michal/mcpctl
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(gate): fast no-think selection + dedicated selection Llm #88

Merged
michal merged 2 commits from feat/gate-select-no-think into main 2026-07-24 13:29:59 +00:00
Conversation 0 Commits 2 Files Changed 2 +29 -4
2 changed files with 29 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
src/mcplocal/src/http/project-mcp-endpoint.ts
View File

@@ -147,10 +147,14 @@ export function registerProjectMcpEndpoint(app: FastifyInstance, mcpdClient: Mcp
providerRegistry: effectiveRegistry,
};
if (resolvedModel) pluginConfig.modelOverride = resolvedModel;
// Route gate prompt-selection through this project's server Llm (mcpd
// inference proxy) so cloud/server keys stay at the k8s level; the local
// personal-token provider is the fallback. See credential-tiering.
if (mcpdConfig.llmProvider) pluginConfig.llmProvider = mcpdConfig.llmProvider;
// Route gate prompt-selection through a server Llm (mcpd inference proxy)
// so cloud/server keys stay at the k8s level; the local personal-token
// provider is the fallback. See credential-tiering. A dedicated fast
// (no-think) selection Llm can be pinned globally via
// MCPCTL_GATE_SELECTION_LLM — it overrides the project's chat llmProvider so
// selection stays fast while chat keeps its (thinking) model.
const gateSelectionLlm = process.env['MCPCTL_GATE_SELECTION_LLM'] || mcpdConfig.llmProvider;
if (gateSelectionLlm) pluginConfig.llmProvider = gateSelectionLlm;
const basePlugin = createDefaultPlugin(pluginConfig);
// Optional favourite-index presentation: curated favourite/<tool> + full
// all/<server>/<tool> + a "prefer favourite/" instruction. Composed AFTER

21
src/mcplocal/src/proxymodel/plugins/gate.ts
View File

@@ -21,6 +21,26 @@ import { withTimeout, TimeoutError } from '../../util/with-timeout.js';
* begin_session — on timeout we fall back to deterministic tag matching. */
const GATE_LLM_TIMEOUT_MS = Number(process.env['MCPCTL_GATE_LLM_TIMEOUT_MS'] ?? '8000');
/**
* Extra request fields for the gate's server-Llm selection call. Prompt
* selection is mechanical classification that gains nothing from chain-of-
* thought, so we ask reasoning models to skip thinking (they otherwise burn the
* whole budget reasoning and blow the gate timeout). Sent verbatim by mcpd's
* passthrough adapter → litellm/vLLM. Harmless for models that ignore them, and
* if a backend rejects them the selector falls back to the local provider.
* - `chat_template_kwargs.enable_thinking:false` — Qwen3 hard-off.
* - `reasoning_effort:'low'` — OpenAI o-series / newer vLLM.
* Override with a JSON object in MCPCTL_GATE_SELECT_EXTRA_BODY, or '' to disable.
*/
const GATE_SELECT_EXTRA_BODY: Record<string, unknown> = (() => {
const raw = process.env['MCPCTL_GATE_SELECT_EXTRA_BODY'];
if (raw === '') return {};
if (raw !== undefined) {
try { return JSON.parse(raw) as Record<string, unknown>; } catch { /* use default */ }
}
return { chat_template_kwargs: { enable_thinking: false }, reasoning_effort: 'low' };
})();
export interface GatePluginConfig {
gated?: boolean;
providerRegistry?: ProviderRegistry | null;
@@ -308,6 +328,7 @@ async function handleBeginSession(
temperature: o.temperature,
max_tokens: o.maxTokens,
stream: false,
...GATE_SELECT_EXTRA_BODY, // ask reasoning models for a fast, no-think answer
});
return pickCompletionText(resp);
}