vultr/openclaw
1
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-05-06 10:20:42 +00:00
Code Issues Packages Projects Releases Wiki Activity

refactor: centralize provider stream fallback ownership

Browse Source
This commit is contained in:
Peter Steinberger
2026-04-27 12:11:29 +01:00
parent 8200d878a3
commit e98f976a70
9 changed files with 99 additions and 44 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
extensions/vllm/package.json
View File

@@ -4,9 +4,6 @@
"private": true,
"description": "OpenClaw vLLM provider plugin",
"type": "module",
"dependencies": {
"@mariozechner/pi-ai": "0.70.2"
},
"devDependencies": {
"@openclaw/plugin-sdk": "workspace:*"
},

27
extensions/vllm/stream.ts
View File

@@ -1,8 +1,7 @@
import type { StreamFn } from "@mariozechner/pi-agent-core";
import { streamSimple } from "@mariozechner/pi-ai";
import type { ProviderWrapStreamFnContext } from "openclaw/plugin-sdk/plugin-entry";
import { normalizeProviderId } from "openclaw/plugin-sdk/provider-model-shared";
import { streamWithPayloadPatch } from "openclaw/plugin-sdk/provider-stream-shared";
import { createPayloadPatchStreamWrapper } from "openclaw/plugin-sdk/provider-stream-shared";
type VllmThinkingLevel = ProviderWrapStreamFnContext["thinkingLevel"];
type VllmQwenThinkingFormat = "chat-template" | "top-level";
@@ -79,16 +78,13 @@ export function createVllmQwenThinkingWrapper(params: {
format: VllmQwenThinkingFormat;
thinkingLevel: VllmThinkingLevel;
}): StreamFn {
const underlying = params.baseStreamFn ?? streamSimple;
return (model, context, options) => {
if (model.api !== "openai-completions" || !model.reasoning) {
return underlying(model, context, options);
}
const enableThinking = resolveOpenAICompatibleThinkingEnabled({
thinkingLevel: params.thinkingLevel,
options,
});
return streamWithPayloadPatch(underlying, model, context, options, (payloadObj) => {
return createPayloadPatchStreamWrapper(
params.baseStreamFn,
({ payload: payloadObj, options }) => {
const enableThinking = resolveOpenAICompatibleThinkingEnabled({
thinkingLevel: params.thinkingLevel,
options,
});
if (params.format === "chat-template") {
setQwenChatTemplateThinking(payloadObj, enableThinking);
} else {
@@ -97,8 +93,11 @@ export function createVllmQwenThinkingWrapper(params: {
delete payloadObj.reasoning_effort;
delete payloadObj.reasoningEffort;
delete payloadObj.reasoning;
});
};
},
{
shouldPatch: ({ model }) => model.api === "openai-completions" && model.reasoning,
},
);
}
export function wrapVllmProviderStream(ctx: ProviderWrapStreamFnContext): StreamFn | undefined {