@trigger.dev/sdk 4.5.1 → 4.5.3

package/dist/esm/v3/ai-shared.d.ts

@@ -15,138 +15,14 @@
  * import from `ai.ts`.
  */
 import type { Task, AnyTask } from "@trigger.dev/core/v3";
-import type { InferUITools, ModelMessage, ToolSet, UIDataTypes, UIMessage } from "ai";
+import type { InferUITools, ToolSet, UIDataTypes, UIMessage } from "ai";
 /**
  * Message-part `type` value for the pending-message data part the agent
  * injects when a follow-up message arrives mid-turn.
  */
 export declare const PENDING_MESSAGE_INJECTED_TYPE: "data-pending-message-injected";
-/**
- * The wire payload shape sent by `TriggerChatTransport`.
- * Uses `metadata` to match the AI SDK's `ChatRequestOptions` field name.
- *
- * Slim wire: at most ONE message per record. The agent runtime
- * reconstructs prior history at run boot from a durable S3 snapshot +
- * `session.out` replay (or `hydrateMessages` if registered). The wire is
- * delta-only — see plan `vivid-humming-bonbon.md`.
- */
-export type ChatTaskWirePayload<TMessage extends UIMessage = UIMessage, TMetadata = unknown> = {
-    /**
-     * The single message being delivered on this trigger. Set for:
-     *   - `submit-message`: the new user message OR a tool-approval-responded
-     *     assistant message (with `state: "approval-responded"` tool parts).
-     *   - `regenerate-message`: omitted (the agent slices its own history).
-     *   - `preload` / `close` / `action`: omitted.
-     *   - `handover-prepare`: omitted (use `headStartMessages` instead).
-     */
-    message?: TMessage;
-    /**
-     * Bespoke escape hatch for `chat.headStart`. The customer's HTTP route
-     * handler ships full `UIMessage[]` history at the very first turn — before
-     * any snapshot exists. The route handler isn't subject to the
-     * `MAX_APPEND_BODY_BYTES` cap on `/in/append` because it goes through the
-     * customer's own HTTP endpoint. Used ONLY by `trigger: "handover-prepare"`.
-     * Ignored on every other trigger.
-     */
-    headStartMessages?: TMessage[];
-    chatId: string;
-    trigger: "submit-message" | "regenerate-message" | "preload" | "close" | "action"
-    /**
-     * The customer's `chat.handover` route handler kicked us off in
-     * parallel with the first-turn `streamText` running in the warm
-     * Next.js process. The run sits idle on `session.in` waiting for
-     * a `kind: "handover"` (continue from tool execution) or
-     * `kind: "handover-skip"` (handler finished pure-text, exit
-     * cleanly). See `chat.handover` in `@trigger.dev/sdk/chat-server`.
-     */
-     | "handover-prepare";
-    messageId?: string;
-    metadata?: TMetadata;
-    /** Custom action payload when `trigger` is `"action"`. Validated against `actionSchema` on the backend. */
-    action?: unknown;
-    /** Whether this run is continuing an existing chat whose previous run ended. */
-    continuation?: boolean;
-    /** The run ID of the previous run (only set when `continuation` is true). */
-    previousRunId?: string;
-    /** Override idle timeout for this run (seconds). Set by transport.preload(). */
-    idleTimeoutInSeconds?: number;
-    /**
-     * The friendlyId of the Session primitive backing this chat. The
-     * transport opens (or lazy-creates) the session with
-     * `externalId = chatId` on first message, then sends this friendlyId
-     * through to the run so the agent can attach to `.in` / `.out`
-     * without needing to round-trip through the control plane again.
-     * Optional for backward-compat while the migration is in flight;
-     * required once the legacy run-scoped stream path is removed.
-     */
-    sessionId?: string;
-};
-/**
- * One chunk on the chat input stream. `kind` discriminates the variants —
- * a single ordered stream now carries all the signals the old three-stream
- * split did (`chat-messages`, `chat-stop`, plus action messages piggybacked
- * on `chat-messages`).
