recording

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Recording Mode

录制模式

Activate this mode when the user runs

/recording

or otherwise signals a demo/screen-share. Stay in this mode for the rest of the session unless the user says "stop recording", "/recording off", or equivalent.

当用户运行/recording指令，或以其他方式表示要进行演示/屏幕共享时，激活此模式。除非用户说“停止录制”、“/recording off”或类似表述，否则在会话剩余时间内保持此模式。

Core rule

核心规则

While recording mode is active, every user-visible output (chat text, code, file contents shown inline, tool result summaries, commit messages, file names invented for examples) MUST have sensitive content replaced with obviously fake placeholder data before it leaves the assistant.

This applies to text the model generates. It does NOT retroactively edit files on disk — only what the audience sees on screen. If asked to write redacted content to a file, do so explicitly; otherwise leave files alone.

在录制模式激活期间，所有用户可见的输出（聊天文本、代码、内联显示的文件内容、工具结果摘要、提交信息、为示例虚构的文件名）在输出前必须将敏感内容替换为明显的虚假占位数据。

此规则适用于模型生成的文本。不会追溯编辑磁盘上的文件——仅处理观众在屏幕上看到的内容。如果被要求将脱敏内容写入文件，请明确执行；否则不要改动文件。

What to redact

需要脱敏的内容

Replace these categories:

Names (people, partners, family, colleagues, clients) →
```
Alex Doe
```
,
```
Jamie Roe
```
,
```
Sam Park
```
Handles / emails / phones / URLs with identifiers →
```
@demo_user
```
,
```
user@example.com
```
,
```
+49 000 000 0000
```
Org / company / brand names (when private) →
```
Acme Co
```
,
```
Globex
```
Locations — anything more specific than continent. City, neighborhood, street, venue, coordinates, IP-derived location →
```
Some City
```
,
```
Main Street
```
,
```
Venue A
```
. Even "Berlin" gets replaced if it could identify the user.
Dates — any real calendar date (birthdays, appointments, sessions, deadlines, deploy dates, transaction dates, file timestamps shown inline) → shift to placeholder dates like
```
2025-01-01
```
,
```
2025-01-02
```
. Keep relative ordering and weekday if it matters to the demo. Today's actual date should be replaced too if it appears in output.
Financial values (revenue, prices, salaries, invoice amounts) → round dummy numbers like
```
€1,234
```
or
```
$X,XXX
```
Medical info (diagnoses, medications, doses, symptoms, lab values) →
```
[medication]
```
,
```
[condition]
```
,
```
[symptom]
```
Emotional / therapy / coaching content (feelings, session notes, DIMs/SIMs, relationship details) →
```
[personal reflection]
```
Business info (deal terms, client lists, internal strategy, unreleased projects) →
```
[business detail]
```
Credentials (tokens, keys, passwords, session IDs, file paths containing usernames) →
```
sk-XXXX
```
,
```
/Users/demo/...
```
Genetic / health data specific to the user →
```
[genetic marker]
```

When in doubt, redact. The cost of over-redaction in a demo is near zero; the cost of leaking is high.

替换以下类别：

姓名（个人、合作伙伴、家人、同事、客户）→
```
Alex Doe
```
,
```
Jamie Roe
```
,
```
Sam Park
```
账号/邮箱/电话/含标识符的URL →
```
@demo_user
```
,
```
user@example.com
```
,
```
+49 000 000 0000
```
组织/公司/品牌名称（非公开时）→
```
Acme Co
```
,
```
Globex
```
地点——比大洲更具体的任何信息。城市、社区、街道、场所、坐标、IP推导的位置→
```
Some City
```
,
```
Main Street
```
,
```
Venue A
```
。即使是“柏林”，如果可能识别用户身份，也需替换。
日期——任何真实日历日期（生日、预约、会话、截止日期、部署日期、交易日期、内联显示的文件时间戳）→ 替换为占位日期，如
```
2025-01-01
```
,
```
2025-01-02
```
。如果对演示重要，保留相对顺序和星期几。如果输出中出现当前实际日期，也需替换。
财务数值（收入、价格、薪资、发票金额）→ 近似的虚拟数字，如
```
€1,234
```
或
```
$X,XXX
```
医疗信息（诊断、药物、剂量、症状、实验室数值）→
```
[medication]
```
,
```
[condition]
```
,
```
[symptom]
```
情感/治疗/辅导内容（感受、会话记录、DIMs/SIMs、关系细节）→
```
[personal reflection]
```
商业信息（交易条款、客户名单、内部策略、未发布项目）→
```
[business detail]
```
凭证（令牌、密钥、密码、会话ID、含用户名的文件路径）→
```
sk-XXXX
```
,
```
/Users/demo/...
```
用户特定的遗传/健康数据 →
```
[genetic marker]
```

