@stratta/mcp 1.19.0 → 1.20.0

package/README.md

@@ -198,18 +198,18 @@ package announces 59 of them; the remote connector serves 61: everything minus
 
 **Read** (10 tools — query the norms of your workspace):
 
-| Tool              | Purpose                                                                                 |
-| ----------------- | --------------------------------------------------------------------------------------- |
-| `get_methodology` | Behavioural contract: persona, workflow, meta-routing hints, answer rules. Call first.  |
-| `whoami`          | Which organisation, role and plan this connection reads as, and how many norms it sees. |
-| `list_norms`      | List all norms published in your workspace (code, year, title, language, coverage).     |
-| `get_toc`         | Hierarchical TOC for a norm (default `maxDepth=1` = chapters).                          |
-| `get_subtree`     | Drill into a chapter/section subtree (`path` + `maxDepth`).                             |
-| `get_section`     | Full enriched content of a section (formulas, tables, figures, cross-refs).             |
-| `search_in_norm`  | Keyword search inside a norm.                                                           |
-| `search_corpus`   | Keyword search across every norm of the workspace, grouped by norm.                     |
-| `get_figure`      | Retrieve a figure inline (base64 ImageContent).                                         |
-| `get_cross_refs`  | Outgoing cross-refs from a section to other norms.                                      |
+| Tool              | Purpose                                                                                          |
+| ----------------- | ------------------------------------------------------------------------------------------------ |
+| `get_methodology` | Behavioural contract: persona, workflow, meta-routing hints, answer rules. Call first.           |
+| `whoami`          | Which organisation, role and plan this connection reads as, and how many norms it sees.          |
+| `list_norms`      | List the norms of your workspace, filtered by `query` (code or title words), bounded by `limit`. |
+| `get_toc`         | Hierarchical TOC for a norm (default `maxDepth=1` = chapters).                                   |
+| `get_subtree`     | Drill into a chapter/section subtree (`path` + `maxDepth`).                                      |
+| `get_section`     | Full enriched content of a section (formulas, tables, figures, cross-refs).                      |
+| `search_in_norm`  | Keyword search inside a norm.                                                                    |
+| `search_corpus`   | Keyword search across every norm of the workspace, grouped by norm.                              |
+| `get_figure`      | Retrieve a figure inline (base64 ImageContent).                                                  |
+| `get_cross_refs`  | Outgoing cross-refs from a section to other norms.                                               |
 
 **Site** (10 tools — what public Swiss registers know about a plot, and the site sheet as the app shows it):
 

package/dist/tools/catalog.gen.js

@@ -37,7 +37,7 @@ export const CATALOG = [
     {
         "name": "list_norms",
         "title": "Available norms",
-        "description": "List the norms and reference documents (standards, laws, regulations) published in the signed-in organization, with code, year, title, language and coverage (how much of the norm was ingested). Use this when a question may be settled by the documents of the organization and the norm is not yet known: a norm absent from this list cannot be read here. A demo entry is fictional and never a technical reference; a sparse entry carries a notice to relay.",
+        "description": "List the norms and reference documents (standards, laws, regulations) published in the signed-in organization, with code, year, title, edition, language and coverage (how much of the norm was ingested). Use this to check whether a norm is held, which editions are readable, or what a norm covers: a norm absent from this organization cannot be read here. Pass `query` with a code or words of the title; a large corpus is listed in part, and `total` says how many norms there are. A demo entry is fictional and never a technical reference; a sparse entry carries a notice to relay.",
         "annotations": {
             "readOnlyHint": true,
             "destructiveHint": false,
@@ -48,7 +48,10 @@ export const CATALOG = [
             "stdio",
             "remote"
         ],
-        "params": {}
+        "params": {
+            "query": "A code or words of the title or scope, accents optional, e.g. \"SIA 267\" or \"geotechnique\". Every word must match. With a query, each norm comes with its scope.",
+            "limit": "Maximum number of norms listed, 1 to 500. Default 60."
+        }
     },
     {
         "name": "get_toc",
@@ -829,7 +832,7 @@ export const CATALOG = [
         ],
         "params": {
             "dossierId": "Dossier id from list_dossiers, open_dossier or load_dossier.",
-            "limit": "Lines per page, 1 to 200. Default 50.",
+            "limit": "Lines per page, 1 to 200. Default 15, the most recent first.",
             "cursor": "The nextCursor of the previous page."
         }
     },

