Use a tracing debugger to find bugs in its own implementation
At a glance
A developer has an Opus coding agent inspect Revizor through the debugger's own trace tools. This workflow is listed under debugging, execution-tracing, agent-tools, self-testing.
After building a six-module Python debugging prototype, the author asked the coding agent to check Revizor itself. It activated trace points, located bugs, fixed them and ran the debugger's tests.
How it went
The author reports several bugs fixed and 199 passing tests in about three and a half minutes, then rewrote the prototype in Go.
Worth knowing
He explicitly cautions that agent-generated estimates of time saved are exaggerated.
Save ideas in this browser. Upvotes count across the board.
A developer leaves Codex CLI running for hours to add debug prints and test hypotheses against a deterministic front-door unit test until it can explain the bug with evidence.
DeepSeek shipped standalone Search (`POST /v1/tools/search`) and Fetch (`POST /v1/tools/fetch` → Markdown) APIs for agents/RAG: $0.75 per 1,000 successful requests each (empty/failed free); Claude Code built-in Web Search and Codex `web_search` waive Search fees for the first two weeks after launch, then standard pricing—docs live under Search & Fetch on api-docs.deepseek.com.
Show HN: jevcrawl (Apache-2.0 MCP + CLI) crawls for a goal and returns only relevant passages—small Jev model picks links/passages instead of Claude in the loop; README claims ~2× answer-page hit rate vs Crawl4AI and ~10× cheaper per answer than LLM-driven crawl; tools: crawl/scrape/map.
ExcaliClaw’s hosted Streamable HTTP MCP (https://excaliclaw.com/mcp) lets Claude Code/Desktop, Cursor, Codex, VS Code, OpenCode and OpenClaw list/create/update diagrams, ER/flowcharts, collections, PNG/SVG export, and live canvas collab under browser OAuth—unlimited MCP on all plans; launched on Product Hunt around Oct 12, 2026.
