compact

Compact

Hard character limits on identity files with intelligent LLM-assisted consolidation. Prevents unbounded growth by rewriting at higher information density, not by deleting.

Usage

/compact                     -- check all files, compact any over limit
/compact preferences.md      -- compact a specific file
/compact --dry-run            -- show what would change without writing
/compact --status             -- show current sizes vs limits

How It Works

Step 1: Load Limits

Read ~/.homaruscc/config.json field identityLimits. Default limits (chars):

File	Limit
soul.md	8,000
preferences.md	4,000
user.md	3,000
state.md	2,000
MEMORY.md	5,000 (+ 200 lines)
disagreements.md	1,500
bisociations.md	3,000

Identity files live at ~/.homaruscc/identity/. MEMORY.md lives at the project root.

Step 2: Measure Files

Read each file. Count characters. For --status, display a table:

File               Chars   Limit    Pct    Status
soul.md            7,200   8,000    90%    OK
preferences.md     4,800   4,000   120%    OVER - needs compaction
user.md            4,500   3,000   150%    OVER - flagged for human review
...

Mark 100-110% as WARNING, >110% as OVER. Stop here if --status.

Step 3: Identify Targets

• Files >110% of limit: add to compaction queue
• Files 100-110%: log warning, skip (buffer zone)
• user.md: NEVER auto-compact. If over limit, say: "user.md is over limit ({pct}%). This file requires human review -- I won't compact it automatically."

Step 4: Compact Each File

For each file in the queue, read its content and build a consolidation prompt using the per-file rules below. The LLM output IS the compacted content.

If --dry-run: show the proposed compacted version and character savings. Do not write.

Otherwise: write the compacted content back to the file.

Step 5: Log