Josh Palmer 7a6c40872d Agents: add system prompt safety guardrails (#5445) ...

* 🤖 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)

2026-01-31 15:50:15 +01:00

..

acp

chore: Enable "curly" rule to avoid single-statement if confusion/errors.

2026-01-31 16:19:20 +09:00

agents

Agents: add system prompt safety guardrails (#5445)

2026-01-31 15:50:15 +01:00

auto-reply

fix: lint cleanups

2026-01-31 07:59:01 +00:00

browser

chore: Enable "curly" rule to avoid single-statement if confusion/errors.

2026-01-31 16:19:20 +09:00

canvas-host

chore: Enable "curly" rule to avoid single-statement if confusion/errors.

2026-01-31 16:19:20 +09:00

channels

chore: Enable "curly" rule to avoid single-statement if confusion/errors.

2026-01-31 16:19:20 +09:00

cli

revert: Switch back to tsc for compiling.

2026-01-31 18:31:49 +09:00

commands

feat: add MiniMax OAuth plugin (#4521) (thanks @Maosghoul)

2026-01-31 12:42:45 +01:00

compat

refactor: rename to openclaw

2026-01-30 03:16:21 +01:00

config

feat: add MiniMax OAuth plugin (#4521) (thanks @Maosghoul)

2026-01-31 12:42:45 +01:00

cron

chore: Enable "curly" rule to avoid single-statement if confusion/errors.

2026-01-31 16:19:20 +09:00

daemon

revert: Switch back to tsc for compiling.

2026-01-31 18:31:49 +09:00

discord

chore: Emit TypeScript declaration files so that we can type-check the extensions folder soon.

2026-01-31 21:57:21 +09:00

docs

bugfix:The Mintlify navbar (logo + search bar with ⌘K) scrolls away w… (#2445)

2026-01-26 17:39:10 -08:00

gateway

chore: Emit TypeScript declaration files so that we can type-check the extensions folder soon.

2026-01-31 21:57:21 +09:00

hooks

chore: Enable "curly" rule to avoid single-statement if confusion/errors.

2026-01-31 16:19:20 +09:00

imessage

chore: Oops, "long" is actually used + fix TypeScript error.

2026-01-31 17:12:28 +09:00

infra

revert: Switch back to tsc for compiling.

2026-01-31 18:31:49 +09:00

line

chore: Emit TypeScript declaration files so that we can type-check the extensions folder soon.

2026-01-31 21:57:21 +09:00

link-understanding

chore: Enable "curly" rule to avoid single-statement if confusion/errors.

2026-01-31 16:19:20 +09:00

logging

chore: Enable "curly" rule to avoid single-statement if confusion/errors.

2026-01-31 16:19:20 +09:00

macos

chore: Enable "curly" rule to avoid single-statement if confusion/errors.

2026-01-31 16:19:20 +09:00

markdown

chore: Enable "curly" rule to avoid single-statement if confusion/errors.

2026-01-31 16:19:20 +09:00

media

chore: Enable "curly" rule to avoid single-statement if confusion/errors.

2026-01-31 16:19:20 +09:00

media-understanding

chore: Enable "curly" rule to avoid single-statement if confusion/errors.

2026-01-31 16:19:20 +09:00

memory

chore: Enable "curly" rule to avoid single-statement if confusion/errors.

2026-01-31 16:19:20 +09:00

node-host

chore: Fix TypeScript errors 1/n.

2026-01-31 16:38:03 +09:00

pairing

chore: Enable "curly" rule to avoid single-statement if confusion/errors.

2026-01-31 16:19:20 +09:00

plugin-sdk

refactor: rename to openclaw

2026-01-30 03:16:21 +01:00

plugins

revert: Switch back to tsc for compiling.

2026-01-31 18:31:49 +09:00

process

chore: Enable "curly" rule to avoid single-statement if confusion/errors.

2026-01-31 16:19:20 +09:00

providers

chore: Enable "curly" rule to avoid single-statement if confusion/errors.

2026-01-31 16:19:20 +09:00

routing

chore: Enable "curly" rule to avoid single-statement if confusion/errors.

