Bug

Symptom After upgrading to OpenClaw v2026.4.9, TTS (text-to-speech) voice note functionality is completely broken: TTS Outbound (Voice Note Replies): Assistant calls tts tool with channel: "telegram" Tool returns Generated audio reply Expected: Voice note delivered to user via Telegram Actual: Only text response received; no voice note delivered STT Inbound (Voice Note Transcription): pdf tool fails with: Expected PDF but got audio/ogg image tool fails with: Unsupported media type: audio No transcription occurs Gateway Logs Show No Delivery Attempts: ...

Symptom When a Slack channel is configured with requireMention: true, OpenClaw still responds to untagged messages in a thread after it has previously participated in that thread. This behavior violates the expected mention gating logic. Steps to reproduce: Configure OpenClaw with Slack and set requireMention: true for a channel. Add the OpenClaw Bot user to that Slack channel. Start a thread and explicitly mention the bot in the first message (or any thread reply) so OpenClaw replies once. After OpenClaw has replied in that thread, send another reply in the same thread without mentioning the bot. Observe that OpenClaw still replies, even though requireMention: true is set. Expected behavior: OpenClaw should only reply when explicitly mentioned. Prior participation in the thread should not count as a mention. ...

Symptom When using the OpenClaw CLI to add a Slack channel via openclaw channels add, the generated JSON manifest is displayed with decorative pipe characters framing the output. The manifest appears as follows: │ { │ │ “key”: “value” │ │ } │ These pipe characters make the JSON invalid when copied and pasted, forcing users to manually remove all the pipe characters before the JSON can be used. Root Cause Analysis The CLI code renders the JSON manifest using ASCII box-drawing characters for visual presentation in the terminal. While this makes the output look “pretty” in the CLI interface, it includes pipe (|) characters as part of the actual output string. ...

Symptom When using LM Studio or other local LLM providers, OpenClaw’s web interface displays 0 tokens for both lifetime and past 30-day usage statistics, even though the model is actively being used for inference. The usage data remains at zero regardless of how many requests are made through the local provider. Environment Details: LM Studio running on 192.168.X.X:1234 Model: qwen/qwen3.5-35b-a3b OpenClaw version: 2026.3.13 (61d171a) Operating System: Ubuntu 22.04 Root Cause Analysis The root cause is that OpenClaw’s token usage tracking does not properly parse or display the usage field from local provider API responses. ...