fix: sanitize thinking blocks for GitHub Copilot Claude models (openclaw#19459) thanks @jackheuberger

Verified:
- pnpm build
- pnpm check
- pnpm test:macmini

Co-authored-by: jackheuberger <12731288+jackheuberger@users.noreply.github.com>
Co-authored-by: Tak Hoffman <781889+Takhoffman@users.noreply.github.com>

src/agents/pi-embedded-runner.sanitize-session-history.test.ts

@@ -284,4 +284,172 @@ describe("sanitizeSessionHistory", () => {
       ),
     ).toBe(false);
   });
+
+  it("drops assistant thinking blocks for github-copilot models", async () => {
+    vi.mocked(helpers.isGoogleModelApi).mockReturnValue(false);
+
+    const messages = [
+      { role: "user", content: "hello" },
+      {
+        role: "assistant",
+        content: [
+          {
+            type: "thinking",
+            thinking: "internal",
+            thinkingSignature: "reasoning_text",
+          },
+          { type: "text", text: "hi" },
+        ],
+      },
+    ] as unknown as AgentMessage[];
+
+    const result = await sanitizeSessionHistory({
+      messages,
+      modelApi: "openai-completions",
+      provider: "github-copilot",
+      modelId: "claude-opus-4.6",
+      sessionManager: makeMockSessionManager(),
+      sessionId: TEST_SESSION_ID,
+    });
+
+    expect(result[1]?.role).toBe("assistant");
+    const assistant = result[1] as Extract<AgentMessage, { role: "assistant" }>;
+    expect(assistant.content).toEqual([{ type: "text", text: "hi" }]);
+  });
+
+  it("preserves assistant turn when all content is thinking blocks (github-copilot)", async () => {
+    vi.mocked(helpers.isGoogleModelApi).mockReturnValue(false);
+
+    const messages = [
+      { role: "user", content: "hello" },
+      {
+        role: "assistant",
+        content: [
+          {
+            type: "thinking",
+            thinking: "some reasoning",
+            thinkingSignature: "reasoning_text",
+          },
+        ],
+      },
+      { role: "user", content: "follow up" },
+    ] as unknown as AgentMessage[];
+
+    const result = await sanitizeSessionHistory({
+      messages,
+      modelApi: "openai-completions",
+      provider: "github-copilot",
+      modelId: "claude-opus-4.6",
+      sessionManager: makeMockSessionManager(),
+      sessionId: TEST_SESSION_ID,
+    });
+
+    // Assistant turn should be preserved (not dropped) to maintain turn alternation
+    expect(result).toHaveLength(3);
+    expect(result[1]?.role).toBe("assistant");
+    const assistant = result[1] as Extract<AgentMessage, { role: "assistant" }>;
+    expect(assistant.content).toEqual([{ type: "text", text: "" }]);
+  });
+
+  it("preserves tool_use blocks when dropping thinking blocks (github-copilot)", async () => {
+    vi.mocked(helpers.isGoogleModelApi).mockReturnValue(false);
+
+    const messages = [
+      { role: "user", content: "read a file" },
+      {
+        role: "assistant",
+        content: [
+          {
+            type: "thinking",
+            thinking: "I should use the read tool",
+            thinkingSignature: "reasoning_text",
+          },
+          { type: "toolCall", id: "tool_123", name: "read", arguments: { path: "/tmp/test" } },
+          { type: "text", text: "Let me read that file." },
+        ],
+      },
+    ] as unknown as AgentMessage[];
+
+    const result = await sanitizeSessionHistory({
+      messages,
+      modelApi: "openai-completions",
+      provider: "github-copilot",
+      modelId: "claude-opus-4.6",
+      sessionManager: makeMockSessionManager(),
+      sessionId: TEST_SESSION_ID,
+    });
+
+    expect(result[1]?.role).toBe("assistant");
+    const assistant = result[1] as Extract<AgentMessage, { role: "assistant" }>;
+    const types = assistant.content.map((b: { type: string }) => b.type);
+    expect(types).toContain("toolCall");
+    expect(types).toContain("text");
+    expect(types).not.toContain("thinking");
+  });
+
+  it("does not drop thinking blocks for non-copilot providers", async () => {
+    vi.mocked(helpers.isGoogleModelApi).mockReturnValue(false);
+
+    const messages = [
+      { role: "user", content: "hello" },
+      {
+        role: "assistant",
+        content: [
+          {
+            type: "thinking",
+            thinking: "internal",
+            thinkingSignature: "some_sig",
+          },
+          { type: "text", text: "hi" },
+        ],
+      },
+    ] as unknown as AgentMessage[];
+
+    const result = await sanitizeSessionHistory({
+      messages,
+      modelApi: "anthropic-messages",
+      provider: "anthropic",
+      modelId: "claude-opus-4-6",
+      sessionManager: makeMockSessionManager(),
+      sessionId: TEST_SESSION_ID,
+    });
+
+    expect(result[1]?.role).toBe("assistant");
+    const assistant = result[1] as Extract<AgentMessage, { role: "assistant" }>;
+    const types = assistant.content.map((b: { type: string }) => b.type);
+    expect(types).toContain("thinking");
+  });
+
+  it("does not drop thinking blocks for non-claude copilot models", async () => {
+    vi.mocked(helpers.isGoogleModelApi).mockReturnValue(false);
+
+    const messages = [
+      { role: "user", content: "hello" },
+      {
+        role: "assistant",
+        content: [
+          {
+            type: "thinking",
+            thinking: "internal",
+            thinkingSignature: "some_sig",
+          },
+          { type: "text", text: "hi" },
+        ],
+      },
+    ] as unknown as AgentMessage[];
+
+    const result = await sanitizeSessionHistory({
+      messages,
+      modelApi: "openai-completions",
+      provider: "github-copilot",
+      modelId: "gpt-5.2",
+      sessionManager: makeMockSessionManager(),
+      sessionId: TEST_SESSION_ID,
+    });
+
+    expect(result[1]?.role).toBe("assistant");
+    const assistant = result[1] as Extract<AgentMessage, { role: "assistant" }>;
+    const types = assistant.content.map((b: { type: string }) => b.type);
+    expect(types).toContain("thinking");
+  });
 });