media": "2.3.6",
+      "@solid-primitives/resize-observer": "2.2.0",
+      "@solid-primitives/storage": "4.4.0",
      "@tailwindcss/vite": "4.1.11",
-      "diff": "8.0.2",
-      "dompurify": "3.3.1",
+      "diff": "8.0.4",
+      "dompurify": "3.4.14",
      "drizzle-kit": "1.0.0-rc.5-ab785fc",
      "drizzle-orm": "1.0.0-rc.5-169397b",
-      "effect": "4.0.0-rc.111",
+      "effect": "4.0.0-rc.112",
      "ai": "6.0.168",
      "cross-spawn": "7.0.6",
      "hono": "4.10.7",
@@ -81,9 +84,9 @@
      "fuzzysort": "3.1.0",
      "get-east-asian-width": "1.6.0",
      "luxon": "3.6.1",
-      "marked": "18.0.7",
+      "marked": "18.0.11",
      "marked-shiki": "1.2.1",
-      "remend": "1.3.0",
+      "remend": "1.3.1",
      "@playwright/test": "1.59.1",
      "semver": "7.7.4",
      "typescript": "5.8.2",
@@ -92,17 +95,17 @@
      "remeda": "2.26.0",
      "resolve.exports": "2.0.3",
      "sst": "4.13.1",
-      "shiki": "4.2.0",
+      "shiki": "4.4.3",
      "solid-list": "0.3.0",
      "string-width": "7.2.0",
      "tailwindcss": "4.1.11",
-      "vite": "7.1.4",
+      "vite": "7.3.6",
      "@solidjs/meta": "0.29.4",
-      "@solidjs/router": "0.15.4",
+      "@solidjs/router": "1.0.0",
      "@solidjs/start": "https://pkg.pr.new/@solidjs/start@dfb2020",
-      "@sentry/solid": "10.36.0",
-      "@sentry/vite-plugin": "4.6.0",
-      "solid-js": "1.9.10",
+      "@sentry/solid": "10.71.0",
+      "@sentry/vite-plugin": "5.4.0",
+      "solid-js": "1.9.15",
      "solid-sonner": "0.3.1",
      "vite-plugin-solid": "2.11.10",
      "@lydell/node-pty": "1.2.0-beta.12"
@@ -158,7 +161,8 @@
    "@effect/platform-node-shared": "catalog:",
    "@types/bun": "catalog:",
    "@types/node": "catalog:",
-    "effect": "catalog:"
+    "effect": "catalog:",
+    "solid-js": "catalog:"
  },
  "patchedDependencies": {
    "@ai-sdk/openai-compatible@2.0.41": "patches/@ai-sdk%2Fopenai-compatible@2.0.41.patch",
@@ -166,7 +170,7 @@
    "@npmcli/agent@4.0.2": "patches/@npmcli%2Fagent@4.0.2.patch",
    "@silvia-odwyer/photon-node@0.3.4": "patches/@silvia-odwyer%2Fphoton-node@0.3.4.patch",
    "@standard-community/standard-openapi@0.2.9": "patches/@standard-community%2Fstandard-openapi@0.2.9.patch",
-    "solid-js@1.9.10": "patches/solid-js@1.9.10.patch",
+    "solid-js@1.9.15": "patches/solid-js@1.9.15.patch",
    "@ai-sdk/mistral@3.0.51": "patches/@ai-sdk%2Fmistral@3.0.51.patch",
    "gcp-metadata@8.1.2": "patches/gcp-metadata@8.1.2.patch",
    "pacote@21.5.0": "patches/pacote@21.5.0.patch",
@@ -214,22 +214,40 @@ the requests sent by code under test:
 import { Effect } from "effect"
 import { TestLLM } from "@opencode-ai/ai/testing"

-const testLLM = TestLLM.layer({
-  fallback: TestLLM.text("Hello from the test model", "text-1"),
-})
-
-// TestLLM.clientLayer provides LLMClient.Service and consumes TestLLM.Service.
 const programWithTestClient = Effect.gen(function* () {
+  const test = yield* TestLLM.Test
+  yield* test.push(TestLLM.text("Hello from the test model", "text-1"))
  const result = yield* program
-  const test = yield* TestLLM.Service
-  console.log(test.requests)
+  console.log(yield* test.requests())
  return result
-}).pipe(Effect.provide(TestLLM.clientLayer), Effect.provide(testLLM))
+}).pipe(Effect.provide(TestLLM.testLayer()))
 ```

-`TestLLM.push(...)` scripts one-shot responses, `TestLLM.always(...)` changes the fallback, and
-`TestLLM.wait(...)` lets concurrent tests wait until a request has arrived. Every received canonical request is
-available on the yielded `TestLLM.Service`.
+`testLayer()` provides the same object under `LLMClient.Service` and `TestLLM.Test`. Production consumes the
+normal client; tests use the additional controls. Each layer build has fresh state.
+
+- `test.push(...)` queues one-shot responses in execution order. Each argument is one response.
+- `test.always(response)` installs a repeatable fallback. The layer's `fallback` option sets its initial value.
+- `test.serve(request => response)` installs a request-dependent fallback. `always` and `serve` replace each
+  other without changing queued replies; queued replies take precedence.
+- `test.requests()` returns an array snapshot. `transformRequest` changes only the recorded observation;
+  `serve` receives the original canonical request.
+- `test.wait(count)` waits for request arrivals, not output or completion, and supports concurrent waiters.
+- `test.gate()` returns a scoped gate with countable `started` notifications and a `release` Effect. Release
+  unblocks all requests captured by that gate; closing its scope also releases it. Effect-aware test runners
+  already provide Scope.
+
+Constructing `stream()` or `generate()` does not record a request, invoke a responder, or consume a script.
+Each execution does. An exhausted queue without a fallback defects immediately rather than waiting for a
+future reply.
+
+Responses remain canonical event arrays or arbitrary `Stream<LLMEvent, AIError>` values. The client consumes
+supplied streams directly, preserving failure identity, finalizers, incomplete output, and post-finish tails;
+it does not repair or truncate them.
+
+The published legacy `Service`, `layer`, `clientLayer`, and module-level controls remain available as adapters
+over the same implementation, including the legacy live `requests` array. New tests should use `Test` and
+`testLayer`.

 ## Caching

@@ -374,6 +374,12 @@ const lowerMessages = Effect.fn("BedrockConverse.lowerMessages")(function* (
            content.push({ reasoningContent: { redactedContent: redactedData } })
            continue
          }
+          if (signature === undefined || signature.trim().length === 0) {
+            // Interrupted streams and model switches can leave unsigned reasoning.
+            // Preserve readable history as text rather than replay invalid reasoningContent.
+            if (part.text.trim().length > 0) content.push(...textWithCache(breakpoints, part.text, part.cache))
+            continue
+          }
          content.push({ reasoningContent: { reasoningText: { text: part.text, signature } } })
          continue
        }
@@ -382,7 +388,7 @@ const lowerMessages = Effect.fn("BedrockConverse.lowerMessages")(function* (
          continue
        }
      }
-      messages.push({ role: "assistant", content })
+      if (content.length > 0) messages.push({ role: "assistant", content })
      continue
    }

@@ -490,6 +496,7 @@ const mapUsage = (usage: BedrockUsageSchema | undefined, providerMetadataKey: st
 interface ParserState {
  readonly providerMetadataKey: string
  readonly tools: ToolStream.State<number>
+  readonly finishedTools: ReadonlySet<number>
  // Bedrock splits the finish into `messageStop` (carries `stopReason`) and
  // `metadata` (carries usage). Hold the terminal event in state so `onHalt`
  // can emit exactly one finish after both chunks have had a chance to arrive.
@@ -568,6 +575,7 @@ const step = (state: ParserState, event: BedrockEvent) =>

    if (event.contentBlockDelta?.delta?.toolUse) {
      const index = event.contentBlockDelta.contentBlockIndex
+      if (state.finishedTools.has(index)) return [state, []] as const
      const result = ToolStream.appendExisting(
        ADAPTER,
        state.tools,
@@ -606,6 +614,7 @@ const step = (state: ParserState, event: BedrockEvent) =>
            state.hasToolCalls,
          lifecycle,
          tools: result.tools,
+          finishedTools: resultEvents.length > 0 ? new Set([...state.finishedTools, index]) : state.finishedTools,
          reasoningSignatures: Object.fromEntries(
            Object.entries(state.reasoningSignatures).filter(([key]) => key !== String(index)),
          ),
@@ -697,6 +706,7 @@ export const protocol = Protocol.make({
    initial: (request) => ({
      providerMetadataKey: request.model.route.providerMetadataKey ?? String(request.model.provider),
      tools: ToolStream.empty<number>(),
+      finishedTools: new Set<number>(),
      pendingFinish: undefined,
      hasToolCalls: false,
      lifecycle: Lifecycle.initial(),
@@ -391,17 +391,19 @@ export interface ParserState {
  readonly name: string
  readonly providerMetadataKey: string
  readonly tools: ToolStream.State<string>
+  // Call ids stay independent of item ids, which may be omitted or reused.
+  readonly completedTools: ReadonlySet<string>
  readonly hasFunctionCall: boolean
  readonly lifecycle: Lifecycle.State
  readonly outputItems: Readonly<Record<number, string>>
-  readonly messageItems: ReadonlySet<string>
-  readonly messagePhases: Readonly<Record<string, MessagePhase | null>>
+  readonly message: { readonly id: string; readonly phase: MessagePhase | null | undefined } | undefined
  readonly reasoningItems: Readonly<Record<string, ReasoningStreamItem>>
 }

 type ReasoningSummaryStatus = "active" | "can-conclude" | "concluded"

 interface ReasoningStreamItem {
+  readonly open: boolean
  readonly encryptedContent: string | null | undefined
  // Keyed by the wire protocol's numeric `summary_index`. JS object keys coerce to
  // strings, but typing the map as `Record<number, ...>` documents intent
@@ -826,16 +828,16 @@ const TERMINAL_TYPES = new Set(["error", "response.completed", "response.incompl
 export const terminal = (event: Event) => TERMINAL_TYPES.has(event.type)

 const onOutputTextDelta = (state: ParserState, event: Event, id: string): StepResult => {
-  if (!event.delta || !state.messageItems.has(id)) return [state, NO_EVENTS]
+  if (!event.delta || state.message?.id !== id) return [state, NO_EVENTS]
  const events: LLMEvent[] = []
-  const phase = state.messagePhases[id]
+  const phase = state.message.phase
  const metadata = providerMetadata(state, { itemId: id, ...(phase === undefined ? {} : { phase }) })
  const lifecycle = Lifecycle.textStart(state.lifecycle, events, id, metadata)
  return [{ ...state, lifecycle: Lifecycle.textDelta(lifecycle, events, id, event.delta) }, events]
 }

 const onOutputTextDone = (state: ParserState, event: Event, id: string): StepResult => {
-  if (state.messageItems.has(id)) {
+  if (state.message?.id === id) {
    if (state.lifecycle.text.has(id) || event.text === undefined) return [state, NO_EVENTS]
    return onOutputTextDelta(state, { ...event, delta: event.text }, id)
  }
@@ -846,18 +848,62 @@ const onOutputTextDone = (state: ParserState, event: Event, id: string): StepRes
 export const outputItemID = (state: ParserState, event: Event) =>
  event.output_index === undefined ? event.item_id : (state.outputItems[event.output_index] ?? event.item_id)

-export const onReasoningDelta = (state: ParserState, event: Event, itemID: string): StepResult => {
+const startReasoningSummaryPart = (state: ParserState, itemID: string, index: number): StepResult => {
  const item = state.reasoningItems[itemID]
-  if (!event.delta || !item) return [state, NO_EVENTS]
-  const index = event.summary_index ?? 0
+  if (!item?.open || index === 0 || item.summaryParts[index] !== undefined) return [state, NO_EVENTS]
+
  const events: LLMEvent[] = []
+  const lifecycle = Object.entries(item.summaryParts)
+    .filter((entry) => entry[1] !== "concluded")
+    .reduce(
+      (lifecycle, entry) =>
+        Lifecycle.reasoningEnd(lifecycle, events, `${itemID}:${entry[0]}`, providerMetadata(state, { itemId: itemID })),
+      state.lifecycle,
+    )
  return [
    {
      ...state,
-      lifecycle: Lifecycle.reasoningDelta(state.lifecycle, events, `${itemID}:${index}`, event.delta),
+      lifecycle: Lifecycle.reasoningStart(
+        lifecycle,
+        events,
+        `${itemID}:${index}`,
+        providerMetadata(state, { itemId: itemID, reasoningEncryptedContent: item.encryptedContent ?? null }),
+      ),
      reasoningItems: {
        ...state.reasoningItems,
-        [itemID]: { ...item, deltaIndexes: new Set([...item.deltaIndexes, index]) },
+        [itemID]: {
+          ...item,
+          summaryParts: {
+            ...Object.fromEntries(
+              Object.entries(item.summaryParts).map((entry) =>
+                entry[1] === "concluded" ? entry : [entry[0], "concluded" as const],
+              ),
+            ),
+            [index]: "active",
+          },
+        },
+      },
+    },
+    events,
+  ]
+}
+
+export const onReasoningDelta = (state: ParserState, event: Event, itemID: string): StepResult => {
+  const item = state.reasoningItems[itemID]
+  if (!event.delta || !item?.open) return [state, NO_EVENTS]
+  const index = event.summary_index ?? 0
+  if (item.summaryParts[index] === "concluded") return [state, NO_EVENTS]
+  const [started, emitted] = startReasoningSummaryPart(state, itemID, index)
+  const current = started.reasoningItems[itemID]
+  if (!current) return [started, emitted]
+  const events: LLMEvent[] = [...emitted]
+  return [
+    {
+      ...started,
+      lifecycle: Lifecycle.reasoningDelta(started.lifecycle, events, `${itemID}:${index}`, event.delta),
+      reasoningItems: {
+        ...started.reasoningItems,
+        [itemID]: { ...current, deltaIndexes: new Set([...current.deltaIndexes, index]) },
      },
    },
    events,
@@ -869,7 +915,7 @@ export const onReasoningDelta = (state: ParserState, event: Event, itemID: strin
 // as a single delta unless that summary index already streamed one.
 export const onReasoningDone = (state: ParserState, event: Event, itemID: string): StepResult => {
  const item = state.reasoningItems[itemID]
-  if (!item || typeof event.text !== "string") return [state, NO_EVENTS]
+  if (!item?.open || typeof event.text !== "string") return [state, NO_EVENTS]
  const index = event.summary_index ?? 0
  if (item.deltaIndexes.has(index)) return [state, NO_EVENTS]
  return onReasoningDelta(state, { ...event, delta: event.text }, itemID)
@@ -878,32 +924,48 @@ export const onReasoningDone = (state: ParserState, event: Event, itemID: string
 const reasoningMetadata = (state: ParserState, item: StreamItem & { id: string }) =>
  providerMetadata(state, { itemId: item.id, reasoningEncryptedContent: item.encrypted_content ?? null })

-// Responses APIs stream reasoning items in a stable order:
+// Responses APIs normally stream reasoning items in this order:
 //   `output_item.added` (reasoning) →
 //     `reasoning_summary_part.added` (index=0) →
 //     `reasoning_summary_text.delta` →
 //     `reasoning_summary_part.done` (index=0) →
 //     (repeat for index>0) →
 //   `output_item.done` (reasoning).
-// The handlers below rely on this ordering: `onOutputItemAdded` seeds the
-// per-item entry, `onReasoningSummaryPartAdded` for `summary_index === 0`
-// short-circuits when the entry already exists, and higher-index handlers
-// fold against the same entry. Behaviour for out-of-order events is
-// best-effort, not guaranteed.
+// `onOutputItemAdded` seeds the per-item entry, while each later part start is
+// also an implicit boundary for the previous part. This keeps the common event
+// lifecycle ordered when a compatible provider omits or delays a part-done event.
 const onOutputItemAdded = (state: ParserState, event: Event): StepResult => {
  const item = event.item
  if (item?.type === "message" && item.id !== undefined) {
+    const itemID = item.id
    const phase = messagePhase(item.phase)
+    // A new message closes earlier messages, including ones that never streamed.
+    const events: LLMEvent[] = []
+    const lifecycle = [...state.lifecycle.text]
+      .filter((id) => id !== itemID)
+      .reduce((lifecycle, id) => {
+        const openPhase = state.message?.id === id ? state.message.phase : undefined
+        return Lifecycle.textEnd(
+          lifecycle,
+          events,
+          id,
+          providerMetadata(state, { itemId: id, ...(openPhase === undefined ? {} : { phase: openPhase }) }),
+        )
+      }, state.lifecycle)
    return [
      {
        ...state,
-        messageItems: new Set([...state.messageItems, item.id]),
-        messagePhases: phase === undefined ? state.messagePhases : { ...state.messagePhases, [item.id]: phase },
+        lifecycle,
+        message: {
+          id: itemID,
+          phase: phase === undefined && state.message?.id === itemID ? state.message.phase : phase,
+        },
      },
-      NO_EVENTS,
+      events,
    ]
  }
  if (item && isReasoningItem(item)) {
+    if (state.reasoningItems[item.id] !== undefined) return [state, NO_EVENTS]
    const events: LLMEvent[] = []
    return [
      {
@@ -912,6 +974,7 @@ const onOutputItemAdded = (state: ParserState, event: Event): StepResult => {
        reasoningItems: {
          ...state.reasoningItems,
          [item.id]: {
+            open: true,
            encryptedContent: item.encrypted_content,
            summaryParts: { 0: "active" },
            deltaIndexes: new Set(),
@@ -923,6 +986,8 @@ const onOutputItemAdded = (state: ParserState, event: Event): StepResult => {
  }
  if (item?.type !== "function_call" || !item.call_id) return [state, NO_EVENTS]
  const id = item.id ?? item.call_id
+  if (Object.values(state.tools).some((tool) => tool?.id === item.call_id) || state.completedTools.has(item.call_id))
+    return [state, NO_EVENTS]
  const metadata = item.id !== undefined ? providerMetadata(state, { itemId: item.id }) : undefined
  const events: LLMEvent[] = []
  const lifecycle = Lifecycle.stepStart(state.lifecycle, events)
@@ -943,55 +1008,14 @@ const onOutputItemAdded = (state: ParserState, event: Event): StepResult => {

 const onReasoningSummaryPartAdded = (state: ParserState, event: Event): StepResult => {
  if (event.item_id === undefined || event.summary_index === undefined) return [state, NO_EVENTS]
-  const item = state.reasoningItems[event.item_id]
-  if (!item) return [state, NO_EVENTS]
-  if (event.summary_index === 0) return [state, NO_EVENTS]
-
-  const events: LLMEvent[] = []
-  const closed = Object.entries(item.summaryParts)
-    .filter((entry) => entry[1] === "can-conclude")
-    .reduce(
-      (lifecycle, entry) =>
-        Lifecycle.reasoningEnd(
-          lifecycle,
-          events,
-          `${event.item_id}:${entry[0]}`,
-          providerMetadata(state, { itemId: event.item_id }),
-        ),
-      state.lifecycle,
-    )
-  return [
-    {
-      ...state,
-      lifecycle: Lifecycle.reasoningStart(
-        closed,
-        events,
-        `${event.item_id}:${event.summary_index}`,
-        providerMetadata(state, { itemId: event.item_id, reasoningEncryptedContent: item.encryptedContent ?? null }),
-      ),
-      reasoningItems: {
-        ...state.reasoningItems,
-        [event.item_id]: {
-          ...item,
-          summaryParts: {
-            ...Object.fromEntries(
-              Object.entries(item.summaryParts).map((entry) =>
-                entry[1] === "can-conclude" ? [entry[0], "concluded" as const] : entry,
-              ),
-            ),
-            [event.summary_index]: "active",
-          },
-        },
-      },
-    },
-    events,
-  ]
+  return startReasoningSummaryPart(state, event.item_id, event.summary_index)
 }

 const onReasoningSummaryPartDone = (state: ParserState, event: Event): StepResult => {
  if (event.item_id === undefined || event.summary_index === undefined) return [state, NO_EVENTS]
  const item = state.reasoningItems[event.item_id]
-  if (!item) return [state, NO_EVENTS]
+  if (!item?.open) return [state, NO_EVENTS]
+  if (item.summaryParts[event.summary_index] !== "active") return [state, NO_EVENTS]
  return [
    {
      ...state,
@@ -1047,11 +1071,8 @@ const onOutputItemDone = Effect.fn("OpenResponses.onOutputItemDone")(function* (

  if (item.type === "message" && item.id !== undefined) {
    const itemPhase = messagePhase(item.phase)
-    const phase = itemPhase === undefined ? state.messagePhases[item.id] : itemPhase
+    const phase = itemPhase === undefined && state.message?.id === item.id ? state.message.phase : itemPhase
    const events: LLMEvent[] = []
-    const messageItems = new Set(state.messageItems)
-    messageItems.delete(item.id)
-    const { [item.id]: _phase, ...messagePhases } = state.messagePhases
    return [
      {
        ...state,
@@ -1061,8 +1082,7 @@ const onOutputItemDone = Effect.fn("OpenResponses.onOutputItemDone")(function* (
          item.id,
          providerMetadata(state, { itemId: item.id, ...(phase === undefined ? {} : { phase }) }),
        ),
-        messageItems,
-        messagePhases,
+        message: state.message?.id === item.id ? undefined : state.message,
      },
      events,
    ] satisfies StepResult
@@ -1070,20 +1090,36 @@ const onOutputItemDone = Effect.fn("OpenResponses.onOutputItemDone")(function* (

  if (item.type === "function_call") {
    if (!item.call_id || !item.name) return [state, NO_EVENTS] satisfies StepResult
-    const id = item.id ?? item.call_id
-    const tools = state.tools[id]
-      ? state.tools
-      : ToolStream.start(state.tools, id, {
-          id: item.call_id,
-          name: item.name,
-          providerMetadata: item.id !== undefined ? providerMetadata(state, { itemId: item.id }) : undefined,
-        })
+    const callID = item.call_id
+    if (state.completedTools.has(callID)) return [state, NO_EVENTS] satisfies StepResult
+    const metadata = item.id !== undefined ? providerMetadata(state, { itemId: item.id }) : undefined
+    const fallback = item.id ?? callID
+    // Match the pending tool by call id so item events that disagree on
+    // whether `item.id` is present still resolve the same call.
+    const registered =
+      state.tools[fallback] !== undefined
+        ? fallback
+        : Object.keys(state.tools).find((key) => state.tools[key]?.id === callID)
+    const id = registered ?? fallback
+    const tools =
+      registered !== undefined
+        ? state.tools
+        : ToolStream.start(state.tools, id, {
+            id: callID,
+            name: item.name,
+            providerMetadata: metadata,
+          })
    const result =
      item.arguments === undefined
        ? yield* ToolStream.finish(state.id, tools, id)
        : yield* ToolStream.finishWithInput(state.id, tools, id, item.arguments)
    const events: LLMEvent[] = []
-    const resultEvents = result.events ?? []
+    const finished = result.events ?? []
+    // A done-only call never streamed a start event, so open its lifecycle here.
+    const resultEvents =
+      registered !== undefined || finished.length === 0
+        ? finished
+        : [LLMEvent.toolInputStart({ id: callID, name: item.name, providerMetadata: metadata }), ...finished]
    const lifecycle = resultEvents.length ? Lifecycle.stepStart(state.lifecycle, events) : state.lifecycle
    events.push(...resultEvents)
    return [
@@ -1094,6 +1130,7 @@ const onOutputItemDone = Effect.fn("OpenResponses.onOutputItemDone")(function* (
          resultEvents.some((event) => LLMEvent.is.toolCall(event) || LLMEvent.is.toolInputError(event)) ||
          state.hasFunctionCall,
        tools: result.tools,
+        completedTools: new Set([...state.completedTools, callID]),
      },
      events,
    ] satisfies StepResult
@@ -1104,20 +1141,49 @@ const onOutputItemDone = Effect.fn("OpenResponses.onOutputItemDone")(function* (
    const metadata = reasoningMetadata(state, item)
    const reasoningItem = state.reasoningItems[item.id]
    if (reasoningItem) {
+      if (!reasoningItem.open) return [state, NO_EVENTS] satisfies StepResult
      const lifecycle = Object.entries(reasoningItem.summaryParts)
        .filter((entry) => entry[1] === "active" || entry[1] === "can-conclude")
        .reduce(
          (lifecycle, entry) => Lifecycle.reasoningEnd(lifecycle, events, `${item.id}:${entry[0]}`, metadata),
          state.lifecycle,
        )
-      const { [item.id]: _removed, ...reasoningItems } = state.reasoningItems
-      return [{ ...state, lifecycle, reasoningItems }, events] satisfies StepResult
+      return [
+        {
+          ...state,
+          lifecycle,
+          reasoningItems: {
+            ...state.reasoningItems,
+            [item.id]: {
+              ...reasoningItem,
+              open: false,
+              encryptedContent: item.encrypted_content ?? reasoningItem.encryptedContent,
+            },
+          },
+        },
+        events,
+      ] satisfies StepResult
    }
    if (!state.lifecycle.reasoning.has(item.id)) {
      const lifecycle = Lifecycle.stepStart(state.lifecycle, events)
      events.push(LLMEvent.reasoningStart({ id: item.id, providerMetadata: metadata }))
      events.push(LLMEvent.reasoningEnd({ id: item.id, providerMetadata: metadata }))
-      return [{ ...state, lifecycle }, events] satisfies StepResult
+      return [
+        {
+          ...state,
+          lifecycle,
+          reasoningItems: {
+            ...state.reasoningItems,
+            [item.id]: {
+              open: false,
+              encryptedContent: item.encrypted_content,
+              summaryParts: { 0: "concluded" },
+              deltaIndexes: new Set(),
+            },
+          },
+        },
+        events,
+      ] satisfies StepResult
    }
    return [
      { ...state, lifecycle: Lifecycle.reasoningEnd(state.lifecycle, events, item.id, metadata) },
@@ -1139,7 +1205,7 @@ const onResponseFinish = Effect.fn("OpenResponses.onResponseFinish")(function* (
            if (
              id === undefined ||
              ((item.type !== "function_call" || !current.tools[id]) &&
-                (item.type !== "reasoning" || !current.reasoningItems[id]))
+                (item.type !== "reasoning" || !current.reasoningItems[id]?.open))
            )
              return Effect.succeed([current, events] satisfies StepResult)
            return onOutputItemDone(current, { type: "response.output_item.done", item }).pipe(
@@ -1256,6 +1322,13 @@ export const step = (state: ParserState, input: Event) => {
  if (event.type === "response.output_item.added") {
    if (event.item?.type === "message" && event.item.id === undefined)
      return ProviderShared.eventError(state.id, `${event.type} message is missing id`)
+    if (
+      event.item &&
+      isReasoningItem(event.item) &&
+      state.reasoningItems[event.item.id] === undefined &&
+      state.lifecycle.reasoning.size > 0
+    )
+      return ProviderShared.eventError(state.id, `${event.type} started reasoning before the previous item ended`)
    const id = event.item?.id ?? (event.item?.type === "function_call" ? event.item.call_id : undefined)
    return Effect.succeed(
      onOutputItemAdded(
@@ -1305,10 +1378,10 @@ export const initial = (request: LLMRequest, extension: Extension = BASE): Parse
  providerMetadataKey: request.model.route.providerMetadataKey ?? "openresponses",
  hasFunctionCall: false,
  tools: ToolStream.empty<string>(),
+  completedTools: new Set<string>(),
  lifecycle: Lifecycle.initial(),
  outputItems: {},
-  messageItems: new Set<string>(),
-  messagePhases: {},
+  message: undefined,
  reasoningItems: {},
 })

@@ -3,6 +3,7 @@ import { Tool } from "@opencode-ai/schema/tool"
 import { Route } from "../route/client.js"
 import { Auth } from "../route/auth.js"
 import { Endpoint } from "../route/endpoint.js"
+import { Framing } from "../route/framing.js"
 import { HttpTransport } from "../route/transport/index.js"
 import { Protocol } from "../route/protocol.js"
 import {
@@ -245,6 +246,8 @@ export const OpenAIChatEvent = Schema.StructWithRest(
  [Schema.Record(Schema.String, Schema.Unknown)],
 )
 export type OpenAIChatEvent = Schema.Schema.Type<typeof OpenAIChatEvent>
+const DONE = "[DONE]" as const
+const OpenAIChatStreamEvent = Schema.Union([Schema.Literal(DONE), Protocol.jsonEvent(OpenAIChatEvent)])
 type OpenAIChatRequestMessage = LLMRequest["messages"][number]

 interface PendingToolDelta {
@@ -997,33 +1000,12 @@ const step = (state: ParserState, event: OpenAIChatEvent) =>
      lifecycle = Lifecycle.reasoningStart(lifecycle, events, "reasoning-0", deltaMetadata)
    const reasoningEmitted = state.reasoningEmitted || lifecycle.reasoning.has("reasoning-0")

-    if (delta?.content) {
-      lifecycle = Lifecycle.reasoningEnd(
-        lifecycle,
-        events,
-        "reasoning-0",
-        reasoningMetadata(
-          state.providerMetadataKey,
-          reasoningField,
-          reasoningDetailsObserved ? state.reasoningDetails : undefined,
-        ),
-      )
-      lifecycle = Lifecycle.textDelta(lifecycle, events, "text-0", delta.content)
-    }
+    // Reasoning is one response-wide channel: it stays open alongside text and
+    // refusal output so late reasoning deltas and details join the same block,
+    // and `finishEvents` closes it once with the complete metadata.
+    if (delta?.content) lifecycle = Lifecycle.textDelta(lifecycle, events, "text-0", delta.content)

-    if (delta?.refusal) {
-      lifecycle = Lifecycle.reasoningEnd(
-        lifecycle,
-        events,
-        "reasoning-0",
-        reasoningMetadata(
-          state.providerMetadataKey,
-          reasoningField,
-          reasoningDetailsObserved ? state.reasoningDetails : undefined,
-        ),
-      )
-      lifecycle = Lifecycle.textDelta(lifecycle, events, "text-0", delta.refusal)
-    }
+    if (delta?.refusal) lifecycle = Lifecycle.textDelta(lifecycle, events, "text-0", delta.refusal)

    // Compatible providers may omit indexes. Prefer durable identity, then use
    // batch position for parallel deltas or the latest call for sparse chunks.
