Gaps: full lifecycle management (get/update/delete), pure PostgreSQL (no web search)

2026-10-15 17:47:40 +05:00
1 parent adfa630578
commit a4c4a766c1
@@ -1,84 +1,114 @@
-"""Цикл исследования пробелов: detect → plan → acquire → extract → verify → commit."""
+"""Управление пробелами в знаниях (research gaps).
+
+Работает **только с PostgreSQL** — никакого веб-поиска. Поиск выполняет сама
+модель встроенным инструментом \`web_search\` (SearXNG и автоматический
+research-цикл убраны).
+
+Жизненный цикл пробела:
+    open → researching → resolved | dismissed
+
+Поля:
+    question  — что нужно исследовать (формулировка)
+    reason    — почему пробел обнаружен
+    priority  — 0.0 .. 1.0 (больше = важнее)
+    status    — open | researching | resolved | dismissed
+"""
 from __future__ import annotations
-import json
-import httpx
-from . import config, db, pipeline

-_client = httpx.Client(timeout=600)
+VALID_REASONS = ("low_coverage", "low_confidence", "stale", "contested", "user_query")
+VALID_STATUSES = ("open", "researching", "resolved", "dismissed")

-def detect_gaps(conn) -> list[dict]:
-    """Найти пробелы в базе знаний."""
+_COLS = "id, question, reason, priority, status, created_at"
+
+
+def list_gaps(conn, *, status: str | None = None, limit: int = 50) -> list[dict]:
+    """Список пробелов. Без фильтра — сначала открытые, затем по приоритету."""
+    limit = max(1, min(int(limit), 200))
    with conn.cursor() as cur:
-        cur.execute(
-            "SELECT id, question, reason, priority, status FROM pm_research_gap "
-            "WHERE status = 'open' ORDER BY priority DESC, id LIMIT 20"
-        )
+        if status:
+            if status not in VALID_STATUSES:
+                raise ValueError(f"status must be one of {VALID_STATUSES}")
+            cur.execute(
+                f"SELECT {_COLS} FROM pm_research_gap WHERE status = %s "
+                "ORDER BY priority DESC, id LIMIT %s",
+                (status, limit),
+            )
+        else:
+            cur.execute(
+                f"SELECT {_COLS} FROM pm_research_gap "
+                "ORDER BY (status = 'open') DESC, priority DESC, id LIMIT %s",
+                (limit,),
+            )
        return cur.fetchall()

-def add_gap(conn, question: str, reason: str = "user_query", priority: float = 0.5):
+
+def get_gap(conn, gap_id: int) -> dict | None:
+    """Один пробел по id (или None)."""
+    with conn.cursor() as cur:
+        cur.execute(f"SELECT {_COLS} FROM pm_research_gap WHERE id = %s", (gap_id,))
+        return cur.fetchone()
+
+
+def add_gap(conn, question: str, reason: str = "user_query", priority: float = 0.5) -> int:
+    """Зарегистрировать пробел. Возвращает id."""
+    question = (question or "").strip()
+    if not question:
+        raise ValueError("question must not be empty")
+    if reason not in VALID_REASONS:
+        raise ValueError(f"reason must be one of {VALID_REASONS}")
+    priority = max(0.0, min(1.0, float(priority)))
    with conn.cursor() as cur:
        cur.execute(
-            "INSERT INTO pm_research_gap (question, reason, priority) VALUES (%s, %s, %s) RETURNING id",
+            "INSERT INTO pm_research_gap (question, reason, priority, status) "
+            "VALUES (%s, %s, %s, 'open') RETURNING id",
            (question, reason, priority),
        )
+        row = cur.fetchone()
    conn.commit()
+    return row["id"]