2026-01-31 16:19:20 +09:00

scripts

refactor: rename to openclaw

2026-01-30 03:16:21 +01:00

security

chore: Enable "curly" rule to avoid single-statement if confusion/errors.

2026-01-31 16:19:20 +09:00

sessions

chore: Enable "curly" rule to avoid single-statement if confusion/errors.

2026-01-31 16:19:20 +09:00

shared/text

chore: Enable "curly" rule to avoid single-statement if confusion/errors.

2026-01-31 16:19:20 +09:00

signal

chore: Enable "curly" rule to avoid single-statement if confusion/errors.

2026-01-31 16:19:20 +09:00

slack

chore: Emit TypeScript declaration files so that we can type-check the extensions folder soon.

2026-01-31 21:57:21 +09:00

telegram

chore: Enable "curly" rule to avoid single-statement if confusion/errors.

2026-01-31 16:19:20 +09:00

terminal

chore: Enable "curly" rule to avoid single-statement if confusion/errors.

2026-01-31 16:19:20 +09:00

test-helpers

refactor: rename to openclaw

2026-01-30 03:16:21 +01:00

test-utils

chore: Enable "curly" rule to avoid single-statement if confusion/errors.

2026-01-31 16:19:20 +09:00

tts

chore: Enable "curly" rule to avoid single-statement if confusion/errors.

2026-01-31 16:19:20 +09:00

tui

chore: Enable "curly" rule to avoid single-statement if confusion/errors.

2026-01-31 16:19:20 +09:00

types

chore: Enable more lint rules, disable some that trigger a lot. Will clean up later.

2026-01-31 16:04:04 +09:00

utils

chore: Enable "curly" rule to avoid single-statement if confusion/errors.

2026-01-31 16:19:20 +09:00

web

chore: Emit TypeScript declaration files so that we can type-check the extensions folder soon.

2026-01-31 21:57:21 +09:00

whatsapp

chore: Enable "curly" rule to avoid single-statement if confusion/errors.

2026-01-31 16:19:20 +09:00

wizard

fix: restore tsc build and plugin install tests

2026-01-31 07:54:15 +00:00

channel-web.barrel.test.ts

refactor!: rename chat providers to channels

2026-01-13 08:40:39 +00:00

channel-web.ts

refactor!: rename chat providers to channels

2026-01-13 08:40:39 +00:00

docker-setup.test.ts

refactor: rename to openclaw

2026-01-30 03:16:21 +01:00

entry.ts

chore: Enable "curly" rule to avoid single-statement if confusion/errors.

2026-01-31 16:19:20 +09:00

git-hooks.test.ts

chore: Enable "curly" rule to avoid single-statement if confusion/errors.

2026-01-31 16:19:20 +09:00

globals.test.ts

…

globals.ts

chore: Enable "curly" rule to avoid single-statement if confusion/errors.

2026-01-31 16:19:20 +09:00

index.test.ts

chore: migrate to oxlint and oxfmt

2026-01-14 15:02:19 +00:00

index.ts

refactor: rename to openclaw

2026-01-30 03:16:21 +01:00

logger.test.ts

refactor: rename to openclaw

2026-01-30 03:16:21 +01:00

logger.ts

chore: Enable "curly" rule to avoid single-statement if confusion/errors.

2026-01-31 16:19:20 +09:00

logging.ts

fix: unblock bundled plugin load

2026-01-18 19:34:21 +00:00

polls.test.ts

chore: migrate to oxlint and oxfmt

2026-01-14 15:02:19 +00:00

polls.ts

chore: migrate to oxlint and oxfmt

2026-01-14 15:02:19 +00:00

postinstall-patcher.test.ts

refactor: rename to openclaw

2026-01-30 03:16:21 +01:00

runtime.ts

perf: speed up memory batch polling

2026-01-18 03:55:14 +00:00

utils.test.ts

chore: Enable "curly" rule to avoid single-statement if confusion/errors.

2026-01-31 16:19:20 +09:00

utils.ts

chore: Enable "curly" rule to avoid single-statement if confusion/errors.

2026-01-31 16:19:20 +09:00

version.ts

refactor: rename to openclaw

2026-01-30 03:16:21 +01:00