when sending chunked lite JSON data to new player on server (i.e. someone reconnects or logins in).

Update player login message from server to be sent in chunks for 32000 characters, to avoid the max String length errors. The client will reassemble all chunks and then load the JSON.

Added a new FleePlayerGoal, if an entity feel scared or threatened by the player. They run away at 1.5x speed. Also updated the system-chat examples to provide a more sequential list of messages.

- Added moveConflictingGoals function (to prevent duplicate goal priorities)
- Fixed FollowPlayerGoal to not clear the this.targetPlayer variable when stop() is called. This can be temporarily stopped due to a higher priority goal.
- Updated TALK priority to 2, and FOLLOW priority to 3, for maximum compatability across entities, without overriding their most important survival/attack goals.

Fixing issue with message order in Chat GPT request, to add them in reverse order (limiting them by token usages), and then reversing the list at the end.

- Added a long list of random "no response" phrases. Sometimes the LLM just outputs a behavior and no text.
- Added the actual output with behaviors to chat history (for better context)
- Fixed a bug which was broadcasting the new generated message at the wrong time.

Small refactor to ChatGPT requests, separating all the key variables to make it easier to modify. Also, adding in token estimation and limits: 200 output tokens, 75% of the 16k context window, so super long conversations exceeding 12k tokens will be trimmed to the most recent messages.

Update UI to newest artwork from owlmaddie. Update some X,Y coordinates since a few images changes sizes and locations.

- New method to retrieve and use an Entity Renderer to return the texture path associated with it
- Large refactor of entity texture folders and file names to match the Minecraft texture paths.

- Refactored Goal Adding/Removing to make it more generic
- Added enum for Goal Priorities, since an entity can have both Talk and Follow goals at the same time.
- Updated Follow goal to no longer look at the player once they reach the player.
- Removed slowness status effect, replaced with Talk Goal

Simplifying character creation, to specify name and type in user message. Lowered chat bubble a bit. New improved user message for system-character prompt. Added lots of examples outputs for system-chat prompt.

Adding friendship property to entities, and update value when FRIENDSHIP behavior is updated. Clamp range to -3 to 3.

Added goals for "FOLLOW" and "UNFOLLOW", so Mob Entity types will follow the player. Refactored some code, to make this cleaner. GPT 3.5 still struggles to output the behaviors correctly, so I updated to GPT 4 Turbo.

Improve chat prompt to include behaviors: <FOLLOW> <FRIENDSHIP> <UNFOLLOW>, etc... Added code to detect separate these behaviors from the cleaned message. Also, better detection of character sheets (making the - optional).

- active status effects
- creative mode & hard-core mode
- is Swimming, is on the Ground
- Weather: is raining / thundering
- Moon phases
- World difficulty

Improve creativeness with chat gpt temperature, improve prompts, better support for GPT 3.5 and 4.0. Update model to gpt-3.5-turbo.

Set customName of an entity after the initial greeting has been generated (and only if the customName is not already set)

Fully integrate loading / saving data when players join the server, by sending a "light" version of the chat data on login.

Added support for both Json mode and text mode. Connected Save/Load methods when world loads, writing to local json file in level save folder.

Integrate experimental quest system message when ChatDataManager is initialized... disabled for now. Integrate item and entity rarity collectors into prompt. Added "JSON mode" for both 3.5 and 4.0 ChatGPT.

Initial rarity item & entity generator class, to help classify and categorize items and entities for our ChatGPT prompts. It turns out that ChatGPT is not good at randomizing or using valid entity types or item types, so we need to inject valid choices into the prompts.

Added message history for each entity conversation. Also tweaked the prompts a bit. Feels pretty nice now