Make maximum monologue length configurable

[lowlyocean]

Describe your question

Can anyone else reproduce this odd behavior when running ollama/codeqwen:7b-chat-v1.5-q4_0 ?

The first MonlogueAgent prompt has too many thoughts for it to succeeed. It just prints out something like :
101011 10 ▅ ▅10

This is the last thought that it can tolerate (and print correctly-formatted JSON response):

  {
    "action": "think",
    "args": {
      "thought": "Very cool. Now to accomplish my task."
    }
  },

Because as soon as the next one is added, it generates that nonsense output:

  {
    "action": "think",
    "args": {
      "thought": "I'll need a strategy. And as I make progress, I'll need to keep refining that strategy. I'll need to set goals, and break them into sub-goals."
    }
  },

Additional context

Using the docker image, launched from WSL on Windows 11. Ollama version 0.1.32

[lowlyocean]

Is there already a way to expose Agent-specific parameters to the UI, or would I need to perform a build to adjust this parameter below (which I suspect may be too high for this local LLM) ?

OpenDevin/agenthub/monologue_agent/agent.py

Line 32 in ba556ea

MAX_MONOLOGUE_LENGTH = 20000

Edit: looks like there's already a proposal to expose these to UI
#1135 (comment)

[rbren]

Definitely! We could also add this to config.py so it can be set with an env var--feel free to open a PR!