Merge pull request 'start web search in chat' (#15) from websearchmanager into main

Reviewed-on: meulilivio/AISE1_Project#15

backend/managers/search_manager.py

@@ -0,0 +1,122 @@
+"""Handles internet search requests and page fetching for use as AI chat context."""
+
+import ipaddress
+import socket
+from urllib.parse import urlparse
+
+import requests
+from bs4 import BeautifulSoup
+from ddgs import DDGS
+
+# Maximum characters extracted from a fetched page before truncating.
+MAX_PAGE_CHARS = 3000
+
+_HEADERS = {"User-Agent": "Mozilla/5.0 (compatible; AICodeEditor/1.0)"}
+
+
+class SearchManager:
+    """Performs DuckDuckGo searches and fetches web pages for AI context injection.
+
+    All outbound requests are validated against an SSRF blocklist so that
+    localhost and private network addresses can never be reached.
+    """
+
+    def perform_search(self, query: str, max_results: int = 5) -> list[dict]:
+        """Execute a DuckDuckGo text search and return normalised results.
+
+        Args:
+            query:       The search query string.
+            max_results: Maximum number of results to return.
+
+        Returns:
+            List of {"title": str, "url": str, "snippet": str} dicts,
+            or an empty list if the search fails.
+        """
+        try:
+            with DDGS() as ddgs:
+                raw = list(ddgs.text(query, max_results=max_results))
+            return self.parse_results(raw)
+        except Exception:
+            return []
+
+    def parse_results(self, raw_results: list[dict]) -> list[dict]:
+        """Normalise raw DDGS result dicts to a consistent {"title", "url", "snippet"} shape.
+
+        Args:
+            raw_results: List of raw dicts returned by ddgs.text().
+
+        Returns:
+            Normalised list of result dicts.
+        """
+        results = []
+        for r in raw_results:
+            results.append({
+                "title":   r.get("title", ""),
+                "url":     r.get("href", r.get("url", "")),
+                "snippet": r.get("body", r.get("snippet", "")),
+            })
+        return results
+
+    def fetch_page(self, url: str) -> str:
+        """Fetch a web page and return its plain text content, truncated to MAX_PAGE_CHARS.
+
+        Args:
+            url: The URL to fetch.
+
+        Returns:
+            Plain text extracted from the page, or an error message string.
+
+        Raises:
+            ValueError: if the URL fails the SSRF safety check.
+        """
+        self._validate_url(url)
+        try:
+            response = requests.get(url, timeout=10, headers=_HEADERS)
+            response.raise_for_status()
+
+            soup = BeautifulSoup(response.text, "html.parser")
+
+            # Remove non-content elements before extracting text.
+            for tag in soup(["script", "style", "nav", "footer"]):
+                tag.decompose()
+
+            text = soup.get_text(separator="\n", strip=True)
+
+            if len(text) > MAX_PAGE_CHARS:
+                text = text[:MAX_PAGE_CHARS] + "\n... [truncated]"
+
+            return text
+
+        except ValueError:
+            raise
+        except Exception as e:
+            return f"Error fetching page: {e}"
+
+    def _validate_url(self, url: str) -> None:
+        """Block localhost, private IPs, and non-http(s) schemes to prevent SSRF attacks.
+
+        Args:
+            url: The URL to validate.
+
+        Raises:
+            ValueError: if the URL is considered unsafe.
+        """
+        parsed = urlparse(url)
+
+        if parsed.scheme not in ("http", "https"):
+            raise ValueError(f"Blocked: only http/https allowed, got '{parsed.scheme}'")
+
+        hostname = parsed.hostname or ""
+
+        if hostname.lower() in ("localhost", "127.0.0.1", "::1"):
+            raise ValueError("Blocked: localhost access denied")
+
+        try:
+            ip = ipaddress.ip_address(socket.gethostbyname(hostname))
+            if ip.is_private or ip.is_loopback or ip.is_link_local:
+                raise ValueError(f"Blocked: private/loopback IP denied ({ip})")
+        except (socket.gaierror, ValueError) as e:
+            # Re-raise our own ValueError; ignore DNS resolution failures
+            # (let requests handle unknown hostnames naturally).
+            if isinstance(e, ValueError):
+                raise

backend/managers/system_prompter.py

@@ -12,12 +12,17 @@ class SystemPrompter:
     """
 
     @staticmethod
-    def generate_prompt(file_context: dict | None = None) -> str:
-        """Build a system prompt, optionally embedding a file's content.
+    def generate_prompt(
+        file_context: dict | None = None,
+        search_context: list[dict] | None = None,
+    ) -> str:
+        """Build a system prompt, optionally embedding a file and/or web search results.
 
