feat: add web search block functionality and integrate with existing plugins

- Introduced a new web search block plugin to handle web search queries and results.
- Updated copilot, doc block, and pro block plugins to include web search context in AI completions.
- Implemented utility functions for parsing and building web search markdown.
- Enhanced API to support web search requests and responses.
- Added configuration for web search URL and timeout settings.
- Updated size limit checks to account for web search content.

backend/llm_policy.py

@@ -47,6 +47,16 @@ def resolve_llm_policy(job_type: str, request_payload: dict[str, Any], config: R
             temperature=config.pro_temperature,
             thinking=_normalize_thinking(request_payload.get("pro_thinking"), allow_high=True) or "medium",
         )
+    if job_type == "web_search":
+        return LLMPolicy(
+            job_type=job_type,
+            model=config.web_search_model,
+            profile="completion",
+            max_input_chars=config.web_search_max_input_chars,
+            max_output_tokens=config.web_search_max_output_tokens,
+            temperature=config.web_search_temperature,
+            thinking="low",
+        )
     if job_type == "compress":
         return LLMPolicy(
             job_type=job_type,