@@ -1129,10 +1111,12 @@ const finishEvents = Effect.fn("OpenAIChat.finishEvents")(function* (state: Pars
          state.finishReason.normalized === "stop" && hasToolCalls ? "tool-calls" : state.finishReason.normalized,
      }
    : { normalized: hasToolCalls ? ("tool-calls" as const) : ("stop" as const) }
+  // Snapshot details at publish time so the emitted event never observes later
+  // mutation of the accumulated `reasoningDetails` array.
  const metadata = reasoningMetadata(
    state.providerMetadataKey,
    state.reasoningField,
-    state.reasoningDetailsObserved ? state.reasoningDetails : undefined,
+    state.reasoningDetailsObserved ? [...state.reasoningDetails] : undefined,
  )
  const started =
    state.reasoningDetailsObserved && !state.reasoningEmitted
@@ -1166,7 +1150,7 @@ export const protocol = Protocol.make({
    from: fromRequest,
  },
  stream: {
-    event: Protocol.jsonEvent(OpenAIChatEvent),
+    event: OpenAIChatStreamEvent,
    initial: (request) => ({
      providerMetadataKey: request.model.route.providerMetadataKey ?? String(request.model.provider),
      tools: ToolStream.empty<number>(),
@@ -1180,12 +1164,14 @@ export const protocol = Protocol.make({
      nextToolIndex: 0,
      requireFinishReason: request.model.compatibility?.requireFinishReason ?? true,
    }),
-    step,
+    step: (state: ParserState, event) => (event === DONE ? Effect.succeed([state, []] as const) : step(state, event)),
+    terminal: (event) => event === DONE,
    onHalt: finishEvents,
  },
 })

-export const httpTransport = HttpTransport.sseJson.with<OpenAIChatBody>()
+export const framing = Framing.sseWithDone
+export const httpTransport = HttpTransport.sseJson.with<OpenAIChatBody>().with({ framing })

 export const route = Route.make({
  id: ADAPTER,
@@ -1,6 +1,5 @@
 import { Route, type RouteRoutedLanguageModelInput } from "../route/client.js"
 import { Endpoint } from "../route/endpoint.js"
-import { Framing } from "../route/framing.js"
 import * as OpenAIChat from "./openai-chat.js"

 const ADAPTER = "openai-compatible-chat"
@@ -19,7 +18,7 @@ export const route = Route.make({
  providerMetadataKey: "openai",
  protocol: OpenAIChat.protocol,
  endpoint: Endpoint.path("/chat/completions"),
-  framing: Framing.sse,
+  framing: OpenAIChat.framing,
 })

 export * as OpenAICompatibleChat from "./openai-compatible-chat.js"
@@ -207,15 +207,16 @@ export const errorText = (error: unknown) => {

 /**
 * `framing` step for Server-Sent Events. Decodes UTF-8, runs the SSE channel
- * decoder, optionally filters named events, and drops empty / `[DONE]`
- * keep-alive events so the protocol event schema sees one JSON string per
- * element. Retry control events are ignored without interrupting the stream.
+ * decoder, optionally filters named events, and drops empty events. `[DONE]`
+ * is dropped by default or retained for protocols that use it as their stream
+ * boundary. Retry control events are ignored without interrupting the stream.
 * Decoder failures become provider output errors so the public error channel
 * stays `AIError`.
 */
 export const sseFraming = (
  bytes: Stream.Stream<Uint8Array, AIError>,
  events?: ReadonlySet<string>,
+  includeDone = false,
 ): Stream.Stream<string, AIError> =>
  bytes.pipe(
    Stream.decodeText(),
@@ -240,7 +241,7 @@ export const sseFraming = (
      (event) =>
        (events === undefined || events.has(event.event)) &&
        event.data.length > 0 &&
-        (event.data !== "[DONE]" || (events !== undefined && event.event !== "message")),
+        (event.data !== "[DONE]" || includeDone || (events !== undefined && event.event !== "message")),
    ),
    Stream.map((event) => event.data),
  )
@@ -62,22 +62,31 @@ export const reasoningEnd = (
  events: LLMEvent[],
  id: string,
  providerMetadata?: ProviderMetadata,
+  /** Authoritative complete value; replaces accumulated deltas when present. */
+  text?: string,
 ): State => {
  if (!state.reasoning.has(id)) return state
  const stepped = stepStart(state, events)
-  events.push(LLMEvent.reasoningEnd({ id, providerMetadata }))
+  events.push(LLMEvent.reasoningEnd({ id, text, providerMetadata }))
  const reasoning = new Set(stepped.reasoning)
  reasoning.delete(id)
  return { ...stepped, reasoning }
 }

-export const textEnd = (state: State, events: LLMEvent[], id: string, providerMetadata?: ProviderMetadata): State => {
+export const textEnd = (
+  state: State,
+  events: LLMEvent[],
+  id: string,
+  providerMetadata?: ProviderMetadata,
+  /** Authoritative complete value; replaces accumulated deltas when present. */
+  text?: string,
+): State => {
  if (!state.text.has(id)) return state
  const stepped = stepStart(state, events)
-  events.push(LLMEvent.textEnd({ id, providerMetadata }))
-  const text = new Set(stepped.text)
-  text.delete(id)
-  return { ...stepped, text }
+  events.push(LLMEvent.textEnd({ id, text, providerMetadata }))
+  const open = new Set(stepped.text)
+  open.delete(id)
+  return { ...stepped, text: open }
 }

 const closeOpenBlocks = (state: State, events: LLMEvent[]): State => {
@@ -37,6 +37,7 @@ const patterns = [
  /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,
+  /range of input length should be/i,
  /too many tokens/i,
  /token limit exceeded/i,
  /request_too_large/i,
@@ -59,6 +60,7 @@ export const isContextOverflowFailure = (failure: unknown) =>

 const decodeJson = Schema.decodeUnknownOption(Schema.fromJsonString(Schema.Unknown))
 const QUOTA_CODES = new Set(["insufficient_quota", "usage_not_included", "billing_error"])
+const AUTH_CODES = new Set(["authentication_error", "permission_error"])
 const SERVER_CODES = new Set([
  "api_error",
  "internal_error",
@@ -74,7 +76,6 @@ const INVALID_REQUEST_CODES = new Set(["invalid_prompt", "invalid_request_error"
 const RATE_LIMIT_TEXT = /rate increased too quickly|rate[-_\s]?limit|too[_\s]?many[_\s]?requests/i
 const QUOTA_TEXT = /insufficient[-_\s]?quota|quota[-_\s]?exceeded/i
 const CONTENT_POLICY_TEXT = /content[-_\s]?policy|content_filter|safety/i
-const NETWORK_ERROR_TEXT = /network[-_\s]error/i

 export interface ProviderFailure {
  readonly message: string
@@ -90,8 +91,12 @@ export interface ProviderFailure {
  readonly rateLimit?: HttpRateLimitDetails | undefined
 }

-// Keep HTTP failures and provider-reported stream failures on one typed path so
-// session retry policy never needs provider-specific string matching.
+// Classification records affirmative evidence about a failure. Deterministic
+// failures need positive identification (a 4xx status, quota/auth/policy
+// signals); anything unrecognized stays UnknownProvider, which the session
+// retry policy treats as retry-eligible because transient failures arrive in
+// unpredictable shapes while deterministic rejections almost always carry a
+// status or known code.
 export function classifyProviderFailure(input: ProviderFailure): AIError["reason"] {
  const details = { message: input.message, body: input.rawBody, http: input.http, cause: input.cause }
  const body = input.rawBody ?? ""
@@ -116,46 +121,33 @@ export function classifyProviderFailure(input: ProviderFailure): AIError["reason
  if (CONTENT_POLICY_TEXT.test(text)) return new ContentPolicyError(details)
  if (codes.some((code) => QUOTA_CODES.has(code)) || (input.status === 429 && QUOTA_TEXT.test(text)))
    return new QuotaExceededError(details)
-  if (input.status === 401) return new AuthenticationError({ ...details, kind: "invalid" })
-  if (input.status === 403) return new AuthenticationError({ ...details, kind: "insufficient-permissions" })
-  if (codes.includes("authentication_error")) return new AuthenticationError({ ...details, kind: "invalid" })
-  if (codes.includes("permission_error"))
-    return new AuthenticationError({ ...details, kind: "insufficient-permissions" })
+  if (input.status === 401 || input.status === 403 || codes.some((code) => AUTH_CODES.has(code)))
+    return new AuthenticationError(details)
  if (
-    codes.some((code) => code.includes("rate_limit") || code === "too_many_requests" || code === "throttlingexception")
+    input.status === 429 ||
+    codes.some(
+      (code) => code.includes("rate_limit") || code === "too_many_requests" || code === "throttlingexception",
+    ) ||
+    RATE_LIMIT_TEXT.test(text)
  )
    return new RateLimitError({
      ...details,
      retryAfterMs: input.retryAfterMs,
      rateLimit: input.rateLimit,
    })
-  if (RATE_LIMIT_TEXT.test(text))
-    return new RateLimitError({
-      ...details,
-      retryAfterMs: input.retryAfterMs,
-      rateLimit: input.rateLimit,
-    })
-  if (NETWORK_ERROR_TEXT.test(text)) return new ProviderInternalError(details)
-  if (codes.some((code) => SERVER_CODES.has(code) || code.includes("exhausted") || code.includes("unavailable")))
-    return new ProviderInternalError({
-      ...details,
-      retryAfterMs: input.retryAfterMs,
-    })
-  if (input.status === 429) {
-    return new RateLimitError({
-      ...details,
-      retryAfterMs: input.retryAfterMs,
-      rateLimit: input.rateLimit,
-    })
-  }
-  if (input.status === 408 || input.status === 409 || (input.status !== undefined && input.status >= 500))
+  if (
+    input.status === 408 ||
+    input.status === 409 ||
+    (input.status !== undefined && input.status >= 500) ||
+    codes.some((code) => SERVER_CODES.has(code) || code.includes("exhausted") || code.includes("unavailable"))
+  )
    return new ProviderInternalError({
      ...details,
      retryAfterMs: input.retryAfterMs,
    })
  if (codes.some((code) => INVALID_REQUEST_CODES.has(code))) return new InvalidRequestError(details)
-  if (input.status === 400 || input.status === 404 || input.status === 413 || input.status === 422)
-    return new InvalidRequestError(details)
+  // Any remaining 4xx is a deterministic rejection of this request.
+  if (input.status !== undefined && input.status >= 400 && input.status < 500) return new InvalidRequestError(details)
  return new UnknownProviderError(details)
 }

@@ -5,7 +5,6 @@ import { ProviderShared } from "../protocols/shared.js"
 import { AuthOptions, type ProviderAuthOption } from "../route/auth-options.js"
 import { Route, type RouteDefaultsInput } from "../route/client.js"
 import { Endpoint } from "../route/endpoint.js"
-import { Framing } from "../route/framing.js"
 import { Protocol } from "../route/protocol.js"
 import { ProviderID, type ModelID, type LLMRequest } from "../schema/index.js"
 import { profiles } from "./openai-compatible-profile.js"
@@ -75,7 +74,7 @@ export const route = Route.make({
  providerMetadataKey: "openai",
  protocol,
  endpoint: Endpoint.path("/chat/completions", { baseURL: profiles.groq.baseURL }),
-  framing: Framing.sse,
+  framing: OpenAIChat.framing,
 })

 export const configure = (input: LanguageModelOptions = {}) => {
@@ -1,7 +1,6 @@
 import { Effect, Schema } from "effect"
 import { Route, type RouteDefaultsInput } from "../route/client.js"
 import { Endpoint } from "../route/endpoint.js"
-import { Framing } from "../route/framing.js"
 import { Protocol } from "../route/protocol.js"
 import { AuthOptions, type ProviderAuthOption } from "../route/auth-options.js"
 import { ProviderID, type CacheHint, type ModelID } from "../schema/index.js"
@@ -167,7 +166,7 @@ export const route = Route.make({
  providerMetadataKey: "openrouter",
  protocol,
  endpoint: Endpoint.path("/chat/completions", { baseURL: profile.baseURL }),
-  framing: Framing.sse,
+  framing: OpenAIChat.framing,
 })

 export const routes = [route]
@@ -139,7 +139,7 @@ const toAIError = (error: AuthError): AIError => {
    return new AIError({
      reason:
        error instanceof MissingCredentialError
-          ? new AuthenticationError({ message: error.message, cause: error, kind: "missing" })
+          ? new AuthenticationError({ message: error.message, cause: error })
          : new InvalidRequestError({ message: `Failed to resolve auth config: ${error.message}`, cause: error }),
    })
  }
@@ -8,8 +8,8 @@ import type { AIError } from "../schema/index.js"
 * `Framing` is the byte-stream-shaped seam between transport and protocol:
 *
 * - SSE (`Framing.sse`) — UTF-8 decode the body, run the SSE channel decoder,
- *   drop empty / `[DONE]` keep-alives. Each emitted frame is the JSON `data:`
- *   payload of one event.
+ *   and emit the `data:` payload of each non-empty event. The default drops
+ *   `[DONE]`; protocols that use it as a terminal select `sseWithDone`.
 * - AWS event stream — length-prefixed binary frames with CRC checksums.
 *   Each emitted frame is one parsed binary event record.
 *
@@ -26,6 +26,12 @@ export interface Definition<Frame> {
 /** Server-Sent Events framing. Used by every JSON-streaming HTTP provider. */
 export const sse: Definition<string> = { id: "sse", frame: ProviderShared.sseFraming }

+/** Server-Sent Events framing that retains the conventional `[DONE]` sentinel. */
+export const sseWithDone: Definition<string> = {
+  id: "sse",
+  frame: (bytes) => ProviderShared.sseFraming(bytes, undefined, true),
+}
+
 /** SSE framing restricted to protocol-recognized event names. */
 export const sseEvents = (events: ReadonlySet<string>): Definition<string> => ({
  id: "sse",
@@ -44,10 +44,7 @@ export class NoRouteError extends Schema.TaggedError<NoRouteError>("AI.Error.NoR

 export class AuthenticationError extends Schema.TaggedError<AuthenticationError>("AI.Error.Authentication")(
  "Authentication",
-  {
-    ...ReasonFields,
-    kind: Schema.Literals(["missing", "invalid", "expired", "insufficient-permissions", "unknown"]),
-  },
+  ReasonFields,
 ) {}

 export class RateLimitError extends Schema.TaggedError<RateLimitError>("AI.Error.RateLimit")("RateLimit", {
@@ -112,6 +112,8 @@ export type TextDelta = Schema.Schema.Type<typeof TextDelta>
 export const TextEnd = Schema.Struct({
  type: Schema.tag("text-end"),
  id: ContentBlockID,
+  /** Authoritative complete value; replaces accumulated deltas when present. */
+  text: Schema.optional(Schema.String),
  providerMetadata: Schema.optional(ProviderMetadata),
 }).annotate({ identifier: "LLM.Event.TextEnd" })
 export type TextEnd = Schema.Schema.Type<typeof TextEnd>
@@ -134,6 +136,8 @@ export type ReasoningDelta = Schema.Schema.Type<typeof ReasoningDelta>
 export const ReasoningEnd = Schema.Struct({
  type: Schema.tag("reasoning-end"),
  id: ContentBlockID,
+  /** Authoritative complete value; replaces accumulated deltas when present. */
+  text: Schema.optional(Schema.String),
  providerMetadata: Schema.optional(ProviderMetadata),
 }).annotate({ identifier: "LLM.Event.ReasoningEnd" })
 export type ReasoningEnd = Schema.Schema.Type<typeof ReasoningEnd>
@@ -328,17 +332,32 @@ export const LLMEvent = Object.assign(llmEventTagged, {
 })
 export type LLMEvent = Schema.Schema.Type<typeof llmEventTagged>

+/** Joins deltas per fragment, letting an authoritative end value replace that fragment's accumulated deltas. */
+const joinFragments = <Delta extends { id: string; text: string }, End extends { id: string; text?: string }>(
+  events: ReadonlyArray<LLMEvent>,
+  isDelta: (event: LLMEvent) => event is Extract<LLMEvent, Delta>,
+  isEnd: (event: LLMEvent) => event is Extract<LLMEvent, End>,
+) => {
+  const order: string[] = []
+  const parts = new Map<string, string>()
+  for (const event of events) {
+    if (isDelta(event)) {
+      if (!parts.has(event.id)) order.push(event.id)
+      parts.set(event.id, (parts.get(event.id) ?? "") + event.text)
+    }
+    if (isEnd(event) && event.text !== undefined) {
+      if (!parts.has(event.id)) order.push(event.id)
+      parts.set(event.id, event.text)
+    }
+  }
+  return order.map((id) => parts.get(id)).join("")
+}
+
 const responseText = (events: ReadonlyArray<LLMEvent>) =>
-  events
-    .filter(LLMEvent.is.textDelta)
-    .map((event) => event.text)
-    .join("")
+  joinFragments(events, LLMEvent.is.textDelta, LLMEvent.is.textEnd)

 const responseReasoning = (events: ReadonlyArray<LLMEvent>) =>
-  events
-    .filter(LLMEvent.is.reasoningDelta)
-    .map((event) => event.text)
-    .join("")
+  joinFragments(events, LLMEvent.is.reasoningDelta, LLMEvent.is.reasoningEnd)

 const responseUsage = (events: ReadonlyArray<LLMEvent>) =>
  events.reduce<Usage | undefined>(
@@ -445,10 +464,11 @@ const reduceTextDelta = (state: ResponseState, event: TextDelta): ResponseState
 const reduceTextEnd = (state: ResponseState, event: TextEnd): ResponseState => {
  const current = state.textParts[event.id]
  if (!current) return state
+  const text = event.text ?? current.text
  const providerMetadata = event.providerMetadata ?? current.providerMetadata
  return {
-    ...replaceContent(state, current.contentIndex, textContent(current.text, providerMetadata)),
-    textParts: { ...state.textParts, [event.id]: { ...current, providerMetadata } },
+    ...replaceContent(state, current.contentIndex, textContent(text, providerMetadata)),
+    textParts: { ...state.textParts, [event.id]: { ...current, text, providerMetadata } },
  }
 }

@@ -478,10 +498,11 @@ const reduceReasoningDelta = (state: ResponseState, event: ReasoningDelta): Resp
 const reduceReasoningEnd = (state: ResponseState, event: ReasoningEnd): ResponseState => {
  const current = state.reasoningParts[event.id]
  if (!current) return state
+  const text = event.text ?? current.text
  const providerMetadata = event.providerMetadata ?? current.providerMetadata
  return {
-    ...replaceContent(state, current.contentIndex, reasoningContent(current.text, providerMetadata)),
-    reasoningParts: { ...state.reasoningParts, [event.id]: { ...current, providerMetadata } },
+    ...replaceContent(state, current.contentIndex, reasoningContent(text, providerMetadata)),
+    reasoningParts: { ...state.reasoningParts, [event.id]: { ...current, text, providerMetadata } },
  }
 }

@@ -579,12 +600,12 @@ export class LLMResponse extends Schema.Class<LLMResponse>("LLM.Response")({
  usage: Schema.optional(Usage),
  finishReason: FinishReasonDetails,
 }) {
-  /** Concatenated assistant text assembled from streamed `text-delta` events. */
+  /** Concatenated assistant text; each fragment's `text-end` value replaces its accumulated deltas when present. */
  get text() {
    return responseText(this.events)
  }

-  /** Concatenated reasoning text assembled from streamed `reasoning-delta` events. */
+  /** Concatenated reasoning text; each fragment's `reasoning-end` value replaces its accumulated deltas when present. */
  get reasoning() {
    return responseReasoning(this.events)
  }
@@ -1,6 +1,6 @@
 export * as TestLLM from "./testing.js"

-import { LLMClient, type Interface as LLMClientShape } from "./route/client.js"
+import { LLMClient } from "./route/client.js"
 import {
  LLMEvent,
  LLMResponse,
@@ -16,13 +16,33 @@ export type Response = readonly LLMEvent[] | Stream.Stream<LLMEvent, AIError>

 export type Gate = Readonly<{ started: Effect.Effect<void>; release: Effect.Effect<void> }>

+type ClientInterface = Context.Service.Shape<typeof LLMClient.Service>
+
+export type Responder = (request: LLMRequest) => Response
+
+export interface TestInterface extends ClientInterface {
+  /** Returns a snapshot of requests observed at execution time. */
+  readonly requests: () => Effect.Effect<readonly LLMRequest[]>
+  readonly push: (...responses: readonly Response[]) => Effect.Effect<void>
+  /** Replaces the fallback without changing queued responses. */
+  readonly always: (response: Response) => Effect.Effect<void>
+  /** Answers requests after the one-shot queue is exhausted; receives the original request. */
+  readonly serve: (responder: Responder) => Effect.Effect<void>
+  /** Waits for request arrivals, not output or completion. */
+  readonly wait: (count: number) => Effect.Effect<void>
+  readonly gate: () => Effect.Effect<Gate, never, Scope.Scope>
+}
+
+export class Test extends Context.Service<Test, TestInterface>()("@opencode/ai/TestLLM/Test") {}
+
+/** @deprecated Use TestInterface through Test and testLayer. */
 export interface Interface {
  readonly requests: LLMRequest[]
  readonly push: (...responses: readonly Response[]) => Effect.Effect<void>
  readonly always: (response: Response) => Effect.Effect<void>
  readonly wait: (count: number) => Effect.Effect<void>
  readonly gate: Effect.Effect<Gate, never, Scope.Scope>
-  readonly client: LLMClientShape
+  readonly client: ClientInterface
 }

 export interface LayerOptions {
@@ -31,6 +51,7 @@ export interface LayerOptions {
  readonly fallback?: Response
 }

+/** @deprecated Use Test and testLayer for normal client methods and test controls. */
 export class Service extends Context.Service<Service, Interface>()("@opencode/ai/TestLLM") {}

 export const complete = (
@@ -80,59 +101,64 @@ export const hangAfter = (...events: readonly LLMEvent[]) => Stream.concat(Strea

 const toStream = (response: Response) => (Stream.isStream(response) ? response : Stream.fromIterable(response))

-export const layer = (options: LayerOptions = {}) =>
-  Layer.effect(
-    Service,
-    Effect.gen(function* () {
-      const requests: LLMRequest[] = []
-      const responses: Response[] = []
-      let started = Deferred.makeUnsafe<void>()
-      let fallback = options.fallback
-      let activeGate: { readonly started: Queue.Queue<void>; readonly release: Latch.Latch } | undefined
-      const wait = (count: number): Effect.Effect<void> =>
-        Effect.suspend(() =>
-          requests.length >= count ? Effect.void : Deferred.await(started).pipe(Effect.andThen(wait(count))),
-        )
+const make = (options: LayerOptions) =>
+  Effect.sync(() => {
+    const requests: LLMRequest[] = []
+    const responses: Response[] = []
+    let started = Deferred.makeUnsafe<void>()
+    let fallback: Response | Responder | undefined = options.fallback
+    let activeGate: { readonly started: Queue.Queue<void>; readonly release: Latch.Latch } | undefined
+    const wait = (count: number): Effect.Effect<void> =>
+      Effect.suspend(() =>
+        requests.length >= count ? Effect.void : Deferred.await(started).pipe(Effect.andThen(wait(count))),
+      )

-      const stream = ((request: LLMRequest) => {
-        requests.push(options.transformRequest?.(request) ?? request)
+    const stream: ClientInterface["stream"] = (request) =>
+      Stream.suspend(() => {
+        const count = requests.push(options.transformRequest?.(request) ?? request)
        const waiting = started
        started = Deferred.makeUnsafe()
-        Deferred.doneUnsafe(waiting, Effect.void)
-        const response = responses.shift() ?? fallback
-        if (!response) return Stream.die(new Error(`TestLLM has no response for request ${requests.length}`))
-        const streamed = toStream(response)
        const gate = activeGate
-        if (!gate) return streamed
-        return Stream.unwrap(
-          Queue.offer(gate.started, undefined).pipe(Effect.andThen(gate.release.await), Effect.as(streamed)),
-        )
-      }) as LLMClientShape["stream"]
-      const client = LLMClient.Service.of({
-        stream,
-        generate: (request) =>
-          stream(request).pipe(
-            Stream.runFold(LLMResponse.empty, LLMResponse.reduce),
-            Effect.flatMap((state) => {
-              const response = LLMResponse.complete(state)
-              if (response) return Effect.succeed(response)
-              return Effect.die("TestLLM response ended without a terminal finish event")
-            }),
-          ),
+        try {
+          const response = responses.shift() ?? (typeof fallback === "function" ? fallback(request) : fallback)
+          if (!response) return Stream.die(new Error(`TestLLM has no response for request ${count}`))
+          const streamed = toStream(response)
+          if (!gate) return streamed
+          return Stream.unwrap(
+            Queue.offer(gate.started, undefined).pipe(Effect.andThen(gate.release.await), Effect.as(streamed)),
+          )
+        } finally {
+          // Waiters can resume synchronously; assign the reply and gate before notifying them.
