Model intelligence.
Follow the changes. Understand what comes next.
Why AI Router ZDR Labels Are Not a Guarantee: Inside OpenRouter's MiniMax Warning and a 4-Step Hardening Guide
Following Dragos's November 19, 2026 study of two million canary-seeded prompts, OpenRouter emailed affected customers on November 20–21 warning that prompts and outputs sent to MiniMax models from July to October 2026 may have been read by a third party—whether served directly or forwarded via AtlasCloud, Novita, or StreamLake—and removed ZDR labels from affected endpoints pending investigation.
Latest stories126
Newest publishedOpenCode 1.19.5 Stops Failed TUI Worker Requests from Hanging
OpenCode published v1.19.5 on October 28, 2026 as a formal GitHub Release. The Bugfixes line says failed TUI worker requests now return an error instead of leaving the caller hanging (@Nowaker; PR #54936). Release notes list Bugfixes only—no new features. When a TUI worker handler fails, callers can see an error and exit rather than hang. npm package opencode-ai lists latest=1.19.5; a common path is npm i -g opencode-ai@latest. No pricing change appears with this cut—for reference only.
Mistral Puts Responses API in Public Preview for Agents
Mistral (October 28, 2026) puts the Responses API in public preview for building agents. Versus Chat Completions, each response returns the model’s answer, reasoning, and tool calls as separate items. Docs describe an OpenAI Responses format surface that is stateless—apps keep history and resend it in input. It works with all chat models hosted by Mistral, including Large 4. Preview capabilities include text, image/file input, structured output, streaming, function calling, reasoning, and input_tokens. No new Responses pricing was announced in this window—for reference only.
Opera WebAI Early Preview: What Local Inference Saves, Which Devices Can't Run It
Opera (27 Oct 2026) opens WebAI early preview in Opera One, GX, and Neon: sites and extensions call local Prompt, Decision, and Semantic Embeddings APIs in-browser. No separate AI app, local server, or API key; page content used by local AI need not go to a cloud provider. Opt-in: Settings → Opera AI → Enable Web AI API. Supported: Win64 Intel/AMD and Apple silicon Macs; not Intel Mac, Linux, or Windows on Arm. Six demo extensions are samples, not built-in. Proposed web standard—not a finished universal API. Speed and CJK quality not tested here. For reference only.
GitHub Copilot Adds Server-to-Server Auth in Public Preview
GitHub’s Changelog dated October 27, 2026 says GitHub Copilot supports server-to-server authentication for GitHub Apps installed on organizations, in public preview. Services and agents built with the Copilot SDK can request on behalf of an organization without signed-in user credentials. Apps need the read-only Copilot Requests organization permission and a short-lived installation access token. Usage is billed to the org under its model policies, budgets, and spending controls. Tokens expire after one hour. Details follow GitHub Changelog and docs. For reference only.
OpenAI API Pricing (November 2026)
OpenAI API token rates (USD/1M) across Standard, Batch, Flex, Fast, Ultrafast. Standard short (≤272K): gpt-6-astra $10/$1/$50; gpt-6.1-sol $2/$0.10/$10; gpt-6.1-terra $1/$0.05/$5; gpt-6-sol $2/$0.20/$10; gpt-6-luna $0.10/$0.01/$0.50 (in/cache/out). Batch/Flex ~half Standard on many flagships; Fast ~2x (Priority renamed Fast 2026-07-30); Ultrafast only gpt-6-astra & gpt-6.1-sol (~6x). Data residency/FedRAMP +10% for eligible models from 2026-03-05. GPT-5.6 Sol promo at least through 2026-11-21. API tokens only—not ChatGPT Plus/Pro. For reference only.
Gemini CLI 0.66.0 Adds UI Sync Fixes and Gemini 4 Banner
Google shipped Gemini CLI 0.66.0 (GitHub v0.66.0; published_at 2026-10-27T20:26:28Z / 2026-10-28 04:26 Asia/Shanghai). npm @google/gemini-cli latest is 0.66.0; preview remains 0.67.0-preview.0. Release notes: UI/tool-output sync and scroll fixes; resolve settings placeholders after .env; harden SKILL.md frontmatter; keybindings keys array; verify updates against PATH shadowing; banner that Gemini CLI is not optimized for Gemini 4. This build has not been installed on this site; for reference only.
