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

chapter9/prompt-auto-optimization/tests/conftest.py

@@ -0,0 +1,9 @@
+"""Test import bootstrap for the prompt-auto-optimization experiment."""
+
+from pathlib import Path
+import sys
+
+
+EXPERIMENT_ROOT = Path(__file__).resolve().parents[1]
+if str(EXPERIMENT_ROOT) not in sys.path:
+    sys.path.insert(0, str(EXPERIMENT_ROOT))

chapter9/prompt-auto-optimization/tests/test_apply_one_null.py

@@ -0,0 +1,21 @@
+from coding_agent import _apply_one
+
+
+def test_apply_one_null_old_str():
+    content, err = _apply_one("hello world", None, "x")
+    assert content == "hello world"
+    assert err is not None
+    assert "null" in err
+
+
+def test_apply_one_null_new_str():
+    content, err = _apply_one("hello world", "hello", None)
+    assert content == "hello world"
+    assert err is not None
+    assert "null" in err
+
+
+def test_apply_one_normal():
+    content, err = _apply_one("hello world", "hello", "hi")
+    assert err is None
+    assert content == "hi world"

chapter9/prompt-auto-optimization/tests/test_baggage_policy_null.py

@@ -0,0 +1,22 @@
+import json
+
+from airline_env import _run_tool
+
+
+def test_baggage_policy_null_cabin():
+    # 模型显式传 {"cabin": null}：应回退到经济舱默认，而不是 TypeError
+    args = json.loads('{"cabin": null}')
+    result = json.loads(_run_tool("get_baggage_policy", args))
+    assert result["cabin"] == "经济舱"
+    assert result["free_allowance"] == "20kg"
+
+
+def test_baggage_policy_missing_cabin():
+    result = json.loads(_run_tool("get_baggage_policy", {}))
+    assert result["cabin"] == "经济舱"
+    assert result["free_allowance"] == "20kg"
+
+
+def test_baggage_policy_business_cabin():
+    result = json.loads(_run_tool("get_baggage_policy", {"cabin": "商务舱"}))
+    assert result["free_allowance"] == "30kg"

chapter9/prompt-auto-optimization/tests/test_edits_list_null.py

@@ -0,0 +1,27 @@
+from coding_agent import _apply_edits_from_args, _apply_one
+
+
+def test_null_edits_like_empty():
+    working, applied, errors, warnings, edits = _apply_edits_from_args("hello world", {"edits": None})
+    assert working == "hello world"
+    assert applied == 0
+    assert errors == []
+    assert warnings == []
+    assert edits == []
+
+
+def test_apply_edits_normal():
+    working, applied, errors, warnings, edits = _apply_edits_from_args(
+        "hello world",
+        {"edits": [{"old_str": "hello", "new_str": "hi"}]},
+    )
+    assert working == "hi world"
+    assert applied == 1
+    assert errors == []
+    assert warnings == []
+    assert len(edits) == 1
+
+
+def test_apply_one_still_rejects_null_strings():
+    content, err = _apply_one("hello", None, "x")
+    assert err is not None

chapter9/prompt-auto-optimization/tests/test_learning_and_release.py

@@ -0,0 +1,57 @@
+import unittest
+
+from learning_signal import diagnose_failures, format_learning_signal
+from release_gate import build_candidate_manifest, evaluate_release_gate
+
+
+def evaluation(holdout=(2, 2), boundary=(0, 2)):
+    return {
+        "holdout": holdout,
+        "boundary": boundary,
+        "results": [
+            {
+                "id": "B1",
+                "group": "boundary",
+                "correct": False,
+                "transferred": True,
+                "should_transfer": False,
+                "handled": None,
+                "note": "不应转接：却转接了",
+            }
+        ],
+    }
+
+
+class LearningAndReleaseTest(unittest.TestCase):
+    def test_diagnosis_comes_from_failed_case(self):
+        report = diagnose_failures(evaluation())
+        self.assertEqual(["B1"], report["source_case_ids"])
+        self.assertEqual("system_prompt.transfer_policy", report["scope"])
+        self.assertEqual("B1", report["dimensions"]["compliant_flexibility"][0]["case_id"])
+        self.assertIn("Source cases: B1", format_learning_signal(report))
+
+    def test_release_requires_improvement_and_no_regression(self):
+        signal = diagnose_failures(evaluation())
+        manifest = build_candidate_manifest({
+            "diff": "+ new rule", "rationale": "narrow transfer",
+            "edits": [{"old_str": "old rule", "new_str": "new rule"}],
+        }, signal)
+        accepted = evaluate_release_gate(evaluation(), evaluation(boundary=(1, 2)), manifest)
+        self.assertTrue(accepted["accepted"])
+        self.assertEqual("release_to_canary", accepted["decision"])
+
+        regressed = evaluate_release_gate(
+            evaluation(holdout=(2, 2)), evaluation(holdout=(1, 2), boundary=(1, 2)), manifest
+        )
+        self.assertFalse(regressed["accepted"])
+        self.assertFalse(regressed["checks"]["holdout_did_not_regress"])
+
+    def test_empty_patch_is_rejected(self):
+        signal = diagnose_failures(evaluation())
+        manifest = build_candidate_manifest({"diff": "", "rationale": "none", "edits": []}, signal)
+        decision = evaluate_release_gate(evaluation(), evaluation(boundary=(1, 2)), manifest)
+        self.assertEqual("reject_candidate", decision["decision"])
+
+
+if __name__ == "__main__":
+    unittest.main()