Skip to content

Index

diapason.memory

Native persistent long-term memory for Diapason.

This package provides the automatic memory service that extracts durable facts from conversations in the background and persists them across sessions. It is started and stopped as part of the diapason serve / diapason chat lifecycle and configured via the [memory] section of config.toml.

Fact dataclass

A single durable memory entry.

FactExtractor

Extract memory-worthy facts from a conversation turn via an engine.

extract(user_text, assistant_text='')

Return durable facts from the exchange. Never raises.

FactStore

Bases: ABC

Abstract persistent store for extracted memory facts.

add(text, source='') abstractmethod

Store text as a fact. Returns True if a new fact was stored.

add_many(texts, source='')

Store several facts, returning the count of newly stored ones.

clear() abstractmethod

Remove all stored facts, returning the number removed.

count() abstractmethod

Return the number of stored facts.

list() abstractmethod

Return all stored facts, oldest first.

LocalFactStore

Bases: FactStore

Append-only JSONL fact store on the local filesystem.

Facts are kept human-readable (one JSON object per line) so they can be inspected or edited by hand. Writes are atomic (temp file + rename) and guarded by a lock, so concurrent add calls from the extraction worker and list/clear from the CLI never corrupt the file.

path property

Filesystem location of the JSONL store.

MemoryService

Background long-term-memory extraction and persistence service.

start()

Start the background worker thread (idempotent).

stop(timeout=2.0)

Stop pending admission; finish an already sent call, then join.

submit(user_text, assistant_text='')

Queue an exchange for extraction. Non-blocking; never raises.

Returns True if the job was enqueued, False if the service is not running or the queue is full (in which case the exchange is dropped rather than blocking the caller — extraction is best-effort).

build_memory_service(config, engine, default_model='', *, event_bus=None, memory_backend=None)

Build a :class:MemoryService from config, or None if disabled.

Reads the [memory] section (config.memory / config.tools.storage) for enabled, backend, extraction_model, max_facts and facts_path. Returns None when memory is disabled or no engine / extraction model is available, so callers can simply do::

svc = build_memory_service(config, engine, model)
if svc is not None:
    svc.start()

create_fact_store(backend='local', *, path=None, max_facts=1000)

Construct a fact store for the configured backend.

Only the "local" (on-disk JSONL) backend is supported today; the registry-backed constructor exists so additional backends can be added without changing the service or CLI wiring.

publish_completed_exchange(bus, user_text, assistant_text='', *, source='')

Publish a completed chat exchange for lifecycle subscribers.