- Restore backticks around `prompt` in `Agent.prompt()` comment.
- Drop two stray blank lines around `mergedRecent` in `summarizeMessages`.
- Collapse deliberation comments in the new context-strategy test to one line.
- Add JSDoc note on `contextStrategy.custom.compress` that it fires every turn including the first; implementations must self-gate.
Replace `slice(initialMessages.length)` with an explicit `newMessages` accumulator so summarize/custom/sliding-window strategies that shrink conversation history no longer drop newly generated turns. Drops the `turns > 1` gate so oversized initial prompts can trigger compaction before the first LLM call.
Fixes#152.
* feat: add rule-based compact context strategy (#111)
Add `contextStrategy: 'compact'` as a zero-LLM-cost alternative to `summarize`.
Instead of making an LLM call to compress everything into prose, it selectively
compresses old turns using structural rules:
- Preserve tool_use blocks (agent decisions) and error tool_results
- Replace long tool_result content with compact markers including tool name
- Truncate long assistant text blocks with head excerpts
- Keep recent turns (configurable via preserveRecentTurns) fully intact
- Detect already-compressed markers from compressToolResults to avoid double-processing
Closes#111
* fix: remove redundant length guard and fix compact type indentation
Jack Chen
Mark Galyan
MrAvalonApple