AI Deep-Research Requests Drained Three Usage Windows Due to Routing Policy Gap

·1 views

A single deep-research query submitted to a top-tier AI model consumed three consecutive five-hour usage windows, totaling roughly 194% of available capacity. The root cause was a gap in the system's routing policy, which only activates at session decision points and was bypassed entirely by direct research-style requests. A harness designed to manage such requests was invoked in three of six test runs but never fully executed, as a required dispatcher tool called Workflow was unavailable inside delegated sessions. Testing was further complicated by a measurement failure — subagent transcript files remained empty, masking whether the harness had actually run. A partial fix was implemented by updating the routing rule to verify harness execution, though the underlying issue of reliable triggering without specific research vocabulary remains unresolved.

Read the full story at DEV Community

This is an AI-generated summary. ShortSingh links to the original source for the complete article.

Discussion (0)

Start RAG Projects Locally to Fix Retrieval Before Adding Infrastructure

RAG (Retrieval-Augmented Generation) projects often accumulate complex infrastructure—vector stores, queues, object storage—before retrieval quality is properly validated, making failures hard to diagnose. A developer-focused approach recommends starting small: use real documents people already rely on, ask questions with known answers, and inspect returned passages directly. Effective retrieval testing should include queries with exact terms, context-dependent questions, and at least one unanswerable query to verify the system handles gaps transparently. Hybrid retrieval—combining semantic vector search with lexical keyword matching—is recommended because each method covers the other's weaknesses, especially for product codes, names, or domain-specific abbreviations. A lightweight local setup using SQLite with FTS5 and a vector extension can be sufficient to validate document processing and chunking logic before scaling to production infrastructure like PostgreSQL and pgvector.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

How Context Compression and Prompt Design Make RAG Systems Production-Ready

Part 4 of a developer series on Retrieval-Augmented Generation (RAG) systems shifts focus from retrieval to the generation stage of the pipeline. The article explains that even accurate retrieval fails if the language model is handed too much noisy or redundant context, making compression a critical step rather than an optional one. It outlines how reducing retrieved chunks to only the most relevant sentences lowers token costs, cuts latency, and reduces the risk of hallucinations. The piece also covers prompt construction techniques that keep model outputs grounded and consistent, particularly when retrieved information is incomplete. Finally, it introduces evaluation frameworks for measuring faithfulness, relevancy, precision, recall, latency, and cost in live production environments.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

Developer finds 32 competitor brand mentions hidden in affiliate site's raw HTML

A developer auditing a top-ranking crypto trading comparison site discovered it contained 32 hidden references to a competitor brand buried in the raw HTML markup. The site, which ranked first for its target keyword, showed no structured data and had a sitemap copied from a different domain. Inspecting downloaded HTML files revealed the competitor's name appeared across eight pages, including in a fees section, indicating the template had been repurposed from another product's affiliate site. The findings highlight how affiliate templates are frequently resold and reused without thorough content audits, leaving outdated or incorrect brand references intact. The developer concluded that rendered page views can mask such errors and that raw HTML inspection is essential when auditing comparison or affiliate sites.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

SMTP Verifier Blocklisted by Spamhaus Despite Never Sending a Single Email

A developer building an email verification service discovered his server had been blocklisted by Spamhaus and rejected by iCloud, even though the server had never sent any email. The service works by initiating SMTP handshakes to check if mailboxes exist, then disconnecting before any message is transmitted. Investigation revealed the root cause was a misconfigured HELO hostname that did not match the server's PTR and A records, a mismatch that triggered Spamhaus detection during probe connections. After correcting the hostname configuration to ensure all four SMTP identity checks aligned, no new detections were recorded. The Spamhaus listing subsequently expired on its own within a few days, resolving the issue without requiring a manual delisting request.

0 comments Read more at DEV Community