fix: ensemble 温度从 3 个增至 4 个增加多样性 - Closes #75

新增 t=0.5 温度变体，提高 ensemble 多样性以捕获更多功能单元。

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

skills/ir_generation_skill/config.py

@@ -86,7 +86,8 @@ COVERAGE_TARGET = float(os.environ.get("IR_COVERAGE_TARGET", "0.95"))
 ENSEMBLE_TEMPERATURES = [
     float(os.environ.get("IR_ENSEMBLE_T1", "0.0")),
     float(os.environ.get("IR_ENSEMBLE_T2", "0.3")),
-    float(os.environ.get("IR_ENSEMBLE_T3", "0.7")),
+    float(os.environ.get("IR_ENSEMBLE_T3", "0.5")),
+    float(os.environ.get("IR_ENSEMBLE_T4", "0.7")),
 ]
 
 

skills/ir_generation_skill/step1_semantic_index.py

@@ -880,9 +880,9 @@ def run_ensemble_semantic_index(doc: dict) -> dict:
             if v:
                 print(f"    {k}: {len(v)} 个问题")
 
-        # Feedback retry: re-run with coverage feedback (up to 2 retries, quality-gated)
+        # Feedback retry: re-run with coverage feedback (up to 3 retries, quality-gated)
         retry_count = 0
-        while retry_count < 2:
+        while retry_count < 3:
             feedback = _build_coverage_feedback(gaps)
             if not feedback:
                 break
@@ -906,13 +906,16 @@ def run_ensemble_semantic_index(doc: dict) -> dict:
                             if src.get("section"):
                                 retry_sections.add(src["section"])
                     print(f"  重试新增 sections: {sorted(retry_sections)}", flush=True)
-                    # Quality gate: only include retry if it improves coverage
+                    # Quality gate: include retry if it adds new sections or doesn't regress coverage
                     trial_indices = semantic_indices + [retry_result]
                     trial_merged = ensemble_merge(trial_indices)
                     trial_passed, trial_gaps = _quick_validate(trial_merged, doc, all_paths)
                     trial_warnings = len(trial_gaps.get("coverage_warnings", []))
                     trial_missing = len(trial_gaps.get("missing_table_rows", []))
-                    if trial_warnings < pre_warnings or trial_missing < pre_missing_rows:
+                    improved = trial_warnings < pre_warnings or trial_missing < pre_missing_rows
+                    no_regression = trial_warnings <= pre_warnings and trial_missing <= pre_missing_rows
+                    has_new_sections = len(retry_sections) > 0
+                    if improved or (no_regression and has_new_sections):
                         semantic_indices.append(retry_result)
                         merged = trial_merged
                         passed, gaps = trial_passed, trial_gaps

skills/ir_generation_skill/step3_merge_and_audit.py

@@ -206,7 +206,12 @@ def _normalize_rule(rule: dict) -> dict:
             if stype and stype not in valid_types:
                 src["type"] = "text"
                 stype = "text"
-            if stype in ("table", "text"):
+            if stype == "table":
+                if not src.get("section"):
+                    src["section"] = default_section
+                if src.get("row") is None:
+                    src["row"] = 0
+            elif stype == "text":
                 if not src.get("section"):
                     src["section"] = default_section
     else:

skills/ir_generation_skill/tests/test_step3.py

@@ -512,6 +512,18 @@ class TestNormalizeRule:
         normalized = _normalize_rule(rule)
         assert "section" not in normalized["sources"][0]
 
+
+    def test_normalize_table_source_null_row(self):
+        """Table source with null row gets row=0 (defensive)."""
+        rule = {
+            "trigger": {"conditions": [{"signal": "x", "operator": "==", "value": "1"}]},
+            "sources": [
+                {"type": "table", "section": "3.1 功能", "row": None},
+            ],
+        }
+        normalized = _normalize_rule(rule)
+        assert normalized["sources"][0]["row"] == 0
+
     def test_normalize_source_invalid_type(self):
         """Invalid source types (LLM hallucinations) are normalized to text."""
         rule = {

tests/test_config.py

@@ -83,8 +83,8 @@ def test_output_dir_structure():
 
 
 def test_ensemble_temperatures_count():
-    """Should have exactly 3 ensemble temperatures."""
+    """Should have exactly 4 ensemble temperatures."""
-    assert len(config.ENSEMBLE_TEMPERATURES) == 3
+    assert len(config.ENSEMBLE_TEMPERATURES) == 4
 
 
 def test_max_tokens_is_int():