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

V
Visual Studio Blog
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
G
Google Developers Blog
J
Java Code Geeks
爱范儿
爱范儿
Microsoft Azure Blog
Microsoft Azure Blog
美团技术团队
人人都是产品经理
人人都是产品经理
Martin Fowler
Martin Fowler
IT之家
IT之家
博客园_首页
B
Blog RSS Feed
Google DeepMind News
Google DeepMind News
B
Blog
U
Unit 42
Apple Machine Learning Research
Apple Machine Learning Research
L
LangChain Blog
Stack Overflow Blog
Stack Overflow Blog
罗磊的独立博客
N
Netflix TechBlog - Medium
T
Tailwind CSS Blog
博客园 - 聂微东
腾讯CDC
A
About on SuperTechFans

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(agents): pass agent id to bootstrap preload · opencla...
steipete · 2026-05-29 · via Recent Commits to openclaw:main

File tree

  • src/agents/embedded-agent-runner/run

Original file line numberDiff line numberDiff line change

@@ -23,6 +23,41 @@ const transformProviderSystemPrompt: Parameters<

2323

>[0]["transformProviderSystemPrompt"] = ({ context }) => context.systemPrompt;

2424
2525

describe("buildAttemptSystemPrompt", () => {

26+

it("injects workspace identity context without a system prompt override", () => {

27+

const result = buildAttemptSystemPrompt({

28+

isRawModelRun: false,

29+

transformProviderSystemPrompt,

30+

embeddedSystemPrompt: {

31+

workspaceDir: "/tmp/openclaw",

32+

reasoningTagHint: false,

33+

runtimeInfo: {

34+

host: "test-host",

35+

os: "Darwin",

36+

arch: "arm64",

37+

node: "v22.0.0",

38+

model: "openai/gpt-5.5",

39+

},

40+

tools: [],

41+

modelAliasLines: [],

42+

userTimezone: "UTC",

43+

contextFiles: [

44+

{ path: "/tmp/openclaw/SOUL.md", content: "SOUL_CONTEXT_MARKER" },

45+

{ path: "/tmp/openclaw/IDENTITY.md", content: "IDENTITY_CONTEXT_MARKER" },

46+

{ path: "/tmp/openclaw/USER.md", content: "USER_CONTEXT_MARKER" },

47+

],

48+

},

49+

providerTransform: baseProviderTransform,

50+

});

51+
52+

expect(result.systemPrompt).toContain("# Project Context");

53+

expect(result.systemPrompt).toContain("## /tmp/openclaw/SOUL.md");

54+

expect(result.systemPrompt).toContain("SOUL_CONTEXT_MARKER");

55+

expect(result.systemPrompt).toContain("## /tmp/openclaw/IDENTITY.md");

56+

expect(result.systemPrompt).toContain("IDENTITY_CONTEXT_MARKER");

57+

expect(result.systemPrompt).toContain("## /tmp/openclaw/USER.md");

58+

expect(result.systemPrompt).toContain("USER_CONTEXT_MARKER");

59+

});

60+
2661

it("preserves bootstrap Project Context when a system prompt override is configured", () => {

2762

const result = buildAttemptSystemPrompt({

2863

isRawModelRun: false,

Original file line numberDiff line numberDiff line change

@@ -34,9 +34,10 @@ describe("runEmbeddedAttempt cwd/workspace split", () => {

3434

});

3535
3636

const bootstrapCall = hoisted.resolveBootstrapFilesForRunMock.mock.calls[0]?.[0] as

37-

| { workspaceDir?: string }

37+

| { agentId?: string; workspaceDir?: string }

3838

| undefined;

3939

expect(bootstrapCall?.workspaceDir).not.toBe("/tmp/task-repo");

40+

expect(bootstrapCall?.agentId).toBe("main");

4041
4142

const toolsCall = hoisted.createOpenClawCodingToolsMock.mock.calls[0]?.[0] as

4243

| { cwd?: string; workspaceDir?: string; spawnWorkspaceDir?: string }

Original file line numberDiff line numberDiff line change

@@ -1200,6 +1200,7 @@ export async function runEmbeddedAttempt(

12001200

config: params.config,

12011201

sessionKey: params.sessionKey,

12021202

sessionId: params.sessionId,

1203+

agentId: sessionAgentId,

12031204

warn: bootstrapWarn,

12041205

contextMode: params.bootstrapContextMode,

12051206

runKind: params.bootstrapContextRunKind,