+          Deferred.doneUnsafe(waiting, Effect.void)
+        }
      })
-
-      return Service.of({
-        requests,
-        push: (...input) =>
-          Effect.sync(() => {
-            responses.push(...input)
+    const test = Test.of({
+      stream,
+      generate: (request) =>
+        stream(request).pipe(
+          Stream.runFold(LLMResponse.empty, LLMResponse.reduce),
+          Effect.flatMap((state) => {
+            const response = LLMResponse.complete(state)
+            if (response) return Effect.succeed(response)
+            return Effect.die("TestLLM response ended without a terminal finish event")
          }),
-        always: (response) =>
-          Effect.sync(() => {
-            fallback = response
-          }),
-        wait,
-        gate: Effect.gen(function* () {
+        ),
+      requests: () => Effect.sync(() => [...requests]),
+      push: (...input) =>
+        Effect.sync(() => {
+          responses.push(...input)
+        }),
+      always: (response) =>
+        Effect.sync(() => {
+          fallback = response
+        }),
+      serve: (responder) =>
+        Effect.sync(() => {
+          fallback = responder
+        }),
+      wait,
+      gate: () =>
+        Effect.gen(function* () {
          const gate = {
            started: yield* Effect.acquireRelease(Queue.unbounded<void>(), Queue.shutdown),
            release: yield* Latch.make(),
@@ -147,11 +173,36 @@ export const layer = (options: LayerOptions = {}) =>
            release,
          }
        }),
-        client,
-      })
-    }),
+    })
+
+    return { test, requests }
+  })
+
+/** Provides one shared implementation under the normal client and test-control tags. */
+export const testLayer = (options: LayerOptions = {}) =>
+  Layer.effectContext(
+    Effect.map(make(options), (implementation) =>
+      Context.make(LLMClient.Service, implementation.test).pipe(Context.add(Test, implementation.test)),
+    ),
  )

+/** @deprecated Use testLayer; retained for published callers of the legacy control interface. */
+export const layer = (options: LayerOptions = {}) =>
+  Layer.effect(
+    Service,
+    Effect.map(make(options), (implementation) =>
+      Service.of({
+        requests: implementation.requests,
+        push: implementation.test.push,
+        always: implementation.test.always,
+        wait: implementation.test.wait,
+        gate: implementation.test.gate(),
+        client: implementation.test,
+      }),
+    ),
+  )
+
+/** @deprecated testLayer provides LLMClient.Service directly. */
 export const clientLayer = Layer.effect(
  LLMClient.Service,
  Effect.map(Service, (service) => service.client),
@@ -1,4 +1,4 @@
-import { describe, expect } from "bun:test"
+import { describe, expect, test } from "bun:test"
 import { Effect, Schema, Stream } from "effect"
 import { LLM, LLMRequest, LLMResponse } from "../src/index.js"
 import { Route, Endpoint, LLMClient, Protocol, type FramingDef } from "../src/route.js"
@@ -148,15 +148,13 @@ describe("llm route", () => {
    }),
  )

-  it.effect("builds models from configured routes", () =>
-    Effect.gen(function* () {
-      const configured = fake.with({ provider: "fake-provider", endpoint: { baseURL: "https://fake.local" } })
+  test("builds models from configured routes", () => {
+    const configured = fake.with({ provider: "fake-provider", endpoint: { baseURL: "https://fake.local" } })

-      expect(configured.model({ id: "fake-model" })).toMatchObject({
-        provider: "fake-provider",
-      })
-    }),
-  )
+    expect(configured.model({ id: "fake-model" })).toMatchObject({
+      provider: "fake-provider",
+    })
+  })

  it.effect("does not register duplicate route ids globally", () =>
    Effect.gen(function* () {
@@ -1,10 +1,10 @@
 import { describe, expect } from "bun:test"
-import { Deferred, Effect, Fiber, Layer, Ref, Stream } from "effect"
-import { Headers, HttpClient, HttpClientError, HttpClientRequest, HttpClientResponse } from "effect/unstable/http"
+import { Deferred, Effect, Fiber, Ref, Stream } from "effect"
+import { Headers, HttpClientError, HttpClientRequest } from "effect/unstable/http"
 import { LLM, AIError, HttpContext, InvalidProviderOutputError, TransportError } from "../src/index.js"
 import { LLMClient, RequestExecutor, WebSocketTransport, type WebSocketChannelExecutor } from "../src/route.js"
-import * as OpenAIChat from "../src/protocols/openai-chat.js"
-import * as OpenAI from "../src/providers/openai.js"
+import { route } from "../src/protocols/openai-chat.js"
+import { configure } from "../src/providers/openai.js"
 import { dynamicResponse, fixedResponse, systemError } from "./lib/http.js"
 import { deltaChunk } from "./lib/openai-chunks.js"
 import { sseEvents, sseRaw } from "./lib/sse.js"
@@ -18,47 +18,6 @@ const secretRequest = HttpClientRequest.post("https://provider.test/v1/chat?api_
  HttpClientRequest.setHeaders(Headers.fromInput({ authorization: "Bearer header-secret-456" })),
 )

-const responsesLayer = (responses: ReadonlyArray<Response>) =>
-  RequestExecutor.layer.pipe(
-    Layer.provide(
-      Layer.unwrap(
-        Effect.gen(function* () {
-          const cursor = yield* Ref.make(0)
-          return Layer.succeed(
-            HttpClient.HttpClient,
-            HttpClient.make((request) =>
-              Effect.gen(function* () {
-                const index = yield* Ref.getAndUpdate(cursor, (value) => value + 1)
-                return HttpClientResponse.fromWeb(request, responses[index] ?? responses[responses.length - 1])
-              }),
-            ),
-          )
-        }),
-      ),
-    ),
-  )
-
-const countedResponsesLayer = (attempts: Ref.Ref<number>, responses: ReadonlyArray<Response>) =>
-  RequestExecutor.layer.pipe(
-    Layer.provide(
-      Layer.unwrap(
-        Effect.gen(function* () {
-          const cursor = yield* Ref.make(0)
-          return Layer.succeed(
-            HttpClient.HttpClient,
-            HttpClient.make((request) =>
-              Effect.gen(function* () {
-                yield* Ref.update(attempts, (value) => value + 1)
-                const index = yield* Ref.getAndUpdate(cursor, (value) => value + 1)
-                return HttpClientResponse.fromWeb(request, responses[index] ?? responses[responses.length - 1])
-              }),
-            ),
-          )
-        }),
-      ),
-    ),
-  )
-
 const expectAIError = (error: unknown) => {
  expect(error).toBeInstanceOf(AIError)
  if (!(error instanceof AIError)) throw new Error("expected AIError")
@@ -107,19 +66,17 @@ describe("RequestExecutor", () => {
        return yield* executor.execute(request).pipe(Effect.flip)
      }).pipe(
        Effect.provide(
-          responsesLayer([
-            new Response(
-              new ReadableStream({
-                start(controller) {
-                  controller.error(cause)
-                },
-              }),
-              {
-                status: 503,
-                headers: { "x-request-id": "req_failed_body" },
+          fixedResponse(
+            new ReadableStream({
+              start(controller) {
+                controller.error(cause)
              },
-            ),
-          ]),
+            }),
+            {
+              status: 503,
+              headers: { "x-request-id": "req_failed_body" },
+            },
+          ),
        ),
      )

@@ -148,15 +105,14 @@ describe("RequestExecutor", () => {
      })
    }).pipe(
      Effect.provide(
-        responsesLayer([
-          new Response(
-            new ReadableStream({
-              start(controller) {
-                controller.error(systemError("ECONNRESET", "disconnected query-secret-123 header-secret-456"))
-              },
-            }),
-          ),
-        ]),
+        fixedResponse(
+          new ReadableStream({
+            start(controller) {
+              controller.error(systemError("ECONNRESET", "disconnected query-secret-123 header-secret-456"))
+            },
+          }),
+          {},
+        ),
      ),
    ),
  )
@@ -176,15 +132,14 @@ describe("RequestExecutor", () => {
      })
    }).pipe(
      Effect.provide(
-        responsesLayer([
-          new Response(
-            new ReadableStream({
-              pull(controller) {
-                controller.error(new TypeError("fetch failed", { cause: systemError("ECONNRESET", "socket closed") }))
-              },
-            }),
-          ),
-        ]),
+        fixedResponse(
+          new ReadableStream({
+            pull(controller) {
+              controller.error(new TypeError("fetch failed", { cause: systemError("ECONNRESET", "socket closed") }))
+            },
+          }),
+          {},
+        ),
      ),
    ),
  )
@@ -200,7 +155,7 @@ describe("RequestExecutor", () => {
      expect(error.message).toBe("plugin rejected request")
      expect(error.reason.cause).toBeInstanceOf(Error)
      expect(error.reason.http).toBeUndefined()
-    }).pipe(Effect.provide(responsesLayer([]))),
+    }).pipe(Effect.provide(dynamicResponse(() => Effect.die(new Error("unexpected HTTP request"))))),
  )

  it.effect("reports the request sent by middleware", () =>
@@ -249,11 +204,9 @@ describe("RequestExecutor", () => {
      expect(error.reason).toMatchObject({ _tag: "InvalidRequest", classification: "context-overflow" })
    }).pipe(
      Effect.provide(
-        responsesLayer([
-          new Response('{"error":{"code":"context_length_exceeded","message":"prompt too long"}}', {
-            status: 400,
-          }),
-        ]),
+        fixedResponse('{"error":{"code":"context_length_exceeded","message":"prompt too long"}}', {
+          status: 400,
+        }),
      ),
    ),
  )
@@ -269,7 +222,7 @@ describe("RequestExecutor", () => {
        classification: "payload-too-large",
      })
      expect(error.reason.http?.status).toBe(413)
-    }).pipe(Effect.provide(responsesLayer([new Response("request too large", { status: 413 })]))),
+    }).pipe(Effect.provide(fixedResponse("request too large", { status: 413 }))),
  )

  it.effect("classifies Anthropic request_too_large as context overflow", () =>
@@ -285,11 +238,9 @@ describe("RequestExecutor", () => {
      expect(error.reason.http?.status).toBe(413)
    }).pipe(
      Effect.provide(
-        responsesLayer([
-          new Response('{"error":{"type":"request_too_large","message":"Request exceeds the maximum size"}}', {
-            status: 413,
-          }),
-        ]),
+        fixedResponse('{"error":{"type":"request_too_large","message":"Request exceeds the maximum size"}}', {
+          status: 413,
+        }),
      ),
    ),
  )
@@ -303,7 +254,7 @@ describe("RequestExecutor", () => {
      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")
-    }).pipe(Effect.provide(responsesLayer([new Response("invalid parameter", { status: 400 })]))),
+    }).pipe(Effect.provide(fixedResponse("invalid parameter", { status: 400 }))),
  )

  it.effect("preserves structured provider messages from large error bodies", () =>
@@ -317,15 +268,13 @@ describe("RequestExecutor", () => {
      expect(error.reason.body).toContain(largeProviderMessage)
    }).pipe(
      Effect.provide(
-        responsesLayer([
-          new Response(
-            JSON.stringify({
-              model: "gpt-5.6-sol",
-              error: { type: "invalid_request", message: largeProviderMessage },
-            }),
-            { status: 400 },
-          ),
-        ]),
+        fixedResponse(
+          JSON.stringify({
+            model: "test-model",
+            error: { type: "invalid_request", message: largeProviderMessage },
+          }),
+          { status: 400 },
+        ),
      ),
    ),
  )
@@ -340,7 +289,7 @@ describe("RequestExecutor", () => {
        _tag: "InvalidRequest",
      })
      expect(error.message).toBe("Provider request failed with HTTP 400")
-    }).pipe(Effect.provide(responsesLayer([new Response('{"error":{"message":"  "}}', { status: 400 })]))),
+    }).pipe(Effect.provide(fixedResponse('{"error":{"message":"  "}}', { status: 400 }))),
  )

  it.effect("classifies provider rate limits hidden behind HTTP 400", () =>
@@ -352,7 +301,7 @@ describe("RequestExecutor", () => {

          expectAIError(error)
          expect(error.reason).toMatchObject({ _tag: "RateLimit" })
-        }).pipe(Effect.provide(responsesLayer([new Response(body, { status: 400 })])))
+        }).pipe(Effect.provide(fixedResponse(body, { status: 400 })))

      yield* classify("Request rate increased too quickly")
      yield* classify('{"type":"error","error":{"type":"too_many_requests"}}')
@@ -369,7 +318,7 @@ describe("RequestExecutor", () => {

          expectAIError(error)
          expect(error.reason).toMatchObject({ _tag: "ProviderInternal" })
-        }).pipe(Effect.provide(responsesLayer([new Response(body, { status: 400 })])))
+        }).pipe(Effect.provide(fixedResponse(body, { status: 400 })))

      yield* classify('{"code":"resource_exhausted"}')
      yield* classify('{"code":"service_unavailable"}')
@@ -399,12 +348,10 @@ describe("RequestExecutor", () => {
      expect(error.reason.body).toBe("rate limited")
    }).pipe(
      Effect.provide(
-        responsesLayer([
-          new Response("rate limited", {
-            status: 429,
-            headers: { "retry-after-ms": "0", "x-request-id": "req_123", "x-api-key": "secret" },
-          }),
-        ]),
+        fixedResponse("rate limited", {
+          status: 429,
+          headers: { "retry-after-ms": "0", "x-request-id": "req_123", "x-api-key": "secret" },
+        }),
      ),
    ),
  )
@@ -417,7 +364,7 @@ describe("RequestExecutor", () => {
      expectAIError(error)
      expect(error.reason.http?.headers["x-safe"]).toBe("response-secret")
    }).pipe(
-      Effect.provide(responsesLayer([new Response("bad", { status: 400, headers: { "x-safe": "response-secret" } })])),
+      Effect.provide(fixedResponse("bad", { status: 400, headers: { "x-safe": "response-secret" } })),
      Effect.provideService(Headers.CurrentRedactedNames, ["x-safe"]),
    ),
  )
@@ -437,20 +384,18 @@ describe("RequestExecutor", () => {
      })
    }).pipe(
      Effect.provide(
-        responsesLayer([
-          new Response("rate limited", {
-            status: 429,
-            headers: {
-              "retry-after-ms": "0",
-              "x-ratelimit-limit-requests": "500",
-              "x-ratelimit-limit-tokens": "30000",
-              "x-ratelimit-remaining-requests": "499",
-              "x-ratelimit-remaining-tokens": "29900",
-              "x-ratelimit-reset-requests": "1s",
-              "x-ratelimit-reset-tokens": "10s",
-            },
-          }),
-        ]),
+        fixedResponse("rate limited", {
+          status: 429,
+          headers: {
+            "retry-after-ms": "0",
+            "x-ratelimit-limit-requests": "500",
+            "x-ratelimit-limit-tokens": "30000",
+            "x-ratelimit-remaining-requests": "499",
+            "x-ratelimit-remaining-tokens": "29900",
+            "x-ratelimit-reset-requests": "1s",
+            "x-ratelimit-reset-tokens": "10s",
+          },
+        }),
      ),
    ),
  )
@@ -470,20 +415,18 @@ describe("RequestExecutor", () => {
      })
    }).pipe(
      Effect.provide(
-        responsesLayer([
-          new Response("rate limited", {
-            status: 429,
-            headers: {
-              "retry-after-ms": "0",
-              "anthropic-ratelimit-requests-limit": "100",
-              "anthropic-ratelimit-requests-remaining": "12",
-              "anthropic-ratelimit-requests-reset": "2026-05-06T12:00:00Z",
-              "anthropic-ratelimit-input-tokens-limit": "10000",
-              "anthropic-ratelimit-input-tokens-remaining": "9000",
-              "anthropic-ratelimit-input-tokens-reset": "2026-05-06T12:00:10Z",
-            },
-          }),
-        ]),
+        fixedResponse("rate limited", {
+          status: 429,
+          headers: {
+            "retry-after-ms": "0",
+            "anthropic-ratelimit-requests-limit": "100",
+            "anthropic-ratelimit-requests-remaining": "12",
+            "anthropic-ratelimit-requests-reset": "2026-05-06T12:00:00Z",
+            "anthropic-ratelimit-input-tokens-limit": "10000",
+            "anthropic-ratelimit-input-tokens-remaining": "9000",
+            "anthropic-ratelimit-input-tokens-reset": "2026-05-06T12:00:10Z",
+          },
+        }),
      ),
    ),
  )
@@ -496,10 +439,14 @@ describe("RequestExecutor", () => {
        return yield* executor.execute(request).pipe(Effect.flip)
      }).pipe(
        Effect.provide(
-          countedResponsesLayer(attempts, [
-            new Response("busy", { status: 503, headers: { "retry-after-ms": "0" } }),
-            new Response("ok", { status: 200 }),
-          ]),
+          dynamicResponse((input) =>
+            Effect.gen(function* () {
+              const attempt = yield* Ref.getAndUpdate(attempts, (value) => value + 1)
+              return attempt === 0
+                ? input.respond("busy", { status: 503, headers: { "retry-after-ms": "0" } })
+                : input.respond("ok", { status: 200 })
+            }),
+          ),
        ),
      )

@@ -522,12 +469,10 @@ describe("RequestExecutor", () => {
          expect(error.reason.http?.status).toBe(status)
        }).pipe(
          Effect.provide(
-            responsesLayer([
-              new Response("provider failure", {
-                status,
-                headers: { "retry-after-ms": "0" },
-              }),
-            ]),
+            fixedResponse("provider failure", {
+              status,
+              headers: { "retry-after-ms": "0" },
+            }),
          ),
        )

@@ -538,20 +483,28 @@ describe("RequestExecutor", () => {

  it.effect("preserves large authentication error bodies", () =>
    Effect.gen(function* () {
-      const executor = yield* RequestExecutor.Service
-      const error = yield* executor.execute(request).pipe(Effect.flip)
+      const attempts = yield* Ref.make(0)
+      const error = yield* Effect.gen(function* () {
+        const executor = yield* RequestExecutor.Service
+        return yield* executor.execute(request).pipe(Effect.flip)
+      }).pipe(
+        Effect.provide(
+          dynamicResponse((input) =>
+            Effect.gen(function* () {
+              const attempt = yield* Ref.getAndUpdate(attempts, (value) => value + 1)
+              return attempt === 0
+                ? input.respond("x".repeat(20_000), { status: 401 })
+                : input.respond("should not retry", { status: 200 })
+            }),
+          ),
+        ),
+      )

      expectAIError(error)
      expect(error.reason).toMatchObject({ _tag: "Authentication" })
      expect(error.reason.body).toHaveLength(20_000)
-    }).pipe(
-      Effect.provide(
-        responsesLayer([
-          new Response("x".repeat(20_000), { status: 401 }),
-          new Response("should not retry", { status: 200 }),
-        ]),
-      ),
-    ),
+      expect(yield* Ref.get(attempts)).toBe(1)
+    }),
  )

  it.effect("preserves response body fields", () =>
@@ -563,11 +516,9 @@ describe("RequestExecutor", () => {
      expect(error.reason.body).toBe('{"error":{"message":"bad","key":"body-secret","detail":"api_key=query-secret"}}')
    }).pipe(
      Effect.provide(
-        responsesLayer([
-          new Response('{"error":{"message":"bad","key":"body-secret","detail":"api_key=query-secret"}}', {
-            status: 400,
-          }),
-        ]),
+        fixedResponse('{"error":{"message":"bad","key":"body-secret","detail":"api_key=query-secret"}}', {
+          status: 400,
+        }),
      ),
    ),
  )
@@ -581,9 +532,7 @@ describe("RequestExecutor", () => {
      expect(error.reason.body).toBe("provider echoed query-secret-123 and authorization header-secret-456")
    }).pipe(
      Effect.provide(
-        responsesLayer([
-          new Response("provider echoed query-secret-123 and authorization header-secret-456", { status: 400 }),
-        ]),
+        fixedResponse("provider echoed query-secret-123 and authorization header-secret-456", { status: 400 }),
      ),
    ),
  )
@@ -591,9 +540,7 @@ describe("RequestExecutor", () => {
  it.effect("does not re-execute after a successful response reaches stream parsing", () =>
    Effect.gen(function* () {
      const attempts = yield* Ref.make(0)
-      const model = OpenAIChat.route
-        .with({ endpoint: { baseURL: "https://api.openai.test/v1" } })
-        .model({ id: "gpt-4o-mini" })
+      const model = route.with({ endpoint: { baseURL: "https://api.openai.test/v1" } }).model({ id: "gpt-4o-mini" })
      const error = yield* LLMClient.generate(LLM.request({ model, prompt: "Say hello." })).pipe(
        Effect.provide(
          dynamicResponse((input) =>
@@ -624,9 +571,10 @@ describe("RequestExecutor", () => {
 })

 describe("WebSocket channel execution", () => {
-  const model = OpenAI.configure({ baseURL: "https://api.openai.test/v1/", apiKey: "test" }).responses("gpt-4.1-mini")
+  const model = configure({ baseURL: "https://api.openai.test/v1/", apiKey: "test" }).responses("gpt-4.1-mini")
  const request = LLM.request({ model, prompt: "Say hello." })
  const frames = [
+    JSON.stringify({ type: "response.output_item.added", item: { type: "message", id: "msg_1" } }),
    JSON.stringify({ type: "response.output_text.delta", item_id: "msg_1", delta: "Hi" }),
    JSON.stringify({ type: "response.completed", response: { id: "resp_1" } }),
  ]
@@ -32,6 +32,8 @@ describe("public exports", () => {
    expect(Provider.make).toBeFunction()
    expect(ProviderSubpath.make).toBe(Provider.make)
    expect(TestLLM.layer).toBeFunction()
+    expect(TestLLM.testLayer).toBeFunction()
+    expect(TestLLM.Test.of).toBeFunction()
  })

  test("route barrel exposes route-authoring APIs", () => {
@@ -10,7 +10,7 @@
      "transport": "http",
      "request": {
        "method": "POST",
-        "url": "https://api.anthropic.com/v1/messages",
+        "url": "https://api.anthropic.com/v1/messages?beta=true",
        "headers": {
          "anthropic-version": "2023-06-01",
          "content-type": "application/json"
@@ -29,7 +29,7 @@
      "transport": "http",
      "request": {
        "method": "POST",
-        "url": "https://api.anthropic.com/v1/messages",
+        "url": "https://api.anthropic.com/v1/messages?beta=true",
        "headers": {
          "anthropic-version": "2023-06-01",
          "content-type": "application/json"
@@ -10,7 +10,7 @@
      "transport": "http",
      "request": {
        "method": "POST",
-        "url": "https://api.anthropic.com/v1/messages",
+        "url": "https://api.anthropic.com/v1/messages?beta=true",
        "headers": {
          "anthropic-version": "2023-06-01",
          "content-type": "application/json"
@@ -29,7 +29,7 @@
      "transport": "http",
      "request": {
        "method": "POST",
-        "url": "https://api.anthropic.com/v1/messages",
+        "url": "https://api.anthropic.com/v1/messages?beta=true",
        "headers": {
          "anthropic-version": "2023-06-01",
          "content-type": "application/json"
@@ -24,7 +24,7 @@
      "transport": "http",
      "request": {
        "method": "POST",
-        "url": "https://api.anthropic.com/v1/messages",
+        "url": "https://api.anthropic.com/v1/messages?beta=true",
        "headers": {
          "anthropic-version": "2023-06-01",
          "content-type": "application/json"
@@ -23,7 +23,7 @@
        "headers": {
          "content-type": "application/json"
        },
-        "body": "{\"model\":\"anthropic/claude-sonnet-4.6\",\"messages\":[{\"role\":\"system\",\"content\":\"Use the get_weather tool exactly once. After the tool result, reply exactly: Paris is sunny.\"},{\"role\":\"user\",\"content\":\"What is the weather in Paris?\"}],\"tools\":[{\"type\":\"function\",\"function\":{\"name\":\"get_weather\",\"description\":\"Get current weather for a city.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false}}}],\"stream\":true,\"stream_options\":{\"include_usage\":true},\"max_tokens\":1536,\"reasoning\":{\"max_tokens\":1024}}"
+        "body": "{\"model\":\"anthropic/claude-sonnet-4.6\",\"messages\":[{\"role\":\"system\",\"content\":\"Use the get_weather tool exactly once. After the tool result, reply exactly: Paris is sunny.\"},{\"role\":\"user\",\"content\":\"What is the weather in Paris?\"}],\"tools\":[{\"type\":\"function\",\"function\":{\"name\":\"get_weather\",\"description\":\"Get current weather for a city.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false},\"strict\":false}}],\"stream\":true,\"stream_options\":{\"include_usage\":true},\"reasoning\":{\"max_tokens\":1024},\"max_completion_tokens\":1536,\"store\":false,\"usage\":{\"include\":true}}"
      },
      "response": {
        "status": 200,
@@ -41,7 +41,7 @@
        "headers": {
          "content-type": "application/json"
        },
-        "body": "{\"model\":\"anthropic/claude-sonnet-4.6\",\"messages\":[{\"role\":\"system\",\"content\":\"Use the get_weather tool exactly once. After the tool result, reply exactly: Paris is sunny.\"},{\"role\":\"user\",\"content\":\"What is the weather in Paris?\"},{\"role\":\"assistant\",\"content\":\"Sure! Let me check the weather in Paris for you right now!\",\"tool_calls\":[{\"id\":\"toolu_01PaChhcyw3yu2P2bDS2bgAA\",\"type\":\"function\",\"function\":{\"name\":\"get_weather\",\"arguments\":\"{\\\"city\\\":\\\"Paris\\\"}\"}}],\"reasoning\":\"The user wants to know the weather in Paris. I'll use the get_weather tool.\",\"reasoning_details\":[{\"type\":\"reasoning.text\",\"text\":\"The user wants to know the weather in Paris. I'll use the get_weather tool.\",\"format\":\"anthropic-claude-v1\",\"index\":0,\"signature\":\"ErkCCosBCA8YAipAjKnRKpxkZ4eHrMPJ63IWEOYPSzb+XSHyG+vLK+2ks2O9T4N9M37Xn2kausQSH1rfsrdmKxgUlBg6yUFRgMVR7DIRY2xhdWRlLXNvbm5ldC00LTY4AEIIdGhpbmtpbmdaJDRjMGYwNDZmLTI1ZmQtNDVmYi1iZmIzLWEwOGE4ZTI0OWNhNxIMNFb5O6pb4nX0HojdGgyL5h+CAIpsxpdM1QgiMGm/i3ST6F5mAhxB+Uez0Cm95ra9yvQkrzHaA/AmWoXpdmPlczSn1S1RDk2IqeA57Spbf7JT44jygtLQt6yZmGzoTBHn3VkwaNZsuuAtbdo4B5QJXooa/AoKKs54QZ2kfS640vsv5flQVCg7CoQCFuLKjIeLMO7MnxVyuskXJr1DgesTa7I0ScF53U9JGhgB\"}]},{\"role\":\"tool\",\"tool_call_id\":\"toolu_01PaChhcyw3yu2P2bDS2bgAA\",\"content\":\"{\\\"temperature\\\":22,\\\"condition\\\":\\\"sunny\\\"}\"}],\"tools\":[{\"type\":\"function\",\"function\":{\"name\":\"get_weather\",\"description\":\"Get current weather for a city.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false}}}],\"stream\":true,\"stream_options\":{\"include_usage\":true},\"max_tokens\":1536,\"reasoning\":{\"max_tokens\":1024}}"
+        "body": "{\"model\":\"anthropic/claude-sonnet-4.6\",\"messages\":[{\"role\":\"system\",\"content\":\"Use the get_weather tool exactly once. After the tool result, reply exactly: Paris is sunny.\"},{\"role\":\"user\",\"content\":\"What is the weather in Paris?\"},{\"role\":\"assistant\",\"content\":\"Sure! Let me check the weather in Paris for you right now!\",\"tool_calls\":[{\"id\":\"toolu_01PaChhcyw3yu2P2bDS2bgAA\",\"type\":\"function\",\"function\":{\"name\":\"get_weather\",\"arguments\":\"{\\\"city\\\":\\\"Paris\\\"}\"}}],\"reasoning\":\"The user wants to know the weather in Paris. I'll use the get_weather tool.\",\"reasoning_details\":[{\"type\":\"reasoning.text\",\"text\":\"The user wants to know the weather in Paris. I'll use the get_weather tool.\",\"format\":\"anthropic-claude-v1\",\"index\":0,\"signature\":\"ErkCCosBCA8YAipAjKnRKpxkZ4eHrMPJ63IWEOYPSzb+XSHyG+vLK+2ks2O9T4N9M37Xn2kausQSH1rfsrdmKxgUlBg6yUFRgMVR7DIRY2xhdWRlLXNvbm5ldC00LTY4AEIIdGhpbmtpbmdaJDRjMGYwNDZmLTI1ZmQtNDVmYi1iZmIzLWEwOGE4ZTI0OWNhNxIMNFb5O6pb4nX0HojdGgyL5h+CAIpsxpdM1QgiMGm/i3ST6F5mAhxB+Uez0Cm95ra9yvQkrzHaA/AmWoXpdmPlczSn1S1RDk2IqeA57Spbf7JT44jygtLQt6yZmGzoTBHn3VkwaNZsuuAtbdo4B5QJXooa/AoKKs54QZ2kfS640vsv5flQVCg7CoQCFuLKjIeLMO7MnxVyuskXJr1DgesTa7I0ScF53U9JGhgB\"}]},{\"role\":\"tool\",\"tool_call_id\":\"toolu_01PaChhcyw3yu2P2bDS2bgAA\",\"content\":\"{\\\"temperature\\\":22,\\\"condition\\\":\\\"sunny\\\"}\"}],\"tools\":[{\"type\":\"function\",\"function\":{\"name\":\"get_weather\",\"description\":\"Get current weather for a city.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false},\"strict\":false}}],\"stream\":true,\"stream_options\":{\"include_usage\":true},\"reasoning\":{\"max_tokens\":1024},\"max_completion_tokens\":1536,\"store\":false,\"usage\":{\"include\":true}}"
      },
      "response": {
        "status": 200,
@@ -15,7 +15,7 @@
        "headers": {
          "content-type": "application/json"
        },
-        "body": "{\"model\":\"anthropic/claude-sonnet-4.6\",\"messages\":[{\"role\":\"system\",\"content\":\"Think through the arithmetic, then reply with only the final integer.\"},{\"role\":\"user\",\"content\":\"What is 173 multiplied by 219?\"}],\"stream\":true,\"stream_options\":{\"include_usage\":true},\"max_tokens\":1536,\"temperature\":0,\"reasoning\":{\"max_tokens\":1024}}"
+        "body": "{\"model\":\"anthropic/claude-sonnet-4.6\",\"messages\":[{\"role\":\"system\",\"content\":\"Think through the arithmetic, then reply with only the final integer.\"},{\"role\":\"user\",\"content\":\"What is 173 multiplied by 219?\"}],\"stream\":true,\"stream_options\":{\"include_usage\":true},\"temperature\":0,\"reasoning\":{\"max_tokens\":1024},\"max_completion_tokens\":1536,\"store\":false,\"usage\":{\"include\":true}}"
      },
      "response": {
        "status": 200,
@@ -10,11 +10,11 @@
      "transport": "http",
      "request": {
        "method": "POST",
-        "url": "https://api.anthropic.com/v1/messages",
+        "url": "https://api.anthropic.com/v1/messages?beta=true",
        "headers": {
          "content-type": "application/json"
        },
-        "body": "{\"model\":\"claude-haiku-4-5-20251001\",\"system\":[{\"type\":\"text\",\"text\":\"Read the PDF returned by the tool and follow the user's response format exactly.\"}],\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Return only the verification code from the PDF.\"}]},{\"role\":\"assistant\",\"content\":[{\"type\":\"tool_use\",\"id\":\"call_pdf_1\",\"name\":\"read_pdf\",\"input\":{}}]},{\"role\":\"user\",\"content\":[{\"type\":\"tool_result\",\"tool_use_id\":\"call_pdf_1\",\"content\":[{\"type\":\"text\",\"text\":\"PDF read successfully\"},{\"type\":\"document\",\"source\":{\"type\":\"base64\",\"media_type\":\"application/pdf\",\"data\":\"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\"}}]}]}],\"tools\":[{\"name\":\"read_pdf\",\"description\":\"Read the attached PDF.\",\"input_schema\":{\"type\":\"object\",\"properties\":{},\"additionalProperties\":false}}],\"stream\":true,\"max_tokens\":40,\"temperature\":0}"