package/dist/tools/read.d.ts

@@ -1,7 +1,10 @@
 import { z } from 'zod';
 export declare const getMethodology: import("./define.js").ToolDef<{}>;
 export declare const whoami: import("./define.js").ToolDef<{}>;
-export declare const listNorms: import("./define.js").ToolDef<{}>;
+export declare const listNorms: import("./define.js").ToolDef<{
+    query: z.ZodOptional<z.ZodString>;
+    limit: z.ZodOptional<z.ZodNumber>;
+}>;
 export declare const getToc: import("./define.js").ToolDef<{
     code: z.ZodString;
     edition: z.ZodOptional<z.ZodString>;
@@ -42,6 +45,9 @@ export declare const getFigure: import("./define.js").ToolDef<{
     figureId: z.ZodString;
 }>;
 export declare const readTools: (import("./define.js").ToolDef<{}> | import("./define.js").ToolDef<{
+    query: z.ZodOptional<z.ZodString>;
+    limit: z.ZodOptional<z.ZodNumber>;
+}> | import("./define.js").ToolDef<{
     code: z.ZodString;
     edition: z.ZodOptional<z.ZodString>;
     maxDepth: z.ZodOptional<z.ZodNumber>;

package/dist/tools/read.js

@@ -50,11 +50,24 @@ export const whoami = defineTool({
 });
 export const listNorms = defineTool({
     ...headOf('list_norms'),
-    inputSchema: {},
-    run: async (client) => ({
-        norms: await client.action(api._mcp.listPublishedNorms, {
-            apiKey: requireApiKey(),
-        }),
+    inputSchema: {
+        query: z
+            .string()
+            .max(200)
+            .optional()
+            .describe(param('list_norms', 'query')),
+        limit: z
+            .number()
+            .int()
+            .min(1)
+            .max(500)
+            .optional()
+            .describe(param('list_norms', 'limit')),
+    },
+    run: (client, args) => client.action(api._mcp.listNorms, {
+        apiKey: requireApiKey(),
+        query: args.query,
+        limit: args.limit,
     }),
 });
 export const getToc = defineTool({

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@stratta/mcp",
   "mcpName": "ch.stratta/mcp",
-  "version": "1.19.0",
+  "version": "1.20.0",
   "description": "MCP server exposing your organization’s norms and reference documents (standards, laws, regulations) to any MCP client, with exact citations, via Stratta TreeRAG.",
   "license": "UNLICENSED",
   "author": "SmartFlow <hello@stratta.ch>",

package/scripts/ingest-prepass.py

@@ -51,7 +51,9 @@ TOC_DOT_RE = re.compile(r"\.\s*\.\s*\.")
 CLEAN_DOTS = re.compile(r"\s*(\.\s*){3,}.*$")
 
 CAPTION_RE = re.compile(
-    r"^\s*(?:Figure|Fig\.|Bild|Abbildung|Figura)\s+(\d+[a-z]?)\b[\s:.\-—–]*(.*)$",
+    # « Figure 1.2 » garde tout son numéro : réduit à « 1 », il était dédoublonné avec « 1.1 »
+    # et ASIRI ne gardait qu'une figure par chapitre.
+    r"^\s*(?:Figure|Fig\.|Bild|Abbildung|Figura)\s+(\d+(?:\.\d+)*[a-z]?)\b[\s:.\-—–]*(.*)$",
     re.IGNORECASE | re.MULTILINE,
 )
 
@@ -199,10 +201,26 @@ def page_lines(doc: "pymupdf.Document", pageno: int) -> list[str]:
             text = OCR_DOTTED_NUMBER_RE.sub(r"\1.\2", text)
             lines.append(text)
     lines = [l.rstrip() for l in lines]
+    # ⚠️⚠️ Regrouper les mots par hauteur suppose que la hauteur dit la ligne. Sur certains PDF
+    # (RMP, LVMP, SUVA BauAV neu : chaque mot posé à sa propre hauteur) le regroupement rend une
+    # soupe de mots que le compte de mots ne voit pas, puisqu'il ignore l'ordre. Quand les paires
+    # de mots consécutifs ne recoupent pas à 30 % celles de la lecture native, la native l'emporte.
+    native = page.get_text("text")
+    ours = _word_pairs("\n".join(lines))
+    if len(ours) >= 20 and len(ours & _word_pairs(native)) / len(ours) < 0.3:
+        lines = [l.rstrip() for l in join_split_headings(native).splitlines()]
     _LINES_CACHE[key] = lines
     return lines
 
