Jiang Bohan 3dd7ff52d6 feat(context): add tool result pruning for smarter context management ... Two-phase pruning approach based on OpenClaw's microcompact-style: - Soft Trim (30% utilization): Keep head 1500 + tail 1500 chars of large tool results - Hard Clear (50% utilization): Replace old tool results with placeholder Protections: - Never prunes before first real user message (bootstrap protection) - Protects last 3 assistant messages and their corresponding tool results - Skips image-containing tool results - Respects tool allow/deny lists Enabled by default in tokens/summary compaction modes.		2026-02-05 15:50:58 +08:00
..
guard.test.ts	test(context): add unit tests for context window guard	2026-01-30 14:00:38 +08:00
guard.ts	docs: translate comments from Chinese to English (#15)	2026-01-30 04:01:14 +08:00
index.ts	feat(context): add tool result pruning for smarter context management	2026-02-05 15:50:58 +08:00
summarization.ts	docs: translate comments from Chinese to English (#15)	2026-01-30 04:01:14 +08:00
token-estimation.test.ts	test(context): add unit tests for token estimation and compaction	2026-01-30 13:54:57 +08:00
token-estimation.ts	docs: translate comments from Chinese to English (#15)	2026-01-30 04:01:14 +08:00
tool-result-pruning.test.ts	feat(context): add tool result pruning for smarter context management	2026-02-05 15:50:58 +08:00
tool-result-pruning.ts	feat(context): add tool result pruning for smarter context management	2026-02-05 15:50:58 +08:00
types.ts	docs: translate comments from Chinese to English (#15)	2026-01-30 04:01:14 +08:00