+        "body": "{\"model\":\"claude-haiku-4-5-20251001\",\"system\":[{\"type\":\"text\",\"text\":\"Read the PDF returned by the tool and follow the user's response format exactly.\"}],\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Return only the verification code from the PDF.\"}]},{\"role\":\"assistant\",\"content\":[{\"type\":\"tool_use\",\"id\":\"call_pdf_1\",\"name\":\"read_pdf\",\"input\":{}}]},{\"role\":\"user\",\"content\":[{\"type\":\"tool_result\",\"tool_use_id\":\"call_pdf_1\",\"content\":[{\"type\":\"text\",\"text\":\"PDF read successfully\"},{\"type\":\"document\",\"source\":{\"type\":\"base64\",\"media_type\":\"application/pdf\",\"data\":\"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\"},\"title\":\"verification.pdf\"}]}]}],\"tools\":[{\"name\":\"read_pdf\",\"description\":\"Read the attached PDF.\",\"input_schema\":{\"type\":\"object\",\"properties\":{},\"additionalProperties\":false}}],\"stream\":true,\"max_tokens\":40,\"temperature\":0}"
      },
      "response": {
        "status": 200,
@@ -10,11 +10,11 @@
      "transport": "http",
      "request": {
        "method": "POST",
-        "url": "https://api.anthropic.com/v1/messages",
+        "url": "https://api.anthropic.com/v1/messages?beta=true",
        "headers": {
          "content-type": "application/json"
        },
-        "body": "{\"model\":\"claude-haiku-4-5-20251001\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"document\",\"source\":{\"type\":\"base64\",\"media_type\":\"application/pdf\",\"data\":\"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\"}},{\"type\":\"text\",\"text\":\"Return only the verification code from the PDF.\"}]}],\"stream\":true,\"max_tokens\":40,\"temperature\":0}"
+        "body": "{\"model\":\"claude-haiku-4-5-20251001\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"document\",\"source\":{\"type\":\"base64\",\"media_type\":\"application/pdf\",\"data\":\"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\"},\"title\":\"verification.pdf\"},{\"type\":\"text\",\"text\":\"Return only the verification code from the PDF.\"}]}],\"stream\":true,\"max_tokens\":40,\"temperature\":0}"
      },
      "response": {
        "status": 200,
@@ -44,21 +44,23 @@ describe("Tool.make (dynamic JSON Schema)", () => {
    expect(definition?.inputSchema).toEqual(jsonSchema)
  })

-  test("execute receives the raw input untouched", async () => {
-    const seen: unknown[] = []
-    const tool = Tool.make({
-      description: "echo",
-      jsonSchema: { type: "object" },
-      execute: (params) =>
-        Effect.sync(() => {
-          seen.push(params)
-          return { ok: true }
-        }),
-    })
-    const result = await Effect.runPromise(tool.execute({ hello: "world" }))
-    expect(seen).toEqual([{ hello: "world" }])
-    expect(result).toEqual({ ok: true })
-  })
+  it.effect("execute receives the raw input untouched", () =>
+    Effect.gen(function* () {
+      const seen: unknown[] = []
+      const tool = Tool.make({
+        description: "echo",
+        jsonSchema: { type: "object" },
+        execute: (params) =>
+          Effect.sync(() => {
+            seen.push(params)
+            return { ok: true }
+          }),
+      })
+      const result = yield* tool.execute({ hello: "world" })
+      expect(seen).toEqual([{ hello: "world" }])
+      expect(result).toEqual({ ok: true })
+    }),
+  )
 })

 describe("LLM.generateObject", () => {
@@ -11,6 +11,7 @@ describe("provider error classification", () => {
      "Input length 131393 exceeds the maximum allowed input length of 131040 tokens.",
      "The input (516368 tokens) is longer than the model's context length (262144 tokens).",
      "Prompt has 5,958,968 tokens, but the configured context size is 256,000 tokens",
+      "Range of input length should be [1, 129024]",
      "Too many tokens",
      "Token limit exceeded",
    ]
@@ -87,10 +88,12 @@ describe("provider error classification", () => {
    ])
  })

-  test("classifies network error text as provider internal", () => {
+  test("classifies any remaining 4xx status as an invalid request", () => {
    expect(
-      ["network error", "network-error", "network_error"].map((message) => classifyProviderFailure({ message })._tag),
-    ).toEqual(["ProviderInternal", "ProviderInternal", "ProviderInternal"])
+      [400, 402, 404, 418, 422, 451].map(
+        (status) => classifyProviderFailure({ message: `HTTP ${status}`, status })._tag,
+      ),
+    ).toEqual(Array(6).fill("InvalidRequest"))
  })

  test("classifies nested provider codes when a top-level code is also present", () => {
@@ -103,10 +106,12 @@ describe("provider error classification", () => {
    ).toEqual(["QuotaExceeded", "ProviderInternal", "InvalidRequest"])
  })

-  test("keeps unknown and malformed provider payloads non-retryable", () => {
+  test("leaves unrecognized failures unclassified for the retry default", () => {
    expect(classifyProviderFailure({ message: '{"error":{"message":"no_kv_space"}}' })._tag).toBe("UnknownProvider")
    expect(classifyProviderFailure({ message: '{"type":"error","error":{"code":123}}' })._tag).toBe("UnknownProvider")
    expect(classifyProviderFailure({ message: "not-json" })._tag).toBe("UnknownProvider")
+    expect(classifyProviderFailure({ message: "network error" })._tag).toBe("UnknownProvider")
+    expect(classifyProviderFailure({ message: "Provider returned error" })._tag).toBe("UnknownProvider")
  })
 })

@@ -1,5 +1,7 @@
 import { describe, expect, test } from "bun:test"
 import { model } from "@opencode-ai/ai/providers/openai"
+import { LLM } from "../src/index.js"
+import { Endpoint } from "../src/route/endpoint.js"

 describe("provider package entrypoints", () => {
  test("semantic API aliases expose the same contract", async () => {
@@ -36,7 +38,8 @@ describe("provider package entrypoints", () => {
    expect(modules[0].model).toBe(modules[1].model)
    expect(modules[8].model).toBe(modules[9].model)
    expect(modules[12].model).toBe(modules[13].model)
-    expect(modules[19].model).toBe(modules[20].model)
+    expect(modules[19].model).toBe(modules[21].model)
+    expect(modules[19].model).not.toBe(modules[20].model)
  })

  test("maps DeepInfra package settings onto its native executable model", async () => {
@@ -139,8 +142,10 @@ describe("provider package entrypoints", () => {
    expect(selected.route.id).toBe("anthropic-messages")
    expect(selected.route.endpoint).toMatchObject({
      baseURL: "https://messages.example.test/v1",
-      path: "/messages",
    })
+    expect(
+      Endpoint.render(selected.route.endpoint, { request: LLM.request({ model: selected }), body: {} }).toString(),
+    ).toBe("https://messages.example.test/v1/messages")
    expect(selected.route.defaults.headers).toEqual({ "x-application": "opencode" })
    expect(selected.route.defaults.http?.body).toEqual({ metadata: { user_id: "user_1" } })
    expect(selected.route.defaults.providerOptions).toEqual({ effort: "low" })
@@ -491,6 +491,59 @@ describe("Bedrock Converse route", () => {
    }),
  )

+  it.effect("ignores late tool deltas after contentBlockStop", () =>
+    Effect.gen(function* () {
+      const body = eventStreamBody(
+        [
+          "contentBlockStart",
+          {
+            contentBlockIndex: 0,
+            start: { toolUse: { toolUseId: "tool_1", name: "lookup" } },
+          },
+        ],
+        ["contentBlockDelta", { contentBlockIndex: 0, delta: { toolUse: { input: '{"query":"weather"}' } } }],
+        ["contentBlockStop", { contentBlockIndex: 0 }],
+        ["contentBlockDelta", { contentBlockIndex: 0, delta: { toolUse: { input: '{"late":true}' } } }],
+        ["messageStop", { stopReason: "tool_use" }],
+      )
+      const response = yield* LLMClient.generate(baseRequest).pipe(Effect.provide(fixedBytes(body)))
+
+      expect(response.toolCalls).toEqual([
+        { type: "tool-call", id: "tool_1", name: "lookup", input: { query: "weather" } },
+      ])
+      expect(response.events.filter((event) => event.type === "tool-input-delta")).toEqual([
+        {
+          type: "tool-input-delta",
+          id: "tool_1",
+          name: "lookup",
+          text: '{"query":"weather"}',
+          input: { query: "weather" },
+        },
+      ])
+    }),
+  )
+
+  it.effect("rejects tool deltas without contentBlockStart", () =>
+    Effect.gen(function* () {
+      const error = yield* LLMClient.generate(baseRequest).pipe(
+        Effect.provide(
+          fixedBytes(
+            eventStreamBody(
+              ["contentBlockDelta", { contentBlockIndex: 0, delta: { toolUse: { input: "{}" } } }],
+              ["messageStop", { stopReason: "tool_use" }],
+            ),
+          ),
+        ),
+        Effect.flip,
+      )
+
+      expect(error).toMatchObject({
+        reason: { _tag: "InvalidProviderOutput" },
+        message: "Bedrock Converse tool delta is missing its tool call",
+      })
+    }),
+  )
+
  it.effect("recovers incomplete tool input at finalization", () =>
    Effect.gen(function* () {
      const body = eventStreamBody(
@@ -531,6 +584,104 @@ describe("Bedrock Converse route", () => {
    }),
  )

+  for (const signature of [undefined, "", "   "]) {
+    for (const cache of ["none", "auto"] as const) {
+      it.effect(`demotes unsigned reasoning to text (${JSON.stringify(signature)}, cache: ${cache})`, () =>
+        Effect.gen(function* () {
+          const prepared = yield* compileRequest(
+            LLM.request({
+              model,
+              messages: [
+                Message.user("Think"),
+                Message.assistant([
+                  {
+                    type: "reasoning",
+                    text: "Partial thought",
+                    providerMetadata: signature === undefined ? undefined : { bedrock: { signature } },
+                    cache: new CacheHint({ type: "ephemeral" }),
+                  },
+                ]),
+                Message.user("Continue"),
+              ],
+              cache,
+            }),
+          )
+          expect(prepared.body.messages[1]).toEqual({
+            role: "assistant",
+            content: [{ text: "Partial thought" }, { cachePoint: { type: "default" } }],
+          })
+        }),
+      )
+    }
+  }
+
+  it.effect("omits empty unsigned reasoning without leaving an empty or cache-only assistant", () =>
+    Effect.gen(function* () {
+      const cache = new CacheHint({ type: "ephemeral" })
+      const prepared = yield* compileRequest(
+        LLM.request({
+          model,
+          messages: [
+            Message.user("Think"),
+            Message.assistant([
+              { type: "reasoning", text: "", cache },
+              { type: "reasoning", text: "  ", providerMetadata: { bedrock: { signature: "" } }, cache },
+            ]),
+            Message.user([{ type: "text", text: "Continue", cache }]),
+          ],
+          cache: "none",
+        }),
+      )
+      expect(prepared.body.messages).toEqual([
+        {
+          role: "user",
+          content: [{ text: "Think" }, { text: "Continue" }, { cachePoint: { type: "default" } }],
+        },
+      ])
+    }),
+  )
+
+  it.effect("demotes foreign reasoning while preserving signed, redacted, text, and tool blocks", () =>
+    Effect.gen(function* () {
+      const cache = new CacheHint({ type: "ephemeral" })
+      const prepared = yield* compileRequest(
+        LLM.request({
+          model,
+          messages: [
+            Message.assistant([
+              { type: "reasoning", text: "Foreign thought", providerMetadata: { anthropic: { signature: "old" } } },
+              {
+                type: "reasoning",
+                text: "Signed thought",
+                providerMetadata: { bedrock: { signature: "sig_1" } },
+                cache,
+              },
+              { type: "reasoning", text: "", encrypted: "sig_2", cache },
+              { type: "reasoning", text: "", providerMetadata: { bedrock: { redactedData: "cmVkYWN0ZWQ=" } }, cache },
+              { type: "text", text: "Checking" },
+              ToolCallPart.make({ id: "call_1", name: "lookup", input: {} }),
+            ]),
+          ],
+          tools: [{ name: "lookup", description: "Lookup data", inputSchema: { type: "object" } }],
+          cache: "none",
+        }),
+      )
+      expect(prepared.body.messages).toEqual([
+        {
+          role: "assistant",
+          content: [
+            { text: "Foreign thought" },
+            { reasoningContent: { reasoningText: { text: "Signed thought", signature: "sig_1" } } },
+            { reasoningContent: { reasoningText: { text: "", signature: "sig_2" } } },
+            { reasoningContent: { redactedContent: "cmVkYWN0ZWQ=" } },
+            { text: "Checking" },
+            { toolUse: { toolUseId: "call_1", name: "lookup", input: {} } },
+          ],
+        },
+      ])
+    }),
+  )
+
  it.effect("preserves streamed reasoning signatures for continuation lowering", () =>
    Effect.gen(function* () {
      const body = eventStreamBody(
@@ -1,4 +1,4 @@
-import { describe, expect } from "bun:test"
+import { describe, expect, test } from "bun:test"
 import { ConfigProvider, Effect, Schema } from "effect"
 import { HttpClientRequest } from "effect/unstable/http"
 import { LLM, LLMEvent } from "../../src/index.js"
@@ -136,17 +136,15 @@ describe("Cloudflare", () => {
    }),
  )

-  it.effect("defaults AI Gateway id to default when omitted or blank", () =>
-    Effect.gen(function* () {
-      expect(
-        CloudflareAIGateway.configure({
-          accountId: "test-account",
-          gatewayId: "",
-          gatewayApiKey: "test-token",
-        }).model("workers-ai/@cf/meta/llama-3.3-70b-instruct").route.endpoint.baseURL,
-      ).toBe("https://gateway.ai.cloudflare.com/v1/test-account/default/compat")
-    }),
-  )
+  test("defaults AI Gateway id to default when omitted or blank", () => {
+    expect(
+      CloudflareAIGateway.configure({
+        accountId: "test-account",
+        gatewayId: "",
+        gatewayApiKey: "test-token",
+      }).model("workers-ai/@cf/meta/llama-3.3-70b-instruct").route.endpoint.baseURL,
+    ).toBe("https://gateway.ai.cloudflare.com/v1/test-account/default/compat")
+  })

  it.effect("supports authenticated AI Gateway plus upstream provider auth", () =>
    Effect.gen(function* () {
@@ -52,7 +52,7 @@ describe("provider error retention", () => {
          Effect.flip,
        )
        expect(error.message).toContain("Slow down")
-        expect(error.reason._tag).toBe(entry.name === "Gemini" ? "ProviderInternal" : "RateLimit")
+        expect(error.reason._tag).toBe("RateLimit")
        expect(error.reason.body).toBe(body)
        expect(error.reason.http).toMatchObject({ status: 200, headers: { "x-provider-trace": "trace-1" } })
        expect(error.reason.http?.url).toStartWith("https://provider.test/")
@@ -1,4 +1,4 @@
-import { describe, expect } from "bun:test"
+import { describe, expect, test } from "bun:test"
 import { Effect } from "effect"
 import { HttpClientRequest } from "effect/unstable/http"
 import { LLM, Message, ToolCallPart } from "../../src/index.js"
@@ -376,11 +376,9 @@ describe("Google Vertex providers", () => {
    }),
  )

-  it.effect("rejects tuned Gemini models in express mode", () =>
-    Effect.sync(() => {
-      expect(() => GoogleVertex.configure({ apiKey: "fixture" }).model("endpoints/1234567890")).toThrow(
-        "Google Vertex tuned models do not support Express Mode API keys",
-      )
-    }),
-  )
+  test("rejects tuned Gemini models in express mode", () => {
+    expect(() => GoogleVertex.configure({ apiKey: "fixture" }).model("endpoints/1234567890")).toThrow(
+      "Google Vertex tuned models do not support Express Mode API keys",
+    )
+  })
 })
@@ -1,4 +1,4 @@
-import { describe, expect } from "bun:test"
+import { describe, expect, test } from "bun:test"
 import { ConfigProvider, Effect } from "effect"
 import { HttpClientRequest } from "effect/unstable/http"
 import { LLM, Message, ToolDefinition } from "../../src/index.js"
@@ -31,82 +31,71 @@ import { dynamicResponse } from "../lib/http.js"
 import { sseEvents } from "../lib/sse.js"

 describe("native OpenAI-compatible providers", () => {
-  it.effect("assigns provider-owned metadata namespaces across native routes", () =>
-    Effect.gen(function* () {
-      const vertex = { project: "project", accessToken: "token" }
-      const providers = [
-        [OpenAI.configure({ apiKey: "test" }).chat("model"), "openai"],
-        [OpenAI.configure({ apiKey: "test" }).responses("model"), "openai"],
-        [Azure.configure({ resourceName: "resource", apiKey: "test" }).chat("model"), "azure"],
-        [Azure.configure({ resourceName: "resource", apiKey: "test" }).responses("model"), "azure"],
-        [AmazonBedrock.configure({ apiKey: "test" }).model("model"), "bedrock"],
-        [AmazonBedrockMantle.configure({ apiKey: "test" }).chat("model"), "mantle"],
-        [AmazonBedrockMantle.configure({ apiKey: "test" }).responses("model"), "mantle"],
-        [Google.configure({ apiKey: "test" }).model("model"), "google"],
-        [GoogleVertex.configure(vertex).model("model"), "vertex"],
-        [GoogleVertexChat.configure(vertex).model("model"), "vertex"],
-        [GoogleVertexResponses.configure(vertex).model("model"), "vertex"],
-        [GoogleVertexMessages.configure(vertex).model("model"), "anthropic"],
-        [Anthropic.configure({ apiKey: "test" }).model("model"), "anthropic"],
-        [
-          AnthropicCompatible.configure({ baseURL: "https://example.test/v1", provider: "minimax" }).model("model"),
-          "minimax",
-        ],
-        [
-          OpenAICompatible.configure({ baseURL: "https://example.test/v1", provider: "custom" }).model("model"),
-          "custom",
-        ],
-        [
-          OpenAICompatibleResponses.configure({ baseURL: "https://example.test/v1", provider: "custom" }).model(
-            "model",
-          ),
-          "custom",
-        ],
-        [Cerebras.configure({ apiKey: "test" }).model("model"), "cerebras"],
-        [DeepInfra.configure({ apiKey: "test" }).model("model"), "deepinfra"],
-        [TogetherAI.configure({ apiKey: "test" }).model("model"), "togetherai"],
-        [CloudflareAIGateway.configure({ accountId: "account" }).model("model"), "cloudflare-ai-gateway"],
-        [CloudflareWorkersAI.configure({ accountId: "account" }).model("model"), "cloudflare-workers-ai"],
-        [OpenRouter.configure({ apiKey: "test" }).model("model"), "openrouter"],
-        [XAI.configure({ apiKey: "test" }).chat("model"), "xai"],
-        [XAI.configure({ apiKey: "test" }).responses("model"), "xai"],
-      ] as const
+  test("assigns provider-owned metadata namespaces across native routes", () => {
+    const vertex = { project: "project", accessToken: "token" }
+    const providers = [
+      [OpenAI.configure({ apiKey: "test" }).chat("model"), "openai"],
+      [OpenAI.configure({ apiKey: "test" }).responses("model"), "openai"],
+      [Azure.configure({ resourceName: "resource", apiKey: "test" }).chat("model"), "azure"],
+      [Azure.configure({ resourceName: "resource", apiKey: "test" }).responses("model"), "azure"],
+      [AmazonBedrock.configure({ apiKey: "test" }).model("model"), "bedrock"],
+      [AmazonBedrockMantle.configure({ apiKey: "test" }).chat("model"), "mantle"],
+      [AmazonBedrockMantle.configure({ apiKey: "test" }).responses("model"), "mantle"],
+      [Google.configure({ apiKey: "test" }).model("model"), "google"],
+      [GoogleVertex.configure(vertex).model("model"), "vertex"],
+      [GoogleVertexChat.configure(vertex).model("model"), "vertex"],
+      [GoogleVertexResponses.configure(vertex).model("model"), "vertex"],
+      [GoogleVertexMessages.configure(vertex).model("model"), "anthropic"],
+      [Anthropic.configure({ apiKey: "test" }).model("model"), "anthropic"],
+      [
+        AnthropicCompatible.configure({ baseURL: "https://example.test/v1", provider: "minimax" }).model("model"),
+        "minimax",
+      ],
+      [OpenAICompatible.configure({ baseURL: "https://example.test/v1", provider: "custom" }).model("model"), "custom"],
+      [
+        OpenAICompatibleResponses.configure({ baseURL: "https://example.test/v1", provider: "custom" }).model("model"),
+        "custom",
+      ],
+      [Cerebras.configure({ apiKey: "test" }).model("model"), "cerebras"],
+      [DeepInfra.configure({ apiKey: "test" }).model("model"), "deepinfra"],
+      [TogetherAI.configure({ apiKey: "test" }).model("model"), "togetherai"],
+      [CloudflareAIGateway.configure({ accountId: "account" }).model("model"), "cloudflare-ai-gateway"],
+      [CloudflareWorkersAI.configure({ accountId: "account" }).model("model"), "cloudflare-workers-ai"],
+      [OpenRouter.configure({ apiKey: "test" }).model("model"), "openrouter"],
+      [XAI.configure({ apiKey: "test" }).chat("model"), "xai"],
+      [XAI.configure({ apiKey: "test" }).responses("model"), "xai"],
+    ] as const

-      for (const [model, key] of providers) expect(model.route.providerMetadataKey).toBe(key)
-    }),
-  )
+    for (const [model, key] of providers) expect(model.route.providerMetadataKey).toBe(key)
+  })

-  it.effect("preserves native Together AI and Cerebras provider and route identities", () =>
-    Effect.gen(function* () {
-      const together = TogetherAI.configure({ apiKey: "fixture" }).model("meta-llama/Llama-3.3-70B")
-      const cerebras = Cerebras.configure({ apiKey: "fixture" }).model("qwen-3-235b-a22b")
+  test("preserves native Together AI and Cerebras provider and route identities", () => {
+    const together = TogetherAI.configure({ apiKey: "fixture" }).model("meta-llama/Llama-3.3-70B")
+    const cerebras = Cerebras.configure({ apiKey: "fixture" }).model("qwen-3-235b-a22b")

-      expect(together).toMatchObject({
-        provider: "togetherai",
-        compatibility: { maxTokensField: "max_tokens", supportsStore: false, supportsStrictMode: false },
-        route: { id: "togetherai-chat", protocol: "openai-chat" },
-      })
-      expect(together.route.endpoint.baseURL).toBe("https://api.together.xyz/v1")
-      expect(cerebras).toMatchObject({
-        provider: "cerebras",
-        compatibility: { maxTokensField: "max_tokens", reasoningField: "reasoning", supportsStore: false },
-        route: { id: "cerebras-chat", protocol: "openai-chat" },
-      })
-      expect(cerebras.route.endpoint.baseURL).toBe("https://api.cerebras.ai/v1")
-    }),
-  )
+    expect(together).toMatchObject({
+      provider: "togetherai",
+      compatibility: { maxTokensField: "max_tokens", supportsStore: false, supportsStrictMode: false },
+      route: { id: "togetherai-chat", protocol: "openai-chat" },
+    })
+    expect(together.route.endpoint.baseURL).toBe("https://api.together.xyz/v1")
+    expect(cerebras).toMatchObject({
+      provider: "cerebras",
+      compatibility: { maxTokensField: "max_tokens", reasoningField: "reasoning", supportsStore: false },
+      route: { id: "cerebras-chat", protocol: "openai-chat" },
+    })
+    expect(cerebras.route.endpoint.baseURL).toBe("https://api.cerebras.ai/v1")
+  })

-  it.effect("preserves native DeepInfra provider and route identity", () =>
-    Effect.gen(function* () {
-      const deepinfra = DeepInfra.configure({ apiKey: "fixture" }).model("google/gemma-3-27b-it")
-      expect(deepinfra).toMatchObject({
-        provider: "deepinfra",
-        compatibility: { maxTokensField: "max_tokens", reasoningField: "reasoning_content", supportsStore: false },
-        route: { id: "deepinfra-chat", protocol: "openai-chat" },
-      })
-      expect(deepinfra.route.endpoint.baseURL).toBe("https://api.deepinfra.com/v1/openai")
-    }),
-  )
+  test("preserves native DeepInfra provider and route identity", () => {
+    const deepinfra = DeepInfra.configure({ apiKey: "fixture" }).model("google/gemma-3-27b-it")
+    expect(deepinfra).toMatchObject({
+      provider: "deepinfra",
+      compatibility: { maxTokensField: "max_tokens", reasoningField: "reasoning_content", supportsStore: false },
+      route: { id: "deepinfra-chat", protocol: "openai-chat" },
+    })
+    expect(deepinfra.route.endpoint.baseURL).toBe("https://api.deepinfra.com/v1/openai")
+  })

  it.effect("applies native provider request defaults even with a custom gateway URL", () =>
    Effect.gen(function* () {
@@ -161,39 +150,35 @@ describe("native OpenAI-compatible providers", () => {
    }),
  )

-  it.effect("normalizes DeepInfra API roots without duplicating the OpenAI path", () =>
-    Effect.gen(function* () {
-      for (const baseURL of [
-        "https://gateway.example/v1",
-        "https://gateway.example/v1/",
+  test("normalizes DeepInfra API roots without duplicating the OpenAI path", () => {
+    for (const baseURL of [
+      "https://gateway.example/v1",
+      "https://gateway.example/v1/",
+      "https://gateway.example/v1/openai",
+      "https://gateway.example/v1/openai/",
+    ]) {
+      expect(DeepInfra.configure({ apiKey: "fixture", baseURL }).model("gemma").route.endpoint.baseURL).toBe(
        "https://gateway.example/v1/openai",
-        "https://gateway.example/v1/openai/",
-      ]) {
-        expect(DeepInfra.configure({ apiKey: "fixture", baseURL }).model("gemma").route.endpoint.baseURL).toBe(
-          "https://gateway.example/v1/openai",
-        )
-      }
-    }),
-  )
+      )
+    }
+  })

-  it.effect("maps package settings onto native executable models", () =>
-    Effect.gen(function* () {
-      for (const native of [TogetherAI, Cerebras]) {
-        const selected = native.model("provider-model", {
-          apiKey: "fixture",
-          baseURL: "https://gateway.example/v1",
-          headers: { "x-application": "opencode" },
-          body: { service_tier: "priority" },
-          providerOptions: { reasoningEffort: "high" },
-        })
+  test("maps package settings onto native executable models", () => {
+    for (const native of [TogetherAI, Cerebras]) {
+      const selected = native.model("provider-model", {
+        apiKey: "fixture",
+        baseURL: "https://gateway.example/v1",
+        headers: { "x-application": "opencode" },
+        body: { service_tier: "priority" },
+        providerOptions: { reasoningEffort: "high" },
+      })

-        expect(selected.route.endpoint.baseURL).toBe("https://gateway.example/v1")
-        expect(selected.route.defaults.headers).toEqual({ "x-application": "opencode" })
-        expect(selected.route.defaults.http?.body).toEqual({ service_tier: "priority" })
-        expect(selected.route.defaults.providerOptions).toEqual({ reasoningEffort: "high" })
-      }
-    }),
-  )
+      expect(selected.route.endpoint.baseURL).toBe("https://gateway.example/v1")
+      expect(selected.route.defaults.headers).toEqual({ "x-application": "opencode" })
+      expect(selected.route.defaults.http?.body).toEqual({ service_tier: "priority" })
+      expect(selected.route.defaults.providerOptions).toEqual({ reasoningEffort: "high" })
+    }
+  })

  it.effect("resolves provider environment credentials and preserves deprecated Together credentials", () =>
    Effect.gen(function* () {
@@ -0,0 +1,467 @@
+import { describe, expect } from "bun:test"
+import { Effect, Stream } from "effect"
+import { LLM, LLMEvent } from "../../src/index.js"
+import { OpenResponses } from "../../src/protocols/open-responses.js"
+import { configure } from "../../src/providers/openai-compatible-responses.js"
+import { LLMClient } from "../../src/route.js"
+import { it } from "../lib/effect.js"
+import { fixedResponse } from "../lib/http.js"
+import { sseEvents } from "../lib/sse.js"
+
+const request = LLM.request({
+  model: configure({ apiKey: "test-key", baseURL: "https://responses.example.test/v1" }).model("example-model"),
+  prompt: "Respond.",
+})
+const completed = { type: "response.completed", response: { id: "resp_1" } }
+
+const collect = (...input: OpenResponses.Event[]) =>
+  Effect.gen(function* () {
+    const events = yield* LLMClient.stream(request).pipe(
+      Stream.runCollect,
+      Effect.provide(fixedResponse(sseEvents(...input))),
+    )
+    expectLifecycle(
+      events,
+      input.some((event) => event.type === "response.completed"),
+    )
+    return events
+  })
+
+// Deliberately local to these basic-item fixtures, not a general stream validator.
+function expectLifecycle(events: ReadonlyArray<LLMEvent>, completed: boolean) {
+  const active = { text: new Set<string>(), reasoning: new Set<string>() }
+  const tools = new Map<string, "started" | "ended" | "called">()
+  events.forEach((event) => {
+    if (event.type === "text-start" || event.type === "reasoning-start") {
+      const blocks = event.type === "text-start" ? active.text : active.reasoning
+      expect(blocks.size).toBe(0)
+      blocks.add(event.id)
+    }
+    if (event.type === "text-delta" || event.type === "reasoning-delta") {
+      expect((event.type === "text-delta" ? active.text : active.reasoning).has(event.id)).toBe(true)
+    }
+    if (event.type === "text-end" || event.type === "reasoning-end") {
+      expect((event.type === "text-end" ? active.text : active.reasoning).delete(event.id)).toBe(true)
+    }
+    if (event.type === "tool-input-start") {
+      expect(tools.has(event.id)).toBe(false)
+      tools.set(event.id, "started")
+    }
+    if (event.type === "tool-input-delta") expect(tools.get(event.id)).toBe("started")
+    if (event.type === "tool-input-end") {
+      expect(tools.get(event.id)).toBe("started")
+      tools.set(event.id, "ended")
+    }
+    if (event.type === "tool-call") {
+      expect(tools.get(event.id)).toBe("ended")
+      tools.set(event.id, "called")
+    }
+    // Incomplete responses may leave pending tool inputs without a call.
+    if (event.type === "finish" && completed) {
+      expect(active.text.size).toBe(0)
+      expect(active.reasoning.size).toBe(0)
+      expect([...tools.values()].every((status) => status === "called")).toBe(true)
+    }
+  })
+  expect(events.filter(LLMEvent.is.stepStart)).toHaveLength(1)
+  expect(events[0]?.type).toBe("step-start")
+  expect(events.filter(LLMEvent.is.stepFinish)).toHaveLength(1)
+  expect(events.filter(LLMEvent.is.finish)).toHaveLength(1)
+  expect(events.slice(-2).map((event) => event.type)).toEqual(["step-finish", "finish"])
+}
+
+describe("Open Responses basic-item lifecycles", () => {
+  it.effect("closes implicit summary boundaries and ignores late events for completed reasoning", () =>
+    Effect.gen(function* () {
+      const item = { type: "reasoning", id: "rs_1", encrypted_content: "encrypted-state" }
+      const events = yield* collect(
+        { type: "response.output_item.added", output_index: 0, item: { ...item, encrypted_content: null } },
+        { type: "response.output_item.added", item: { ...item, encrypted_content: null } },
+        { type: "response.reasoning_summary_text.delta", item_id: "rs_1", summary_index: 0, delta: "First" },
+        { type: "response.reasoning_summary_part.added", item_id: "rs_1", summary_index: 1 },
+        { type: "response.reasoning_summary_part.done", item_id: "rs_1", summary_index: 0 },
+        { type: "response.reasoning_summary_text.done", item_id: "rs_1", summary_index: 1, text: "Second" },
+        // The third part omits both explicit summary boundaries.
