Guide

OpenClaw v2026.3.12: Anthropic/Claude fast mode, upgrade notes

March 13, 20264 min readUpdated September 11, 2026By OpenClawBlog Team

v2026.3.12 arrived on 2026-03-13 with a change that matters during maintenance: anthropic/claude fast mode. The page is a researched reading note from the official release record, with a test path for a real Gateway.

The tag is stable, but the direct notes still define its migrations, corrections, and package-specific limits. Support still depends on the provider, channel, platform, and account behind the installation, so check those boundaries before extrapolating from the tag.

Channel
Stable

Primary signals
Control UI/dashboard-v2; OpenAI/GPT-5.4 fast mode; Anthropic/Claude fast mode

Publication date
2026-03-13

Before the package changes

01 / Control UI/dashboard-v2

Source signal. refresh the gateway dashboard with modular overview, chat, config, agent, and session views, plus a command palette, mobile bottom tabs, and richer chat tools like slash commands, search, export, and pinned messages.

Control UI/dashboard-v2 lives at the handoff between the Gateway and a conversation. Send one harmless message, reconnect once, and compare the account, thread, sender, and final transcript.

02 / OpenAI/GPT-5.4 fast mode

Source signal. add configurable session-level fast toggles across /fast, TUI, Control UI, and ACP, with per-model config defaults and OpenAI/Codex request shaping.

Check OpenAI/GPT-5.4 fast mode with a known prompt and a disposable account. Save the selected route, reasoning setting, latency, and refusal or fallback result so another operator can reproduce it.

03 / Anthropic/Claude fast mode

Source signal. map the shared /fast toggle and params.fastMode to direct Anthropic API-key service_tier requests, with live verification for both Anthropic and OpenAI fast-mode tiers.

Anthropic/Claude fast mode changes a capability choice, not automatically a billing or privacy agreement. Record provider, model id, context setting, and fallback behavior before changing a default.

04 / Security/device pairing

Source signal. switch /pair and openclaw qr setup codes to short-lived bootstrap tokens so the next release no longer embeds shared gateway credentials in chat or QR pairing payloads.

The useful evidence for Security/device pairing is the refusal path as well as the success path. Use synthetic credentials and record the policy that made each decision.

Details behind the headline

Security/plugins

disable implicit workspace plugin auto-load so cloned repositories cannot execute workspace plugin code without an explicit trust decision. (GHSA-99qw-6mr3-36qr).

Before widening access for Security/plugins, replay a narrow allow and deny case. A readable denial and a revoked test credential are part of the acceptance record.

Test this release without widening the boundary

  1. Note the current version, host, provider, and workspace before exercising Control UI/dashboard-v2.
  2. Keep a tested backup beside the release record if the update can touch configuration, sessions, or a database.
  3. Send one harmless message through the named account and save the account, thread, and sender identifiers.
  4. Compare the transcript before and after reconnect, including delivery state and any visible error.
  5. Stop if the observed behavior falls outside the official note, and link the log or screenshot to the version record.
openclaw --version
openclaw gateway status
openclaw security audit

Record what the release actually changed

Keep the version, source URL, test identity, and rollback decision together. If this tag is pre-release, leave it isolated; if it is stable, record the migration and rollback result before reconnecting every channel.

Corrections worth replaying

Security/device pairing. switch /pair and openclaw qr setup codes to short-lived bootstrap tokens so the next release no longer embeds shared gateway credentials in chat or QR pairing payloads. Keep the reproduction and the post-fix result together in the acceptance record.

Security/plugins. disable implicit workspace plugin auto-load so cloned repositories cannot execute workspace plugin code without an explicit trust decision. (GHSA-99qw-6mr3-36qr). Record the failure that this correction addresses before declaring the upgrade complete.

Use the complete OpenClaw v2026.3.12 release notes for the exact change list, then cross-check the official release index and the model provider reference before acting.

Reference Trail

Sources and further reading

  1. complete OpenClaw v2026.3.12 release notesgithub.com
  2. official release indexgithub.com
  3. model provider referencedocs.openclaw.ai
Back to ArchiveMore: GuidesNext: OpenClaw v2026.3.11: iOS/Home canvas, provider notes