chore: T-P-1 工作区收敛——并行会话成果与历史未入库文件整理入库

- 入库历史遗漏源码/测试：router_system 9 模块（agent/executors/inference/knowledge/ memory/planner/skills/trace）、tests 11 个测试文件、config/knowledge 领域知识 - 入库根目录方案文档（v2/v3/可行性×2）、references 文献（arxiv 14-18/cnki_open/ 参考文献清单）、research 论文素材（routerarena/paper/中文文献 PDF） - 前端构建产物刷新（新 hash）；webapp 误写文档删除 - gitignore 增补：deepseek-harness、research/_refs、.mimosa/.zcode、网关日志/pid、临时调试脚本、tests/e2e/node_modules、AI代理功能开发/prefix - 基线确认：318 passed
2026-09-05 08:28:25 +08:00
parent 747d85c3ba
commit ce0f6170d3
82 changed files with 74132 additions and 36 deletions
@@ -0,0 +1,158 @@
+"""RouterArena 适配器最小测试。
+
+覆盖：
+- BaseRouter 接口契约：返回模型名必须在 config.models
+- 路由决策：code→gpt-4o-mini、math→claude-3-haiku、低置信度→mistral-medium
+- 预测文件格式：包含 RouterArena 必填字段
+- Arena Score 公式与官方一致
+"""
+from __future__ import annotations
+
+import json
+import math
+import os
+import sys
+import tempfile
+from pathlib import Path
+
+# 让 tests/ 目录能找到项目根
+sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
+
+from research.routerarena.adapter import (  # noqa: E402
+    DOMAIN_TO_MODEL_SLOT,
+    ESCALATION_MODEL_SLOT,
+    ESExpertRouter,
+    LOW_CONFIDENCE_THRESHOLD,
+)
+from research.routerarena.base_router import BaseRouter  # noqa: E402
+from research.routerarena.local_runner import (  # noqa: E402
+    MODEL_PRICING,
+    build_mock_dataset,
+    compute_arena_score,
+)
+
+
+CONFIG_PATH = str(
+    Path(__file__).resolve().parent.parent
+    / "research"
+    / "routerarena"
+    / "config"
+    / "es-expert.json"
+)
+
+
+def test_base_router_loads_config():
+    """BaseRouter 应能加载 config 并提取 models 列表。"""
+    r = ESExpertRouter(router_name="es-expert", config_path=CONFIG_PATH)
+    assert "gpt-4o-mini" in r.models
+    assert "claude-3-haiku-20240307" in r.models
+    assert "mistral-medium" in r.models
+    assert len(r.models) == 5
+
+
+def test_prediction_in_models():
+    """所有 get_prediction 返回值必须在 config.models 中。"""
+    r = ESExpertRouter(router_name="es-expert", config_path=CONFIG_PATH)
+    samples = [
+        "用 Python 写一个快速排序函数",
+        "Solve x^2 = 4",
+        "Is a non-compete clause enforceable?",
+        "高血压患者日常饮食",
+        "How to calculate ROI on a fund",
+        "Why is the sky blue",
+    ]
+    for q in samples:
+        m = r.get_prediction(q)
+        assert m in r.models, f"{q} -> {m} not in {r.models}"
+
+
+def test_domain_to_slot_mapping_evidence():
+    """映射表与 00_integration_plan.md §3.2 严格一致。"""
+    assert DOMAIN_TO_MODEL_SLOT["code"] == "gpt-4o-mini"
+    assert DOMAIN_TO_MODEL_SLOT["math"] == "claude-3-haiku-20240307"
+    assert DOMAIN_TO_MODEL_SLOT["legal"] == "claude-3-haiku-20240307"
+    assert DOMAIN_TO_MODEL_SLOT["medical"] == "claude-3-haiku-20240307"
+    assert DOMAIN_TO_MODEL_SLOT["finance"] == "claude-3-haiku-20240307"
+    assert DOMAIN_TO_MODEL_SLOT["life"] == "gemini-2.0-flash-001"
+    assert DOMAIN_TO_MODEL_SLOT["education"] == "deepseek-chat"