 
+_PAIR_WORD = re.compile(r"[0-9A-Za-zÀ-ÿ]{2,}")
+
+
+def _word_pairs(text: str) -> set[tuple[str, str]]:
+    w = [x.lower() for x in _PAIR_WORD.findall(text)]
+    return set(zip(w, w[1:]))
+
+
 def page_text(doc: "pymupdf.Document", pageno: int) -> str:
     return "\n".join(page_lines(doc, pageno))
 
@@ -1091,7 +1109,48 @@ def extract_figures(
                 "renderDpi": dpi,
                 "mimeType": "image/png",
             }
-    return list(seen.values())
+    # ⚠️ Une page qui porte un grand dessin sans légende « Figure N » (« Beilage C : », « Abb. 3 »,
+    # un schéma sans titre) n'était pas retenue : 65 normes du corpus KF perdaient 847 images.
+    # Une image de 300 × 300 px couvrant 10 % de la page au moins en fait une figure ; la page 1
+    # (couverture) et les logos en sont exclus.
+    have = {f["page"] for f in seen.values()}
+    for pageno in range(1, doc.page_count):
+        if pageno in toc_pages or pageno + 1 in have:
+            continue
+        page = doc[pageno]
+        area = page.rect.width * page.rect.height
+        big = any(
+            i.get("width", 0) >= 300
+            and i.get("height", 0) >= 300
+            and (i["bbox"][2] - i["bbox"][0]) * (i["bbox"][3] - i["bbox"][1]) >= 0.10 * area
+            for i in page.get_image_info()
+        )
+        if not big:
+            continue
+        m = FREE_LABEL_RE.search(page_text(doc, pageno))
+        label = re.sub(r"\s+", " ", m.group(1)).strip().rstrip(":") if m else None
+        rest = re.sub(r"\s+", " ", m.group(2)).strip() if m else ""
+        number = label or f"p. {pageno + 1}"
+        while number in seen:
+            number = f"{number} (p. {pageno + 1})"
+        pix = page.get_pixmap(matrix=matrix, alpha=False)
+        page_png = figs_dir / f"page-{pageno + 1:03d}.png"
+        pix.save(str(page_png))
+        seen[number] = {
+            "figureNumber": number,
+            "caption": (f"{label} — {rest}" if label and rest else label or f"Illustration, page {pageno + 1}")[:240],
+            "page": pageno + 1,
+            "fileName": f"figures/{page_png.name}",
+            "renderDpi": dpi,
+            "mimeType": "image/png",
+        }
+    return sorted(seen.values(), key=lambda f: f["page"])
+
+
+FREE_LABEL_RE = re.compile(
+    r"^\s*((?:Beilage|Anhang|Annexe|Abb\.?|Bild|Schéma|Schema|Planche|Tafel)\s*[\w.]*)\s*[:\-–]?\s*(.{3,120})$",
+    re.IGNORECASE | re.MULTILINE,
+)
 
 
 def guess_language(doc: "pymupdf.Document") -> str:

package/skills/consult-stratta/SKILL.md

@@ -5,7 +5,7 @@ description: Use Stratta to answer professional questions from the norms and ref
 
 # Consult Stratta
 
-Use this skill when the user asks a technical civil engineering question that should be answered from the norms available in Stratta, or when the user asks to resume, create or update a Stratta project dossier.
+Use this skill when the user asks a professional question that should be answered from the norms, laws or reference documents available in Stratta, or when the user asks to resume, create or update a Stratta project dossier.
 
 You answer professionals (engineers, lawyers, accountants, public administrations and others) from the norms and reference documents their organization holds in Stratta (technical standards, laws, ordinances, regulations, accounting standards, internal references), and only from them. The corpus below is the whole of what you can read: a document absent from it cannot be consulted, and a question outside it is answered by saying so, not by general knowledge. "Norm" below means any such document. Reply in the language the user writes in; quote the norm in the language it is written in and translate only when asked.