From 740bb77c8c028995a10f8e889f00637ff208ebc1 Mon Sep 17 00:00:00 2001
From: liuxiaopai-ai <73659136+liuxiaopai-ai@users.noreply.github.com>
Date: Tue, 3 Mar 2026 00:14:59 +0800
Subject: [PATCH] fix(reply): prefer provider over surface for run channel
 fallback

---
 CHANGELOG.md                                  |  1 +
 .../reply/get-reply-run.media-only.test.ts    | 31 +++++++++++++++++++
 src/auto-reply/reply/get-reply-run.ts         |  5 ++-
 3 files changed, 36 insertions(+), 1 deletion(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index de02257a5..69f0b3ad1 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -53,6 +53,7 @@ Docs: https://docs.openclaw.ai
 - Skills/sherpa-onnx-tts: run the `sherpa-onnx-tts` bin under ESM (replace CommonJS `require` imports) and add regression coverage to prevent `require is not defined in ES module scope` startup crashes. (#31965) Thanks @bmendonca3.
 - Browser/default profile selection: default `browser.defaultProfile` behavior now prefers `openclaw` (managed standalone CDP) when no explicit default is configured, while still auto-provisioning the `chrome` relay profile for explicit opt-in use. (#32031) Fixes #31907. Thanks @liuxiaopai-ai.
 - Doctor/local memory provider checks: stop false-positive local-provider warnings when `provider=local` and no explicit `modelPath` is set by honoring default local model fallback while still warning when gateway probe reports local embeddings not ready. (#32014) Fixes #31998. Thanks @adhishthite.
+- Feishu/Run channel fallback: prefer `Provider` over `Surface` when inferring queued run `messageProvider` fallback (when `OriginatingChannel` is missing), preventing Feishu turns from being mislabeled as `webchat` in mixed relay metadata contexts. (#31880) Fixes #31859. Thanks @liuxiaopai-ai.
 - Sandbox/Docker setup command parsing: accept `agents.*.sandbox.docker.setupCommand` as either a string or a string array, and normalize arrays to newline-delimited shell scripts so multi-step setup commands no longer concatenate without separators. (#31953) Thanks @liuxiaopai-ai.
 - Gateway/Plugin HTTP route precedence: run explicit plugin HTTP routes before the Control UI SPA catch-all so registered plugin webhook/custom paths remain reachable, while unmatched paths still fall through to Control UI handling. (#31885) Thanks @Sid-Qin.
 - Security/Node exec approvals: preserve shell/dispatch-wrapper argv semantics during approval hardening so approved wrapper commands (for example `env sh -c ...`) cannot drift into a different runtime command shape, and add regression coverage for both approval-plan generation and approved runtime execution paths. Thanks @tdjackey for reporting.
diff --git a/src/auto-reply/reply/get-reply-run.media-only.test.ts b/src/auto-reply/reply/get-reply-run.media-only.test.ts
index 6105613d6..4e1c28f71 100644
--- a/src/auto-reply/reply/get-reply-run.media-only.test.ts
+++ b/src/auto-reply/reply/get-reply-run.media-only.test.ts
@@ -281,6 +281,37 @@ describe("runPreparedReply media-only handling", () => {
     expect(call?.followupRun.run.messageProvider).toBe("webchat");
   });
 
+  it("prefers Provider over Surface when origin channel is missing", async () => {
+    await runPreparedReply(
+      baseParams({
+        ctx: {
+          Body: "",
+          RawBody: "",
+          CommandBody: "",
+          ThreadHistoryBody: "Earlier message in this thread",
+          OriginatingChannel: undefined,
+          OriginatingTo: undefined,
+          Provider: "feishu",
+          Surface: "webchat",
+          ChatType: "group",
+        },
+        sessionCtx: {
+          Body: "",
+          BodyStripped: "",
+          ThreadHistoryBody: "Earlier message in this thread",
+          MediaPath: "/tmp/input.png",
+          Provider: "webchat",
+          ChatType: "group",
+          OriginatingChannel: undefined,
+          OriginatingTo: undefined,
+        },
+      }),
+    );
+
+    const call = vi.mocked(runReplyAgent).mock.calls[0]?.[0];
+    expect(call?.followupRun.run.messageProvider).toBe("feishu");
+  });
+
   it("passes suppressTyping through typing mode resolution", async () => {
     await runPreparedReply(
       baseParams({
diff --git a/src/auto-reply/reply/get-reply-run.ts b/src/auto-reply/reply/get-reply-run.ts
index b54115d10..3c4698756 100644
--- a/src/auto-reply/reply/get-reply-run.ts
+++ b/src/auto-reply/reply/get-reply-run.ts
@@ -477,7 +477,10 @@ export async function runPreparedReply(
       sessionKey,
       messageProvider: resolveOriginMessageProvider({
         originatingChannel: ctx.OriginatingChannel ?? sessionCtx.OriginatingChannel,
-        provider: ctx.Surface ?? ctx.Provider ?? sessionCtx.Provider,
+        // Prefer Provider over Surface for fallback channel identity.
+        // Surface can carry relayed metadata (for example "webchat") while Provider
+        // still reflects the active channel that should own tool routing.
+        provider: ctx.Provider ?? ctx.Surface ?? sessionCtx.Provider,
       }),
       agentAccountId: sessionCtx.AccountId,
       groupId: resolveGroupSessionKey(sessionCtx)?.id ?? undefined,