Can't get dependencies to be injected into my system prompt

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 **************************************************

Hi @k3vob, thanks for reaching out and supporting Agno. I’ve shared this with the team, we’re working through all requests one by one and will get back to you soon.If it’s urgent, please let us know. We appreciate your patience!

Hi @k3vob I tried the code snippet provided above and I am getting a response as a is 1. Can you please confirm you are using the latest version of Agno ?
Thanks

@monalisha Yes, upgrading from 2.0.3 to 2.0.5 fixed this. Thank you.