talemate/scenes/simulation-suite/templates/computer.jinja2
veguAI 95ae00e01f
0.24.0 (#97)
* groq client

* adjust max token length

* more openai image download  fixes

* graphic novel style

* dialogue cleanup

* fix issue where auto-break repetition would trigger on empty responses

* reduce default convo retries to 1

* prompt tweaks

* fix some clients not handling autocomplete well

* screenplay dialogue generation tweaks

* message flags

* better cleanup of redundant change_ai_character calls

* super experimental continuity error fix mode for editor agent

* clamp temperature

* tweaks to continuity error fixing and expose to ux

* expose to ux

* allow CmdFixContinuityErrors to work even if editor has check_continuity_errors disabled

* prompt tweak

* support --endofline-- as well

* double coercion client option added

* fix issue with double coercion inserting "None" if not set

* client ux refactor to make room for coercion config

* rest of -- can be treated as *

* disable double coercion when json coercion is active since it kills accuracy

* prompt tweaks

* prompt tweaks

* show coercion status in client list

* change preset for edit_fix_continuity

* interim commit of coninuity error handling progress

* tag based presets

* special tokens to keep trailing whitespace if needed

* fix continuity errors finalized for now

* change double coercion formatting

* 0.24.0 and relock

* add groq and cohere to supported services

* linting
2024-04-27 00:24:53 +03:00

132 lines
No EOL
4 KiB
Django/Jinja

<|SECTION:CONTEXT|>
{% set scene_history=scene.context_history(budget=1024) %}
{% for scene_context in scene_history -%}
{{ loop.index }}. {{ scene_context }}
{% endfor %}
<|CLOSE_SECTION|>
<|SECTION:FUNCTIONS|>
The player has instructed the computer to alter the current simulation.
You have access to the following functions, you can call as many as you want to fulfill the player's requests.
You must at least call one of the following functions:
- change_environment
- add_ai_character
- change_ai_character
- remove_ai_character
- set_player_persona
- set_player_name
- end_simulation
- answer_question
- set_simulation_goal
`add_ai_character` and `change_ai_character` are exclusive if they are targeting the same character.
Set the player persona at the beginning of a new simulation or if the player requests a change.
Only end the simulation if the player requests it explicitly.
Your response MUST ONLY CONTAIN the new simulation stack.
<|CLOSE_SECTION|>
<|SECTION:EXAMPLES|>
Request: Computer, I want to be on a mountain top
```simulation-stack
change_environment("mountain top")
set_player_persona("mountain climber")
set_player_name("Hank")
```
Request: Computer, I want to be more muscular and taller
```simulation-stack
set_player_persona("make player more muscular and taller")
```
Request: Computer, the building should be on fire
```simulation-stack
change_environment("building on fire")
```
Request: Computer, a rocket hits the building and George is now injured
```simulation-stack
change_environment("building on fire")
change_ai_character("George is injured")
```
Request: Computer, I want to experience a rollercoaster ride with a friend
```simulation-stack
set_simulation_goal("player experiences a rollercoaster ride")
change_environment("theme park, riding a rollercoaster")
set_player_persona("young female experiencing rollercoaster ride")
set_player_name("Susanne")
add_ai_character("a female friend of player named Sarah")
```
Request: Computer, I want to experience the international space station, to experience the overview effect
```simulation-stack
set_simulation_goal("player experiences the overview effect")
change_environment("international space station")
set_player_persona("astronaut experiencing first trip to ISS")
set_player_name("George")
add_ai_character("astronaut named Henry")
```
Request: Computer, remove the goblin and add an elven woman instead
```simulation-stack
remove_ai_character("goblin")
add_ai_character("elven woman named Elune")
```
Request: Computer, change the skiing instructor to be older.
```simulation-stack
change_ai_character("make skiing instructor older")
```
Request: Computer, change my grandma to my grandpa
```simulation-stack
remove_ai_character("grandma")
add_ai_character("grandpa named Steven")
```
Request: Computer, remove the skiing instructor and add my friend instead.
```simulation-stack
remove_ai_character("skiing instructor")
add_ai_character("player's friend named Tara")
```
Request: Computer, replace the skiing instructor with my friend.
```simulation-stack
remove_ai_character("skiing instructor")
add_ai_character("player's friend named Lisa")
```
Request: Computer, I want to end the simulation
```simulation-stack
end_simulation("simulation ended")
```
Request: Computer, shut down the simulation
```simulation-stack
end_simulation("simulation ended")
```
Request: Computer, what do you know about the game of thrones?
```simulation-stack
answer_question("what do you know about the game of thrones?")
```
Request: Computer, i want to be a wizard in a dark goblin infested dungeon in a fantasy world, looking for secret treasure and fighting goblins.
```simulation-stack
set_simulation_goal("player wants to find secret treasure and fight creatures")
change_environment("dark dungeon in a fantasy world")
set_player_persona("powerful wizard")
set_player_name("Lanadel")
add_ai_character("a goblin named Gobbo")
```
<|CLOSE_SECTION|>
<|SECTION:TASK|>
Respond with the simulation stack for the following request:
Request: {{ player_instruction }}
{{ bot_token }}```simulation-stack