- */
-export type ChatInputChunk<TMessage extends UIMessage = UIMessage, TMetadata = unknown> = {
-    kind: "message";
-    /**
-     * Full wire payload for a new user message or regeneration. Mirrors
-     * what the legacy `chat-messages` input stream carried.
-     */
-    payload: ChatTaskWirePayload<TMessage, TMetadata>;
-} | {
-    kind: "stop";
-    /** Optional human-readable reason. Maps to the legacy `chat-stop` record. */
-    message?: string;
-} | {
-    /**
-     * Sent by `chat.headStart` when the customer's first-turn
-     * `streamText` finishes. The agent run (currently parked in
-     * `handover-prepare`) wakes, seeds its accumulators with
-     * `partialAssistantMessage`, and runs the normal turn loop
-     * (`onChatStart` → `onTurnStart` → … → `onTurnComplete`).
-     *
-     * What happens after that depends on `isFinal`:
-     *
-     * - `isFinal: false` — step 1 ended with `finishReason:
-     *   "tool-calls"`. The partial carries the assistant's
-     *   tool-call(s) wrapped in AI SDK's tool-approval round. The
-     *   agent's `streamText` runs the approved tools and continues
-     *   from step 2.
-     * - `isFinal: true` — step 1 ended pure-text (no tool calls).
-     *   The partial carries the final assistant text. The agent
-     *   skips the LLM call entirely (the response is already
-     *   complete on the customer side) and runs `onTurnComplete`
-     *   with the partial as `responseMessage` so persistence and
-     *   any post-turn work fire normally.
-     */
-    kind: "handover";
-    /** Customer's step-1 response messages (ModelMessage form). */
-    partialAssistantMessage: ModelMessage[];
-    /**
-     * The UI messageId the customer's handler used for its step-1
-     * assistant message. The agent reuses this so any post-handover
-     * chunks (tool-output-available, step-2 text, data-* parts
-     * written by hooks) merge into the SAME assistant message on
-     * the browser side instead of starting a new one.
-     */
-    messageId?: string;
-    /**
-     * Whether the customer's step 1 is the final response. See
-     * `kind` description above for the two branches.
-     */
-    isFinal: boolean;
-} | {
-    /**
-     * Sent by `chat.headStart` only when the customer's handler
-     * ABORTS before producing a finishReason (e.g., dispatch error,
-     * stream cancelled before any tokens). The agent run exits
-     * cleanly without firing turn hooks. Normal pure-text and
-     * tool-call finishes go through `kind: "handover"` with the
-     * appropriate `isFinal` flag.
-     */
-    kind: "handover-skip";
-};
+import type { ChatTaskWirePayload } from "./chat.js";
+export type { ChatTaskWirePayload, ChatInputChunk } from "./chat.js";
 /**
  * Extracts the client-data (`metadata`) type from a chat task.
