fix(auto-reply): honor webchat textChunkLimit/chunkMode config overrides [AI-assisted] (#83742)

clawsweeper[bot] · luyao618 · Takhoffman · web-flow · commit 424c6d0a5f46 · 2026-05-18T20:09:40.000Z
Summary: - This PR removes the WebChat special-case from auto-reply chunk limit/mode resolution, adds WebChat override regression tests, and records the fix in the changelog. - Reproducibility: yes. from source inspection rather than runtime execution: current main returns the fallbac ... bchat` before reading `cfg.channels`, so a configured `channels.webchat.textChunkLimit` cannot take effect. Automerge notes: - PR branch already contained follow-up commit before automerge: fix(auto-reply): honor webchat textChunkLimit/chunkMode config overri… Validation: - ClawSweeper review passed for head cd9ac01. - Required merge gates passed before the squash merge. Prepared head SHA: cd9ac01 Review: #83742 (comment) Co-authored-by: luyao618 <364939526@qq.com> Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com> Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com> Approved-by: takhoffman Co-authored-by: takhoffman <781889+takhoffman@users.noreply.github.com>
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -54,6 +54,7 @@ Docs: https://docs.openclaw.ai
 - Models: show the effective OpenAI/Codex auth profile in `/models` provider headers instead of falling back to the OpenAI env-key label. (#83697) Thanks @yu-xin-c.
 - Browser: keep a profile `cdpPort` when its `cdpUrl` omits a port, while still letting explicitly written URL ports win. (#82166) Thanks @Marvae.
 - Agents/image generation: allow distinct `image_generate` prompts to start separate session-backed background tasks while same-prompt retries still return the active task status. (#83614) Thanks @Elarwei001.
+- Gateway/WebChat: honor configured `channels.webchat.textChunkLimit` and `chunkMode` overrides when chunking WebChat replies. (#83713)
 - Control UI: stop the chat reading indicator from sticking after an assistant response finishes. (#83515) Thanks @njuboy11.
 - Skills: reject empty or whitespace-only skill names and descriptions during quick validation. (#27061)
 - Sessions: skip trailing custom transcript entries when checking tail assistant replies so embedded CLI gap-fill does not duplicate canonical assistant output. (#83635) Thanks @yaoyi1222.
diff --git a/src/auto-reply/chunk.test.ts b/src/auto-reply/chunk.test.ts
@@ -330,6 +330,26 @@ describe("resolveTextChunkLimit", () => {
       options: undefined,
       expected: 4000,
     },
+    {
+      name: "honors webchat textChunkLimit override from config",
+      cfg: {
+        channels: {
+          webchat: { textChunkLimit: 16000 },
+        },
+      },
+      provider: "webchat" as const,
+      accountId: undefined,
+      options: undefined,
+      expected: 16000,
+    },
+    {
+      name: "falls back to default when webchat has no override",
+      cfg: { channels: {} },
+      provider: "webchat" as const,
+      accountId: undefined,
+      options: undefined,
+      expected: 4000,
+    },
   ] as const)("$name", ({ cfg, provider, accountId, options, expected }) => {
     expect(resolveTextChunkLimit(cfg as never, provider, accountId, options)).toBe(expected);
   });
@@ -584,6 +604,12 @@ describe("resolveChunkMode", () => {
     { cfg: providerCfg, provider: "discord", accountId: undefined, expected: "length" },
     { cfg: accountCfg, provider: "slack", accountId: "primary", expected: "newline" },
     { cfg: accountCfg, provider: "slack", accountId: "other", expected: "length" },
+    {
+      cfg: { channels: { webchat: { chunkMode: "newline" as const } } },
+      provider: "webchat",
+      accountId: undefined,
+      expected: "newline",
+    },
   ] as const)(
     "resolves default/provider/account/internal chunk mode for $provider $accountId",
     ({ cfg, provider, accountId, expected }) => {
diff --git a/src/auto-reply/chunk.ts b/src/auto-reply/chunk.ts
@@ -9,7 +9,6 @@ import { resolveChannelStreamingChunkMode } from "../plugin-sdk/channel-streamin
 import { resolveAccountEntry } from "../routing/account-lookup.js";
 import { normalizeAccountId } from "../routing/session-key.js";
 import { chunkTextByBreakResolver } from "../shared/text-chunking.js";
-import { INTERNAL_MESSAGE_CHANNEL } from "../utils/message-channel.js";
 
 export type TextChunkProvider = ChannelId;
 
@@ -64,7 +63,7 @@ export function resolveTextChunkLimit(
       ? opts.fallbackLimit
       : DEFAULT_CHUNK_LIMIT;
   const providerOverride = (() => {
-    if (!provider || provider === INTERNAL_MESSAGE_CHANNEL) {
+    if (!provider) {
       return undefined;
     }
     const channelsConfig = cfg?.channels as Record<string, unknown> | undefined;
@@ -102,7 +101,7 @@ export function resolveChunkMode(
   provider?: TextChunkProvider,
   accountId?: string | null,
 ): ChunkMode {
-  if (!provider || provider === INTERNAL_MESSAGE_CHANNEL) {
+  if (!provider) {
     return DEFAULT_CHUNK_MODE;
   }
   const channelsConfig = cfg?.channels as Record<string, unknown> | undefined;
