Using the /v1/chat/completions API and I am getting a python error send_message_to_agent() missing 1 required positional argument: 'stream_legacy'

[vysona-scott]

Describe the bug
A clear and concise description of what the bug is.

Using the /v1/chat/completions API and I am getting a python error send_message_to_agent() missing 1 required positional argument: 'stream_legacy'

It looks like the method that implements this API https://github.com/cpacker/MemGPT/blob/main/memgpt/server/rest_api/openai_chat_completions/chat_completions.py#L73C4-L82C14 requires a boolean to be set that does not have a default value https://github.com/cpacker/MemGPT/blob/main/memgpt/server/rest_api/agents/message.py#L90C1-L91C1 .

Please describe your setup

• How did you install memgpt?
  • https://github.com/cpacker/MemGPT/blob/main/CONTRIBUTING.md#1--getting-started
• Describe your setup
  • What's your OS (Windows/MacOS/Linux)?
    • Ubuntu host on Windows VSCode over ssh
  • How are you running memgpt? (cmd.exe/Powershell/Anaconda Shell/Terminal)
    - dotenv run -- memgpt server
    Screenshots
    If applicable, add screenshots to help explain your problem.
    Pylance output
    

Additional context

curl --location 'http://localhost:8083/v1/chat/completions' \
--header 'Authorization: Bearer <USER TOKEN>' \
--header 'Content-Type: application/json' \
--data '{
    "messages": [
        {
            "id": "UnzuNq8",
            "createdAt": "2024-07-29T14:14:10.412Z",
            "role": "user",
            "content": "ssssss"
        }
    ],
    "user": "355e3a6a-7176-42d6-a4b0-09db2d202a0f",
    "model":"gpt-4o",
    "requestData": {}
}'

MemGPT Config

[defaults]
preset = memgpt_chat
persona = sam_pov
human = basic

[model]
model = gpt-4o
model_endpoint = https://api.openai.com/v1
model_endpoint_type = openai
context_window = 8192

[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 = postgres
path = /home/scott/.memgpt/chroma

[recall_storage]
type = postgres
path = /home/scott/.memgpt

[metadata_storage]
type = postgres
path = /home/scott/.memgpt

[version]
memgpt_version = 0.3.21

[client]
anon_clientid = 00000000-0000-0000-0000-000000000000

---

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?)