keyword cleanup: v2 engine, alias rule layer, LLM semantic suggestions

- build_review_bundle.py: 新增 _compute_percentile/_compute_growth,
  候选池从固定阈值改为百分位排名 + 增速因子 (v2 policy)
- term_cleanup_policy.json: 升级 v2 schema
- generate_term_cleanup_suggestions.py: 新增 _prepare_alias_suggestions,
  规则层输出 alias (大小写/单复数/分词变体)
- generate_term_cleanup_semantic_suggestions.py: 新增 LLM 语义建议脚本
  (DeepSeek API, 产出 semantic alias/stopword/promote)
- SKILL.md: 更新为 5 Phase 工作流程
- 首轮清洗 apply: interest 54, aliases 17组, stopwords 17个
- docs/design/keyword-cleanup-flow-overview.md: 流程文档
- plans/: 引擎设计方案

scripts/generate_term_cleanup_suggestions.py

@@ -175,6 +175,121 @@ def _prepare_watch_suggestions(bundle: dict[str, Any], reserved_terms: set[str])
     return suggestions
 
 
+def _prepare_alias_suggestions(
+    bundle: dict[str, Any],
+    all_terms: list[dict[str, Any]] | None = None,
+) -> list[dict[str, Any]]:
+    """
+    Generate alias suggestions using surface-form rules (no LLM).
+
+    Rules:
+    1. casefold match — same normalized form, different original casing
+    2. trailing-s singularization — singular/plural variants
+    3. whitespace/hyphen normalization — word boundary variants
+
+    Scans all_terms (full term_stats) if provided; otherwise falls back
+    to top_global_terms from the bundle.
+    """
+    current_config = _require_dict(bundle.get("current_config"), "bundle.current_config")
+    interest_keywords = _require_list(
+        current_config.get("interest_keywords"), "bundle.current_config.interest_keywords"
+    )
+    top_global_terms = _require_list(bundle.get("top_global_terms"), "bundle.top_global_terms")
+    source_terms = all_terms if all_terms is not None else top_global_terms
+
+    interest_set = {_term_key(t) for t in interest_keywords if isinstance(t, str)}
+    interest_originals: set[str] = {t for t in interest_keywords if isinstance(t, str)}
+
+    # Build full casefold → [original forms] map
+    cf_map: dict[str, list[str]] = {}
+    for item in source_terms:
+        term = None
+        if isinstance(item, dict):
+            term = item.get("term")
+        elif isinstance(item, str):
+            term = item
+        if not isinstance(term, str) or not term.strip():
+            continue
+        key = _term_key(term)
+        if key not in cf_map:
+            cf_map[key] = []
+        if term not in cf_map[key]:
+            cf_map[key].append(term)
+
+    suggestions: list[dict[str, Any]] = []
+    seen_pairs: set[tuple[str, str]] = set()
+
+    def _add(from_term: str, to_term: str, reason: str) -> None:
+        pair = (_term_key(from_term), _term_key(to_term))
+        if pair in seen_pairs:
+            return
+        seen_pairs.add(pair)
+        suggestions.append({"from": from_term, "to": to_term, "reason": reason})
+
+    # Build a set of all term keys from source for quick lookup
+    source_keys = set(cf_map.keys())
+
+    # Rule 1: casefold match — same normalized form, different casing
+    for key, variants in cf_map.items():
+        if len(variants) < 2:
+            continue
+        canonical = None
+        alt_forms = []
+        for v in variants:
+            if v in interest_originals:
+                canonical = v
+            else:
+                alt_forms.append(v)
+        if canonical and alt_forms:
+            for alt in alt_forms:
+                _add(alt, canonical, "Case variant")
+        elif len(variants) >= 2 and not canonical:
+            # None is canonical — suggest the highest-frequency form
+            ranked = sorted(variants, key=lambda t: -(
+                next(
+                    (it.get("total_count", 0) for it in top_global_terms if it.get("term") == t),
+                    0,
+                )
+            ))
+            for alt in ranked[1:]:
+                _add(alt, ranked[0], "Case variant (auto-ranked)")
+
+    # Rule 2: singular/plural — trailing-s normalization
+    # Check all source terms (not just interest keys) for bidirectional matching
+    for key in source_keys:
+        if key in interest_set:
+            continue
+        if key.endswith("s") and len(key) > 2:
+            singular_key = key.rstrip("s")
+            if singular_key in interest_set and singular_key != key:
+                # Find canonical interest keyword
+                canon = next((t for t in interest_keywords if _term_key(t) == singular_key), None)
+                from_form = cf_map[key][0]
+                if canon:
+                    _add(from_form, canon, "Plural variant")
+        # singular form → interest has plural
+        plural_key = key + "s"
+        if plural_key in interest_set and plural_key != key:
+            canon = next((t for t in interest_keywords if _term_key(t) == plural_key), None)
+            from_form = cf_map[key][0]
+            if canon:
+                _add(from_form, canon, "Singular variant")
+
+    # Rule 3: whitespace/hyphen normalization
+    for key in source_keys:
+        if key in interest_set:
+            continue
+        normalized = key.replace("-", "").replace("_", "").replace(" ", "")
+        if normalized in interest_set and normalized != key:
+            canon = next((t for t in interest_keywords if _term_key(t) == normalized), None)
+            from_form = cf_map[key][0]
+            if canon:
+                _add(from_form, canon, "Whitespace/punctuation variant")
+
+    suggestions.sort(key=lambda x: (x["from"].casefold(), x["to"].casefold()))
+    return suggestions
+
+
 def _render_table(items: list[dict[str, Any]]) -> str:
     if not items:
         return "_None in this pass._\n"
@@ -361,9 +476,19 @@ def main() -> None:
         markdown_output=args.markdown_output,
     )
 
+    # Load full term_stats for alias scanning (bundle only has top N)
+    stats_path = REPO_ROOT / "data" / "term_index" / "term_stats.json"
+    all_stats_terms: list[str] = []
+    if stats_path.exists():
+        stats_payload = _load_json(stats_path)
+        raw_terms = stats_payload.get("terms") if isinstance(stats_payload, dict) else []
+        if isinstance(raw_terms, list):
+            all_stats_terms = [str(t["term"]) for t in raw_terms if isinstance(t, dict) and isinstance(t.get("term"), str)]
+
     interest_items = _prepare_interest_suggestions(bundle)
     reserved_terms = {_term_key(str(item.get("term") or "")) for item in interest_items}
     watch_items = _prepare_watch_suggestions(bundle, reserved_terms=reserved_terms)
+    alias_items = _prepare_alias_suggestions(bundle, all_terms=all_stats_terms)
 
     suggestions = {
         "date": suggestion_date,
@@ -373,10 +498,10 @@ def main() -> None:
         "summary": {
             "interest_keyword_suggestions": len(interest_items),
             "watch_terms": len(watch_items),
-            "alias_suggestions": 0,
+            "alias_suggestions": len(alias_items),
             "stopword_suggestions": 0,
         },
-        "alias_suggestions": [],
+        "alias_suggestions": alias_items,
         "stopword_suggestions": [],
         "interest_keyword_suggestions": interest_items,
         "watch_terms": watch_items,
@@ -400,7 +525,7 @@ def main() -> None:
         "markdown_output": str(markdown_output_path) if args.emit_markdown else None,
         "interest_keyword_suggestions": len(interest_items),
         "watch_terms": len(watch_items),
-        "alias_suggestions": 0,
+        "alias_suggestions": len(alias_items),
         "stopword_suggestions": 0,
         "emit_markdown": args.emit_markdown,
     }