+        {
+          type: "response.reasoning_summary_text.delta",
+          output_index: 0,
+          item_id: "wrong",
+          summary_index: 2,
+          delta: "Third",
+        },
+        { type: "response.output_item.done", item },
+        { type: "response.output_item.done", item },
+        { type: "response.output_item.added", item },
+        { type: "response.reasoning_summary_part.added", item_id: "rs_1", summary_index: 3 },
+        { type: "response.reasoning_summary_text.delta", item_id: "rs_1", summary_index: 3, delta: "late" },
+        { type: "response.reasoning_summary_text.done", item_id: "rs_1", summary_index: 2, text: "late final" },
+        { type: "response.reasoning_summary_part.done", item_id: "rs_1", summary_index: 3 },
+        completed,
+      )
+
+      expect(events.filter((event) => event.type.startsWith("reasoning-"))).toEqual([
+        {
+          type: "reasoning-start",
+          id: "rs_1:0",
+          providerMetadata: { "openai-compatible": { itemId: "rs_1", reasoningEncryptedContent: null } },
+        },
+        { type: "reasoning-delta", id: "rs_1:0", text: "First" },
+        { type: "reasoning-end", id: "rs_1:0", providerMetadata: { "openai-compatible": { itemId: "rs_1" } } },
+        {
+          type: "reasoning-start",
+          id: "rs_1:1",
+          providerMetadata: { "openai-compatible": { itemId: "rs_1", reasoningEncryptedContent: null } },
+        },
+        { type: "reasoning-delta", id: "rs_1:1", text: "Second" },
+        { type: "reasoning-end", id: "rs_1:1", providerMetadata: { "openai-compatible": { itemId: "rs_1" } } },
+        {
+          type: "reasoning-start",
+          id: "rs_1:2",
+          providerMetadata: { "openai-compatible": { itemId: "rs_1", reasoningEncryptedContent: null } },
+        },
+        { type: "reasoning-delta", id: "rs_1:2", text: "Third" },
+        {
+          type: "reasoning-end",
+          id: "rs_1:2",
+          providerMetadata: { "openai-compatible": { itemId: "rs_1", reasoningEncryptedContent: "encrypted-state" } },
+        },
+      ])
+    }),
+  )
+
+  it.effect("preserves done-only encrypted reasoning without replaying its summary or late events", () =>
+    Effect.gen(function* () {
+      const item = {
+        type: "reasoning",
+        id: "rs_1",
+        encrypted_content: "encrypted-state",
+        summary: [{ type: "summary_text", text: "Not streamed" }],
+      }
+      const events = yield* collect(
+        { type: "response.output_item.done", item },
+        { type: "response.output_item.done", item },
+        { type: "response.output_item.added", item },
+        { type: "response.reasoning_summary_text.delta", item_id: "rs_1", delta: "late" },
+        { type: "response.reasoning_summary_part.added", item_id: "rs_1", summary_index: 1 },
+        { type: "response.reasoning_summary_text.done", item_id: "rs_1", summary_index: 1, text: "late final" },
+        completed,
+        // Route termination must also prevent events after response completion.
+        { type: "response.output_item.added", item: { type: "reasoning", id: "rs_after" } },
+      )
+      expect(events.filter((event) => event.type.startsWith("reasoning-"))).toEqual([
+        {
+          type: "reasoning-start",
+          id: "rs_1",
+          providerMetadata: { "openai-compatible": { itemId: "rs_1", reasoningEncryptedContent: "encrypted-state" } },
+        },
+        {
+          type: "reasoning-end",
+          id: "rs_1",
+          providerMetadata: { "openai-compatible": { itemId: "rs_1", reasoningEncryptedContent: "encrypted-state" } },
+        },
+      ])
+    }),
+  )
+
+  it.effect("forgets never-streamed messages at implicit boundaries and preserves refusal phases", () =>
+    Effect.gen(function* () {
+      const events = yield* collect(
+        { type: "response.output_item.added", item: { type: "message", id: "msg_empty" } },
+        { type: "response.output_item.added", item: { type: "message", id: "msg_1", phase: "commentary" } },
+        { type: "response.output_text.done", item_id: "msg_1", text: "Checking" },
+        { type: "response.output_text.done", item_id: "msg_1", text: "Duplicate" },
+        { type: "response.output_item.added", item: { type: "message", id: "msg_2", phase: null } },
+        { type: "response.output_text.delta", item_id: "msg_empty", delta: "stale" },
+        { type: "response.output_text.done", item_id: "msg_empty", text: "stale final" },
+        { type: "response.output_text.delta", item_id: "msg_1", delta: "late" },
+        { type: "response.refusal.delta", item_id: "msg_2", delta: "Cannot help." },
+        { type: "response.refusal.done", item_id: "msg_2", refusal: "Cannot help." },
+        { type: "response.output_item.done", item: { type: "message", id: "msg_2", phase: "final_answer" } },
+        { type: "response.output_item.added", item: { type: "message", id: "msg_3", phase: null } },
+        { type: "response.refusal.done", item_id: "msg_3", refusal: "Done-only refusal." },
+        { type: "response.output_item.done", item: { type: "message", id: "msg_3" } },
+        completed,
+      )
+      expect(events.filter((event) => event.type.startsWith("text-"))).toEqual([
+        {
+          type: "text-start",
+          id: "msg_1",
+          providerMetadata: { "openai-compatible": { itemId: "msg_1", phase: "commentary" } },
+        },
+        { type: "text-delta", id: "msg_1", text: "Checking" },
+        {
+          type: "text-end",
+          id: "msg_1",
+          providerMetadata: { "openai-compatible": { itemId: "msg_1", phase: "commentary" } },
+        },
+        {
+          type: "text-start",
+          id: "msg_2",
+          providerMetadata: { "openai-compatible": { itemId: "msg_2", phase: null } },
+        },
+        { type: "text-delta", id: "msg_2", text: "Cannot help." },
+        {
+          type: "text-end",
+          id: "msg_2",
+          providerMetadata: { "openai-compatible": { itemId: "msg_2", phase: "final_answer" } },
+        },
+        {
+          type: "text-start",
+          id: "msg_3",
+          providerMetadata: { "openai-compatible": { itemId: "msg_3", phase: null } },
+        },
+        { type: "text-delta", id: "msg_3", text: "Done-only refusal." },
+        { type: "text-end", id: "msg_3", providerMetadata: { "openai-compatible": { itemId: "msg_3", phase: null } } },
+      ])
+    }),
+  )
+  it.effect("allows a message to be registered again without inheriting its previous phase", () =>
+    Effect.gen(function* () {
+      const events = yield* collect(
+        { type: "response.output_item.added", item: { type: "message", id: "msg_1", phase: "commentary" } },
+        { type: "response.output_text.delta", item_id: "msg_1", delta: "First" },
+        { type: "response.output_item.done", item: { type: "message", id: "msg_1" } },
+        { type: "response.output_item.added", item: { type: "message", id: "msg_1" } },
+        { type: "response.output_text.delta", item_id: "msg_1", delta: "Second" },
+        { type: "response.output_item.done", item: { type: "message", id: "msg_1" } },
+        completed,
+      )
+      expect(events.filter(LLMEvent.is.textEnd)).toEqual([
+        {
+          type: "text-end",
+          id: "msg_1",
+          providerMetadata: { "openai-compatible": { itemId: "msg_1", phase: "commentary" } },
+        },
+        { type: "text-end", id: "msg_1", providerMetadata: { "openai-compatible": { itemId: "msg_1" } } },
+      ])
+      expect(events.filter(LLMEvent.is.textDelta).map((event) => event.text)).toEqual(["First", "Second"])
+    }),
+  )
+  ;[undefined, "fc_1"].forEach((id) => {
+    it.effect(`opens and closes a done-only tool ${id === undefined ? "without" : "with"} an item id`, () =>
+      Effect.gen(function* () {
+        const item = {
+          type: "function_call",
+          ...(id === undefined ? {} : { id }),
+          call_id: "call_1",
+          name: "lookup",
+          arguments: '{"query":"weather"}',
+        }
+        const events = yield* collect(
+          { type: "response.output_item.done", item },
+          { type: "response.output_item.done", item: { ...item, id: "fc_1" } },
+          { type: "response.output_item.added", item },
+          completed,
+        )
+        const providerMetadata = id === undefined ? undefined : { "openai-compatible": { itemId: id } }
+        expect(events.filter((event) => event.type.startsWith("tool-"))).toEqual([
+          { type: "tool-input-start", id: "call_1", name: "lookup", providerMetadata },
+          { type: "tool-input-end", id: "call_1", name: "lookup", providerMetadata },
+          { type: "tool-call", id: "call_1", name: "lookup", input: { query: "weather" }, providerMetadata },
+        ])
+        expect(events.filter(LLMEvent.is.finish)).toEqual([
+          {
+            type: "finish",
+            reason: { normalized: "tool-calls", raw: undefined },
+            providerMetadata: { "openai-compatible": { responseId: "resp_1", serviceTier: undefined } },
+          },
+        ])
+      }),
+    )
+
+    it.effect(`deduplicates a pending call whose item id is ${id === undefined ? "introduced" : "omitted"} later`, () =>
+      Effect.gen(function* () {
+        const item = { type: "function_call", call_id: "call_1", name: "lookup" }
+        const first = { ...item, ...(id === undefined ? {} : { id }) }
+        const duplicate = { ...item, ...(id === undefined ? { id: "fc_1" } : {}) }
+        const events = yield* collect(
+          { type: "response.output_item.added", item: first },
+          { type: "response.function_call_arguments.delta", item_id: id ?? "call_1", delta: '{"query":"weather"}' },
+          { type: "response.output_item.added", item: duplicate },
+          { type: "response.output_item.done", item: duplicate },
+          { type: "response.output_item.done", item: first },
+          { type: "response.output_item.added", item: duplicate },
+          completed,
+        )
+        // Identity metadata comes from the first admission, not the duplicate.
+        const providerMetadata = id === undefined ? undefined : { "openai-compatible": { itemId: id } }
+        expect(events.filter((event) => event.type.startsWith("tool-"))).toEqual([
+          { type: "tool-input-start", id: "call_1", name: "lookup", providerMetadata },
+          {
+            type: "tool-input-delta",
+            id: "call_1",
+            name: "lookup",
+            text: '{"query":"weather"}',
+            input: { query: "weather" },
+          },
+          { type: "tool-input-end", id: "call_1", name: "lookup", providerMetadata },
+          { type: "tool-call", id: "call_1", name: "lookup", input: { query: "weather" }, providerMetadata },
+        ])
+      }),
+    )
+  })
+
+  it.effect("recovers pending items in completed output order with terminal encrypted metadata", () =>
+    Effect.gen(function* () {
+      const events = yield* collect(
+        {
+          type: "response.output_item.added",
+          item: { type: "function_call", id: "fc_1", call_id: "call_1", name: "lookup" },
+        },
+        { type: "response.function_call_arguments.delta", item_id: "fc_1", delta: '{"query":"draft"}' },
+        { type: "response.output_item.added", item: { type: "reasoning", id: "rs_1", encrypted_content: null } },
+        { type: "response.reasoning_summary_text.delta", item_id: "rs_1", delta: "Thinking" },
+        { type: "response.reasoning_summary_part.done", item_id: "rs_1", summary_index: 0 },
+        {
+          type: "response.completed",
+          response: {
+            id: "resp_1",
+            output: [
+              { type: "reasoning", id: "rs_1", encrypted_content: "terminal-state" },
+              { type: "function_call", id: "fc_1", call_id: "call_1", name: "lookup", arguments: '{"query":"final"}' },
+              { type: "function_call", id: "fc_unseen", call_id: "call_unseen", name: "lookup", arguments: "{}" },
+            ],
+          },
+        },
+      )
+      expect(events.slice(5, -2)).toEqual([
+        {
+          type: "reasoning-end",
+          id: "rs_1:0",
+          providerMetadata: { "openai-compatible": { itemId: "rs_1", reasoningEncryptedContent: "terminal-state" } },
+        },
+        {
+          type: "tool-input-end",
+          id: "call_1",
+          name: "lookup",
+          providerMetadata: { "openai-compatible": { itemId: "fc_1" } },
+        },
+        {
+          type: "tool-call",
+          id: "call_1",
+          name: "lookup",
+          input: { query: "final" },
+          providerMetadata: { "openai-compatible": { itemId: "fc_1" } },
+        },
+      ])
+    }),
+  )
+
+  it.effect("preserves call identity and pending order when an item id is reused", () =>
+    Effect.gen(function* () {
+      const first = { type: "function_call", id: "fc_1", call_id: "call_1", name: "lookup", arguments: "{}" }
+      const events = yield* collect(
+        { type: "response.output_item.added", item: first },
+        { type: "response.output_item.added", item: { ...first, id: "fc_2", call_id: "call_2" } },
+        { type: "response.output_item.done", item: first },
+        { type: "response.output_item.added", item: { ...first, call_id: "call_3" } },
+        { type: "response.output_item.done", item: first },
+        completed,
+      )
+      expect(events.filter(LLMEvent.is.toolCall).map((event) => event.id)).toEqual(["call_1", "call_2", "call_3"])
+    }),
+  )
+
+  it.effect("keeps text and reasoning identities separate even with empty item ids", () =>
+    Effect.gen(function* () {
+      const events = yield* collect(
+        { type: "response.output_item.added", item: { type: "reasoning", id: "" } },
+        { type: "response.output_item.added", item: { type: "message", id: "" } },
+        { type: "response.output_item.added", item: { type: "reasoning", id: "" } },
+        { type: "response.reasoning_summary_text.delta", item_id: "", delta: "Thinking" },
+        { type: "response.output_text.delta", item_id: "", delta: "Answer" },
+        { type: "response.output_item.done", item: { type: "reasoning", id: "", encrypted_content: "state" } },
+        { type: "response.output_item.done", item: { type: "message", id: "" } },
+        completed,
+      )
+      expect(events.filter(LLMEvent.is.reasoningDelta).map((event) => event.text)).toEqual(["Thinking"])
+      expect(events.filter(LLMEvent.is.textDelta).map((event) => event.text)).toEqual(["Answer"])
+      expect(events.filter(LLMEvent.is.reasoningEnd)).toEqual([
+        {
+          type: "reasoning-end",
+          id: ":0",
+          providerMetadata: { "openai-compatible": { itemId: "", reasoningEncryptedContent: "state" } },
+        },
+      ])
+    }),
+  )
+
+  it.effect("does not recover a completed tool from a tracked message with the same id", () =>
+    Effect.gen(function* () {
+      const events = yield* collect(
+        { type: "response.output_item.added", item: { type: "message", id: "item_1" } },
+        { type: "response.output_text.delta", item_id: "item_1", delta: "Answer" },
+        {
+          type: "response.completed",
+          response: {
+            id: "resp_1",
+            output: [{ type: "function_call", id: "item_1", call_id: "call_1", name: "lookup", arguments: "{}" }],
+          },
+        },
+      )
+      expect(events.filter(LLMEvent.is.toolCall)).toEqual([])
+      expect(events.filter(LLMEvent.is.finish).map((event) => event.reason.normalized)).toEqual(["stop"])
+    }),
+  )
+
+  it.effect("flushes pending calls and open text when completed output is absent", () =>
+    Effect.gen(function* () {
+      const events = yield* collect(
+        { type: "response.output_item.added", item: { type: "message", id: "msg_1", phase: "final_answer" } },
+        { type: "response.output_text.delta", item_id: "msg_1", delta: "Answer" },
+        {
+          type: "response.output_item.added",
+          item: { type: "function_call", call_id: "call_1", name: "lookup", arguments: "{}" },
+        },
+        completed,
+      )
+      // Generic terminal closure does not repeat the message's phase metadata.
+      expect(events.slice(4, -2)).toEqual([
+        { type: "tool-input-end", id: "call_1", name: "lookup" },
+        { type: "tool-call", id: "call_1", name: "lookup", input: {} },
+        { type: "text-end", id: "msg_1" },
+      ])
+    }),
+  )
+
+  it.effect("does not reconcile pending calls or terminal reasoning metadata on incomplete responses", () =>
+    Effect.gen(function* () {
+      const events = yield* collect(
+        { type: "response.output_item.added", item: { type: "reasoning", id: "rs_1", encrypted_content: null } },
+        { type: "response.reasoning_summary_text.delta", item_id: "rs_1", delta: "Partial" },
+        {
+          type: "response.output_item.added",
+          item: { type: "function_call", id: "fc_1", call_id: "call_1", name: "lookup" },
+        },
+        { type: "response.function_call_arguments.delta", item_id: "fc_1", delta: '{"query":' },
+        {
+          type: "response.incomplete",
+          response: {
+            id: "resp_1",
+            incomplete_details: { reason: "max_output_tokens" },
+            output: [
+              { type: "reasoning", id: "rs_1", encrypted_content: "not-reconciled" },
+              {
+                type: "function_call",
+                id: "fc_1",
+                call_id: "call_1",
+                name: "lookup",
+                arguments: '{"query":"not-reconciled"}',
+              },
+            ],
+          },
+        },
+      )
+      expect(events.filter(LLMEvent.is.toolInputEnd)).toEqual([])
+      expect(events.filter(LLMEvent.is.toolCall)).toEqual([])
+      expect(events.filter(LLMEvent.is.reasoningEnd)).toEqual([{ type: "reasoning-end", id: "rs_1:0" }])
+      expect(events.filter(LLMEvent.is.finish)).toEqual([
+        {
+          type: "finish",
+          reason: { normalized: "length", raw: "max_output_tokens" },
+          providerMetadata: { "openai-compatible": { responseId: "resp_1", serviceTier: undefined } },
+        },
+      ])
+    }),
+  )
+})
@@ -7,6 +7,7 @@ import {
  AIError,
  LLMEvent,
  LLMRequest,
+  LLMResponse,
  Message,
  LanguageModel,
  ToolCallPart,
@@ -807,6 +808,28 @@ describe("OpenAI Chat route", () => {
    }),
  )

+  it.effect("finishes at the done sentinel without waiting for response EOF", () =>
+    Effect.gen(function* () {
+      const stream = new ReadableStream<Uint8Array>({
+        start(controller) {
+          controller.enqueue(
+            new TextEncoder().encode(sseEvents(deltaChunk({ content: "Hello" }), deltaChunk({}, "stop"))),
+          )
+        },
+      })
+      const response = yield* LLMClient.generate(request).pipe(
+        Effect.provide(
+          fixedResponse(stream, {
+            headers: { "content-type": "text/event-stream" },
+          }),
+        ),
+      )
+
+      expect(response.text).toBe("Hello")
+      expect(response.events.at(-1)?.type).toBe("finish")
+    }),
+  )
+
  it.effect("preserves streamed refusals as ordinary assistant text", () =>
    Effect.gen(function* () {
      const response = yield* LLMClient.generate(request).pipe(
@@ -1127,7 +1150,7 @@ describe("OpenAI Chat route", () => {
    }),
  )

-  it.effect("preserves scalar reasoning after content starts", () =>
+  it.effect("preserves scalar reasoning after content starts in one lifecycle", () =>
    Effect.gen(function* () {
      const details = [{ type: "reasoning.text", text: "detail", format: "unknown", index: 0 }]
      const response = yield* LLMClient.generate(request).pipe(
@@ -1144,8 +1167,35 @@ describe("OpenAI Chat route", () => {
      )

      expect(response.reasoning).toBe("detailscalar")
-      expect(response.events.filter(LLMEvent.is.reasoningStart)).toHaveLength(2)
-      expect(response.events.filter(LLMEvent.is.reasoningEnd)).toHaveLength(2)
+      expect(response.events.filter(LLMEvent.is.reasoningStart)).toHaveLength(1)
+      expect(response.events.filter(LLMEvent.is.reasoningEnd)).toHaveLength(1)
+      expect(response.message.content.filter((part) => part.type === "reasoning")).toHaveLength(1)
+      expect(response.message.content.find((part) => part.type === "reasoning")?.providerMetadata).toEqual({
+        openai: { reasoningField: "reasoning", reasoningDetails: details },
+      })
+    }),
+  )
+
+  it.effect("keeps one reasoning lifecycle across many content chunks", () =>
+    Effect.gen(function* () {
+      const details = [{ type: "reasoning.text", text: "thinking", format: "anthropic-claude-v1", index: 0 }]
+      const response = yield* LLMClient.generate(request).pipe(
+        Effect.provide(
+          fixedResponse(
+            sseEvents(
+              { choices: [{ delta: { reasoning: "thinking", reasoning_details: details } }] },
+              ...Array.from({ length: 25 }, (_, index) => deltaChunk({ content: `chunk-${index} ` })),
+              deltaChunk({}, "stop"),
+            ),
+          ),
+        ),
+      )
+
+      expect(response.reasoning).toBe("thinking")
+      expect(response.text).toBe(Array.from({ length: 25 }, (_, index) => `chunk-${index} `).join(""))
+      expect(response.events.filter(LLMEvent.is.reasoningStart)).toHaveLength(1)
+      expect(response.events.filter(LLMEvent.is.reasoningEnd)).toHaveLength(1)
+      expect(response.message.content.filter((part) => part.type === "reasoning")).toHaveLength(1)
      expect(response.message.content.find((part) => part.type === "reasoning")?.providerMetadata).toEqual({
        openai: { reasoningField: "reasoning", reasoningDetails: details },
      })
@@ -1191,7 +1241,18 @@ describe("OpenAI Chat route", () => {
          index: 0,
        },
      ]
-      const response = yield* LLMClient.generate(request).pipe(
+      // Snapshot reasoning-end metadata as each event is published so the
+      // assertion cannot pass through later mutation of a shared array.
+      const publishedEndMetadata: unknown[] = []
+      const response = yield* LLMClient.stream(request).pipe(
+        Stream.tap((event) =>
+          Effect.sync(() => {
+            if (LLMEvent.is.reasoningEnd(event))
+              publishedEndMetadata.push(decodeJson(encodeJson(event.providerMetadata)))
+          }),
+        ),
+        Stream.runFold(LLMResponse.empty, LLMResponse.reduce),
+        Effect.map((state) => LLMResponse.complete(state)!),
        Effect.provide(
          fixedResponse(
            sseEvents(
@@ -1212,10 +1273,12 @@ describe("OpenAI Chat route", () => {
      expect(response.events.filter(LLMEvent.is.reasoningStart)).toHaveLength(1)
      expect(response.events.filter(LLMEvent.is.reasoningDelta)).toHaveLength(1)
      expect(response.events.filter(LLMEvent.is.reasoningEnd)).toHaveLength(1)
-      expect(response.events.filter(LLMEvent.is.reasoningEnd).at(-1)?.providerMetadata).toEqual({
-        openai: { reasoningField: "reasoning", reasoningDetails: merged },
-      })
-      expect(response.events.findIndex(LLMEvent.is.reasoningEnd)).toBeLessThan(
+      expect(publishedEndMetadata).toEqual([{ openai: { reasoningField: "reasoning", reasoningDetails: merged } }])
+      expect(response.events.findIndex(LLMEvent.is.reasoningStart)).toBeLessThan(
+        response.events.findIndex(LLMEvent.is.textStart),
+      )
+      // Reasoning stays open alongside text and closes once during finalization.
+      expect(response.events.findIndex(LLMEvent.is.reasoningEnd)).toBeGreaterThan(
        response.events.findIndex(LLMEvent.is.textStart),
      )

@@ -1,4 +1,4 @@
-import { describe, expect } from "bun:test"
+import { describe, expect, test } from "bun:test"
 import { Effect, Schema } from "effect"
 import { HttpClientRequest } from "effect/unstable/http"
 import { LLM, LLMRequest, Message, ToolCallPart, ToolChoice, ToolDefinition } from "../../src/index.js"
@@ -91,40 +91,38 @@ describe("OpenAI-compatible Chat route", () => {
    }),
  )

-  it.effect("provides model helpers for compatible provider families", () =>
-    Effect.gen(function* () {
-      expect(
-        providerFamilies.map(([provider, family]) => {
-          const model = family.configure({ apiKey: "test-key" }).model(`${provider}-model`)
-          return {
-            id: String(model.id),
-            provider: String(model.provider),
-            route: model.route.id,
-            baseURL: model.route.endpoint.baseURL,
-          }
-        }),
-      ).toEqual(
-        providerFamilies.map(([provider, _, baseURL]) => ({
-          id: `${provider}-model`,
-          provider,
-          route: "openai-compatible-chat",
-          baseURL,
-        })),
-      )
+  test("provides model helpers for compatible provider families", () => {
+    expect(
+      providerFamilies.map(([provider, family]) => {
+        const model = family.configure({ apiKey: "test-key" }).model(`${provider}-model`)
+        return {
+          id: String(model.id),
+          provider: String(model.provider),
+          route: model.route.id,
+          baseURL: model.route.endpoint.baseURL,
+        }
+      }),
+    ).toEqual(
+      providerFamilies.map(([provider, _, baseURL]) => ({
+        id: `${provider}-model`,
+        provider,
+        route: "openai-compatible-chat",
+        baseURL,
+      })),
+    )

-      const custom = OpenAICompatible.deepseek
-        .configure({
-          apiKey: "test-key",
-          baseURL: "https://custom.deepseek.test/v1",
-        })
-        .model("deepseek-chat")
-      expect(custom).toMatchObject({
-        provider: "deepseek",
-        route: { id: "openai-compatible-chat" },
+    const custom = OpenAICompatible.deepseek
+      .configure({
+        apiKey: "test-key",
+        baseURL: "https://custom.deepseek.test/v1",
      })
-      expect(custom.route.endpoint.baseURL).toBe("https://custom.deepseek.test/v1")
-    }),
-  )
+      .model("deepseek-chat")
+    expect(custom).toMatchObject({
+      provider: "deepseek",
+      route: { id: "openai-compatible-chat" },
+    })
+    expect(custom.route.endpoint.baseURL).toBe("https://custom.deepseek.test/v1")
+  })

  it.effect("matches AI SDK compatible basic request body fixture", () =>
    Effect.gen(function* () {
@@ -407,6 +405,19 @@ describe("OpenAI-compatible Chat route", () => {
    }),
  )

+  it.effect("ignores events after the done sentinel", () =>
+    Effect.gen(function* () {
+      const body = `${sseEvents(
+        deltaChunk({ content: "Hello" }),
+        deltaChunk({}, "stop"),
+      )}data: ${JSON.stringify(deltaChunk({ content: " late" }))}\n\n`
+      const response = yield* LLMClient.generate(request).pipe(Effect.provide(fixedResponse(body)))
+
+      expect(response.text).toBe("Hello")
+      expect(response.finishReason).toEqual({ normalized: "stop", raw: "stop" })
+    }),
+  )
+
  it.effect("accepts nullable usage and preserves provider fields", () =>
    Effect.gen(function* () {
      const response = yield* LLMClient.generate(request).pipe(
@@ -2750,6 +2750,227 @@ describe("OpenAI Responses route", () => {
    }),
  )

+  it.effect("concludes reasoning at implicit summary boundaries", () =>
+    Effect.gen(function* () {
+      const response = yield* LLMClient.generate(
+        LLMRequest.update(request, { providerOptions: { store: false } }),
+      ).pipe(
+        Effect.provide(
+          fixedResponse(
+            sseEvents(
+              {
+                type: "response.output_item.added",
+                item: { type: "reasoning", id: "rs_1", encrypted_content: null },
+              },
+              { type: "response.reasoning_summary_part.added", item_id: "rs_1", summary_index: 0 },
+              { type: "response.reasoning_summary_text.delta", item_id: "rs_1", summary_index: 0, delta: "First" },
+              // The next part is enough to conclude the previous one even when
+              // its done event is delayed.
+              { type: "response.reasoning_summary_part.added", item_id: "rs_1", summary_index: 1 },
+              { type: "response.reasoning_summary_part.done", item_id: "rs_1", summary_index: 0 },
+              { type: "response.reasoning_summary_text.delta", item_id: "rs_1", summary_index: 1, delta: "Second" },
+              { type: "response.reasoning_summary_part.done", item_id: "rs_1", summary_index: 1 },
+              // Some compatible providers begin the next part with its first delta.
+              { type: "response.reasoning_summary_text.delta", item_id: "rs_1", summary_index: 2, delta: "Third" },
+              {
+                type: "response.output_item.done",
+                item: { type: "reasoning", id: "rs_1", encrypted_content: "encrypted-state" },
+              },
+              { type: "response.completed", response: { id: "resp_1" } },
+            ),
+          ),
+        ),
+      )
+
+      expect(response.reasoning).toBe("FirstSecondThird")
+      expect(response.events.filter((event) => event.type.startsWith("reasoning-"))).toEqual([
+        {
+          type: "reasoning-start",
+          id: "rs_1:0",
+          providerMetadata: { openai: { itemId: "rs_1", reasoningEncryptedContent: null } },
+        },
+        { type: "reasoning-delta", id: "rs_1:0", text: "First", providerMetadata: undefined },
+        { type: "reasoning-end", id: "rs_1:0", providerMetadata: { openai: { itemId: "rs_1" } } },
+        {
+          type: "reasoning-start",
+          id: "rs_1:1",
+          providerMetadata: { openai: { itemId: "rs_1", reasoningEncryptedContent: null } },
+        },
+        { type: "reasoning-delta", id: "rs_1:1", text: "Second", providerMetadata: undefined },
+        {
+          type: "reasoning-end",
+          id: "rs_1:1",
+          providerMetadata: { openai: { itemId: "rs_1" } },
+        },
+        {
+          type: "reasoning-start",
+          id: "rs_1:2",
+          providerMetadata: { openai: { itemId: "rs_1", reasoningEncryptedContent: null } },
+        },
+        { type: "reasoning-delta", id: "rs_1:2", text: "Third", providerMetadata: undefined },
+        {
+          type: "reasoning-end",
+          id: "rs_1:2",
+          providerMetadata: { openai: { itemId: "rs_1", reasoningEncryptedContent: "encrypted-state" } },
+        },
+      ])
+    }),
+  )
+
+  it.effect("rejects a reasoning item that starts before the previous item ends", () =>
+    Effect.gen(function* () {
+      const error = yield* LLMClient.generate(request).pipe(
+        Effect.provide(
+          fixedResponse(
+            sseEvents(
+              { type: "response.output_item.added", item: { type: "reasoning", id: "rs_1" } },
+              { type: "response.reasoning_summary_text.delta", item_id: "rs_1", summary_index: 0, delta: "First" },
+              { type: "response.output_item.added", item: { type: "reasoning", id: "rs_2" } },
+            ),
+          ),
+        ),
+        Effect.flip,
+      )
+
+      expect(error.reason._tag).toBe("InvalidProviderOutput")
+      expect(error.message).toContain("started reasoning before the previous item ended")
+    }),
+  )
+
+  it.effect("concludes text at implicit message boundaries", () =>
+    Effect.gen(function* () {
+      const response = yield* LLMClient.generate(request).pipe(
+        Effect.provide(
+          fixedResponse(
+            sseEvents(
+              // An item that never streams text is untracked at the boundary too.
+              { type: "response.output_item.added", item: { type: "message", id: "msg_0" } },
+              { type: "response.output_item.added", item: { type: "message", id: "msg_1" } },
+              { type: "response.output_text.delta", item_id: "msg_1", delta: "First" },
+              // The previous message's done event is missing; the next message
+              // item is the boundary for its open text.
+              { type: "response.output_item.added", item: { type: "message", id: "msg_2" } },
+              // Late deltas for concluded or untracked messages must stay no-ops.
