- remove legacy contexts surfaces from the app, MCP bridge, standalone server, and docs
- keep getContext and retrieveQueryContext while aligning the simplified graph-only contract
- harden dev startup migration behavior and disable the accidental chat surface in open source
Generated with Codex
- align os MCP/runtime/docs with ra-h contract
- add safe direct node lookup and context-optional flows
- gate edge and context writes behind confirmation
- add external retrieval and confirmation-gated writeback tools across MCP surfaces
- port direct-search-first retrieval support and supporting ranking/query updates
- update MCP docs and skills to treat agent memory files as optional reinforcement
Generated with Claude Code
- enforce canonical dimensions across app and MCP surfaces
- prioritize title-first node search in UI and query tools
- add regression tests for ranking and dimension validation
- make source the canonical field across os routes, tools, ui, and mcp
- align fresh-install schema, search, and embedding flows with source-first ingestion
Generated with Claude Code
The previous schema sync (86f43c9) was incomplete — it renamed variables
but left the SQL statements writing to `type` and `content` columns that
no longer exist in the schema. Fresh installs crash on first node create.
nodeService.js:
- Remove `type` from INSERT/UPDATE, replace with `event_date`
- Fix `content` → `notes` in INSERT values and UPDATE SET clauses
- Add `sanitizeTitle()` and chunk fallback logic
sqlite-client.js:
- Remove `is_pinned` from CREATE TABLE
- Add `description` and `icon` to dimensions table
index.js:
- Add temporal filter fields to search schema
- Improved description prompts
- Dynamic date injection in instructions
server.js + stdio-server.js:
- Add content→notes mapping in update handlers
- Fix output returning `notes` instead of `content`
- Add extraction tool schemas and handlers
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
“BeeRad”