Back to Details

braintrust-analyze

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Braintrust Analysis

Braintrust 分析

Analyze your Claude Code sessions for patterns, issues, and insights using Braintrust tracing data.
使用Braintrust追踪数据，分析你的Claude Code会话，从中发现模式、问题和洞察。

When to Use

适用场景

  • After completing a complex task (retrospective)
  • When debugging why something failed
  • Weekly review of productivity patterns
  • Finding opportunities to create new skills
  • Understanding token usage trends
  • 完成复杂任务后（回顾总结）
  • 调试失败原因时
  • 每周回顾生产力模式
  • 寻找创建新Skill的机会
  • 了解Token使用趋势

Commands

命令

Run from the project directory:
bash
undefined
从项目目录运行：
bash
undefined

Analyze last session - summary with tool/agent/skill breakdown

Analyze last session - summary with tool/agent/skill breakdown

uv run python -m runtime.harness scripts/braintrust_analyze.py --last-session
uv run python -m runtime.harness scripts/braintrust_analyze.py --last-session

List recent sessions

List recent sessions

uv run python -m runtime.harness scripts/braintrust_analyze.py --sessions 5
uv run python -m runtime.harness scripts/braintrust_analyze.py --sessions 5

Agent usage statistics (last 7 days)

Agent usage statistics (last 7 days)

uv run python -m runtime.harness scripts/braintrust_analyze.py --agent-stats
uv run python -m runtime.harness scripts/braintrust_analyze.py --agent-stats

Skill usage statistics (last 7 days)

Skill usage statistics (last 7 days)

uv run python -m runtime.harness scripts/braintrust_analyze.py --skill-stats
uv run python -m runtime.harness scripts/braintrust_analyze.py --skill-stats

Detect loops - find repeated tool patterns (>5 same tool calls)

Detect loops - find repeated tool patterns (>5 same tool calls)

uv run python -m runtime.harness scripts/braintrust_analyze.py --detect-loops
uv run python -m runtime.harness scripts/braintrust_analyze.py --detect-loops

Replay specific session - show full sequence of actions

Replay specific session - show full sequence of actions

uv run python -m runtime.harness scripts/braintrust_analyze.py --replay <session-id>
uv run python -m runtime.harness scripts/braintrust_analyze.py --replay <session-id>

Weekly summary - daily activity breakdown

Weekly summary - daily activity breakdown

uv run python -m runtime.harness scripts/braintrust_analyze.py --weekly-summary
uv run python -m runtime.harness scripts/braintrust_analyze.py --weekly-summary

Token trends - usage over time

Token trends - usage over time

uv run python -m runtime.harness scripts/braintrust_analyze.py --token-trends
undefined
uv run python -m runtime.harness scripts/braintrust_analyze.py --token-trends
undefined

Options

选项

  • --project NAME
    - Braintrust project name (default: agentica)
  • --project NAME
    - Braintrust项目名称（默认值：agentica）

What You'll Learn

你将获得的信息

Session Analysis

会话分析

  • Tool usage breakdown
  • Agent spawns (plan-agent, debug-agent, etc.)
  • Skill activations (/commit, /research, etc.)
  • Token consumption estimates
  • 工具使用明细
  • Agent实例生成情况（plan-agent、debug-agent等）
  • Skill激活情况（/commit、/research等）
  • Token消耗估算

Loop Detection

循环检测

Find sessions where the same tool was called repeatedly, which may indicate:
  • Stuck in a search loop
  • Inefficient approach
  • Opportunity for better tooling
找出同一工具被重复调用的会话，这可能表明：
  • 陷入搜索循环
  • 方法效率低下
  • 有优化工具的机会

Usage Patterns

使用模式

  • Which agents you use most
  • Which skills get activated
  • Daily/weekly activity trends
  • 你最常使用的Agent
  • 哪些Skill被激活
  • 每日/每周活动趋势

Examples

示例

Quick Retrospective

快速回顾

bash
undefined
bash
undefined

What happened in my last session?

What happened in my last session?

uv run python -m runtime.harness scripts/braintrust_analyze.py --last-session

Output:
uv run python -m runtime.harness scripts/braintrust_analyze.py --last-session

输出：

Session Analysis

Session Analysis

ID: 
92940b91...
Started: 2025-12-24T01:31:05Z Spans: 14
ID: 
92940b91...
Started: 2025-12-24T01:31:05Z Spans: 14

Tool Usage

Tool Usage

  • Read: 4
  • Bash: 2
  • Edit: 2 ...
undefined
  • Read: 4
  • Bash: 2
  • Edit: 2 ...
undefined

Find Loops

查找循环

bash
uv run python -m runtime.harness scripts/braintrust_analyze.py --detect-loops
bash
uv run python -m runtime.harness scripts/braintrust_analyze.py --detect-loops

Weekly Review

每周回顾

bash
uv run python -m runtime.harness scripts/braintrust_analyze.py --weekly-summary
bash
uv run python -m runtime.harness scripts/braintrust_analyze.py --weekly-summary

Requirements

要求

  • BRAINTRUST_API_KEY in ~/.claude/.env or project .env
  • Braintrust tracing enabled (via braintrust-claude-plugin)
  • BRAINTRUST_API_KEY在~/.claude/.env或项目.env文件中配置
  • 已启用Braintrust追踪（通过braintrust-claude-plugin）