---

title: "Convenience function for quick prompt building" component_type: script version: "1.0.0" audience: contributor status: stable summary: "LLM Abstractions Module" keywords: ['abstractions', 'generation', 'llm'] tokens: ~500 created: 2025-12-22 updated: 2025-12-22 script_name: "llm_abstractions.py" language: python executable: true usage: "python3 scripts/llm_abstractions.py [options]" python_version: "3.10+" dependencies: [] modifies_files: false network_access: false requires_auth: false

LLM Abstractions Module

CODITECT Framework - Common abstractions for LLM interactions including framework knowledge retrieval and system prompt building.

Author: CODITECT Framework Version: 1.0.0

File: llm_abstractions.py

Classes

`FrameworkKnowledge`

Container for framework knowledge and context.

`SystemPromptBuilder`

Builder for constructing system prompts with framework context.

Functions

`get_framework_knowledge(framework_path, include_components)`

Retrieve framework knowledge from CODITECT configuration.

`build_agent_prompt(agent_name, description, capabilities, include_framework)`

Build a standard agent system prompt.

`add_section(title, content)`

Add a titled section to the prompt.

`add_framework_context(framework_path)`

Add CODITECT framework context to the prompt.

`add_role(role, responsibilities)`

Add role definition to the prompt.

`add_constraints(constraints)`

Add constraints/rules to the prompt.

`add_examples(examples)`

Add examples to the prompt.

`build()`

Build the final system prompt.

`framework_knowledge()`

Get the loaded framework knowledge if available.

Classes​

FrameworkKnowledge​

SystemPromptBuilder​

Functions​

get_framework_knowledge(framework_path, include_components)​

build_agent_prompt(agent_name, description, capabilities, include_framework)​

add_section(title, content)​

add_framework_context(framework_path)​

add_role(role, responsibilities)​

add_constraints(constraints)​

add_examples(examples)​

build()​

framework_knowledge()​