alvinfeiandClaude Opus 5.5
4746681efe
Experience reconcile no longer falls back to ADD-all, and fact reconcile no
longer inserts without superseding, when the model call fails, returns empty
content, or returns a reply that is not a JSON object with an ops list. The
write returns success=false, agent_error_code=RECONCILE_FAILED and the
cause in reconcile_error_code (LLM_UNAVAILABLE / EMPTY_RESPONSE /
JSON_PARSE_FAILED), the same as chat.
Each reconciler is split into plan() (retrieve + model decision, no store)
and apply() (store). CodingWriter plans both layers before applying either,
so a decision failure in either layer stores no experience or fact and
supersedes no older fact. reconcile() still runs plan + apply.
An experience reply of {"ops": []} is a valid "no changes" decision and
stores nothing. A non-empty ops list with no recognizable op is a parse
failure. A fact reply of {"ops": []} inserts without superseding.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
290 lines
11 KiB
Python
290 lines
11 KiB
Python
# -*- coding: utf-8 -*-
|
||
"""Reconciler 测试 — ADD / UPDATE / DELETE / SKIP / fallback"""
|
||
|
||
import json
|
||
|
||
import pytest
|
||
|
||
from hy_memory.coding.reconciler import CodingMemoryReconciler
|
||
from hy_memory.coding.types import CodingMemory, CodingMemoryDraft, CodingWriteError
|
||
|
||
from tests.coding._helpers import MockLLMProvider, FailingLLMProvider
|
||
|
||
|
||
def _llm_resp(ops):
|
||
return json.dumps({"ops": ops})
|
||
|
||
|
||
@pytest.mark.asyncio
|
||
class TestReconcilerActions:
|
||
async def test_all_add_on_empty_store(self, coding_store, mock_embed):
|
||
llm = MockLLMProvider(_llm_resp([
|
||
{"draft_idx": 0, "action": "ADD"},
|
||
{"draft_idx": 1, "action": "ADD"},
|
||
]))
|
||
rec = CodingMemoryReconciler(coding_store, mock_embed, llm)
|
||
d1 = CodingMemoryDraft(task="T1", solution="S1", user_id="u1")
|
||
d2 = CodingMemoryDraft(task="T2", solution="S2", user_id="u1")
|
||
ops = await rec.reconcile([d1, d2])
|
||
assert len(ops) == 2
|
||
assert all(op.action == "ADD" for op in ops)
|
||
assert all(op.target_experience_id for op in ops)
|
||
tasks = await coding_store.list_user_tasks("u1", 10)
|
||
assert sorted(tasks) == ["T1", "T2"]
|
||
|
||
async def test_update(self, coding_store, mock_embed):
|
||
# 种入 m1
|
||
await coding_store.insert(CodingMemory(
|
||
experience_id="m1", user_id="u1", agent_id="scope-day-1",
|
||
workspace_id="repo-a", session_id="conversation-1", task="T1",
|
||
search_keys=["old"], solution="old",
|
||
))
|
||
llm = MockLLMProvider(_llm_resp([
|
||
{"draft_idx": 0, "action": "UPDATE",
|
||
"target_experience_id": "m1", "reason": "newer solution"},
|
||
]))
|
||
rec = CodingMemoryReconciler(coding_store, mock_embed, llm)
|
||
d = CodingMemoryDraft(task="T1", search_keys=["new1"], solution="new",
|
||
user_id="u1", agent_id="scope-day-1",
|
||
workspace_id="repo-a", session_id="conversation-1")
|
||
ops = await rec.reconcile([d])
|
||
assert len(ops) == 1 and ops[0].action == "UPDATE"
|
||
got = await coding_store.get_by_id("m1", "u1")
|
||
assert got.solution == "new"
|
||
assert got.search_keys == ["new1"]
|
||
|
||
@pytest.mark.parametrize(
|
||
(
|
||
"old_agent",
|
||
"old_workspace",
|
||
"old_session",
|
||
"new_agent",
|
||
"new_workspace",
|
||
"new_session",
|
||
),
|
||
[
|
||
(
|
||
"scope:same-day",
|
||
"repo-a",
|
||
"conversation-a",
|
||
"scope:same-day",
|
||
"repo-a",
|
||
"conversation-b",
|
||
),
|
||
(
|
||
"scope:2026-10-18",
|
||
"repo-a",
|
||
"conversation-a",
|
||
"scope:2026-10-19",
|
||
"repo-a",
|
||
"conversation-a",
|
||
),
|
||
(
|
||
"shared-scope",
|
||
"repo-a",
|
||
"conversation-a",
|
||
"shared-scope",
|
||
"repo-b",
|
||
"conversation-a",
|
||
),
|
||
],
|
||
)
|
||
async def test_update_target_must_match_frozen_authority_scope(
|
||
self,
|
||
coding_store,
|
||
mock_embed,
|
||
old_agent,
|
||
old_workspace,
|
||
old_session,
|
||
new_agent,
|
||
new_workspace,
|
||
new_session,
|
||
):
|
||
"""Near duplicates cannot cross conversation, date, or workspace authority."""