Claude Code 2.1.312 Adds OIDC user_id_claim and Safer Large-File Writes
Anthropic shipped Claude Code 2.1.312 on npm (latest=next=2.1.312; time 2026-10-27T18:36:10.160Z / 2026-10-28 02:36 Asia/Shanghai); stable remains 2.1.308. CHANGELOG: gateway oidc.user_id_claim; fullscreen click-to-send; safer large CLAUDE.md Write; Bash cd skills; "5-hour limit" copy. Brief VS Code/Cloud/Tag/Code Review/OTel notes. This build has not been installed on this site; for reference only.
Codex CLI 0.165.0 Adds Vertex AI Provider and Memory v2 Defaults
OpenAI shipped Codex CLI 0.165.0 (GitHub rust-v0.165.0; 2026-10-27T20:09:38Z / 2026-10-28 04:09 Asia/Shanghai). Highlights: built-in Vertex AI (model_provider="gcp"); Memory v2 on by default for fresh profiles with external-agent memory import; session picker repository filter and agent command center directory grouping; mid-conversation reasoning effort changes allowed by default. GPT-6.1 Terra is a model-catalog entry only. Brief TUI/MCP/marketplace fixes. This build has not been installed on this site; for reference only.
Cursor Design Mode Adds Annotate: Point and Draw for Agents
Cursor Design Mode adds Annotate in the Agents Window browser for frontend/UI work. @cursor_ai on X (created_at 2026-10-27T19:11:57Z / 2026-10-28 03:11 Asia/Shanghai) said Annotate gives agents visual prompts—edit elements and draw on the page. Needs Cursor 3.24.18+; open via Annotate or Cmd+Shift+D. Click, Shift-multi-select, drag markup, double-click text, edit CSS, or Dictate. Notes send text, element details, and a cropped screenshot; Batch edits collect pins before Send. Canvas tabs keep older pen Design Mode without Batch or in-place text. Docs recommend Composer 2.5. For reference only.
What Is Runway App Studio? How It Differs from Apps and Workflows, Plus Credits and Sharing Limits
On October 23, 2026, Runway’s Paid Plans changelog listed App Studio: describe a creative app; it builds with Runway’s models, brand, and files, then hosts it. Help: ~700 credits balance to start a build session; ~50 per block while building—a start-balance threshold, not a fixed price per app. Classic Apps via Switch to classic Apps; Workflows stay node pipelines. Sharing docs conflict—Who can open and the FAQ deny an outside public link, while Publishing lists Anyone with a link—so outside sharing stays pending verification. Credit burn and time savings have not been measured on this site.
Why AGENTS.md in Downloads Is Dangerous: Working-Directory Pitfalls for Codex and Claude Code
Forever Security (22 Oct 2026) found malicious AGENTS.md in a real customer's ~/Downloads; delivery undetermined. Researchers reproduced Codex rewriting ~/.codex/config.toml and pulling function-color (self-test >90%), plus a Claude Code variant writing ANTHROPIC_BASE_URL into .claude/settings.json (~50%). BleepingComputer (25 Oct) verified a PoC can land AGENTS.md in Downloads in Chrome/Edge/Firefox without save-as; Brave asks first—yet the chain still needs the agent started there under approval and sandbox. Working-directory checklist; not a claim every visit or version is compromised.
Entire Trails vs Pull Requests: What AI Review Scores, Tests, and Human Approval Each Control
On October 26, 2026, Entire launched an independent Git forge for agent–human collaboration. Trails put requirements, session traces, code changes, and scored agent evals in one HUD; every push runs evals and findings. Gates can block merge until findings clear, CI passes, and a human approves. CI: Buildkite and Depot. Private repos today in US, EU, India, Australia; public repos and self-hosted Git nodes on the roadmap. Vendor speed and token-savings claims are not measurements run on this site; review scores are not a security guarantee; pricing unverified—no purchase or migration advice.