autograd error

[Bug]: Error: Gateway closed (1000):

执行命令如：我就是执行了一个：openclaw browser extension install 再执行 openclaw browser status 命令就开始报错，系统已经重新安装两次了还是这个问题，谁能帮忙看看这个问题 gateway connect failed: Error: gateway closed (1000): ◇ Error: gateway closed (1000 normal closure): no close reason Gateway target: ws://127.0.0.1:18789 Source: local loopback Config: /home/install/.openclaw/openclaw.json Bind: loopback

[Bug]: Why tools.profile (coding) allowlist contains unknown entries ?

2026.3.14, tools.profile (coding) allowlist contains unknown entries (apply_patch, image). These entries are shipped core tools but unavailable in the current runtime/provider/model/config. What matter? Why?

Memory layout cannot be allocated with num_gpu = N

Error: pull model manifest: 412: The model you are attempting to pull requires a newer version of Ollama.

[Bug]: Control UI model switcher sends wrong provider prefix for cross-provider model switching

The Control UI model picker sends bare model IDs (e.g. k2p5) instead of full provider/model keys (e.g. kimi-coding/k2p5), causing the gateway to prepend the wrong provider and reject the switch with "model not allowed".

🐛 Feishu channel fails with tenant_access_token error when HTTP proxy is configured

Feishu (飞书) channel cannot send messages when system HTTP proxy is configured. Error: `Cannot destructure property 'tenant_access_token' of '(intermediate value)' as it is undefined.` **Root cause:** The `@larksuiteoapi/node-sdk` uses axios which respects system proxy settings (`http_proxy`/`https_proxy`). When proxy is enabled (e.g., v2rayN), requests to `open.feishu.cn` are routed through the proxy and fail with HTTP 400 error: `"The plain HTTP request was sent to HTTPS port"`.

Kimi K2.5 streaming event order error: message_start before message_stop

[Bug]: `openclaw configure` does not fully remove fallback models when selecting "Skip for now"

[Bug]: Telegram forum topic loses ACP/OpenCode routing after heavy bound turn; topic recovers only after gateway restart and then fails again under load

**Title** Telegram forum topic loses ACP/OpenCode routing after heavy bound turn; topic recovers only after gateway restart and then fails again under load **Body** I’m seeing a topic-local failure in OpenClaw’s Telegram ACP thread binding. Environment: * Host/runtime: OpenClaw Gateway running locally on Linux (WSL2, kernel 5.15), Node.js v22.22.1; gateway service is `systemd` managed and reported as `running` (`openclaw status`). * OpenClaw version/channel: stable channel, app/npm latest reported as `2026.3.11` (`openclaw status`). * Transport: Telegram bot channel enabled, using forum topics in group `-1003351905082` (Waggelgroep); issue reproduced in topic context (this thread is topic `1`). * Telegram routing config: `channels.telegram.threadBindings.enabled=true` and `channels.telegram.threadBindings.spawnAcpSessions=true` in `~/.openclaw/openclaw.json`. * Group/topic policy: Telegram group policy is allowlisted (`groupPolicy=allowlist`), messages from authorized sender `5558998798`; routing is topic-aware (forum thread context preserved). * ACP/OpenCode path: ACP runtime/plugin is enabled (`acpx` enabled in config); sessions are persisted under `~/.openclaw/agents/opencode/sessions/`. * Session evidence of topic isolation: persisted OpenCode session metadata includes topic-scoped keys (`groupId` values like `-1000000005082:topic:<id>`) and explicit `threadId`, confirming per-topic routing context instead of global group routing. * Operational symptom: after high-volume / long bound turns in a topic, follow-up messages in the same topic stop routing to the bound ACP/OpenCode session; restarting gateway restores routing temporarily (slash-command work), but the very next message kills it again. **Strongest evidence from logs** 1. **Message reaches Telegram gateway path** * OpenClaw logs raw Telegram updates for the bound topic, including ordinary follow-up messages like `"."`. 2. **Message reaches ACP/OpenCode** * OpenCode loads the persistent session, accepts `POST /session/.../message`, starts `session.prompt step=0`, and resolves tools. 3. **OpenCode remains alive after the topic appears dead** * OpenCode continues emitting `message.part.updated`, `message.part.delta`, and tool/subagent activity after the handoff point. 4. **Telegram side wedges** * OpenClaw logs `typing TTL exceeded (60000ms), auto-stopping typing indicator` instead of a normal usable completion in the topic. **Correlation with heavy turns** This seems much more likely on complex turns, especially when sub-agent/task delegation is involved. In the logs, heavier runs create a developer subagent session and generate a denser nested event stream. I’m treating this as a correlation, not definitive proof of cause. **Likely non-causes** * This does **not** look like “OpenCode never launched”. There are logs proving the bound session received the message and continued processing. * This does **not** look like simple agent-permission inheritance from the orchestrator. The developer subagent is created and proceeds with its own work; what is denied there is further `task` delegation, not the whole execution path. * A separate Telegram chunking bug with `---` exists, but that is a different issue; in my case, the more severe failure persists even after isolating around that. Telegram channel settings support different chunking/streaming modes, so this appears distinct from the already-known delivery fragility around formatting/preview. ([[OpenClaw](https://docs.openclaw.ai/channels/telegram?utm_source=chatgpt.com)][1]) **Working theory** This looks like a bug in the Telegram topic-bound ACP bridge/routing layer inside OpenClaw: * inbound topic message is accepted, * bound ACP session receives and processes it, * but outbound propagation or topic-local routing state wedges under heavier nested event streams, * and after that the topic may stop reaching OpenClaw at all until gateway restart.

