Win11 本地部署 OpenClaw 通过 WSL 实现飞书机器人

2. WSL 侧配置

2.1 OpenClaw 飞书配置

(base) gpu3090@DESKTOP-8IU6393:~/openclaw$ openclaw onboard
Config warnings:
- plugins.entries.feishu: plugin feishu: duplicate plugin id detected; later plugin may be overridden (/home/gpu3090/.nvm/versions/node/v22.12.0/lib/node_modules/openclaw/extensions/feishu/index.ts)
🦞 OpenClaw 2026.2.23 (b817600) — Your messages, your servers, your control.
│ ◇ Config warnings ────────────────────────────────────────────────────────────────────────────────────╮
│ │ │ │ - plugins.entries.feishu: plugin feishu: duplicate plugin id detected; later plugin may │ │ │ │ be overridden │ │ │ │ (/home/gpu3090/.nvm/versions/node/v22.12.0/lib/node_modules/openclaw/extensions/feishu/index.ts) │ │ │ ├──────────────────────────────────────────────────────────────────────────────────────────────────────╯
│ ◇ Doctor changes ────────────────────────────╮
│ │ │ │ feishu configured, enabled automatically. │ │ │ ├─────────────────────────────────────────────╯
│ ◇ Doctor ──────────────────────────────────────────────╮
│ │ │ │ Run "openclaw doctor --fix" to apply these changes. │ │ │ ├───────────────────────────────────────────────────────╯
Config warnings:
- plugins.entries.feishu: plugin feishu: duplicate plugin id detected; later plugin may be overridden (/home/gpu3090/.nvm/versions/node/v22.12.0/lib/node_modules/openclaw/extensions/feishu/index.ts)
12:00:52 [plugins] plugins.allow is empty; discovered non-bundled plugins may auto-load: feishu (/home/gpu3090/.openclaw/extensions/feishu/index.ts). Set plugins.allow to explicit trusted ids.
Config warnings:
- plugins.entries.feishu: plugin feishu: duplicate plugin id detected; later plugin may be overridden (/home/gpu3090/.nvm/versions/node/v22.12.0/lib/node_modules/openclaw/extensions/feishu/index.ts)
12:01:01 [plugins] feishu_doc: Registered feishu_doc, feishu_app_scopes
12:01:01 [plugins] feishu_wiki: Registered feishu_wiki tool
12:01:01 [plugins] feishu_drive: Registered feishu_drive tool
12:01:01 [plugins] feishu_bitable: Registered bitable tools
12:01:01 [plugins] feishu: loaded without install/load-path provenance; treat as untracked local code and pin trust via plugins.allow or install records (/home/gpu3090/.openclaw/extensions/feishu/index.ts)
...
│ ◇ Feishu: ok Agents: main (default) Heartbeat interval: 30m (main) Session store (main): /home/gpu3090/.openclaw/agents/main/sessions/sessions.json (1 entries) - agent:main:main (1m ago) │ ◇ Control UI ─────────────────────────────────────────────────────────────────────────────────────╮
│ │ │ │ Web UI: http://127.0.0.1:18789/ │ │ │ │ Web UI (with token): │ │ │ │ http://127.0.0.1:18789/#token=*** │ │ │ │ Gateway WS: ws://127.0.0.1:18789 │ │ │ │ Gateway: reachable │ │ │ │ Docs: https://docs.openclaw.ai/web/control-ui │ │ │ ├───────────────────────────────────────────────────────────────────────────────────────────╯
...
(base) gpu3090@DESKTOP-8IU6393:~/openclaw$ openclaw pairing approve feishu ZMBRUDJ8
...
Approved feishu sender ou_ca33d772eb1cdf7fd9dbfa225f53ce4d.

