chatlab-analyze
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseChatLab Analyze
ChatLab 分析
Query and analyze records already imported into ChatLab through the read-only CLI.
clbFollow the user's requested response language; otherwise use the conversation language, preserving the user's Chinese variant when applicable. Keep commands, field names, IDs, and evidence markers unchanged.
For importing a new chat export, use when available; otherwise follow and preview the exact import before writing.
chatlab-importclb import --help通过只读的 CLI 查询和分析已导入 ChatLab 的记录。
clb遵循用户要求的回复语言;否则使用对话语言,适用时保留用户的中文变体。命令、字段名、ID 和证据标记保持不变。
如需导入新的聊天导出文件,优先使用 (若可用);否则参照 的说明,并在写入前预览确切的导入内容。
chatlab-importclb import --helpWorkflow
工作流程
1. Prepare the Query
1. 准备查询
Load the current command contract once per task. List sessions only when the target is not already known:
bash
clb manifest
clb sessions list --format jsonReuse the session, member, and time range already identified in the conversation. Ask only when the returned candidates and context cannot resolve a material ambiguity. If the CLI is unavailable, report the missing capability; installation requires authorization.
每个任务加载一次当前命令契约。仅当目标未知时才列出会话:
bash
clb manifest
clb sessions list --format json复用对话中已确定的会话、成员和时间范围。仅当返回的候选结果和上下文无法解决实质性歧义时才进行询问。如果 CLI 不可用,说明缺失该能力;安装需要授权。
2. Start with a Dedicated Command
2. 从专用命令开始
Use the simplest command that directly answers the question:
bash
clb messages search "<keyword>" --session <session-id> --format agent
clb messages between --member me --member <member> --session <session-id> --last 90d --format agent
clb topics list --session <session-id> --last 30d --format agentUse for message text and for structural scouting such as sessions, members, counts, and searches.
--format agent--format json--no-content使用能够直接回答问题的最简单命令:
bash
clb messages search "<keyword>" --session <session-id> --format agent
clb messages between --member me --member <member> --session <session-id> --last 90d --format agent
clb topics list --session <session-id> --last 30d --format agent消息文本查询使用 ,会话、成员、计数等结构探查以及 搜索使用 。
--format agent--no-content--format json3. Add Context or Statistics
3. 添加上下文或统计信息
Only deepen the query when the first result is insufficient:
bash
clb messages context --id 1021 --session <session-id> --window 10 --format agent
clb stats keywords --session <session-id> --member <member> --last 90d --top 20 --format jsonWhen more evidence is needed and is true, continue with and the same query conditions. Stop when the question is answered; disclose any partial coverage instead of treating a page as the complete dataset.
meta.hasMore--cursor <meta.nextCursor>仅当首次返回结果不足时才深化查询:
bash
clb messages context --id 1021 --session <session-id> --window 10 --format agent
clb stats keywords --session <session-id> --member <member> --last 90d --top 20 --format json当需要更多证据且 为 true 时,使用 和相同的查询条件继续查询。问题得到解答后即停止;需说明部分覆盖情况,切勿将单页结果视为完整数据集。
meta.hasMore--cursor <meta.nextCursor>4. Use SQL Only as a Fallback
4. 仅将 SQL 作为备用方案
Use read-only SQL only when no dedicated command can answer the question:
bash
clb schema --session <session-id> --format json
clb sql "SELECT COUNT(*) AS n FROM message" --session <session-id> --format json仅当没有专用命令可以回答问题时,才使用只读 SQL:
bash
clb schema --session <session-id> --format json
clb sql "SELECT COUNT(*) AS n FROM message" --session <session-id> --format jsonPrivacy and Answers
隐私与答复
- Queries keep privacy preprocessing enabled; do not use or mutate data/config. A separate request to import follows the import workflow.
--raw - Never reveal full chat dumps. ChatLab's safe output applies the user's privacy preprocessing.
- Cite available evidence with ,
[#1021], or[#1021*]. Only individual IDs can be passed to[#1021-1024]; merged ranges are display-only.messages context --id - Start with the answer, name the queried session and time range, then separate observed facts from interpretation.
- Avoid overclaiming emotional intent in relationship analysis. Follow only when the correction is clear.
error.hint
- 查询保持隐私预处理启用状态;请勿使用 或修改数据/配置。单独的导入请求需遵循导入工作流程。
--raw - 切勿泄露完整的聊天转储内容。ChatLab 的安全输出会应用用户的隐私预处理规则。
- 使用 、
[#1021]或[#1021*]引用可用证据。只有单个 ID 可以传递给[#1021-1024];合并范围仅用于展示。messages context --id - 先给出答案,说明查询的会话和时间范围,再将观察到的事实与解读分开。
- 在关系分析中避免过度推断情感意图。仅当修正方向明确时,才遵循 。
error.hint