chimera_compress
Compress text via contractions and symbols at light, medium, or aggressive levels. Quantum algorithm preserves key content. Returns compressed text and ratio, automatically tracking token savings to dashboard.
Instructions
Compress text via contractions/symbols. Levels: light, medium, aggressive. Returns compressed text and compression ratio. Token savings are automatically recorded to chimera_dashboard (set auto_track=false to disable). Prefer over manual regex replacement — the quantum algorithm uses structural salience so important sentences near the task focus survive compression.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | Text to compress | |
| level | No | Compression aggressiveness. Default: medium. | medium |
| preserve_code | No | Skip compression inside code fences (``` blocks). Default true. | |
| focus | No | Optional task focus/query. quantum mode uses it to preserve the most relevant content. | |
| algorithm | No | Compression algorithm. quantum = structural salience compression. classic = legacy rewrite-only compression. | quantum |
| auto_track | No | Automatically record token savings to the cost tracker (visible in chimera_dashboard). Default true. | |
| model | No | Model name used for cost tracking (e.g. 'claude-sonnet-4-6'). Default: claude-sonnet-4-6. | claude-sonnet-4-6 |
| namespace | No | Cost tracker namespace (default: 'default'). | default |