Expose chat-latest and default Quick Question to it

docs/api/rest.md

@@ -31,7 +31,7 @@ Chat upload limits:
 ```json
 {
   "providers": {
-    "openai": { "models": ["gpt-4.1-mini"], "loadedAt": "2026-02-14T00:00:00.000Z", "error": null },
+    "openai": { "models": ["chat-latest", "gpt-4.1-mini"], "loadedAt": "2026-02-14T00:00:00.000Z", "error": null },
     "anthropic": { "models": ["claude-3-5-sonnet-latest"], "loadedAt": null, "error": null },
     "xai": { "models": ["grok-3-mini"], "loadedAt": null, "error": null },
     "gemini": { "models": ["gemini-3.5-flash"], "loadedAt": null, "error": null },
@@ -39,7 +39,7 @@ Chat upload limits:
   }
 }
 ```
-- OpenAI model lists are filtered to models that are expected to work with the backend's Responses API implementation.
+- OpenAI model lists are filtered to models that are expected to work with the backend's Responses API implementation, including the exact `chat-latest` alias when returned by OpenAI. Audio, image-generation, embedding, moderation, and other specialized model ids remain excluded. See [OpenAI's Chat Latest documentation](https://developers.openai.com/api/docs/models/chat-latest) for supported capabilities.
 - Gemini model lists are loaded from Google's native Models API and filtered to Gemini `generateContent` model ids.
 - `hermes-agent` is included only when `HERMES_AGENT_API_KEY` is configured. Set it to Hermes `API_SERVER_KEY`, or any non-empty value if that local server does not require auth. `HERMES_AGENT_API_BASE_URL` defaults to `http://127.0.0.1:8642/v1`; set `HERMES_AGENT_MODEL` only when you need an additional fallback/override model id.
 - The backend loads provider model lists at startup and refreshes them about once every 24 hours. If a later provider refresh fails, the response keeps the last loaded model list for that provider and sets `error` to the latest failure message.

docs/api/streaming-chat.md

@@ -109,6 +109,7 @@ Request body:
 ```
 
 Behavior notes:
+- `provider` and `model` are required. Web and native clients default Quick Question to `provider: "openai"` and `model: "chat-latest"` when no Quick Question selection has been saved. Saved Quick Question choices take precedence over this default and are separate from regular chat preferences.
 - `question` is required, trimmed by the server, and must not be empty.
 - The server prepends a Quick Question system prompt that asks for a succinct, direct, self-contained answer without follow-up questions. Clients do not send or maintain this prompt.
 - Quick Questions are always non-persistent. The endpoint does not create a chat or store messages, tool-call logs, assistant output, or `LlmCall` metadata.

ios/Packages/Sybil/Sources/Sybil/SybilSettingsStore.swift

@@ -52,9 +52,9 @@ final class SybilSettingsStore {
         self.preferredModelByProvider = preferredModels
 
         self.quickQuestionPreferredProvider =
-            defaults.string(forKey: Keys.quickQuestionPreferredProvider).flatMap(Provider.init(rawValue:)) ?? provider
+            defaults.string(forKey: Keys.quickQuestionPreferredProvider).flatMap(Provider.init(rawValue:)) ?? .openai
         self.quickQuestionPreferredModelByProvider = [
-            .openai: defaults.string(forKey: Keys.quickQuestionPreferredOpenAIModel) ?? preferredModels[.openai] ?? "gpt-4.1-mini",
+            .openai: defaults.string(forKey: Keys.quickQuestionPreferredOpenAIModel) ?? "chat-latest",
             .anthropic: defaults.string(forKey: Keys.quickQuestionPreferredAnthropicModel) ?? preferredModels[.anthropic] ?? "claude-3-5-sonnet-latest",
             .xai: defaults.string(forKey: Keys.quickQuestionPreferredXAIModel) ?? preferredModels[.xai] ?? "grok-3-mini",
             .gemini: defaults.string(forKey: Keys.quickQuestionPreferredGeminiModel) ?? preferredModels[.gemini] ?? "gemini-3.5-flash",

ios/Packages/Sybil/Sources/Sybil/SybilViewModel.swift

@@ -222,7 +222,7 @@ final class SybilViewModel {
     private let clientFactory: (APIConfiguration) -> any SybilAPIClienting
 
     private let fallbackModels: [Provider: [String]] = [
-        .openai: ["gpt-4.1-mini"],
+        .openai: ["gpt-4.1-mini", "chat-latest"],
         .anthropic: ["claude-3-5-sonnet-latest"],
         .xai: ["grok-3-mini"],
         .gemini: ["gemini-3.5-flash", "gemini-flash-latest"],

ios/Packages/Sybil/Tests/SybilTests/SybilTests.swift

@@ -52,6 +52,7 @@ private actor MockSybilClient: SybilAPIClienting {
     private let updateChatStarResponses: [String: ChatSummary]
     private let updateSearchStarResponses: [String: SearchSummary]
     private let activeRunsResponse: ActiveRunsResponse
+    private let modelCatalogResponse: ModelCatalogResponse
 
     private var snapshot = MockClientCallSnapshot()
     private var lastCreateChatCall: ChatCreateCallSnapshot?