2.2 启动 Ollama 大模型

PS C:\Users\Administrator> wsl -u gpu3090
Now using node v22.12.0 (npm v10.9.0)
(base) gpu3090@DESKTOP-8IU6393:/mnt/c/Users/Administrator$ cd
(base) gpu3090@DESKTOP-8IU6393:~$ OLLAMA_HOST=0.0.0.0:12346 OLLAMA_MODELS=/home/gpu3090/.ollama/models ollama serve
[1]15030
(base) gpu3090@DESKTOP-8IU6393:~$ time=2026-02-24T20:10:33.806+08:00 level=INFO source=routes.go:1663 msg="server config"env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY:http://127.0.0.1:7897 HTTP_PROXY:http://127.0.0.1:7897 NO_PROXY:172.31.*,172.30.*,172.29.*,172.28.*,172.27.*,172.26.*,172.25.*,172.24.*,172.23.*,172.22.*,172.21.*,172.20.*,172.19.*,172.18.*,172.17.*,172.16.*,10.*,192.168.*,127.*,localhost,<local> OLLAMA_CONTEXT_LENGTH:0 OLLAMA_DEBUG:INFO OLLAMA_EDITOR: OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:12346 OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/home/gpu3090/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NO_CLOUD:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false OLLAMA_VULKAN:false ROCR_VISIBLE_DEVICES: http_proxy:http://127.0.0.1:7897 https_proxy:http://127.0.0.1:7897 no_proxy:172.31.*,172.30.*,172.29.*,172.28.*,172.27.*,172.26.*,172.25.*,172.24.*,172.23.*,172.22.*,172.21.*,172.20.*,172.19.*,172.18.*,172.17.*,172.16.*,10.*,192.168.*,127.*,localhost,<local>]"time=2026-02-24T20:10:33.810+08:00 level=INFO source=routes.go:1665 msg="Ollama cloud disabled: false"
time=2026-02-24T20:10:34.150+08:00 level=INFO source=images.go:473 msg="total blobs: 53"
time=2026-02-24T20:10:34.313+08:00 level=INFO source=images.go:480 msg="total unused blobs removed: 0"
time=2026-02-24T20:10:34.458+08:00 level=INFO source=routes.go:1718 msg="Listening on [::]:12346 (version 0.16.3)"
time=2026-02-24T20:10:34.473+08:00 level=INFO source=runner.go:67 msg="discovering available GPUs..."
time=2026-02-24T20:10:34.502+08:00 level=INFO source=server.go:431 msg="starting runner"cmd="/usr/local/bin/ollama runner --ollama-engine --port 46037"
time=2026-02-24T20:10:36.614+08:00 level=INFO source=runner.go:106 msg="experimental Vulkan support disabled. To enable, set OLLAMA_VULKAN=1"
time=2026-02-24T20:10:36.615+08:00 level=INFO source=server.go:431 msg="starting runner"cmd="/usr/local/bin/ollama runner --ollama-engine --port 46237"
time=2026-02-24T20:10:38.176+08:00 level=INFO source=server.go:431 msg="starting runner"cmd="/usr/local/bin/ollama runner --ollama-engine --port 46265"
time=2026-02-24T20:10:38.186+08:00 level=INFO source=server.go:431 msg="starting runner"cmd="/usr/local/bin/ollama runner --ollama-engine --port 45607"
time=2026-02-24T20:10:38.416+08:00 level=INFO source=types.go:42 msg="inference compute"id=GPU-67135303-3c02-f35c-3e58-dc2c1b4892fc filter_id=""library=CUDA compute=8.9name=CUDA0 description="NVIDIA GeForce RTX 4090 D"libdirs=ollama,cuda_v13 driver=13.0pci_id=0000:07:00.0 type=discrete total="24.0 GiB"available="20.5 GiB"
time=2026-02-24T20:10:38.416+08:00 level=INFO source=routes.go:1768 msg="vram-based default context"total_vram="24.0 GiB"default_num_ctx=32768
time=2026-02-24T20:10:55.284+08:00 level=INFO source=server.go:431 msg="starting runner"cmd="/usr/local/bin/ollama runner --ollama-engine --port 45515"
time=2026-02-24T20:10:55.902+08:00 level=INFO source=server.go:247 msg="enabling flash attention"
time=2026-02-24T20:10:55.903+08:00 level=INFO source=server.go:431 msg="starting runner"cmd="/usr/local/bin/ollama runner --ollama-engine --model /home/gpu3090/.ollama/models/blobs/sha256-e7b273f9636059a689e3ddcab3716e4f65abe0143ac978e46673ad0e52d09efb --port 46267"
time=2026-02-24T20:10:55.903+08:00 level=INFO source=sched.go:491 msg="system memory"total="62.7 GiB"free="60.9 GiB"free_swap="16.0 GiB"
time=2026-02-24T20:10:55.903+08:00 level=INFO source=sched.go:498 msg="gpu memory"id=GPU-67135303-3c02-f35c-3e58-dc2c1b4892fc library=CUDA available="20.0 GiB"free="20.4 GiB"minimum="457.0 MiB"overhead="0 B"
time=2026-02-24T20:10:55.903+08:00 level=INFO source=server.go:757 msg="loading model""model layers"=25requested=-1
time=2026-02-24T20:10:55.919+08:00 level=INFO source=runner.go:1411 msg="starting ollama engine"
time=2026-02-24T20:10:55.941+08:00 level=INFO source=runner.go:1446 msg="Server listening on 127.0.0.1:46267"
