releaseintermediate
[Release] openclaw/openclaw v2026.4.25-beta.3: openclaw 2026.4.25-beta.3
By steipetegithub
View original on githubOpenClaw v2026.4.25-beta.3 introduces major upgrades to text-to-speech (TTS) with new providers and chat-scoped controls, migrates plugin management to a cold persisted registry for faster startup, expands OpenTelemetry observability across model calls and tool loops, enhances browser automation safety with iframe-aware snapshots, and hardens installation/update processes across multiple platforms. The release also adds PWA/Web Push support to the control UI and includes new CLI tools for setup and diagnostics.
Key Points
- •TTS system completely redesigned with `/tts latest` read-aloud, chat-scoped auto-TTS toggles (`/tts chat on|off|default`), per-agent and per-account overrides, and 8 new providers (Azure Speech, Xiaomi, Local CLI, Inworld, Volcengine, ElevenLabs v3)
- •Plugin registry migrated from manifest scanning to cold persisted registry, eliminating broad manifest scans during startup and making plugin discovery, updates, and metadata deterministic
- •OpenTelemetry coverage expanded across model calls, token usage, tool loops, harness runs, exec processes, and memory pressure with bounded low-cardinality attributes and signal-specific OTLP endpoint overrides
- •Browser automation hardened with safe tab URLs, iframe-aware role snapshots, CDP readiness tuning, headless one-shot launch mode, and deeper diagnostic probes via `openclaw browser doctor --deep`
- •Control UI and CLI enhanced with PWA/Web Push support, TUI-based first-run setup, context mode selection, Crestodian repair workflows, and shorter startup greeting
- •Installation/update process hardened across Windows, macOS, Linux, Docker with bundled plugin runtime dependency management, Node service restarts, LaunchAgent token rotation, and mixed-version gateway verification
- •Plugin hooks expanded with before-agent-finalize hooks, cron jobId context, bounded permission fingerprints, and Codex MCP relay support
- •New CLI commands added: `openclaw plugins registry` for registry inspection, `openclaw browser start --headless` for one-shot launch, and enhanced `openclaw doctor --fix` for plugin index refresh
- •Discord voice channels now support per-channel LLM override via `channels.discord.voice.model` while maintaining separate STT/TTS media settings
- •Bundled Prometheus plugin added with protected gateway scrape route for low-cardinality metrics collection and diagnostics
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)
TTS Configuration Exampleyamlconfig
# Per-agent TTS override
agents:
list:
- id: agent-1
tts:
provider: azure-speech
voice: en-US-AriaNeural
# Channel and account TTS overrides
channels:
discord:
accounts:
account-123:
tts:
provider: elevenlabs-v3
voice: custom-voice-id
# Global TTS configuration
messages:
tts:
provider: azure-speech
voice: en-US-GuyNeuralBrowser Automation CLI Commandscommand
# One-shot headless browser launch
openclaw browser start --headless
# Deep browser diagnostics with live snapshot probing
openclaw browser doctor --deep
# Raise CDP readiness timeout for slower hosts (e.g., Raspberry Pi)
openclaw browser config set --cdp-readiness-timeout 10000Plugin Registry and CLI Commandscommand
# Inspect persisted plugin registry
openclaw plugins registry
# List plugins from cold registry (default)
openclaw plugins list
# Refresh plugin index and cold registry
openclaw doctor --fix
# List models for specific provider using installed plugin index
openclaw models list --all --provider <provider-id>OpenTelemetry Configurationyamlconfig
# Signal-specific OTLP endpoint overrides
diagnostics:
otel:
traces:
endpoint: http://localhost:4317
metrics:
endpoint: http://localhost:4317
logs:
endpoint: http://localhost:4317
# Enable latest GenAI semantic conventions
env:
OTEL_SEMCONV_STABILITY_OPT_IN: gen_ai_latest_experimentalDiscord Voice Channel LLM Overrideyamlconfig
# Override LLM for Discord voice channel responses
channels:
discord:
voice:
model: gpt-4-turbo
# STT and TTS remain on existing media settings
stt:
provider: openai-whisper
tts:
provider: elevenlabs