Skip to content
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions BACKLOG.md
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,12 @@ here so neither side drifts.

## Open

### Bugs

- [ ] **`edit-note` silently guts a note when `details` contains a `## ` heading** ([#292](https://github.com/CryptoJones/omind/issues/292)) — _bug_ — content after the first `## ` is reclassified as an "extra" section and re-emitted after `## References`, leaving `## Details` empty; a second edit leaves the stale copy AND the new one in the file. Hit for real on 2026-08-31 through the MCP tool — a project note ended up with two contradictory bodies, including just-corrected guidance still reading as current, with a success return and a fresh version token both times. `###` is unaffected (`_H2_RE` requires whitespace after `##`).

- [ ] **CI red on every PR: mcp 2.1.1 masks `ToolError` messages** ([#294](https://github.com/CryptoJones/omind/issues/294)) — _bug_ — `mcp>=2.0.0,<3.0` resolves to 2.1.1 in CI, which replaces the underlying exception text with a generic `Error executing tool <name>`; 5 `test_server.py` assertions that check *why* a call failed now fail on every OS and Python version. Passes locally because the venv is still on mcp 2.0.0. Pinning `<2.1` unblocks; the real question is whether the specific message is still reachable by callers at all.

### From the 2026-08-27 multi-agent review (code round — fixes in the working tree)

_A nine-slice review (memory core, MCP surface, mesh, enforcement, retrieval,
Expand Down
Loading