fix(LongTermMemory): support memory tools in Agent processors (#2843)

* fix(LongTermMemory): support memory tools in Agent processors

* docs(LongTermMemory): clarify tool and Pipeline lifecycle access

* test(LongTermMemory): isolate persistent Chroma clients across fixtures
This commit is contained in:
huanghuoguoguo
2026-11-02 20:11:23 +08:00
committed by GitHub
parent 1a344aeb9f
commit 558ded2b7a
11 changed files with 422 additions and 76 deletions
@@ -468,6 +468,7 @@ class LongTermMemoryEngine(KnowledgeEngine):
batch_texts.append(content)
batch_ids.append(mid)
batch_metas.append({
"episode_id": mid,
"content": content,
"tags": ",".join(tags) if isinstance(tags, list) else str(tags),
"importance": str(importance),
@@ -5,7 +5,6 @@ from typing import Any
from langbot_plugin.api.definition.components.tool.tool import Tool
from langbot_plugin.api.entities.builtin.provider import session as provider_session
from langbot_plugin.api.proxies.query_based_api import QueryBasedAPIProxy
logger = logging.getLogger(__name__)
@@ -18,12 +17,7 @@ class Forget(Tool):
query_id: int,
) -> str:
store = self.plugin.memory_store
api = QueryBasedAPIProxy(
query_id=query_id,
plugin_runtime_handler=self.plugin.plugin_runtime_handler,
)
bot_uuid = await api.get_bot_uuid()
query_vars = await api.get_query_vars()
bot_uuid = session.bot_uuid or ""
session_key, user_key, kb_id, _, config = await store.resolve_user_context(
session, bot_uuid
)
@@ -48,6 +42,8 @@ class Forget(Tool):
episode_id=episode_id,
user_key=user_key,
)
if not deleted:
return "No matching memory found in the current scope."
await store.append_audit_entry(
scope_key=session_key,
user_key=user_key,
@@ -55,8 +51,7 @@ class Forget(Tool):
target_type="episode",
target_id=str(episode_id),
summary=f"Deleted episode {episode_id}",
sender_id=str(query_vars.get("sender_id", "") or ""),
sender_name=str(query_vars.get("sender_name", "") or ""),
sender_id=str(session.sender_id or ""),
query_id=query_id,
metadata={"kb_id": kb_id, "deleted": deleted},
)
@@ -6,7 +6,6 @@ from typing import Any
from langbot_plugin.api.definition.components.tool.tool import Tool
from langbot_plugin.api.entities.builtin.provider import session as provider_session
from langbot_plugin.api.proxies.query_based_api import QueryBasedAPIProxy
logger = logging.getLogger(__name__)
@@ -26,27 +25,19 @@ class RecallMemory(Tool):
query_id: int,
) -> str:
store = self.plugin.memory_store
api = QueryBasedAPIProxy(
query_id=query_id,
plugin_runtime_handler=self.plugin.plugin_runtime_handler,
)
logger.info(
"[LongTermMemory] recall_memory called: query_id=%s params_keys=%s",
query_id,
sorted(params.keys()),
)
bot_uuid = await api.get_bot_uuid()
_, user_key, kb_id, _isolation, config = await store.resolve_user_context(
bot_uuid = session.bot_uuid or ""
session_key, user_key, kb_id, _isolation, config = await store.resolve_user_context(
session, bot_uuid
)
if not kb_id:
return "Error: no memory knowledge base configured. Create one first."
pipeline_kbs = await api.list_pipeline_knowledge_bases()
if not any(kb.get("uuid") == kb_id for kb in pipeline_kbs):
return "Error: memory knowledge base is not configured for the current pipeline."
embedding_model_uuid = config.get("embedding_model_uuid", "")
if not embedding_model_uuid:
return "Error: no embedding model configured in knowledge base."
@@ -140,7 +131,9 @@ class RecallMemory(Tool):
except ValueError as exc:
return f"Error: {exc}"
if not episodes:
session_profile = await store.load_session_profile(session_key)
speaker_profile = await store.load_speaker_profile(session_key, str(session.sender_id or ""))
if not episodes and not any(store.has_profile_data(profile) for profile in (session_profile, speaker_profile)):
logger.info(
"[LongTermMemory] recall_memory no results: query_id=%s kb_id=%s",
query_id,
@@ -154,4 +147,8 @@ class RecallMemory(Tool):
kb_id,
len(episodes),
)
return json.dumps(episodes, ensure_ascii=False)
return json.dumps({
"session_profile": store.format_profile_text(session_profile),
"speaker_profile": store.format_profile_text(speaker_profile),
"episodes": episodes,
}, ensure_ascii=False)
@@ -6,8 +6,8 @@ metadata:
en_US: RecallMemory
zh_Hans: 主动回忆
description:
en_US: Search long-term episodic memories with controlled filters such as speaker and time range.
zh_Hans: 使用受控过滤条件(如说话人、时间范围)主动搜索长期情景记忆。
