fix: make conversation labels work with Codex (#78450)

Summary:
- The PR changes the shared conversation-label generator to send label instructions as `systemPrompt`, omit `temperature` for Codex simple completions, log error stop reasons, and add focused tests plus a changelog entry.
- Reproducibility: yes. Source reproduction is high-confidence: current main sends the prompt only inside user ... ple transport reads instructions from `context.systemPrompt` and only includes `temperature` when supplied.

Automerge notes:
- PR branch already contained follow-up commit before automerge: docs: note Codex topic label fix

Validation:
- ClawSweeper review passed for head 9380907984.
- Required merge gates passed before the squash merge.

Prepared head SHA: 9380907984
Review: https://github.com/openclaw/openclaw/pull/78450#issuecomment-4387573775

Co-authored-by: Clever <clever@users.noreply.github.com>

CHANGELOG.md

@@ -113,6 +113,7 @@ Docs: https://docs.openclaw.ai
 
 ### Fixes
 
+- Telegram/Codex: generate DM topic labels with Codex-compatible simple-completion requests so auto-created private topics can be renamed instead of staying `New Chat`.
 - Web fetch: bound guarded dispatcher cleanup after request timeouts so timed-out fetches return tool errors instead of leaving Gateway tool lanes active. (#78439) Thanks @obviyus.
 - Gate Slack startup user allowlist resolution [AI]. (#77898) Thanks @pgondhi987.
 - OpenAI/Codex: suppress stale `openai-codex` GPT-5.1/5.2/5.3 model refs that ChatGPT/Codex OAuth accounts now reject, keeping model lists, config validation, and forward-compat resolution on current 5.4/5.5 routes. Fixes #67158. Thanks @drpau.
@@ -174,6 +175,7 @@ Docs: https://docs.openclaw.ai
 - Hooks/session-memory: add collision suffixes to fallback memory filenames so repeated `/new` or `/reset` captures in the same minute do not overwrite the earlier session archive. Thanks @vincentkoc.
 - Agents/config: remove the ambiguous legacy `main` agent dir helper from runtime paths; model, auth, gateway, bundled plugin, and test helpers now resolve default/session agent dirs through `agents.list`/agent-scope helpers while plugin SDK keeps a deprecated compatibility export.
 - CLI/status: show the selected agent runtime/harness in `openclaw status` session rows so terminal status matches the `/status` runtime line. Thanks @vincentkoc.
+
 - CLI/sessions: prune old unreferenced transcript, compaction checkpoint, and trajectory artifacts during normal `sessions cleanup`, so gateway restart or crash orphans do not accumulate indefinitely outside `sessions.json`. Fixes #77608. Thanks @slideshow-dingo.
 - Doctor/Codex: repair legacy `openai-codex/*` routes in primary models, fallbacks, heartbeat/subagent/compaction overrides, hooks, channel overrides, and stale session pins to canonical `openai/*`, selecting `agentRuntime.id: "codex"` only when the Codex plugin is installed, enabled, contributes the `codex` harness, and has usable OAuth; otherwise select `agentRuntime.id: "pi"`. Thanks @vincentkoc.
 - Video generation: wait up to 20 minutes for slow fal/MiniMax queue-backed jobs, stop forwarding unsupported Google Veo generated-audio options, and normalize MiniMax `720P` requests to its supported `768P` resolution with the usual override warning/details instead of failing fallback.

src/auto-reply/reply/conversation-label-generator.test.ts

@@ -2,6 +2,7 @@ import { beforeEach, describe, expect, it, vi } from "vitest";
 
 const completeSimple = vi.hoisted(() => vi.fn());
 const getRuntimeAuthForModel = vi.hoisted(() => vi.fn());
+const logVerbose = vi.hoisted(() => vi.fn());
 const requireApiKey = vi.hoisted(() => vi.fn());
 const resolveDefaultModelForAgent = vi.hoisted(() => vi.fn());
 const resolveModelAsync = vi.hoisted(() => vi.fn());
@@ -18,6 +19,8 @@ vi.mock("@mariozechner/pi-ai", async () => {
 
 vi.mock("../../agents/model-auth.js", () => ({ requireApiKey }));
 
