- name
SKILL.md
Tệp skill vẫn nằm trong kho mã của nhà phát hành.
Dán lệnh đã sao chép vào terminal. Lệnh sẽ cài đặt tệp SKILL.md này vào agent đó.
npx skills add topoteretes/cognee --skill cognee-improve-sessions -a cursor -yDán lệnh đã sao chép vào terminal. Lệnh sẽ cài đặt tệp SKILL.md này vào agent đó.
npx skills add topoteretes/cognee --skill cognee-improve-sessions -a claude-code -yDán lệnh đã sao chép vào terminal. Lệnh sẽ cài đặt tệp SKILL.md này vào agent đó.
npx skills add topoteretes/cognee --skill cognee-improve-sessions -a codex -yDán lệnh đã sao chép vào terminal. Lệnh sẽ cài đặt tệp SKILL.md này vào agent đó.
npx skills add topoteretes/cognee --skill cognee-improve-sessions -a grok -yGửi tin nhắn đã sao chép trong cuộc trò chuyện Grok Bot. Bot sẽ lấy tệp SKILL.md này từ GitHub và thêm vào bộ skill mà mọi Bot của bạn dùng chung.
Install this skill: https://github.com/topoteretes/cognee/tree/HEAD/.agents/skills/cognee-improve-sessionsTừ nhà phát hành
cognee has two kinds of memory:
session_id. Writing is instant, with no LLM
extraction.remember() builds without a session.improve() connects them. It bridges session content into the graph and
enriches the graph itself. remember() calls it automatically, so most
users never call it directly.
import cognee
# Session write: returns immediately; improve() bridges it in the background
await cognee.remember("User prefers dark mode.", session_id="chat_1")
# Session-aware query: session cache first, then the graph
results = await cognee.recall("What does the user prefer?", session_id="chat_1")
# Bridge sessions into a dataset's graph explicitly
result = await cognee.improve(dataset="main_dataset", session_ids=["chat_1"])
print(result.status, result.stage_summary())
await cognee.wait_for_background_tasks() # before a script exits
Requirements: CACHING=true (default). The cache backend is
CACHE_BACKEND, one of sqlite (default), postgres, redis,
tapes. Sessions expire after SESSION_TTL_SECONDS (default 7 days).
Every run goes through the same ordered stages
(cognee/modules/improve/registry.py). Each stage checks a gate before it
spends any LLM or embedding cost, and reports one StageResult.
Stages 1–7 need session_ids; 8–9 work on the graph alone. The order
matters: 4 feeds 5, 5 feeds 7, and 7 runs before 8.
extraction_tasks / enrichment_tasks are deprecated and removed in the next
release: they still run, as a custom_tasks stage after the others, scoped by
node_name, data, node_type, vector_db_config and graph_db_config.
Without custom tasks those options are ignored. Both cases warn with a
FutureWarning; use run_custom_pipeline() instead.
improve() returns an ImproveResult, and so do POST /api/v1/improve, the
CLI, and RememberResult.improve.
result.status: completed, errored (any stage errored), skipped
(every stage skipped), or running (background, not finished).result.stages: one StageResult per stage, with stage, status
(completed / already_completed / skipped / errored), reason,
error, counts, duration_ms.result.stage("distill_sessions"), result.stage_summary().await result.wait() finishes a background run (no-op otherwise).Skip and no-op reasons:
add, then cognify, then a foreground improve().
Its outcome is on result.improve / result.improve_error. A failed
improve never marks the remember as errored.session_id: the text is cached, then a background
improve(dataset, session_ids=[session_id]) starts if the debounce allows
it. result.improve fills in only after await result or
wait_for_background_tasks().self_improvement=False turns it off per call; IMPROVE_AUTO_ENABLED=false
turns it off everywhere and overrides self_improvement=True.cognee.modules.improve.register_auto_improve_admission(check)
registers one async check that remember() awaits on both paths. Returning
a reason string skips the improve and sets result.improve_skipped
(result.improve stays None); the data is stored either way. A check that
raises allows the improve. Explicit improve() calls are never gated.IMPROVE_*, cognee/modules/improve/config.py)There is no debounce timer: held-back entries wait for the next
remember() with that session, or an explicit improve().
improve(dataset) often does nothing. Without session_ids,
only stages 8–9 can run, and both are off by default. Result: every
stage skipped. That is expected, not an error.node_set fixes it for the session; a different set is a 409, start a
new session instead. Bridged Q&A, traces and lessons carry the set, user
preferences never do. The guarantee holds within one worker process (an
in-process lock); with several workers, send a session's writes to one.