Ollama API error 400: {"error":"registry.ollama.ai/library/Qwen3.5:0.8b does not support tools"}

[Bug]: issue while adding Custom MCP server

App Router _rsc navigations intermittently fail with "The router state header was sent but could not be parsed" when Proxy matcher is broad on Vercel

Bug: webchat model dropdown sends model name without provider prefix, causing 'model not allowed' error

[Bug]: qwen3.5-27b-gptq deploy fail

[Bug]: openclaw --profile <name> devices list fails with gateway closed (1000) / handshake timeout on 2026.3.13

When using a non-default profile / secondary gateway, `openclaw --profile <name> devices list` fails with: gateway connect failed: Error: gateway closed (1000): [openclaw] Failed to start CLI: Error: gateway closed (1000 normal closure): no close reason

gateway probe/status reports missing operator.read even when local paired device/token has operator.read

`openclaw gateway probe` / `openclaw status --all` report `missing scope: operator.read` even though the local paired device and local operator token on disk clearly include `operator.read`.

web_fetch 工具缺少 ssrfPolicy 配置，TUN 模式下被阻止

[CLI] Gateway connection fails with "gateway closed (1000)" in non-JSON mode (Potential race condition with `withProgress` spinner)

When running CLI commands like `openclaw browser status`, the connection to the local gateway consistently fails with: `Error: gateway closed (1000 normal closure): no close reason` Interestingly, the command works perfectly when the `--json` flag is added. This suggests a race condition or event-loop blockage caused by the terminal progress indica tor (spinner).

[Skills] 37 "Skipping skill path that resolves outside its configured root" warnings from built-in extensions

```markdown

unknown model architecture: 'qwen35moe' when loading imported GGUF with mmproj (vision projector)

Imported Qwen3.5-35B-A3B GGUF models fail to load when a vision projector (mmproj) file is attached. The same model loads fine for text-only (without mmproj), and loads fine with mmproj via llama.cpp's --mmproj flag. Ollama version 0.17.7 Steps to reproduce 1. Download a community Qwen 3.5 GGUF (e.g., from llmfan46/Qwen3.5-35B-A3B-heretic-v2-GGUF) and its mmproj file (Qwen3.5-35B-A3B-mmproj-BF16.gguf) 2. Create a Modelfile: FROM Qwen3.5-35B-A3B-heretic-v2-Q5_K_M.gguf FROM Qwen3.5-35B-A3B-mmproj-BF16.gguf TEMPLATE """{{ .Prompt }}""" 3. ollama create qwen3.5:test -f Modelfile → succeeds 4. ollama run qwen3.5:test → fails Also tried ADAPTER instead of second FROM — same result. Error llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'qwen35moe' Expected behavior The model should load with vision support, same as it does with llama.cpp: llama-server -m Qwen3.5-35B-A3B-heretic-v2-Q5_K_M.gguf --mmproj Qwen3.5-35B-A3B-mmproj-BF16.gguf -c 4096 This works perfectly — text and vision both functional. Notes - Without mmproj, the model loads fine for text (families: ['qwen35moe']) - With mmproj, families becomes ['qwen35moe', 'clip'] and loading fails - The official qwen3.5:35b works with vision because it has native qwen35moe.vision.* tensors embedded in the main GGUF — no clip involved - PR #14517 fixed text-only loading of imported qwen35moe GGUFs but the multimodal/clip runner path was not updated for this architecture - GPU: 2x RTX 5060 16GB