TREE(74): training modules, entity profiles, 2890 references, keyword indices SPROUT(42): knowledge pages, project docs, curated source material SEED(164): daily notes, raw session logs, unprocessed material Updated AUDIT_MANIFEST.json with growth classifications.
1.2 KiB
1.2 KiB
pageType, id, title, sourceType, sourcePath, ingestedAt, updatedAt, status, growth
| pageType | id | title | sourceType | sourcePath | ingestedAt | updatedAt | status | growth |
|---|---|---|---|---|---|---|---|---|
| source | source.2026-03-23 | 2026-03-23 | local-file | /home/topher/.openclaw/workspace-2890-bot/memory/2026-03-23.md | 2026-05-02T21:36:27.468Z | 2026-05-02T21:36:27.468Z | active | seed |
2026-03-23
Source
- Type:
local-file - Path:
/home/topher/.openclaw/workspace-2890-bot/memory/2026-03-23.md - Bytes: 549
- Updated: 2026-05-02T21:36:27.468Z
Content
# 2026-03-23
## Context Pruning Rule (85% Trigger)
- Topher asked for a new heartbeat rule at 85% context limit
- When triggered (~85K tokens):
1. Save most recent 50% to `memory/context_snapshot_recent_*.md`
2. Delete oldest 30% from session storage
3. Log to `memory/context-log.md`
- Implemented in `scripts/context_monitor.py`
- Added TOKEN_PREEMPTIVE = 85000 constant
- New functions: `save_recent_context()`, `prune_oldest_context()`, `log_to_context_log()`
## Testing
- Script runs: `python3 scripts/context_monitor.py --check` → OK
Notes
Related
- No related pages yet.