The .openclaw/workspace-* dirs were empty templates. Antoine's real
OpenClaw workspace is /home/papa/clawd with SOUL.md, USER.md,
MEMORY.md, MODEL-ROUTING.md, IDENTITY.md, PROJECT_STATE.md and
rich continuity subdirs (decisions/, lessons/, knowledge/,
commitments/, preferences/, goals/, projects/, handoffs/, memory/).
First real import: 10 candidates produced from 11 files scanned.
MEMORY.md (36K chars) skipped as duplicate content; needs smarter
section-level splitting in a follow-up.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
scripts/import_openclaw_state.py reads the OpenClaw file continuity
layer from clawdbot (T420) via SSH and imports candidate memories
into AtoCore. Loose coupling: OpenClaw's internals don't need to
change, AtoCore pulls from stable markdown files.
Per codex's integration proposal (docs/openclaw-atocore-integration-proposal.md):
Classification:
- SOUL.md -> identity candidate
- USER.md -> identity candidate
- MODEL-ROUTING.md -> adaptation candidate (routing rules)
- MEMORY.md -> memory candidate (long-term curated)
- memory/YYYY-MM-DD.md -> episodic candidate (daily logs, last 7 days)
- heartbeat-state.json -> skipped (ops metadata only, not canonical)
Delta detection: SHA-256 hash per file stored in project_state
under atocore/status/openclaw_import_hashes. Only changed files
re-import. Hashes persist across runs so no wasted work.
All imports land as status=candidate. Auto-triage filters. Nothing
auto-promotes — the importer is a signal producer, the pipeline
decides what graduates.
Discord: deferred per codex's proposal — no durable local store in
current OpenClaw snapshot. Revisit if OpenClaw exposes an export.
Wired into cron-backup.sh as Step 3a (before vault refresh +
extraction) so OpenClaw signals flow through the same pipeline.
Gated on ATOCORE_OPENCLAW_IMPORT=true (default true).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