|
||
await coding_store.insert(CodingMemory(
|
||
experience_id="old-target", user_id="u1", agent_id=old_agent,
|
||
workspace_id=old_workspace, session_id=old_session,
|
||
task="fix flaky release", solution="old solution",
|
||
))
|
||
llm = MockLLMProvider(_llm_resp([
|
||
{
|
||
"draft_idx": 0,
|
||
"action": "UPDATE",
|
||
"target_experience_id": "old-target",
|
||
"reason": "near duplicate",
|
||
},
|
||
]))
|
||
rec = CodingMemoryReconciler(coding_store, mock_embed, llm)
|
||
draft = CodingMemoryDraft(
|
||
task="fix flaky release",
|
||
solution="new solution",
|
||
user_id="u1",
|
||
agent_id=new_agent,
|
||
workspace_id=new_workspace,
|
||
session_id=new_session,
|
||
)
|
||
|
||
ops = await rec.reconcile([draft])
|
||
|
||
old = await coding_store.get_by_id("old-target", "u1")
|
||
assert old is not None
|
||
assert old.solution == "old solution"
|
||
assert old.agent_id == old_agent
|
||
assert old.workspace_id == old_workspace
|
||
assert old.session_id == old_session
|
||
assert len(ops) == 1
|
||
assert ops[0].action == "ADD"
|
||
assert ops[0].target_experience_id != "old-target"
|
||
|
||
@pytest.mark.parametrize("legacy_agent", ["", "default_agent", "scope:legacy"])
|
||
async def test_legacy_target_without_conversation_falls_back_to_add(
|
||
self, coding_store, mock_embed, legacy_agent
|
||
):
|
||
await coding_store.insert(CodingMemory(
|
||
experience_id="legacy-target",
|
||
user_id="u1",
|
||
agent_id=legacy_agent,
|
||
session_id=None,
|
||
workspace_id="repo-a",
|
||
task="upgrade dependency",
|
||
solution="legacy solution",
|
||
))
|
||
llm = MockLLMProvider(_llm_resp([
|
||
{
|
||
"draft_idx": 0,
|
||
"action": "UPDATE",
|
||
"target_experience_id": "legacy-target",
|
||
},
|
||
]))
|
||
rec = CodingMemoryReconciler(coding_store, mock_embed, llm)
|
||
draft = CodingMemoryDraft(
|
||
task="upgrade dependency",
|
||
solution="current solution",
|
||
user_id="u1",
|
||
agent_id=legacy_agent,
|
||
session_id="current-conversation",
|
||
workspace_id="repo-a",
|
||
)
|
||
|
||
ops = await rec.reconcile([draft])
|
||
|
||
legacy = await coding_store.get_by_id("legacy-target", "u1")
|
||
assert legacy is not None
|
||
assert legacy.solution == "legacy solution"
|
||
assert legacy.session_id is None
|
||
assert [op.action for op in ops] == ["ADD"]
|
||
|
||
async def test_skip(self, coding_store, mock_embed):
|
||
await coding_store.insert(CodingMemory(
|
||
experience_id="m1", user_id="u1", task="X", solution="Y",
|
||
session_id="conversation-1",
|
||
))
|
||
llm = MockLLMProvider(_llm_resp([
|
||
{"draft_idx": 0, "action": "SKIP", "reason": "duplicate"},
|
||
]))
|
||
rec = CodingMemoryReconciler(coding_store, mock_embed, llm)
|
||
d = CodingMemoryDraft(task="X", solution="Y",
|
||
user_id="u1", session_id="conversation-1")
|
||
ops = await rec.reconcile([d])
|
||
assert len(ops) == 1 and ops[0].action == "SKIP"
|
||
# store 不变
|
||
tasks = await coding_store.list_user_tasks("u1", 10)
|
||
assert tasks == ["X"]
|
||
|
||
async def test_add_with_delete_multi_op(self, coding_store, mock_embed):
|
||
# 旧记忆要被 DELETE
|
||
await coding_store.insert(CodingMemory(
|
||
experience_id="m_dep", user_id="u1", task="use old.sh",
|
||
solution="old script", session_id="conversation-1",
|
||
))
|
||
llm = MockLLMProvider(_llm_resp([
|
||
{"draft_idx": 0, "action": "ADD"},
|
||
{"draft_idx": 0, "action": "DELETE", "target_experience_id": "m_dep",
|
||
"reason": "user explicitly deprecated old.sh"},
|
||
]))
|
||
rec = CodingMemoryReconciler(coding_store, mock_embed, llm)
|
||
d = CodingMemoryDraft(task="use new CLI", solution="new way",
|
||
user_id="u1", session_id="conversation-1")
