Every agent gets the live web: web_search and fetch_url by default

"Be ashamed to guess APIs blindly; be proud to look things up carefully" —
until now the agents had no way to look anything up: no search, no fetch,
so market research, API usage, and competitive claims were all invented
from model memory.

agent-web-tools.ts, carried by every agent in every run (same pattern as
the workspace tools, no grant needed):
- web_search: keyless DuckDuckGo HTML backend; parses titles, unwraps the
  /l/?uddg= redirect hrefs, pairs snippets; reports honestly when nothing
  parses instead of fabricating results. Verified against the live endpoint.
- fetch_url: readable-text extraction (dependency-free HTML-to-text with
  entity decoding), 20k-char page cap, 2MB body cap read in chunks, 30s
  timeout.
- SSRF guard on both: hostnames resolve before connecting and loopback,
  private, link-local, CGNAT, and reserved ranges are refused — re-checked
  on every redirect hop, so a public page cannot bounce the agent into
  127.0.0.1 or the cloud metadata address. IPv6 and v4-mapped forms covered.
- The fetcher is injectable, so the test suite covers the guard, redirect
  policy, truncation, extraction, and the DuckDuckGo parser without
  touching the network.

src/main/services/task-prompts.ts

@@ -94,7 +94,7 @@ export function buildAgentInstructions(input: AgentInstructionContext): string {
     `You are ${agent.name}, ${agent.title || agent.role} in ${agent.department} at ${input.companyName}. You are a real member of this company with your own judgment and voice — a colleague, not a generic assistant.`,
     roleVoice(input),
     "Work like a sharp person: take in what is actually in front of you, decide the smallest real next step, do it, then tell whoever needs to know. Do not narrate busywork.",
-    `Your tools are how you act: hire_agent builds your team, create_task delegates and assigns work by name (set requires_filesystem for engineering work that must change code or run commands), update_task_status tracks it, list_files and read_file explore the company workspace, write_deliverable produces real files, run_command builds and tests for real on filesystem tasks, create_document writes versioned company documents (PRDs, specs, memos, reports), read_messages catches you up on what teammates said, and send_message is how you talk to everyone.`,
+    `Your tools are how you act: hire_agent builds your team, create_task delegates and assigns work by name (set requires_filesystem for engineering work that must change code or run commands), update_task_status tracks it, list_files and read_file explore the company workspace, write_deliverable produces real files, run_command builds and tests for real on filesystem tasks, create_document writes versioned company documents (PRDs, specs, memos, reports), read_messages catches you up on what teammates said, and send_message is how you talk to everyone. web_search and fetch_url reach the live web — look up APIs, docs, and facts instead of guessing them.`,
     ...(input.language === "zh"
       ? ["公司的工作语言是简体中文：你写的每一条消息、任务标题与描述、文档和交付物都用中文表达（代码、命令、API 名称等技术标识保持原样）。工具名称和工具参数的字段名仍按定义使用英文。"]
       : []),