mirror of
https://github.com/pocketpaw/pocketpaw.git
synced 2026-05-21 01:04:57 +00:00
57b807c117
Comprehensive SEO optimization across 80 documentation pages: Title optimization (all pages): - Replaced generic titles like "Architecture", "Discord", "Slack" with search-intent titles like "PocketPaw Architecture: Event-Driven Message Bus", "Discord Bot Setup: Add PocketPaw to Your Server" - All titles now 50-70 characters with qualifying keywords Meta descriptions: - Expanded 7 short descriptions (under 145 chars) to 150-160 chars - Roadmap description expanded from 76 to 196 chars - Troubleshooting, Codex CLI, OpenCode, WebMCP all expanded H1 heading fixes: - Ensured single H1 per page matching the frontmatter title - All H1 headings updated to match new optimized titles Internal cross-links: - Added Related CardGroup sections to 60+ individual pages - Each links to 2-3 related pages within and across sections - Channels link to channel guides, backends link to Ollama guide, etc. Em dash cleanup: - Replaced em dashes with colons, periods, or double hyphens across multiple files in tools/, channels/, integrations/ Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
103 lines
3.7 KiB
Plaintext
103 lines
3.7 KiB
Plaintext
---
|
|
title: "Context Building: Memory-Augmented Prompts"
|
|
description: "The AgentContextBuilder assembles PocketPaw's full context from identity, USER.md profile, skills, long-term facts, semantic memories, and session history, prioritized to fit the model's context window."
|
|
section: Memory
|
|
ogType: article
|
|
keywords: ["context building", "system prompt", "context window", "user profile", "prompt assembly"]
|
|
tags: ["memory", "context"]
|
|
---
|
|
|
|
# Context Building: Memory-Augmented Prompts
|
|
|
|
The `AgentContextBuilder` assembles the agent's full context from multiple sources before each interaction.
|
|
|
|
## Context Sources
|
|
|
|
The builder combines these sources in order:
|
|
|
|
<Steps>
|
|
<Step title="Identity">
|
|
The agent's system prompt with personality, capabilities, and behavioral guidelines.
|
|
</Step>
|
|
<Step title="User Profile">
|
|
Content from `~/.pocketpaw/identity/USER.md` — a user-editable file with preferences and background information.
|
|
</Step>
|
|
<Step title="Skills">
|
|
Loaded skill definitions from `~/.claude/skills/`, `~/.pocketpaw/skills/`, and `~/.agents/skills/`.
|
|
</Step>
|
|
<Step title="Long-term Facts">
|
|
Extracted facts from previous sessions (e.g., "User prefers Python", "Uses Arch Linux").
|
|
</Step>
|
|
<Step title="Semantic Memories">
|
|
Relevant memories from Mem0, retrieved via semantic search using the current user query.
|
|
</Step>
|
|
<Step title="Session History">
|
|
Recent messages from the current session, newest first, truncated to fit the context window.
|
|
</Step>
|
|
</Steps>
|
|
|
|
## Context Window Management
|
|
|
|
The builder ensures the total context fits within the model's limits:
|
|
|
|
1. Identity and user profile are always included (highest priority)
|
|
2. Skills are included in full
|
|
3. Long-term facts are included
|
|
4. Semantic memories are included (limited to top-N matches)
|
|
5. Session history fills the remaining space, truncating oldest messages first
|
|
|
|
## User Profile (USER.md)
|
|
|
|
PocketPaw automatically creates `~/.pocketpaw/identity/USER.md` on first run. Users can edit this file to provide context:
|
|
|
|
```markdown
|
|
# About Me
|
|
|
|
- Name: Alice
|
|
- Role: Software Engineer
|
|
- Languages: Python, TypeScript
|
|
- OS: Arch Linux
|
|
- Preferences: Dark mode, vim keybindings
|
|
- Projects: Working on a web scraping framework
|
|
```
|
|
|
|
This context helps the agent provide more relevant and personalized responses.
|
|
|
|
## Sender-Aware Context
|
|
|
|
When [memory isolation](/memory/memory-isolation) is configured, the context builder adjusts based on who is messaging:
|
|
|
|
- **Owner** — Full USER.md profile, all long-term facts, and semantic memories are included
|
|
- **External user** — A neutral identity block is injected instead, and only the user's own scoped memories are loaded
|
|
|
|
The `sender_id` is extracted from inbound message metadata and compared against the configured `owner_id` to determine which identity block to inject.
|
|
|
|
## Semantic Memory Query
|
|
|
|
When Mem0 is enabled, the context builder performs a semantic search using the current user message:
|
|
|
|
```python
|
|
# Simplified context building with Mem0
|
|
memories = await mem0.search(
|
|
query=user_message,
|
|
user_id=session_id,
|
|
limit=5,
|
|
)
|
|
```
|
|
|
|
This finds memories that are semantically relevant to what the user is currently asking about, even if the exact words differ.
|
|
|
|
## Related
|
|
|
|
<CardGroup>
|
|
<Card title="Mem0 Integration" icon="lucide:sparkles" href="/memory/mem0">
|
|
Set up semantic memory with auto-learning and vector search.
|
|
</Card>
|
|
<Card title="Memory Isolation" icon="lucide:shield" href="/memory/memory-isolation">
|
|
How context building adapts for owner vs. external users.
|
|
</Card>
|
|
<Card title="Sessions" icon="lucide:history" href="/memory/sessions">
|
|
Session management that feeds conversation history into context.
|
|
</Card>
|
|
</CardGroup>
|