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

S
SegmentFault 最新的问题
MongoDB | Blog
MongoDB | Blog
J
Java Code Geeks
Stack Overflow Blog
Stack Overflow Blog
The GitHub Blog
The GitHub Blog
博客园 - Franky
博客园 - 叶小钗
大猫的无限游戏
大猫的无限游戏
V
Visual Studio Blog
IT之家
IT之家
美团技术团队
博客园 - 司徒正美
Martin Fowler
Martin Fowler
Last Week in AI
Last Week in AI
酷 壳 – CoolShell
酷 壳 – CoolShell
Vercel News
Vercel News
雷峰网
雷峰网
B
Blog
WordPress大学
WordPress大学
aimingoo的专栏
aimingoo的专栏
D
Docker
P
Proofpoint News Feed
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
爱范儿
爱范儿

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: add self-knowledge docs rule to system prompt (#9088...
SutraHsing · 2026-06-19 · via Recent Commits to openclaw:main

@@ -507,7 +507,9 @@ describe("buildAgentSystemPrompt", () => {

507507

expect(prompt).toContain("If a skill's <version> differs from a previous turn");

508508

expect(prompt).toContain("If several apply, choose the most specific.");

509509

expect(prompt).toContain("Docs: /tmp/openclaw/docs");

510-

expect(prompt).toContain("OpenClaw behavior/config/architecture: read local docs first.");

510+

expect(prompt).toContain(

511+

"Docs are authoritative for OpenClaw self-knowledge: before understanding how OpenClaw works (memory/daily notes, sessions, tools, Gateway, config, commands, project context), use `Read` or search local docs first; treat AGENTS.md/project context, workspace/profile/memory notes, and `memory_search` as instruction context or user memory, not OpenClaw design/implementation knowledge.",

512+

);

511513

});

512514513515

it("includes docs guidance when docsPath is provided", () => {

@@ -520,8 +522,30 @@ describe("buildAgentSystemPrompt", () => {

520522

expect(prompt).toContain("## Documentation");

521523

expect(prompt).toContain("Docs: /tmp/openclaw/docs");

522524

expect(prompt).toContain("Source: /tmp/openclaw");

523-

expect(prompt).toContain("OpenClaw behavior/config/architecture: read local docs first.");

524-

expect(prompt).toContain("If docs are stale/incomplete, inspect local source.");

525+

expect(prompt).toContain(

526+

"Docs are authoritative for OpenClaw self-knowledge: before understanding how OpenClaw works (memory/daily notes, sessions, tools, Gateway, config, commands, project context), use `read` or search local docs first; treat AGENTS.md/project context, workspace/profile/memory notes, and `memory_search` as instruction context or user memory, not OpenClaw design/implementation knowledge.",

527+

);

528+

expect(prompt).toContain("If docs are silent/stale, say so and inspect local source.");

529+

});

530+531+

it("keeps self-knowledge docs guidance concise and authoritative", () => {

532+

const prompt = buildAgentSystemPrompt({

533+

workspaceDir: "/tmp/openclaw",

534+

docsPath: "/tmp/openclaw/docs",

535+

sourcePath: "/tmp/openclaw",

536+

toolNames: ["read", "memory_search"],

537+

});

538+

const docsStart = prompt.indexOf("## Documentation");

539+

const nextSection = prompt.indexOf("\n## ", docsStart + 1);

540+

const docsSection = prompt.slice(docsStart, nextSection);

541+542+

expect(prompt).toContain(

543+

"Docs are authoritative for OpenClaw self-knowledge: before understanding how OpenClaw works (memory/daily notes, sessions, tools, Gateway, config, commands, project context), use `read` or search local docs first; treat AGENTS.md/project context, workspace/profile/memory notes, and `memory_search` as instruction context or user memory, not OpenClaw design/implementation knowledge.",

544+

);

545+

expect(docsSection.length).toBeLessThan(840);

546+

expect(prompt).not.toContain("Self-knowledge rule: for questions about");

547+

expect(prompt).not.toContain("Treat questions about daily notes");

548+

expect(prompt).not.toContain("never answer from AGENTS.md/project context");

525549

});

526550527551

it("falls back to public docs and GitHub source guidance when local docs are unavailable", () => {

@@ -531,7 +555,10 @@ describe("buildAgentSystemPrompt", () => {

531555532556

expect(prompt).toContain("Docs: https://docs.openclaw.ai");

533557

expect(prompt).toContain("Source: https://github.com/openclaw/openclaw");

534-

expect(prompt).toContain("If docs are stale/incomplete, inspect GitHub source.");

558+

expect(prompt).toContain(

559+

"Docs are authoritative for OpenClaw self-knowledge: before understanding how OpenClaw works (memory/daily notes, sessions, tools, Gateway, config, commands, project context), use the docs mirror first when web tooling is available; treat AGENTS.md/project context, workspace/profile/memory notes, and `memory_search` as instruction context or user memory, not OpenClaw design/implementation knowledge.",

560+

);

561+

expect(prompt).toContain("If docs are silent/stale, say so and inspect GitHub source.");

535562

});

536563537564

it("includes workspace notes when provided", () => {