Remembering Conversations

Remembering Conversations

Core principle: Search before reinventing. Searching costs nothing; reinventing or repeating mistakes costs everything.

Mandatory: Search Historical Memory

YOU MUST search historical memory for any historical search.

Announce: "Searching past conversations for [topic]."

Claude Code

Use the Task tool with subagent_type: "search-conversations":

Task tool:
  description: "Search past conversations for [topic]"
  prompt: "Search for [specific query or topic]. Focus on [what you're looking for - e.g., decisions, patterns, gotchas, code examples]."
  subagent_type: "search-conversations"

Codex

If a search-conversations agent is available, dispatch it with the same prompt. If not, use the MCP tools directly:

1. Search with the episodic-memory search tool 2. Read the top 2-5 results with the episodic-memory read tool 3. Synthesize findings in your response 4. Include source pointers so the user can inspect the original conversations

The search workflow will: 1. Search with the search tool 2. Read top 2-5 results with the read tool 3. Synthesize findings (200-1000 words) 4. Return actionable insights + sources

Saves 50-100x context vs. loading raw conversations.

When to Use

Use this whenever the current task would benefit from information you may have learned before, even if the user did not explicitly ask you to search.

When past experience may help:

• You need to recall decisions, rationale, patterns, solutions, pitfalls, or project context from earlier work
• A task resembles something you've solved, debugged, reviewed, released, or planned before
• You need to repeat a workflow or process that may have prior gotchas or established steps

When you're stuck:

• You've investigated a problem and can't find the solution
• Facing a complex problem without obvious solution in current code
• Need to follow an unfamiliar workflow or process

When historical signals are present:

• User says "last time", "before", "we discussed", "you implemented"
• User asks "why did we...", "what was the reason..."
• User says "do you remember...", "what do we know about..."

Before answering from uncertainty:

• Before guessing from memory or saying "I don't know" about something that may have been learned in a past conversation, search memory unless the current conversation already answers it

Don't search first:

• For current codebase structure (use Grep/Read to explore first)
• For info in current conversation
• Before understanding what you're being asked to do

Direct MCP Tool Access

Use these directly when a search agent is unavailable or the current harness does not support agent dispatch:

• mcp__plugin_episodic-memory_episodic-memory__search
• mcp__plugin_episodic-memory_episodic-memory__read

When using MCP tools directly, keep context small: search first, then read only the top 2-5 relevant conversations or line ranges.

See MCP-TOOLS.md for complete API reference if needed for advanced usage.

Episodic Memory MCP Tools Reference

The episodic-memory plugin exposes two MCP tools for searching and displaying past Claude Code and Codex conversations.

search

Search your episodic memory of past Claude Code and Codex conversations using semantic or text search.

Tool name: mcp__plugin_episodic-memory_episodic-memory__search

Parameters

Search Modes

• `vector` - Semantic similarity search using embeddings
• `text` - Exact text matching (case-insensitive)
• `both` - Combined semantic + text search (default, recommended)

Single-Concept Search

{
  query: "React Router authentication errors",
  mode: "both",
  limit: 10
}

Multi-Concept Search (AND)

Search for conversations containing ALL concepts:

{
  query: ["authentication", "React Router", "error handling"],
  limit: 10
}

Note: mode is ignored for multi-concept searches (always uses vector similarity).

Date Filtering

{
  query: "refactoring patterns",
  after: "2025-09-01",
  before: "2025-10-01"
}

Response Format

Markdown (default)

Human-readable format with:

• Project name and date
• Conversation summary
• Matched exchange snippet
• Similarity score
• File path and line numbers

JSON

Machine-readable format:

{
  "results": [...],
  "count": 5,
  "mode": "both"
}

read

Display a full conversation from episodic memory as markdown.

Tool name: mcp__plugin_episodic-memory_episodic-memory__read

Parameters

Usage

Read entire conversation:

{
  path: "/Users/name/.config/superpowers/conversation-archive/project/uuid.jsonl"
}

Read specific range:

{
  path: "/Users/name/.config/superpowers/conversation-archive/project/uuid.jsonl",
  startLine: 100,
  endLine: 200
}

Response Format

Markdown-formatted conversation with:

• Message roles (user/assistant)
• Content (including tool uses and results)
• Line numbers for reference

Error Handling

Both tools return errors as text content with isError: true:

• Invalid parameters (validation errors)
• File not found
• Date parsing errors
• Search failures

Performance Notes

• Search is fast (< 100ms typically)
• Read can be slow for large conversations
• Use startLine/endLine to paginate
• Conversations can be 1000+ lines
• Vector search uses sqlite-vec with cached embeddings
• Text search uses SQLite FTS5 full-text index