惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

Microsoft Azure Blog
Microsoft Azure Blog
J
Java Code Geeks
量子位
腾讯CDC
C
Check Point Blog
小众软件
小众软件
IT之家
IT之家
I
InfoQ
Hugging Face - Blog
Hugging Face - Blog
Stack Overflow Blog
Stack Overflow Blog
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
GbyAI
GbyAI
Apple Machine Learning Research
Apple Machine Learning Research
大猫的无限游戏
大猫的无限游戏
博客园_首页
S
SegmentFault 最新的问题
The Cloudflare Blog
阮一峰的网络日志
阮一峰的网络日志
aimingoo的专栏
aimingoo的专栏
P
Proofpoint News Feed
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
Google DeepMind News
Google DeepMind News
T
Tailwind CSS Blog
Martin Fowler
Martin Fowler

Recent Commits to openclaw:main

test: merge chat side-result checks · openclaw/openclaw@ddd2c2a test: merge cron history checks · openclaw/openclaw@f7eb746 test: merge responsive navigation shell checks · openclaw/openclaw@c2e4b47 docs(changelog): add codex oauth fixes · openclaw/openclaw@628e6cd test: merge navigation routing cases · openclaw/openclaw@5d8cecb Tests: mock channel registry bundled fallback · openclaw/openclaw@2b08233 Secrets: avoid broad web search discovery for single plugin config · openclaw/openclaw@a464f59 test: merge config view browser checks · openclaw/openclaw@20cf511 fix(status): align oauth health with runtime · openclaw/openclaw@eed7116 feat: add macOS screen snapshots for monitor preview (#67954) thanks … · openclaw/openclaw@f377db1 fix: report shared auth scopes in hello-ok (#67810) thanks @BunsDev · openclaw/openclaw@0b6c39b Auto-reply: avoid eager bundled route fallback · openclaw/openclaw@3ea1bf4 Tests: narrow session binding contract setup · openclaw/openclaw@54e4e16 fix(macOS): enable undo/redo in webchat composer text input (#34962) · openclaw/openclaw@00951dc Tests: speed up channel setup promotion · openclaw/openclaw@82b529a Docs: refresh agent instructions · openclaw/openclaw@5775fe2 fix(auth): serialize OAuth refresh across agents to fix #26322 (#67876) · openclaw/openclaw@8e79080 test: allow ollama public surface boundary test · openclaw/openclaw@7d4f1a6 Docs: add test performance guardrails · openclaw/openclaw@89706d3 Tests: restore context-engine usage proof · openclaw/openclaw@e4c4f95 Tests: slim context engine runtime coverage · openclaw/openclaw@74c198f ci: retry failed custom checkouts · openclaw/openclaw@0ee5baf test: trim duplicate provider auth onboarding cases · openclaw/openclaw@1ffc02e matrix: fix sessions_spawn --thread subagent session spawning (#67643) · openclaw/openclaw@1ce2596 test: reduce auth choice fixture churn · openclaw/openclaw@857b9cd test: mock health status config boundaries · openclaw/openclaw@9d5ab4a test: mock onboard config io boundary · openclaw/openclaw@299694d test: mock legacy state plugin boundaries · openclaw/openclaw@2713089 test: mock channel install boundaries · openclaw/openclaw@b945248 test: mock doctor preview channel boundaries · openclaw/openclaw@b1a3ad4
fix(deepseek): backfill v4 reasoning for proxy models · o...
steipete · 2026-05-10 · via Recent Commits to openclaw:main

@@ -4,6 +4,7 @@ import { streamSimple } from "@mariozechner/pi-ai";

44

import type { SettingsManager } from "@mariozechner/pi-coding-agent";

55

import type { ThinkLevel } from "../../auto-reply/thinking.js";

66

import type { OpenClawConfig } from "../../config/types.openclaw.js";

7+

import { createDeepSeekV4OpenAICompatibleThinkingWrapper } from "../../plugin-sdk/provider-stream-shared.js";

78

import {

89

prepareProviderExtraParams as prepareProviderExtraParamsRuntime,

910

type ProviderRuntimePluginHandle,

@@ -689,6 +690,12 @@ function applyPostPluginStreamWrappers(

689690

ctx.agent.streamFn = createOpenAICompletionsToolsCompatWrapper(ctx.agent.streamFn);

690691691692

if (!ctx.providerWrapperHandled) {

693+

ctx.agent.streamFn = createDeepSeekV4OpenAICompatibleThinkingWrapper({

694+

baseStreamFn: ctx.agent.streamFn,

695+

thinkingLevel: ctx.thinkingLevel,

696+

shouldPatchModel: isDeepSeekV4OpenAICompatibleModel,

697+

});

698+692699

// Guard Google-family payloads against invalid negative thinking budgets

693700

// emitted by upstream model-ID heuristics for Gemini 3.1 variants.

694701

ctx.agent.streamFn = createGoogleThinkingPayloadWrapper(ctx.agent.streamFn, ctx.thinkingLevel);

@@ -752,6 +759,22 @@ function applyPostPluginStreamWrappers(

752759

log.warn(`ignoring invalid parallel_tool_calls param: ${summary}`);

753760

}

754761762+

function normalizeDeepSeekV4CandidateId(modelId: unknown): string | undefined {

763+

if (typeof modelId !== "string") {

764+

return undefined;

765+

}

766+

const withoutSuffix = modelId.trim().toLowerCase().split(":", 1)[0];

767+

return withoutSuffix.split("/").pop();

768+

}

769+770+

function isDeepSeekV4OpenAICompatibleModel(model: Parameters<StreamFn>[0]): boolean {

771+

const normalizedModelId = normalizeDeepSeekV4CandidateId(model.id);

772+

return (

773+

model.api === "openai-completions" &&

774+

(normalizedModelId === "deepseek-v4-flash" || normalizedModelId === "deepseek-v4-pro")

775+

);

776+

}

777+755778

/**

756779

* Apply extra params (like temperature) to an agent's streamFn.

757780

* Also applies verified provider-specific request wrappers, such as OpenRouter attribution.