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

量子位
云风的 BLOG
云风的 BLOG
小众软件
小众软件
IT之家
IT之家
T
Tailwind CSS Blog
WordPress大学
WordPress大学
S
SegmentFault 最新的问题
美团技术团队
博客园 - 叶小钗
V
V2EX
博客园 - Franky
大猫的无限游戏
大猫的无限游戏
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
阮一峰的网络日志
阮一峰的网络日志
博客园 - 【当耐特】
罗磊的独立博客
博客园_首页
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
爱范儿
爱范儿
宝玉的分享
宝玉的分享
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
Jina AI
Jina AI
月光博客
月光博客
有赞技术团队
有赞技术团队

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 embedded runner history tests · openclaw/o...
steipete · 2026-06-05 · via Recent Commits to openclaw:main

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

1+

// Behavior coverage for replay-history sanitization across provider policies.

12

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

23

import type {

34

AssistantMessage,

@@ -42,6 +43,8 @@ vi.mock("../plugins/provider-hook-runtime.js", async () => {

4243

resolveProviderHookPlugin: vi.fn(() => undefined),

4344

resolveProviderPluginsForHooks: vi.fn(() => []),

4445

resolveProviderRuntimePlugin: vi.fn(({ provider }: { provider?: string }) =>

46+

// Provider-specific replay policies are injected through the hook runtime

47+

// so core tests assert the contract without importing plugin internals.

4548

provider === "openrouter" || provider === "github-copilot"

4649

? {

4750

buildReplayPolicy: (context?: { modelId?: string | null }) => {

@@ -94,6 +97,8 @@ vi.mock("../plugins/provider-runtime.js", async () => {

9497

};

9598

};

9699

}) => {

100+

// Google-style providers may need a synthetic user turn before replaying

101+

// assistant-first history; the session marker prevents duplicate repair.

97102

if (

98103

provider &&

99104

provider.startsWith("google") &&

@@ -120,8 +125,8 @@ let mockedHelpers: SanitizeSessionHistoryHarness["mockedHelpers"];

120125

let testTimestamp = 1;

121126

const nextTimestamp = () => testTimestamp++;

122127123-

// We don't mock session-transcript-repair.js as it is a pure function and complicates mocking.

124-

// We rely on the real implementation which should pass through our simple messages.

128+

// Keep session-transcript-repair real: it is a pure repair boundary, and these

129+

// tests should fail if the shared sanitizer stops passing simple messages.

125130126131

describe("sanitizeSessionHistory", () => {

127132

let mockSessionManager: ReturnType<typeof makeMockSessionManager>;

@@ -135,6 +140,8 @@ describe("sanitizeSessionHistory", () => {

135140

modelApi?: string;

136141

modelId?: string;

137142

}) =>

143+

// Copilot routes through OpenAI-shaped APIs but can apply provider-owned

144+

// replay policy such as dropping Claude thinking blocks.

138145

sanitizeSessionHistory({

139146

messages: params.messages,

140147

modelApi: params.modelApi ?? "openai-completions",

@@ -480,6 +487,8 @@ describe("sanitizeSessionHistory", () => {

480487

it("drops stale assistant usage snapshots kept before latest compaction summary", async () => {

481488

vi.mocked(mockedHelpers.isGoogleModelApi).mockReturnValue(false);

482489490+

// Historical usage before a compaction summary would double-count prompt

491+

// budget if replayed as fresh model metadata.

483492

const messages = castAgentMessages([

484493

{ role: "user", content: "old context" },

485494

makeAssistantUsageMessage({