  *

package/dist/esm/v3/ai-shared.js.map

@@ -1 +1 @@
-{"version":3,"file":"ai-shared.js","sourceRoot":"","sources":["../../../src/v3/ai-shared.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;GAeG;AAKH;;;GAGG;AACH,MAAM,CAAC,MAAM,6BAA6B,GAAG,+BAAwC,CAAC;AA6LtF;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAqCG;AACH,MAAM,UAAU,qBAAqB,CACnC,MAAc,EACd,KAGC;IAED,IAAI,KAAK,CAAC,OAAO,KAAK,gBAAgB;QAAE,OAAO,KAAK,CAAC;IACrD,IAAI,KAAK,CAAC,gBAAgB,CAAC,MAAM,KAAK,CAAC;QAAE,OAAO,KAAK,CAAC;IACtD,MAAM,MAAM,GAAG,KAAK,CAAC,gBAAgB,CAAC,KAAK,CAAC,gBAAgB,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC;IACzE,IAAI,CAAC,MAAM;QAAE,OAAO,KAAK,CAAC;IAC1B,IAAI,MAAM,CAAC,EAAE,EAAE,CAAC;QACd,MAAM,WAAW,GAAG,MAAM,CAAC,SAAS,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,EAAE,KAAK,MAAM,CAAC,EAAE,CAAC,CAAC;QAChE,IAAI,WAAW,KAAK,CAAC,CAAC;YAAE,OAAO,KAAK,CAAC;IACvC,CAAC;IACD,MAAM,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC;IACpB,OAAO,IAAI,CAAC;AACd,CAAC;AAED;;;;;;GAMG;AACH,SAAS,0BAA0B,CACjC,KAAc;IAEd,OAAO,CACL,KAAK,KAAK,kBAAkB;QAC5B,KAAK,KAAK,cAAc;QACxB,KAAK,KAAK,oBAAoB;QAC9B,KAAK,KAAK,eAAe,CAC1B,CAAC;AACJ,CAAC;AAED,2EAA2E;AAC3E,SAAS,cAAc,CAAC,IAAa;IACnC,OAAO,OAAO,IAAI,KAAK,QAAQ,IAAI,CAAC,IAAI,CAAC,UAAU,CAAC,OAAO,CAAC,IAAI,IAAI,KAAK,cAAc,CAAC,CAAC;AAC3F,CAAC;AAED;;;;;;;;;;;;;;;;;;;;;;;;;;GA0BG;AACH,MAAM,UAAU,wBAAwB,CAAqC,OAAa;IACxF,IAAI,CAAC,OAAO;QAAE,OAAO,OAAO,CAAC;IAC7B,IAAI,OAAO,CAAC,IAAI,KAAK,WAAW;QAAE,OAAO,OAAO,CAAC;IACjD,MAAM,KAAK,GAAG,CAAC,OAAO,CAAC,KAAK,IAAI,EAAE,CAAU,CAAC;IAC7C,MAAM,iBAAiB,GAAG,KAAK,CAAC,MAAM,CACpC,CAAC,CAAC,EAAE,EAAE,CACJ,CAAC,IAAI,OAAO,CAAC,KAAK,QAAQ,IAAI,cAAc,CAAC,CAAC,CAAC,IAAI,CAAC,IAAI,0BAA0B,CAAC,CAAC,CAAC,KAAK,CAAC,CAC9F,CAAC;IACF,IAAI,iBAAiB,CAAC,MAAM,KAAK,CAAC;QAAE,OAAO,OAAO,CAAC;IACnD,MAAM,SAAS,GAAG,iBAAiB,CAAC,GAAG,CAAC,CAAC,CAAM,EAAE,EAAE;QACjD,MAAM,IAAI,GAA4B;YACpC,IAAI,EAAE,CAAC,CAAC,IAAI;YACZ,UAAU,EAAE,CAAC,CAAC,UAAU;YACxB,KAAK,EAAE,CAAC,CAAC,KAAK;SACf,CAAC;QACF,IAAI,CAAC,CAAC,IAAI,KAAK,cAAc,IAAI,OAAO,CAAC,CAAC,QAAQ,KAAK,QAAQ,EAAE,CAAC;YAChE,IAAI,CAAC,QAAQ,GAAG,CAAC,CAAC,QAAQ,CAAC;QAC7B,CAAC;QACD,IAAI,CAAC,CAAC,KAAK,KAAK,kBAAkB,EAAE,CAAC;YACnC,IAAI,CAAC,MAAM,GAAG,CAAC,CAAC,MAAM,CAAC;YACvB,IAAI,CAAC,CAAC,QAAQ,KAAK,SAAS;gBAAE,IAAI,CAAC,QAAQ,GAAG,CAAC,CAAC,QAAQ,CAAC;QAC3D,CAAC;aAAM,IAAI,CAAC,CAAC,KAAK