Example: examples/guides/session_node_sets.py.remember(..., session_id=...) goes to the bound
dataset; naming another one (dataset_id, or a dataset_name other than
the main_dataset default) raises ValueError (HTTP 409 on
POST /api/v1/remember, 400 on /remember/entry). Start a new session
for another dataset. The turn's Q&A vector is written to that dataset's own
vector store, where its recalls read it.DATASET_QUEUE_MAX_CONCURRENT, default 6, per process), so it waits
while that many datasets are busy, and the first write to a new dataset
provisions the dataset's databases (one database per dataset on
pgvector/Postgres, a container with neo4j_community). If those
databases cannot be bound, the write raises instead of storing the turn.remember(QAEntry/TraceEntry/ FeedbackEntry, session_id=...) stores the entry but never starts an
improve. Call improve(session_ids=[...]) yourself.cognify(): improves, cognify, add and forget on one dataset
run one at a time, and improves sharing a session also wait for each
other. A background call returns at once and waits inside its task. The
lock is per process only; multiple API workers do not share it.improve() resolves the dataset once (creating it if the name is new),
waits for the dataset's lock and then for every
session:<user>:<session_id> claim, probes the graph adapter's capabilities, and
runs the stages with one frozen ImproveRunInputs. Each stage is a gate
plus a call into existing pipelines plus a result mapping. Stages never own
retries or ordering.
Watermarks keep repeat runs cheap:
The improve operation row is written when the run finishes: failed if any
stage errored (a retry is never gated off), noop if nothing ran.
cognee/api/v1/improve/improve.py (HTTP:
routers/get_improve_router.py; CLI: cognee/cli/commands/improve_command.py)cognee/modules/improve/ (stages.py,
registry.py, stage.py, result.py, inputs.py, capabilities.py,
config.py, watermarks.py, constants.py)cognee/infrastructure/locks/session_lock.pycognee/infrastructure/session/
(session_manager.py, session_persist_watermark.py,
feedback_detection.py); cache backends in
cognee/infrastructure/databases/cache/cognee/api/v1/remember/remember.py,
cognee/api/v1/remember/auto_improve_debounce.pycognee/memory/entries.pycognee/infrastructure/background_tasks.pyExamples: examples/guides/improve_quickstart.py, sessions.py,
session_distillation.py, review_conflicts.py, global_context_index.py,
agent_memory_quickstart.py, and
examples/advanced_guides/remember_recall_improve_example.py.
Adding a stage:
BaseStage in cognee/modules/improve/stages.py. Set name,
needs_sessions, and fatal (leave it False; exactly one fatal stage
is enforced at import). Implement gate() (return a skip reason
constant, or None, before any LLM/embedding cost) and run() (call
existing pipeline code, return a StageResult).DEFAULT_STAGES in registry.py at the right position.
The order is pinned by cognee/tests/unit/modules/improve/test_registry_order.py;
update it deliberately.already_completed (graph-wide stages can stamp the improve row with the
helpers in watermarks.py, as conflict review does).cognee/tests/unit/modules/improve/ (gates, results, config) and
cognee/tests/unit/api/v1/improve/ (orchestration, queue, router).Use when working with cognee's session memory or improve() — storing conversation turns, agent traces and feedback with session_id, bridging sessions into the permanent graph, reading an ImproveResult
---name: cognee-improve-sessionsdescription: Use when working with cognee's session memory or improve() — storing conversation turns, agent traces and…---# .agents/skills/cognee-improve-sessions/SKILL.mdTổng quan
Use when working with cognee's session memory or improve() — storing conversation turns, agent traces and feedback with session_id, bridging sessions into the permanent graph, reading an ImproveResult, understanding why an improve stage was skipped or already_completed, or tuning the IMPROVE_* settings.
Câu hỏi thường gặp
Tải .agents/skills/cognee-improve-sessions/SKILL.md từ nhà phát hành, hoặc sao chép đường dẫn và mở kho mã. PlugMCP chỉ liệt kê skill và không lưu trữ tệp này.
Nhà phát hành duy trì nó tại https://github.com/topoteretes/cognee.
Claude, Cursor, Codex và Grok Build có thể đọc tệp SKILL.md mà bạn thêm từ kho mã của nhà phát hành. Grok Bot cài đặt skill khi bạn gửi liên kết thư mục GitHub của skill trong cuộc trò chuyện.
IMPROVE_STAGES_DISABLED is validated.persist_session_qaValueErrorremember(text, session_id=...)
with CACHING=false only logs a warning and stores nothing; typed entries
raise RuntimeError. An explicit improve(session_ids=...) then fails in
the fatal stage.improve() raises (HTTP 409)
and the error carries .improve_result. In background mode it is recorded
on result.error instead. Other stages failing only mark themselves
errored; HTTP still returns 200, so check status.cognee.serve(url), a background improve is
fire-and-forget: status stays running and there is no polling.cognee/modules/session_bridge/ is gone (only stale __pycache__ may be
left). The bridging now lives in the improve stages; some test names still
say "session_bridge".