[Bug]: Trace does not record temperature parameter in span attributes

[TYTaO]

Describe the bug

When using AgentScope-Java's tracing feature with TelemetryTracer, the gen_ai.request.temperature attribute is not being recorded in the trace spans, even when the model is configured with temperature or when users expect temperature to be tracked.

According to the OpenTelemetry GenAI Semantic Conventions, the gen_ai.request.temperature attribute should be captured for LLM requests.

Expected attributes that are missing:

• gen_ai.request.temperature - The temperature parameter for text generation
• agentscope.function.input.temperature (if applicable in the function input JSON)

Root Cause Analysis

After investigating the code, the root cause has been identified:

1. ReActAgent.buildGenerateOptions() does not include temperature

In ReActAgent.java:787-794:

@Override
protected GenerateOptions buildGenerateOptions() {
    GenerateOptions.Builder builder = GenerateOptions.builder();
    if (modelExecutionConfig != null) {
        builder.executionConfig(modelExecutionConfig);
    }
    return builder.build();  // ❌ No temperature, topP, maxTokens, etc.
}

The buildGenerateOptions() method only sets executionConfig (timeout/retry settings), but does NOT set any generation parameters like temperature, topP, maxTokens, etc.

2. ReActAgent.Builder lacks generateOptions configuration

In ReActAgent.Builder, there is no generateOptions(GenerateOptions) method to configure generation parameters at the agent level.

Available configurations:

• ✅ modelExecutionConfig(ExecutionConfig) - timeout, retry, backoff
• ❌ generateOptions(GenerateOptions) - MISSING - temperature, topP, maxTokens, etc.

3. Flow of options in reasoning phase

In ReActAgent.reasoning() method:

private Mono<Msg> reasoning(int iter, boolean ignoreMaxIters) {
    // ...
    return checkInterruptedAsync()
            .then(notifyPreReasoningEvent(prepareMessages()))
            .flatMapMany(
                    event -> {
                        GenerateOptions options =
                                event.getEffectiveGenerateOptions() != null
                                        ? event.getEffectiveGenerateOptions()
                                        : buildGenerateOptions();  // ← Returns options WITHOUT temperature
                        return model.stream(
                                        event.getInputMessages(),
                                        toolkit.getToolSchemas(),
                                        options)  // ← Options passed to model.stream()
                                .concatMap(chunk -> checkInterruptedAsync().thenReturn(chunk));
                    })
    // ...
}

The options passed to model.stream() comes from buildGenerateOptions(), which returns a GenerateOptions object with temperature = null.

4. TelemetryTracer correctly checks for temperature

In AttributesExtractors.getLLMRequestAttributes():

static Attributes getLLMRequestAttributes(..., GenerateOptions options) {
    // ...
    if (options != null) {
        internalSet(builder, GEN_AI_REQUEST_TEMPERATURE, options.getTemperature());  // ← null
        // ...
    }
    // ...
}

Since options.getTemperature() returns null, the attribute is not set (due to internalSet skipping null values).

To Reproduce

Steps to reproduce the behavior:

1. Setup TelemetryTracer with Langfuse:

TelemetryTracer tracer = TelemetryTracer.builder()
    .endpoint("https://us.cloud.langfuse.com/api/public/otel/v1/traces")
    .addHeader("Authorization", "Basic " + Base64.getEncoder()
        .encodeToString((publicKey + ":" + secretKey).getBytes()))
    .build();
TracerRegistry.register(tracer);

2. Create an agent (no way to set temperature):

// Note: There is no generateOptions() method in the Builder!
ReActAgent agent = ReActAgent.builder()
    .name("TestAgent")
    .model(chatModel)
    // .generateOptions(GenerateOptions.builder().temperature(0.7).build())  // ❌ This method doesn't exist!
    .build();

agent.call(Msg.userMsg("Hello")).block();

3. Check the trace in Langfuse/Jaeger/etc.:
   • Navigate to the trace viewer
   • Inspect the chat span attributes
   • Observe that gen_ai.request.temperature is not present

Expected behavior

1. ReActAgent.Builder should have a generateOptions(GenerateOptions) method
2. ReActAgent.buildGenerateOptions() should return the configured generation options
3. The trace span for model calls should include:

gen_ai.request.temperature: 0.7
gen_ai.request.top_p: 0.9
gen_ai.request.max_tokens: 1000