,KAAK,cAAc,EAAE,CAAC;YACtC,IAAI,CAAC,CAAC,SAAS,KAAK,SAAS;gBAAE,IAAI,CAAC,SAAS,GAAG,CAAC,CAAC,SAAS,CAAC;YAC5D,IAAI,CAAC,CAAC,QAAQ,KAAK,SAAS;gBAAE,IAAI,CAAC,QAAQ,GAAG,CAAC,CAAC,QAAQ,CAAC;QAC3D,CAAC;aAAM,IAAI,CAAC,CAAC,KAAK,KAAK,oBAAoB,IAAI,CAAC,CAAC,KAAK,KAAK,eAAe,EAAE,CAAC;YAC3E,IAAI,CAAC,CAAC,QAAQ,KAAK,SAAS;gBAAE,IAAI,CAAC,QAAQ,GAAG,CAAC,CAAC,QAAQ,CAAC;QAC3D,CAAC;QACD,OAAO,IAAI,CAAC;IACd,CAAC,CAAC,CAAC;IACH,OAAO;QACL,EAAE,EAAE,OAAO,CAAC,EAAE;QACd,IAAI,EAAE,OAAO,CAAC,IAAI;QAClB,KAAK,EAAE,SAAS;KACE,CAAC;AACvB,CAAC"}
+{"version":3,"file":"ai-shared.js","sourceRoot":"","sources":["../../../src/v3/ai-shared.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;GAeG;AAKH;;;GAGG;AACH,MAAM,CAAC,MAAM,6BAA6B,GAAG,+BAAwC,CAAC;AA0DtF;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAqCG;AACH,MAAM,UAAU,qBAAqB,CACnC,MAAc,EACd,KAGC;IAED,IAAI,KAAK,CAAC,OAAO,KAAK,gBAAgB;QAAE,OAAO,KAAK,CAAC;IACrD,IAAI,KAAK,CAAC,gBAAgB,CAAC,MAAM,KAAK,CAAC;QAAE,OAAO,KAAK,CAAC;IACtD,MAAM,MAAM,GAAG,KAAK,CAAC,gBAAgB,CAAC,KAAK,CAAC,gBAAgB,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC;IACzE,IAAI,CAAC,MAAM;QAAE,OAAO,KAAK,CAAC;IAC1B,IAAI,MAAM,CAAC,EAAE,EAAE,CAAC;QACd,MAAM,WAAW,GAAG,MAAM,CAAC,SAAS,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,EAAE,KAAK,MAAM,CAAC,EAAE,CAAC,CAAC;QAChE,IAAI,WAAW,KAAK,CAAC,CAAC;YAAE,OAAO,KAAK,CAAC;IACvC,CAAC;IACD,MAAM,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC;IACpB,OAAO,IAAI,CAAC;AACd,CAAC;AAED;;;;;;GAMG;AACH,SAAS,0BAA0B,CACjC,KAAc;IAEd,OAAO,CACL,KAAK,KAAK,kBAAkB;QAC5B,KAAK,KAAK,cAAc;QACxB,KAAK,KAAK,oBAAoB;QAC9B,KAAK,KAAK,eAAe,CAC1B,CAAC;AACJ,CAAC;AAED,2EAA2E;AAC3E,SAAS,cAAc,CAAC,IAAa;IACnC,OAAO,OAAO,IAAI,KAAK,QAAQ,IAAI,CAAC,IAAI,CAAC,UAAU,CAAC,OAAO,CAAC,IAAI,IAAI,KAAK,cAAc,CAAC,CAAC;AAC3F,CAAC;AAED;;;;;;;;;;;;;;;;;;;;;;;;;;GA0BG;AACH,MAAM,UAAU,wBAAwB,CAAqC,OAAa;IACxF,IAAI,CAAC,OAAO;QAAE,OAAO,OAAO,CAAC;IAC7B,IAAI,OAAO,CAAC,IAAI,KAAK,WAAW;QAAE,OAAO,OAAO,CAAC;IACjD,MAAM,KAAK,GAAG,CAAC,OAAO,CAAC,KAAK,IAAI,EAAE,CAAU,CAAC;IAC7C,MAAM,iBAAiB,GAAG,KAAK,CAAC,MAAM,CACpC,CAAC,CAAC,EAAE,EAAE,CACJ,CAAC,IAAI,OAAO,CAAC,KAAK,QAAQ,IAAI,cAAc,CAAC,CAAC,CAAC,IAAI,CAAC,IAAI,0BAA0B,CAAC,CAAC,CAAC,KAAK,CAAC,CAC9F,CAAC;IACF,IAAI,iBAAiB,CAAC,MAAM,KAAK,CAAC;QAAE,OAAO,OAAO,CAAC;IACnD,MAAM,SAAS,GAAG,iBAAiB,CAAC,GAAG,CAAC,CAAC,CAAM,EAAE,EAAE;QACjD,MAAM,IAAI,GAA4B;YACpC,IAAI,EAAE,CAAC,CAAC,IAAI;YACZ,UAAU,EAAE,CAAC,CAAC,UAAU;YACxB,KAAK,EAAE,CAAC,CAAC,KAAK;SACf,CAAC;QACF,IAAI,CAAC,CAAC,IAAI,KAAK,cAAc,IAAI,OAAO,CAAC,CAAC,QAAQ,KAAK,QAAQ,EAAE,CAAC;YAChE,IAAI,CAAC,QAAQ,GAAG,CAAC,CAAC,QAAQ,CAAC;QAC7B,CAAC;QACD,IAAI,CAAC,CAAC,KAAK,KAAK,kBAAkB,EAAE,CAAC;YACnC,IAAI,CAAC,MAAM,GAAG,CAAC,CAAC,MAAM,CAAC;YACvB,IAAI,CAAC,CAAC,QAAQ,KAAK,SAAS;gBAAE,IAAI,CAAC,QAAQ,GAAG,CAAC,CAAC,QAAQ,CAAC;QAC3D,CAAC;aAAM,IAAI,CAAC,CAAC,KAAK,KAAK,cAAc,EAAE,CAAC;YACtC,IAAI,CAAC,CAAC,SAAS,KAAK,SAAS;gBAAE,IAAI,CAAC,SAAS,GAAG,CAAC,CAAC,SAAS,CAAC;YAC5D,IAAI,CAAC,CAAC,QAAQ,KAAK,SAAS;gBAAE,IAAI,CAAC,QAAQ,GAAG,CAAC,CAAC,QAAQ,CAAC;QAC3D,CAAC;aAAM,IAAI,CAAC,CAAC,KAAK,KAAK,oBAAoB,IAAI,CAAC,CAAC,KAAK,KAAK,eAAe,EAAE,CAAC;YAC3E,IAAI,CAAC,CAAC,QAAQ,KAAK,SAAS;gBAAE,IAAI,CAAC,QAAQ,GAAG,CAAC,CAAC,QAAQ,CAAC;QAC3D,CAAC;QACD,OAAO,IAAI,CAAC;IACd,CAAC,CAAC,CAAC;IACH,OAAO;QACL,EAAE,EAAE,OAAO,CAAC,EAAE;QACd,IAAI,EAAE,OAAO,CAAC,IAAI;QAClB,KAAK,EAAE,SAAS;KACE,CAAC;AACvB,CAAC"}

package/dist/esm/v3/ai.js

@@ -2916,6 +2916,11 @@ function chatAgent(options) {
             // default, `inFlightUsers`). The turn-loop checks this queue ahead of
             // `messagesInput.waitWithIdleTimeout` so recovered turns fire first.
             const bootInjectedQueue = [];
+            // Messages consumed by a turn's `messagesInput.on` handler, dispatched
+            // one per turn by the end-of-turn pickup. Loop-level on purpose:
+            // consuming a record advances the committed `.in` cursor, so entries
+            // dropped with a turn-local buffer are lost permanently.
+            const pendingWireMessages = [];
             const couldHavePriorState = payload.continuation === true || ctx.attempt.number > 1;
             // `.in` resume cursor, computed at most once per boot. The boot
             // block below resolves it (snapshot field or records scan) and the
@@ -3622,6 +3627,9 @@ function chatAgent(options) {
                     } // end else (no boot-injected first turn)
                 }
                 for (let turn = 0; turn < maxTurns; turn++) {
+                    // Declared here so the finally can detach it — a handler leaked past
+                    // its turn duplicates every mid-stream message into the shared buffer.
