mirror of https://github.com/openclaw/openclaw.git
7a6c40872d
* 🤖 agents: add system prompt safety guardrails What: - add safety guardrails to system prompt - update system prompt docs - update prompt tests Why: - discourage power-seeking or self-modification behavior - clarify safety/oversight priority when conflicts arise Tests: - pnpm lint (pass) - pnpm build (fails: DefaultResourceLoader missing in pi-coding-agent) - pnpm test (not run; build failed) * 🤖 agents: tighten safety wording for prompt guardrails What: - scope safety wording to system prompts/safety/tool policy changes - document Safety inclusion in minimal prompt mode - update safety prompt tests Why: - avoid blocking normal code changes or PR workflows - keep prompt mode docs consistent with implementation Tests: - pnpm lint (pass) - pnpm build (fails: DefaultResourceLoader missing in pi-coding-agent) - pnpm test (not run; build failed) * 🤖 docs: note safety guardrails are soft What: - document system prompt safety guardrails as advisory - add security note on prompt guardrails vs hard controls Why: - clarify threat model and operator expectations - avoid implying prompt text is an enforcement layer Tests: - pnpm lint (pass) - pnpm build (fails: DefaultResourceLoader missing in pi-coding-agent) - pnpm test (not run; build failed) |
||
|---|---|---|
| .. | ||
| security | ||
| authentication.md | ||
| background-process.md | ||
| bonjour.md | ||
| bridge-protocol.md | ||
| cli-backends.md | ||
| configuration-examples.md | ||
| configuration.md | ||
| discovery.md | ||
| doctor.md | ||
| gateway-lock.md | ||
| health.md | ||
| heartbeat.md | ||
| index.md | ||
| local-models.md | ||
| logging.md | ||
| multiple-gateways.md | ||
| openai-http-api.md | ||
| openresponses-http-api.md | ||
| pairing.md | ||
| protocol.md | ||
| remote-gateway-readme.md | ||
| remote.md | ||
| sandbox-vs-tool-policy-vs-elevated.md | ||
| sandboxing.md | ||
| tailscale.md | ||
| tools-invoke-http-api.md | ||
| troubleshooting.md | ||