Skip to main content
When your conversation gets close to the model’s context window, SoulForge compacts it — summarizes older messages into a concise state, preserves the recent ones verbatim. The conversation continues; nothing is lost. Compaction fires automatically at 70% of the context window. You can also run it manually: 
/compact

​
Two strategies

SoulForge tracks structured state — files touched, decisions, discoveries, tool results — as the conversation happens. When compaction fires, this state is already built. Most sessions compact in zero LLM calls.Best for: typical coding sessions.
Switch with /compact settings or in config.

​
Config

{
  "compaction": {
    "strategy": "v2",
    "triggerThreshold": 0.7,
    "keepRecent": 4
  }
}
FieldDefaultWhat it does
strategy"v2""v2" or "v1"
triggerThreshold0.7Auto-compact at this fraction of context
keepRecent4Recent messages kept verbatim
maxToolResults30Rolling window of tool results (V2)
llmExtractiontrueAllow a cheap gap-fill pass (V2)

​
Which model compacts

Assign a cheap model in the task router: 
{
  "taskRouter": {
    "compact": "google/gemini-2.5-flash"
  }
}
For V2, this model only runs the optional gap-fill. For V1, it does the whole summary.

​
Signals

  • Context bar shows compaction strategy + slot count.
  • Compacting spinner during an active compaction.
  • System message reports before/after context percentages.