37 lines
1.2 KiB
Markdown
37 lines
1.2 KiB
Markdown
|
---
|
||
|
|
name: context-budgeting
|
||
|
|
description: Manager context small, raw data to files, token estimation workflow for the orchestrator agent.
|
||
|
|
tags: ['management', 'context', 'tokens']
|
||
|
|
---
|
||
|
|
|
||
|
|
# Context Budgeting
|
||
|
|
|
||
|
|
## Purpose
|
||
|
|
Keep the main agent's context small by storing raw data in files and using includes/references instead of inline data.
|
||
|
|
|
||
|
|
## When to Use
|
||
|
|
- When a tool returns more than 80 lines of text
|
||
|
|
- When the user provides large files for processing
|
||
|
|
- When the conversation history grows large
|
||
|
|
- When a subordinate returns a long report
|
||
|
|
|
||
|
|
## When Not to Use
|
||
|
|
- For short tool outputs (< 30 lines)
|
||
|
|
- For data that must be reasoned about inline
|
||
|
|
|
||
|
|
## Procedure
|
||
|
|
1. Receive large output from tool or subordinate
|
||
|
|
2. Save to a file (e.g., /a0/usr/workdir/<name>.md)
|
||
|
|
3. Reference the file in the response: `See §include(/path/to/file.md)`
|
||
|
|
4. Optionally summarize the file in a few lines for context
|
||
|
|
5. Use raw file only when deep analysis is needed
|
||
|
|
|
||
|
|
## Token Estimation Rule
|
||
|
|
- 1 line of code/markdown ≈ 10-20 tokens
|
||
|
|
- 80 lines of tool output ≈ 1000-1500 tokens
|
||
|
|
- 1000 lines of conversation ≈ 15000-20000 tokens
|
||
|
|
- Compress when output exceeds 1000 tokens
|
||
|
|
|
||
|
|
## See Also
|
||
|
|
- Tool: `context_compactor` (plugin tool for structured compression)
|