fix: preserve gene-family stage intent and completed results

gfa_core/mas/utils/intent_parser.py

@@ -1344,6 +1344,46 @@ def _build_msa_region_plot_message(params: Dict) -> str:
     return "我理解你想对 MSA 指定区间进行局部绘图；请在确认弹窗中填写 alignment 起止列。"
 
 
+def _stage_keyword_pattern(keyword: str) -> str:
+    """Build a boundary-safe regex for one existing stage keyword."""
+    escaped = re.escape(keyword.lower())
+    if keyword and keyword[0].isascii() and keyword[0].isalnum():
+        escaped = rf"(?<![a-z0-9_]){escaped}"
+    if keyword and keyword[-1].isascii() and keyword[-1].isalnum():
+        escaped = rf"{escaped}(?![a-z0-9_])"
+    return escaped
+
+
+def extract_negated_target_stages(query: str) -> List[str]:
+    """Return explicitly excluded ordinary gene-family/RNA-seq target stages."""
+    query_lower = str(query or "").lower()
+    if any(marker in query_lower for marker in (
+        "亚家族", "subfamily", "reference_classification", "subfamily_confirm",
+        "build_subfamily_evidence", "subfamily_evidence", "subfamily_prediction",
+    )):
+        return []
+    if re.search(r"(?:不是|并非)\s*(?:不执行|不单独执行|不要|不用|无需|不做|跳过|排除|去掉)", query_lower):
+        return []
+
+    eligible = set(CORE_STAGES) | set(RNASEQ_STAGES) | {"expression", "annotation", "msa"}
+    chinese_prefix = r"(?:不单独执行|不执行|不要(?:执行|做|进行)?|不用(?:执行|做|进行)?|无需(?:执行|做|进行)?|不做|跳过|排除|去掉)\s*"
+    english_prefix = r"(?:without(?:\s+(?:running|executing|performing))?|skip|exclude|do\s+not\s+(?:run|execute|perform)?)\s+"
+    excluded = []
+    for stage, keywords in STAGE_KEYWORDS.items():
+        if stage not in eligible:
+            continue
+        for keyword in sorted(keywords, key=len, reverse=True):
+            keyword_pattern = _stage_keyword_pattern(keyword)
+            if (
+                re.search(chinese_prefix + keyword_pattern, query_lower)
+                or re.search(english_prefix + keyword_pattern, query_lower)
+                or re.search(r"(?:^|[\s,，;；。:：])-\s*" + keyword_pattern, query_lower)
+            ):
+                excluded.append(stage)
+                break
+    return list(dict.fromkeys(excluded))
+
+
 def _handle_stage_resolution(query: str, query_lower: str, stages: List[str]) -> Dict:
     """
     方案B: 处理阶段解析逻辑
@@ -1352,11 +1392,15 @@ def _handle_stage_resolution(query: str, query_lower: str, stages: List[str]) ->
     - 有"分析"但不明确 → 引导澄清
     - 完全无法识别 → 引导澄清
     """
+    excluded_stages = set(extract_negated_target_stages(query))
+    stages = [stage for stage in stages if stage not in excluded_stages]
+
     # 情况1: 明确指定了具体阶段 → 直接执行。
     # 如果同时出现“完整/全流程”等词，则以基础基因家族链路为主体，
     # 再追加用户明确点名的 Expression/KaKs/PPI/种间共线性等可选阶段。
     if stages:
         resolved_stages = list(dict.fromkeys([*CORE_STAGES, *stages])) if _is_complete_workflow_query(query_lower) else stages
+        resolved_stages = [stage for stage in resolved_stages if stage not in excluded_stages]
         return {
             "stages": resolved_stages,
             "need_clarify": False,
@@ -1368,7 +1412,13 @@ def _handle_stage_resolution(query: str, query_lower: str, stages: List[str]) ->
     if any(marker in query_lower for marker in RNASEQ_MARKERS):
         if any(kw in query_lower for kw in ["分析", "执行", "运行", "开始", "流程", "pipeline"]):
             return {
-                "stages": ["rnaseq_de", "rnaseq_go_enrich", "rnaseq_kegg_enrich", "rnaseq_fgsea", "rnaseq_wgcna", "rnaseq_candidate_family"],
+                "stages": [
+                    stage for stage in (
+                        "rnaseq_de", "rnaseq_go_enrich", "rnaseq_kegg_enrich",
+                        "rnaseq_fgsea", "rnaseq_wgcna", "rnaseq_candidate_family",
+                    )
+                    if stage not in excluded_stages
+                ],
                 "need_clarify": False,
                 "confidence": 0.9,
                 "note": "generic_rnaseq_workflow"
@@ -1377,7 +1427,7 @@ def _handle_stage_resolution(query: str, query_lower: str, stages: List[str]) ->
     # 情况2: "基因家族分析" = 基础基因家族链路
     if _is_complete_workflow_query(query_lower):
         return {
-            "stages": CORE_STAGES,
+            "stages": [stage for stage in CORE_STAGES if stage not in excluded_stages],
             "need_clarify": False,
             "confidence": 0.9,
             "note": "完整流程"