I have reduced my problem down to the following simplest form:
from agno.agent import Agentfrom agno.models.openai import OpenAIChat
agent = Agent(
model=OpenAIChat(id=“gpt-4.1”,api_key=“...”,),
instructions=“a={a}”,
debug_mode=True
)
response = agent.run(“what is a?”, dependencies={“a”: 1})
print(response.content)
DEBUG **************************************************** Agent ID: 5e8e87d2-7a1b-487e-819f-669560eb7b75
****************************************************
DEBUG Creating new AgentSession: 01cf3332-fd4e-4f42-97ce-83fc80f0c622DEBUG Resolving dependencies
DEBUG ************************************************ Agent Run Start: a91ccc31-2d7a-4dfc-a131-e37fd9e18e37 *************************************************
DEBUG ---------------------------------------------------------------- OpenAI Response Start -----------------------------------------------------------------
DEBUG -------------------------------------------------------------------- Model: gpt-4.1 --------------------------------------------------------------------
DEBUG ======================================================================== system ========================================================================
DEBUG a={a}
DEBUG ========================================================================= user =========================================================================
DEBUG what is a?
DEBUG ====================================================================== assistant =======================================================================
DEBUG You wrote a code-like instruction setting a variable: a={a}.
In this context, a is assigned the value {a}. However, {a} appears to be a placeholder and has not been given a specific value. So, a equals {a}, which is an
undefined or placeholder value.
If you meant to assign a specific value to a, you should replace {a} with the value you want, for example: a=5.
DEBUG ********************************************************************** METRICS ***********************************************************************
DEBUG * Tokens: input=25, output=91, total=116
DEBUG * Duration: 3.3363sDEBUG * Tokens per second: 27.2756 tokens/s
DEBUG ********************************************************************** METRICS ***********************************************************************
DEBUG ----------------------------------------------------------------- OpenAI Response End ------------------------------------------------------------------DEBUG Added RunOutput to Agent Session
DEBUG ************************************************* Agent Run End: a91ccc31-2d7a-4dfc-a131-e37fd9e18e37 **************************************************