v2026.3.31 is a channel and session story. The official source describes a skills, plugin, marketplace, or SDK change, and the important question is what survives the handoff between a Gateway, a conversation, and a reconnect.
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
ACP/plugins; Agents/LLM; Agents/MCP
Publication date
2026-03-31
Follow the message path
ACP/plugins
Evidence from the release. add an explicit default-off ACPX plugin-tools MCP bridge config, document the trust boundary, and harden the built-in bridge packaging/logging path so global installs and stdio MCP sessions work reliably.
Operator reading. Treat ACP/plugins as a boundary change. Exercise one permitted request and one refused request with a test identity, then keep both decisions in the log.
Agents/LLM
Evidence from the release. add a configurable idle-stream timeout for embedded runner requests so stalled model streams abort cleanly instead of hanging until the broader run timeout fires.
Operator reading. Agents/LLM changes a capability choice, not automatically a billing or privacy agreement. Record provider, model id, context setting, and fallback behavior before changing a default.
Agents/MCP
Evidence from the release. materialize bundle MCP tools with provider-safe names (serverNametoolName), support optional streamable-http transport selection plus per-server connection timeouts, and preserve real tool results from aborted/error turns unless truncation explicitly drops them.
Operator reading. Agents/MCP changes a capability choice, not automatically a billing or privacy agreement. Record provider, model id, context setting, and fallback behavior before changing a default.
Slack
Evidence from the release. stop retry-driven duplicate replies when draft-finalization edits fail ambiguously, and log configured allowlisted users/channels by readable name instead of raw IDs.
Operator reading. Before widening access for Slack, replay a narrow allow and deny case. A readable denial and a revoked test credential are part of the acceptance record.
The less visible details
Agents/OpenAI Responses
normalize raw bundled MCP tool schemas on the WebSocket/Responses path so bare-object, object-ish, and top-level union MCP tools no longer get rejected by OpenAI during tool registration.
The safe reading of Agents/OpenAI Responses is operational: prove the model can answer the intended task, then force a bounded failure and verify that no side effect is repeated.
Test this release without widening the boundary
- Note the current version, host, provider, and workspace before exercising ACP/plugins.
- Keep a tested backup beside the release record if the update can touch configuration, sessions, or a database.
- Send one harmless message through the named account and save the account, thread, and sender identifiers.
- Compare the transcript before and after reconnect, including delivery state and any visible error.
- 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 models
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
Slack. stop retry-driven duplicate replies when draft-finalization edits fail ambiguously, and log configured allowlisted users/channels by readable name instead of raw IDs. Keep the reproduction and the post-fix result together in the acceptance record.
Agents/OpenAI Responses. normalize raw bundled MCP tool schemas on the WebSocket/Responses path so bare-object, object-ish, and top-level union MCP tools no longer get rejected by OpenAI during tool registration. Record the failure that this correction addresses before declaring the upgrade complete.
Use the complete OpenClaw v2026.3.31 release notes for the exact change list, then cross-check the official release index and the skills documentation before acting.
Reference Trail
Sources and further reading
- complete OpenClaw v2026.3.31 release notesgithub.com
- official release indexgithub.com
- skills documentationdocs.openclaw.ai