+              { type: "response.output_text.delta", item_id: "msg_1", delta: " late" },
+              { type: "response.output_text.delta", item_id: "msg_0", delta: " stale" },
+              { type: "response.output_text.delta", item_id: "msg_2", delta: "Second" },
+              { type: "response.output_item.done", item: { type: "message", id: "msg_2" } },
+              { type: "response.completed", response: { id: "resp_1" } },
+            ),
+          ),
+        ),
+      )
+
+      expect(response.text).toBe("FirstSecond")
+      expect(response.events.filter((event) => event.type.startsWith("text-"))).toMatchObject([
+        { type: "text-start", id: "msg_1" },
+        { type: "text-delta", id: "msg_1", text: "First" },
+        { type: "text-end", id: "msg_1" },
+        { type: "text-start", id: "msg_2" },
+        { type: "text-delta", id: "msg_2", text: "Second" },
+        { type: "text-end", id: "msg_2" },
+      ])
+    }),
+  )
+
+  it.effect("opens the tool lifecycle for a done-only function call", () =>
+    Effect.gen(function* () {
+      const response = yield* LLMClient.generate(request).pipe(
+        Effect.provide(
+          fixedResponse(
+            sseEvents(
+              // No output_item.added: the call arrives only as a completed item.
+              {
+                type: "response.output_item.done",
+                item: {
+                  type: "function_call",
+                  id: "fc_1",
+                  call_id: "call_1",
+                  name: "lookup",
+                  arguments: '{"query":"weather"}',
+                },
+              },
+              { type: "response.completed", response: { id: "resp_1" } },
+            ),
+          ),
+        ),
+      )
+
+      expect(response.events.filter((event) => event.type.startsWith("tool-"))).toMatchObject([
+        { type: "tool-input-start", id: "call_1", name: "lookup" },
+        { type: "tool-input-end", id: "call_1", name: "lookup" },
+        { type: "tool-call", id: "call_1", name: "lookup", input: { query: "weather" } },
+      ])
+      expect(response.finishReason.normalized).toBe("tool-calls")
+    }),
+  )
+
+  it.effect("ignores duplicate item boundary events", () =>
+    Effect.gen(function* () {
+      const response = yield* LLMClient.generate(request).pipe(
+        Effect.provide(
+          fixedResponse(
+            sseEvents(
+              { type: "response.output_item.added", item: { type: "reasoning", id: "rs_1" } },
+              // Duplicate added for a known item is not overlap and must no-op.
+              { type: "response.output_item.added", item: { type: "reasoning", id: "rs_1" } },
+              { type: "response.reasoning_summary_text.delta", item_id: "rs_1", summary_index: 0, delta: "Think" },
+              { type: "response.output_item.done", item: { type: "reasoning", id: "rs_1" } },
+              { type: "response.output_item.done", item: { type: "reasoning", id: "rs_1" } },
+              {
+                type: "response.output_item.added",
+                item: { type: "function_call", id: "fc_1", call_id: "call_1", name: "lookup", arguments: "" },
+              },
+              {
+                type: "response.output_item.added",
+                item: { type: "function_call", id: "fc_1", call_id: "call_1", name: "lookup", arguments: "" },
+              },
+              { type: "response.function_call_arguments.delta", item_id: "fc_1", delta: '{"query":"weather"}' },
+              {
+                type: "response.output_item.done",
+                item: {
+                  type: "function_call",
+                  id: "fc_1",
+                  call_id: "call_1",
+                  name: "lookup",
+                  arguments: '{"query":"weather"}',
+                },
+              },
+              {
+                type: "response.output_item.done",
+                item: {
+                  type: "function_call",
+                  id: "fc_1",
+                  call_id: "call_1",
+                  name: "lookup",
+                  arguments: '{"query":"weather"}',
+                },
+              },
+              // Duplicates that drop the item id still resolve the same call.
+              {
+                type: "response.output_item.done",
+                item: { type: "function_call", call_id: "call_1", name: "lookup", arguments: '{"query":"weather"}' },
+              },
+              {
+                type: "response.output_item.added",
+                item: { type: "function_call", call_id: "call_1", name: "lookup", arguments: "" },
+              },
+              { type: "response.completed", response: { id: "resp_1" } },
+            ),
+          ),
+        ),
+      )
+
+      expect(response.reasoning).toBe("Think")
+      expect(response.events.filter((event) => event.type === "reasoning-start")).toHaveLength(1)
+      expect(response.events.filter((event) => event.type === "reasoning-end")).toHaveLength(1)
+      expect(response.events.filter((event) => event.type === "tool-input-start")).toHaveLength(1)
+      expect(response.events.filter(LLMEvent.is.toolCall)).toEqual([
+        expect.objectContaining({ id: "call_1", input: { query: "weather" } }),
+      ])
+    }),
+  )
+
  it.effect("reconciles reasoning summaries that arrive only as finals", () =>
    Effect.gen(function* () {
      const response = yield* LLMClient.generate(
@@ -305,9 +305,11 @@ describe("OpenRouter", () => {
      expect(prepared.body.messages).toEqual([
        {
          role: "assistant",
-          content: null,
+          content: "",
          reasoning: "Thinking",
+          reasoning_content: undefined,
          reasoning_details: details,
+          reasoning_text: undefined,
        },
      ])
    }),
@@ -335,7 +337,14 @@ describe("OpenRouter", () => {
      )

      expect(prepared.body.messages).toEqual([
-        { role: "assistant", content: null, reasoning: "Thinking", reasoning_details: details },
+        {
+          role: "assistant",
+          content: "",
+          reasoning: "Thinking",
+          reasoning_content: undefined,
+          reasoning_details: details,
+          reasoning_text: undefined,
+        },
      ])
    }),
  )
@@ -361,7 +370,14 @@ describe("OpenRouter", () => {
      )

      expect(prepared.body.messages).toEqual([
-        { role: "assistant", content: null, reasoning: "AB", reasoning_details: details },
+        {
+          role: "assistant",
+          content: "",
+          reasoning: "AB",
+          reasoning_content: undefined,
+          reasoning_details: details,
+          reasoning_text: undefined,
+        },
      ])
    }),
  )
@@ -376,7 +392,16 @@ describe("OpenRouter", () => {
        }),
      )

-      expect(prepared.body.messages).toEqual([{ role: "assistant", content: null }])
+      expect(prepared.body.messages).toEqual([
+        {
+          role: "assistant",
+          content: "",
+          reasoning: undefined,
+          reasoning_content: undefined,
+          reasoning_details: undefined,
+          reasoning_text: undefined,
+        },
+      ])
    }),
  )
 })
@@ -104,6 +104,60 @@ describe("LLMResponse reducer", () => {
    ])
  })

+  test("authoritative text-end value replaces accumulated deltas", () => {
+    const response = LLMResponse.fromEvents([
+      LLMEvent.textStart({ id: "t1" }),
+      LLMEvent.textDelta({ id: "t1", text: "Hel" }),
+      LLMEvent.textEnd({ id: "t1", text: "Hello!" }),
+      LLMEvent.finish({ reason: { normalized: "stop" } }),
+    ])
+
+    expect(response?.message.content).toEqual([{ type: "text", text: "Hello!" }])
+    expect(response?.text).toBe("Hello!")
+  })
+
+  test("text-end without value keeps joined deltas", () => {
+    const response = LLMResponse.fromEvents([
+      LLMEvent.textStart({ id: "t1" }),
+      LLMEvent.textDelta({ id: "t1", text: "Hel" }),
+      LLMEvent.textDelta({ id: "t1", text: "lo" }),
+      LLMEvent.textEnd({ id: "t1" }),
+      LLMEvent.finish({ reason: { normalized: "stop" } }),
+    ])
+
+    expect(response?.message.content).toEqual([{ type: "text", text: "Hello" }])
+    expect(response?.text).toBe("Hello")
+  })
+
+  test("authoritative reasoning-end value replaces only its own fragment", () => {
+    const response = LLMResponse.fromEvents([
+      LLMEvent.reasoningStart({ id: "r1:0" }),
+      LLMEvent.reasoningDelta({ id: "r1:0", text: "First summ" }),
+      LLMEvent.reasoningEnd({ id: "r1:0", text: "First summary." }),
+      LLMEvent.reasoningStart({ id: "r1:1" }),
+      LLMEvent.reasoningDelta({ id: "r1:1", text: "Second summary." }),
+      LLMEvent.reasoningEnd({ id: "r1:1" }),
+      LLMEvent.finish({ reason: { normalized: "stop" } }),
+    ])
+
+    expect(response?.message.content).toEqual([
+      { type: "reasoning", text: "First summary." },
+      { type: "reasoning", text: "Second summary." },
+    ])
+    expect(response?.reasoning).toBe("First summary.Second summary.")
+  })
+
+  test("end value recovers a fragment that streamed no deltas", () => {
+    const response = LLMResponse.fromEvents([
+      LLMEvent.textStart({ id: "t1" }),
+      LLMEvent.textEnd({ id: "t1", text: "Hello!" }),
+      LLMEvent.finish({ reason: { normalized: "stop" } }),
+    ])
+
+    expect(response?.message.content).toEqual([{ type: "text", text: "Hello!" }])
+    expect(response?.text).toBe("Hello!")
+  })
+
  test("clears malformed tool input without appending an executable call", () => {
    const state = reduce([
      LLMEvent.toolInputStart({ id: "call_1", name: "lookup" }),
@@ -26,6 +26,7 @@ import {
  Usage,
 } from "../src/schema/index.js"
 import { ProviderShared } from "../src/protocols/shared.js"
+import { it } from "./lib/effect.js"

 const model = new LanguageModel({
  id: ModelID.make("fake-model"),
@@ -101,49 +102,48 @@ describe("AI.Usage", () => {
    expect(ProviderShared.sumTokens()).toBeUndefined()
  })

-  test("sseFraming maps decoder failures to AI errors", async () => {
-    const error = await Effect.runPromise(
-      ProviderShared.sseFraming(Stream.make(new TextEncoder().encode(`data: ${"x".repeat(10 * 1024 * 1024)}`))).pipe(
-        Stream.runCollect,
-        Effect.flip,
-      ),
-    )
+  it.effect("sseFraming maps decoder failures to AI errors", () =>
+    Effect.gen(function* () {
+      const error = yield* ProviderShared.sseFraming(
+        Stream.make(new TextEncoder().encode(`data: ${"x".repeat(10 * 1024 * 1024)}`)),
+      ).pipe(Stream.runCollect, Effect.flip)

-    expect(error).toBeInstanceOf(AIError)
-    expect(error.reason._tag).toBe("InvalidProviderOutput")
-  })
+      expect(error).toBeInstanceOf(AIError)
+      expect(error.reason._tag).toBe("InvalidProviderOutput")
+    }),
+  )

-  test("sseFraming ignores retry directives without ending the stream", async () => {
-    const encoder = new TextEncoder()
-    const frames = await Effect.runPromise(
-      ProviderShared.sseFraming(
+  it.effect("sseFraming ignores retry directives without ending the stream", () =>
+    Effect.gen(function* () {
+      const encoder = new TextEncoder()
+      const frames = yield* ProviderShared.sseFraming(
        Stream.make(
          encoder.encode("retry: 1000\n\n"),
          encoder.encode('data: {"first":true}\n\n'),
          encoder.encode("retry: 2000\n\n"),
          encoder.encode('data: {"second":true}\n\n'),
        ).pipe(Stream.rechunk(1)),
-      ).pipe(Stream.runCollect),
-    )
+      ).pipe(Stream.runCollect)

-    expect(Array.from(frames)).toEqual(['{"first":true}', '{"second":true}'])
-  })
+      expect(Array.from(frames)).toEqual(['{"first":true}', '{"second":true}'])
+    }),
+  )

-  test("sseFraming preserves event data around retry directives", async () => {
-    const encoder = new TextEncoder()
-    const frames = await Effect.runPromise(
-      ProviderShared.sseFraming(
+  it.effect("sseFraming preserves event data around retry directives", () =>
+    Effect.gen(function* () {
+      const encoder = new TextEncoder()
+      const frames = yield* ProviderShared.sseFraming(
        Stream.make(
          encoder.encode("event: update\ndata: first\n"),
          encoder.encode("retry: 1000\n"),
          encoder.encode("data: second\n\n"),
        ).pipe(Stream.rechunk(1)),
        new Set(["update"]),
-      ).pipe(Stream.runCollect),
-    )
+      ).pipe(Stream.runCollect)

-    expect(Array.from(frames)).toEqual(["first\nsecond"])
-  })
+      expect(Array.from(frames)).toEqual(["first\nsecond"])
+    }),
+  )

  test("visibleOutputTokens clamps reasoning > output to zero", () => {
    expect(new Usage({ outputTokens: 10, reasoningTokens: 4 }).visibleOutputTokens).toBe(6)
@@ -153,18 +153,18 @@ describe("AI.Usage", () => {
  })
 })

-test("AI errors expose the shared runtime tag", async () => {
-  const error = new AIError({
-    reason: new InvalidRequestError({ message: "invalid" }),
-  })
-  expect(error._tag).toBe("AI.Error")
-  expect(error.message).toBe("invalid")
-  expect(error.cause).toBe(error.reason)
-  expect(error.reason.cause).toBeUndefined()
-  expect(
-    await Effect.runPromise(Effect.fail(error).pipe(Effect.catchTag("AI.Error", () => Effect.succeed("caught")))),
-  ).toBe("caught")
-})
+it.effect("AI errors expose the shared runtime tag", () =>
+  Effect.gen(function* () {
+    const error = new AIError({
+      reason: new InvalidRequestError({ message: "invalid" }),
+    })
+    expect(error._tag).toBe("AI.Error")
+    expect(error.message).toBe("invalid")
+    expect(error.cause).toBe(error.reason)
+    expect(error.reason.cause).toBeUndefined()
+    expect(yield* Effect.fail(error).pipe(Effect.catchTag("AI.Error", () => Effect.succeed("caught")))).toBe("caught")
+  }),
+)

 test("transport errors serialize execution facts", () => {
  const reason = new TransportError({
@@ -250,7 +250,7 @@ test("AI error reasons are tagged Errors with required messages", () => {
      provider: model.provider,
      model: model.id,
    }),
-    new AuthenticationError({ message: "Missing credentials", kind: "missing" }),
+    new AuthenticationError({ message: "Missing credentials" }),
    new RateLimitError({ message: "Rate limited" }),
    new QuotaExceededError({ message: "Quota exceeded" }),
    new ContentPolicyError({ message: "Content blocked" }),
@@ -0,0 +1,331 @@
+import { describe, expect } from "bun:test"
+import { AIError, LanguageModel, LLM, LLMClient, LLMEvent, LLMRequest, RateLimitError } from "../src/index.js"
+import { OpenAIChat } from "../src/protocols/openai-chat.js"
+import { TestLLM } from "../src/testing.js"
+import { Effect, Fiber, Latch, Stream } from "effect"
+import { testEffect } from "./lib/effect.js"
+
+const request = LLM.request({
+  model: LanguageModel.make({ id: "fictional-model", provider: "fixture", route: OpenAIChat.route }),
+  prompt: "Say hello",
+})
+const legacy = testEffect(TestLLM.layer())
+const it = testEffect(TestLLM.testLayer())
+
+describe("TestLLM legacy client", () => {
+  legacy.effect("does not observe requests or consume responses until execution", () =>
+    Effect.gen(function* () {
+      const llm = yield* TestLLM.Service
+      yield* llm.push(TestLLM.text("first", "first"), TestLLM.text("second", "second"))
+
+      llm.client.stream(request)
+      llm.client.generate(request)
+      expect(llm.requests).toEqual([])
+
+      expect((yield* llm.client.generate(request)).text).toBe("first")
+      expect((yield* llm.client.generate(request)).text).toBe("second")
+      expect(llm.requests).toEqual([request, request])
+    }),
+  )
+
+  legacy.effect("assigns and records a fresh response for each execution", () =>
+    Effect.gen(function* () {
+      const llm = yield* TestLLM.Service
+      yield* llm.push(
+        TestLLM.text("first", "first"),
+        TestLLM.text("second", "second"),
+        TestLLM.text("third", "third"),
+        TestLLM.text("fourth", "fourth"),
+      )
+      const stream = llm.client.stream(request)
+      const generate = llm.client.generate(request)
+
+      expect(yield* Stream.runCollect(stream)).toEqual(TestLLM.text("first", "first"))
+      expect(yield* Stream.runCollect(stream)).toEqual(TestLLM.text("second", "second"))
+      expect((yield* generate).text).toBe("third")
+      expect((yield* generate).text).toBe("fourth")
+      expect(llm.requests).toEqual([request, request, request, request])
+    }),
+  )
+
+  legacy.effect("keeps module-level controls and clientLayer on the same backing state", () =>
+    Effect.gen(function* () {
+      const llm = yield* TestLLM.Service
+      const requests = llm.requests
+      yield* TestLLM.push(TestLLM.text("queued", "queued"))
+      yield* TestLLM.always(TestLLM.text("fallback", "fallback"))
+      expect((yield* LLMClient.generate(request).pipe(Effect.provide(TestLLM.clientLayer))).text).toBe("queued")
+      yield* TestLLM.wait(1)
+      expect(requests).toEqual([request])
+      requests.length = 0
+      expect((yield* llm.client.generate(request)).text).toBe("fallback")
+      expect(llm.requests).toBe(requests)
+      expect(requests).toEqual([request])
+    }),
+  )
+})
+
+describe("TestLLM first-class client", () => {
+  it.effect("provides the same object under normal and test tags with snapshot observations", () =>
+    Effect.gen(function* () {
+      const llm = yield* TestLLM.Test
+      const client = yield* LLMClient.Service
+      expect(client).toBe(llm)
+      const before = yield* llm.requests()
+      yield* llm.push(TestLLM.text("hello", "answer"))
+      const generate = client.generate(request)
+      client.stream(request)
+      expect(yield* llm.requests()).toEqual([])
+
+      expect((yield* generate).text).toBe("hello")
+      expect(before).toEqual([])
+      expect(yield* llm.requests()).toEqual([request])
+      expect(yield* llm.requests()).not.toBe(yield* llm.requests())
+    }),
+  )
+
+  it.effect("prioritizes queued replies over request-dependent and constant fallbacks", () =>
+    Effect.gen(function* () {
+      const llm = yield* TestLLM.Test
+      const served: LLMRequest[] = []
+      yield* llm.always(TestLLM.text("old fallback", "old"))
+      yield* llm.push(TestLLM.text("first", "first"), TestLLM.text("second", "second"))
+      yield* llm.serve((request) => {
+        served.push(request)
+        return TestLLM.text(request.promptCacheKey ?? "default", "served")
+      })
+
+      expect((yield* LLMClient.generate(request)).text).toBe("first")
+      expect((yield* LLMClient.generate(request)).text).toBe("second")
+      expect(served).toEqual([])
+      const selected = LLMRequest.update(request, { promptCacheKey: "selected" })
+      expect((yield* LLMClient.generate(selected)).text).toBe("selected")
+      expect((yield* LLMClient.generate(request)).text).toBe("default")
+      expect(served).toEqual([selected, request])
+
+      yield* llm.push(TestLLM.text("queued again", "queued"))
+      yield* llm.always(TestLLM.text("constant", "constant"))
+      expect((yield* LLMClient.generate(request)).text).toBe("queued again")
+      expect((yield* LLMClient.generate(request)).text).toBe("constant")
+      expect((yield* LLMClient.generate(request)).text).toBe("constant")
+      expect(served).toEqual([selected, request])
+    }),
+  )
+
+  testEffect(
+    TestLLM.testLayer({
+      transformRequest: (request) => LLMRequest.update(request, { promptCacheKey: "observation" }),
+    }),
+  ).effect("transforms observations without changing the request passed to the responder", () =>
+    Effect.gen(function* () {
+      const llm = yield* TestLLM.Test
+      yield* llm.serve((input) => {
+        expect(input).toBe(request)
+        return TestLLM.text("original", "answer")
+      })
+      const generate = llm.generate(request)
+      expect(yield* llm.requests()).toEqual([])
+      expect((yield* generate).text).toBe("original")
+      expect(yield* llm.requests()).toEqual([LLMRequest.update(request, { promptCacheKey: "observation" })])
+    }),
+  )
+
+  it.effect("broadcasts request-arrival waits and satisfies waits registered afterward", () =>
+    Effect.gen(function* () {
+      const llm = yield* TestLLM.Test
+      yield* llm.always(TestLLM.stop())
+      const first = yield* llm.wait(2).pipe(Effect.forkChild({ startImmediately: true }))
+      const second = yield* llm.wait(2).pipe(Effect.forkChild({ startImmediately: true }))
+      yield* llm.generate(request)
+      expect(first.pollUnsafe()).toBeUndefined()
+      expect(second.pollUnsafe()).toBeUndefined()
+      yield* llm.generate(request)
+      yield* Fiber.join(first)
+      yield* Fiber.join(second)
+      yield* llm.wait(2)
+      expect(yield* llm.requests()).toHaveLength(2)
+    }),
+  )
+  ;(["queued", "served"] as const).forEach((mode) => {
+    it.effect(`assigns ${mode} replies before resuming request-arrival continuations`, () =>
+      Effect.gen(function* () {
+        const llm = yield* TestLLM.Test
+        const responses = [TestLLM.text("first", "first"), TestLLM.text("second", "second")]
+        yield* mode === "queued" ? llm.push(...responses) : llm.serve(() => responses.shift() ?? [])
+        const later = yield* llm
+          .wait(1)
+          .pipe(Effect.andThen(llm.generate(request)), Effect.forkChild({ startImmediately: true }))
+
+        expect((yield* llm.generate(request)).text).toBe("first")
+        expect((yield* Fiber.join(later)).text).toBe("second")
+        expect(yield* llm.requests()).toEqual([request, request])
+      }),
+    )
+  })
+
+  it.effect("notifies arrival waiters even when the responder defects", () =>
+    Effect.gen(function* () {
+      const llm = yield* TestLLM.Test
+      const defect = new Error("Broken fixture responder")
+      yield* llm.serve(() => {
+        throw defect
+      })
+      const waiter = yield* llm.wait(1).pipe(Effect.forkChild({ startImmediately: true }))
+      expect(yield* llm.generate(request).pipe(Effect.catchDefect(Effect.succeed))).toBe(defect)
+      yield* Fiber.join(waiter)
+    }),
+  )
+
+  it.effect("builds independent state even when the same layer is provided concurrently", () => {
+    const layer = TestLLM.testLayer()
+    const run = Effect.gen(function* () {
+      const llm = yield* TestLLM.Test
+      expect(yield* llm.requests()).toEqual([])
+      yield* llm.push(TestLLM.text("one", "answer"))
+      expect((yield* LLMClient.generate(request)).text).toBe("one")
+      return yield* llm.requests()
+    }).pipe(Effect.provide(layer))
+    return Effect.gen(function* () {
+      expect(yield* Effect.all([run, run], { concurrency: "unbounded" })).toEqual([[request], [request]])
+    })
+  })
+
+  it.effect("counts concurrent starts on one gate without serializing their response assignment", () =>
+    Effect.gen(function* () {
+      const llm = yield* TestLLM.Test
+      yield* llm.push(TestLLM.text("first", "first"), TestLLM.text("second", "second"))
+      const generate = llm.generate(request)
+      const gate = yield* llm.gate()
+      const first = yield* generate.pipe(Effect.forkChild({ startImmediately: true }))
+      yield* gate.started
+      const second = yield* generate.pipe(Effect.forkChild({ startImmediately: true }))
+      yield* gate.started
+      yield* llm.wait(2)
+      expect(first.pollUnsafe()).toBeUndefined()
+      expect(second.pollUnsafe()).toBeUndefined()
+      yield* gate.release
+      expect((yield* Fiber.join(first)).text).toBe("first")
+      expect((yield* Fiber.join(second)).text).toBe("second")
+    }),
+  )
+
+  it.effect("does not clear a replacement gate when the previous gate is released", () =>
+    Effect.gen(function* () {
+      const llm = yield* TestLLM.Test
+      yield* llm.always(TestLLM.stop())
+      const previous = yield* llm.gate()
+      const first = yield* llm.generate(request).pipe(Effect.forkChild({ startImmediately: true }))
+      yield* previous.started
+      const next = yield* llm.gate()
+      yield* previous.release
+      yield* Fiber.join(first)
+
+      const second = yield* llm.generate(request).pipe(Effect.forkChild({ startImmediately: true }))
+      yield* next.started
+      expect(second.pollUnsafe()).toBeUndefined()
+      yield* next.release
+      yield* Fiber.join(second)
+    }),
+  )
+
+  it.effect("releases a gate when its deliberately narrower scope closes", () =>
+    Effect.gen(function* () {
+      const llm = yield* TestLLM.Test
+      yield* llm.always(TestLLM.stop())
+      // Only the gate is scoped here; its release must happen before the test ends.
