cd /news/ai-agents/my-agent-could-fetch-a-url-but-could… · home › topics › ai-agents › article
[ARTICLE · art-170030] src=dev.to ↗ pub= topic=ai-agents verified=true sentiment=· neutral

My agent could fetch a URL but could not search for one

A developer testing DeepSeek Harness v0.1.1-rc.2 found that the agent's web_fetch tool worked via anonymous HTTP while web_search failed with a 402 Insufficient Balance error, because the default searchProvider (deepseek-official) required a funded DeepSeek API account. The developer wrote a Tavily search provider and plugin checked against the installed type declarations, but it was not tested with a Tavily key, so the fix remains unverified. The developer concluded that agent tooling should surface provider and account dependencies before a task needs them, since 'tool enabled' is weaker than 'the selected provider can complete a request with this account.'

by read2 min views2 publishedNov 15, 2026

In my September 1 setup of DeepSeek Harness v0.1.1-rc.2, web_fetch worked while web_search could not complete a search. The difference was the service behind each tool, rather than whether the agent could reach the web.

This is a record of that setup, not a claim about the current release or every account.

The default profile selected searchProvider: deepseek-official and looked for its key in DEEPSEEK_API_KEY. My fresh DeepSeek API account returned 402 Insufficient Balance.

Having a key was therefore insufficient. The request reached a service that required a funded account. In the version I inspected, the three bundled search backends were DeepSeek, Exa, and Perplexity; none supplied a free search path for my setup.

web_fetch still worked. Fetching an already-known public URL used anonymous HTTP, without that search-provider balance requirement. That made the failure easy to describe too broadly: “the agent cannot use the web” would have hidden the useful capability that remained.

For a similar failure, I would separate these checks: web_search does not tell you which external service will receive the request. Those are diagnostic steps, not a guarantee that every 402 has the same cause. The concrete observation here was the Insufficient Balance response from my account.

I wrote a Tavily provider and plugin, and checked the interface against the installed type declarations. I had not tested it with a Tavily key. That means I had an implementation to try, not a verified alternative, and I cannot report that it fixed search.

The useful result from this investigation was a smaller, more accurate description of the system: fetching worked; the configured search service required funding; the proposed replacement remained untested.

For agent tooling, I would like a setup check to expose those dependencies before the first task needs them. “Tool enabled” is a much weaker statement than “the selected provider can complete a request with this account.”

── more in #ai-agents 4 stories · sorted by recency
── more on @deepseek 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/my-agent-could-fetch…] indexed:0 read:2min 2026-11-15 · —