Recall

Retrieve past knowledge from the memory layers.

When to use

• Fetching the current active context (session, working items, entities, tasks, claims)
• Querying journal history to see what changed and when
• Composing a unified context snapshot that merges active, trusted, and speculative layers
• Deciding whether to include speculative inference in the retrieved context

Quick start

import pathlib
from datetime import date
from src.api.memory_manager import MemoryManager
from src.retrieval.composer import RetrievalComposer
from src.journal.appender import JournalAppender

root = pathlib.Path(".agent-memory")

# High-level retrieval via MemoryManager
mgr = MemoryManager(root_dir=root)
context = mgr.retrieve_context(include_terminus=False)
# context keys: session, working_items, entities, tasks, claims,
#               terminus_memories, speculative_inference, facet_relations

# Include trusted Terminus memories and speculative inference
full = mgr.retrieve_context(
    include_terminus=True,
    include_speculative=True,
    inference_branch="inference/sess-1",
)

# Journal history for today
appender = JournalAppender(root)
events = appender.read_day(date.today())
for event in events:
    print(event.mutation_kind, event.changed_files)