Remove memory_research (depended on unreliable SearXNG); research now uses built-in web_search

AGENTS.md

@@ -32,7 +32,7 @@ Read this file before answering any question about knowledge, memory, or researc
 | "What should you research next?" · "What gaps exist?" · "What is missing?" | `memory_list_gaps` |
 | "What do you know about X?" · "Find X in memory" | `memory_search` |
 | "Give me context about X" (before answering) | `memory_get_context` |
-| "Research X on the internet" | `memory_research` |
+| "Research X on the internet" | `web_search` → `web_fetch` → `memory_ingest` → `memory_verify` |
 | "Save/store this fact" | `memory_store` |
 | "Ingest this URL / file / text" | `memory_ingest` |
 | "Is X true?" · "Check this fact" | `memory_verify` |

ARCHITECTURE.md

@@ -1,7 +1,7 @@
 # Pegas Memory — Architecture
 
 Pegas Memory is the long-term memory and knowledge base for the **Pegas** research agent.
-It is a Python service exposed to the agent as an **MCP server** (14 tools).
+It is a Python service exposed to the agent as an **MCP server** (13 tools).
 
 ---
 
@@ -14,7 +14,7 @@ It is a Python service exposed to the agent as an **MCP server** (14 tools).
                  └───────────────────┬──────────────────────┘
                                      │  JSON-RPC 2.0 / stdio
                  ┌───────────────────▼──────────────────────┐
-                 │  mcp_server.py  (tool layer, 14 tools)   │
+                 │  mcp_server.py  (tool layer, 13 tools)   │
                  └───────────────────┬──────────────────────┘
                                      │  Python API
         ┌────────────────────────────┼────────────────────────────┐
@@ -153,7 +153,7 @@ Only single-token kinds (no spaces) are accepted — human-readable rules from d
 
 ---
 
-## 6. MCP tools (14)
+## 6. MCP tools (13)
 
 | Tool | Purpose |
 |---|---|
@@ -165,7 +165,6 @@ Only single-token kinds (no spaces) are accepted — human-readable rules from d
 | `memory_verify` | self-critique + cross-confirmation |
 | `memory_add_gap` | register a research gap |
 | `memory_list_gaps` | list open gaps |
-| `memory_research` | full research cycle for one question |
 | `memory_store_code` | extract + store code symbols |
 | `memory_search_code` | lexical search over code symbols |
 | `memory_code_graph` | build symbol + dependency graph |

EXAMPLES.md

@@ -91,9 +91,9 @@ If nothing is found → say "not in the knowledge base" and offer to research it
 1. memory_search("HNSW")            → []                        # not known yet
 2. memory_add_gap("How does HNSW work?",
                   reason = "low_coverage", priority = 0.8)
-3. memory_research("How does HNSW indexing work?")
+3. web_search(["How does HNSW indexing work?"])   # built-in search
-                                    → searches the web, ingests sources,
+   web_fetch(chosen_url)              → full page text
-                                      distills atoms, saves them
+   memory_ingest(url)                 → distills atoms, saves them
 4. memory_verify()                  → cross-confirm the new atoms
 5. memory_search("HNSW")            → now returns verified hits
 ```

README.md

@@ -43,7 +43,7 @@ schema.sql         — DDL PostgreSQL
 - **Сервер**: [mcp_server.py](./mcp_server.py) — чистый stdlib, JSON-RPC 2.0, stdio.
 - **Инструменты** (видны модели как `mcp__pegas-memory__*`):
   `memory_search`, `memory_store`, `memory_ingest`, `memory_add_gap`,
-  `memory_list_gaps`, `memory_research`, `memory_stats`, `memory_get_context`.
+  `memory_list_gaps`, `memory_stats`, `memory_get_context`.
 - **Регистрация**: в `~/.dsh/profiles/web/cordis.patch.yml` через `@deepseek-ai/dsh-mcp-client`.
 - **Live-reload**: профиль web имеет `patchReload: live` — изменения конфига
   подхватываются без рестарта (проверено: сервер спавнится автоматически).

mcp_server.py

@@ -126,16 +126,6 @@ def _tool_list_gaps(args):
     return json.dumps({"gaps": gaps}, ensure_ascii=False, indent=2), False
 
 
-def _tool_research(args):
-    from pegas_memory import research
-    question = str(args.get("question") or "").strip()
-    if not question:
-        return json.dumps({"error": "пустой question"}, ensure_ascii=False), True
-    result = research.research_question(_conn(), question)
-    _sync()
-    return json.dumps(result, ensure_ascii=False, indent=2), False
-
-
 def _tool_stats(args):
     c = _conn()
     with c.cursor() as cur:
@@ -310,18 +300,6 @@ TOOLS = [
                        "отсортированный по приоритету. Вызывай, чтобы узнать, что ещё нужно исследовать.",
         "inputSchema": {"type": "object", "properties": {}, "required": []},
     },
-    {
-        "name": "memory_research",
-        "description": "Полный цикл исследования вопроса: веб-поиск, загрузка найденных источников, "
-                       "дистилляция в атомы, сохранение. Для ручного поиска используй встроенный web_search.",
-        "inputSchema": {
-            "type": "object",
-            "properties": {
-                "question": {"type": "string", "description": "Исследовательский вопрос."},
-            },
-            "required": ["question"],
-        },
-    },
     {
         "name": "memory_stats",
         "description": "Сколько всего в твоей базе знаний: атомов, документов, открытых пробелов. "
@@ -463,7 +441,6 @@ def handle(msg):
             "memory_ingest": _tool_ingest,
             "memory_add_gap": _tool_add_gap,
             "memory_list_gaps": _tool_list_gaps,
-            "memory_research": _tool_research,
             "memory_stats": _tool_stats,
             "memory_store_code": _tool_store_code,
             "memory_search_code": _tool_search_code,