fix(feishu): fetch quoted content before empty-message guard (#90192)

* fix(feishu): fetch quoted content before empty-message guard Moves the quoted/replied message content fetching before the empty-message early return so a reply with only @bot mention (no text, no media) is not dropped when it quotes a message with meaningful content. The guard now also checks that quoted text is empty before skipping. Note: because the fetch is now unconditional on parentId after passing the group admission/mention gate, an empty-text reply that quotes a parent in an open group (requireMention: false) without mentioning the bot will now be dispatched, where before it was dropped. This is the intended behavior for open groups — any non-empty turn (including one where context comes from a quote) should reach the agent. For requireMention:true groups, unmentioned messages still exit at the mention gate before the fetch, so no over-fetch occurs. Adds group-based regression tests for the #90177 scenario: - Positive: mention-only reply in requireMention:true group with quoted parent — dispatches with [Replying to: "..."] in the body. - Negative: empty reply with no bot mention in requireMention:true group — getMessageFeishu is never called and nothing is dispatched. * fix(feishu): fetch quoted content before empty-message guard (#90192) (thanks @bladin) --------- Co-authored-by: 黑承亮0668000844 <bladin@users.noreply.github.com> Co-authored-by: sliverp <870080352@qq.com>
2026-06-22 06:28:12 +00:00 · 2026-06-17 15:34:23 +08:00
parent e349bdb949
commit bda7581126
3 changed files with 197 additions and 46 deletions
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -26,6 +26,7 @@ Docs: https://docs.openclaw.ai

 - Channels and delivery: preserve account-scoped DM channel send policy, intentional rich-message line breaks in Telegram and status output, rich Telegram final replies, rich Telegram tables and lists, Telegram thread-create CLI remapping, Feishu dynamic-agent routes after persisted binding reuse, Slack outbound `message_sent` hooks, contributed message-tool schema optionality, same-channel generated media completions, and channel chunking around surrogate pairs and Infinity limits. (#92788, #93164, #92679, #89421, #89943, #42837, #92814, #91137, #91246, #92735) Thanks @yetval, @obviyus, @spacegeologist, @rishitamrakar, @liuhao1024, @lundog, @TurboTheTurtle, and @yhterrance.
 - Gemini CLI: use the selected OpenClaw OAuth/API-key auth profile in an isolated Gemini CLI runtime home, preventing ambient Google machine credentials from overriding the chosen profile. (#88748) Thanks @jason-allen-oneal and @shakkernerd.
+- Feishu: fetch quoted/replied message content before the empty-message guard so a mention-only reply that quotes a message with meaningful content is no longer dropped. (#90192) Thanks @bladin.
 - Discord: give generated auto-thread titles a 60-second timeout and 4,096-token reasoning-model output budget, clamped to the selected model output cap. (#64734) Thanks @hanamizuki.
 - Agent, cron, and Gateway runtime: mark active main sessions before restart shutdown aborts, pause yielded subagent runs whose terminal also signals abort, clamp trusted subagent thinking overrides through provider/model fallback, preserve yielded media completions, deliver channel message-tool final replies through auto-reply while hiding internal delivery hints, restore reset archive fallback reads when active async transcripts are missing, de-duplicate main-session heartbeat events, expose session identity in runtime prompts, reject unknown OpenAI agent selectors, keep generated media completions, slash-command block replies, and trajectory export commands in WebChat, and require admin privileges for HTTP session/model override surfaces. (#91357, #92631, #92412, #92146, #92879, #91287, #92468, #92510, #91246, #92651, #92646) Thanks @ooiuuii, @openperf, @IWhatsskill, @masatohoshino, @CadanHu, @ZengWen-DT, @zhangguiping-xydt, and @TurboTheTurtle.
