# ============================================================ # 黄金测试：四层上下文策略（plan.md §4.8 / 矩阵 64 行） # 四层组装可检查 / 预算溢出可预测拒绝 / 摘要可溯源 / pin 生效 # ============================================================ from __future__ import annotations import pytest from server.agent_core.context_policy import ( ContextAssembly, ContextBudget, ContextBudgetExceeded, assemble_context, estimate_tokens, get_policy, pin_message, scroll_summary, unpin_message, ) def _store_data() -> dict: """工作区快照：项目 + 会话 + 带 id 的消息。""" return { "systemPrompt": "你是 APS 排产智能体：提议权，写操作必须经门禁。", "projects": [ { "id": "p1", "name": "青岛Q3排产", "scopeLabel": "青岛工厂/总装车间", "sharedContext": ["本项目用 V3 参数版本", "以 V20260701-005 为基准版本"], "archived": False, }, ], "sessions": [ {"id": "s1", "projectId": "p1", "title": "本周主排产", "status": "running"}, ], "messages": { "s1": [ {"id": "m0", "role": "user", "text": "验收标准：插单必须满足交期优先"}, {"id": "m1", "role": "agent", "text": "好的，按交期优先试排"}, {"id": "m2", "role": "user", "text": "再看看产能是否足够"}, {"id": "m3", "role": "agent", "text": "产能利用率 92%，足够"}, ], }, } def test_assemble_four_layers_inspectable(): sd = _store_data() sd["ragResults"] = [{"assetId": "kb_1", "title": "换线标准SOP", "version": "2", "content": "换线前 30 分钟通知"}] assembly = assemble_context(sd, "s1", "换线需要多久", ContextBudget()) assert isinstance(assembly, ContextAssembly) # 四层齐全且可检查 assert list(assembly.layers.keys()) == ["fixed", "project", "session", "retrieval"] assert "提议权" in assembly.layer("fixed") assert "青岛Q3排产" in assembly.layer("project") assert "V3 参数版本" in assembly.layer("project") assert "验收标准" in assembly.layer("session") assert "kb_1" in assembly.layer("retrieval") # 整体文本按固定/项目/会话/检索拼接，可注入 prompt text = assembly.text() assert "[fixed]" in text and "[project]" in text assert "[session]" in text and "[retrieval]" in text # 用量与预算一一对应（可检查） assert assembly.usage == {k: estimate_tokens(assembly.layers[k]) for k in assembly.layers} assert assembly.budgets == { "fixed": 1500, "project": 3000, "session": 6000, "retrieval": 4000, } def test_budget_overflow_predictable_rejection(): sd = _store_data() sd["messages"]["s1"].append({"id": "m10", "role": "user", "text": "排产" * 120}) budget = ContextBudget(session=50) def expect() -> ContextBudgetExceeded: with pytest.raises(ContextBudgetExceeded) as exc_info: assemble_context(sd, "s1", None, budget) return exc_info.value first = expect() assert first.layer == "session" assert first.required > first.budget == 50 # 可预测：同一输入重复触发得到完全一致的层/用量/限额 second = expect() assert (second.layer, second.required, second.budget) == (first.layer, first.required, first.budget) # 检索层独立限额：RAG 命中过长 -> 拒绝在 retrieval 层 sd2 = _store_data() sd2["ragResults"] = [{"assetId": "kb_1", "title": "长文", "content": "换线" * 200}] with pytest.raises(ContextBudgetExceeded) as exc_info: assemble_context(sd2, "s1", None, ContextBudget(retrieval=10)) assert exc_info.value.layer == "retrieval" # 提升预算后组装成功（预算控制可逆、可预测） ok = assemble_context(sd2, "s1", None, ContextBudget(retrieval=10000)) assert "kb_1" in ok.layer("retrieval") def test_context_budget_totals_and_token_estimate(): budget = ContextBudget(fixed=100, session=200) assert budget.layer_limit("fixed") == 100 assert