-def web_search(query: str, engine: str = "local") -> list[dict]:
-    """Веб-поиск (локальный инстанс). Возвращает [{title, url, snippet}]."""
-    # прямого MCP-инструмента searxng больше нет; internal HTTP JSON API остаётся
-    import urllib.parse
-    q = urllib.parse.quote(query)
-    # endpoint локального поискового инстанса
-    for base in ("http://127.0.0.1:8889", "http://127.0.0.1:8080"):
-        try:
-            r = _client.get(f"{base}/search", params={"q": query, "format": "json"}, timeout=15)
-            r.raise_for_status()
-            results = r.json().get("results", [])
-            return [{"title": x.get("title"), "url": x.get("url"), "snippet": x.get("content")}
-                    for x in results[:3]]
-        except Exception:
-            continue
-    return []

-def research_question(conn, question: str, *, top_k: int = 5, model: str | None = None) -> dict:
-    """Полный цикл исследования одного вопроса.
+def update_gap(conn, gap_id: int, *, question: str | None = None,
+               reason: str | None = None, priority: float | None = None,
+               status: str | None = None) -> bool:
+    """Обновить поля пробела. Возвращает True, если запись найдена.

-    1. веб-поиск;
-    2. для каждого источника: полная загрузка URL; при недоступности (гео-блок,
-       нет прокси) — дистилляция сниппета из поиска;
-    3. пометка вопроса resolved.
+    Типичные переходы: status='researching' (взял в работу),
+    status='resolved' (закрыт), status='dismissed' (не актуален).
    """
-    result = {"question": question, "sources": [], "atoms_created": 0}
-    sources = web_search(question)
-    result["sources"] = [s["url"] for s in sources if s.get("url")]
+    sets: list[str] = []
+    vals: list = []
+    if question is not None:
+        question = question.strip()
+        if not question:
+            raise ValueError("question must not be empty")
+        sets.append("question = %s"); vals.append(question)
+    if reason is not None:
+        if reason not in VALID_REASONS:
+            raise ValueError(f"reason must be one of {VALID_REASONS}")
+        sets.append("reason = %s"); vals.append(reason)
+    if priority is not None:
+        sets.append("priority = %s"); vals.append(max(0.0, min(1.0, float(priority))))
+    if status is not None:
+        if status not in VALID_STATUSES:
+            raise ValueError(f"status must be one of {VALID_STATUSES}")
+        sets.append("status = %s"); vals.append(status)

-    for s in sources:
-        url = s.get("url")
-        if not url:
-            continue
-        # попытка полной загрузки
-        ingested = False
-        try:
-            stats = pipeline.ingest_url(conn, url, min_confidence=0.4)
-            result["atoms_created"] += stats["atoms_created"]
-            ingested = True
-        except Exception as e:
-            print(f"[research] ingest {url} failed: {e}")
-        # fallback: сниппет из поиска (когда сайт недоступен напрямую)
-        if not ingested and s.get("snippet"):
-            try:
-                title = s.get("title") or url
-                stats = pipeline.ingest_text(
-                    conn, s["snippet"], title=title, uri=url, min_confidence=0.4,
-                )
-                result["atoms_created"] += stats["atoms_created"]
-            except Exception as e:
-                print(f"[research] snippet fallback {url} failed: {e}")
+    if not sets:
+        return get_gap(conn, gap_id) is not None

+    vals.append(gap_id)
    with conn.cursor() as cur:
-        cur.execute(
-            "UPDATE pm_research_gap SET status = 'resolved' WHERE question = %s AND status = 'open'",
-            (question,),
-        )
+        cur.execute(f"UPDATE pm_research_gap SET {', '.join(sets)} WHERE id = %s", vals)
+        found = cur.rowcount > 0
    conn.commit()
-    return result
+    return found
+
+
+def delete_gap(conn, gap_id: int) -> bool:
+    """Удалить пробел. Возвращает True, если запись существовала."""
+    with conn.cursor() as cur:
+        cur.execute("DELETE FROM pm_research_gap WHERE id = %s", (gap_id,))
+        found = cur.rowcount > 0
+    conn.commit()
+    return found