Back to Details

recall-reasoning

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Recall Past Work

回顾过往工作

Search through previous sessions to find relevant decisions, approaches that worked, and approaches that failed. Queries two sources:
  1. Artifact Index - Handoffs, plans, ledgers with post-mortems (what worked/failed)
  2. Reasoning Files - Build attempts, test failures, commit context
搜索过往会话记录，查找相关决策、有效的方法以及失败的尝试。查询两个数据源：
  1. Artifact Index - 包含事后分析的交接文档、计划、台账（记录了有效/无效的方法）
  2. Reasoning Files - 构建尝试记录、测试失败信息、提交上下文

When to Use

使用场景

  • Starting work similar to past sessions
  • "What did we do last time with X?"
  • Looking for patterns that worked before
  • Investigating why something was done a certain way
  • Debugging an issue encountered previously
  • 开展与过往会话类似的工作时
  • 想知道“上次我们处理X问题时做了什么？”
  • 寻找之前验证有效的模式
  • 调查某项工作采用特定方式的原因
  • 调试之前遇到过的问题

Usage

使用方法

Primary: Artifact Index (rich context)

主要方式：Artifact Index（丰富上下文）

bash
uv run python scripts/core/artifact_query.py "<query>" [--outcome SUCCEEDED|FAILED] [--limit N]
This searches handoffs with post-mortems (what worked, what failed, key decisions).
bash
uv run python scripts/core/artifact_query.py "<query>" [--outcome SUCCEEDED|FAILED] [--limit N]
该命令搜索包含事后分析的交接文档（记录了有效方法、失败原因、关键决策）。

Secondary: Reasoning Files (build attempts)

次要方式：Reasoning Files（构建尝试记录）

bash
bash "$CLAUDE_PROJECT_DIR/.claude/scripts/search-reasoning.sh" "<query>"
This searches 
.git/claude/commits/*/reasoning.md
for build failures and fixes.
bash
bash "$CLAUDE_PROJECT_DIR/.claude/scripts/search-reasoning.sh" "<query>"
该命令搜索 
.git/claude/commits/*/reasoning.md
文件，查找构建失败与修复记录。

Examples

示例

bash
undefined
bash
undefined

Search for authentication-related work

搜索与认证相关的工作记录

uv run python scripts/core/artifact_query.py "authentication OAuth JWT"
uv run python scripts/core/artifact_query.py "authentication OAuth JWT"

Find only successful approaches

仅查找成功的方法

uv run python scripts/core/artifact_query.py "implement agent" --outcome SUCCEEDED
uv run python scripts/core/artifact_query.py "implement agent" --outcome SUCCEEDED

Find what failed (to avoid repeating mistakes)

查找失败案例（避免重复犯错）

uv run python scripts/core/artifact_query.py "hook implementation" --outcome FAILED
uv run python scripts/core/artifact_query.py "hook implementation" --outcome FAILED

Search build/test reasoning

搜索构建/测试推理记录

bash "$CLAUDE_PROJECT_DIR/.claude/scripts/search-reasoning.sh" "TypeError"
undefined
bash "$CLAUDE_PROJECT_DIR/.claude/scripts/search-reasoning.sh" "TypeError"
undefined

What Gets Searched

搜索范围

Artifact Index (handoffs, plans, ledgers):
  • Task summaries and status
  • What worked - Successful approaches
  • What failed - Dead ends and why
  • Key decisions - Choices with rationale
  • Goal and constraints from ledgers
Reasoning Files (
.git/claude/
):
  • Failed build attempts and error output
  • Successful builds after failures
  • Commit context and branch info
Artifact Index（交接文档、计划、台账）：
  • 任务摘要与状态
  • 有效方法 - 验证成功的方案
  • 失败尝试 - 行不通的方法及原因
  • 关键决策 - 带有决策依据的选择
  • 台账中的目标与约束条件
Reasoning Files（
.git/claude/
目录下）：
  • 构建失败尝试与错误输出
  • 失败后成功的构建记录
  • 提交上下文与分支信息

Interpreting Results

结果解读

From Artifact Index:
  • ✓
    = SUCCEEDED outcome (pattern to follow)
  • ✗
    = FAILED outcome (pattern to avoid)
  • ?
    = UNKNOWN outcome (not yet marked)
  • Post-mortem sections show distilled learnings
From Reasoning:
  • build_fail
    = approach that didn't work
  • build_pass
    = what finally succeeded
  • Multiple failures before success = non-trivial problem
来自Artifact Index的结果：
  • ✓
    = SUCCEEDED（可遵循的模式）
  • ✗
    = FAILED（需避免的模式）
  • ?
    = UNKNOWN（未标记结果）
  • 事后分析部分包含提炼后的经验总结
来自Reasoning Files的结果：
  • build_fail
    = 无效的方法
  • build_pass
    = 最终成功的方案
  • 多次失败后成功 = 问题具有一定复杂度

Process

操作流程

  1. Run Artifact Index query first - richer context, post-mortems
  2. Review relevant handoffs - check what worked/failed sections
  3. If needed, search reasoning - for specific build errors
  4. Apply learnings - follow successful patterns, avoid failed ones
  1. 优先运行Artifact Index查询 - 上下文更丰富，包含事后分析
  2. 查看相关交接文档 - 检查有效/无效方法部分
  3. 如有需要，搜索Reasoning Files - 针对特定构建错误
  4. 应用经验 - 遵循成功模式，避免失败尝试

No Results?

无结果怎么办？

Artifact Index empty:
  • Run 
    uv run python scripts/core/artifact_index.py --all
    to index existing handoffs
  • Create handoffs with post-mortem sections for future recall
Reasoning files empty:
  • Use 
    /commit
    after builds to capture reasoning
  • Check if 
    .git/claude/
    directory exists
Artifact Index为空：
  • 运行 
    uv run python scripts/core/artifact_index.py --all
    索引现有交接文档
  • 后续创建交接文档时加入事后分析部分，便于未来回顾
Reasoning Files为空：
  • 构建完成后使用 
    /commit
    命令捕获推理记录
  • 检查 
    .git/claude/
    目录是否存在