SUMMARY

• Overview
• Path-scoped write coordination: per-path coordinator lease + per-box zettelkasten locks
• Built core stream/ package: portable drivers + headless executor + multi-schema extraction template + config/feeds/router facade
• v2 spine model: structure tree + first-class spine-side membership relation (supersedes grid framing)
• Schemas can declare materialized structure (the synthesis spine); added a schema-generation tool
• Spines are additive/separate/selectable layers: NOT project sources, spine-side edges, 'Organize by' picker
• Implemented grounded-extraction bundle via a generic coordinator capability-contribution seam
• Per-workspace dashboard identity: stable instance id + auto-derived ports
• Source-first ingestion for the zettelkasten agent (ingest_source + content-hash + full-text cache)
• Moved zettelkasten storage to committed .zettelkasten/ (mirrors .memory/)
• Committing code auto-writes to memory (git-commit/push triggers memory record + flush)
• Plan: cloud-first experiment rerun with S3 job queue and AWS runner
• Cluster view: semantic embedding layout with auto-detected clusters
• Multi-parent DAG: contains edges, ELK layered layout, cycle-safe add_parent API
• Decision: Memory-native manifests over DVC pipelines for experiment tracking
• Replaced linear pipeline with alias-based DAG graph
• Chose KGLite as the knowledge graph backend