wehub-resource-sync
272 lines
8.2 KiB
Python
272 lines
8.2 KiB
Python
from opentelemetry.sdk.trace import ReadableSpan
|
|
from opentelemetry.trace import SpanContext, TraceFlags
|
|
from opentelemetry.trace.status import Status, StatusCode
|
|
|
|
# Create a simple span context
|
|
span_context = SpanContext(
|
|
trace_id=1, # Simple trace ID
|
|
span_id=1, # Simple span ID
|
|
is_remote=False,
|
|
trace_flags=TraceFlags(0x01), # Sampled flag
|
|
)
|
|
|
|
# Create the ReadableSpan with one attribute
|
|
readable_span = ReadableSpan(
|
|
name="test_span",
|
|
context=span_context,
|
|
attributes={
|
|
"agent_name": "test_agent",
|
|
"model_name": "gpt-4",
|
|
"logfire.msg": "test_agent run",
|
|
"confident.span.name": "test_agent",
|
|
"confident.span.type": "agent",
|
|
"logfire.json_schema": '{"type": "object", "properties": {"pydantic_ai.all_messages": {"type": "array"}, "gen_ai.system_instructions": {"type": "array"}, "final_result": {"type": "object"}}}',
|
|
"confident.trace.name": "test_trace_name",
|
|
"confident.trace.tags": '["test_tag", "source:test"]',
|
|
"confident.span.prompt": '{"alias": "test_agent", "version": "00.00.01"}',
|
|
"confident.trace.metadata": '{"prompt_version": "00.00.01"}',
|
|
"pydantic_ai.all_messages": """[
|
|
{
|
|
"role": "user",
|
|
"parts": [
|
|
{
|
|
"type": "text",
|
|
"content": "What should I do next?"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"parts": [
|
|
{
|
|
"type": "thinking",
|
|
"content": "Test thinking part 1"
|
|
},
|
|
{
|
|
"type": "thinking",
|
|
"content": "Test thinking part 2"
|
|
},
|
|
{
|
|
"type": "tool_call",
|
|
"id": "call_test123",
|
|
"name": "test_tool",
|
|
"arguments": "{\\"query\\": \\"test query\\"}"
|
|
}
|
|
],
|
|
"finish_reason": "stop"
|
|
},
|
|
{
|
|
"role": "user",
|
|
"parts": [
|
|
{
|
|
"type": "tool_call_response",
|
|
"id": "call_test123",
|
|
"name": "test_tool",
|
|
"result": "Test tool result"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"parts": [
|
|
{
|
|
"type": "thinking",
|
|
"content": "Test final thinking"
|
|
},
|
|
{
|
|
"type": "text",
|
|
"content": "Final response text"
|
|
}
|
|
],
|
|
"finish_reason": "stop"
|
|
}
|
|
]""",
|
|
"confident.trace.thread_id": "test_thread_id",
|
|
"gen_ai.usage.input_tokens": 1000,
|
|
"gen_ai.system_instructions": '[{"type": "text", "content": "You are a test assistant. Follow these instructions: 1. Be concise 2. Use tools when needed 3. Provide clear responses"}]',
|
|
"gen_ai.usage.output_tokens": 500,
|
|
"confident.trace.environment": "development",
|
|
"gen_ai.usage.details.reasoning_tokens": 300,
|
|
"gen_ai.operation.name": "chat",
|
|
"model_request_parameters": '{"temperature": 0.7, "max_tokens": 2048, "top_p": 0.9, "frequency_penalty": 0.5, "presence_penalty": 0.2}',
|
|
}, # Single attribute
|
|
status=Status(StatusCode.OK),
|
|
start_time=1000000000, # nanoseconds since epoch
|
|
end_time=1000001000, # nanoseconds since epoch
|
|
)
|
|
|
|
list_of_readable_spans = [readable_span]
|
|
|
|
llm_readable_span = ReadableSpan(
|
|
name="test_span",
|
|
context=span_context,
|
|
attributes={
|
|
"model_name": "gpt-4",
|
|
"logfire.msg": "test_agent run",
|
|
"confident.span.name": "test_agent",
|
|
"logfire.json_schema": '{"type": "object", "properties": {"pydantic_ai.all_messages": {"type": "array"}, "gen_ai.system_instructions": {"type": "array"}, "final_result": {"type": "object"}}}',
|
|
"confident.trace.name": "test_trace_name",
|
|
"confident.trace.tags": '["test_tag", "source:test"]',
|
|
"confident.span.prompt": '{"alias": "test_agent", "version": "00.00.01"}',
|
|
"confident.trace.metadata": '{"prompt_version": "00.00.01"}',
|
|