budget.layer_limit("session") == 200 assert budget.total() == 100 + 3000 + 200 + 4000 parsed = ContextBudget.from_dict({"fixed": "10", "project": 20, "bogus": 999}) assert (parsed.fixed, parsed.project) == (10, 20) with pytest.raises(ValueError): budget.layer_limit("bogus") # 确定性 token 估算：CJK 1 token/字，其余 4 字符 1 token assert estimate_tokens("你好ab") == 2 + 1 assert estimate_tokens("") == 0 def test_scroll_summary_traceable_to_source_messages(): sd = _store_data() s1 = scroll_summary( sd, "s1", "验收标准：插单必须满足交期优先；已决策采用方案B", source_message_ids=["m0", "m1"], decision_points=["采用方案B"], open_items=["未决：产能上限"], key_numbers=["利用率 92%"], by="agent", ) assert s1["sourceMessageIds"] == ["m0", "m1"] assert s1["decisionPoints"] == ["采用方案B"] # 滚动：新摘要压缩更早对话，supersedes 链指向旧摘要，旧摘要入历史 s2 = scroll_summary(sd, "s1", "插单已评估完毕，等待确认", source_message_ids=["m2", "m3"]) assert s2["supersedes"] == s1["summaryId"] assert s2["generation"] == 2 policy = get_policy(sd, "s1") assert policy["summary"]["summaryId"] == s2["summaryId"] assert len(policy["summaries"]) == 1 assert policy["summaries"][0]["sourceMessageIds"] == ["m0", "m1"] # 组装后会话层注入摘要，且摘要可溯源到原消息 id assembly = assemble_context(sd, "s1", None, ContextBudget()) session_text = assembly.layer("session") assert "插单已评估完毕" in session_text assert "来源消息：m2、m3" in session_text assert assembly.summary is not None and assembly.summary["summaryId"] == s2["summaryId"] # 空摘要拒绝（fail closed） with pytest.raises(ValueError): scroll_summary(sd, "s1", " ") def test_pin_message_survives_window_and_unpin(): sd = _store_data() sd["messages"]["s1"] = [ {"id": f"m{i}", "role": "user" if i % 2 == 0 else "agent", "text": f"消息{i}"} for i in range(20) ] pinned = pin_message(sd, "s1", "m0", note="验收标准不可淘汰") assert pinned["messageId"] == "m0" # 幂等：重复钉住不产生重复项 pin_message(sd, "s1", "m0", note="验收标准不可淘汰") assert len(get_policy(sd, "s1")["pinned"]) == 1 assembly = assemble_context(sd, "s1", None, ContextBudget(), window=5) session_text = assembly.layer("session") # pin 生效：窗口外的最早消息仍注入 assert "消息0" in session_text assert "（备注：验收标准不可淘汰）" in session_text # 最近 N 轮原文在窗口内 assert "消息15" in session_text # 窗口外未钉住的消息被淘汰 assert "消息10" not in session_text assert [p["messageId"] for p in assembly.pinned] == ["m0"] # 解除钉住：恢复窗口淘汰 assert unpin_message(sd, "s1", "m0") is True after = assemble_context(sd, "s1", None, ContextBudget(), window=5) assert "消息0" not in after.layer("session") assert unpin_message(sd, "s1", "m0") is False # 钉住不存在的消息：显式失败 with pytest.raises(ValueError): pin_message(sd, "s1", "m_no_such") def test_resolved_refs_render_into_retrieval_layer(): """方向 A 内联：会话引用解析结果按需注入检索层（L-检索）。""" sd = _store_data() sd["resolvedRefs"] = [ {"kind": "session", "target_id": "sess_a", "snapshot_at": "2026-08-02 10:30"}, {"kind": "version", "target_id": "V20260716-003", "snapshot_at": "2026-08-02 10:30"}, ] assembly = assemble_context(sd, "s1", None, ContextBudget()) retrieval_text = assembly.layer("retrieval") assert "[引用 session:sess_a @2026-08-02 10:30]" in retrieval_text assert "[引用 version:V20260716-003 @2026-08-02 10:30]" in retrieval_text # ============================================================ # 越权上下文测试（矩阵 64 行剩余项 · 方向 L）： # 访问其他项目/会话的上下文 -> fail closed；预算超限拒绝可预测。 # ============================================================ def test_unauthorized_other_project_session_fails_closed(): """越权上下文：会话归属项目不在可见项目列表 -> 显式拒绝（fail closed）。 可见快照由租户/成员过滤生成（ProjectStore.snapshot 只返回可见会话）， 因此越权会话要么在快照中缺失（session not found），要么其项目不可访问 （project not accessible）——两条路径都绝不允许组装出任何一层上下文。 """ sd = _store_data() sd["projects"].append({ "id": "p2", "name": "别厂项目", "scopeLabel": "外部工厂/总装", "sharedContext": ["别厂参数版本"], "archived": False, }) sd["sessions"].append({"id": "s2", "projectId": "p2", "title": "别厂会话", "status": "running"}) sd["messages"]["s2"] = [ {"id": "x0", "role": "user", "text": "机密：别厂排产方案不可外泄"}, {"id": "x1", "role": "agent", "text": "别厂关键路径已锁定"}, ] # 路径 1：越权会话在可见快照中缺失（等同无权访问）——先于预算检查拒绝 visible = { **sd, "projects": sd["projects"][:1], "sessions": sd["sessions"][:1], "messages": {"s1": sd["messages"]["s1"]}, } with pytest.raises(ValueError) as exc_info: assemble_context(visible, "s2", None, ContextBudget(session=10 ** 9)) assert "session not found" in str(exc_info.value) # 路径 2：会话在快照中但其项目不在可见项目列表——同样显式拒绝 half_visible = { **sd, "projects": sd["projects"][:1], # p2 对当前用户不可访问 } with pytest.raises(ValueError) as exc_info2: assemble_context(half_visible, "s2", None, ContextBudget()) assert "project not accessible" in str(exc_info2.value) # 拒绝是可预测的：同一输入重复触发，异常信息一致 with pytest.raises(ValueError) as exc_info3: assemble_context(half_visible, "s2", None, ContextBudget()) assert str(exc_info3.value) == str(exc_info2.value) def test_authorized_session_never_leaks_other_session_context(): """隔离：授权会话 s1 的组装绝不混入 s2 的消息/摘要（越权内容零泄漏）。""" sd = _store_data() sd["projects"].append({ "id": "p2", "name": "别厂项目", "scopeLabel": "外部工厂", "sharedContext": [], "archived": False, }) sd["sessions"].append({"id": "s2", "projectId": "p2", "title": "别厂会话", "status": "running"}) sd["messages"]["s2"] = [ {"id": "x0", "role": "user", "text": "机密：别厂排产方案不可外泄"}, {"id": "x1", "role": "agent", "text": "别厂关键路径已锁定"}, ] scroll_summary(sd, "s2", "别厂滚动摘要：方案不可外泄", source_message_ids=["x0", "x1"]) assembly = assemble_context(sd, "s1", None, ContextBudget()) blob = assembly.text() assert "机密" not in blob assert "别厂" not in blob assert "x0" not in blob and "x1" not in blob # 会话层只带 s1 自己的策略/消息 assert assembly.summary is None or "别厂" not in assembly.summary.get("text", "") assert get_policy(sd, "s1") == {} def test_budget_overflow_predictable_rejection_diagnostics(): """预算超限拒绝可预测：异常携带 layer/required/budget，同一输入结果一致。 补齐「预算超限拒绝可预测」的验收：不仅拒绝，还给出可检查的诊断字段， 且重复触发得到完全相同的层/用量/限额（确定性）。 """ sd = _store_data() sd["messages"]["s1"].append({"id": "m20", "role": "user", "text": "排产" * 200}) budget = ContextBudget(session=50) with pytest.raises(ContextBudgetExceeded) as exc_info: assemble_context(sd, "s1", None, budget) first = exc_info.value assert (first.layer, first.budget) == ("session", 50) assert first.required > 50 assert str(first) == f"context layer 'session' needs {first.required} tokens, budget 50" with pytest.raises(ContextBudgetExceeded) as exc_info2: assemble_context(sd, "s1", None, budget) second = exc_info2.value assert (second.layer, second.required, second.budget) == ( first.layer, first.required, first.budget, )