vvzvlad afd2248a75 feat(ai-chat): tolerate markdown in edit_page_text/insert_node locators ...

Locators (edit_page_text `find`, insert_node `anchorText`) are matched
against the document's plain text, so a model-supplied locator carrying
markdown wrappers (**bold**, *italic*, `code`, [t](url)) or trailing emoji
never matched and the edit/insert failed. Add stripInlineMarkdown() and a
fallback: try the locator verbatim first (exact match wins, so literal
asterisks/underscores still work), and only on zero matches retry with a
markdown-stripped form. The ambiguity guard runs on the post-fallback count,
and `replace` / inserted node content are never stripped, so no formatting is
lost. Failed edits gain an atom-aware reason plus a bounded "closest block
text" hint; the insert_node "anchor not found" error now points at plain-text
anchors / anchorNodeId.

New packages/mcp/src/lib/text-normalize.ts (+ unit tests); wired into
json-edit.ts and node-ops.ts; tool descriptions updated. Tests: 212 pass.

2026-06-17 15:44:19 +03:00

1.4 KiB

Raw Blame History

View Raw