AnoobFeng 446fa03801
fix(context): resolve context compress bug (#4065)
* fix(runtime): persist original human input outside model sanitization

* refactor(history): load thread messages by global event sequence

* fix(frontend): make summarization rescue a transient history bridge

* fix(frontend): old message not append tail

1. add identity anchor
2. add bridgeOrder

* fix(frontend): lint error fix

* fix: address review feedback and harden pagination coverage

- defer transient history ref writes until after render commit
- cover large middleware-only history scans
- verify infinite-query refetch recalculates page cursors
- document AI event types and anchor-weaving differences

* fix: harden message pagination and enrichment

- append unmatched live tails after canonical history
- warn and stop when pagination has_more lacks a cursor
- deep-copy restored UI messages to isolate model-facing content
- log invalid event sequence and non-advancing cursor errors
- pass user_id explicitly through event-store history queries
- cover middleware-only AI runs across memory, JSONL, and DB stores

* fix: address pagination review feedback

* fix(frontend): checkpoint has unknow redener content, optimize the anchor policy

* fix(frontend): unit test issue missed previously, remove the TanStack cache trimming

* fix(gateway): harden message history queries and provenance

- reject externally forged original_user_content metadata
- validate provenance metadata in upload and sanitization middleware
- make run lookups fail closed by default
- batch feedback queries by run ID
- align memory message filtering with persistent stores
2026-07-14 10:43:13 +08:00

136 lines
4.6 KiB
Python

"""Abstract interface for run event storage.
RunEventStore is the unified storage interface for run event streams.
Messages (frontend display) and execution traces (debugging/audit) go
through the same interface, distinguished by the ``category`` field.
Implementations:
- MemoryRunEventStore: in-memory dict (development, tests)
- Future: DB-backed store (SQLAlchemy ORM), JSONL file store
"""
from __future__ import annotations
import abc
from deerflow.runtime.user_context import AUTO, _AutoSentinel
class RunEventStore(abc.ABC):
"""Run event stream storage interface.
All implementations must guarantee:
1. put() events are retrievable in subsequent queries
2. seq is strictly increasing within the same thread
3. list_messages() only returns category="message" events
4. list_events() returns all events for the specified run
5. Returned dicts match the RunEvent field structure
"""
@abc.abstractmethod
async def put(
self,
*,
thread_id: str,
run_id: str,
event_type: str,
category: str,
content: str | dict = "",
metadata: dict | None = None,
created_at: str | None = None,
) -> dict:
"""Write an event, auto-assign seq, return the complete record."""
@abc.abstractmethod
async def put_batch(self, events: list[dict]) -> list[dict]:
"""Batch-write events. Used by RunJournal flush buffer.
Each dict's keys match put()'s keyword arguments.
Returns complete records with seq assigned.
"""
@abc.abstractmethod
async def list_messages(
self,
thread_id: str,
*,
limit: int = 50,
before_seq: int | None = None,
after_seq: int | None = None,
user_id: str | None | _AutoSentinel = AUTO,
) -> list[dict]:
"""Return displayable messages (category=message) for a thread, ordered by seq ascending.
Supports bidirectional cursor pagination:
- before_seq: return the last ``limit`` records with seq < before_seq (ascending)
- after_seq: return the first ``limit`` records with seq > after_seq (ascending)
- neither: return the latest ``limit`` records (ascending)
``user_id`` may be passed explicitly by request-independent callers;
user-scoped backends must apply it according to their isolation model.
"""
@abc.abstractmethod
async def list_events(
self,
thread_id: str,
run_id: str,
*,
event_types: list[str] | None = None,
task_id: str | None = None,
limit: int = 500,
after_seq: int | None = None,
) -> list[dict]:
"""Return the full event stream for a run, ordered by seq ascending.
Optionally filter by ``event_types`` and/or ``task_id`` (matched against
``metadata["task_id"]``). ``after_seq`` is a forward cursor returning the
first ``limit`` records with seq > after_seq, so callers can page through
a single subagent task's events without the run-wide ``limit`` truncating
the tail (#3779).
"""
@abc.abstractmethod
async def list_messages_by_run(
self,
thread_id: str,
run_id: str,
*,
limit: int = 50,
before_seq: int | None = None,
after_seq: int | None = None,
) -> list[dict]:
"""Return displayable messages (category=message) for a specific run, ordered by seq ascending.
Supports bidirectional cursor pagination:
- after_seq: return the first ``limit`` records with seq > after_seq (ascending)
- before_seq: return the last ``limit`` records with seq < before_seq (ascending)
- neither: return the latest ``limit`` records (ascending)
"""
@abc.abstractmethod
async def get_last_visible_ai_seq_by_run(
self,
thread_id: str,
run_ids: set[str],
*,
user_id: str | None | _AutoSentinel = AUTO,
) -> dict[str, int]:
"""Return each run's last non-middleware AI message sequence.
``user_id`` follows the same explicit-caller semantics as
:meth:`list_messages`.
"""
@abc.abstractmethod
async def count_messages(self, thread_id: str) -> int:
"""Count displayable messages (category=message) in a thread."""
@abc.abstractmethod
async def delete_by_thread(self, thread_id: str) -> int:
"""Delete all events for a thread. Return the number of deleted events."""
@abc.abstractmethod
async def delete_by_run(self, thread_id: str, run_id: str) -> int:
"""Delete all events for a specific run. Return the number of deleted events."""