+vi.mock("../../globals.js", () => ({ logVerbose }));
+
 vi.mock("../../agents/model-selection.js", () => ({
   resolveDefaultModelForAgent,
 }));
@@ -40,6 +43,7 @@ describe("generateConversationLabel", () => {
   beforeEach(() => {
     completeSimple.mockReset();
     getRuntimeAuthForModel.mockReset();
+    logVerbose.mockReset();
     requireApiKey.mockReset();
     resolveDefaultModelForAgent.mockReset();
     resolveModelAsync.mockReset();
@@ -88,4 +92,70 @@ describe("generateConversationLabel", () => {
       cfg: {},
     });
   });
+
+  it("passes the label prompt as systemPrompt and the user text as message content", async () => {
+    await generateConversationLabel({
+      userMessage: "Need help with invoices",
+      prompt: "Generate a label",
+      cfg: {},
+    });
+
+    expect(completeSimple).toHaveBeenCalledWith(
+      { provider: "openai" },
+      {
+        systemPrompt: "Generate a label",
+        messages: [
+          {
+            role: "user",
+            content: "Need help with invoices",
+            timestamp: expect.any(Number),
+          },
+        ],
+      },
+      expect.objectContaining({
+        apiKey: "resolved-key",
+        maxTokens: 100,
+        temperature: 0.3,
+        signal: expect.any(AbortSignal),
+      }),
+    );
+  });
+
+  it("omits temperature for Codex Responses simple completions", async () => {
+    resolveDefaultModelForAgent.mockReturnValue({ provider: "openai-codex", model: "gpt-5.5" });
+    resolveModelAsync.mockResolvedValue({
+      model: { provider: "openai-codex", api: "openai-codex-responses" },
+      authStorage: {},
+      modelRegistry: {},
+    });
+
+    await generateConversationLabel({
+      userMessage: "тест создания топика-треда",
+      prompt: "Generate a label",
+      cfg: {},
+    });
+
+    expect(completeSimple.mock.calls[0]?.[2]).toEqual(
+      expect.not.objectContaining({ temperature: expect.anything() }),
+    );
+  });
+
+  it("logs completion errors instead of treating them as empty labels", async () => {
+    completeSimple.mockResolvedValue({
+      content: [],
+      stopReason: "error",
+      errorMessage: "Codex error: Instructions are required",
+    });
+
+    const label = await generateConversationLabel({
+      userMessage: "Need help with invoices",
+      prompt: "Generate a label",
+      cfg: {},
+    });
+
+    expect(label).toBeNull();
+    expect(logVerbose).toHaveBeenCalledWith(
+      "conversation-label-generator: completion failed: Codex error: Instructions are required",
+    );
+  });
 });

src/auto-reply/reply/conversation-label-generator.ts

@@ -23,6 +23,20 @@ function isTextContentBlock(block: { type: string }): block is TextContent {
   return block.type === "text";
 }
 
+function isCodexSimpleCompletionModel(model: { api?: string; provider?: string }): boolean {
+  return model.provider === "openai-codex" || model.api === "openai-codex-responses";
+}
+
+function extractSimpleCompletionError(result: {
+  stopReason?: string;
+  errorMessage?: string;
+}): string | null {
+  if (result.stopReason !== "error") {
+    return null;
+  }
+  return result.errorMessage?.trim() || "unknown error";
+}
+
 export async function generateConversationLabel(
   params: ConversationLabelParams,
 ): Promise<string | null> {
@@ -58,10 +72,11 @@ export async function generateConversationLabel(
     const result = await completeSimple(
       completionModel,
       {
+        systemPrompt: prompt,
         messages: [
           {
             role: "user",
-            content: `${prompt}\n\n${userMessage}`,
+            content: userMessage,
             timestamp: Date.now(),
           },
         ],
@@ -69,10 +84,15 @@ export async function generateConversationLabel(
       {
         apiKey,
         maxTokens: 100,
-        temperature: 0.3,
+        ...(isCodexSimpleCompletionModel(completionModel) ? {} : { temperature: 0.3 }),
         signal: controller.signal,
       },
     );
+    const errorMessage = extractSimpleCompletionError(result);
+    if (errorMessage) {
+      logVerbose(`conversation-label-generator: completion failed: ${errorMessage}`);
+      return null;
+    }
 
     const text = result.content
       .filter(isTextContentBlock)