fix(models): sanitize name field in OpenAIMessageConverter to satisfy…

[hhbin2026]

… (#2345 )

AgentScope-Java Version

[The version of AgentScope-Java you are working on, e.g. 2.0.1, check your pom.xml dependency version or run mvn dependency:tree | grep agentscope-parent:pom(only mac/linux)]

Description

Example:

 /** Logical name used to register and resolve the model via {@link ModelRegistry}. */
    private static final String MODEL_ALIAS = "my-gpt5";

    public static void main(String[] args) throws Exception {
        // ----------------------------------------------------------------
        // 1. Resolve API key and optional custom base URL
        //    Override via env vars so the binary contains no secrets.
        // ----------------------------------------------------------------
        String apiKey = System.getenv("OPENAI_API_KEY");
        
        // Custom base URL for compatible providers (leave null to use OpenAI's default).
        // Example: "https://api.ciyuanshen.top/v1"
        String baseUrl = System.getenv("OPENAI_BASE_URL");

        // ----------------------------------------------------------------
        // 2. Build OpenAIChatModel
        //    Use GenerateOptions to apply call-level defaults (temperature,
        //    maxTokens, etc.) without changing the model's core configuration.
        // ----------------------------------------------------------------
        OpenAIChatModel.Builder modelBuilder =
                OpenAIChatModel.builder()
                        .apiKey(apiKey)
                        .modelName("gpt-5.4")
                        .stream(true)
                        .generateOptions(
                                GenerateOptions.builder()
                                        .temperature(0.2)
                                        .maxCompletionTokens(2048)
                                        .build());

        if (baseUrl != null && !baseUrl.isBlank()) {
            modelBuilder.baseUrl(baseUrl);
        }

        // ----------------------------------------------------------------
        // 3. Register the model under a logical alias so HarnessAgent (and
        //    any other component) can resolve it by name via ModelRegistry.
        // ----------------------------------------------------------------
        ModelRegistry.register(MODEL_ALIAS, modelBuilder.build());

        // ----------------------------------------------------------------
        // 4. Prepare workspace directory
        // ----------------------------------------------------------------
        Path workspace = Paths.get(".agentscope/openai-chat");
        initWorkspaceIfAbsent(workspace);

        // ----------------------------------------------------------------
        // 5. Build HarnessAgent — references the model by its registered name
        // ----------------------------------------------------------------
        HarnessAgent agent =
                HarnessAgent.builder()
                        .name("demo")
                        .sysPrompt(
                                "You are a helpful AI assistant. Be friendly, accurate and"
                                        + " concise.")
                        .model(MODEL_ALIAS)
                        .workspace(workspace)
                        .stateStore(new InMemoryAgentStateStore())
                        .build();

        // ----------------------------------------------------------------
        // 6. Single RuntimeContext for the entire session so multi-turn
        //    history is preserved across invocations.
        // ----------------------------------------------------------------
        RuntimeContext ctx =
                RuntimeContext.builder()
                        .sessionId("openai-chat-session")
                        .userId("user-1")
                        .build();

        // ----------------------------------------------------------------
        // 7. Interactive chat loop with streaming output
        // ----------------------------------------------------------------
        System.out.println("\n" + "=".repeat(60));
        System.out.println("OpenAI Chat Example  (model: gpt-5.5)");
        System.out.println("=".repeat(60));
        System.out.println("Type your message and press Enter. Type 'exit' to quit.\n");

        BufferedReader reader = new BufferedReader(new InputStreamReader(System.in));

        while (true) {
            System.out.print("You: ");
            String input = reader.readLine();

            if (input == null || input.trim().equalsIgnoreCase("exit")) {
                System.out.println("\nGoodbye!");
                break;
            }
            if (input.isBlank()) {
                continue;
            }

            System.out.print("\nAssistant: ");

            agent.streamEvents(new UserMessage("test name",input.trim()), ctx)
                    .doOnNext(
                            event -> {
                                if (event instanceof TextBlockDeltaEvent e) {
                                    System.out.print(e.getDelta());
                                }
                            })
                    .blockLast();
            System.out.println("\n");
        }
    }

    private static void initWorkspaceIfAbsent(Path workspace) throws Exception {
        Files.createDirectories(workspace);
        Path agentsMd = workspace.resolve("AGENTS.md");
        if (Files.exists(agentsMd)) return;
        Files.writeString(
                agentsMd,
                """
                # OpenAI Chat Assistant

                You are a general-purpose assistant powered by GPT.

                ## Behavior Guidelines
                - Answer questions clearly and concisely
                - If you are unsure, say so rather than guessing
                - Use bullet lists for multi-step answers when helpful
                """);
    }

Checklist

Please check the following items before code is ready to be reviewed.

• [X ] Code has been formatted with mvn spotless:apply
• All tests are passing (mvn test)
• Javadoc comments are complete and follow project conventions
• Related documentation has been updated (e.g. links, examples, etc.)
• Code is ready for review

[CLAassistant]

All committers have signed the CLA.

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.

📢 Thoughts on this report? Let us know!