internal/api/agent.go

@@ -124,10 +124,28 @@ type eventStream struct {
 // Headers go out before the first write and the stream is flushed immediately,
 // so a proxy holding the response until it looks complete can't reintroduce
 // exactly the silence streaming exists to remove.
+//
+// Clearing the write deadline is what makes a turn longer than the server's
+// WriteTimeout possible at all (#78). That timeout is an ABSOLUTE deadline from
+// when the request header was read, not an idle timeout, so a streaming response
+// has to opt out of it explicitly or it is cut mid-turn no matter how recently
+// it wrote. Without this the 4-minute runTimeout is unreachable and the
+// keep-alive below tops out at one tick — it would be pacing a connection that
+// is destroyed underneath it.
+//
+// This failure is INVISIBLE from in here: the writes after the deadline return
+// err == nil and their bytes are dropped, so there is nothing to detect and
+// report. Only the client sees it, as a truncated stream it reports as a dropped
+// connection. That is why this is done up front rather than handled on write.
 func openEventStream(c *gin.Context) *eventStream {
 	c.Header("Content-Type", "text/event-stream")
 	c.Header("Cache-Control", "no-cache")
 	c.Header("X-Accel-Buffering", "no")
+	// A failure here is worth saying out loud: it means this stream WILL be cut
+	// at WriteTimeout and we cannot stop it.
+	if err := http.NewResponseController(c.Writer).SetWriteDeadline(time.Time{}); err != nil {
+		slog.Error("api: cannot clear SSE write deadline; long turns will be truncated", "error", err)
+	}
 	c.Writer.Flush()
 	return &eventStream{c: c}
 }

internal/api/sse_deadline_test.go

@@ -0,0 +1,67 @@
+package api
+
+import (
+	"bufio"
+	"net/http/httptest"
+	"strings"
+	"testing"
+	"time"
+
+	"github.com/gin-gonic/gin"
+)
+
+// TestEventStreamOutlivesWriteTimeout is the regression test for #78.
+//
+// http.Server.WriteTimeout is an ABSOLUTE deadline measured from when the
+// request header was read — not an idle timeout — so a streaming response is cut
+// once it passes, however recently the handler wrote. pansy sets it to 30s while
+// an agent turn may run for minutes.
+//
+// This has to be driven through a real http.Server and asserted from the CLIENT
+// side, because the failure cannot be observed from the handler: writes made
+// after the deadline return err == nil and their bytes are silently discarded.
+// A test that checked the return of io.WriteString would pass against the bug.
+func TestEventStreamOutlivesWriteTimeout(t *testing.T) {
+	// Long enough that the frames below straddle it, short enough to keep the
+	// test quick. Everything else is scaled off it.
+	const writeTimeout = 300 * time.Millisecond
+	const tick = 200 * time.Millisecond
+	const frames = 4 // last one lands at ~800ms, well past the deadline
+
+	gin.SetMode(gin.TestMode)
+	r := gin.New()
+	r.GET("/stream", func(c *gin.Context) {
+		s := openEventStream(c)
+		for i := 0; i < frames; i++ {
+			time.Sleep(tick)
+			s.send(chatEvent{Error: "frame"})
+		}
+	})
+
+	srv := httptest.NewUnstartedServer(r)
+	srv.Config.WriteTimeout = writeTimeout
+	srv.Start()
+	defer srv.Close()
+
+	resp, err := srv.Client().Get(srv.URL + "/stream")
+	if err != nil {
+		t.Fatalf("get: %v", err)
+	}
+	defer resp.Body.Close()
+
+	got := 0
+	sc := bufio.NewScanner(resp.Body)
+	for sc.Scan() {
+		if strings.HasPrefix(sc.Text(), "data: ") {
+			got++
+		}
+	}
+	// Read errors are the symptom, not an aside: against the bug the client gets
+	// an unexpected EOF partway through. Report it rather than only the count.
+	if err := sc.Err(); err != nil {
+		t.Errorf("client read error after %d/%d frames: %v", got, frames, err)
+	}
+	if got != frames {
+		t.Errorf("client received %d frames, want %d — the stream was cut at WriteTimeout", got, frames)
+	}
+}