+                    let turnMsgSub;
                     try {
                         // Extract turn-level context before entering the span. Slim
                         // wire: at most one delta message per record. `headStartMessages`
@@ -3697,8 +3705,6 @@ function chatAgent(options) {
                             const stopSignal = stopController.signal;
                             const cancelSignal = runSignal;
                             const combinedSignal = AbortSignal.any([runSignal, stopController.signal]);
-                            // Buffer messages that arrive during streaming
-                            const pendingMessages = [];
                             const pmConfig = locals.get(chatPendingMessagesKey);
                             const msgSub = messagesInput.on(async (msg) => {
                                 // If pendingMessages is configured, route to the steering queue
@@ -3745,8 +3751,9 @@ function chatAgent(options) {
                                     return; // Don't add to wire buffer — frontend handles non-injected case
                                 }
                                 // No pendingMessages config — standard wire buffer for next turn
-                                pendingMessages.push(msg);
+                                pendingWireMessages.push(msg);
                             });
+                            turnMsgSub = msgSub;
                             // Track new messages for this turn (user input + assistant response).
                             const turnNewModelMessages = [];
                             const turnNewUIMessages = [];
@@ -4801,9 +4808,10 @@ function chatAgent(options) {
                                 return "continue";
                             }
                             // If messages arrived during streaming (without pendingMessages config),
-                            // use the first one immediately as the next turn.
-                            if (pendingMessages.length > 0) {
-                                currentWirePayload = pendingMessages[0];
+                            // dispatch the oldest as the next turn. The rest stay queued
+                            // and drain one per turn.
+                            if (pendingWireMessages.length > 0) {
+                                currentWirePayload = pendingWireMessages.shift();
                                 return "continue";
                             }
                             // chat.requestUpgrade() was called — exit the loop so the
@@ -4889,6 +4897,9 @@ function chatAgent(options) {
                         // Turn error handler: write an error chunk + turn-complete to the stream
                         // so the client sees the error, then wait for the next message instead
                         // of killing the entire run. This keeps the conversation alive.
+                        // Detach the turn's message handler first — left attached it would
+                        // eat the very message the wait below is waiting for.
+                        turnMsgSub?.off();
                         if (turnError instanceof Error &&
                             turnError.name === "AbortError" &&
                             runSignal.aborted) {
@@ -5008,6 +5019,11 @@ function chatAgent(options) {
                             currentWirePayload = bootInjectedQueue.shift();
                             continue;
                         }
+                        // Same for messages buffered during the errored turn — already consumed, idling strands them.
+                        if (pendingWireMessages.length > 0) {
+                            currentWirePayload = pendingWireMessages.shift();
+                            continue;
+                        }
                         // Wait for the next message — same as after a successful turn
                         const effectiveIdleTimeout = metadata.get(IDLE_TIMEOUT_METADATA_KEY) ??
                             idleTimeoutInSeconds;
@@ -5023,6 +5039,9 @@ function chatAgent(options) {
                         currentWirePayload = next.output;
                         // Continue to next iteration of the for loop
                     }
+                    finally {
+                        turnMsgSub?.off();
+                    }
                 }
             }
             finally {
@@ -5933,8 +5952,17 @@ function createChatSession(payload, options) {
             const accumulator = new ChatMessageAccumulator();
             let previousTurnUsage;
             let cumulativeUsage = emptyUsage();
+            // Messages consumed mid-turn, dispatched one per next(). Iterator-level
+            // for the same reason as the agent loop's `pendingWireMessages`:
+            // consumed records never replay, so a turn-local buffer loses them.
+            const sessionPendingWire = [];
+            // The current turn's message subscription — detached defensively at the
+            // top of next() in case user code threw without complete()/done().
