fix(openai): normalize prompt overlay personality config

CHANGELOG.md

@@ -41,6 +41,7 @@ Docs: https://docs.openclaw.ai
 - Providers/Google: recognize Gemma model ids in native Google forward-compat resolution, keep the requested provider when cloning fallback templates, and force Gemma reasoning off so Gemma 4 routes stop failing through the Google catalog fallback. (#61507) Thanks @eyjohn.
 - Providers/Anthropic: skip `service_tier` injection for OAuth-authenticated stream wrapper requests so Claude OAuth requests stop failing with HTTP 401. (#60356) thanks @openperf.
 - Providers/OpenAI: keep WebSocket text buffered until a real assistant phase arrives, even when text deltas land before a phaseless `output_item.added` announcement. (#61954) Thanks @100yenadmin.
+- Providers/OpenAI: accept case-insensitive `plugins.entries.openai.config.personality` values, keep unknown overrides on the friendly overlay path, and add `on` as an alias for `friendly`. Thanks @vincentkoc.
 - Discord/thread titles: stop forcing a hardcoded temperature for generated auto-thread names so Codex-backed thread title generation works on `openai-codex/*` models again. (#59525)
 - Agents/message tool: add a `read` plus `threadId` discoverability hint when the configured channel actions support threaded message reads.
 - Agents/context overflow: combine oversized and aggregate tool-result recovery in one repair pass, and restore a total-context overflow backstop during tool loops so recoverable sessions retry instead of failing early. (#61651) Thanks @Takhoffman.
@@ -56,6 +57,7 @@ Docs: https://docs.openclaw.ai
 - Docs/i18n: relocalize final localized-page links after translation so generated locale pages stop keeping stale English-root links when targets appear later in the same run. (#61796) thanks @hxy91819.
 - Docs/i18n: remove the zh-CN homepage redirect override so Mintlify can resolve the localized Chinese homepage without self-redirecting `/zh-CN/index`.
 - Tools/web_fetch and web_search: fix `TypeError: fetch failed` caused by undici 8.0 enabling HTTP/2 by default; pinned SSRF-guard dispatchers now explicitly set `allowH2: false` to restore HTTP/1.1 behavior and keep the custom DNS-pinning lookup compatible. (#61738, #61777) Thanks @zozo123.
+
 ## 2026.4.5
 
 ### Breaking

docs/providers/openai.md

@@ -28,6 +28,7 @@ Config key:
 Allowed values:
 
 - `"friendly"`: default; enable the OpenAI-specific overlay.
+- `"on"`: alias for `"friendly"`.
 - `"off"`: disable the overlay and use the base OpenClaw prompt only.
 
 Scope:
@@ -77,6 +78,9 @@ You can also set it directly with the config CLI:
 openclaw config set plugins.entries.openai.config.personality off
 ```
 
+OpenClaw normalizes this setting case-insensitively at runtime, so values like
+`"Off"` still disable the friendly overlay.
+
 ## Option A: OpenAI API key (OpenAI Platform)
 
 **Best for:** direct API access and usage-based billing.

extensions/openai/index.test.ts

@@ -387,6 +387,32 @@ describe("openai plugin", () => {
     });
   });
 
+  it("treats mixed-case off values as disabling the friendly prompt overlay", async () => {
+    const { providers } = await registerOpenAIPluginWithHook({
+      pluginConfig: { personality: "Off" },
+    });
+
+    const openaiProvider = requireRegisteredProvider(providers, "openai");
+    expect(
+      openaiProvider.resolveSystemPromptContribution?.({
+        config: undefined,
+        agentDir: undefined,
+        workspaceDir: undefined,
+        provider: "openai",
+        modelId: "gpt-5.4",
+        promptMode: "full",
+        runtimeChannel: undefined,
+        runtimeCapabilities: undefined,
+        agentId: undefined,
+      }),
+    ).toEqual({
+      stablePrefix: OPENAI_GPT5_OUTPUT_CONTRACT,
+      sectionOverrides: {
+        execution_bias: OPENAI_GPT5_EXECUTION_BIAS,
+      },
+    });
+  });
+
   it("supports explicitly configuring the friendly prompt overlay", async () => {
     const { on, providers } = await registerOpenAIPluginWithHook({
       pluginConfig: { personality: "friendly" },
@@ -414,4 +440,31 @@ describe("openai plugin", () => {
       },
     });
   });
+
+  it("treats on as an alias for the friendly prompt overlay", async () => {
+    const { providers } = await registerOpenAIPluginWithHook({
+      pluginConfig: { personality: "on" },
+    });
+
+    const openaiProvider = requireRegisteredProvider(providers, "openai");
+    expect(
+      openaiProvider.resolveSystemPromptContribution?.({
+        config: undefined,
+        agentDir: undefined,
+        workspaceDir: undefined,
+        provider: "openai",
+        modelId: "gpt-5.4",
+        promptMode: "full",
+        runtimeChannel: undefined,
+        runtimeCapabilities: undefined,
+        agentId: undefined,
+      }),
+    ).toEqual({
+      stablePrefix: OPENAI_GPT5_OUTPUT_CONTRACT,
+      sectionOverrides: {
+        interaction_style: OPENAI_FRIENDLY_PROMPT_OVERLAY,
+        execution_bias: OPENAI_GPT5_EXECUTION_BIAS,
+      },
+    });
+  });
 });

extensions/openai/openclaw.plugin.json

@@ -49,9 +49,9 @@
     "properties": {
       "personality": {
         "type": "string",
-        "enum": ["friendly", "off"],
+        "enum": ["friendly", "on", "off"],
         "default": "friendly",
-        "description": "Controls the default OpenAI-specific personality used for OpenAI and OpenAI Codex runs."
+        "description": "Controls the default OpenAI-specific personality used for OpenAI and OpenAI Codex runs. `friendly` and `on` enable the overlay; `off` disables it."
       }
     }
   }

extensions/openai/prompt-overlay.ts

@@ -54,7 +54,11 @@ export type OpenAIPromptOverlayMode = "friendly" | "off";
 export function resolveOpenAIPromptOverlayMode(
   pluginConfig?: Record<string, unknown>,
 ): OpenAIPromptOverlayMode {
-  return pluginConfig?.personality === "off" ? "off" : "friendly";
+  const normalized =
+    typeof pluginConfig?.personality === "string"
+      ? pluginConfig.personality.trim().toLowerCase()
+      : "";
+  return normalized === "off" ? "off" : "friendly";
 }
 
 export function shouldApplyOpenAIPromptOverlay(params: {