getcompanion-ai/co-mono
1
0
Fork 0
mirror of https://github.com/getcompanion-ai/co-mono.git synced 2026-04-15 08:03:39 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Note settings.json for compaction settings in compaction.md

Browse source
This commit is contained in:
Mario Zechner 2025-12-31 12:35:45 +01:00
parent 679343de55
commit dfc63a7bac
1 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
packages/coding-agent/docs/compaction.md
View file

@ -23,13 +23,13 @@ Auto-compaction triggers when:
contextTokens > contextWindow - reserveTokens
```
By default, `reserveTokens` is 16384 tokens. This leaves room for the LLM's response.
By default, `reserveTokens` is 16384 tokens (configurable in `~/.pi/agent/settings.json`). This leaves room for the LLM's response.
You can also trigger manually with `/compact [instructions]`, where optional instructions focus the summary.
### How It Works
1. **Find cut point**: Walk backwards from newest message, accumulating token estimates until `keepRecentTokens` (default 20k) is reached
1. **Find cut point**: Walk backwards from newest message, accumulating token estimates until `keepRecentTokens` (default 20k, configurable in `~/.pi/agent/settings.json`) is reached
2. **Extract messages**: Collect messages from previous compaction (or start) up to cut point
3. **Generate summary**: Call LLM to summarize with structured format
4. **Append entry**: Save `CompactionEntry` with summary and `firstKeptEntryId`