releaseintermediate
[Release] openclaw/openclaw v2026.4.29: openclaw 2026.4.29
By steipetegithub
View original on githubOpenClaw v2026.4.29 is a major release introducing active-run steering for messaging, people-aware memory wiki with provenance tracking, expanded provider coverage (NVIDIA, Bedrock), and enhanced reliability across gateway, channels, and security. Key improvements include opt-in follow-up commitments with heartbeat delivery, per-conversation Active Memory filters, faster model manifest paths, and comprehensive channel fixes for Slack, Telegram, Discord, WhatsApp, and Teams. Security enhancements add OpenGrep scanning and safer exec/pairing handling.
Key Points
- •Messaging defaults to active-run `steer` mode with 500ms followup debounce; legacy one-at-a-time steering available as `queue` mode
- •Memory evolves into people-aware wiki with provenance views, canonical aliases, person cards, relationship graphs, and privacy reports
- •Active Memory now supports per-conversation `allowedChatIds`/`deniedChatIds` filters and returns bounded partial recall summaries on timeout
- •NVIDIA provider onboarding added with API-key setup, static catalog metadata, and model-ref picker support
- •Opt-in inferred follow-up commitments with hidden batched extraction, per-agent/per-channel scoping, and heartbeat delivery for reminders
- •Gateway startup diagnostics timeline added (opt-in) to diagnose slow-start issues without bespoke instrumentation
- •Channel reliability improvements: Slack Block Kit limits, Telegram proxy/webhook/polling resilience, Discord rate-limit handling, WhatsApp delivery/liveness
- •Security: OpenGrep scanning with rulepack validation, GHSA triage policy refinement, safer exec/pairing/owner-scope handling
- •Restricted tool profiles (`messaging`, `minimal`) no longer implicitly allow `tools.exec` and `tools.fs`; explicit `alsoAllow` entries required
- •SQLite-backed plugin state store added for restart-safe keyed registries with TTL, eviction, and automatic plugin isolation
Found this useful? Add it to a playbook for a step-by-step implementation guide.
Workflow Diagram
Start Process
Step A
Step B
Step C
Complete
Concepts
Artifacts (5)
commitments_configyamlconfig
commitments:
enabled: true
maxPerDay: <number>
heartbeatInterval: <duration>active_memory_filteryamlconfig
activeMemory:
allowedChatIds:
- <chat_id_1>
- <chat_id_2>
deniedChatIds:
- <chat_id_3>tool_profile_restrictionyamlconfig
profiles:
messaging:
tools: []
alsoAllow:
- tools.exec
- tools.fs
minimal:
tools: []
alsoAllow:
- tools.execdocker_skip_onboardingbashcommand
docker run -e OPENCLAW_SKIP_ONBOARDING=true openclaw:v2026.4.29nvidia_provider_setupyamlconfig
providers:
nvidia:
apiKey: ${NVIDIA_API_KEY}
catalog: static
modelRefPicker: enabled