如有疑问，一律脱敏。演示中过度脱敏的成本几乎为零；而信息泄露的代价很高。

Style of replacement

替换风格

Use obviously dummy values, not plausible fakes that could be mistaken for real ones.
```
Alex Doe
```
not
```
Andrey Volkov
```
.
```
Acme Co
```
not
```
Northwind Studio
```
.
Keep replacements consistent within a session: the same real name maps to the same fake name every time, so the demo stays coherent. Maintain this mapping mentally for the duration of recording mode.
Preserve structure and length roughly so the demo still reads naturally (e.g. a real email becomes a fake email, not
```
[REDACTED]
```
).
Preserve technical accuracy of non-sensitive parts: code logic, library names, public APIs, framework terminology stay exact.

使用明显虚拟的值，而非可能被误认为真实信息的合理虚构值。例如用
```
Alex Doe
```
而非
```
Andrey Volkov
```
，用
```
Acme Co
```
而非
```
Northwind Studio
```
。
在会话中保持替换一致性：同一个真实姓名每次都映射到同一个虚拟姓名，确保演示连贯。在录制模式期间，需在脑海中维持此映射关系。
大致保留结构和长度，使演示读起来自然（例如，真实邮箱替换为虚拟邮箱，而非
```
[REDACTED]
```
）。
保留非敏感部分的技术准确性：代码逻辑、库名称、公共API、框架术语保持原样。

What NOT to redact

无需脱敏的内容

Public technical content: language keywords, public package names, public docs URLs, generic file names (
```
README.md
```
,
```
package.json
```
).
The user's own typed input — do not rewrite what they said, only what the assistant outputs.
Vault structure conventions and folder names that are already public knowledge from CLAUDE.md.

公开技术内容：语言关键字、公共包名称、公共文档URL、通用文件名（
```
README.md
```
,
```
package.json
```
）。
用户自己输入的内容——不要改写用户的输入，仅处理助手的输出。
已在CLAUDE.md中公开的Vault结构约定和文件夹名称。

Tool calls

工具调用

Tool calls themselves run normally — redaction is about what the assistant says. But:

When summarizing tool results back to the user, apply redaction to the summary.
When quoting file contents inline (e.g. showing a snippet of a daily note), redact the snippet.
Avoid reading sensitive files into the visible transcript unnecessarily — prefer to act on them silently and report a redacted summary.

工具调用本身正常运行——脱敏针对的是助手输出的内容。但需注意：

当向用户总结工具结果时，对总结内容进行脱敏。
当内联引用文件内容时（例如显示每日笔记的片段），对片段进行脱敏。
避免不必要地将敏感文件内容读入可见对话——优先静默处理并报告脱敏后的摘要。

Toggle behavior

切换行为

/recording

is a toggle. Calling it flips the current state:

If recording mode is OFF,
```
/recording
```
turns it ON. Reply with one short redacted line confirming it's on.
If recording mode is ON,
```
/recording
```
turns it OFF. Reply with one short line confirming it's off, then resume normal output.

Track the current state across the session. Natural-language equivalents also toggle: "I'm about to record" / "starting a demo" turn it on; "stop recording" / "demo done" / "you can stop redacting" turn it off. When in doubt about intent, infer from current state — if already recording and the user says "recording", they mean stop.

/recording

是一个切换指令。调用它会翻转当前状态：

如果录制模式处于关闭状态，
```
/recording
```
将其开启。回复一行简短的脱敏确认信息表示已开启。
如果录制模式处于开启状态，
```
/recording
```
将其关闭。回复一行简短的确认信息表示已关闭，然后恢复正常输出。

在会话中跟踪当前状态。自然语言表述也可切换：“我即将开始录制”/“开始演示”会开启模式；“停止录制”/“演示结束”/“可以停止脱敏了”会关闭模式。如果对用户意图有疑问，根据当前状态推断——如果已处于录制状态，用户说“录制”则表示停止。

Self-check before sending

发送前自检

Before emitting any message while recording mode is active, scan the draft for:

Any proper noun that isn't a public technical term.
Any number that looks like money, age, dose, or measurement tied to the user.
Any path containing
```
glebkalinin
```
,
```
Brains/brain
```
, real folder names from People/, Daily/, etc.
Any emotional or medical vocabulary tied to a first-person subject.

If any hit, redact and re-check. Only then send.

在录制模式激活期间发送任何消息前，检查草稿是否包含：

任何非公开技术术语的专有名词。
任何看起来像是金钱、年龄、剂量或与用户相关的测量值的数字。
任何包含
```
glebkalinin
```
,
```
Brains/brain
```
, People/, Daily/等真实文件夹名称的路径。
任何与第一人称主体相关的情感或医学词汇。

如果发现任何上述内容，进行脱敏并重新检查。确认无误后再发送。