"pydantic_ai.all_messages": """[
|
|
{
|
|
"role": "user",
|
|
"parts": [
|
|
{
|
|
"type": "text",
|
|
"content": "What should I do next?"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"parts": [
|
|
{
|
|
"type": "thinking",
|
|
"content": "Test thinking part 1"
|
|
},
|
|
{
|
|
"type": "thinking",
|
|
"content": "Test thinking part 2"
|
|
},
|
|
{
|
|
"type": "tool_call",
|
|
"id": "call_test123",
|
|
"name": "test_tool",
|
|
"arguments": "{\\"query\\": \\"test query\\"}"
|
|
}
|
|
],
|
|
"finish_reason": "stop"
|
|
},
|
|
{
|
|
"role": "user",
|
|
"parts": [
|
|
{
|
|
"type": "tool_call_response",
|
|
"id": "call_test123",
|
|
"name": "test_tool",
|
|
"result": "Test tool result"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"parts": [
|
|
{
|
|
"type": "thinking",
|
|
"content": "Test final thinking"
|
|
},
|
|
{
|
|
"type": "text",
|
|
"content": "Final response text"
|
|
}
|
|
],
|
|
"finish_reason": "stop"
|
|
}
|
|
]""",
|
|
"confident.trace.thread_id": "test_thread_id",
|
|
"gen_ai.usage.input_tokens": 1000,
|
|
"gen_ai.system_instructions": '[{"type": "text", "content": "You are a test assistant. Follow these instructions: 1. Be concise 2. Use tools when needed 3. Provide clear responses"}]',
|
|
"gen_ai.usage.output_tokens": 500,
|
|
"confident.trace.environment": "development",
|
|
"gen_ai.usage.details.reasoning_tokens": 300,
|
|
"gen_ai.operation.name": "chat",
|
|
"model_request_parameters": '{"temperature": 0.7, "max_tokens": 2048, "top_p": 0.9, "frequency_penalty": 0.5, "presence_penalty": 0.2}',
|
|
}, # Single attribute
|
|
status=Status(StatusCode.OK),
|
|
start_time=1000000000, # nanoseconds since epoch
|
|
end_time=1000001000, # nanoseconds since epoch
|
|
)
|
|
|
|
llm_span_list = [llm_readable_span]
|
|
|
|
# Create a multi-turn span context
|
|
multi_turn_span_context = SpanContext(
|
|
trace_id=3,
|
|
span_id=3,
|
|
is_remote=False,
|
|
trace_flags=TraceFlags(0x01),
|
|
)
|
|
|
|
# Create the multi-turn readable span
|
|
multi_turn_readable_span = ReadableSpan(
|
|
name="multi_turn_span",
|
|
context=multi_turn_span_context,
|
|
attributes={
|
|
"agent_name": "test_agent",
|
|
"model_name": "gpt-4",
|
|
"confident.span.name": "test_agent",
|
|
"confident.span.type": "agent",
|
|
"confident.trace.name": "multi_turn_trace",
|
|
"pydantic_ai.all_messages": """[
|
|
{
|
|
"role": "user",
|
|
"parts": [
|
|
{
|
|
"type": "text",
|
|
"content": "What is the report name?"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"parts": [
|
|
{
|
|
"type": "tool_call",
|
|
"id": "call_abc",
|
|
"name": "get_report",
|
|
"arguments": "{\\"id\\": \\"123\\"}"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"role": "user",
|
|
"parts": [
|
|
{
|
|
"type": "tool_call_response",
|
|
"id": "call_abc",
|
|
"name": "get_report",
|
|
"result": "Report: All Applications"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"parts": [
|
|
{
|
|
"type": "text",
|
|
"content": "The report name is All Applications."
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"role": "user",
|
|
"parts": [
|
|
{
|
|
"type": "text",
|
|
"content": "What are the columns in the report?"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"parts": [
|
|
{
|
|
"type": "text",
|
|
"content": "The report contains 68 columns."
|
|
}
|
|
]
|
|
}
|
|
]""",
|
|
"gen_ai.system_instructions": '[{"type": "text", "content": "You are a data analysis assistant."}]',
|
|
"gen_ai.operation.name": "chat",
|
|
"final_result": "The report contains 68 columns.",
|
|
},
|
|
status=Status(StatusCode.OK),
|
|
start_time=2000000000,
|
|
end_time=2000001000,
|
|
)
|
|
|
|
multi_turn_span_list = [multi_turn_readable_span]
|