You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
-**OpenRouter**: <imgsrc="public/provider-logos/openrouter.png"alt="OpenRouter logo"width="20"height="20" /> Use OpenRouter as a first-class built-in provider with its standard OpenAI-compatible endpoint and routed model IDs such as `openai/gpt-4.1-mini`.
187
187
-**Hermes Agent**: <imgsrc="public/provider-logos/hermes-agent.png"alt="Hermes Agent logo"width="20"height="20" /> Connect Hermes through its OpenAI-compatible API server, locally or through a reachable remote `/v1` endpoint.
188
188
-**Delegation**: built-in delegation to Claude Code, Codex CLI, OpenCode CLI, Gemini CLI, Cursor Agent CLI, Qwen Code CLI, and native SwarmClaw subagents.
Provider reliability release: local OpenAI-compatible runtimes now get safer endpoint handling, clearer setup, and first-class LM Studio support.
413
+
414
+
-**LM Studio provider.** LM Studio is available in setup, provider settings, agent editing, model discovery, and connection checks with an optional API key.
415
+
-**Endpoint normalization.** LM Studio and OpenAI-compatible OpenAI overrides normalize bare hosts like `http://127.0.0.1:1234` to `/v1` before calling models or chat completions.
416
+
-**Provider switch isolation.** Switching an agent from a local endpoint back to a fixed cloud provider clears stale per-agent endpoints and fallback keys.
417
+
-**Manual model flow.** Provider model saves now preserve explicit empty endpoint resets and optional-key providers can be tested without creating a credential.
418
+
410
419
### v1.9.19 Highlights
411
420
412
421
Output hygiene release: final assistant responses now use the shared internal metadata scrubber before persistence, UI reset, connector delivery, and completion hooks.
Copy file name to clipboardExpand all lines: package.json
+1-1Lines changed: 1 addition & 1 deletion
Original file line number
Diff line number
Diff line change
@@ -1,6 +1,6 @@
1
1
{
2
2
"name": "@swarmclawai/swarmclaw",
3
-
"version": "1.9.19",
3
+
"version": "1.9.20",
4
4
"description": "Build and run autonomous AI agents with OpenClaw, Hermes, multiple model providers, orchestration, delegation, memory, skills, schedules, and chat connectors.",
<pclassName="text-[13px] text-text-3/70 mt-2">The URL of your OpenClaw gateway</p>
1738
1751
)}
1739
1752
{provider==='hermes'&&(
1740
1753
<pclassName="text-[13px] text-text-3/70 mt-2">Point this at the Hermes API server, usually <codeclassName="text-text-2">http://127.0.0.1:8642/v1</code>.</p>
1741
1754
)}
1755
+
{provider==='lmstudio'&&(
1756
+
<pclassName="text-[13px] text-text-3/70 mt-2">Point this at the LM Studio local server. A bare host is normalized to <codeclassName="text-text-2">/v1</code>.</p>
Copy file name to clipboardExpand all lines: src/components/auth/setup-wizard/step-connect.tsx
+6Lines changed: 6 additions & 0 deletions
Original file line number
Diff line number
Diff line change
@@ -335,6 +335,12 @@ export function StepConnect({
335
335
<pclassName="text-[12px] text-text-3">Use any reachable local or remote API-server endpoint exposed by Hermes.</p>
336
336
</div>
337
337
)}
338
+
{provider==='lmstudio'&&(
339
+
<divclassName="mt-2 space-y-0.5">
340
+
<pclassName="text-[12px] text-text-3">LM Studio's local server defaults to <codeclassName="text-text-2">http://127.0.0.1:1234/v1</code>.</p>
341
+
<pclassName="text-[12px] text-text-3">If you paste a host without <codeclassName="text-text-2">/v1</code>, SwarmClaw normalizes it before testing and chat.</p>
0 commit comments