Merge remote-tracking branch 'origin/main' into performance-improvements

packages/ui/src/sync/DOCUMENTATION.md

@@ -232,6 +232,7 @@ Rules:
 3. `session-ui-store.ts` should delegate to `session-actions.ts` for these mutations instead of duplicating SDK calls.
 4. Sending after a revert commits the new branch optimistically: remove the reverted tail and marker before inserting the new message, and restore both if the send is rejected.
 5. After session creation, the directory returned by the server is authoritative over the requested draft directory. The server may canonicalize a worktree path, and the first prompt must use the same directory identity as the created session.
+6. A prompt send that fails **after** the request left the client is ambiguous, never a definite failure: the server may already be answering it. Transports tag those errors (`markAmbiguousTransportFailure` in `@/lib/relay/transport-error`; the relay tunnel tags every stream that dies with a request in flight), and `isAmbiguousSendFailure` reads the tag before falling back to status/text heuristics. An ambiguous failure waits for the connection to return, refetches recent messages, and confirms the optimistic message in place instead of rolling it back — rolling it back lets the message queue re-send a prompt the engine is already running, producing two independent AI responses for one user message.
 
 Examples of global-store updates performed in `session-actions.ts`:
 

packages/ui/src/sync/session-actions.test.ts

@@ -1014,6 +1014,53 @@ describe("optimisticSend target directory", () => {
     expect(targetStore.getState().part[sentMessageID]?.[0]?.id).toBe("server-part")
   })
 
+  // Relay tunnel aborts carry no HTTP status and no wording the text-matching
+  // heuristic recognizes. Without the transport tag they were classified as
+  // definite failures, the accepted prompt was rolled back, and the queue
+  // re-sent a message the engine was already answering (#2425).
+  test("confirms a tunnel-tagged transport failure that no text heuristic matches", async () => {
+    const targetStore = createStore({})
+    const childStores = createChildStores([["/target/project", targetStore]])
+    let optimisticRemove: OptimisticRemoveCall | null = null
+    let optimisticConfirm: OptimisticRemoveCall | null = null
+    let sentMessageID = ""
+
+    const { markAmbiguousTransportFailure } = await import("@/lib/relay/transport-error")
+    const { optimisticSend, setActionRefs, setOptimisticRefs } = await import("./session-actions")
+    setActionRefs(mockSdk as unknown as OpencodeClient, childStores, () => "/target/project")
+    setOptimisticRefs(
+      () => {},
+      (input) => {
+        optimisticRemove = input
+      },
+      (input) => {
+        optimisticConfirm = input
+      },
+    )
+
+    await optimisticSend({
+      sessionId: "session-tunnel",
+      directory: "/target/project",
+      content: "hello",
+      providerID: "provider",
+      modelID: "model",
+      send: async (messageID) => {
+        sentMessageID = messageID
+        sessionMessagesResult = {
+          data: [{
+            info: { id: messageID, role: "user", sessionID: "session-tunnel", time: { created: 1 } } as Message,
+            parts: [{ id: "server-part", type: "text", text: "hello" } as Part],
+          }],
+        }
+        throw markAmbiguousTransportFailure(new Error("stream aborted by host"))
+      },
+    })
+
+    expect(optimisticRemove).toBe(null)
+    expect((optimisticConfirm as OptimisticRemoveCall | null)?.messageID).toBe(sentMessageID)
+    expect(targetStore.getState().message["session-tunnel"]?.[0]?.id).toBe(sentMessageID)
+  })
+
   test("rolls back an ambiguous send failure when recent messages do not contain the sent ID", async () => {
     const targetStore = createStore({})
     const childStores = createChildStores([["/target/project", targetStore]])

packages/ui/src/sync/session-actions.ts

@@ -29,11 +29,21 @@ import { withContextObligatoryMessage, type ContextObligatoryMessage } from "@/l
 import { getImperativeSessionMessageLoader } from "./session-message-loader"
 import { cleanupPersistedSessionState } from "./session-deletion-cleanup"
 import { getRuntimeKey } from "@/lib/runtime-switch"
+import { isAmbiguousTransportFailure } from "@/lib/relay/transport-error"
 
 const MESSAGE_REFETCH_LIMIT = 100
 const SEND_CONFIRMATION_REFETCH_LIMIT = 30
-const SEND_CONFIRMATION_REFETCH_ATTEMPTS = 2
-const SEND_CONFIRMATION_REFETCH_RETRY_MS = 150
+// A relay-tunnel send fails when the tunnel drops, and the confirming refetch
+// then has to travel over that same tunnel to answer "did my message land?".
+// Two attempts 150ms apart always answered "no" on a remote connection, so an
+// accepted prompt looked like a failed one and got re-sent — two AI responses
+// for one user message. Wait for the connection to actually come back (an
+// authoritative signal, not a blind sleep), then retry with backoff. A healthy
+// connection skips the wait and answers on the first attempt.
+const SEND_CONFIRMATION_REFETCH_ATTEMPTS = 3
+const SEND_CONFIRMATION_REFETCH_BASE_RETRY_MS = 250
+const SEND_CONFIRMATION_RECONNECT_TIMEOUT_MS = 3000
+const SEND_CONFIRMATION_RECONNECT_POLL_MS = 100
 const MESSAGE_REFETCH_SKIP_PARTS = new Set(["patch", "step-start", "step-finish"])
 const UNREVERT_REFETCH_ATTEMPTS = 3
 const UNREVERT_REFETCH_RETRY_MS = 150
@@ -360,6 +370,13 @@ function getErrorStatus(error: unknown): number | null {
 }
 
 function isAmbiguousSendFailure(error: unknown): boolean {
+  // Authoritative first: the transport that lost the request says whether it
+  // had already been dispatched. The text matching below only covers direct
+  // fetch/HTTP failures, whose wording we do not control either — relay tunnel
+  // aborts ("stream aborted by host", "relay keepalive timeout", …) match none
+  // of those patterns and used to be misread as definite failures.
+  if (isAmbiguousTransportFailure(error)) return true
+
   const status = getErrorStatus(error)
   if (status === 503 || status === 504 || status === 408) return true
   if (error instanceof TypeError) return true
@@ -1255,8 +1272,15 @@ async function fetchRecentSendConfirmationRecords(
   messageID: string,
   directory?: string | null,
 ): Promise<Array<{ info: Message; parts?: Part[] }> | null> {
+  // Bounded: a connection that never returns must still let the send fail
+  // rather than hang the composer.
+  const reconnectDeadline = Date.now() + SEND_CONFIRMATION_RECONNECT_TIMEOUT_MS
+  while (!useConfigStore.getState().isConnected && Date.now() < reconnectDeadline) {
+    await wait(SEND_CONFIRMATION_RECONNECT_POLL_MS)
+  }
+
   for (let attempt = 0; attempt < SEND_CONFIRMATION_REFETCH_ATTEMPTS; attempt += 1) {
-    if (attempt > 0) await wait(SEND_CONFIRMATION_REFETCH_RETRY_MS)
+    if (attempt > 0) await wait(SEND_CONFIRMATION_REFETCH_BASE_RETRY_MS * 2 ** (attempt - 1))
     try {
       const result = await sdk().session.messages({
         sessionID: sessionId,