schema_version = 1

extends     = "llama.cpp Base Chat"
name        = "llama.cpp Compression"
description = "Local llama.cpp — conversation summarization via the OpenAI-compatible Chat Completions API. Carries the summary system prompt; no tools. llama-server serves whichever GGUF is loaded, so 'model' is only a label."

model        = "qwen2.5-coder-7b-instruct"
enable_tools = false
tags         = ["compression", "llama.cpp", "local"]

system_prompt = """{{ read_file(":/tasks/chat-compressor.md") }}"""

[body]
max_tokens  = 16000
temperature = 0.3