OpenClaw v2026.7.1-1: Memory Core startup repair, recovery notes

v2026.7.1-1 is easiest to understand through failure. The official record describes a provider, model, voice, or context change; the sections below spell out what to save, what to interrupt, and what must remain available afterward.

Stable status describes the release line, not every local provider or channel. Check the version-specific notes before upgrading. Treat the version as one input to the decision. Local credentials, enabled plugins, channels, and host support still need their own evidence.

Failure and recovery path

01 / Codex progress replies

Source signal. keep app-server turns running after delivered progress messages so GPT/Codex reaches its authoritative terminal response instead of stopping mid-turn.

The useful evidence for Codex progress replies is the refusal path as well as the success path. Use synthetic credentials and record the policy that made each decision.

02 / Memory Core startup repair

Source signal. recover derived legacy-index and cache-sidecar conflicts without trapping the Gateway in a fatal restart loop, while keeping structural vector-store corruption retryable.

Do not infer continuity from a populated screen when testing Memory Core startup repair. Compare the transcript, session id, and source workspace before and after compaction or refresh.

The limits of the recovery promise

Read the narrow change in context

v2026.7.1-1 is a stable checkpoint with a deliberately small surface. The source names Codex progress replies: keep app-server turns running after delivered progress messages so GPT/Codex reaches its authoritative terminal response instead of stopping mid-turn. A narrow patch still has a clear job: it should remove one failure or preserve one compatibility promise without changing unrelated configuration.

Keep this patch beside the release line it belongs to. Compare the installed tag, package version, and service owner before applying it. If this entry is a correction release, record the broken behavior that led you here, then repeat that exact scenario after the update. That evidence is more useful than a general claim that the package installed successfully.

The adjacent source detail is Memory Core startup repair: recover derived legacy-index and cache-sidecar conflicts without trapping the Gateway in a fatal restart loop, while keeping structural vector-store corruption retryable. Read both signals together, because a hotfix can alter the boundary around a plugin, channel, session, or installer even when the version number looks like a minor suffix.

A small worksheet for this version

• Write the old version, the new version, and the package or tag that actually changed.
• Capture one reproduction before the update and the same reproduction after it.
• Record the first useful log line, the final user-visible result, and any rollback command that was tested.
• Leave unrelated channels, skills, and provider defaults untouched until the correction is understood.

Run the smallest useful rehearsal

1. Write down the baseline for Codex progress replies, including the installed version, host, provider, and workspace.
2. Confirm what can be restored, then take a verified backup before applying the candidate package.
3. Exercise the affected channel with synthetic text and note the thread, sender, reaction, or attachment id that comes back.
4. Restart or reconnect the Gateway, then check for one intended reply rather than a duplicate, missing, or misrouted message.
5. Keep the experiment bounded; an unexpected result belongs in the release record before any wider rollout.

openclaw --version
openclaw gateway status
openclaw security audit

Leave a usable maintenance note

Save the command, output, source link, and environment used for this check. Future operators should be able to tell whether a difference belongs to the release or to local provider, channel, or platform state.

Fix details to carry forward

Codex progress replies. keep app-server turns running after delivered progress messages so GPT/Codex reaches its authoritative terminal response instead of stopping mid-turn. This is the edge case to include in a regression check, especially when the release is pre-release.

Memory Core startup repair. recover derived legacy-index and cache-sidecar conflicts without trapping the Gateway in a fatal restart loop, while keeping structural vector-store corruption retryable. Treat the fix as a boundary condition and retain the source wording beside your local result.

Keep the full v2026.7.1-1 notes with your test result. Read the official release index for neighboring versions and the session concepts for configuration limits.