Functions are not updated when preset changed for agent

[mb-doo007]

Describe the bug
When I change the preset for an agent with
memgpt_agent.agent_state.preset = instance.preset, as I created a new preset for the agent with some new extra functions, the functions are not updated, but stay with the initially given functions (so when a new agent is created the additional functions are available for that new agent and they work).

The new functions are correctly added to the availble_functions in
def generate_functions_json(preset_functions: List[str]):
but in there, they are not added to the functions for the agent, as preset_functions still contains the old list of functions.

This preset_functions of the agent needs to be updated by reading the preset, I guess.

Please describe your setup

• How did you install memgpt?
  • pip install pymemgpt
  • pymemgpt==0.3.3
• Describe your setup
  • Windows 11 pro
  • venv
  • using the MemGPT Client for integration in python code
    Screenshots
    If applicable, add screenshots to help explain your problem.

Additional context
Add any other context about the problem here.

MemGPT Config
Please attach your ~/.memgpt/config file or copy past it below.

'
[defaults]
preset = summary_to_md
persona = Lex-theSummarizer
human = basic

[model]
model = gpt-4-1106-preview
model_endpoint = https://api.openai.com/v1
model_endpoint_type = openai
context_window = 128000

[embedding]
embedding_endpoint_type = openai
embedding_endpoint = https://api.openai.com/v1
embedding_model = text-embedding-ada-002
embedding_dim = 1536
embedding_chunk_size = 300

[archival_storage]
type = chroma
path = C:\Users\mberl.memgpt\chroma

[recall_storage]
type = sqlite
path = C:\Users\mberl.memgpt

[metadata_storage]
type = sqlite
path = C:\Users\mberl.memgpt

[version]
memgpt_version = 0.3.3

[client]
anon_clientid = 00000000000000000000c89665e06421
'

---

If you're not using OpenAI, please provide additional information on your local LLM setup:

Local LLM details

If you are trying to run MemGPT with local LLMs, please provide the following information:

• The exact model you're trying to use (e.g. dolphin-2.1-mistral-7b.Q6_K.gguf)
• The local LLM backend you are using (web UI? LM Studio?)
• Your hardware for the local LLM backend (local computer? operating system? remote RunPod?)