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

J
Java Code Geeks
Martin Fowler
Martin Fowler
B
Blog RSS Feed
D
DataBreaches.Net
L
LangChain Blog
月光博客
月光博客
S
SegmentFault 最新的问题
阮一峰的网络日志
阮一峰的网络日志
V
Visual Studio Blog
美团技术团队
Jina AI
Jina AI
博客园 - 司徒正美
雷峰网
雷峰网
Last Week in AI
Last Week in AI
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
IT之家
IT之家
博客园 - 三生石上(FineUI控件)
WordPress大学
WordPress大学
小众软件
小众软件
罗磊的独立博客
博客园_首页
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
A
About on SuperTechFans
Engineering at Meta
Engineering at Meta

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(memory): add guidance for action-sensitive memories ...
cassthebandi · 2026-05-23 · via Recent Commits to openclaw:main

@@ -55,6 +55,46 @@ If you want your agent to remember something, just ask it: "Remember that I

5555

prefer TypeScript." It will write it to the appropriate file.

5656

</Tip>

575758+

## Action-sensitive memories

59+60+

Most memories can be written as ordinary Markdown notes. But some memories affect what the agent should do later. For those, capture when it is safe to act on the note, not just the fact itself.

61+62+

Capture that action boundary when a note involves:

63+64+

- approval or permission requirements,

65+

- temporary constraints,

66+

- handoffs to another session, thread, or person,

67+

- expiry conditions,

68+

- safe-to-act timing,

69+

- source or owner authority,

70+

- instructions to avoid a tempting action.

71+72+

A useful action-sensitive memory makes clear:

73+74+

- what changes future behavior,

75+

- when or under what condition it applies,

76+

- when it expires, or what unlocks action,

77+

- what the agent should avoid doing,

78+

- who is the source or owner, if that affects trust or authority.

79+80+

Memory can preserve approval context, but it does not enforce policy. Use OpenClaw approval settings, sandboxing, and scheduled tasks for hard operational controls.

81+82+

Example:

83+84+

```md

85+

The API migration is being designed in another session. Future turns should not edit the API implementation from this thread; use findings here only as design input until the migration plan lands.

86+

```

87+88+

Another example:

89+90+

```md

91+

A report from an untrusted source needs review before promotion. Future turns should treat it as evidence only; do not store it as durable memory until a trusted reviewer confirms the contents.

92+

```

93+94+

Use [commitments](/concepts/commitments) for inferred, short-lived follow-ups. Use [scheduled tasks](/automation/cron-jobs) for exact reminders, timed checks, and recurring work. Memory can still summarize the durable context around either path.

95+96+

This is not a required schema for every memory. Simple facts can stay concise. Use action-sensitive boundaries when losing timing, authority, expiry, or safe-to-act context could cause the agent to do the wrong thing later.

97+5898

## Inferred commitments

599960100

Some future follow-ups are not durable facts. If you mention an interview