+      const run = yield* Effect.scoped(
+        Effect.gen(function* () {
+          const gate = yield* llm.gate()
+          const run = yield* llm.generate(request).pipe(Effect.forkChild({ startImmediately: true }))
+          yield* gate.started
+          return run
+        }),
+      )
+      yield* Fiber.join(run)
+      yield* llm.generate(request)
+      expect(yield* llm.requests()).toHaveLength(2)
+    }),
+  )
+
+  it.effect("keeps an executed response consumed after interruption and permits later requests", () =>
+    Effect.gen(function* () {
+      const llm = yield* TestLLM.Test
+      yield* llm.push(TestLLM.text("interrupted", "first"), TestLLM.text("next", "second"))
+      const gate = yield* llm.gate()
+      const run = yield* llm.generate(request).pipe(Effect.forkChild({ startImmediately: true }))
+      yield* gate.started
+      yield* Fiber.interrupt(run)
+      yield* gate.release
+      expect((yield* llm.generate(request)).text).toBe("next")
+      expect(yield* llm.requests()).toHaveLength(2)
+    }),
+  )
+
+  it.effect("consumes a supplied stream's post-finish tail and runs its finalizer", () =>
+    Effect.gen(function* () {
+      const llm = yield* TestLLM.Test
+      const tail = yield* Latch.make()
+      const release = yield* Latch.make()
+      const finalized = yield* Latch.make()
+      yield* llm.push(
+        Stream.unwrap(
+          Effect.gen(function* () {
+            yield* Effect.addFinalizer(() => finalized.open)
+            return Stream.fromIterable(TestLLM.text("complete", "answer")).pipe(
+              Stream.concat(Stream.fromEffect(tail.open.pipe(Effect.andThen(release.await))).pipe(Stream.drain)),
+            )
+          }),
+        ),
+      )
+      const run = yield* llm.generate(request).pipe(Effect.forkChild({ startImmediately: true }))
+      yield* tail.await
+      expect(run.pollUnsafe()).toBeUndefined()
+      yield* release.open
+      expect((yield* Fiber.join(run)).text).toBe("complete")
+      yield* finalized.await
+    }),
+  )
+
+  it.effect("preserves irregular events, ordinary EOF, typed failures, and responder defects", () =>
+    Effect.gen(function* () {
+      const llm = yield* TestLLM.Test
+      const events = [LLMEvent.textDelta({ id: "without-start", text: "partial" })]
+      yield* llm.push(events, [])
+      expect(yield* Stream.runCollect(llm.stream(request))).toEqual(events)
+      expect(yield* Stream.runCollect(llm.stream(request))).toEqual([])
+
+      const failure = new AIError({ reason: new RateLimitError({ message: "Try later" }) })
+      const observed: LLMEvent[] = []
+      yield* llm.serve(() => TestLLM.failAfter(failure, ...events))
+      expect(
+        yield* llm.stream(request).pipe(
+          Stream.runForEach((event) => Effect.sync(() => observed.push(event))),
+          Effect.flip,
+        ),
+      ).toBe(failure)
+      expect(observed).toEqual(events)
+      expect(yield* llm.generate(request).pipe(Effect.flip)).toBe(failure)
+
+      const defect = new Error("Broken fixture responder")
+      yield* llm.serve(() => {
+        throw defect
+      })
+      expect(yield* llm.generate(request).pipe(Effect.catchDefect(Effect.succeed))).toBe(defect)
+      yield* llm.push(TestLLM.text("recovered", "answer"))
+      expect((yield* llm.generate(request)).text).toBe("recovered")
+    }),
+  )
+
+  it.effect("defects on unexpected requests instead of waiting for a late script", () =>
+    Effect.gen(function* () {
+      const llm = yield* TestLLM.Test
+      const defect = yield* llm.generate(request).pipe(Effect.catchDefect(Effect.succeed))
+      expect(defect).toBeInstanceOf(Error)
+      if (!(defect instanceof Error)) return
+      expect(defect.message).toBe("TestLLM has no response for request 1")
+      expect(yield* llm.requests()).toEqual([request])
+      yield* llm.push(TestLLM.stop())
+      yield* llm.generate(request)
+    }),
+  )
+})
@@ -1,4 +1,4 @@
-import { describe, expect } from "bun:test"
+import { describe, expect, test } from "bun:test"
 import { Content } from "@opencode-ai/schema/tool"
 import { Effect, Schema, Stream } from "effect"
 import {
@@ -277,65 +277,61 @@ describe("LLMClient tools", () => {
    }),
  )

-  it.effect("models canonical tool files with URIs", () =>
-    Effect.sync(() => {
-      const decode = Schema.decodeUnknownSync(Content)
+  test("models canonical tool files with URIs", () => {
+    const decode = Schema.decodeUnknownSync(Content)

-      expect(decode({ type: "file", uri: "data:image/png;base64,AAAA", mime: "image/png" })).toEqual({
-        type: "file",
-        uri: "data:image/png;base64,AAAA",
-        mime: "image/png",
-      })
-      expect(decode({ type: "file", uri: "https://example.test/image.png", mime: "image/png" })).toEqual({
-        type: "file",
-        uri: "https://example.test/image.png",
-        mime: "image/png",
-      })
-      expect(decode({ type: "file", uri: "file:///tmp/image.png", mime: "image/png" })).toEqual({
-        type: "file",
-        uri: "file:///tmp/image.png",
-        mime: "image/png",
-      })
-    }),
-  )
+    expect(decode({ type: "file", uri: "data:image/png;base64,AAAA", mime: "image/png" })).toEqual({
+      type: "file",
+      uri: "data:image/png;base64,AAAA",
+      mime: "image/png",
+    })
+    expect(decode({ type: "file", uri: "https://example.test/image.png", mime: "image/png" })).toEqual({
+      type: "file",
+      uri: "https://example.test/image.png",
+      mime: "image/png",
+    })
+    expect(decode({ type: "file", uri: "file:///tmp/image.png", mime: "image/png" })).toEqual({
+      type: "file",
+      uri: "file:///tmp/image.png",
+      mime: "image/png",
+    })
+  })

-  it.effect("preserves canonical tool file URIs", () =>
-    Effect.sync(() => {
-      expect(
-        ToolOutput.toResultValue(
-          ToolOutput.make({}, [{ type: "file", uri: "data:image/png;base64,AAAA", mime: "image/png" }]),
-        ),
-      ).toEqual({
-        type: "content",
-        value: [{ type: "file", uri: "data:image/png;base64,AAAA", mime: "image/png" }],
-      })
-      expect(
-        ToolOutput.toResultValue(
-          ToolOutput.make({}, [{ type: "file", uri: "https://example.test/image.png", mime: "image/png" }]),
-        ),
-      ).toEqual({
+  test("preserves canonical tool file URIs", () => {
+    expect(
+      ToolOutput.toResultValue(
+        ToolOutput.make({}, [{ type: "file", uri: "data:image/png;base64,AAAA", mime: "image/png" }]),
+      ),
+    ).toEqual({
+      type: "content",
+      value: [{ type: "file", uri: "data:image/png;base64,AAAA", mime: "image/png" }],
+    })
+    expect(
+      ToolOutput.toResultValue(
+        ToolOutput.make({}, [{ type: "file", uri: "https://example.test/image.png", mime: "image/png" }]),
+      ),
+    ).toEqual({
+      type: "content",
+      value: [{ type: "file", uri: "https://example.test/image.png", mime: "image/png" }],
+    })
+    expect(
+      ToolOutput.toResultValue(
+        ToolOutput.make({}, [{ type: "file", uri: "file:///tmp/image.png", mime: "image/png" }]),
+      ),
+    ).toEqual({
+      type: "content",
+      value: [{ type: "file", uri: "file:///tmp/image.png", mime: "image/png" }],
+    })
+    expect(
+      ToolOutput.fromResultValue({
        type: "content",
        value: [{ type: "file", uri: "https://example.test/image.png", mime: "image/png" }],
-      })
-      expect(
-        ToolOutput.toResultValue(
-          ToolOutput.make({}, [{ type: "file", uri: "file:///tmp/image.png", mime: "image/png" }]),
-        ),
-      ).toEqual({
-        type: "content",
-        value: [{ type: "file", uri: "file:///tmp/image.png", mime: "image/png" }],
-      })
-      expect(
-        ToolOutput.fromResultValue({
-          type: "content",
-          value: [{ type: "file", uri: "https://example.test/image.png", mime: "image/png" }],
-        }),
-      ).toEqual({
-        structured: {},
-        content: [{ type: "file", uri: "https://example.test/image.png", mime: "image/png" }],
-      })
-    }),
-  )
+      }),
+    ).toEqual({
+      structured: {},
+      content: [{ type: "file", uri: "https://example.test/image.png", mime: "image/png" }],
+    })
+  })

  it.effect("settles projected URL files as canonical tool results", () =>
    Effect.gen(function* () {
@@ -364,24 +360,22 @@ describe("LLMClient tools", () => {
    }),
  )

-  it.effect("derives typed output schemas and preserves dynamic output schemas", () =>
-    Effect.sync(() => {
-      const [typed] = toDefinitions({ get_weather })
-      const schema = { type: "object", properties: { result: { type: "string" } } } as const
-      const [dynamic] = toDefinitions({
-        dynamic: Tool.make({ description: "Dynamic tool.", jsonSchema: { type: "object" }, outputSchema: schema }),
-      })
+  test("derives typed output schemas and preserves dynamic output schemas", () => {
+    const [typed] = toDefinitions({ get_weather })
+    const schema = { type: "object", properties: { result: { type: "string" } } } as const
+    const [dynamic] = toDefinitions({
+      dynamic: Tool.make({ description: "Dynamic tool.", jsonSchema: { type: "object" }, outputSchema: schema }),
+    })

-      expect(typed?.outputSchema).toMatchObject({
-        type: "object",
-        properties: { condition: { type: "string" } },
-        required: ["temperature", "condition"],
-        additionalProperties: false,
-      })
-      expect(Reflect.get(Reflect.get(typed?.outputSchema ?? {}, "properties") as object, "temperature")).toBeDefined()
-      expect(dynamic?.outputSchema).toEqual(schema)
-    }),
-  )
+    expect(typed?.outputSchema).toMatchObject({
+      type: "object",
+      properties: { condition: { type: "string" } },
+      required: ["temperature", "condition"],
+      additionalProperties: false,
+    })
+    expect(Reflect.get(Reflect.get(typed?.outputSchema ?? {}, "properties") as object, "temperature")).toBeDefined()
+    expect(dynamic?.outputSchema).toEqual(schema)
+  })

  it.effect("preserves content tool results from dynamic tools", () =>
    Effect.gen(function* () {
@@ -1,4 +1,4 @@
-import { describe, expect } from "bun:test"
+import { describe, expect, test } from "bun:test"
 import { Effect } from "effect"
 import { AIError } from "../src/schema/index.js"
 import { ToolStream } from "../src/protocols/utils/tool-stream.js"
@@ -38,44 +38,40 @@ describe("ToolStream", () => {
    }),
  )

-  it.effect("exposes cumulative partial string values", () =>
-    Effect.gen(function* () {
-      const result = ToolStream.appendOrStart(
-        ADAPTER,
-        ToolStream.empty<number>(),
-        0,
-        { id: "call_1", name: "lookup", text: '{"query":"wea' },
-        "missing tool",
-      )
-      if (ToolStream.isError(result)) return yield* result
+  test("exposes cumulative partial string values", () => {
+    const result = ToolStream.appendOrStart(
+      ADAPTER,
+      ToolStream.empty<number>(),
+      0,
+      { id: "call_1", name: "lookup", text: '{"query":"wea' },
+      "missing tool",
+    )
+    if (ToolStream.isError(result)) throw result

-      expect(result.events.at(-1)).toEqual({
-        type: "tool-input-delta",
-        id: "call_1",
-        name: "lookup",
-        text: '{"query":"wea',
-        input: { query: "wea" },
-      })
-    }),
-  )
+    expect(result.events.at(-1)).toEqual({
+      type: "tool-input-delta",
+      id: "call_1",
+      name: "lookup",
+      text: '{"query":"wea',
+      input: { query: "wea" },
+    })
+  })

-  it.effect("defaults partial input to an empty object when the accumulated value cannot be parsed", () =>
-    Effect.gen(function* () {
-      const result = ToolStream.appendOrStart(
-        ADAPTER,
-        ToolStream.empty<number>(),
-        0,
-        { id: "call_1", name: "lookup", text: "x" },
-        "missing tool",
-      )
-      if (ToolStream.isError(result)) return yield* result
+  test("defaults partial input to an empty object when the accumulated value cannot be parsed", () => {
+    const result = ToolStream.appendOrStart(
+      ADAPTER,
+      ToolStream.empty<number>(),
+      0,
+      { id: "call_1", name: "lookup", text: "x" },
+      "missing tool",
+    )
+    if (ToolStream.isError(result)) throw result

-      expect(result.events).toEqual([
-        { type: "tool-input-start", id: "call_1", name: "lookup" },
-        { type: "tool-input-delta", id: "call_1", name: "lookup", text: "x", input: {} },
-      ])
-    }),
-  )
+    expect(result.events).toEqual([
+      { type: "tool-input-start", id: "call_1", name: "lookup" },
+      { type: "tool-input-delta", id: "call_1", name: "lookup", text: "x", input: {} },
+    ])
+  })

  it.effect("keeps accumulated identity when later deltas contain empty strings", () =>
    Effect.gen(function* () {
@@ -104,14 +100,12 @@ describe("ToolStream", () => {
    }),
  )

-  it.effect("fails appendExisting when the provider skipped the tool start", () =>
-    Effect.gen(function* () {
-      const error = ToolStream.appendExisting(ADAPTER, ToolStream.empty<number>(), 0, "{}", "missing tool")
+  test("fails appendExisting when the provider skipped the tool start", () => {
+    const error = ToolStream.appendExisting(ADAPTER, ToolStream.empty<number>(), 0, "{}", "missing tool")

-      expect(error).toBeInstanceOf(AIError)
-      if (ToolStream.isError(error)) expect(error.message).toBe("missing tool")
-    }),
-  )
+    expect(error).toBeInstanceOf(AIError)
+    if (ToolStream.isError(error)) expect(error.message).toBe("missing tool")
+  })

  it.effect("uses final input override without losing accumulated deltas", () =>
    Effect.gen(function* () {
@@ -5,5 +5,5 @@
    "noEmit": true,
    "rootDir": "."
  },
-  "include": ["test/**/*.types.ts"]
+  "include": ["test/**/*.types.ts", "test/testing.test.ts"]
 }
@@ -25,6 +25,7 @@ for (const viewport of [
    const mock = await openDraft(page)
    const pending = await submitPending(page, mock)

+    expect(mock.worktreeRequests).toEqual([expect.objectContaining({ from: directory })])
    await expect(pending.message).toBeInViewport()
    await expect(pending.shimmer).toBeInViewport()
    await testInfo.attach("creating-worktree", {
@@ -184,6 +185,7 @@ test("restores the draft after closing and revisiting a pending session that fai
 async function openDraft(page: Page, options?: { failSessionCreate?: boolean }) {
  const worktree = Promise.withResolvers<{ status: number; json: { directory?: string; message?: string } }>()
  const calls: string[] = []
+  const worktreeRequests: Record<string, unknown>[] = []
  const creates: Record<string, unknown>[] = []
  const prompts: { sessionID: string; body: Record<string, unknown> }[] = []
  const project = {
@@ -216,7 +218,10 @@ async function openDraft(page: Page, options?: { failSessionCreate?: boolean })
  page.on("request", (request) => {
    if (request.method() !== "POST") return
    const path = new URL(request.url()).pathname
-    if (path === `/api/worktree/${projectID}`) calls.push("worktree")
+    if (path === `/api/worktree/${projectID}`) {
+      calls.push("worktree")
+      worktreeRequests.push(request.postDataJSON())
+    }
    if (path === "/api/session") calls.push("session")
    if (/^\/api\/session\/[^/]+\/prompt$/.test(path)) calls.push("prompt")
  })
@@ -274,7 +279,7 @@ async function openDraft(page: Page, options?: { failSessionCreate?: boolean })
  await page.getByRole("menuitem", { name: "New workspace", exact: true }).click()
  await expect(page.getByRole("button", { name: "New workspace", exact: true })).toBeVisible()
  await expect(page.locator('[data-component="composer-editor"]')).toBeEditable()
-  return { worktree, calls, creates, prompts }
+  return { worktree, worktreeRequests, calls, creates, prompts }
 }

 async function submitPending(page: Page, mock: Awaited<ReturnType<typeof openDraft>>) {
@@ -308,8 +308,8 @@ for (const delivery of ["steer", "queue"] as const) {
    })
    const tools = page.locator('[data-timeline-part-ids="tool_queue_read,tool_queue_grep"]')
    await expect(tools).toBeVisible()
-    await expect(tools).toContainText(/Used\s*Read, Grep/)
-    await expect(tools.locator('[data-component="tag"]')).toHaveText("2")
+    await expect(tools).toHaveText(/^Used\s*2 Read, Grep$/)
+    await expect(tools.locator('[data-slot="basic-tool-tool-title"]')).toHaveText("2 Read, Grep")
    await expect(thinking).toHaveCount(0)
    await expect(pending).toBeVisible()
    expect(mock.rows.map((row) => ({ id: row.id, delivery: row.delivery }))).toEqual([
@@ -318,7 +318,7 @@ for (const delivery of ["steer", "queue"] as const) {
    await transcript.screenshot({ path: testInfo.outputPath("pending-steer.png") })

    // Soft assertions let delivery run too, even when the pending ordering regresses.
-    await expect.soft(tools.or(pending)).toHaveText([/Used\s*Read, Grep/, /U2: Also check the retry path\./])
+    await expect.soft(tools.or(pending)).toHaveText([/^Used\s*2 Read, Grep$/, /U2: Also check the retry path\./])
    await expect
      .soft(transcript.locator('[data-timeline-row="AssistantPart"]').filter({ has: tools }))
      .toHaveAttribute("data-message-id", userID)
@@ -350,7 +350,7 @@ for (const delivery of ["steer", "queue"] as const) {
    await expect(response).toHaveAttribute("data-message-id", inboxID)
    await expect(thinking).toHaveCount(0)
    await expect(tools.or(pending).or(response)).toHaveText([
-      /Used\s*Read, Grep/,
+      /^Used\s*2 Read, Grep$/,
      /U2: Also check the retry path\./,
      /A3: Now checking the retry path for U2\./,
    ])
@@ -25,7 +25,7 @@ test("space activates a focused timeline button instead of scrolling", async ({
    seedHistory: true,
  })
  const scroller = page.locator(".scroll-view__viewport", { has: page.locator("[data-timeline-row]") })
-  const trigger = page.getByRole("button", { name: "Used Shell" })
+  const trigger = page.getByRole("button", { name: "Used 1 Shell", exact: true })
  await expect
    .poll(() => scroller.evaluate((element) => element.scrollHeight - element.clientHeight))
    .toBeGreaterThan(300)
@@ -93,7 +93,8 @@ test.describe("regression: session timeline local row state", () => {
    await expectSessionTitle(page, title)

    const group = page.locator('[data-component="collapsed-tool-group"]')
-    const summary = group.getByRole("button", { name: "Used Patch", exact: true })
+    const summary = group.getByRole("button", { name: /^Used \d+ Patch$/ })
+    await expect(summary).toHaveAccessibleName("Used 1 Patch")
    await summary.click()
    await group.locator(`[data-timeline-part-id="${editPartID}"]`).evaluate((element) => {
      element.setAttribute("data-disclosure-probe", "existing")
@@ -109,7 +110,8 @@ test.describe("regression: session timeline local row state", () => {
      if (count === 3) await trigger.click()
      const id = `prt_patch_${count}`
      events.push(...toolEvents({ ...part, id, callID: id }))
-      await expect(group.locator('[data-component="tag"]')).toHaveText(String(count))
+      await expect(summary).toHaveAccessibleName(`Used ${count} Patch`)
+      await expect(summary.locator('[data-slot="basic-tool-tool-title"]')).toHaveText(`${count} Patch`)
      await expect(group).toHaveAttribute("data-timeline-part-ids", new RegExp(`${id}$`))
      await expect(trigger).toHaveAttribute("aria-expanded", String(count === 2))
      await expect(summary).toHaveAttribute("aria-expanded", "true")
@@ -55,7 +55,7 @@ test.describe("regression: session timeline context group resize", () => {
    await devtools.send("Emulation.setCPUThrottlingRate", { rate: 4 })
    const context = page.locator(`[data-timeline-part-ids="${contextIDs.join(",")}"]`).first()
    await expectAppVisible(context)
-    await expect(context.getByRole("button")).toHaveAccessibleName("Used Read, Glob, Grep, List")
+    await expect(context.getByRole("button")).toHaveAccessibleName("Used 4 Read, Glob, Grep, List")

    const contextSelector = `[data-timeline-part-ids="${contextIDs.join(",")}"]`
    const regions = defineVisualRegions({
@@ -88,7 +88,7 @@ test.describe("regression: session timeline context group resize", () => {
      await page.waitForTimeout(delay)
    }

-    await expect(context.getByRole("button")).toHaveAccessibleName("Used Read, Glob, Grep, List")
+    await expect(context.getByRole("button")).toHaveAccessibleName("Used 4 Read, Glob, Grep, List")
    await page.waitForTimeout(700)
    const trace = await stopVisualProbe<keyof typeof regions>(page)
    const labels = trace.samples
@@ -107,7 +107,7 @@ test.describe("regression: session timeline context group resize", () => {
      ]),
    )

-    expect(labels).toEqual(["Used Read, Glob, Grep, List"])
+    expect(labels).toEqual(["Used 4 Read, Glob, Grep, List"])
    expect(issues, JSON.stringify(trace.samples, null, 2)).toEqual([])
  })
 })
@@ -28,7 +28,7 @@ for (const expanded of [false, true]) {
    })
    const trigger = expanded
      ? page.locator(`[data-timeline-part-id="${id}"] [data-slot="collapsible-trigger"]`)
-      : page.getByRole("button", { name: "Used Shell" })
+      : page.getByRole("button", { name: "Used 1 Shell", exact: true })
    await expect(trigger).toHaveAttribute("aria-expanded", String(expanded))
    await trigger.click()
    await expect(trigger).toHaveAttribute("aria-expanded", String(!expanded))
@@ -141,7 +141,7 @@ for (const open of [false, true]) {
    await timeline.send(partUpdated(shell(shellID, "completed", "done")))
    await timeline.send(messageUpdated(completedAssistantInfo(assistant)))
    await timeline.send(status("idle"))
-    const used = group.getByRole("button", { name: "Used Shell", exact: true })
+    const used = group.getByRole("button", { name: "Used 1 Shell", exact: true })
    await expect(used).toHaveAttribute("aria-expanded", "false")
    await used.click()
    await expect(used).toHaveAttribute("aria-expanded", "true")
@@ -150,7 +150,7 @@ for (const open of [false, true]) {
      "aria-expanded",
      String(open),
    )
-    await expect(group.locator('[data-component="tag"]')).toHaveText("1")
+    await expect(used.locator('[data-slot="basic-tool-tool-title"]')).toHaveText("1 Shell")
    await expect(page.locator('[data-timeline-row="Thinking"]')).toHaveCount(0)
    await expect(used).toHaveAttribute("aria-expanded", "true")
    if (!open) await thought.click()
@@ -16,8 +16,9 @@ for (const locale of ["de", "ar"] as const) {
    })

    const group = page.locator(`[data-timeline-part-ids="${ids.join(",")}"]`)
-    await expect(group.getByRole("button")).toHaveAccessibleName(/^Used /)
-    await expect(group.locator('[data-component="tag"]')).toHaveText("2")
+    const names = locale === "de" ? "Lesen, Glob" : "\u0642\u0631\u0627\u0621\u0629, Glob"
+    await expect(group.getByRole("button")).toHaveAccessibleName(`Used 2 ${names}`)
+    await expect(group.locator('[data-slot="basic-tool-tool-title"]')).toHaveText(`2 ${names}`)
    await expect(page.locator("html")).toHaveAttribute("lang", locale)
  })
 }
@@ -105,10 +105,10 @@ for (const summaries of [false, true]) {
      if (profile === "tool") {
        const group = page.locator('[data-component="collapsed-tool-group"]')
        const used = group.locator(':scope > [data-component="collapsible"] > [data-slot="collapsible-trigger"]')
-        await expect(used).toContainText("UsedSkill")
+        await expect(used).toHaveText(/^Used\s*1 Skill$/)
        await expect(used).toHaveAttribute("aria-expanded", "false")
        await expect(page.getByText("Inspecting stability", { exact: true })).toBeHidden()
-        await expect(group.locator('[data-component="tag"]')).toHaveText("1")
+        await expect(used.locator('[data-slot="basic-tool-tool-title"]')).toHaveText("1 Skill")
        await used.click()
        await expect(used).toHaveAttribute("aria-expanded", "true")
        await expect(group.locator(`[data-timeline-part-id="prt_reasoning_tool_${summaries}"]`)).toBeVisible()
@@ -45,10 +45,11 @@ test("expands a mixed collapsed tool stack without expanding its individual call
  const group = page.locator(
    '[data-timeline-part-ids="prt_stack_shell_1,prt_stack_explore,prt_stack_patch,prt_stack_shell_2"]',
  )
-  const summary = group.getByRole("button", { name: "Used Shell, Agent, Patch" })
+  const summary = group.getByRole("button", { name: "Used 4 Shell, Agent, Patch", exact: true })
  await expect(summary).toHaveAttribute("aria-expanded", "false")
  await expect(summary).toHaveCSS("height", "28px")
-  await expect(group.locator('[data-component="tag"]')).toHaveText("4")
+  await expect(summary.locator('[data-slot="basic-tool-tool-title"]')).toHaveText("4 Shell, Agent, Patch")
+  await expect(summary.locator('[data-component="tag"]')).toHaveCount(0)
  await summary.click()
  await expect(summary).toHaveAttribute("aria-expanded", "true")
  await expect(group.locator('[data-slot="context-tool-group-item"]')).toHaveCount(4)
@@ -74,8 +75,8 @@ test("leaves tools expanded by settings outside the collapsed stack", async ({ p

  await expect(page.locator('[data-timeline-part-id="prt_expanded_shell"]')).toBeVisible()
  const group = page.locator('[data-timeline-part-ids="prt_collapsed_patch,prt_collapsed_read"]')
-  await expect(group.getByRole("button", { name: "Used Patch, Read" })).toBeVisible()
-  await expect(group.locator('[data-component="tag"]')).toHaveText("2")
+  await expect(group.getByRole("button", { name: "Used 2 Patch, Read", exact: true })).toBeVisible()
+  await expect(group.locator('[data-slot="basic-tool-tool-title"]')).toHaveText("2 Patch, Read")
  await expect(page.locator('[data-timeline-spacing="tool"]')).toHaveCSS("padding-top", "8px")
 })

@@ -113,7 +114,7 @@ test("combines follow-up patches into one three-file stack inside Used", async (
    ],
  })
  const group = page.locator('[data-component="collapsed-tool-group"]')
-  await group.getByRole("button", { name: "Used Shell, Patch", exact: true }).click()
+  await group.getByRole("button", { name: "Used 2 Shell, Patch", exact: true }).click()
  await expect(group.getByText("2 files", { exact: true })).toBeVisible()
  await timeline.send(
    partUpdated(
@@ -128,7 +129,10 @@ test("combines follow-up patches into one three-file stack inside Used", async (
      ),
    ),
  )
-  await expect(group.locator('[data-component="tag"]')).toHaveText("3")
+  await expect(group.getByRole("button", { name: "Used 3 Shell, Patch", exact: true })).toHaveAttribute(
+    "aria-expanded",
+    "true",
+  )
  await expect(group.locator('[data-component="apply-patch-tool"]')).toHaveCount(1)
  await expect(group.getByText("3 files", { exact: true })).toBeVisible()
  await expect(group.locator('[data-slot="apply-patch-filename"]')).toHaveText(["a.ts", "b.ts", "c.ts"])
@@ -158,8 +162,8 @@ test("keeps failed search calls and their error cards inside the collapsed stack
  await setupTimeline(page, { messages: [userMessage(), assistantMessage(parts)] })

  const group = page.locator('[data-timeline-part-ids="prt_error_glob,prt_error_grep"]')
-  const summary = group.getByRole("button", { name: "Used Glob, Grep" })
-  await expect(group.locator('[data-component="tag"]')).toHaveText("2")
+  const summary = group.getByRole("button", { name: "Used 2 Glob, Grep", exact: true })
+  await expect(summary.locator('[data-slot="basic-tool-tool-title"]')).toHaveText("2 Glob, Grep")
  await summary.click()
  await expect(group.locator('[data-kind="tool-error-card"]')).toHaveCount(2)
  const glob = group.locator('[data-timeline-part-id="prt_error_glob"]')
@@ -52,7 +52,7 @@ test("shows parent lineage while the child timeline loads", async ({ page }) =>

  await page.goto(sessionHref(parentID))
  await expectSessionTitle(page, parentTitle)
-  await page.getByRole("button", { name: "Used Agent" }).click()
+  await page.getByRole("button", { name: "Used 1 Agent", exact: true }).click()
  await page.locator(`a[href="${sessionHref(childID)}"]`).click()
  await Promise.all([requested.promise, expect(page).toHaveURL(sessionHref(childID))])
  await Promise.all([
@@ -77,7 +77,7 @@ test("keeps the parent visible while the child session resolves", async ({ page
  await page.goto(sessionHref(parentID))
  await expectSessionTitle(page, parentTitle)

-  await page.getByRole("button", { name: "Used Agent" }).click()
+  await page.getByRole("button", { name: "Used 1 Agent", exact: true }).click()
  await page.locator(`a[href="${sessionHref(childID)}"]`).click()
  await requested.promise
  await Promise.all([expect(page).toHaveURL(sessionHref(parentID)), expectSessionTitle(page, parentTitle)]).finally(
@@ -195,7 +195,7 @@ async function setup(page: Page, events?: () => OpenCodeEvent[]) {
 async function openChildFromParent(page: Page) {
  await page.goto(sessionHref(parentID))
  await expectSessionTitle(page, parentTitle)
-  await page.getByRole("button", { name: "Used Agent" }).click()
+  await page.getByRole("button", { name: "Used 1 Agent", exact: true }).click()

  const card = page.locator(`a[href="${sessionHref(childID)}"]`)
  await expect(card).toBeVisible()
@@ -209,6 +209,29 @@ test("appearance experimental setting switches tab orientation", async ({ page }
  await page.setViewportSize({ width: 390, height: 360 })
  await version.scrollIntoViewIfNeeded()
  await expect(version).toBeInViewport()
+
+  // Reload the UI-selected preference without seeding settings storage.
