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

雷峰网
雷峰网
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
博客园 - 三生石上(FineUI控件)
博客园 - 聂微东
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
Hugging Face - Blog
Hugging Face - Blog
Apple Machine Learning Research
Apple Machine Learning Research
博客园 - Franky
MyScale Blog
MyScale Blog
A
About on SuperTechFans
博客园_首页
B
Blog RSS Feed
Martin Fowler
Martin Fowler
大猫的无限游戏
大猫的无限游戏
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
Vercel News
Vercel News
C
Check Point Blog
H
Hackread – Cybersecurity News, Data Breaches, AI and More
博客园 - 【当耐特】
M
MIT News - Artificial intelligence
宝玉的分享
宝玉的分享
T
Tailwind CSS Blog
I
InfoQ
罗磊的独立博客

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(release): preserve provider reasoning replay · opencl...
steipete · 2026-05-16 · via Recent Commits to openclaw:main

@@ -5441,6 +5441,32 @@ describe("buildOpenAICompletionsParams sanitizes reasoning replay fields", () =>

54415441

maxTokens: 8192,

54425442

} satisfies Model<"openai-completions">;

544354435444+

const nativeDeepSeekModel = {

5445+

id: "deepseek-v4-flash",

5446+

name: "DeepSeek V4 Flash",

5447+

api: "openai-completions",

5448+

provider: "deepseek",

5449+

baseUrl: "https://api.deepseek.com",

5450+

reasoning: true,

5451+

input: ["text"],

5452+

cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },

5453+

contextWindow: 1_000_000,

5454+

maxTokens: 384_000,

5455+

} satisfies Model<"openai-completions">;

5456+5457+

const nativeZaiModel = {

5458+

id: "glm-5.1",

5459+

name: "GLM 5.1",

5460+

api: "openai-completions",

5461+

provider: "zai",

5462+

baseUrl: "https://api.z.ai/api/paas/v4",

5463+

reasoning: true,

5464+

input: ["text"],

5465+

cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },

5466+

contextWindow: 200_000,

5467+

maxTokens: 131_072,

5468+

} satisfies Model<"openai-completions">;

5469+54445470

const xiaomiModel = {

54455471

id: "mimo-v2.5-pro",

54465472

name: "MiMo V2.5 Pro",

@@ -5589,6 +5615,26 @@ describe("buildOpenAICompletionsParams sanitizes reasoning replay fields", () =>

55895615

}

55905616

});

559156175618+

it.each([

5619+

["DeepSeek", nativeDeepSeekModel],

5620+

["Z.AI", nativeZaiModel],

5621+

] as const)("preserves native %s reasoning_content replay", (_label, model) => {

5622+

const assistant = getAssistantMessage(buildReplayParams(model, "reasoning_content"));

5623+5624+

expect(assistant.reasoning_content).toBe("Need to answer politely.");

5625+

});

5626+5627+

it.each([

5628+

["DeepSeek", nativeDeepSeekModel],

5629+

["Z.AI", nativeZaiModel],

5630+

] as const)("strips non-native %s reasoning replay fields", (_label, model) => {

5631+

const assistant = getAssistantMessage(buildReplayParams(model, "reasoning_details"));

5632+5633+

expect(assistant).not.toHaveProperty("reasoning_details");

5634+

expect(assistant).not.toHaveProperty("reasoning");

5635+

expect(assistant).not.toHaveProperty("reasoning_text");

5636+

});

5637+55925638

it("normalizes OpenRouter reasoning_text to reasoning", () => {

55935639

const assistant = getAssistantMessage(buildReplayParams(openRouterModel, "reasoning_text"));

55945640