Add dedicated quick question API

ios/Packages/Sybil/Sources/Sybil/SybilAPIClient.swift

@@ -183,6 +183,29 @@ actor SybilAPIClient: SybilAPIClienting {
         SybilLog.info(SybilLog.network, "Chat stream completed")
     }
 
+    func runQuickQuestionStream(
+        body: QuickQuestionStreamRequest,
+        onEvent: @escaping @Sendable (CompletionStreamEvent) async -> Void
+    ) async throws {
+        let request = try makeRequest(
+            path: "/v1/quick-questions/stream",
+            method: "POST",
+            body: AnyEncodable(body),
+            acceptsSSE: true
+        )
+
+        SybilLog.info(
+            SybilLog.network,
+            "Starting quick question stream POST \(request.url?.absoluteString ?? "<unknown>")"
+        )
+
+        try await stream(request: request) { eventName, dataText in
+            try await Self.handleCompletionStreamEvent(eventName: eventName, dataText: dataText, onEvent: onEvent)
+        }
+
+        SybilLog.info(SybilLog.network, "Quick question stream completed")
+    }
+
     func attachCompletionStream(
         chatID: String,
         onEvent: @escaping @Sendable (CompletionStreamEvent) async -> Void
@@ -664,6 +687,12 @@ struct CompletionStreamRequest: Codable, Sendable {
     var userLocation: String? = nil
 }
 
+struct QuickQuestionStreamRequest: Codable, Sendable {
+    var provider: Provider
+    var model: String
+    var question: String
+}
+
 private struct ChatCreateBody: Encodable {
     var title: String?
     var provider: Provider?

ios/Packages/Sybil/Sources/Sybil/SybilAPIClienting.swift

@@ -27,6 +27,10 @@ protocol SybilAPIClienting: Sendable {
         body: CompletionStreamRequest,
         onEvent: @escaping @Sendable (CompletionStreamEvent) async -> Void
     ) async throws
+    func runQuickQuestionStream(
+        body: QuickQuestionStreamRequest,
+        onEvent: @escaping @Sendable (CompletionStreamEvent) async -> Void
+    ) async throws
     func attachCompletionStream(
         chatID: String,
         onEvent: @escaping @Sendable (CompletionStreamEvent) async -> Void

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

@@ -1162,13 +1162,11 @@ final class SybilViewModel {
         let streamStatus = CompletionStreamStatus()
 
         do {
-            try await client().runCompletionStream(
-                body: CompletionStreamRequest(
-                    chatId: nil,
-                    persist: false,
+            try await client().runQuickQuestionStream(
+                body: QuickQuestionStreamRequest(
                     provider: provider,
                     model: model,
-                    messages: [CompletionRequestMessage(role: .user, content: prompt)]
+                    question: prompt
                 )
             ) { [weak self] event in
                 guard let self else { return }

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

@@ -22,6 +22,7 @@ private struct MockClientCallSnapshot: Sendable {
     var getSearch = 0
     var getActiveRuns = 0
     var runCompletionStream = 0
+    var runQuickQuestionStream = 0
     var attachCompletionStream = 0
     var attachSearchStream = 0
 }
@@ -50,7 +51,7 @@ private actor MockSybilClient: SybilAPIClienting {
 
     private var snapshot = MockClientCallSnapshot()
     private var lastCreateChatCall: ChatCreateCallSnapshot?
-    private var lastCompletionStreamBody: CompletionStreamRequest?
+    private var lastQuickQuestionStreamBody: QuickQuestionStreamRequest?
     private var completionStreamEvents: [CompletionStreamEvent]?
     private var listChatsDelayNanoseconds: UInt64 = 0
     private var listSearchesDelayNanoseconds: UInt64 = 0
@@ -103,8 +104,8 @@ private actor MockSybilClient: SybilAPIClienting {
         lastCreateChatCall
     }
 
