OpenClaw v2026.4.9-beta.1: Memory/dreaming, provider notes

v2026.4.9-beta.1 changes how an agent selects, calls, or remembers a provider. The official record describes a provider, model, voice, or context change; the useful test is a small request with the provider boundary recorded.

Because this is a pre-release, use a disposable Gateway first and leave the stable version available for comparison. The release body cannot certify every local combination of provider, channel, platform, and account; use the bounded test below for the path you actually run.

Provider and model consequences

Memory/dreaming

What changed. add a grounded REM backfill lane with historical rem-harness --path, diary commit/reset flows, cleaner durable-fact extraction, and live short-term promotion integration so old daily notes can replay into Dreams and durable memory without a second memory stack.

Check it with. The acceptance test for Memory/dreaming is idempotence under interruption: start once, stop the transport, resume, and compare the final record with the original request.

Control UI/dreaming

What changed. add a structured diary view with timeline navigation, backfill/reset controls, traceable dreaming summaries, and a grounded Scene lane with promotion hints plus a safe clear-grounded action for staged backfill signals.

Check it with. A successful click does not establish Control UI/dreaming. Compare the state before and after a reload, then verify that a user can tell what happened without reading internal logs.

QA/lab

What changed. add character-vibes evaluation reports with model selection and parallel runs so live QA can compare candidate behavior faster.

Check it with. A catalog label for QA/lab is only the first signal. Confirm the account, endpoint, context limit, and tool policy that the running Gateway actually selected.

Browser/security

What changed. re-run blocked-destination safety checks after interaction-driven main-frame navigations from click, evaluate, hook-triggered click, and batched action flows, so browser interactions cannot bypass the SSRF quarantine when they land on forbidden URLs.

Check it with. Read Browser/security as an authorization checkpoint: prove who may act, what the action can reach, and how the rejected attempt is surfaced to the operator.

What changes outside the chat box

Security/dotenv

block runtime-control env vars plus browser-control override and skip-server env vars from untrusted workspace .env files, and reject unsafe URL-style browser control override specifiers before lazy loading.

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

A bounded check for this version

1. Start with a disposable checkpoint: record the version, host, provider, and workspace tied to Memory/dreaming.
2. Check the release's migration notes and make a restorable backup before changing persistent state.
3. Ask the same small question through the affected route and record the account, model id, context, and response time.
4. Compare the answer, tool permissions, and fallback behavior with the baseline before changing a default.
5. If the result differs from the release body, stop the rollout and attach the log, screenshot, or transcript to the version record.

openclaw --version
openclaw gateway status
openclaw security audit

Close the loop with evidence

A useful maintenance record names the changed behavior, the behavior that stayed stable, the identity that approved the test, and the step that would undo it. Preserve that record beside the release tag.

Edge cases in this tag

Browser/security. re-run blocked-destination safety checks after interaction-driven main-frame navigations from click, evaluate, hook-triggered click, and batched action flows, so browser interactions cannot bypass the SSRF quarantine when they land on forbidden URLs. Record the failure that this correction addresses before declaring the upgrade complete.

Security/dotenv. block runtime-control env vars plus browser-control override and skip-server env vars from untrusted workspace .env files, and reject unsafe URL-style browser control override specifiers before lazy loading. This is the edge case to include in a regression check, especially when the release is pre-release.

The authoritative record is the v2026.4.9-beta.1 GitHub release. The release index gives the surrounding sequence, while the session concepts supplies the operational background.