 - Providers and model replay: preserve storeless OpenAI Responses replay compatibility, recover invalid OpenAI reasoning signatures and genericized Anthropic thinking-signature replay errors, route OAuth image defaults through Codex for eligible OpenAI profiles, avoid eager tool streaming for Claude 4.5 in Copilot, quarantine unreadable and post-hook OpenAI/Anthropic-family tool schemas without broadening allowed tool choices, deliver explicit thinking-off requests to LM Studio binary-thinking models, honor profile auth for SecretRef model entries, bound model browsing, strip provider prefixes where runtimes need bare IDs, and surface nested embedding fetch failures. (#90706, #92941, #92201, #92916, #92824, #75393, #92908, #92921, #92928, #92002, #90686, #92247, #92627, #91218, #92628) Thanks @snowzlm, @mmyzwl, @CarlCapital, @bek91, @Kailigithub, @vincentkoc, @rohitjavvadi, @samson910022, @nxmxbbd, @liuhao1024, @bymle, and @mushuiyu886.
--- a/extensions/feishu/src/bot.test.ts
+++ b/extensions/feishu/src/bot.test.ts
@@ -424,6 +424,7 @@ async function dispatchMessage(params: {
  currentCfg?: ClawdbotConfig;
  event: FeishuMessageEvent;
  channelRuntime?: PluginRuntime["channel"];
+  botOpenId?: string;
 }) {
  const runtime = createRuntimeEnv();
  const feishuConfig = params.cfg.channels?.feishu;
@@ -444,6 +445,7 @@ async function dispatchMessage(params: {
  await handleFeishuMessage({
    cfg,
    event: params.event,
+    botOpenId: params.botOpenId,
    runtime,
    channelRuntime: params.channelRuntime,
  });
@@ -4164,6 +4166,150 @@ describe("handleFeishuMessage command authorization", () => {
    // No reply should be dispatched: empty message is silently skipped
    expect(mockDispatchReplyFromConfig).not.toHaveBeenCalled();
  });
+
+  it("does not drop empty-text message when it quotes a parent message (#90177)", async () => {
+    // A Feishu reply containing only @bot (no additional text) was being
+    // dropped before the quoted message content was fetched. The handler
+    // should fetch quoted content first and only skip if all of current
+    // text, media, and quoted content are empty.
+    mockShouldComputeCommandAuthorized.mockReturnValue(false);
+    mockGetMessageFeishu.mockResolvedValueOnce({
+      messageId: "om_quoted_001",
+      chatId: "oc-dm",
+      content: "quoted message content from parent",
+      contentType: "text",
+    });
+
+    const cfg: ClawdbotConfig = {
+      channels: {
+        feishu: {
+          dmPolicy: "open",
+          allowFrom: ["*"],
+        },
+      },
+    } as ClawdbotConfig;
+
+    const event: FeishuMessageEvent = {
+      sender: {
+        sender_id: {
+          open_id: "ou-reply-only-bot",
+        },
+      },
+      message: {
+        message_id: "msg-empty-with-quote",
+        parent_id: "om_quoted_001",
+        chat_id: "oc-dm",
+        chat_type: "p2p",
+        message_type: "text",
+        // Empty text — only @bot mention, no additional content
+        content: JSON.stringify({ text: "" }),
+      },
+    };
+
+    await dispatchMessage({ cfg, event });
+
+    // A reply should be dispatched because quoted content provides context
+    expect(mockDispatchReplyFromConfig).toHaveBeenCalledTimes(1);
+  });
+
+  it("dispatches mention-only group reply with quoted content in requireMention:true group (#90177)", async () => {
+    // #90177 is specifically about group chats. The empty-message drop happens
+    // after the group admission/mention gate, so the fix must also work when
+    // the sender mentions the bot in a requireMention:true group and quotes a
+    // parent message with meaningful content — the reply should dispatch with
+    // the quoted text in the body.
