games-development-ai/tier2/gen-worker/tests/test_jsonl_sink.py

"""test_jsonl_sink.py —— U-C1a JSONL sink 落盘单测(TDD:先红后绿)。

跑:python3 tests/test_jsonl_sink.py(无 pytest,__main__ 跑全部断言)。
验 JsonlFileSink:
  1. emit 三条 trace step → trace.jsonl 落盘;
  2. 每行是合法 JSON;
  3. 五字段(traceId / step / cost / verdict / timestamp)齐全;
  4. 目录不存在 → 自动创建;
  5. 写失败(不可写路径) → 只告警、不抛,不中断调用方。
"""
import sys
import os
import json
import tempfile
from pathlib import Path

_HERE = os.path.dirname(os.path.abspath(__file__))
_GW = os.path.dirname(_HERE)  # gen-worker/
sys.path.insert(0, _GW)

from observability.trace import JsonlFileSink, make_jsonl_sink, TraceAdapter  # noqa: E402


# ── 测试一:核心落盘 + 五字段完整性 ──────────────────────────────────────────────
def test_jsonl_sink_creates_file_and_lines():
    """emit 三条 trace step → trace.jsonl 落盘、每行合法 JSON、五字段齐、内容对。"""
    with tempfile.TemporaryDirectory() as tmpdir:
        out = Path(tmpdir) / "trace.jsonl"
        sink = JsonlFileSink(out)

        # 用 TraceAdapter + dict 桩事件(无需 AgentScope 真环境)驱动 sink。
        adapter = TraceAdapter(trace_id="test-trace-001", sink=sink)
        fake_events = [
            # ReplyStartEvent → 落 raw.reply_boundary / agent_name
            {"type": "ReplyStartEvent", "created_at": "2026-06-29T10:00:00",
             "reply_id": "r1", "name": "writer"},
            # ModelCallEndEvent → cost.tokens 非空
            {"type": "ModelCallEndEvent", "created_at": "2026-06-29T10:00:01",
             "input_tokens": 100, "output_tokens": 50},
            # ToolResultEndEvent → verdict=success
            {"type": "ToolResultEndEvent", "created_at": "2026-06-29T10:00:02",
             "state": "success"},
        ]
        for e in fake_events:
            adapter.ingest(e)

        # 断言①:文件已落盘
        assert out.exists(), f"trace.jsonl 应存在,但未落盘:{out}"

        lines = out.read_text(encoding="utf-8").strip().split("\n")
        # 断言②:三条事件 → 三行
        assert len(lines) == 3, f"应有 3 行,实际 {len(lines)} 行:\n" + "\n".join(lines)

        # 断言③:每行合法 JSON + 五字段齐
        CORE_FIELDS = {"traceId", "step", "cost", "verdict", "timestamp"}
        for i, line in enumerate(lines):
            obj = json.loads(line)  # 若非合法 JSON 此处抛
            missing = CORE_FIELDS - set(obj.keys())
            assert not missing, f"第 {i} 行缺五字段 {missing}:{line}"
            assert obj["traceId"] == "test-trace-001", (
                f"第 {i} 行 traceId 错(期望 test-trace-001,实际 {obj['traceId']})")
            assert obj["step"] == i, f"第 {i} 行 step 错(期望 {i},实际 {obj['step']})"

        # 断言④:ModelCallEnd 步 cost 非空且 token 字段正确
        second = json.loads(lines[1])
        assert second["cost"] is not None, "ModelCallEnd 步 cost 应非空"
        assert second["cost"]["tokens"]["in"] == 100, "input_tokens 应为 100"
        assert second["cost"]["tokens"]["out"] == 50, "output_tokens 应为 50"

        # 断言⑤:ToolResultEnd 步 verdict=success
        third = json.loads(lines[2])
        assert third["verdict"] == "success", (
            f"ToolResultEnd 步 verdict 应为 success,实际 {third['verdict']}")

        print(f"  [ok] lines={len(lines)}, traceId={json.loads(lines[0])['traceId']}, "
              f"cost.tokens.in={second['cost']['tokens']['in']}, verdict={third['verdict']}")


# ── 测试二:嵌套目录自动创建 ─────────────────────────────────────────────────────
def test_jsonl_sink_auto_creates_dir():
    """目录不存在 → sink 自动创建嵌套目录;emit 成功落盘。"""
    with tempfile.TemporaryDirectory() as tmpdir:
        out = Path(tmpdir) / "subdir" / "nested" / "trace.jsonl"
        sink = make_jsonl_sink(out)
        step = {"traceId": "t2", "step": 0, "cost": None, "verdict": None,
                "timestamp": "2026-06-29T00:00:00",
                "ext": {"raw": {"event": "ReplyStartEvent"}}}
        sink(step)

        assert out.exists(), f"嵌套目录下 trace.jsonl 应自动创建:{out}"
        obj = json.loads(out.read_text(encoding="utf-8").strip())
        assert obj["traceId"] == "t2", f"traceId 错:{obj['traceId']}"
        print(f"  [ok] auto-mkdir:{out}")


# ── 测试三:写失败只告警、不抛 ────────────────────────────────────────────────────
def test_jsonl_sink_write_failure_no_raise():
    """写失败(不可写路径) → 只 print 告警,绝不抛,不中断调用方。"""
    # /proc/nonexistent/ 在 macOS 下不存在且不可写,触发写失败场景。
    bad_path = Path("/proc/nonexistent_for_test_sink/trace.jsonl")
    sink = JsonlFileSink(bad_path)
    try:
        sink({"traceId": "t3", "step": 0, "cost": None, "verdict": None,
              "timestamp": "", "ext": {"raw": {"event": "X"}}})
        print("  [ok] write-fail → 只告警,不抛")
    except Exception as e:
        raise AssertionError(f"sink 写失败时不应抛异常,但抛了:{e}") from e


# ── 入口 ────────────────────────────────────────────────────────────────────────
if __name__ == "__main__":
    tests = [
        ("test_jsonl_sink_creates_file_and_lines", test_jsonl_sink_creates_file_and_lines),
        ("test_jsonl_sink_auto_creates_dir", test_jsonl_sink_auto_creates_dir),
        ("test_jsonl_sink_write_failure_no_raise", test_jsonl_sink_write_failure_no_raise),
    ]
    passed = failed = 0
    for name, fn in tests:
        try:
            print(f"[RUN] {name}")
            fn()
            print(f"[PASS] {name}")
            passed += 1
        except Exception as exc:
            import traceback
            print(f"[FAIL] {name}: {exc}")
            traceback.print_exc()
            failed += 1
    print(f"\n结果:{passed} 通过 / {failed} 失败")
    sys.exit(0 if failed == 0 else 1)