releaseintermediate
[Release] openclaw/openclaw v2026.6.8-beta.1: openclaw 2026.6.8-beta.1
By vincentkocgithub
View original on githubOpenClaw v2026.6.8-beta.1 introduces significant improvements to channel delivery (Telegram rich text, WhatsApp ACP bindings), agent and gateway recovery mechanisms, expanded provider/model support (GLM-5.2, Claude Haiku 4.5), enhanced usage hooks with footer rendering, and UI/mobile stability fixes. The release addresses 50+ issues across messaging, runtime reliability, authentication, memory management, and user interface components, with contributions from 30+ developers.
Key Points
- •Telegram now supports rich text delivery with tables, lists, expandable blockquotes, and CLI backend prompt preservation; WhatsApp honors configured ACP bindings for improved channel delivery
- •Agent and Gateway recovery enhanced across account-scoped DM sends, media completions, restart shutdown aborts, subagent pauses, heartbeat deduplication, and session identity prompts
- •Provider/model handling expanded with GLM-5.2 and Claude Haiku 4.5 support; OpenRouter and Google Vertex provider-prefix normalization; managed SecretRef auth; bounded model discovery
- •Usage hooks now feature native full footer rendering, default templates, fixed-decimal formatting, credential-aware limits, and warnings for broken templates instead of silent failures
- •UI/mobile improvements: workspace file collapse functionality, WebChat backscroll persistence, interactive sidebar session picker, reset soft args preservation, stale dashboard session lineage retention
- •Memory and state management: oversized OpenAI embedding batches split before 431s, QMD memory search available in transient mode, SQLite WAL avoided on NFS volumes, unbounded Infinity chunk limits
- •CLI agent commands support `/btw` in CLI-backed sessions; usage-error exits properly classified as usage failures rather than successful runs
- •Documentation and operator guidance updated with node config examples, hook scope clarification, provider docs refresh, and current Telegram/WhatsApp behavior documentation
- •Test reliability improvements: extended Gateway/full-suite watchdogs, split local full-suite shards when throttled, stabilized plugin auth fixtures, aligned QA Lab bootstrap assertions
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