-    func currentCompletionStreamBody() -> CompletionStreamRequest? {
-        lastCompletionStreamBody
+    func currentQuickQuestionStreamBody() -> QuickQuestionStreamRequest? {
+        lastQuickQuestionStreamBody
     }
 
     func setCompletionStreamEvents(_ events: [CompletionStreamEvent], delayNanoseconds: UInt64 = 0) {
@@ -287,7 +288,27 @@ private actor MockSybilClient: SybilAPIClienting {
         onEvent: @escaping @Sendable (CompletionStreamEvent) async -> Void
     ) async throws {
         snapshot.runCompletionStream += 1
-        lastCompletionStreamBody = body
+        if completionStreamDelayNanoseconds > 0 {
+            try await Task.sleep(nanoseconds: completionStreamDelayNanoseconds)
+        }
+        if let completionStreamNetworkErrorMessage {
+            throw APIError.networkError(message: completionStreamNetworkErrorMessage)
+        }
+        if let completionStreamEvents {
+            for event in completionStreamEvents {
+                await onEvent(event)
+            }
+            return
+        }
+        throw UnexpectedClientCall()
+    }
+
+    func runQuickQuestionStream(
+        body: QuickQuestionStreamRequest,
+        onEvent: @escaping @Sendable (CompletionStreamEvent) async -> Void
+    ) async throws {
+        snapshot.runQuickQuestionStream += 1
+        lastQuickQuestionStreamBody = body
         if completionStreamDelayNanoseconds > 0 {
             try await Task.sleep(nanoseconds: completionStreamDelayNanoseconds)
         }
@@ -1005,7 +1026,8 @@ private func makeToolCallMessage(id: String, date: Date, summary: String = "Ran
     await first?.value
 
     let calls = await client.currentSnapshot()
-    #expect(calls.runCompletionStream == 1)
+    #expect(calls.runQuickQuestionStream == 1)
+    #expect(calls.runCompletionStream == 0)
     #expect(viewModel.quickQuestionAnswerText == "One answer.")
     #expect(!viewModel.isQuickQuestionSending)
 }
@@ -1021,12 +1043,12 @@ private func makeToolCallMessage(id: String, date: Date, summary: String = "Ran
     await task?.value
 
     let calls = await client.currentSnapshot()
-    #expect(calls.runCompletionStream == 0)
+    #expect(calls.runQuickQuestionStream == 0)
     #expect(!viewModel.isQuickQuestionSending)
 }
 
 @MainActor
-@Test func quickQuestionRunsNonPersistentCompletionStream() async throws {
+@Test func quickQuestionUsesDedicatedServerEndpoint() async throws {
     let client = MockSybilClient()
     await client.setCompletionStreamEvents([
         .delta(CompletionStreamDelta(text: "Reset it from ")),
@@ -1041,13 +1063,11 @@ private func makeToolCallMessage(id: String, date: Date, summary: String = "Ran
     await task?.value
 
     let snapshot = await client.currentSnapshot()
-    let body = await client.currentCompletionStreamBody()
-    #expect(snapshot.runCompletionStream == 1)
-    #expect(body?.persist == false)
-    #expect(body?.chatId == nil)
+    let body = await client.currentQuickQuestionStreamBody()
+    #expect(snapshot.runQuickQuestionStream == 1)
+    #expect(snapshot.runCompletionStream == 0)
     #expect(body?.provider == .openai)
-    #expect(body?.messages.first?.role == .user)
-    #expect(body?.messages.first?.content == "How do I reset my password?")
+    #expect(body?.question == "How do I reset my password?")
     #expect(viewModel.quickQuestionAnswerText == "Reset it from Settings.")
     #expect(!viewModel.isQuickQuestionSending)
 }
@@ -1572,7 +1592,7 @@ private final class MockQuickQuestionLifecycle {
     #expect(panel.state.prompt == "Keep this draft")
     #expect(panel.state.answer == "An answer arrived while hidden.")
     let calls = await client.currentSnapshot()
-    #expect(calls.runCompletionStream == 0)
+    #expect(calls.runQuickQuestionStream == 0)
     controller.stop()
 }
 
@@ -1630,7 +1650,7 @@ private final class MockQuickQuestionLifecycle {
     #expect(panel.presentationCount == 2)
     #expect(panel.state.canSend)
     let calls = await client.currentSnapshot()
-    #expect(calls.runCompletionStream == 0)
+    #expect(calls.runQuickQuestionStream == 0)
     controller.stop()
 }
 
@@ -1652,7 +1672,7 @@ private final class MockQuickQuestionLifecycle {
     #expect(panel.state.prompt == "A signed-out question")
     #expect(!viewModel.isQuickQuestionSending)
     let calls = await client.currentSnapshot()
-    #expect(calls.runCompletionStream == 0)
+    #expect(calls.runQuickQuestionStream == 0)
     controller.stop()
 }
 #endif