Context compaction - SoulForge

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

V2 (default) — instant, usually free
V1 — LLM summary

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
  }
}

Field	Default	What it does
`strategy`	`"v2"`	`"v2"` or `"v1"`
`triggerThreshold`	`0.7`	Auto-compact at this fraction of context
`keepRecent`	`4`	Recent messages kept verbatim
`maxToolResults`	`30`	Rolling window of tool results (V2)
`llmExtraction`	`true`	Allow 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.