6d9efe2f5e
* fix(lmstudio): validate setup URLs before discovery Reject malformed interactive endpoints in the provider-owned prompt instead of sending Control UI and CLI operators into an unreachable-server retry. Retain the authored draft and the existing HTTP(S) host-shorthand support. Validate before the permissive path/default normalization can hide a missing host. Reuse the existing host normalizer; no config or SDK surface changes. The registered setup-entry regression fails against the original validator. Real Gateway/Chromium proof rejects the invalid draft inline, then configures the corrected local stub endpoint and sends chat through the selected model. Owner and sibling coverage: 115 tests, 13.804 seconds wall; new case 2 ms. Production delta +19 lines, tests +28, docs +3. The added code owns recoverable prompt validation; existing prompt types move rather than being duplicated. * fix(llama-cpp): validate server URLs in setup Run the existing endpoint parser inside the provider-owned URL validator so Control UI and CLI users can correct an invalid URL without losing setup. Previously the parser threw after submission, closing the editable prompt with a raw Invalid URL error. Preserve host shorthand and the existing HTTP(S) and embedded-credential rules; no config or SDK surface changes. The setup-entry regression fails against the original nonempty validator. Real Gateway/Chromium proof keeps the draft with actionable inline guidance, then activates the corrected local stub endpoint and sends chat through it. Owner and sibling coverage: 115 tests, 13.804 seconds wall; new case 2 ms. Production delta +10 lines, tests +29, docs +4. Growth converts the existing throwing parser into a recoverable prompt result without duplicating policy. * fix(lmstudio): reject credential-bearing setup URLs inline * test(setup): use credential-free embedded-user URLs in validation fixtures Co-authored-by: Peter Steinberger <steipete@gmail.com> |
||
|---|---|---|
| .. | ||
| assets | ||
| src | ||
| index.test.ts | ||
| index.ts | ||
| openclaw.plugin.json | ||
| package.json | ||
| provider-policy-api.test.ts | ||
| provider-policy-api.ts | ||
| README.md | ||
@openclaw/llama-cpp-provider
Official llama.cpp provider for managed and external OpenClaw model servers.
The llama-cpp provider either installs a pinned, integrity-verified
llama-server under OpenClaw's localService supervisor or connects to a
server that you already operate. Both choices use llama-cpp/<model> references
and OpenClaw's normal OpenAI-compatible chat transport. Local embeddings require
the managed choice.
Install
openclaw plugins install @openclaw/llama-cpp-provider
Restart the Gateway after installing or updating the plugin. Interactive setup shows Managed local server and Existing llama-server under one Local llama.cpp group.
Configure managed text inference
After explicit consent, OpenClaw installs the matching server build and a recommended chat model that fits the Gateway's memory, GPU, and free disk space. The download also includes the configured local embedding model, or EmbeddingGemma by default (approximately 0.3 GB). See the provider guide for current recommendations.
When local memory search is configured and chat setup is unavailable or declined, OpenClaw offers a separate embedding-only setup. After explicit consent, it installs only the server and EmbeddingGemma. It leaves the current chat model unchanged. Move any llama.cpp chat routes and remove its configured chat model entries first. Remove an existing external server config before retrying embedding-only setup.
Custom GGUF models remain supported through params.modelPath. Rerun llama.cpp
setup after changing the model so OpenClaw can verify the file and regenerate
the managed router preset.
See the llama.cpp provider guide for platform requirements, custom GGUF configuration, diagnostics, and repair.
Connect to an existing server
Choose Existing llama-server during setup and enter the endpoint and optional API key. OpenClaw passively discovers single-model and router catalogs. It never installs, starts, stops, or reconfigures the external process.
See the llama.cpp provider guide for authentication, router behavior, manual configuration, and troubleshooting.
Configure embeddings
Set memory.search.provider to local. The plugin preserves the historical
local embedding provider and index identity while serving requests through
the managed server's /v1/embeddings endpoint.
Package
- Plugin id:
llama-cpp - Provider id:
llama-cpp - Package:
@openclaw/llama-cpp-provider - Minimum OpenClaw host:
2026.6.2