         Args:
-            file_context: dict with keys 'name' (filename) and 'content' (raw text),
-                          or None if no file should be included.
+            file_context:   dict with keys 'name' (filename) and 'content' (raw text),
+                            or None if no file should be included.
+            search_context: list of {"title", "url", "snippet"} dicts from SearchManager,
+                            or None if no search results should be included.
 
         Returns:
             A ready-to-use system prompt string.
@@ -28,6 +33,8 @@ class SystemPrompter:
             "Be concise and precise. Use markdown and fenced code blocks where appropriate."
         )
 
+        prompt = base
+
         if file_context:
             name = file_context.get("name", "unknown")
             content = file_context.get("content", "")
@@ -36,13 +43,23 @@ class SystemPrompter:
             if len(content) > MAX_FILE_CHARS:
                 content = content[:MAX_FILE_CHARS] + "\n... [truncated]"
 
-            file_section = (
+            prompt += (
                 f"\n\nThe user currently has the following file open in the editor:\n"
                 f"<file name=\"{name}\">\n"
                 f"<code>\n{content}\n</code>\n"
                 f"</file>\n"
                 f"Refer to this file when answering questions about the code."
             )
-            return base + file_section
 
-        return base
+        if search_context:
+            search_section = "\n\nThe user has performed a web search. Use the results below as additional context if relevant:\n<search_results>\n"
+            for i, r in enumerate(search_context, 1):
+                search_section += (
+                    f"[{i}] {r.get('title', '')}\n"
+                    f"URL: {r.get('url', '')}\n"
+                    f"{r.get('snippet', '')}\n\n"
+                )
+            search_section += "</search_results>"
+            prompt += search_section
+
+        return prompt

frontend/chat.py

@@ -3,6 +3,7 @@
 import streamlit as st
 from backend.managers.chat_manager import ChatManager
 from backend.managers.system_prompter import SystemPrompter
+from backend.managers.search_manager import SearchManager
 
 import asyncio
 
@@ -212,13 +213,59 @@ def render_agent_mode():
 
 # ── Normal Chat ───────────────────────────────────────────────────────────────
 
+def _render_search_panel():
+    """Render the collapsible web search panel above the chat history.
+
+    Stores results in session_state.search_results so they are automatically
+    injected as context into the next message the user sends.
+    """
+    search_results = st.session_state.get("search_results", [])
+    label = f"🔍 Web Search  ({len(search_results)} result{'s' if len(search_results) != 1 else ''} active)" if search_results else "🔍 Web Search"
+
+    with st.expander(label, expanded=False):
+        col_input, col_btn = st.columns([5, 1])
+        with col_input:
+            query = st.text_input(
+                "Search query",
+                key="search_query_input",
+                placeholder="e.g. Python asyncio best practices",
+                label_visibility="collapsed",
+            )
+        with col_btn:
+            search_clicked = st.button("Search", use_container_width=True)
+
+        if search_clicked and query.strip():
+            with st.spinner("Searching..."):
+                sm = SearchManager()
+                results = sm.perform_search(query.strip())
+            if results:
+                st.session_state.search_results = results
+                st.rerun()
+            else:
+                st.warning("No results found.")
+
+        # Display active results with a clear button.
+        if search_results:
+            st.caption("Results will be injected as context into your next message.")
+            for r in search_results:
+                st.markdown(f"**{r['title']}**  \n{r['snippet']}  \n[{r['url']}]({r['url']})")
+                st.divider()
+            if st.button("Clear search results", use_container_width=True):
+                st.session_state.search_results = []
+                st.rerun()
+
+
 def render_normal_chat():
     """Render the standard multi-turn chat interface.
 