@@ -84,7 +85,8 @@ private actor MockSybilClient: SybilAPIClienting {
         updateChatStarResponses: [String: ChatSummary] = [:],
         updateSearchStarResponses: [String: SearchSummary] = [:],
         activeRunsResponse: ActiveRunsResponse = ActiveRunsResponse(),
-        workspaceItemsResponse: [WorkspaceItem]? = nil
+        workspaceItemsResponse: [WorkspaceItem]? = nil,
+        modelCatalogResponse: ModelCatalogResponse = ModelCatalogResponse(providers: [:])
     ) {
         self.chatsResponse = chatsResponse
         self.searchesResponse = searchesResponse
@@ -98,6 +100,7 @@ private actor MockSybilClient: SybilAPIClienting {
         self.updateChatStarResponses = updateChatStarResponses
         self.updateSearchStarResponses = updateSearchStarResponses
         self.activeRunsResponse = activeRunsResponse
+        self.modelCatalogResponse = modelCatalogResponse
     }
 
     private static func makeWorkspaceItems(chats: [ChatSummary], searches: [SearchSummary]) -> [WorkspaceItem] {
@@ -306,7 +309,7 @@ private actor MockSybilClient: SybilAPIClienting {
     }
 
     func listModels() async throws -> ModelCatalogResponse {
-        ModelCatalogResponse(providers: [:])
+        modelCatalogResponse
     }
 
     func getActiveRuns() async throws -> ActiveRunsResponse {
@@ -1257,6 +1260,7 @@ private func makeCompletionToolCall(
     #expect(snapshot.runQuickQuestionStream == 1)
     #expect(snapshot.runCompletionStream == 0)
     #expect(body?.provider == .openai)
+    #expect(body?.model == "chat-latest")
     #expect(body?.question == "How do I reset my password?")
     #expect(viewModel.quickQuestionAnswerText == "Reset it from Settings.")
     #expect(!viewModel.isQuickQuestionSending)
@@ -1370,6 +1374,42 @@ private func makeCompletionToolCall(
     #expect(viewModel.quickQuestionPrompt.isEmpty)
 }
 
+@MainActor
+@Test func quickQuestionDefaultsToChatLatestIndependentlyOfRegularChatPreferences() async {
+    let defaults = UserDefaults(suiteName: #function)!
+    defaults.removePersistentDomain(forName: #function)
+    defer { defaults.removePersistentDomain(forName: #function) }
+    defaults.set("anthropic", forKey: "sybil.ios.preferredProvider")
+    defaults.set("gpt-4o", forKey: "sybil.ios.preferredOpenAIModel")
+    let settings = SybilSettingsStore(defaults: defaults)
+    let client = MockSybilClient(modelCatalogResponse: ModelCatalogResponse(providers: [
+        .openai: ProviderModelInfo(models: ["gpt-4.1-mini", "chat-latest"], loadedAt: nil, error: nil),
+        .anthropic: ProviderModelInfo(models: ["claude-3-5-sonnet-latest"], loadedAt: nil, error: nil)
+    ]))
+    let viewModel = SybilViewModel(settings: settings) { _ in client }
+
+    #expect(viewModel.provider == .anthropic)
+    #expect(settings.preferredModelByProvider[.openai] == "gpt-4o")
+    #expect(viewModel.quickQuestionProvider == .openai)
+    #expect(viewModel.quickQuestionModel == "chat-latest")
+    #expect(viewModel.quickQuestionProviderModelOptions.contains("chat-latest"))
+
+    viewModel.setQuickQuestionProvider(.anthropic)
+    viewModel.setQuickQuestionProvider(.openai)
+    #expect(viewModel.quickQuestionModel == "chat-latest")
+
+    await viewModel.bootstrap()
+    #expect(viewModel.quickQuestionModel == "chat-latest")
+    #expect(viewModel.quickQuestionProviderModelOptions == ["gpt-4.1-mini", "chat-latest"])
+
+    viewModel.setQuickQuestionProvider(.anthropic)
+    viewModel.setQuickQuestionProvider(.openai)
+    #expect(viewModel.quickQuestionModel == "chat-latest")
+    #expect(SybilSettingsStore(defaults: defaults).quickQuestionPreferredModelByProvider[.openai] == "chat-latest")
+    #expect(settings.preferredProvider == .anthropic)
+    #expect(settings.preferredModelByProvider[.openai] == "gpt-4o")
+}
+
 @MainActor
 @Test func quickQuestionProviderAndModelSelectionPersistSeparately() async throws {
     let defaults = UserDefaults(suiteName: #function)!

