feat(ai): ecosysteme d'outils phase 2 - recherche a cle, cache/retry, Playwright, crawl, Gitea/GitHub, documents (#92)

backend/tools/webcache.py

@@ -0,0 +1,138 @@
+"""SQLite cache for web tool results (search results, fetched pages).
+
+Phase 2 of the web-toolset roadmap (« Transverse »): repeated web searches and
+page fetches (common in agent loops, where the model re-reads a source) must
+not hammer the providers. Results are cached in a dedicated SQLite table with
+a TTL; the cache is best-effort — any error silently disables it so a broken
+database file never takes the assistant down.
+
+Configuration (environment):
+* ``OBSIGATE_DATA_DIR``        — base data directory (default ``data``)
+* ``OBSIGATE_WEB_CACHE_PATH``  — explicit cache file override
+* ``OBSIGATE_WEB_CACHE_TTL``   — seconds, ``0`` disables the cache (default 900)
+"""
+
+from __future__ import annotations
+
+import hashlib
+import json
+import logging
+import os
+import sqlite3
+import threading
+import time
+from pathlib import Path
+from typing import Any
+
+logger = logging.getLogger("obsigate.tools.webcache")
+
+DEFAULT_TTL_SECONDS = 900
+_schema_ready = False
+_write_lock = threading.Lock()
+
+
+def ttl_seconds() -> float:
+    """Configured TTL in seconds (``0`` = cache disabled)."""
+    return float(os.environ.get("OBSIGATE_WEB_CACHE_TTL", str(DEFAULT_TTL_SECONDS)))
+
+
+def _cache_path() -> Path:
+    override = os.environ.get("OBSIGATE_WEB_CACHE_PATH", "").strip()
+    if override:
+        return Path(override)
+    return Path(os.environ.get("OBSIGATE_DATA_DIR", "data")) / "web_cache.sqlite3"
+
+
+def _connect() -> sqlite3.Connection:
+    """Open (and lazily create) the cache database."""
+    global _schema_ready
+    path = _cache_path()
+    path.parent.mkdir(parents=True, exist_ok=True)
+    conn = sqlite3.connect(path, timeout=5, check_same_thread=False)
+    if not _schema_ready:
+        conn.execute(
+            "CREATE TABLE IF NOT EXISTS web_cache ("
+            "key TEXT PRIMARY KEY, value TEXT NOT NULL, created REAL NOT NULL)"
+        )
+        conn.commit()
+        _schema_ready = True
+    return conn
+
+
+def cache_key(prefix: str, payload: dict[str, Any]) -> str:
+    """Deterministic cache key from a prefix and the normalized arguments."""
+    raw = json.dumps(payload, ensure_ascii=False, sort_keys=True, default=str)
+    digest = hashlib.sha256(raw.encode("utf-8")).hexdigest()[:32]
+    return f"{prefix}:{digest}"
+
+
+def cache_get(key: str) -> Any | None:
+    """Return the cached payload for *key*, or ``None`` (miss/expiry/disabled)."""
+    if ttl_seconds() <= 0:
+        return None
+    try:
+        conn = _connect()
+        row = conn.execute(
+            "SELECT value, created FROM web_cache WHERE key = ?", (key,)
+        ).fetchone()
+        conn.close()
+    except sqlite3.Error as e:
+        logger.warning("web cache read failed (%s): %s", key, e)
+        return None
+    if row is None:
+        return None
+    value, created = row
+    if time.time() - float(created) > ttl_seconds():
+        return None
+    try:
+        return json.loads(value)
+    except (ValueError, TypeError):
+        return None
+
+
+def cache_set(key: str, value: Any) -> None:
+    """Store *value* under *key* (best effort, never raises)."""
+    if ttl_seconds() <= 0:
+        return
+    try:
+        with _write_lock:
+            conn = _connect()
+            conn.execute(
+                "INSERT INTO web_cache (key, value, created) VALUES (?, ?, ?) "
+                "ON CONFLICT(key) DO UPDATE SET value = excluded.value, created = excluded.created",
+                (key, json.dumps(value, ensure_ascii=False, default=str), time.time()),
+            )
+            conn.commit()
+            conn.close()
+    except sqlite3.Error as e:
+        logger.warning("web cache write failed (%s): %s", key, e)
+
+
+def purge_expired() -> int:
+    """Delete expired rows; return the number of removed entries (maintenance)."""
+    try:
+        conn = _connect()
+        cursor = conn.execute(
+            "DELETE FROM web_cache WHERE created < ?", (time.time() - ttl_seconds(),)
+        )
+        conn.commit()
+        deleted = cursor.rowcount
+        conn.close()
+        return int(deleted)
+    except sqlite3.Error as e:
+        logger.warning("web cache purge failed: %s", e)
+        return 0
+
+
+def clear_cache() -> int:
+    """Drop every cached entry (tests / admin); returns the number of rows."""
+    try:
+        conn = _connect()
+        cursor = conn.execute("DELETE FROM web_cache")
+        conn.commit()
+        deleted = cursor.rowcount
+        conn.close()
+        return int(deleted)
+    except sqlite3.Error as e:
+        logger.warning("web cache clear failed: %s", e)
+        return 0