vultr/openclaw
1
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-05-06 07:00:43 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: keep gateway model probes raw

Browse Source
This commit is contained in:
Peter Steinberger
2026-04-28 09:08:07 +01:00
parent bce6c10290
commit fb3ea9efb1
15 changed files with 455 additions and 139 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docs/cli/infer.md
View File

@@ -131,7 +131,7 @@ This table maps common inference tasks to the corresponding infer command.
- Gateway-managed state commands default to gateway.
- The normal local path does not require the gateway to be running.
- Local `model run` is a lean one-shot provider completion. It resolves the configured agent model and auth, but does not start a chat-agent turn, load tools, or open bundled MCP servers.
- `model run --gateway` still uses the Gateway agent runtime so it can exercise the same routed runtime path as a normal Gateway-backed turn. MCP servers opened through that runtime are retired after the reply, so repeated scripted invocations do not keep stdio MCP child processes alive.
- `model run --gateway` exercises Gateway routing, saved auth, provider selection, and the embedded runtime, but still runs as a raw model probe: it sends the supplied prompt without prior session transcript, bootstrap/AGENTS context, context-engine assembly, tools, or bundled MCP servers.
## Model
@@ -161,7 +161,7 @@ Notes:
- Local `model run` is the narrowest CLI smoke for provider/model/auth health because it sends only the supplied prompt to the selected model.
- `model run --prompt` must contain non-whitespace text; empty prompts are rejected before local providers or the Gateway are called.
- Local `model run` exits non-zero when the provider returns no text output, so unreachable local providers and empty completions do not look like successful probes.
- Use `model run --gateway` when you need to test Gateway routing, agent-runtime setup, or Gateway-managed provider state instead of the lean local completion path.
- Use `model run --gateway` when you need to test Gateway routing, agent-runtime setup, or Gateway-managed provider state while keeping the model input raw. Use `openclaw agent` or chat surfaces when you want the full agent context, tools, memory, and session transcript.
- `model auth login`, `model auth logout`, and `model auth status` manage saved provider auth state.
## Image