+            let activeMsgSub;
             return {
                 async next() {
+                    activeMsgSub?.off();
+                    activeMsgSub = undefined;
                     if (!booted) {
                         booted = true;
                         await seedSessionInResumeCursorForCustomLoop(currentPayload);
@@ -5994,23 +6022,29 @@ function createChatSession(payload, options) {
                             currentPayload = { ...currentPayload, continuation: true };
                         }
                     }
-                    // Subsequent turns: wait for the next message
+                    // Subsequent turns: drain buffered mid-turn messages first (they
+                    // were consumed and won't be re-delivered), then wait.
                     if (turn > 0) {
-                        // chat.requestUpgrade() / chat.endRun() — exit before waiting
-                        if (locals.get(chatUpgradeRequestedKey) || locals.get(chatEndRunRequestedKey)) {
-                            stop.cleanup();
-                            return { done: true, value: undefined };
+                        if (sessionPendingWire.length > 0) {
+                            currentPayload = sessionPendingWire.shift();
                         }
-                        const next = await messagesInput.waitWithIdleTimeout({
-                            idleTimeoutInSeconds,
-                            timeout,
-                            spanName: "waiting for next message",
-                        });
-                        if (!next.ok || runSignal.aborted) {
-                            stop.cleanup();
-                            return { done: true, value: undefined };
+                        else {
+                            // chat.requestUpgrade() / chat.endRun() — exit before waiting
+                            if (locals.get(chatUpgradeRequestedKey) || locals.get(chatEndRunRequestedKey)) {
+                                stop.cleanup();
+                                return { done: true, value: undefined };
+                            }
+                            const next = await messagesInput.waitWithIdleTimeout({
+                                idleTimeoutInSeconds,
+                                timeout,
+                                spanName: "waiting for next message",
+                            });
+                            if (!next.ok || runSignal.aborted) {
+                                stop.cleanup();
+                                return { done: true, value: undefined };
+                            }
+                            currentPayload = next.output;
                         }
-                        currentPayload = next.output;
                     }
                     // Check limits
                     if (turn >= maxTurns || runSignal.aborted) {
@@ -6035,10 +6069,10 @@ function createChatSession(payload, options) {
                         clientData: currentPayload.metadata,
                     });
                     // Listen for messages during streaming (steering + next-turn buffer)
-                    const sessionPendingWire = [];
                     const sessionMsgSub = messagesInput.on(async (msg) => {
-                        sessionPendingWire.push(msg);
                         if (sessionPendingMessages) {
+                            // Steering route — the frontend re-sends non-injected
+                            // messages on turn complete, so don't also buffer the wire.
                             // Slim wire: at most one delta message per record. Read
                             // `msg.message` directly — no array slicing needed.
                             const lastUIMessage = msg.message;
@@ -6063,8 +6097,11 @@ function createChatSession(payload, options) {
                                     /* non-fatal */
                                 }
                             }
+                            return;
                         }
+                        sessionPendingWire.push(msg);
                     });
+                    activeMsgSub = sessionMsgSub;
                     // Accumulate messages. Slim wire: pass the single delta message as
                     // a 0-or-1-length array. The accumulator's behavior is unchanged —
                     // it still appends user messages and reconverts on regenerate.
@@ -6155,6 +6192,11 @@ function createChatSession(payload, options) {
                                     throw error;
                                 }
                             }
+                            finally {
+                                // Detach at stream end (like the agent loop): the steering queue
+                                // can't inject anymore, so later arrivals must buffer for the next turn.
+                                sessionMsgSub.off();
+                            }
                             if (response) {
                                 const cleaned = stop.signal.aborted && !runSignal.aborted
                                     ? cleanupAbortedParts(response)
@@ -6298,6 +6340,8 @@ function createChatSession(payload, options) {
                     return { done: false, value: turnObj };
                 },
                 async return() {
+                    activeMsgSub?.off();
+                    activeMsgSub = undefined;
                     // `stop` only exists once next() has booted the iterator.
                     stop?.cleanup();
                     return { done: true, value: undefined };