make PWA chat resume idempotent

dist/default.conf

@@ -12,17 +12,43 @@ server {
   location /api/ {
     proxy_pass http://server:8787/;
     proxy_http_version 1.1;
+    proxy_buffering off;
+    proxy_cache off;
+    proxy_read_timeout 3600s;
+    proxy_send_timeout 3600s;
     proxy_set_header Host $host;
     proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
     proxy_set_header X-Forwarded-Proto $scheme;
+    proxy_set_header Connection "";
+  }
+
+  location = /sw.js {
+    add_header Cache-Control "no-store, no-cache, must-revalidate" always;
+    expires -1;
+    try_files $uri =404;
   }
 
   location = /manifest.webmanifest {
     default_type application/manifest+json;
+    add_header Cache-Control "no-store, no-cache, must-revalidate" always;
+    expires -1;
+    try_files $uri =404;
+  }
+
+  location = /index.html {
+    add_header Cache-Control "no-store, no-cache, must-revalidate" always;
+    expires -1;
+    try_files $uri =404;
+  }
+
+  location /assets/ {
+    add_header Cache-Control "public, max-age=31536000, immutable" always;
     try_files $uri =404;
   }
 
   location / {
+    add_header Cache-Control "no-store, no-cache, must-revalidate" always;
+    expires -1;
     try_files $uri $uri/ /index.html;
   }
 }

docs/api/rest.md

@@ -323,6 +323,16 @@ Behavior notes:
   - `CHAT_SHELL_EXEC_TIMEOUT_MS=120000` (optional)
 - When a tool call is executed, backend stores a chat `Message` with `role: "tool"` and tool metadata (`metadata.kind = "tool_call"`). Streaming requests emit an initiated SSE `tool_call` event before execution, then persist each completed or failed tool call as its terminal SSE `tool_call` event is emitted, then store the assistant output when the completion finishes.
 
+## Streaming Chat
+
+### `POST /v1/chat-completions/stream`
+
+- The request accepts the chat-completion fields above plus optional `persist` and `clientRequestId` fields.
+- `clientRequestId` is only valid for a persisted request with a `chatId`, may be up to 128 characters, and should be a stable unique value generated once per user submission.
+- Retrying with the same `chatId` and `clientRequestId` replays the matching active or completed stream rather than starting a duplicate provider call.
+- The server persists the ID in `metadata.clientRequestId` on the submitted user message and completed assistant message.
+- The complete request, SSE event, persistence, retry, and attach contracts are defined in `docs/api/streaming-chat.md`.
+
 ## Searches
 
 ### `GET /v1/searches`

docs/api/streaming-chat.md

@@ -21,6 +21,7 @@ Authentication:
 {
   "chatId": "optional-chat-id",
   "persist": true,
+  "clientRequestId": "optional-client-generated-id",
   "provider": "openai|anthropic|xai|gemini|hermes-agent",
   "model": "string",
   "messages": [
@@ -61,6 +62,9 @@ Notes:
 - If `persist` is `true` and `chatId` is omitted, backend creates a new chat.
 - If `chatId` is provided, backend validates it exists.
 - If `persist` is `false`, `chatId` must be omitted. Backend does not create a chat and does not persist input messages, tool-call messages, assistant output, or `LlmCall` metadata.
+- `clientRequestId` is optional and is only valid for a persisted stream with a `chatId`. Clients should generate one stable, unique value per user submission and reuse it when retrying a disconnected request.
+- A retry with the same `chatId` and `clientRequestId` attaches to and replays the matching active stream. If that submission already completed, the endpoint replays `meta` and `done` without invoking the provider again. This makes retrying the initial streaming `POST` idempotent.
+- `clientRequestId` values may be up to 128 characters. The server stores the value in `metadata.clientRequestId` on the submitted user message and completed assistant message.
 - For persisted streams, backend stores only new non-assistant input history rows to avoid duplicates.
 - `additionalSystemPrompt`, when present directly or loaded from stored chat settings, is prepended to the provider request as a `system` message and is not inserted into the persisted chat transcript by this endpoint.
 - `enabledTools` limits Sybil-managed tools for this request. When omitted for a saved chat, the stored chat setting is used; otherwise all available tools are enabled by default. An empty array disables Sybil-managed tools.
@@ -70,7 +74,7 @@ Notes:
 Persisted chat streams with a `chatId` are backend-owned active runs:
 - Once started, the backend keeps the stream running even if the HTTP client disconnects or refreshes.
 - While running, `GET /v1/active-runs` includes the `chatId`.
-- Starting a second persisted stream for the same active `chatId` returns `409`.
+- Starting a second persisted stream for the same active `chatId` returns `409`, unless its `clientRequestId` matches the active submission, in which case the existing stream is replayed.
 - Clients can reattach with `POST /v1/chats/:chatId/stream/attach`.
 