+    assert DOMAIN_TO_MODEL_SLOT["general"] == "gemini-2.0-flash-001"
+
+
+def test_escalation_logic():
+    """_decide 在低置信度或低质量时升级到 ESCALATION_MODEL_SLOT。"""
+    r = ESExpertRouter(router_name="es-expert", config_path=CONFIG_PATH)
+    # 高置信度 + 高质量 → 主映射
+    assert r._decide("code", 0.95, 0.97) == "gpt-4o-mini"
+    # 低置信度 → 升级
+    assert r._decide("code", 0.50, 0.97) == ESCALATION_MODEL_SLOT
+    # 低质量 → 升级
+    assert r._decide("code", 0.95, 0.50) == ESCALATION_MODEL_SLOT
+    # 未知 domain → general
+    assert r._decide("unknown_xyz", 0.95, 0.97) == "gemini-2.0-flash-001"
+
+
+def test_compute_arena_score_matches_formula():
+    """与 RouterArena run.py L65-87 公式逐项核对（0-1 标度）。"""
+    # 已知：Hybrid Router $0.04/1K, 71.38% acc, leaderboard arena=72.08
+    # 官方公式 raw 范围是 [0, 1]，leaderboard 显示 ×100 标度
+    s = compute_arena_score(0.04, 0.7138, beta=0.1, c_max=200, c_min=0.0044)
+    # raw 期望：~0.7208（×100 = leaderboard 的 72.08）
+    assert 0.715 < s < 0.725, f"expected ~0.7208, got {s:.4f}"
+    # 同时验证 leaderboard 标度对齐
+    assert 71.5 < s * 100 < 72.5, f"×100 期望 ~72.08, got {s*100:.4f}"
+
+
+def test_compute_arena_score_clamping():
+    """成本超 c_max/c_min 应被 clamp。"""
+    s1 = compute_arena_score(0.005, 0.7)
+    s2 = compute_arena_score(0.01, 0.7)
+    # 越便宜分越高（在范围内）
+    assert s1 > s2 > 0
+    # cost = c_max 时 C=0, S=0（公式定义）
+    s_max = compute_arena_score(200, 0.7)
+    assert s_max == 0.0
+    # cost 被 clamp 到 c_min
+    s_under = compute_arena_score(0.001, 0.7)
+    s_at_min = compute_arena_score(0.0044, 0.7)
+    assert abs(s_under - s_at_min) < 1e-9
+
+
+def test_mock_dataset_protocol():
+    """mock 数据集符合 RouterArena 协议字段。"""
+    data = build_mock_dataset()
+    assert len(data) >= 80  # 接近 sub_10 的 809
+    for entry in data:
+        assert "global index" in entry
+        assert "prompt" in entry
+        assert "prompt_formatted" in entry
+        assert "domain" in entry  # 仅本地诊断字段
+        # prompt 非空
+        assert len(entry["prompt"]) > 0
+
+
+def test_prediction_file_schema():
+    """预测文件应包含 RouterArena 必填字段。"""
+    from research.routerarena.local_runner import run_local
+
+    with tempfile.TemporaryDirectory() as tmp:
+        summary = run_local(
+            source="mock",
+            router_name="es-expert",
+            config_path=CONFIG_PATH,
+            do_mock_inference=True,
+            output_dir=tmp,
+        )
+        # summary 含关键字段
+        assert summary["n_queries"] >= 80
+        assert "routing_distribution" in summary
+        assert "mock_accuracy" in summary
+        assert "arena_score_mock" in summary
+        # 预测文件存在 + 格式合规
+        with open(summary["prediction_file"], "r", encoding="utf-8") as f:
+            preds = json.load(f)
+        for p in preds:
+            assert "global index" in p
+            assert "prompt" in p
+            assert "prediction" in p
+            assert "for_optimality" in p
+            assert p["prediction"] in MODEL_PRICING or p["prediction"] is None