Suggested Fix

Option 1: Add generateOptions to ReActAgent.Builder

// In ReActAgent.Builder
private GenerateOptions generateOptions;

public Builder generateOptions(GenerateOptions generateOptions) {
    this.generateOptions = generateOptions;
    return this;
}

// In ReActAgent
private final GenerateOptions generateOptions;

@Override
protected GenerateOptions buildGenerateOptions() {
    GenerateOptions.Builder builder = GenerateOptions.builder();
    
    // Merge with user-provided generateOptions
    if (generateOptions != null) {
        if (generateOptions.getTemperature() != null) {
            builder.temperature(generateOptions.getTemperature());
        }
        if (generateOptions.getTopP() != null) {
            builder.topP(generateOptions.getTopP());
        }
        if (generateOptions.getMaxTokens() != null) {
            builder.maxTokens(generateOptions.getMaxTokens());
        }
        // ... other options
    }
    
    if (modelExecutionConfig != null) {
        builder.executionConfig(modelExecutionConfig);
    }
    
    return builder.build();
}

Option 2: Use Model's default options

Alternatively, retrieve default options from the Model itself if configured there.

Environment

• AgentScope-Java Version: [e.g. 1.0.8]
• Java Version: 17
• OS: macOS

Additional context

Related code references:

File	Location	Description
ReActAgent.java	buildGenerateOptions()	Returns GenerateOptions without temperature
ReActAgent.java	reasoning()	Where options are built and passed to model
ReActAgent.java	Builder class	Missing generateOptions() method
TelemetryTracer.java	callModel()	Options passed to getLLMRequestAttributes()
AttributesExtractors.java	Line 176	Temperature attribute extraction (skipped when null)
GenAiIncubatingAttributes.java	Attribute key	gen_ai.request.temperature definition

References:

• OpenTelemetry GenAI Semantic Conventions
• Langfuse OpenTelemetry Integration

[TYTaO]

Background

In addition to temperature, various LLM providers support "thinking mode" or "reasoning mode" parameters that control whether the model exposes its reasoning process. These parameters are equally important for observability and debugging, but are currently NOT being recorded in trace spans.

Affected Parameters by Provider

Provider	Model	Parameters	Description
DashScope (Qwen)	Qwen3, etc.	enableThinking, thinkingBudget	Enable/disable thinking mode and set thinking token budget
DeepSeek	DeepSeek-R1, etc.	reasoning_effort	Control reasoning depth ("low", "medium", "high")
Gemini	Gemini 2.5, etc.	thinkingBudget, includeThoughts	Set thinking budget and include thoughts in response
OpenAI	o1, o3, etc.	reasoning_effort, include_reasoning	Control reasoning effort for o-series models

Current State in Code

1. GenerateOptions has fields for these parameters:

   In GenerateOptions.java:44-45:

   private final Integer thinkingBudget;
   private final String reasoningEffort;

2. Model implementations use provider-specific parameters:

   In DashScopeChatModel.java:61:

   private final Boolean enableThinking;

3. But AttributesExtractors does NOT record these parameters:

   In AttributesExtractors.getLLMRequestAttributes():

   if (options != null) {
       internalSet(builder, GEN_AI_REQUEST_TEMPERATURE, options.getTemperature());
       internalSet(builder, GEN_AI_REQUEST_TOP_P, options.getTopP());
       internalSet(builder, GEN_AI_REQUEST_MAX_TOKENS, options.getMaxTokens());
       // ❌ Missing: options.getThinkingBudget()
       // ❌ Missing: options.getReasoningEffort()
   }

Suggested Enhancement

Add the following attribute extractions in AttributesExtractors.getLLMRequestAttributes():

if (options != null) {
    internalSet(builder, GEN_AI_REQUEST_TEMPERATURE, options.getTemperature());
    internalSet(builder, GEN_AI_REQUEST_TOP_P, options.getTopP());
    internalSet(builder, GEN_AI_REQUEST_MAX_TOKENS, options.getMaxTokens());
    
    // Add thinking/reasoning mode parameters
    internalSet(builder, "gen_ai.request.thinking_budget", options.getThinkingBudget());
    internalSet(builder, "gen_ai.request.reasoning_effort", options.getReasoningEffort());
}

Note: Since OpenTelemetry GenAI Semantic Conventions may not yet define standard attribute names for thinking/reasoning parameters, consider using gen_ai.request.thinking_budget and gen_ai.request.reasoning_effort as custom attributes, or propose these to the OpenTelemetry community.