#config-error
Sorted by views, then solution_desc, solution, and root_cause length (desc).
2601 issues
When spawning a subagent with `sessions_spawn` using an NVIDIA provider configured as `"api": "openai-completions"`, OpenClaw sends Anthropic-style message content (arrays with `type` objects) instead of OpenAI-style simple strings. This causes the NVIDIA API to reject requests with HTTP 400 errors. bug was created using openclaw *
The `openclaw gateway restart` command sends SIGTERM to the gateway process but does not verify that the gateway successfully restarts. This can leave the gateway down for extended periods with no error indication or automatic recovery.
Request to add **ACP (Agent Client Protocol) runtime support** for the Feishu (Lark) channel, enabling automatic ACP session routing for external coding harnesses like OpenCode, Claude Code, Codex, etc.
Gateway token validation fails immediately after upgrading from 2026.4.1 to 2026.4.2. All OpenClaw CLI commands return "Gateway closed (1008): unauthorized: gateway token mismatch" error. Token is correctly configured but rejected by gateway. System becomes completely non-functional until manual service restart.
After updating OpenClaw on Windows to the 2026-03-31 build, the Telegram plugin regressed and no longer starts. This setup was working before the update. After the update, Telegram fails to load at startup with: ```text telegram failed to load from C:\Users\Illidan\AppData\Roaming\npm\node_modules\openclaw\dist\extensions\telegram\index.js: Error: Cannot find module 'grammy' Require stack: - C:\Users\Illidan\AppData\Roaming\npm\node_modules\openclaw\dist\sticker-cache-1Tf7t-45.js
Description: After updating to 2026.3.28 (f9b1079), agents cannot execute any commands. The exec tool fails validation with: Validation failed for tool "exec": command: must have required property 'command' Received arguments: {}Environment: • OpenClaw version: 2026.3.28 (f9b1079) • OS: macOS 15.3.2 (Darwin 25.3.0 arm64) • Install method: npm global • Model: kimi-coding/k2p5 Config (tools section): "tools": { "profile": "full", "allow": ["*"], "exec": { "host": "gateway", "security": "full", "ask": "off" } }Tried: • ✅ Latest version 2026.3.28 • ✅ Downgrade to 2026.2.21 • ✅ Config fix (exec settings with ask: "off") • ✅ Multiple gateway restarts • ✅ All "workarounds" from #39691 Result: Still broken. The agent generates commands but they never execute. Impact: Completely blocks autonomous agent functionality.