Tag
37 posts tagged.
Elicitation has been in MCP since June 2025, but the current 2026-07-28 revision changed how it is delivered and calls the old pattern a breaking change. A field log on the three-revision diff, why elicitationId became requestState, and why the statefulness advice inverted.
Agent teams are off by default in August 2026, and turning them on also changes how ordinary subagent delegation behaves. A documentation field log on the env var everyone writes wrong, the 7x token figure nobody quotes correctly, and the five minute cache bucket.
MCP Apps went stable as the first official MCP extension in January 2026. A pre-build field log on the identifier mismatch, the bilateral opt-in that fails silently, the deny-by-default CSP, and which hosts actually render one in August 2026.
Every comparison ranking for this query calls goose Block's open-source agent. Block donated it to the Agentic AI Foundation at the Linux Foundation in April 2026, alongside Anthropic's MCP. A field log on what that changes and what it does not.
Every explainer quotes a 200,000-token ceiling. Anthropic's own docs say the auto-compact window is a setting you choose, from 100K to 1M, and that Sonnet 5 compacts at about 967K. The popular fix is to disable auto-compact. There is a flag instead.
Every page-one comparison treats this as a choice between two products. Google's own model docs say Antigravity offers Claude Sonnet 4.6 and Opus 4.6, free tier included. That makes it a harness comparison, not a model one, and it changes the answer.
Most of page one still compares Devin the autonomous cloud agent against Claude Code the terminal agent. I opened both 2026 pricing pages and the billing docs, and two of the claims everyone repeats are out of date.
I built the same rate-limiting feature twice, both inside Warp. Warp's own docs argue you should switch off Claude Code, then document running it inside Warp. Here is what that actually means for a solo dev in 2026.
I built the same CSV-export feature with GitHub Copilot and Claude Code from the same commit. The code came out close. The pricing shape is what actually decides it.
Claude Code code review is really two products with one name: a Team-only GitHub PR service and a free local /code-review command. I ran the local one on my own agent-written code for two weeks. Here is what it caught, and the REVIEW.md trap nobody mentions.
Claude Code plugins bundle skills, MCP servers, and language servers into one install. A 2026 field log on which plugins I kept, which I deleted, and the context cost nobody prices.
I ran one real refactor through Claude Code, Cursor, Aider, and Codex CLI, ranked by safety net and review surface, not raw model smarts. A 2026 field log.