en_US: Read current session and speaker profiles, and search episodic memories with controlled filters.
zh_Hans: 读取当前会话和发言人的档案,并使用受控过滤条件搜索情景记忆。
spec:
parameters:
@@ -49,7 +49,9 @@ spec:
- query
llm_prompt: |
Search long-term episodic memories when the default automatic memory recall is not sufficient.
Read long-term memory for the current conversation and speaker.
Returns session_profile and speaker_profile text together with matching episodes.
Independent Agent processors can use this tool without a Pipeline or automatic memory injection.
Use this tool when you need to actively inspect memory with a specific retrieval intent, such as:
- recalling what a specific person said
@@ -5,7 +5,6 @@ from typing import Any
from langbot_plugin.api.definition.components.tool.tool import Tool
from langbot_plugin.api.entities.builtin.provider import session as provider_session
from langbot_plugin.api.proxies.query_based_api import QueryBasedAPIProxy
logger = logging.getLogger(__name__)
@@ -25,17 +24,12 @@ class Remember(Tool):
query_id: int,
) -> str:
store = self.plugin.memory_store
api = QueryBasedAPIProxy(
query_id=query_id,
plugin_runtime_handler=self.plugin.plugin_runtime_handler,
)
logger.info(
"[LongTermMemory] remember called: query_id=%s params_keys=%s",
query_id,
sorted(params.keys()),
)
bot_uuid = await api.get_bot_uuid()
query_vars = await api.get_query_vars()
bot_uuid = session.bot_uuid or ""
session_key, user_key, kb_id, _, config = await store.resolve_user_context(
session, bot_uuid
)
@@ -43,10 +37,6 @@ class Remember(Tool):
if not kb_id:
return "Error: no memory knowledge base configured. Create one first."
pipeline_kbs = await api.list_pipeline_knowledge_bases()
if not any(kb.get("uuid") == kb_id for kb in pipeline_kbs):
return "Error: memory knowledge base is not configured for the current pipeline."
embedding_model_uuid = config.get("embedding_model_uuid", "")
if not embedding_model_uuid:
return "Error: no embedding model configured in knowledge base."
@@ -57,8 +47,7 @@ class Remember(Tool):
tags = params.get("tags", [])
importance = params.get("importance", 2)
sender_id = str(query_vars.get("sender_id", "") or "")
sender_name = str(query_vars.get("sender_name", "") or "")
sender_id = str(session.sender_id or "")
logger.info(
"[LongTermMemory] remember storing episode: query_id=%s kb_id=%s user_key=%s sender_id=%s importance=%s tags=%s content_len=%s",
query_id,
@@ -78,7 +67,6 @@ class Remember(Tool):
tags=tags,
importance=importance,
sender_id=sender_id,
sender_name=sender_name,
bot_uuid=bot_uuid,
)
@@ -97,7 +85,6 @@ class Remember(Tool):
target_id=episode["id"],
summary=self._preview_text(str(content)),
sender_id=sender_id,
sender_name=sender_name,
query_id=query_id,
metadata={
"kb_id": kb_id,
@@ -5,7 +5,6 @@ from typing import Any
from langbot_plugin.api.definition.components.tool.tool import Tool
from langbot_plugin.api.entities.builtin.provider import session as provider_session
from langbot_plugin.api.proxies.query_based_api import QueryBasedAPIProxy
logger = logging.getLogger(__name__)
@@ -94,14 +93,8 @@ class UpdateProfile(Tool):
if not isinstance(previous_value, str):
return "Error: previous_value must be a string."
api = QueryBasedAPIProxy(
query_id=query_id,
plugin_runtime_handler=self.plugin.plugin_runtime_handler,
)
bot_uuid = await api.get_bot_uuid()
query_vars = await api.get_query_vars()
sender_id = str(query_vars.get("sender_id", "") or "")
sender_name = str(query_vars.get("sender_name", "") or "")
bot_uuid = session.bot_uuid or ""
sender_id = str(session.sender_id or "")
session_key, user_key, kb_id, _isolation, _ = await store.resolve_user_context(
session, bot_uuid
@@ -109,10 +102,6 @@ class UpdateProfile(Tool):
if not kb_id:
return "Error: no memory knowledge base configured. Create one first."
pipeline_kbs = await api.list_pipeline_knowledge_bases()
if not any(kb.get("uuid") == kb_id for kb in pipeline_kbs):
return "Error: memory knowledge base is not configured for the current pipeline."
target_scope = self._infer_scope(field, scope)
logger.info(
"[LongTermMemory] update_profile resolved scope: query_id=%s target_scope=%s session_key=%s sender_id=%s value_len=%s",
@@ -165,7 +154,6 @@ class UpdateProfile(Tool):
f"{f' ({fact_key})' if fact_key else ''}: {self._preview_text(str(value))}"
),
sender_id=sender_id,
sender_name=sender_name,
query_id=query_id,
metadata={
"field": field,