+    mockShouldComputeCommandAuthorized.mockReturnValue(false);
+    mockGetMessageFeishu.mockResolvedValueOnce({
+      messageId: "om_group_quoted_001",
+      chatId: "oc-group-90177",
+      content: "parent message with context",
+      contentType: "text",
+    });
+
+    const cfg: ClawdbotConfig = {
+      channels: {
+        feishu: {
+          groupPolicy: "open",
+          groups: {
+            "oc-group-90177": {
+              requireMention: true,
+            },
+          },
+        },
+      },
+    } as ClawdbotConfig;
+
+    const event: FeishuMessageEvent = {
+      sender: {
+        sender_id: {
+          open_id: "ou-group-sender",
+        },
+      },
+      message: {
+        message_id: "msg-group-empty-with-quote",
+        parent_id: "om_group_quoted_001",
+        chat_id: "oc-group-90177",
+        chat_type: "group",
+        message_type: "text",
+        // Empty text — only @bot mention, no additional content
+        content: JSON.stringify({ text: "" }),
+        // Bot mention so the message passes the requireMention gate
+        mentions: [
+          { key: "@_bot_1", id: { open_id: "ou-bot-90177" }, name: "Bot", tenant_key: "" },
+        ],
+      },
+    };
+
+    await dispatchMessage({ cfg, event, botOpenId: "ou-bot-90177" });
+
+    expect(mockDispatchReplyFromConfig).toHaveBeenCalledTimes(1);
+    const context = mockCallArg<{ Body?: string }>(mockFinalizeInboundContext, 0, 0);
+    expect(context.Body).toContain("[Replying to:");
+    expect(context.Body).toContain("parent message with context");
+  });
+
+  it("does not over-fetch quoted message for unmentioned empty reply in requireMention:true group (#90177)", async () => {
+    // An empty-text reply that quotes a parent but does NOT mention the bot
+    // in a requireMention:true group should be rejected at the mention gate
+    // before the quoted message is fetched, so getMessageFeishu is never
+    // called and nothing is dispatched.
+    mockShouldComputeCommandAuthorized.mockReturnValue(false);
+
+    const cfg: ClawdbotConfig = {
+      channels: {
+        feishu: {
+          groupPolicy: "open",
+          groups: {
+            "oc-group-90177-neg": {
+              requireMention: true,
+            },
+          },
+        },
+      },
+    } as ClawdbotConfig;
+
+    const event: FeishuMessageEvent = {
+      sender: {
+        sender_id: {
+          open_id: "ou-group-sender-neg",
+        },
+      },
+      message: {
+        message_id: "msg-group-unmentioned-empty-quote",
+        parent_id: "om_group_quoted_neg",
+        chat_id: "oc-group-90177-neg",
+        chat_type: "group",
+        message_type: "text",
+        // Empty text with no bot mention
+        content: JSON.stringify({ text: "" }),
+      },
+    };
+
+    await dispatchMessage({ cfg, event, botOpenId: "ou-bot-90177-neg" });
+
+    expect(mockGetMessageFeishu).not.toHaveBeenCalled();
+    expect(mockDispatchReplyFromConfig).not.toHaveBeenCalled();
+  });
 });

 describe("createFeishuMessageReceiveHandler media dedupe", () => {
--- a/extensions/feishu/src/bot.ts
+++ b/extensions/feishu/src/bot.ts
@@ -1026,15 +1026,57 @@ export async function handleFeishuMessage(params: {
      log,
      accountId: account.accountId,
    });
-    // Skip messages with no text content and no media attachments. Feishu can
-    // deliver empty-text events (e.g. `{"text":""}`) when a user sends a blank
-    // message or when media parsing produces an empty string. Writing a blank
-    // user turn to the session causes downstream LLM providers (e.g. MiniMax)
-    // to reject the request with "messages must not be empty" errors. Logging
-    // the skip avoids silent loss without polluting the agent session.
-    if (!ctx.content.trim() && mediaList.length === 0) {
+    // Fetch quoted/replied message content before the empty-message guard
+    // so a reply with only @bot (no text, no media) is not dropped when
+    // the quoted message carries meaningful content.