+  await page.reload()
+  const href = `/server/${base64Encode(server)}/session/${sessionA.id}`
+  await expect(
+    page
+      .locator('[data-slot="titlebar-tabs"]')
+      .locator(`[data-titlebar-tab-link][href="${href}"]`)
+      .getByText(sessionA.title, { exact: true }),
+  ).toBeVisible()
+  await expect(page.locator('[data-slot="vertical-tabs-sidebar"]')).toHaveCount(0)
+
+  await page.setViewportSize({ width: 1280, height: 720 })
+  await expect(
+    page
+      .locator('[data-slot="vertical-tabs-sidebar"]')
+      .locator(`[data-titlebar-tab-link][href="${href}"]`)
+      .getByText(sessionA.title, { exact: true }),
+  ).toBeVisible()
+  await expect(page.locator('[data-slot="titlebar-tabs"]')).toHaveCount(0)
+  await page.keyboard.press("Control+,")
+  await settings.getByRole("tab", { name: "Appearance" }).click()
+  await expect(layout).toContainText("Vertical")
 })

 test("vertical tab preference falls back to horizontal on mobile", async ({ page }) => {
@@ -198,6 +198,10 @@ fixture(
 fixture(
  "precaches public files of every type and size, excluding deployment metadata and source maps",
  async ({ page, site, builds, context }) => {
+    for (const output of Object.values(builds)) {
+      expect(output["/sw.js.map"]).toBeUndefined()
+      expect(Object.keys(output).some((path) => path.startsWith("/_assets/") && path.endsWith(".map"))).toBe(true)
+    }
    await install(page, site.url)
    const files = ["/nested/data.json", "/nested/font.woff2", "/nested/module.wasm", "/large.bin"]
    await context.setOffline(true)
@@ -42,21 +42,18 @@
    "@playwright/test": "catalog:",
    "@sentry/vite-plugin": "catalog:",
    "@tailwindcss/vite": "4.3.3",
-    "@tsconfig/bun": "1.0.9",
    "@types/bun": "catalog:",
    "@types/luxon": "catalog:",
    "@types/node": "catalog:",
    "@typescript/native-preview": "catalog:",
+    "diff": "catalog:",
    "happy-dom": "20.11.1",
    "tw-animate-css": "1.4.0",
-    "typescript": "catalog:",
-    "vite": "8.2.1",
-    "vite-plugin-icons-spritesheet": "3.0.1",
+    "vite": "8.2.2",
    "vite-plugin-pwa": "1.3.0",
    "vite-plugin-solid": "2.11.14"
  },
  "dependencies": {
-    "@corvu/drawer": "catalog:",
    "@dnd-kit/abstract": "0.5.0",
    "@dnd-kit/dom": "0.5.0",
    "@dnd-kit/helpers": "0.5.0",
@@ -71,28 +68,23 @@
    "@pierre/trees": "1.0.0-beta.4",
    "@sentry/solid": "catalog:",
    "@solid-primitives/event-bus": "1.1.2",
-    "@solid-primitives/event-listener": "2.4.5",
+    "@solid-primitives/event-listener": "catalog:",
    "@solid-primitives/i18n": "2.2.1",
    "@solid-primitives/keyed": "1.5.3",
-    "@solid-primitives/media": "2.3.3",
-    "@solid-primitives/resize-observer": "2.1.5",
+    "@solid-primitives/media": "catalog:",
+    "@solid-primitives/resize-observer": "catalog:",
    "@solid-primitives/scheduled": "1.5.3",
    "@solid-primitives/storage": "catalog:",
    "@solidjs/meta": "catalog:",
    "@solidjs/router": "catalog:",
    "@tanstack/solid-query": "5.91.4",
    "@tanstack/solid-virtual": "catalog:",
-    "diff": "catalog:",
    "effect": "catalog:",
    "fuzzysort": "catalog:",
    "ghostty-web": "github:anomalyco/ghostty-web#83c0a07b8628b748aed073b232cb4b52a6ca11c1",
    "luxon": "catalog:",
-    "marked": "catalog:",
-    "marked-shiki": "catalog:",
    "remeda": "catalog:",
-    "shiki": "catalog:",
    "solid-js": "catalog:",
-    "solid-list": "catalog:",
    "solid-presence": "0.2.0",
    "tailwindcss": "4.3.3"
  }
@@ -1,5 +1,4 @@
 import { base64Encode } from "@opencode-ai/util/encode"
-import { getDirectory } from "@opencode-ai/util/path"
 import type { SessionMessageUser } from "@opencode-ai/client/promise"
 import { Session } from "@opencode-ai/schema/session"
 import { startTransition } from "solid-js"
@@ -13,6 +12,7 @@ import { useData, useServer } from "@/runtime/server/current"
 import { type ServerSDK, useServerSDK } from "@/runtime/server/client"
 import { useTabs } from "@/shell/tabs/tabs"
 import { useWorkspaceLocation } from "@/workspaces/location"
+import { createWorktree } from "@/workspaces/create"
 import { useSessionKey } from "@/session/session-layout"
 import { showToast } from "@/shell/notifications/toast"
 import { SessionRouteKey, SessionStateKey } from "@/runtime/server/scope"
@@ -192,25 +192,17 @@ async function resolveSessionDirectory(input: {
  if (input.worktree === "main") return input.projectDirectory
  if (input.worktree !== "create") return input.worktree

-  return input.serverSDK.api.worktree
-    .create({
-      projectID: input.data.location.info({ directory: input.projectDirectory })?.project.id ?? "",
-      strategy: "git",
-      branch: input.branch,
-      directory: getDirectory(
-        input.data.location.info({ directory: input.projectDirectory })?.project.directory ?? input.projectDirectory,
-      ),
-    })
-    .then(async (created) => {
-      await input.serverSDK.api.location.get({ location: { directory: created.directory } })
-      return created.directory
-    })
-    .catch((error) => {
-      showToast({
-        title: input.language.t("prompt.toast.worktreeCreateFailed.title"),
-        description: errorMessage(input.language, error),
-      })
+  return createWorktree({
+    api: input.serverSDK.api,
+    directory: input.projectDirectory,
+    project: input.data.location.info({ directory: input.projectDirectory })?.project,
+    branch: input.branch,
+  }).catch((error) => {
+    showToast({
+      title: input.language.t("prompt.toast.worktreeCreateFailed.title"),
+      description: errorMessage(input.language, error),
    })
+  })
 }

 function errorMessage(language: ReturnType<typeof useLanguage>, error: unknown) {
@@ -644,7 +644,7 @@ export function persisted<T>(
      : undefined
  if (channel) onCleanup(() => channel.close())

-  const [state, setState, init] = makePersisted(store, {
+  const [state, setState, init] = makePersisted<T, typeof store>(store, {
    name: config.key,
    storage,
    sync: channel ? messageSync(channel) : undefined,
@@ -0,0 +1,135 @@
+import { describe, expect, test } from "bun:test"
+import { createApiForServer } from "./api"
+import { readLocalImage } from "./image"
+
+function setup(
+  respond: (init?: RequestInit) => Response | Promise<Response> = () => new Response(new Uint8Array([0, 127, 255])),
+) {
+  const requests: Array<{ url: URL; init?: RequestInit }> = []
+  const api = createApiForServer({
+    server: { url: "https://server.example:4096", username: "image-user", password: "secret" },
+    fetch: (async (input: string | URL | Request, init?: RequestInit) => {
+      requests.push({ url: new URL(input instanceof Request ? input.url : input), init })
+      return respond(init)
+    }) as typeof fetch,
+  })
+  return { api, requests }
+}
+
+describe("readLocalImage", () => {
+  test.each([
+    ["images/screen #1 + 50% ?.PNG", "/workspace/project", "images/screen%20%231%20%2B%2050%25%20%3F.PNG"],
+    ["C:/tmp/opencode/screen #1.png", "C:/tmp/opencode/", "screen%20%231.png"],
+    ["d:/screen.png", "d:/", "screen.png"],
+    ["D:/charts/screen.png", "D:/charts/", "screen.png"],
+    ["Z:/charts/screen.png", "Z:/charts/", "screen.png"],
+    ["/tmp/opencode/screen #1.png", "/tmp/opencode/", "screen%20%231.png"],
+    ["/screen.png", "/", "screen.png"],
+  ])("reads %s with the correct location and authentication", async (path, directory, encoded) => {
+    const { api, requests } = setup()
+    const signal = new AbortController().signal
+    const blob = await readLocalImage(api, "/workspace/project", path, signal)
+
+    expect(blob).toBeInstanceOf(Blob)
+    expect(blob?.type).toBe("image/png")
+    expect(new Uint8Array(await blob!.arrayBuffer())).toEqual(new Uint8Array([0, 127, 255]))
+    expect(requests).toHaveLength(1)
+    expect(requests[0].url.origin).toBe("https://server.example:4096")
+    expect(requests[0].url.pathname).toBe(`/api/fs/read/${encoded}`)
+    expect([...requests[0].url.searchParams]).toEqual([["location[directory]", directory]])
+    expect(requests[0].init?.method).toBe("GET")
+    expect(new Headers(requests[0].init?.headers).get("authorization")).toBe(`Basic ${btoa("image-user:secret")}`)
+    expect(requests[0].init?.signal).toBe(signal)
+  })
+
+  test("preserves literal percent escapes and encodes the supplied relative location", async () => {
+    const { api, requests } = setup()
+    await readLocalImage(api, "C:/project #1 + 50%", "images/literal%20name.png", new AbortController().signal)
+
+    expect(requests[0].url.href).toBe(
+      "https://server.example:4096/api/fs/read/images/literal%2520name.png?location%5Bdirectory%5D=C%3A%2Fproject+%231+%2B+50%25",
+    )
+  })
+
+  test.each([
+    ["png", "image/png"],
+    ["jpeg", "image/jpeg"],
+    ["JPG", "image/jpeg"],
+    ["gif", "image/gif"],
+    ["webp", "image/webp"],
+    ["SVG", "image/svg+xml"],
+    ["avif", "image/avif"],
+    ["bmp", "image/bmp"],
+    ["ico", "image/x-icon"],
+  ])("uses the MIME type for .%s rather than the response header", async (extension, type) => {
+    const { api } = setup(
+      () => new Response("image bytes", { headers: { "content-type": "application/octet-stream" } }),
+    )
+    const blob = await readLocalImage(api, "/repo", `image.${extension}`, new AbortController().signal)
+    expect(blob?.type).toBe(type)
+    expect(await blob?.text()).toBe("image bytes")
+  })
+
+  test.each([
+    "https://example.com/image.png",
+    "HTTP://example.com/image.png",
+    "file:///tmp/image.png",
+    "data:image/png;base64,image.png",
+    "blob:https://example.com/image.png",
+    "custom+scheme:image.png",
+    "C:image.png",
+    "//server/share/image.png",
+    "\\\\server\\share\\image.png",
+    "//?/C:/image.png",
+    "///server/share/image.png",
+    "image.txt",
+    "image.html",
+    "image.constructor",
+    "image.png.txt",
+    "image",
+    "images.png/image",
+    "image.png/",
+    "",
+  ])("does not request unsupported input %s", async (path) => {
+    const { api, requests } = setup()
+    expect(await readLocalImage(api, "/repo", path, new AbortController().signal)).toBeUndefined()
+    expect(requests).toHaveLength(0)
+  })
+
+  test.each([400, 401])("propagates declared API errors (%s)", async (status) => {
+    const error = { _tag: "RequestError", message: "Cannot read image" }
+    const { api } = setup(() => Response.json(error, { status }))
+    await expect(readLocalImage(api, "/repo", "image.png", new AbortController().signal)).rejects.toEqual(error)
+  })
+
+  test.each([404, 500])("does not turn an unexpected HTTP status (%s) into a Blob", async (status) => {
+    const { api } = setup(() => new Response("Not an image", { status }))
+    await expect(readLocalImage(api, "/repo", "image.png", new AbortController().signal)).rejects.toMatchObject({
+      reason: "UnexpectedStatus",
+      cause: { status },
+    })
+  })
+
+  test("propagates transport failures", async () => {
+    const error = new Error("Connection lost")
+    const { api } = setup(() => Promise.reject(error))
+    await expect(readLocalImage(api, "/repo", "image.png", new AbortController().signal)).rejects.toMatchObject({
+      reason: "Transport",
+      cause: error,
+    })
+  })
+
+  test("forwards cancellation to an in-flight fetch", async () => {
+    const controller = new AbortController()
+    const { api, requests } = setup(
+      (init) =>
+        new Promise((_resolve, reject) => {
+          init?.signal?.addEventListener("abort", () => reject(init.signal?.reason), { once: true })
+        }),
+    )
+    const result = readLocalImage(api, "/repo", "image.png", controller.signal)
+    expect(requests[0].init?.signal).toBe(controller.signal)
+    controller.abort()
+    await expect(result).rejects.toMatchObject({ reason: "Transport", cause: controller.signal.reason })
+  })
+})
@@ -0,0 +1,36 @@
+import { getDirectory, getFilename } from "@opencode-ai/util/path"
+import type { OpenCodeClient } from "@opencode-ai/client/promise"
+
+const types = new Map([
+  ["png", "image/png"],
+  ["jpeg", "image/jpeg"],
+  ["jpg", "image/jpeg"],
+  ["gif", "image/gif"],
+  ["webp", "image/webp"],
+  ["svg", "image/svg+xml"],
+  ["avif", "image/avif"],
+  ["bmp", "image/bmp"],
+  ["ico", "image/x-icon"],
+])
+
+export async function readLocalImage(
+  api: Pick<OpenCodeClient, "file">,
+  directory: string,
+  path: string,
+  signal: AbortSignal,
+): Promise<Blob | undefined> {
+  const drive = /^[a-z]:\//i.test(path)
+  if (/^[\\/]{2}/.test(path) || (!drive && /^[a-z][a-z\d+.-]*:/i.test(path))) return
+  const type = types.get(path.match(/\.([^./]+)$/)?.[1]?.toLowerCase() ?? "")
+  if (!type) return
+  const absolute = drive || path.startsWith("/")
+  // Scope absolute images to their parent, including files outside the project.
+  const bytes = await api.file.read(
+    {
+      path: absolute ? getFilename(path) : path,
+      location: { directory: absolute ? getDirectory(path) : directory },
+    },
+    { signal },
+  )
+  return new Blob([new Uint8Array(bytes)], { type })
+}
@@ -80,8 +80,8 @@ export function createSessionRequestModel() {
        if (message.type !== "synthetic") return []
        if (message.metadata?.source === "subagent" && typeof message.metadata.childID === "string")
          return [message.metadata.childID]
-        if (message.metadata?.source === "shell" && typeof message.metadata.jobID === "string")
-          return [message.metadata.jobID]
+        if (message.metadata?.source === "shell")
+          return [message.metadata.shellID, message.metadata.jobID].filter((id): id is string => typeof id === "string")
        return []
      }),
    )
@@ -121,6 +121,7 @@ export function createSessionRequestModel() {
        if (part.type !== "tool" || part.name !== "shell" || completed.has(part.id)) return []
        if (part.state.status !== "completed" || part.state.metadata?.status !== "running") return []
        const shellID = part.state.metadata.shellID
+        if (typeof shellID === "string" && completed.has(shellID)) return []
        const command = part.state.input.command
        return [
          {
@@ -1,6 +1,6 @@
 import { Menu } from "@opencode-ai/ui/menu"
 import { Icon } from "@opencode-ai/ui/icon"
-import { getDirectory, getFilename } from "@opencode-ai/util/path"
+import { getFilename } from "@opencode-ai/util/path"
 import { createStore } from "solid-js/store"
 import { createSignal, For, Show, type ComponentProps, type JSX } from "solid-js"
 import type { Project } from "@/runtime/server/types"
@@ -11,6 +11,7 @@ import { useSettingsDialog } from "@/settings/command"
 import { pathKey } from "@/workspaces/path-key"
 import { showToast } from "@/shell/notifications/toast"
 import { containsDirectory, sameDirectory, workspaceDirectories } from "@/workspaces/paths"
+import { createWorktree } from "@/workspaces/create"

 export function SessionWorkspaceMenu(props: {
  eligible?: boolean
@@ -55,7 +56,14 @@ export function SessionWorkspaceMenu(props: {
    setStore("selected", selection)

    try {
-      const destination = selection === "create" ? await createWorkspace(props.project, sdk) : selection
+      const destination =
+        selection === "create"
+          ? await createWorktree({
+              api: sdk.api,
+              directory: props.directory,
+              project: data.location.info({ directory: props.directory })?.project,
+            })
+          : selection
      if (!destination) return

      await sdk.api.session.move({ sessionID, directory: destination })
@@ -124,13 +132,3 @@ export function SessionWorkspaceMenu(props: {
    </Menu>
  )
 }
-
-async function createWorkspace(project: Project, serverSDK: ReturnType<typeof useServerSDK>) {
-  const created = await serverSDK.api.worktree.create({
-    projectID: project.id,
-    strategy: "git",
-    directory: getDirectory(project.worktree),
-  })
-  await serverSDK.api.location.get({ location: { directory: created.directory } })
-  return created.directory
-}
@@ -1,5 +1,5 @@
 import { TextField } from "@opencode-ai/ui/text-field"
-import { captureException, isEnabled } from "@sentry/solid"
+import type { captureException } from "@sentry/solid"
 import { Logo } from "@opencode-ai/ui/logo"
 import { Button } from "@opencode-ai/ui/button"
 import { Component, createSignal, onMount, Show } from "solid-js"
@@ -227,6 +227,7 @@ export const ErrorPage: Component<ErrorPageProps> = (props) => {
  let recordedFatalError: Promise<void> | undefined
  const [store, setStore] = createStore({
    actionError: undefined as string | undefined,
+    captureException: undefined as typeof captureException | undefined,
  })

  function ensureFatalErrorRecorded() {
@@ -243,6 +244,11 @@ export const ErrorPage: Component<ErrorPageProps> = (props) => {

  onMount(() => {
    void ensureFatalErrorRecorded().catch(() => undefined)
+    void import("@sentry/solid")
+      .then(({ captureException, isEnabled }) => {
+        if (isEnabled()) setStore("captureException", () => captureException)
+      })
+      .catch(() => undefined)
  })

  async function checkForUpdates() {
@@ -311,15 +317,15 @@ export const ErrorPage: Component<ErrorPageProps> = (props) => {
              {language.t("error.page.action.exportLogs")}
            </Button>
          </Show>
-          <Show when={isEnabled}>
-            {(_) => {
+          <Show when={store.captureException}>
+            {(capture) => {
              const [reported, setReported] = createSignal(false)
              return (
                <Button
                  size="large"
                  disabled={reported()}
                  onClick={() => {
-                    captureException(props.error)
+                    capture()(props.error)
                    setReported(true)
                  }}
                >
@@ -1,4 +1,5 @@
 import { DataProvider } from "@opencode-ai/session-ui/context"
+import { MarkdownProvider, type ReadMarkdownImage } from "@opencode-ai/session-ui/context/markdown"
 import { useNavigate, useParams } from "@solidjs/router"
 import { createMemo, type ParentProps } from "solid-js"
 import { useProviders } from "@/providers/catalog/providers"
@@ -8,6 +9,7 @@ import { sessionHref } from "@/shell/routes/session"
 import { useData } from "@/runtime/server/current"
 import { useServerSDK } from "@/runtime/server/client"
 import { useTabs } from "@/shell/tabs/tabs"
+import { readLocalImage } from "@/runtime/server/image"

 export function SessionUIProvider(
  props: ParentProps<{
@@ -21,6 +23,10 @@ export function SessionUIProvider(
  const serverSDK = useServerSDK()
  const tabs = useTabs()
  const directory = () => props.directory
+  const readImage = createMemo<ReadMarkdownImage>(() => {
+    const dir = directory()
+    return (path, signal) => readLocalImage(serverSDK.api, dir, path, signal)
+  })
  const href = (sessionID: string) => sessionHref(props.server, sessionID)
  const navigateToSession = async (sessionID: string) => {
    const tab = tabs.store.find(
@@ -60,7 +66,9 @@ export function SessionUIProvider(
      onNavigateToSession={navigateToSession}
      onSessionHref={href}
    >
-      <LocalProvider>{props.children}</LocalProvider>
+      <MarkdownProvider readImage={readImage()}>
+        <LocalProvider>{props.children}</LocalProvider>
+      </MarkdownProvider>
    </DataProvider>
  )
 }
@@ -0,0 +1,90 @@
+import { describe, expect, test } from "bun:test"
+import { OpenCode } from "@opencode-ai/client/promise"
+import { createWorktree } from "./create"
+
+describe("worktree creation", () => {
+  test.each(
+    [
+      { name: "clone", directory: "/copies/repo", root: "/copies/repo", canonical: "/copies/repo", parent: "/copies/" },
+      {
+        name: "clone subdirectory",
+        directory: "/copies/repo/packages/app",
+        root: "/copies/repo",
+        canonical: "/copies/repo",
+        parent: "/copies/",
+      },
+      {
+        name: "linked worktree subdirectory",
+        directory: "/linked/task/packages/app",
+        root: "/linked/task",
+        canonical: "/copies/repo",
+        parent: "/copies/",
+      },
+      {
+        name: "Windows clone",
+        directory: "C:\\copies\\repo\\packages\\app",
+        root: "C:\\copies\\repo",
+        canonical: "C:\\copies\\repo",
+        parent: "C:/copies/",
+      },
+    ].flatMap((input) => [true, false].map((cached) => ({ ...input, cached }))),
+  )("uses the clone-local main for $name (cached: $cached)", async (input) => {
+    const project = { id: "proj_clone", directory: input.root, canonical: input.canonical }
+    const requests: Request[] = []
+    const api = OpenCode.make({
+      baseUrl: "http://localhost:3000",
+      fetch: Object.assign(
+        async (input: RequestInfo | URL, init?: RequestInit) => {
+          const request = new Request(input, init)
+          requests.push(request)
+          if (request.method === "POST") return Response.json({ directory: "/created" })
+          return Response.json({ directory: new URL(request.url).searchParams.get("location[directory]"), project })
+        },
+        { preconnect() {} },
+      ),
+    })
+
+    expect(
+      await createWorktree({
+        api,
+        directory: input.directory,
+        project: input.cached ? project : undefined,
+        branch: "clone-only",
+      }),
+    ).toBe("/created")
+    expect(await requests.find((request) => request.method === "POST")?.json()).toEqual({
+      strategy: "git",
+      from: input.canonical,
+      branch: "clone-only",
+      directory: input.parent,
+    })
+    expect(requests.find((request) => request.method === "POST")?.url).toBe(
+      "http://localhost:3000/api/worktree/proj_clone",
+    )
+    expect(
+      requests
+        .filter((request) => request.method === "GET")
+        .map((request) => new URL(request.url).searchParams.get("location[directory]")),
+    ).toEqual(input.cached ? ["/created"] : [input.directory, "/created"])
+  })
+
+  test("does not fall back to a shared project when location lookup fails", async () => {
+    const requests: Request[] = []
+    const api = OpenCode.make({
+      baseUrl: "http://localhost:3000",
+      fetch: Object.assign(
+        async (input: RequestInfo | URL, init?: RequestInit) => {
+          requests.push(new Request(input, init))
+          return Response.json({ message: "unavailable" }, { status: 503 })
+        },
+        { preconnect() {} },
+      ),
+    })
+
+    await expect(createWorktree({ api, directory: "/copies/repo" })).rejects.toMatchObject({
+      reason: "UnexpectedStatus",
+      cause: { status: 503 },
+    })
+    expect(requests.map((request) => request.method)).toEqual(["GET"])
+  })
+})
@@ -0,0 +1,20 @@
+import type { LocationGetOutput, OpenCodeClient } from "@opencode-ai/client/promise"
+import { getDirectory } from "@opencode-ai/util/path"
+
+export async function createWorktree(input: {
+  api: Pick<OpenCodeClient, "location" | "worktree">
+  directory: string
+  project?: LocationGetOutput["project"]
+  branch?: string
+}) {
+  const project = input.project ?? (await input.api.location.get({ location: { directory: input.directory } })).project
+  const created = await input.api.worktree.create({
+    projectID: project.id,
+    strategy: "git",
+    from: project.canonical,
+    branch: input.branch,
+    directory: getDirectory(project.canonical),
+  })
+  await input.api.location.get({ location: { directory: created.directory } })
+  return created.directory
+}
@@ -0,0 +1,85 @@
+import { expect, test } from "bun:test"
+import { MemoryRouter, Route, createMemoryHistory, useNavigate, useParams } from "@solidjs/router"
+import { createEffect, onCleanup } from "solid-js"
+import { createComponent, render } from "solid-js/web"
+import { createSessionOwnership } from "@/session/session-ownership"
+
+test("session ownership follows navigation, back, forward, replacement, and route disposal", async () => {
+  const host = document.createElement("div")
+  const history = createMemoryHistory()
+  history.set({ value: "/session/A", replace: true, scroll: false })
+  const captured: ReturnType<ReturnType<typeof createSessionOwnership>["capture"]>[] = []
+  const navigate: ReturnType<typeof useNavigate>[] = []
+  const cleaned: string[] = []
+  const settle = () => new Promise((resolve) => setTimeout(resolve, 0))
+
+  const Session = () => {
+    const params = useParams<{ id: string }>()
+    const ownership = createSessionOwnership(() => params.id)
+    const label = document.createElement("div")
+    navigate.push(useNavigate())
+    createEffect(() => {
+      label.textContent = params.id
+      captured.push(ownership.capture())
+    })
+    onCleanup(() => cleaned.push("session"))
+    return label
+  }
+
+  const dispose = render(
+    () =>
+      createComponent(MemoryRouter, {
+        history,
+        get children() {
+          return [
+            createComponent(Route, { path: "/", component: () => "Home" }),
+            createComponent(Route, { path: "/session/:id", component: Session }),
+          ]
+        },
+      }),
+    host,
+  )
+
+  try {
+    expect(host.textContent).toBe("A")
+    expect(captured[0].current()).toBe(true)
+
+    navigate[0]("/session/B")
+    await settle()
+    expect(host.textContent).toBe("B")
+    expect(captured[0].current()).toBe(false)
+    expect(captured[1].current()).toBe(true)
+
+    history.back()
+    await settle()
+    expect(host.textContent).toBe("A")
+    expect(captured[0].current()).toBe(false)
+    expect(captured[1].current()).toBe(false)
+    expect(captured[2].current()).toBe(true)
+
+    history.forward()
+    await settle()
+    expect(host.textContent).toBe("B")
+    expect(captured[2].current()).toBe(false)
+    expect(captured[3].current()).toBe(true)
+    expect(navigate).toHaveLength(1)
+    expect(cleaned).toEqual([])
+
+    navigate[0]("/", { replace: true })
+    await settle()
+    expect(host.textContent).toBe("Home")
+    expect(captured.every((owner) => !owner.current())).toBe(true)
+    expect(cleaned).toEqual(["session"])
+
+    history.back()
+    await settle()
+    expect(host.textContent).toBe("A")
+    expect(captured[4].current()).toBe(true)
+    expect(navigate).toHaveLength(2)
+  } finally {
+    dispose()
+  }
+
+  expect(captured.every((owner) => !owner.current())).toBe(true)
+  expect(cleaned).toEqual(["session", "session"])
+})
@@ -0,0 +1,89 @@
+import { expect, test } from "bun:test"
+import {
+  createComputed,
+  createMemo,
+  createResource,
+  createRoot,
+  createSignal,
+  onCleanup,
+  startTransition,
+  Suspense,
+  type Accessor,
+  type JSX,
+} from "solid-js"
+import { createComponent, render } from "solid-js/web"
+
+// Solid 1.9.15 includes the former transition patch for solidjs/solid#2046.
+test("a memo created during a paused transition has a committed value", async () => {
+  const host = document.createElement("div")
+  const loaded = Promise.withResolvers<string>()
+  const started = Promise.withResolvers<void>()
+  const memos: Accessor<string>[] = []
+  const [session, setSession] = createSignal(false)
+  const dispose = render(
+    () =>
+      createComponent(Suspense, {
+        fallback: "Loading",
+        get children() {
+          return createMemo(() => {
+            if (!session()) return "Home"
+            memos.push(createMemo(() => "Session"))
+            const [data] = createResource(() => loaded.promise)
+            started.resolve()
+            return createMemo(() => data() ?? "")
+          }) as unknown as JSX.Element
+        },
+      }),
+    host,
+  )
+
+  try {
+    expect(host.textContent).toBe("Home")
+    const pending = startTransition(() => setSession(true))
+    await started.promise
+    expect(host.textContent).toBe("Home")
+    expect(memos).toHaveLength(1)
+    expect(memos[0]()).toBe("Session")
+
+    loaded.resolve("Session loaded")
+    await pending
+    expect(host.textContent).toBe("Session loaded")
+    expect(memos[0]()).toBe("Session")
+  } finally {
+    loaded.resolve("Session loaded")
+    dispose()
+  }
+})
+
+// Exercise each patched bundle independently; importing both dev formats emits Solid's duplicate-runtime warning.
+test.each(["solid.js", "solid.cjs", "dev.js", "dev.cjs", "server.js", "server.cjs"])(
+  "%s reentrant disposal cleans owned computations and callbacks exactly once",
+  async (file) => {
+    const runtime: {
+      createRoot: typeof createRoot
+      createComputed: typeof createComputed
+      onCleanup: typeof onCleanup
+    } = await import(`solid-js/dist/${file}`)
+    const cleaned: string[] = []
+    const dispose = runtime.createRoot((dispose) => {
+      runtime.onCleanup(() => cleaned.push("root"))
+      runtime.createComputed(() => {
+        runtime.onCleanup(() => cleaned.push("first"))
+      })
+      runtime.createComputed(() => {
+        runtime.onCleanup(() => cleaned.push("second"))
+        runtime.onCleanup(() => {
+          cleaned.push("reentrant")
+          // Bound the regression so an unpatched runtime fails without overflowing the stack.
+          if (cleaned.filter((item) => item === "reentrant").length === 1) dispose()
+        })
+      })
+      return dispose
+    })
+
+    expect(dispose).not.toThrow()
+    expect(cleaned.toSorted()).toEqual(["first", "reentrant", "root", "second"])
+    dispose()
+    expect(cleaned).toHaveLength(4)
+  },
+)
@@ -10,6 +10,8 @@ export function serviceWorker(directory: string) {
    injectRegister: false,
    manifest: false,
    workbox: {
+      // Workbox runs after Sentry's upload and cleanup, so do not publish an unuploaded map.
+      sourcemap: false,
      globDirectory: directory,
      clientsClaim: false,
      // Keep each open tab on its complete build until all old clients close.
@@ -37,7 +37,7 @@
    "@opencode-ai/protocol": "workspace:*"
  },
  "peerDependencies": {
-    "effect": "4.0.0-rc.111",
+    "effect": "4.0.0-rc.112",
    "solid-js": ">=1.9.0"
  },
  "peerDependenciesMeta": {
@@ -183,6 +183,7 @@ export type SessionCreateInput = {
  readonly agent?: Agent.ID | undefined
  readonly model?: Model.Ref | undefined
  readonly location?: Location.Ref | undefined
+  readonly metadata?: Session.Metadata | undefined
 }
 export type SessionCreateOutput = Session.Info
 export type SessionCreateOperation<E = never> = (input?: SessionCreateInput) => Effect.Effect<SessionCreateOutput, E>
@@ -410,6 +411,7 @@ export type SessionLogOutput =
            readonly title?: string | undefined
            readonly agent?: Agent.ID | undefined
            readonly model?: Model.Ref | undefined
+            readonly metadata?: Session.Metadata | undefined
            readonly version: string
          }
        }
@@ -1637,6 +1639,23 @@ export interface PtyApi<E = never> {
  readonly connect: { readonly token: PtyConnectTokenOperation<E> }
 }

+export type ExperimentalPersistentPtyReadInput = { readonly sessionID: Session.ID; readonly lines?: number | undefined }
+export type ExperimentalPersistentPtyReadOutput = {
+  readonly ptyID: Pty.ID
+  readonly title: string
+  readonly cwd: string
+  readonly foregroundProcess: string | null
+  readonly screen: {
+    readonly text: string
+    readonly cols: number
+    readonly rows: number
+    readonly cursor: { readonly x: number; readonly y: number }
+  }
+} | null
+export type ExperimentalPersistentPtyReadOperation<E = never> = (
+  input: ExperimentalPersistentPtyReadInput,
+) => Effect.Effect<ExperimentalPersistentPtyReadOutput, E>
+
 export type ExperimentalPersistentPtyListInput = { readonly sessionID: Session.ID }
 export type ExperimentalPersistentPtyListOutput = ReadonlyArray<{
  readonly id: Pty.ID
@@ -1785,6 +1804,7 @@ export type ExperimentalPersistentPtyConnectTokenOperation<E = never> = (

 export interface ExperimentalApi<E = never> {
  readonly persistentPty: {
+    readonly read: ExperimentalPersistentPtyReadOperation<E>
    readonly list: ExperimentalPersistentPtyListOperation<E>
    readonly create: ExperimentalPersistentPtyCreateOperation<E>
    readonly shutdown: ExperimentalPersistentPtyShutdownOperation<E>
@@ -198,6 +198,8 @@ import type {
  PtyRemoveOutput,
  PtyConnectTokenInput,
  PtyConnectTokenOutput,
+  ExperimentalPersistentPtyReadInput,
+  ExperimentalPersistentPtyReadOutput,
  ExperimentalPersistentPtyListInput,
  ExperimentalPersistentPtyListOutput,
  ExperimentalPersistentPtyCreateInput,
@@ -360,6 +362,7 @@ const EndpointSessionCreate = (raw: RawClient["server.session"]) => (input?: Ses
        agent: input?.["agent"],
        model: input?.["model"],
        location: input?.["location"],
+        metadata: input?.["metadata"],
      },
    }).pipe(
      Effect.mapError(mapClientError),
@@ -1233,6 +1236,15 @@ const adaptGroupPty = (raw: RawClient["server.pty"]) => ({
  connect: { token: EndpointPtyConnectToken(raw) },
 })

+const EndpointExperimentalPersistentPtyRead =
+  (raw: RawClient["server.experimental"]) => (input: ExperimentalPersistentPtyReadInput) =>
+    preserveEffect<ExperimentalPersistentPtyReadOutput>()(
+      raw["persistentPty.read"]({ params: { sessionID: input["sessionID"] }, query: { lines: input["lines"] } }).pipe(
+        Effect.mapError(mapClientError),
+        Effect.map((value) => value.data),
+      ),
+    )
+
 const EndpointExperimentalPersistentPtyList =
  (raw: RawClient["server.experimental"]) => (input: ExperimentalPersistentPtyListInput) =>
    preserveEffect<ExperimentalPersistentPtyListOutput>()(
@@ -1321,6 +1333,7 @@ const EndpointExperimentalPersistentPtyConnectToken =

 const adaptGroupExperimental = (raw: RawClient["server.experimental"]) => ({
  persistentPty: {
+    read: EndpointExperimentalPersistentPtyRead(raw),
    list: EndpointExperimentalPersistentPtyList(raw),
    create: EndpointExperimentalPersistentPtyCreate(raw),
    shutdown: EndpointExperimentalPersistentPtyShutdown(raw),
--- a/Show More
+++ b/Show More