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

Y
Y Combinator Blog
The GitHub Blog
The GitHub Blog
Vercel News
Vercel News
D
DataBreaches.Net
MongoDB | Blog
MongoDB | Blog
H
Help Net Security
小众软件
小众软件
美团技术团队
T
The Blog of Author Tim Ferriss
爱范儿
爱范儿
D
Docker
Martin Fowler
Martin Fowler
大猫的无限游戏
大猫的无限游戏
博客园 - 聂微东
Blog — PlanetScale
Blog — PlanetScale
H
Hackread – Cybersecurity News, Data Breaches, AI and More
罗磊的独立博客
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
V
V2EX
S
SegmentFault 最新的问题
云风的 BLOG
云风的 BLOG
B
Blog
雷峰网
雷峰网
The Cloudflare Blog

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(openai): recover invalid reasoning signatures (#92941...
steipete · 2026-06-14 · via Recent Commits to openclaw:main
Original file line numberDiff line numberDiff line change

@@ -1,5 +1,6 @@

11

// Verifies OpenAI-compatible streaming payloads, failures, and transport wrapping.

22

import { createServer } from "node:http";

3+

import OpenAI from "openai";

34

import type { Api, Model } from "openclaw/plugin-sdk/llm";

45

import { describe, expect, it, vi } from "vitest";

56

import {

@@ -4502,6 +4503,86 @@ describe("openai transport stream", () => {

45024503

expect(stripped.input[1]).toEqual(params.input[1]);

45034504

});

45044505
4506+

it("retries thinking_signature_invalid once without encrypted reasoning content", async () => {

4507+

const request = {

4508+

model: "gpt-5.5",

4509+

stream: true,

4510+

input: [

4511+

{

4512+

type: "reasoning",

4513+

id: "rs_prior",

4514+

encrypted_content: "ciphertext",

4515+

summary: [],

4516+

},

4517+

{

4518+

type: "message",

4519+

id: "msg_prior",

4520+

role: "assistant",

4521+

content: [{ type: "output_text", text: "visible answer" }],

4522+

},

4523+

{

4524+

type: "function_call",

4525+

id: "fc_prior",

4526+

call_id: "call_abc",

4527+

name: "price_lookup",

4528+

arguments: "{}",

4529+

},

4530+

],

4531+

};

4532+

const recoveredStream = streamChunks([]);

4533+

const create = vi

4534+

.fn()

4535+

.mockRejectedValueOnce(

4536+

new OpenAI.BadRequestError(

4537+

400,

4538+

{

4539+

code: "thinking_signature_invalid",

4540+

message:

4541+

"The encrypted content for item rs_prior could not be verified. Reason: Encrypted content could not be decrypted or parsed.",

4542+

type: "invalid_request_error",

4543+

},

4544+

undefined,

4545+

new Headers(),

4546+

),

4547+

)

4548+

.mockResolvedValueOnce(recoveredStream);

4549+
4550+

await expect(

4551+

testing.createResponsesStreamWithEncryptedContentRetry({

4552+

client: { responses: { create } } as never,

4553+

request: request as never,

4554+

requestOptions: undefined,

4555+

model: {

4556+

id: "gpt-5.5",

4557+

name: "GPT-5.5",

4558+

api: "openai-responses",

4559+

provider: "openai",

4560+

baseUrl: "https://api.openai.com/v1",

4561+

reasoning: true,

4562+

input: ["text"],

4563+

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

4564+

contextWindow: 200_000,

4565+

maxTokens: 8192,

4566+

},

4567+

}),

4568+

).resolves.toBe(recoveredStream);

4569+
4570+

expect(create).toHaveBeenCalledTimes(2);

4571+

expect(create.mock.calls[0]?.[0]).toBe(request);

4572+

expect(create.mock.calls[1]?.[0]).toEqual({

4573+

...request,

4574+

input: [

4575+

{

4576+

type: "reasoning",

4577+

id: "rs_prior",

4578+

summary: [],

4579+

},

4580+

request.input[1],

4581+

request.input[2],

4582+

],

4583+

});

4584+

});

4585+
45054586

it("normalizes overlong Copilot Responses replay tool ids before dispatch", () => {

45064587

const longToolItemId = "iVec" + "A".repeat(360);

45074588

const longToolCallId = `call_ug6lFGKwZDjHfzW8H0PDQRwN|${longToolItemId}`;