|
||
ops = await rec.reconcile([d])
|
||
assert sorted(op.action for op in ops) == ["ADD", "DELETE"]
|
||
# 旧的没了
|
||
assert await coding_store.get_by_id("m_dep", "u1") is None
|
||
# 新的进了
|
||
tasks = await coding_store.list_user_tasks("u1", 10)
|
||
assert "use new CLI" in tasks
|
||
assert "use old.sh" not in tasks
|
||
|
||
|
||
@pytest.mark.asyncio
|
||
class TestReconcilerFallback:
|
||
@pytest.mark.parametrize("llm,cause", [
|
||
(FailingLLMProvider(), "LLM_UNAVAILABLE"),
|
||
(MockLLMProvider(""), "EMPTY_RESPONSE"),
|
||
(MockLLMProvider("not json"), "JSON_PARSE_FAILED"),
|
||
(MockLLMProvider("{}"), "JSON_PARSE_FAILED"),
|
||
(MockLLMProvider('{"ops": [{"draft_idx": 0, "action": "MERGE"}]}'),
|
||
"JSON_PARSE_FAILED"),
|
||
])
|
||
async def test_decision_failure_raises_and_stores_nothing(
|
||
self, coding_store, mock_embed, llm, cause,
|
||
):
|
||
"""LLM 失败 / 空回复 / 解析不出不再回退成 ADD-all：抛 RECONCILE_FAILED。"""
|
||
rec = CodingMemoryReconciler(coding_store, mock_embed, llm)
|
||
d1 = CodingMemoryDraft(task="T1", solution="S", user_id="u1")
|
||
d2 = CodingMemoryDraft(task="T2", solution="S", user_id="u1")
|
||
with pytest.raises(CodingWriteError) as exc:
|
||
await rec.reconcile([d1, d2])
|
||
assert exc.value.error_code == "RECONCILE_FAILED"
|
||
assert exc.value.cause == cause
|
||
assert await coding_store.list_user_tasks("u1") == []
|
||
|
||
async def test_valid_empty_ops_is_a_no_change_decision(
|
||
self, coding_store, mock_embed,
|
||
):
|
||
"""{"ops": []} 与 chat 的 [] 同义：成功、什么都不存。"""
|
||
rec = CodingMemoryReconciler(
|
||
coding_store, mock_embed, MockLLMProvider(_llm_resp([])),
|
||
)
|
||
d = CodingMemoryDraft(task="T", solution="S", user_id="u1")
|
||
ops = await rec.reconcile([d])
|
||
assert ops == []
|
||
assert await coding_store.list_user_tasks("u1") == []
|
||
|
||
async def test_missing_draft_idx_fallback_add(self, coding_store, mock_embed):
|
||
# LLM 只处理了 draft 0，draft 1 漏掉
|
||
llm = MockLLMProvider(_llm_resp([{"draft_idx": 0, "action": "ADD"}]))
|
||
rec = CodingMemoryReconciler(coding_store, mock_embed, llm)
|
||
d1 = CodingMemoryDraft(task="T1", solution="S", user_id="u1")
|
||
d2 = CodingMemoryDraft(task="T2", solution="S", user_id="u1")
|
||
ops = await rec.reconcile([d1, d2])
|
||
# T1 来自 LLM ADD；T2 来自 fallback ADD
|
||
actions = [op.action for op in ops]
|
||
assert actions.count("ADD") == 2
|
||
|
||
async def test_invalid_op_filtered(self, coding_store, mock_embed):
|
||
# UPDATE 缺 target_experience_id 应被丢弃，draft_idx=0 再走 fallback ADD
|
||
llm = MockLLMProvider(_llm_resp([
|
||
{"draft_idx": 0, "action": "UPDATE"}, # 缺 target → 丢弃
|
||
]))
|
||
rec = CodingMemoryReconciler(coding_store, mock_embed, llm)
|
||
d = CodingMemoryDraft(task="T", solution="S", user_id="u1")
|
||
ops = await rec.reconcile([d])
|
||
# fallback ADD
|
||
assert any(op.action == "ADD" for op in ops)
|
||
|
||
async def test_empty_drafts(self, coding_store, mock_embed):
|
||
rec = CodingMemoryReconciler(coding_store, mock_embed, MockLLMProvider("{}"))
|
||
ops = await rec.reconcile([])
|
||
assert ops == []
|
||
|
||
async def test_plan_does_not_store(self, coding_store, mock_embed):
|
||
"""plan() 只做检索 + 决策；apply() 之前库里什么都没有。"""
|
||
llm = MockLLMProvider(_llm_resp([{"draft_idx": 0, "action": "ADD"}]))
|
||
rec = CodingMemoryReconciler(coding_store, mock_embed, llm)
|
||
d = CodingMemoryDraft(task="T", solution="S", user_id="u1")
|
||
plan = await rec.plan([d])
|
||
assert [op.action for op in plan.ops] == ["ADD"]
|
||
assert await coding_store.list_user_tasks("u1") == []
|
||
await rec.apply(plan)
|
||
assert await coding_store.list_user_tasks("u1") == ["T"]
|