 ## Attach Endpoint

server/src/llm/streaming.ts

@@ -119,7 +119,12 @@ export async function* runMultiplexStream(req: MultiplexRequest): AsyncGenerator
     if (shouldPersist && chatId && call) {
       await prisma.$transaction(async (tx) => {
         await tx.message.create({
-          data: { chatId, role: "assistant" as any, content: text },
+          data: {
+            chatId,
+            role: "assistant" as any,
+            content: text,
+            metadata: req.clientRequestId ? ({ clientRequestId: req.clientRequestId } as any) : undefined,
+          },
         });
         await tx.llmCall.update({
           where: { id: call.id },

server/src/llm/types.ts

@@ -33,6 +33,7 @@ export type ChatMessage = {
 export type MultiplexRequest = {
   chatId?: string;
   persist?: boolean;
+  clientRequestId?: string;
   provider: Provider;
   model: string;
   messages: ChatMessage[];

server/src/routes.ts

@@ -88,7 +88,7 @@ function withRequestUserLocation<T extends { userLocation?: string }>(body: T, r
   return body.userLocation ? body : { ...body, userLocation: inferRequestUserLocation(req) };
 }
 
-async function storeNonAssistantMessages(chatId: string, messages: IncomingChatMessage[]) {
+async function storeNonAssistantMessages(chatId: string, messages: IncomingChatMessage[], clientRequestId?: string) {
   const incoming = messages.filter((m) => m.role !== "assistant");
   if (!incoming.length) return;
 
@@ -109,14 +109,21 @@ async function storeNonAssistantMessages(chatId: string, messages: IncomingChatM
   const toInsert = sharedPrefix === existingNonAssistant.length ? incoming.slice(existingNonAssistant.length) : incoming;
   if (!toInsert.length) return;
 
+  const finalUserMessageIndex = toInsert.map((message) => message.role).lastIndexOf("user");
   await prisma.message.createMany({
-    data: toInsert.map((m) => ({
+    data: toInsert.map((m, index) => {
+      const metadata = {
+        ...(m.attachments?.length ? { attachments: m.attachments } : {}),
+        ...(clientRequestId && index === finalUserMessageIndex ? { clientRequestId } : {}),
+      };
+      return {
         chatId,
         role: m.role as any,
         content: m.content,
         name: m.name,
-      metadata: m.attachments?.length ? ({ attachments: m.attachments } as any) : undefined,
+        metadata: Object.keys(metadata).length ? (metadata as any) : undefined,
-    })),
+      };
+    }),
   });
 }
 
@@ -169,6 +176,7 @@ const CompletionStreamBody = z
   .object({
     chatId: z.string().optional(),
     persist: z.boolean().optional(),
+    clientRequestId: z.string().trim().min(1).max(128).optional(),
     provider: ProviderSchema,
     model: z.string().min(1),
     messages: z.array(CompletionMessageSchema),
@@ -186,6 +194,13 @@ const CompletionStreamBody = z
         path: ["chatId"],
       });
     }
+    if (value.clientRequestId && (value.persist === false || !value.chatId)) {
+      ctx.addIssue({
+        code: z.ZodIssueCode.custom,
+        message: "clientRequestId requires a persisted stream with chatId",
+        path: ["clientRequestId"],
+      });
+    }
   });
 
 function mergeAttachmentsIntoMetadata(metadata: unknown, attachments?: ChatAttachment[]) {
@@ -399,6 +414,7 @@ function buildSseHeaders(originHeader: string | undefined) {
 type SearchRunRequest = z.infer<typeof SearchRunBody>;
 
 const activeChatStreams = new Map<string, ActiveSseStream>();
+const activeChatStreamRequestIds = new Map<string, string>();
 const activeSearchStreams = new Map<string, ActiveSseStream>();
 const STARRED_PROJECT_ID = "starred";
 
@@ -554,6 +570,7 @@ function writeSseEvent(reply: FastifyReply, event: SseStreamEvent) {
 }
 
 async function streamActiveRun(req: FastifyRequest, reply: FastifyReply, stream: ActiveSseStream) {
+  if (reply.raw.destroyed || reply.raw.writableEnded) return reply;
   reply.raw.writeHead(200, buildSseHeaders(typeof req.headers.origin === "string" ? req.headers.origin : undefined));
   reply.raw.flushHeaders?.();
 
