fix: show fast mode in status

CHANGELOG.md

@@ -39,6 +39,7 @@ Docs: https://docs.openclaw.ai
 
 ### Fixes
 
+- Status: show `Fast` in `/status` when fast mode is enabled, including config/default-derived fast mode, and omit it when disabled.
 - Models/auth: merge provider-owned default-model additions from `openclaw models auth login` instead of replacing `agents.defaults.models`, so re-authenticating an OAuth provider such as OpenAI Codex no longer wipes other providers' aliases and per-model params. Migrations that must rename keys (Anthropic -> Claude CLI) opt in with `replaceDefaultModels`. Fixes #69414. (#70435) Thanks @neeravmakwana.
 - Media understanding/audio: prefer configured or key-backed STT providers before auto-detected local Whisper CLIs, so installed local transcription tools no longer shadow API providers such as Groq/OpenAI in `tools.media.audio` auto mode. Fixes #68727.
 - Providers/OpenAI: lock the auth picker wording for OpenAI API key, Codex browser login, and Codex device pairing so the setup choices no longer imply a mixed Codex/API-key auth path. (#67848) Thanks @tmlxrd.

docs/tools/thinking.md

@@ -68,6 +68,7 @@ title: "Thinking Levels"
 - For direct public `anthropic/*` requests, including OAuth-authenticated traffic sent to `api.anthropic.com`, fast mode maps to Anthropic service tiers: `/fast on` sets `service_tier=auto`, `/fast off` sets `service_tier=standard_only`.
 - For `minimax/*` on the Anthropic-compatible path, `/fast on` (or `params.fastMode: true`) rewrites `MiniMax-M2.7` to `MiniMax-M2.7-highspeed`.
 - Explicit Anthropic `serviceTier` / `service_tier` model params override the fast-mode default when both are set. OpenClaw still skips Anthropic service-tier injection for non-Anthropic proxy base URLs.
+- `/status` shows `Fast` only when fast mode is enabled.
 
 ## Verbose directives (/verbose or /v)
 

src/auto-reply/reply/commands-info.test.ts

@@ -268,6 +268,23 @@ describe("info command handlers", () => {
     );
   });
 
+  it("forwards resolved fast mode to /status", async () => {
+    const params = buildInfoParams("/status", {
+      commands: { text: true },
+      channels: { whatsapp: { allowFrom: ["*"] } },
+    } as OpenClawConfig);
+    params.resolvedFastMode = true;
+
+    const statusResult = await handleStatusCommand(params, true);
+
+    expect(statusResult?.shouldContinue).toBe(false);
+    expect(vi.mocked(buildStatusReply)).toHaveBeenCalledWith(
+      expect.objectContaining({
+        resolvedFastMode: true,
+      }),
+    );
+  });
+
   it("uses the canonical target session agent when listing /commands", async () => {
     const { handleCommandsListCommand } = await import("./commands-info.js");
     const params = buildInfoParams("/commands", {

src/auto-reply/reply/commands-info.ts

@@ -204,6 +204,7 @@ export const handleStatusCommand: CommandHandler = async (params, allowTextComma
     model: params.model,
     contextTokens: params.contextTokens,
     resolvedThinkLevel: params.resolvedThinkLevel,
+    resolvedFastMode: params.resolvedFastMode,
     resolvedVerboseLevel: params.resolvedVerboseLevel,
     resolvedReasoningLevel: params.resolvedReasoningLevel,
     resolvedElevatedLevel: params.resolvedElevatedLevel,

src/auto-reply/reply/commands-types.ts

@@ -53,6 +53,7 @@ export type HandleCommandsParams = {
   opts?: GetReplyOptions;
   defaultGroupActivation: () => "always" | "mention";
   resolvedThinkLevel?: ThinkLevel;
+  resolvedFastMode?: boolean;
   resolvedVerboseLevel: VerboseLevel;
   resolvedReasoningLevel: ReasoningLevel;
   resolvedElevatedLevel?: ElevatedLevel;

src/auto-reply/status.test.ts

@@ -276,7 +276,24 @@ describe("buildStatusMessage", () => {
       queue: { mode: "collect", depth: 0 },
     });
 
-    expect(normalizeTestText(text)).toContain("Fast: on");
+    expect(normalizeTestText(text)).toContain("Fast");
+  });
+
+  it("hides fast mode when disabled", () => {
+    const text = buildStatusMessage({
+      agent: {
+        model: "anthropic/claude-opus-4-6",
+      },
+      sessionEntry: {
+        sessionId: "fast-off",
+        updatedAt: 0,
+        fastMode: false,
+      },
+      sessionKey: "agent:main:main",
+      queue: { mode: "collect", depth: 0 },
+    });
+
+    expect(normalizeTestText(text)).not.toContain("Fast");
   });
 
   it("shows configured text verbosity for the active model", () => {

src/status/status-message.test.ts

@@ -0,0 +1,29 @@
+import { describe, expect, it } from "vitest";
+import { normalizeTestText } from "../../test/helpers/normalize-text.js";
+import { buildStatusMessage } from "./status-message.js";
+
+const buildFastStatus = (model: string, fastMode: boolean) =>
+  normalizeTestText(
+    buildStatusMessage({
+      modelAuth: "api-key",
+      activeModelAuth: "api-key",
+      agent: { model },
+      sessionEntry: {
+        sessionId: "fast-status",
+        updatedAt: 0,
+        fastMode,
+      },
+      sessionKey: "agent:main:main",
+      queue: { mode: "collect", depth: 0 },
+    }),
+  );
+
+describe("buildStatusMessage fast mode labels", () => {
+  it("shows fast mode when enabled", () => {
+    expect(buildFastStatus("openai/gpt-5.4", true)).toContain("Fast");
+  });
+
+  it("hides fast mode when disabled", () => {
+    expect(buildFastStatus("anthropic/claude-opus-4-6", false)).not.toContain("Fast");
+  });
+});

src/status/status-message.ts

@@ -237,6 +237,13 @@ const formatQueueDetails = (queue?: QueueStatus) => {
   return detailParts.length ? ` (${detailParts.join(" · ")})` : "";
 };
 
+const formatFastModeLabel = (enabled: boolean) => {
+  if (!enabled) {
+    return null;
+  }
+  return "Fast";
+};
+
 const readUsageFromSessionLog = (
   sessionId?: string,
   sessionEntry?: SessionEntry,
@@ -705,7 +712,7 @@ export function buildStatusMessage(args: StatusArgs): string {
   const optionParts = [
     `Runtime: ${runtime.label}`,
     `Think: ${thinkLevel}`,
-    fastMode ? "Fast: on" : null,
+    formatFastModeLabel(fastMode),
     textVerbosity ? `Text: ${textVerbosity}` : null,
     verboseLabel,
     traceLabel,