feat: add llms.txt discovery as default agent behavior

Add automatic llms.txt awareness so agents check for /llms.txt or
/.well-known/llms.txt when exploring new domains.

Changes:
- System prompt: new 'llms.txt Discovery' section (full mode only,
  when web_fetch is available) instructing agents to check for llms.txt
  files when visiting new domains
- web_fetch tool: updated description to mention llms.txt discovery

llms.txt is an emerging standard (like robots.txt for AI) that helps
site owners describe how AI agents should interact with their content.
Making this a default behavior helps the ecosystem adopt agent-native
web experiences.

Ref: https://llmstxt.org

src/agents/tools/web-fetch.ts

@@ -767,7 +767,7 @@ export function createWebFetchTool(options?: {
     label: "Web Fetch",
     name: "web_fetch",
     description:
-      "Fetch and extract readable content from a URL (HTML → markdown/text). Use for lightweight page access without browser automation.",
+      "Fetch and extract readable content from a URL (HTML → markdown/text). Use for lightweight page access without browser automation. When exploring a new domain, also check for /llms.txt or /.well-known/llms.txt — these files describe how AI agents should interact with the site.",
     parameters: WebFetchSchema,
     execute: async (_toolCallId, args) => {
       const params = args as Record<string, unknown>;