ios/README.md

@@ -16,6 +16,9 @@ second **Option+Space**, the close button, or clicking outside dismisses it.
 Hiding the panel preserves the draft and answer and lets an in-flight answer finish.
 **Open in Chat** saves the question and answer in the regular workspace.
 
+Quick Question defaults to OpenAI `chat-latest` on iPhone, iPad, and Mac. Its saved
+provider/model selection takes precedence and is separate from regular chat preferences.
+
 The regular Mac chat/search composer uses the same Return/Shift+Return rules.
 Holding Return does not repeatedly submit. On iOS, Return submits from Quick
 Question, while the normal chat/search composer continues to use Return for a

server/src/llm/provider-adapters.ts

@@ -95,7 +95,7 @@ function isLikelyResponsesApiModel(model: string) {
   if (id.includes("audio") || id.includes("realtime") || id.includes("transcribe") || id.includes("tts")) return false;
   if (id.includes("image") || id.includes("dall-e") || id.includes("sora")) return false;
   if (id.includes("search") || id.includes("computer-use")) return false;
-  return /^(gpt-|o\d|chatgpt-)/.test(id);
+  return id === "chat-latest" || /^(gpt-|o\d|chatgpt-)/.test(id);
 }
 
 function isLikelyGeminiChatModel(model: string) {

server/tests/provider-adapters.test.ts

@@ -1,6 +1,50 @@
 import assert from "node:assert/strict";
 import test from "node:test";
-import { describeProviderChatBackend } from "../src/llm/provider-adapters.js";
+import { env } from "../src/env.js";
+import { describeProviderChatBackend, fetchProviderCatalogModels } from "../src/llm/provider-adapters.js";
+
+for (const { name, listedModels, expectedModels } of [
+  {
+    name: "OpenAI catalog includes chat-latest while excluding non-chat models",
+    listedModels: [
+      "gpt-4.1-mini",
+      "chat-latest",
+      "o3",
+      "chatgpt-4o-latest",
+      "chat-latest",
+      "text-embedding-3-small",
+      "omni-moderation-latest",
+      "gpt-4o-audio-preview",
+      "gpt-realtime",
+      "gpt-4o-transcribe",
+      "gpt-4o-mini-tts",
+      "gpt-image-1",
+      "chatgpt-image-latest",
+      "gpt-4o-search-preview",
+      "computer-use-preview",
+      "sora-2",
+    ],
+    expectedModels: ["chat-latest", "chatgpt-4o-latest", "gpt-4.1-mini", "o3"],
+  },
+  {
+    name: "OpenAI catalog does not invent models absent from the provider response",
+    listedModels: ["gpt-4.1-mini"],
+    expectedModels: ["gpt-4.1-mini"],
+  },
+]) {
+  test(name, async (t) => {
+    const originalKey = env.OPENAI_API_KEY;
+    env.OPENAI_API_KEY = "test-openai-key";
+    t.after(() => { env.OPENAI_API_KEY = originalKey; });
+    t.mock.method(globalThis, "fetch", async (input: RequestInfo | URL) => {
+      const url = input instanceof Request ? input.url : String(input);
+      assert.equal(url, "https://api.openai.com/v1/models");
+      return Response.json({ data: listedModels.map((id) => ({ id })) });
+    });
+
+    assert.deepEqual(await fetchProviderCatalogModels("openai"), expectedModels);
+  });
+}
 
 test("provider backend registry selects chat protocol and managed-tool mode", () => {
   assert.deepEqual(describeProviderChatBackend("openai", []), {

web/src/App.tsx

@@ -80,7 +80,7 @@ import {
   resolveSidebarSelectionAfterRefresh,
   type SidebarSelection,
 } from "@/lib/sidebar-selection";
-import { buildQuickQuestionRequest } from "@/lib/quick-question";
+import { buildQuickQuestionRequest, pickQuickQuestionModel, QUICK_QUESTION_DEFAULT_MODEL } from "@/lib/quick-question";
 import {
   appendStreamingDelta,
   clearStreamingAssistantTrace,
@@ -161,7 +161,7 @@ function buildWorkspaceUrl(selection: SidebarSelection | null) {
 }
 
 const PROVIDER_FALLBACK_MODELS: Record<Provider, string[]> = {
-  openai: ["gpt-4.1-mini"],
+  openai: ["gpt-4.1-mini", QUICK_QUESTION_DEFAULT_MODEL],
   anthropic: ["claude-3-5-sonnet-latest"],
   xai: ["grok-3-mini"],
