> ## Documentation Index
> Fetch the complete documentation index at: https://docs.cognee.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Rust SDK Sessions

> Sessions in cognee-rust: temporary conversational memory, default sessions, session context and personalization.

## What is a session

A session holds short-term memory for one conversation: its questions and answers, agent trace steps, feedback and guidance. [improve](https://docs.cognee.ai/rust/core-concepts/main-operations/improve.md) turns it into permanent graph memory.

## How sessions work in Rust

A **Session** is a temporary memory context — search/answer history and feedback
for a single conversational thread — distinct from permanent, graph-backed
storage. Passing a `--session-id` to `remember` / `recall` scopes a turn to that
session and lets retrieval reuse prior context; omitting it on `remember`
persists input as permanent graph memory (see the memory API in
[operations](https://docs.cognee.ai/rust/core-concepts/main-operations/overview.md)). A completion `search` / `recall` (a retriever
that prepares session turns; not chunks, summaries, lexical, Cypher, …) that
omits it now uses the default session when the caller is known and session
memory is on (`session.caching`); before, such a search was stateless. The
id is `default_session_<dataset_id>` when one distinct dataset is searched, so
separate single-dataset searches never share a session, else
`default_session`. A search over several datasets, or naming none (unless
per-dataset storage leaves the caller exactly one readable dataset, which
scopes it), is one logical turn in the unscoped default session. Such a search
reads the session's history and, while `AUTO_FEEDBACK` is on, its stored guidance entries, analyzes the
turn (also only while `AUTO_FEEDBACK` is on) and saves its Q\&A; pass your own
session id to keep it out of the default session, or turn `session.caching` off
to keep it stateless.
The store backend is pluggable.

Rust: `SessionStore` trait in [`cognee-session`](https://github.com/topoteretes/cognee-rs/blob/main/crates/session/), with
`FsSessionStore` (crate feature `fs`), `RedisSessionStore` (crate feature `redis`),
and `RelationalSessionStore` backends. Setting `session.store = "fs"` or `"redis"`
requires a `cognee` built with its `session-fs` / `session-redis` feature. Those
features register the store factory and its `session.fs` / `session.redis` config
section; enabling `cognee-session/fs` or `cognee-session/redis` alone does neither.

Next to its Q\&A entries and agent trace steps, a session keeps a list of
**session-context rows**: JSON objects with a `"kind"`
field. `"context"` rows are active guidance entries (`SessionContextEntry`:
goals, rules, preferences, lessons); other kinds are feedback records or
internal state rows, such as the `StateRowWatermark` rows the improve stages use
to remember how far they got. Only `"context"` rows are ever rendered
(`coerce_active_context_entries`). `SessionManager::{get,create,update}_session_context_entry`
read and write them on every store (`session_context_entries` table,
`{session_id}.context.json` file, `session_context:{user}:{session}` Redis list);
deleting or pruning a session removes them. The table holds one row per
`(user_id, session_id, entry_id)` (unique index `uq_session_context_entry`), so on the relational store a create of
an existing entry id replaces it in place (the file and Redis stores append); a session without a user is the `"default"` user's, as on
the file and Redis stores. `apply_candidate_updates` is the one
writer of guidance entries (confidence ≥ 0.75, at most 280 characters, an exact
duplicate links its new source instead of a second entry); improve's
`extract_agent_context` stage feeds it the `agent`-profile lessons it draws
from the session's trace steps, and so does every stored trace step while
`AUTO_FEEDBACK` is on (see [`AUTO_FEEDBACK`](https://docs.cognee.ai/rust/configuration/search)).

The session graph-context snapshot is removed: `SessionStore` /
`SessionManager::{get,set}_graph_context`, `cognee::session::{get,set}_graph_context`
and the bindings' graph-context ops are gone, a migration drops the
`session_graph_context` table, and session history no longer starts with a
"Background knowledge from the knowledge graph" prefix. The recall scope
`"graph_context"` is a deprecated alias of `"graph"` (it logs a warning), and
`"all"` means graph, session, trace and session context (see
[recall](https://docs.cognee.ai/rust/core-concepts/main-operations/recall.md)).

With **personalization** on (`personalization_enabled`), improve's
`update_user_preferences` stage keeps one internal `UserPreference` node per
user and dataset, with weighted `prefers` edges to the graph nodes the user's
rated answers used and the user's stated preferences as text; graph, RAG, and
hybrid searches by that user rank by those weights and carry that text (see
[Configuration: feedback & personalization](https://docs.cognee.ai/rust/configuration/search.md#feedback--personalization)).

## Related

> [card] [Recall](https://docs.cognee.ai/rust/core-concepts/main-operations/recall.md)
>
> Session-aware retrieval

> [card] [Improve](https://docs.cognee.ai/rust/core-concepts/main-operations/improve.md)
>
> Bridge sessions into the graph

> [card] [Runtime configuration](https://docs.cognee.ai/rust/configuration/runtime.md)
>
> Session store settings


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.