@@ -588,10 +605,24 @@ function mapChatStreamEvent(ev: StreamEvent): SseStreamEvent {
   return { event: ev.type, data: ev };
 }
 
-function startActiveChatStream(chatId: string, body: z.infer<typeof CompletionStreamBody>) {
+function registerActiveChatStream(chatId: string, clientRequestId?: string) {
   const stream = new ActiveSseStream();
   activeChatStreams.set(chatId, stream);
+  if (clientRequestId) {
+    activeChatStreamRequestIds.set(chatId, clientRequestId);
+  } else {
+    activeChatStreamRequestIds.delete(chatId);
+  }
+  return stream;
+}
 
+function clearActiveChatStream(chatId: string, stream: ActiveSseStream) {
+  if (activeChatStreams.get(chatId) !== stream) return;
+  activeChatStreams.delete(chatId);
+  activeChatStreamRequestIds.delete(chatId);
+}
+
+function executeActiveChatStream(chatId: string, body: z.infer<typeof CompletionStreamBody>, stream: ActiveSseStream) {
   void (async () => {
     let sawTerminalEvent = false;
     try {
@@ -611,13 +642,54 @@ function startActiveChatStream(chatId: string, body: z.infer<typeof CompletionSt
     } catch (err) {
       stream.complete({ event: "error", data: { message: getErrorMessage(err) } });
     } finally {
-      activeChatStreams.delete(chatId);
+      clearActiveChatStream(chatId, stream);
     }
   })();
+}
 
+function startActiveChatStream(chatId: string, body: z.infer<typeof CompletionStreamBody>) {
+  const stream = registerActiveChatStream(chatId, body.clientRequestId);
+  executeActiveChatStream(chatId, body, stream);
   return stream;
 }
 
+function getMetadataClientRequestId(metadata: unknown) {
+  if (!metadata || typeof metadata !== "object" || Array.isArray(metadata)) return null;
+  const clientRequestId = (metadata as Record<string, unknown>).clientRequestId;
+  return typeof clientRequestId === "string" ? clientRequestId : null;
+}
+
+async function findCompletedChatSubmission(chatId: string, clientRequestId: string) {
+  const assistantMessages = await prisma.message.findMany({
+    where: { chatId, role: "assistant" as any },
+    orderBy: { createdAt: "desc" },
+    select: { content: true, metadata: true },
+  });
+  return assistantMessages.find((message) => getMetadataClientRequestId(message.metadata) === clientRequestId) ?? null;
+}
+
+function completeChatSubmissionStream(
+  stream: ActiveSseStream,
+  chatId: string,
+  body: z.infer<typeof CompletionStreamBody>,
+  assistantText: string
+) {
+  stream.emit("meta", {
+    type: "meta",
+    chatId,
+    callId: null,
+    provider: body.provider,
+    model: body.model,
+  });
+  stream.complete({
+    event: "done",
+    data: {
+      type: "done",
+      text: assistantText,
+    },
+  });
+}
+
 async function executeSearchRunStream(searchId: string, body: SearchRunRequest, stream: ActiveSseStream) {
   const startedAt = performance.now();
   const query = body.query?.trim();
@@ -1353,15 +1425,39 @@ export async function registerRoutes(app: FastifyInstance) {
       if (!exists) return app.httpErrors.notFound("chat not found");
     }
 
-    // Store only new non-assistant messages to avoid duplicate history entries.
     if (body.persist !== false && body.chatId) {
-      await storeNonAssistantMessages(body.chatId, body.messages);
+      const activeStream = activeChatStreams.get(body.chatId);
+      if (activeStream) {
+        if (body.clientRequestId && activeChatStreamRequestIds.get(body.chatId) === body.clientRequestId) {
+          return streamActiveRun(req, reply, activeStream);
         }
-
-    if (body.persist !== false && body.chatId) {
-      if (activeChatStreams.has(body.chatId)) {
         return app.httpErrors.conflict("chat completion already running");
       }
+
+      if (body.clientRequestId) {
+        const reservedStream = registerActiveChatStream(body.chatId, body.clientRequestId);
+        try {
+          const completedSubmission = await findCompletedChatSubmission(body.chatId, body.clientRequestId);
+          if (completedSubmission) {
+            completeChatSubmissionStream(reservedStream, body.chatId, body, completedSubmission.content);
+            clearActiveChatStream(body.chatId, reservedStream);
+            return streamActiveRun(req, reply, reservedStream);
+          }
+
+          // Store only new non-assistant messages to avoid duplicate history entries.
+          await storeNonAssistantMessages(body.chatId, body.messages, body.clientRequestId);
+          const configuredBody = await applyStoredChatSettings(body);
+          executeActiveChatStream(body.chatId, configuredBody, reservedStream);
+          return streamActiveRun(req, reply, reservedStream);
+        } catch (err) {
+          reservedStream.complete({ event: "error", data: { message: getErrorMessage(err) } });
+          clearActiveChatStream(body.chatId, reservedStream);
+          throw err;
+        }
+      }
+
+      // Legacy requests without an idempotency key retain the original behavior.
+      await storeNonAssistantMessages(body.chatId, body.messages);
       const stream = startActiveChatStream(body.chatId, await applyStoredChatSettings(body));
       return streamActiveRun(req, reply, stream);
     }

