Build Context For Task • AI Agent SDK

build_context_for_task: Merges relevant short-term, long-term, entity, user memories

build_context_for_task

Method

This is a method of the Memory class in the memory module.

Merges relevant short-term, long-term, entity, user memories into a single text block with deduplication and clean formatting.

Signature

def build_context_for_task(task_descr: str, user_id: Optional[str], additional: str, max_items: int, include_in_output: Optional[bool]) -> str

Parameters

task_descr · str · required

No description available.

user_id · Optional[str]

No description available.

additional · str · default: "''"

No description available.

max_items · int · default: "3"

No description available.

include_in_output · Optional[bool]

If None, memory content is included (the primary purpose of this method is to feed retrieved memory into the prompt). If True, memory content is always included. If False, memory content is never included (only logged for debugging).

Returns

Returns · str

The result of the operation.

Uses

• c.isspace
• content.rfind
• format_content
• normalize_content
• seen_contents.add
• logger.debug
• search_short_term
• search_long_term
• search_entity
• search_user_memory

Used By

• Memory.build_cache_optimized_context
• Memory.get_context

Source

View on GitHub

praisonaiagents/memory/memory.py at line 1879

---

Related Documentation

Tasks Concept

Task Configuration

Task Validation

Context Concept

Context Management