ai-agent-book 精选快照（<2MB 代码与文档，来自 github.com/bojieli/ai-agent-book）

chapter6/end-to-end-speech/tests/conftest.py

@@ -0,0 +1,7 @@
+import sys
+from pathlib import Path
+
+
+PROJECT_ROOT = Path(__file__).resolve().parents[1]
+if str(PROJECT_ROOT) not in sys.path:
+    sys.path.insert(0, str(PROJECT_ROOT))

chapter6/end-to-end-speech/tests/test_demo.py

@@ -0,0 +1,16 @@
+import pytest
+
+from demo import load_cases, matches_expected
+
+
+def test_expected_match_uses_word_boundaries():
+    assert matches_expected("The answer is 79.", ["79"])
+    assert matches_expected("FAST", ["fast"])
+    assert not matches_expected("The answer is 179.", ["79"])
+
+
+def test_case_manifest_validation(tmp_path):
+    empty = tmp_path / "cases.json"
+    empty.write_text("[]", encoding="utf-8")
+    with pytest.raises(ValueError, match="Malformed"):
+        load_cases(empty)

chapter6/end-to-end-speech/tests/test_speech_model.py

@@ -0,0 +1,25 @@
+from pathlib import Path
+
+import pytest
+
+from speech_model import MiniCPMOClient, sha256_file
+
+
+def test_sha256_file(tmp_path):
+    path = tmp_path / "sample"
+    path.write_bytes(b"abc")
+    assert sha256_file(path) == "ba7816bf8f01cfea414140de5dae2223b00361a396177a9cb410ff61f20015ad"
+
+
+def test_inference_requires_loaded_model():
+    client = MiniCPMOClient(enable_tts=False)
+    with pytest.raises(RuntimeError, match=r"Call load\(\)"):
+        client.infer_text("hello")
+
+
+def test_speech_output_requires_tts(monkeypatch, tmp_path):
+    client = MiniCPMOClient(enable_tts=False)
+    client.model = object()
+    monkeypatch.setattr(client, "load_audio", lambda _: [0.0])
+    with pytest.raises(RuntimeError, match="enable_tts=False"):
+        client.infer_audio(tmp_path / "input.wav", "answer", output_audio_path=tmp_path / "out.wav")

chapter6/end-to-end-speech/tests/test_validate_evidence.py

@@ -0,0 +1,53 @@
+import json
+import wave
+from pathlib import Path
+
+from speech_model import MODEL_ID, MODEL_REVISION, sha256_file
+from validate_evidence import validate
+
+
+def test_complete_evidence_passes(tmp_path):
+    wav = tmp_path / "answer.wav"
+    with wave.open(str(wav), "wb") as handle:
+        handle.setnchannels(1)
+        handle.setsampwidth(2)
+        handle.setframerate(24000)
+        handle.writeframes(b"\x00\x00" * 2400)
+    arm = {"response": "ok", "transcript": "spoken words"}
+    evidence = {
+        "experiment": "6-5",
+        "model": {
+            "model_id": MODEL_ID,
+            "model_revision": MODEL_REVISION,
+            "cuda_available": True,
+            "init_audio": True,
+        },
+        "protocol": {"enable_thinking": False},
+        "cases": [
+            {"direct": {"response": "ok"}, "self_cascade": arm}
+            for _ in range(4)
+        ],
+        "speech_output": {
+            "output_audio": {
+                "path": str(wav),
+                "sha256": sha256_file(wav),
+                "sample_rate_hz": 24000,
+                "duration_seconds": 0.1,
+            }
+        },
+        "implementation_sha256": {
+            "requirements.txt": sha256_file(
+                Path(__file__).resolve().parents[1] / "requirements.txt"
+            )
+        },
+        "external_api_calls": 0,
+    }
+    path = tmp_path / "evidence.json"
+    path.write_text(json.dumps(evidence), encoding="utf-8")
+    assert validate(path)["passed"] is True
+
+
+def test_missing_direct_response_fails(tmp_path):
+    path = tmp_path / "evidence.json"
+    path.write_text(json.dumps({"experiment": "6-5", "cases": []}), encoding="utf-8")
+    assert validate(path)["passed"] is False