fix(qqbot): add stream config (#63746)

CHANGELOG.md

@@ -27,6 +27,7 @@ Docs: https://docs.openclaw.ai
 - Sessions/model selection: preserve catalog-backed session model labels and keep already-qualified session model refs stable when catalog metadata is unavailable, so Control UI model selection survives reloads without bogus provider-prefixed values. (#61382) Thanks @Mule-ME.
 - Gateway/startup: keep WebSocket RPC available while channels and plugin sidecars start, hold `chat.history` unavailable until startup sidecars finish so synchronous history reads cannot stall startup (reported in #63450), refresh advertised gateway methods after deferred plugin reloads, and enforce the pre-auth WebSocket upgrade budget before the no-handler 503 path so upgrade floods cannot bypass connection limits during that window. (#63480) Thanks @neeravmakwana.
 - Gateway/tailscale: start Tailscale exposure and the gateway update check before awaiting channel and plugin sidecar startup so remote operators are not locked out when startup sidecars stall.
+- QQBot/streaming: make block streaming configurable per QQ bot account via `streaming.mode` (`"partial"` | `"off"`, default `"partial"`) instead of hardcoding it off, so responses can be delivered incrementally. (#63746)
 
 ## 2026.4.9
 

extensions/qqbot/openclaw.plugin.json

@@ -100,6 +100,17 @@
           "upgradeMode": {
             "type": "string",
             "enum": ["doc", "hot-reload"]
+          },
+          "streaming": {
+            "type": "object",
+            "additionalProperties": false,
+            "properties": {
+              "mode": {
+                "type": "string",
+                "enum": ["off", "partial"],
+                "default": "partial"
+              }
+            }
           }
         }
       }
@@ -129,6 +140,17 @@
         "type": "string",
         "enum": ["doc", "hot-reload"]
       },
+      "streaming": {
+        "type": "object",
+        "additionalProperties": false,
+        "properties": {
+          "mode": {
+            "type": "string",
+            "enum": ["off", "partial"],
+            "default": "partial"
+          }
+        }
+      },
       "accounts": {
         "type": "object",
         "additionalProperties": {

extensions/qqbot/src/config-schema.ts

@@ -41,6 +41,14 @@ const QQBotSttSchema = z
   .strict()
   .optional();
 
+const QQBotStreamingSchema = z
+  .object({
+    /** "partial" (default) enables block streaming; "off" disables it. */
+    mode: z.enum(["off", "partial"]).default("partial"),
+  })
+  .strict()
+  .optional();
+
 const QQBotAccountSchema = z
   .object({
     enabled: z.boolean().optional(),
@@ -56,6 +64,7 @@ const QQBotAccountSchema = z
     urlDirectUpload: z.boolean().optional(),
     upgradeUrl: z.string().optional(),
     upgradeMode: z.enum(["doc", "hot-reload"]).optional(),
+    streaming: QQBotStreamingSchema,
   })
   .strict();
 

extensions/qqbot/src/gateway.ts

@@ -1151,7 +1151,7 @@ export async function startGateway(ctx: GatewayContext): Promise<void> {
                 },
               },
               replyOptions: {
-                disableBlockStreaming: true,
+                disableBlockStreaming: account.config.streaming?.mode === "off",
               },
             });
 

extensions/qqbot/src/types.ts

@@ -57,6 +57,14 @@ export interface QQBotAccountConfig {
    * - "hot-reload": run an in-place npm update flow
    */
   upgradeMode?: "doc" | "hot-reload";
+  /**
+   * Block streaming configuration.
+   * - mode "partial" (default): enable block streaming for incremental delivery.
+   * - mode "off": buffer the full response before sending.
+   */
+  streaming?: {
+    mode?: "off" | "partial";
+  };
 }
 
 /** Audio format policy controlling which formats can skip transcoding. */