web/public/sw.js

@@ -8,5 +8,5 @@ self.addEventListener("activate", (event) => {
 
 self.addEventListener("fetch", (event) => {
   if (event.request.mode !== "navigate") return;
-  event.respondWith(fetch(event.request));
+  event.respondWith(fetch(new Request(event.request, { cache: "no-store" })));
 });

web/src/App.tsx

@@ -206,6 +206,13 @@ function getActiveRunsAfterResume() {
   return retryAfterAppResume(getActiveRuns);
 }
 
+function createClientRequestId() {
+  if (typeof crypto !== "undefined" && typeof crypto.randomUUID === "function") {
+    return crypto.randomUUID();
+  }
+  return `web-${Date.now()}-${Math.random().toString(36).slice(2)}`;
+}
+
 function isRecoverableStreamDisconnect(error: unknown) {
   if (error instanceof TypeError) return true;
   const message = (error instanceof Error ? error.message : String(error)).toLowerCase();
@@ -1085,7 +1092,7 @@ export default function App() {
     resetWorkspaceState();
   };
 
-  const refreshCollections = async (preferredSelection?: SidebarSelection) => {
+  const refreshCollections = async (preferredSelection?: SidebarSelection, reportTransientError = true) => {
     setIsLoadingCollections(true);
     try {
       const nextWorkspaceItems = await listWorkspaceItems();
@@ -1113,7 +1120,7 @@ export default function App() {
       const message = err instanceof Error ? err.message : String(err);
       if (message.includes("bearer token")) {
         handleAuthFailure(message);
-      } else {
+      } else if (reportTransientError || !isRecoverableStreamDisconnect(err)) {
         setError(message);
       }
     } finally {
@@ -2204,15 +2211,19 @@ export default function App() {
         });
     }
 
+    const target: SidebarSelection = { kind: "chat", id: chatId };
+    const clientRequestId = createClientRequestId();
+
+    while (true) {
       let streamErrorMessage: string | null = null;
       const abortController = new AbortController();
       chatStreamAbortRefs.current.set(chatId, abortController);
-    const target: SidebarSelection = { kind: "chat", id: chatId };
 
       try {
         await runCompletionStream(
           {
             chatId,
+            clientRequestId,
             provider,
             model: selectedModel,
             messages: requestMessages,
@@ -2274,60 +2285,80 @@ export default function App() {
         }
 
         backgroundSuspendedChatStreamsRef.current.delete(chatId);
-      await refreshCollections();
-      const currentSelection = selectedItemRef.current;
-      if (currentSelection?.kind === "chat" && currentSelection.id === chatId) {
-        await refreshChat(chatId);
-      }
-      removePendingChatState(chatId);
-      removeActiveRun("chat", chatId);
-      if (currentSelection?.kind === "chat" && currentSelection.id === chatId) {
-        requestSettleTranscriptTailSpacer();
-      }
-      return target;
-    } catch (err) {
-      const wasBackgroundSuspended =
-        abortController.signal.aborted && backgroundSuspendedChatStreamsRef.current.delete(chatId);
-      const shouldResumeStream =
-        wasBackgroundSuspended ||
-        (!abortController.signal.aborted && streamErrorMessage === null && isRecoverableStreamDisconnect(err));
-
-      if (shouldResumeStream) {
-        if (chatStreamAbortRefs.current.get(chatId) === abortController) {
-          chatStreamAbortRefs.current.delete(chatId);
-        }
-
-        try {
-          const resumedRuns = await getActiveRunsAfterResume();
-          setActiveRuns(buildActiveRunsState(resumedRuns));
-
-          if (resumedRuns.chats.includes(chatId)) {
-            removePendingChatState(chatId);
-            await attachToActiveChatStream(chatId, true);
-            return target;
-          }
-
         const persistedChat = await retryAfterAppResume(() => getChat(chatId));
-          await refreshCollections(target);
+        await refreshCollections(target, false);
         if (isCurrentSelection(target)) {
           setSelectedChat(persistedChat);
           setSelectedSearch(null);
         }
         removePendingChatState(chatId);
         removeActiveRun("chat", chatId);
+        if (isCurrentSelection(target)) {
+          requestSettleTranscriptTailSpacer();
+        }
+        return target;
+      } catch (caughtError) {
+        let err: unknown = caughtError;
+        const wasBackgroundSuspended =
+          abortController.signal.aborted && backgroundSuspendedChatStreamsRef.current.delete(chatId);
+        const shouldResumeStream =
+          wasBackgroundSuspended ||
+          (!abortController.signal.aborted && streamErrorMessage === null && isRecoverableStreamDisconnect(err));
 