-    On the first message the system prompt is injected into the history.
+    On the first message the system prompt is injected into the history,
+    including any active search results as context.
     Each subsequent message appends to the same conversation so the AI retains
-    full context throughout the session.
+    full context throughout the session. If search results are active when the
+    user sends a message, they are prepended to that message as a context block.
     """
+    _render_search_panel()
+
     # Replay the conversation history as chat bubbles (skip system messages).
     for message in st.session_state.chat_history:
         role = message["role"]
@@ -227,10 +274,54 @@ def render_normal_chat():
         with st.chat_message(role):
             st.markdown(message["content"])
 
-    # Chat input — Enter to send, no extra button needed
-    user_input = st.chat_input("Type your message here...")
+    # Chat input — Enter to send, no extra button needed.
+    # Supports /search <query> and /search clear as special commands.
+    user_input = st.chat_input("Type a message or /search <query>...")
     if user_input:
+        stripped = user_input.strip()
+
+        # ── /search command ───────────────────────────────────────────────────
+        if stripped.lower().startswith("/search"):
+            arg = stripped[len("/search"):].strip()
+
+            with st.chat_message("user"):
+                st.markdown(stripped)
+
+            if arg.lower() == "clear" or arg == "":
+                # /search clear (or bare /search) — remove active results.
+                st.session_state.search_results = []
+                with st.chat_message("assistant"):
+                    st.markdown("Search context cleared.")
+                st.session_state.chat_history.append({"role": "user", "content": stripped})
+                st.session_state.chat_history.append({"role": "assistant", "content": "Search context cleared."})
+            else:
+                # /search <query> — run search and store results in context.
+                with st.chat_message("assistant"):
+                    with st.spinner(f'Searching for "{arg}"...'):
+                        sm = SearchManager()
+                        results = sm.perform_search(arg)
+
+                    if results:
+                        st.session_state.search_results = results
+                        summary = f"Found {len(results)} result(s) for **{arg}**. They are now in context for this chat session.\n\n"
+                        for i, r in enumerate(results, 1):
+                            summary += f"**{i}. [{r['title']}]({r['url']})**  \n{r['snippet']}\n\n"
+                        st.markdown(summary)
+                        response_text = summary
+                    else:
+                        msg = f'No results found for "{arg}".'
+                        st.warning(msg)
+                        response_text = msg
+
+                st.session_state.chat_history.append({"role": "user", "content": stripped})
+                st.session_state.chat_history.append({"role": "assistant", "content": response_text})
+
+            st.rerun()
+            return
+
+        # ── Normal chat message ───────────────────────────────────────────────
         chat_manager = st.session_state.chat_manager
+        search_results = st.session_state.get("search_results", [])
 
         # On the very first user message, prepend the system prompt so the AI
         # knows it is a code assistant embedded in an editor.
@@ -238,7 +329,22 @@ def render_normal_chat():
             system_prompt = SystemPrompter.generate_prompt()
             chat_manager.add_message("system", system_prompt)
 
-        # Show user message immediately without waiting for response.
+        # If search results are active, prepend them as a context block so the
+        # AI can reference them regardless of where in the conversation we are.
+        if search_results:
+            context_block = "<search_context>\n"
+            for r in search_results:
+                context_block += (
+                    f"Title: {r['title']}\n"
+                    f"URL: {r['url']}\n"
+                    f"Snippet: {r['snippet']}\n\n"
+                )
+            context_block += "</search_context>\n\n"
+            message_to_send = context_block + user_input
+        else:
+            message_to_send = user_input
+
+        # Show the original user text in the UI (not the context-enriched version).
         with st.chat_message("user"):
             st.markdown(user_input)
 
@@ -246,7 +352,7 @@ def render_normal_chat():
         with st.chat_message("assistant"):
             with st.spinner("Thinking..."):
                 try:
-                    ai_response = chat_manager.send_message(user_input)
+                    ai_response = chat_manager.send_message(message_to_send)
                 except Exception as e:
                     ai_response = f"Error: {e}"
             st.markdown(ai_response)

frontend/state.py

@@ -88,6 +88,11 @@ def init_state():
     if "agent_pending_action" not in st.session_state:
         st.session_state.agent_pending_action = None
 
+    # Web search results to be injected as context into the next AI message.
+    # List of {"title": str, "url": str, "snippet": str} dicts, or empty list.
+    if "search_results" not in st.session_state:
+        st.session_state.search_results = []
+
 
 
 if __name__ == "__main__":