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

T
The Blog of Author Tim Ferriss
IT之家
IT之家
Engineering at Meta
Engineering at Meta
WordPress大学
WordPress大学
博客园 - 三生石上(FineUI控件)
博客园 - 聂微东
C
Check Point Blog
T
Tailwind CSS Blog
博客园 - Franky
H
Help Net Security
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
博客园 - 叶小钗
J
Java Code Geeks
腾讯CDC
罗磊的独立博客
爱范儿
爱范儿
阮一峰的网络日志
阮一峰的网络日志
Martin Fowler
Martin Fowler
酷 壳 – CoolShell
酷 壳 – CoolShell
I
InfoQ
B
Blog
V
Visual Studio Blog
F
Fortinet All Blogs

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
docs: document openai live compat tests · openclaw/opencl...
steipete · 2026-06-05 · via Recent Commits to openclaw:main
Original file line numberDiff line numberDiff line change

@@ -1,3 +1,4 @@

1+

// Live-sweeps discovered model profiles with optional provider/model filters and probes.

12

import { writeSync } from "node:fs";

23

import { normalizeProviderId } from "@openclaw/model-catalog-core/provider-id";

34

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

@@ -132,6 +133,7 @@ function parseModelFilter(raw?: string): Set<string> | null {

132133

function parseExplicitLiveModelRefs(

133134

filter: Set<string> | null,

134135

): Array<{ provider: string; id: string }> {

136+

// Explicit refs use provider/model syntax; bare provider filters are handled elsewhere.

135137

if (!filter) {

136138

return [];

137139

}

@@ -202,6 +204,7 @@ function resolveLiveProviderDiscoveryProviderIds(params: {

202204

explicitRefs: readonly { provider: string; id: string }[];

203205

priorityRefs?: readonly { provider: string; id: string }[];

204206

}): string[] | undefined {

207+

// Narrow startup discovery to providers that can affect the requested live target set.

205208

const providers = new Set<string>();

206209

for (const provider of params.providerFilter ?? []) {

207210

const normalized = normalizeProviderId(provider);

Original file line numberDiff line numberDiff line change

@@ -1,3 +1,4 @@

1+

// Live smoke test for Moonshot OpenAI-compatible completions behavior.

12

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

23

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

34

import {

Original file line numberDiff line numberDiff line change

@@ -1,3 +1,4 @@

1+

// Verifies OpenAI-compatible payloads contain at least one sendable conversation turn.

12

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

23

import { hasOpenAICompatibleConversationTurn } from "./openai-compatible-conversation-turn.js";

34

@@ -40,6 +41,7 @@ describe("hasOpenAICompatibleConversationTurn", () => {

4041

});

4142
4243

it("accepts assistant tool calls even when assistant content is empty", () => {

44+

// Tool-call turns are sendable even when visible assistant text is absent.

4345

expect(

4446

hasOpenAICompatibleConversationTurn([

4547

{

Original file line numberDiff line numberDiff line change

@@ -1,3 +1,4 @@

1+

// Verifies OpenAI-compatible endpoint defaults for streaming usage and reasoning payloads.

12

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

23

import {

34

detectOpenAICompletionsCompat,

@@ -50,6 +51,7 @@ describe("resolveOpenAICompletionsCompatDefaults", () => {

5051

it.each(["vllm", "sglang", "lmstudio"])(

5152

"enables streaming usage compat for manifest-declared local provider %s",

5253

(provider) => {

54+

// Manifest capability, not provider id alone, enables local streaming usage compat.

5355

expect(

5456

resolveOpenAICompletionsCompatDefaults({

5557

provider,

@@ -118,6 +120,7 @@ describe("detectOpenAICompletionsCompat", () => {

118120
119121

describe("xiaomi compat detection", () => {

120122

it("sets thinkingFormat to deepseek for xiaomi-native endpoint", () => {

123+

// Xiaomi's OpenAI-compatible route uses DeepSeek-style reasoning payloads.

121124

expect(

122125

resolveOpenAICompletionsCompatDefaults({

123126

provider: "xiaomi",

Original file line numberDiff line numberDiff line change

@@ -1,3 +1,4 @@

1+

// Live checks for OpenAI reasoning compatibility and repaired tool replay payloads.

12

import type { AgentMessage } from "openclaw/plugin-sdk/agent-core";

23

import { SessionManager } from "openclaw/plugin-sdk/agent-sessions";

34

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

@@ -32,6 +33,7 @@ async function completeReplyWithRetry(params: {

3233

apiKey: string;

3334

message: string;

3435

}): Promise<{ text: string; errorMessage?: string }> {

36+

// Some reasoning targets spend the first tiny budget without visible text.

3537

const runOnce = async (maxTokens: number) => {

3638

const response = await completeSimpleWithTimeout(

3739

params.model,

@@ -74,13 +76,15 @@ async function completeReplyWithRetry(params: {

7476

}

7577
7678

function isKnownLiveBlocker(errorMessage: string): boolean {

79+

// Live lane should skip account/usage blockers rather than fail unrelated compat checks.

7780

return (

7881

/not supported when using codex with a chatgpt account/i.test(errorMessage) ||

7982

/hit your chatgpt usage limit/i.test(errorMessage)

8083

);

8184

}

8285
8386

function resolveTargetModelRef(): { provider: string; modelId: string } {

87+

// Keep env override parsing strict so live runs never silently target the wrong model.

8488

const [provider, ...rest] = TARGET_MODEL_REF.split("/");

8589

const modelId = rest.join("/").trim();

8690

if (!provider?.trim() || !modelId) {

Original file line numberDiff line numberDiff line change

@@ -1,3 +1,4 @@

1+

// Verifies model-specific OpenAI reasoning-effort normalization and disablement.

12

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

23

import {

34

resolveOpenAIReasoningEffortForModel,

@@ -38,6 +39,7 @@ describe("OpenAI reasoning effort support", () => {

3839

});

3940
4041

it("allows provider-native compat values when explicitly declared", () => {

42+

// Some OpenAI-compatible providers expose their own reasoning effort labels.

4143

const model = {

4244

provider: "groq",

4345

id: "qwen/qwen3-32b",