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

M
MIT News - Artificial intelligence
罗磊的独立博客
Hugging Face - Blog
Hugging Face - Blog
J
Java Code Geeks
G
Google Developers Blog
美团技术团队
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
腾讯CDC
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
T
The Blog of Author Tim Ferriss
月光博客
月光博客
B
Blog
WordPress大学
WordPress大学
云风的 BLOG
云风的 BLOG
博客园_首页
人人都是产品经理
人人都是产品经理
aimingoo的专栏
aimingoo的专栏
Y
Y Combinator Blog
Jina AI
Jina AI
S
SegmentFault 最新的问题
H
Help Net Security
博客园 - 聂微东
Microsoft Azure Blog
Microsoft Azure Blog
Google DeepMind News
Google DeepMind News

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
test: deduplicate OpenRouter reasoning replay regression ...
steipete · 2026-05-15 · via Recent Commits to openclaw:main

@@ -5658,60 +5658,6 @@ describe("buildOpenAICompletionsParams sanitizes reasoning replay fields", () =>

56585658

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

56595659

});

566056605661-

it("strips empty-string reasoning_content from OpenRouter assistant replay", () => {

5662-

// DeepSeek V4 via OpenRouter injects reasoning_content: "" on tool-call

5663-

// assistant messages. An empty string is technically a "string" but the

5664-

// Chat Completions schema does not accept it, and OpenRouter rejects the

5665-

// replayed message with HTTP 500.

5666-

const params = buildOpenAICompletionsParams(

5667-

openRouterModel,

5668-

{

5669-

systemPrompt: "system",

5670-

messages: [

5671-

{ role: "user", content: "read config" },

5672-

{

5673-

role: "assistant",

5674-

provider: "openrouter",

5675-

api: "openai-completions",

5676-

model: "deepseek/deepseek-v4-pro",

5677-

stopReason: "toolUse",

5678-

timestamp: 0,

5679-

content: [

5680-

{

5681-

type: "thinking",

5682-

thinking: "",

5683-

thinkingSignature: "reasoning_content",

5684-

},

5685-

{

5686-

type: "toolCall",

5687-

id: "call_1",

5688-

name: "read_file",

5689-

arguments: { path: "config.json" },

5690-

},

5691-

],

5692-

},

5693-

{

5694-

role: "toolResult",

5695-

toolCallId: "call_1",

5696-

toolName: "read_file",

5697-

content: [{ type: "text", text: "{ }" }],

5698-

isError: false,

5699-

timestamp: 1,

5700-

},

5701-

{ role: "user", content: "continue" },

5702-

],

5703-

tools: [],

5704-

} as never,

5705-

undefined,

5706-

) as { messages: unknown };

5707-5708-

const msgs = params.messages as Record<string, unknown>[];

5709-

const assistantMsgs = msgs.filter((m) => m.role === "assistant");

5710-

for (const msg of assistantMsgs) {

5711-

expect(msg).not.toHaveProperty("reasoning_content");

5712-

}

5713-

});

5714-57155661

it("preserves OpenRouter array reasoning_details from tool-call signatures", () => {

57165662

const reasoningDetail = { type: "reasoning.encrypted", id: "rs_1", data: "ciphertext" };

57175663

const params = buildOpenAICompletionsParams(