docs: cover v0.23 patches and agent reviews - #47
Conversation
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: b43b8cf83e
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
|
|
||
| ::note{icon="i-lucide-megaphone"} | ||
| **New in v0.23:** the search release — reranking, Milvus, and a deadlock-free indexing core. See [What's New in v0.23](/whats-new/v0-23). Also new in Basic Memory Cloud: [Comments and Suggestions](/whats-new/comments-and-suggestions) and the [Interactive MCP App](/whats-new/interactive-mcp-app) for ChatGPT and Claude. | ||
| **New in v0.23:** the search release — reranking, Milvus, and a deadlock-free indexing core. The latest patch, v0.23.2, adds complete PostgreSQL full-text search and prevents case-duplicate folders. See [What's New in v0.23](/whats-new/v0-23). Also new in Basic Memory Cloud: [Comments and Suggestions](/whats-new/comments-and-suggestions) and the [Interactive MCP App](/whats-new/interactive-mcp-app) for ChatGPT and Claude. |
There was a problem hiding this comment.
Attribute PostgreSQL full-text search to v0.23.1
This attributes complete PostgreSQL full-text search to v0.23.2, but the release page and changelog identify it as a v0.23.1 fix; v0.23.2 only adds case-insensitive destination-folder resolution. Readers comparing patches or deciding which release introduced the search migration will get the wrong version boundary, so describe these as cumulative v0.23 patches or name v0.23.1 explicitly.
Useful? React with 👍 / 👎.
| | `replace_subsections` | boolean | No | For `replace_section`; default `true` replaces nested subsections. Set `false` to preserve them | | ||
| | `metadata` | object | No | Merge frontmatter fields independently of the body operation; provided keys overwrite or add values | | ||
| | `workspace` | string | No | Cloud workspace containing the note (name or tenant ID) | | ||
| | `expected_checksum` | string | No | Cloud reviewed notes require the checksum from structured `read_note`; stale or intersecting edits are rejected | |
There was a problem hiding this comment.
Mark expected_checksum as conditionally required
The Required column says No even though this same row and the workflow guide state that Cloud notes with active review work require the checksum from read_note. An integrator relying on the parameter table can therefore omit it and have edits rejected; use Conditional, as this reference already does for other context-dependent parameters.
Useful? React with 👍 / 👎.
Why
Basic Memory v0.23.1 and v0.23.2 shipped user-facing correctness fixes after the main v0.23 documentation landed. Basic Memory Cloud also merged an agent review workflow, but the public docs only described the visual CriticMarkup editor rather than the supported MCP contracts.
What Changed
#bm:links_todirective, and case-insensitive destination-folder resolution.review_noteworkflow for comments, suggestions, replies, resolution, and accept/reject decisions.read_note,edit_note, andsearch_notesbehavior, including structured review projections, revision checksums, protected review ranges, and clean search excerpts.review_notefor data-tool review actions.Implementation Details
review_noteas Cloud-only and directs assistants not to author CriticMarkup or structured review backmatter directly.Testing
npm run check:docs— passed with the repository's expected release-literal warnings.npm run build— passed.git diff --check— passed.Risks / Follow-ups
basic-memory-cloudPR #1825, but that PR did not itself deploy the feature. The docs should publish with or after the corresponding Cloud deployment.