diff --git a/src/agents/pi-embedded-runner/run/attempt.ts b/src/agents/pi-embedded-runner/run/attempt.ts
index 54ac8b13489..e19dd3cedb2 100644
--- a/src/agents/pi-embedded-runner/run/attempt.ts
+++ b/src/agents/pi-embedded-runner/run/attempt.ts
@@ -1688,6 +1688,14 @@ export async function runEmbeddedAttempt(
         const preCompactionSessionId = activeSession.sessionId;
 
         try {
+          // Flush buffered block replies before waiting for compaction so the
+          // user receives the assistant response immediately.  Without this,
+          // coalesced/buffered blocks stay in the pipeline until compaction
+          // finishes — which can take minutes on large contexts (#35074).
+          if (params.onBlockReplyFlush) {
+            await params.onBlockReplyFlush();
+          }
+
           await abortable(waitForCompactionRetry());
         } catch (err) {
           if (isRunnerAbortError(err)) {
diff --git a/src/agents/pi-embedded-subscribe.handlers.lifecycle.ts b/src/agents/pi-embedded-subscribe.handlers.lifecycle.ts
index 326b51c7266..4c6803e814c 100644
--- a/src/agents/pi-embedded-subscribe.handlers.lifecycle.ts
+++ b/src/agents/pi-embedded-subscribe.handlers.lifecycle.ts
@@ -73,6 +73,11 @@ export function handleAgentEnd(ctx: EmbeddedPiSubscribeContext) {
   }
 
   ctx.flushBlockReplyBuffer();
+  // Flush the reply pipeline so the response reaches the channel before
+  // compaction wait blocks the run.  This mirrors the pattern used by
+  // handleToolExecutionStart and ensures delivery is not held hostage to
+  // long-running compaction (#35074).
+  void ctx.params.onBlockReplyFlush?.();
 
   ctx.state.blockState.thinking = false;
   ctx.state.blockState.final = false;