   gemini: ["gemini-3.5-flash", "gemini-flash-latest"],
@@ -991,7 +991,7 @@ export default function App() {
   );
   const [quickModel, setQuickModel] = useState(() => {
     const stored = loadStoredQuickQuestionModelSelection();
-    return stored.modelPreferences[stored.provider] ?? PROVIDER_FALLBACK_MODELS[stored.provider][0];
+    return pickQuickQuestionModel(stored.provider, PROVIDER_FALLBACK_MODELS[stored.provider], stored.modelPreferences[stored.provider]);
   });
   const [isQuickQuestionOpen, setIsQuickQuestionOpen] = useState(false);
   const [quickPrompt, setQuickPrompt] = useState("");
@@ -1449,7 +1449,7 @@ export default function App() {
   useEffect(() => {
     if (quickModel.trim()) return;
     setQuickModel((current) => {
-      return current.trim() || pickProviderModel(quickProviderModelOptions, quickProviderModelPreferences[quickProvider]);
+      return current.trim() || pickQuickQuestionModel(quickProvider, quickProviderModelOptions, quickProviderModelPreferences[quickProvider]);
     });
   }, [quickModel, quickProvider, quickProviderModelOptions, quickProviderModelPreferences]);
 
@@ -4176,7 +4176,7 @@ export default function App() {
                     const nextProvider = event.currentTarget.value as Provider;
                     setQuickProvider(nextProvider);
                     const options = getModelOptions(modelCatalog, nextProvider);
-                    setQuickModel(pickProviderModel(options, quickProviderModelPreferences[nextProvider]));
+                    setQuickModel(pickQuickQuestionModel(nextProvider, options, quickProviderModelPreferences[nextProvider]));
                   }}
                   disabled={isQuickQuestionSending || isConvertingQuickQuestion}
                   aria-label="Quick question provider"

web/src/lib/quick-question.ts

@@ -1,5 +1,13 @@
 import type { Provider } from "./api";
 
+export const QUICK_QUESTION_DEFAULT_MODEL = "chat-latest";
+
+export function pickQuickQuestionModel(provider: Provider, options: string[], preferred: string | null = null) {
+  if (preferred?.trim()) return preferred.trim();
+  if (provider === "openai") return QUICK_QUESTION_DEFAULT_MODEL;
+  return options[0] ?? "";
+}
+
 export function buildQuickQuestionRequest({
   provider,
   model,

web/tests/quick-question.test.mjs

@@ -1,6 +1,27 @@
 import assert from "node:assert/strict";
 import test from "node:test";
-import { buildQuickQuestionRequest } from "../src/lib/quick-question.ts";
+import { buildQuickQuestionRequest, pickQuickQuestionModel } from "../src/lib/quick-question.ts";
+
+test("quick questions default to chat-latest before and after the model catalog loads", () => {
+  for (const options of [[], ["gpt-4.1-mini"], ["gpt-4.1-mini", "chat-latest"]]) {
+    const model = pickQuickQuestionModel("openai", options);
+    assert.equal(model, "chat-latest");
+    assert.deepEqual(buildQuickQuestionRequest({ provider: "openai", model, content: "What is UTC?" }), {
+      provider: "openai",
+      model: "chat-latest",
+      question: "What is UTC?",
+    });
+  }
+});
+
+test("quick questions preserve saved models and use provider-specific choices when switching providers", () => {
+  assert.equal(pickQuickQuestionModel("openai", ["chat-latest"], " gpt-4.1-mini "), "gpt-4.1-mini");
+  assert.equal(pickQuickQuestionModel("openai", ["gpt-4.1-mini"], " "), "chat-latest");
+  assert.equal(pickQuickQuestionModel("anthropic", ["claude-3-5-sonnet-latest"]), "claude-3-5-sonnet-latest");
+  assert.equal(pickQuickQuestionModel("anthropic", ["claude-3-5-sonnet-latest"], "claude-3-haiku"), "claude-3-haiku");
+  assert.equal(pickQuickQuestionModel("anthropic", []), "");
+  assert.equal(pickQuickQuestionModel("openai", ["gpt-4.1-mini", "chat-latest"]), "chat-latest");
+});
 
 test("quick question requests use the dedicated server endpoint shape", () => {
   const request = buildQuickQuestionRequest({