+        if (chatStreamAbortRefs.current.get(chatId) === abortController) {
+          chatStreamAbortRefs.current.delete(chatId);
+        }
+
+        if (shouldResumeStream) {
+          try {
+            const persistedChat = await retryAfterAppResume(() => getChat(chatId));
+            const userMessageWasAccepted = hasNewPersistedUserMessage(
+              persistedChat,
+              previousMessageIds,
+              content,
+              attachments
+            );
+            setError(null);
+            if (isCurrentSelection(target)) {
+              setSelectedChat(persistedChat);
+              setSelectedSearch(null);
+            }
+            setPendingChatStates((current) => ({
+              ...current,
+              [chatId]: {
+                messages: persistedChat.messages.concat(
+                  ...(userMessageWasAccepted ? [] : [optimisticUserMessage]),
+                  {
+                    ...optimisticAssistantMessage,
+                    id: `temp-assistant-resume-${Date.now()}`,
+                    content: "",
+                  }
+                ),
+              },
+            }));
+
+            // Retrying the same idempotent request either starts an unaccepted
+            // submission or replays the existing backend-owned stream.
+            continue;
+          } catch (resumeError) {
+            err = resumeError;
+          }
+        } else if (streamErrorMessage) {
+          try {
+            const persistedChat = await retryAfterAppResume(() => getChat(chatId));
             if (hasNewPersistedUserMessage(persistedChat, previousMessageIds, content, attachments)) {
+              if (isCurrentSelection(target)) {
+                setSelectedChat(persistedChat);
+                setSelectedSearch(null);
+                setError(streamErrorMessage);
+              }
+              removePendingChatState(chatId);
+              removeActiveRun("chat", chatId);
               requestSettleTranscriptTailSpacer();
               return target;
             }
-
+          } catch (reconcileError) {
-          err = new Error(
+            err = reconcileError;
-            wasBackgroundSuspended
-              ? "The app was backgrounded before the message reached the server. Please send it again."
-              : "The connection dropped before the message reached the server. Please send it again."
-          );
-        } catch (resumeError) {
-          err = resumeError;
           }
         }
 
@@ -2341,6 +2372,7 @@ export default function App() {
           chatStreamAbortRefs.current.delete(chatId);
         }
       }
+    }
   };
 
   const handleSendSearch = async (query: string): Promise<SidebarSelection> => {

web/src/lib/api.ts

@@ -589,6 +589,7 @@ export async function runCompletionStream(
   body: {
     chatId?: string | null;
     persist?: boolean;
+    clientRequestId?: string;
     provider: Provider;
     model: string;
     messages: CompletionRequestMessage[];

web/src/pwa.ts

@@ -2,7 +2,18 @@ export function registerServiceWorker() {
   if (!import.meta.env.PROD || !("serviceWorker" in navigator)) return;
 
   window.addEventListener("load", () => {
-    void navigator.serviceWorker.register("/sw.js").catch((error: unknown) => {
+    const hadController = Boolean(navigator.serviceWorker.controller);
+    let isReloadingForUpdate = false;
+    navigator.serviceWorker.addEventListener("controllerchange", () => {
+      if (!hadController || isReloadingForUpdate) return;
+      isReloadingForUpdate = true;
+      window.location.reload();
+    });
+
+    void navigator.serviceWorker
+      .register("/sw.js", { updateViaCache: "none" })
+      .then((registration) => registration.update())
+      .catch((error: unknown) => {
         console.warn("Sybil service worker registration failed", error);
       });
   });