time=2026-02-24T20:10:55.949+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:32768 KvCacheType: NumThreads:12 GPULayers:25[ID:GPU-67135303-3c02-f35c-3e58-dc2c1b4892fc Layers:25(0..24)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-02-24T20:10:56.075+08:00 level=INFO source=ggml.go:136 msg=""architecture=gptoss file_type=MXFP4 name=""description=""num_tensors=459num_key_values=32 load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-haswell.so ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 1 CUDA devices: Device 0: NVIDIA GeForce RTX 4090 D, compute capability 8.9, VMM: yes, ID: GPU-67135303-3c02-f35c-3e58-dc2c1b4892fc load_backend: loaded CUDA backend from /usr/local/lib/ollama/cuda_v13/libggml-cuda.so
time=2026-02-24T20:10:56.244+08:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=750,800,860,870,890,900,1000,1030,1100,1200,1210 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128compiler=cgo(gcc)"
time=2026-02-24T20:10:58.623+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:alloc LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:32768 KvCacheType: NumThreads:12 GPULayers:25[ID:GPU-67135303-3c02-f35c-3e58-dc2c1b4892fc Layers:25(0..24)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-02-24T20:10:59.089+08:00 level=INFO source=runner.go:1284 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:32768 KvCacheType: NumThreads:12 GPULayers:25[ID:GPU-67135303-3c02-f35c-3e58-dc2c1b4892fc Layers:25(0..24)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-02-24T20:10:59.089+08:00 level=INFO source=ggml.go:482 msg="offloading 24 repeating layers to GPU"
time=2026-02-24T20:10:59.089+08:00 level=INFO source=ggml.go:489 msg="offloading output layer to GPU"
time=2026-02-24T20:10:59.089+08:00 level=INFO source=ggml.go:494 msg="offloaded 25/25 layers to GPU"
time=2026-02-24T20:10:59.089+08:00 level=INFO source=device.go:240 msg="model weights"device=CUDA0 size="11.8 GiB"
time=2026-02-24T20:10:59.089+08:00 level=INFO source=device.go:245 msg="model weights"device=CPU size="1.1 GiB"
time=2026-02-24T20:10:59.089+08:00 level=INFO source=device.go:251 msg="kv cache"device=CUDA0 size="876.0 MiB"
time=2026-02-24T20:10:59.089+08:00 level=INFO source=device.go:262 msg="compute graph"device=CUDA0 size="202.3 MiB"
time=2026-02-24T20:10:59.089+08:00 level=INFO source=device.go:267 msg="compute graph"device=CPU size="5.6 MiB"
time=2026-02-24T20:10:59.089+08:00 level=INFO source=device.go:272 msg="total memory"size="13.9 GiB"
time=2026-02-24T20:10:59.089+08:00 level=INFO source=sched.go:566 msg="loaded runners"count=1
time=2026-02-24T20:10:59.089+08:00 level=INFO source=server.go:1350 msg="waiting for llama runner to start responding"
time=2026-02-24T20:10:59.090+08:00 level=INFO source=server.go:1384 msg="waiting for server to become available"status="llm server loading model"
time=2026-02-24T20:13:29.638+08:00 level=INFO source=server.go:1388 msg="llama runner started in 150.89 seconds"
[GIN]2026/02/24 - 20:13:33 |200| 2m36s |127.0.0.1 | POST "/v1/chat/completions"
[GIN]2026/02/24 - 20:14:13 |200|2.66893432s |127.0.0.1 | POST "/v1/chat/completions"
[GIN]2026/02/24 - 20:14:15 |200|1.55337028s |127.0.0.1 | POST "/v1/chat/completions"
[GIN]2026/02/24 - 20:14:19 |200|3.807682829s |127.0.0.1 | POST "/v1/chat/completions"
[GIN]2026/02/24 - 20:16:44 |200|4.57320368s |127.0.0.1 | POST "/v1/chat/completions"
ggml_backend_cuda_device_get_memory device GPU-67135303-3c02-f35c-3e58-dc2c1b4892fc utilizing NVML memory reporting free: 7589896192 total: 25757220864
time=2026-02-24T20:21:55.251+08:00 level=INFO source=server.go:431 msg="starting runner"cmd="/usr/local/bin/ollama runner --ollama-engine --port 46347"
time=2026-02-24T20:23:16.264+08:00 level=INFO source=server.go:431 msg="starting runner"cmd="/usr/local/bin/ollama runner --ollama-engine --port 44657"
time=2026-02-24T20:23:16.818+08:00 level=INFO source=server.go:247 msg="enabling flash attention"
time=2026-02-24T20:23:16.819+08:00 level=INFO source=server.go:431 msg="starting runner"cmd="/usr/local/bin/ollama runner --ollama-engine --model /home/gpu3090/.ollama/models/blobs/sha256-e7b273f9636059a689e3ddcab3716e4f65abe0143ac978e46673ad0e52d09efb --port 44781"
time=2026-02-24T20:23:16.820+08:00 level=INFO source=sched.go:491 msg="system memory"total="62.7 GiB"free="60.9 GiB"free_swap="16.0 GiB"
time=2026-02-24T20:23:16.820+08:00 level=INFO source=sched.go:498 msg="gpu memory"id=GPU-67135303-3c02-f35c-3e58-dc2c1b4892fc library=CUDA available="20.0 GiB"free="20.4 GiB"minimum="457.0 MiB"overhead="0 B"