+    let quotedMessageInfo: Awaited<ReturnType<typeof getMessageFeishu>> = null;
+    let quotedContent: string | undefined;
+    if (ctx.parentId) {
+      try {
+        quotedMessageInfo = await getMessageFeishu({
+          cfg,
+          messageId: ctx.parentId,
+          accountId: account.accountId,
+        });
+        if (
+          quotedMessageInfo &&
+          (await shouldIncludeFetchedGroupContextMessage({
+            cfg,
+            accountId: account.accountId,
+            chatId: ctx.chatId,
+            isGroup,
+            allowFrom: effectiveGroupSenderAllowFrom,
+            mode: contextVisibilityMode,
+            kind: "quote",
+            senderId: quotedMessageInfo.senderId,
+            senderType: quotedMessageInfo.senderType,
+          }))
+        ) {
+          quotedContent = quotedMessageInfo.content;
+          log(
+            `feishu[${account.accountId}]: fetched quoted message: ${quotedContent?.slice(0, 100)}`,
+          );
+        } else if (quotedMessageInfo) {
+          log(
+            `feishu[${account.accountId}]: skipped quoted message from sender ${quotedMessageInfo.senderId ?? "unknown"} (mode=${contextVisibilityMode})`,
+          );
+        }
+      } catch (err) {
+        log(`feishu[${account.accountId}]: failed to fetch quoted message: ${String(err)}`);
+      }
+    }
+
+    // Skip messages with no text content, no media attachments, and no quoted
+    // content. Feishu can deliver empty-text events (e.g. `{"text":""}`) when
+    // a user sends a blank message or when media parsing produces an empty
+    // string. Writing a blank user turn to the session causes downstream LLM
+    // providers (e.g. MiniMax) to reject the request with "messages must not
+    // be empty" errors. Logging the skip avoids silent loss without polluting
+    // the agent session. Quoted content is checked too so a reply-only @bot
+    // with quoted context is not dropped.
+    if (!ctx.content.trim() && mediaList.length === 0 && !quotedContent?.trim()) {
      log(
-        `feishu[${account.accountId}]: skipping empty message (no text, no media) from ${ctx.senderOpenId}`,
+        `feishu[${account.accountId}]: skipping empty message (no text, no media, no quoted) from ${ctx.senderOpenId}`,
      );
      return;
    }
@@ -1107,44 +1149,6 @@ export async function handleFeishuMessage(params: {
            ).commandAccess.authorized
      : undefined;

-    // Fetch quoted/replied message content if parentId exists
-    let quotedMessageInfo: Awaited<ReturnType<typeof getMessageFeishu>> = null;
-    let quotedContent: string | undefined;
-    if (ctx.parentId) {
-      try {
-        quotedMessageInfo = await getMessageFeishu({
-          cfg,
-          messageId: ctx.parentId,
-          accountId: account.accountId,
-        });
-        if (
-          quotedMessageInfo &&
-          (await shouldIncludeFetchedGroupContextMessage({
-            cfg,
-            accountId: account.accountId,
-            chatId: ctx.chatId,
-            isGroup,
-            allowFrom: effectiveGroupSenderAllowFrom,
-            mode: contextVisibilityMode,
-            kind: "quote",
-            senderId: quotedMessageInfo.senderId,
-            senderType: quotedMessageInfo.senderType,
-          }))
-        ) {
-          quotedContent = quotedMessageInfo.content;
-          log(
-            `feishu[${account.accountId}]: fetched quoted message: ${quotedContent?.slice(0, 100)}`,
-          );
-        } else if (quotedMessageInfo) {
-          log(
-            `feishu[${account.accountId}]: skipped quoted message from sender ${quotedMessageInfo.senderId ?? "unknown"} (mode=${contextVisibilityMode})`,
-          );
-        }
-      } catch (err) {
-        log(`feishu[${account.accountId}]: failed to fetch quoted message: ${String(err)}`);
-      }
-    }
-
    const isTopicSessionForThread =
      isGroup &&
      (groupSession?.groupSessionScope === "group_topic" ||