From 1d0220f9fdc0af1b5c18bef6f5b79be7f4aedb48 Mon Sep 17 00:00:00 2001
From: Hoshina <hoshina@evaz.org>
Date: Sat, 28 Feb 2026 01:39:17 +0800
Subject: [PATCH] fix(agent): prevent reasoning goroutine accumulation on full
 bus

Add a 5-second timeout to handleReasoning's PublishOutbound call so
fire-and-forget goroutines do not block indefinitely when the outbound
bus channel is full. Reasoning output is best-effort; on timeout the
publish is abandoned with a warning log instead of holding the
goroutine alive.

Fixes goroutine leak introduced in #802.
---
 pkg/agent/loop.go | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

diff --git a/pkg/agent/loop.go b/pkg/agent/loop.go
index 29827d0b2..d7daf3775 100644
--- a/pkg/agent/loop.go
+++ b/pkg/agent/loop.go
@@ -574,11 +574,22 @@ func (al *AgentLoop) handleReasoning(ctx context.Context, reasoningContent, chan
 		return
 	}
 
-	al.bus.PublishOutbound(ctx, bus.OutboundMessage{
+	// Use a short timeout so the goroutine does not block indefinitely when
+	// the outbound bus is full.  Reasoning output is best-effort; dropping it
+	// is acceptable to avoid goroutine accumulation.
+	pubCtx, pubCancel := context.WithTimeout(ctx, 5*time.Second)
+	defer pubCancel()
+
+	if err := al.bus.PublishOutbound(pubCtx, bus.OutboundMessage{
 		Channel: channelName,
 		ChatID:  channelID,
 		Content: reasoningContent,
-	})
+	}); err != nil {
+		logger.WarnCF("agent", "Failed to publish reasoning (best-effort)", map[string]any{
+			"channel": channelName,
+			"error":   err.Error(),
+		})
+	}
 }
 
 // runLLMIteration executes the LLM call loop with tool handling.