opentakeoff-mcp 0.9.40 → 0.9.42

package/README.md

@@ -311,6 +311,19 @@ sheet number (`A-101`) wherever a sheet is named.
   has nothing for `detect_rooms`/`sheet_graph`/`resolve_tag` to read: seeds
   come from you (`view_sheet`, then `one_click`). The raster path needs the
   same optional `@napi-rs/canvas` as `view_sheet`.
+- **Stitching is human-only — deliberately, not a gap.** The canvas can join
+  2–4 sheets split at a match line into one composite surface (#200), but no
+  MCP verb creates, aligns, or addresses a stitch. Joining the match line
+  means clicking the same drawn wall junction on both halves — a judgment
+  call with a worse blast radius than a bad scale, because a sloppy align
+  silently skews every quantity that crosses the seam. That stays behind
+  human eyes; it is not staged for later exposure. For a split floor: a
+  human stitches and aligns in the canvas, and over MCP you work each member
+  sheet as its own surface — a seam-crossing room belongs to the canvas.
+  This server also doesn't read the app's additive `stitches` payload field,
+  so a stitched takeoff round-tripped through `import_takeoff` →
+  `export_takeoff` comes back without its stitches — when a stitch is in
+  play, the app's own save is the one to keep.
 - `load_plan` replaces the session by default; `merge: true` builds a multi-document working set (#152). Reloading a merged file is refused — reload = replace, deliberately.
 - The takeoff lives in memory. `export_takeoff` (the app's exact save payload,
   nothing lost in translation) and `export_marked_pdf` (the reviewable marked

package/dist/server-core.js

@@ -10639,7 +10639,7 @@ function applyStagedTools(server, registered) {
 // package.json
 var package_default = {
   name: "opentakeoff-mcp",
-  version: "0.9.40",
+  version: "0.9.42",
   mcpName: "io.github.Kentucky-ai/opentakeoff",
   type: "module",
   description: "OpenTakeoff MCP server \u2014 drive the takeoff engine from your MCP client over stdio.",
@@ -10725,6 +10725,7 @@ function buildServer(session = new Session(), opts = {}) {
       "3. DERIVE what follows from the rooms instead of re-measuring it: derive_base for base LF (perimeter \u2212 the door openings YOU state), derive_transitions for the line where two finishes meet. Both read committed floor shapes, so they come after step 2 and their output is audited in step 4 like anything else.",
       "4. LOOK at what landed with view_sheet overlay:true and fix misses with edit_shape before trusting totals \u2014 crop the work region tight (full-sheet renders downsample too far to audit a ring).",
       "5. Finish by writing the marked-up planset with export_marked_pdf and give the user its file path, alongside export_report for the numbers. Never end a takeoff with numbers alone.",
+      "A floor split across sheets at a MATCH LINE: there is no stitch verb, deliberately \u2014 joining and aligning a match line is human judgment in the canvas (a sloppy join silently skews every seam-crossing quantity). Measure each member sheet as its own surface and tell the user a seam-crossing room needs their stitch in the app; never approximate one by combining sheets yourself.",
       "WITHHELD IS NOT A FAILURE \u2014 IT IS THE ANSWER. detect_rooms, symbol_sweep, sweep_schedule_row and derive_transitions all measure things they then decline to commit, and say why: a near-match in the score band, a room the schedule cannot answer for, adjacency across a WALL rather than a butt joint. Read those arrays, view_sheet the coordinates they hand you, and resolve them or report them. A withheld item you ignore is a hole in the bid; one you never mention is worse.",
       ...staged ? [STAGED_INSTRUCTIONS] : []
     ].join("\n")

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "opentakeoff-mcp",
-  "version": "0.9.40",
+  "version": "0.9.42",
   "mcpName": "io.github.Kentucky-ai/opentakeoff",
   "type": "module",
   "description": "OpenTakeoff MCP server — drive the takeoff engine from your MCP client over stdio.",