@bicharts/chart-mcp 0.6.54 → 0.6.56

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@bicharts/chart-mcp",
-  "version": "0.6.54",
-  "description": "MCP (Model Context Protocol) stdio server for BIC AI charts: profile a dataset locally, then generate chart code that has passed the BIC backend's render gates. Works with any MCP-capable client (Claude Code, Claude Desktop, Cursor, Copilot Studio). Requires a BIC trial or paid account.",
+  "version": "0.6.56",
+  "description": "MCP (Model Context Protocol) stdio server for BIC AI charts: profile a dataset locally, then generate chart code that has passed the BIC backend's render gates. Works with any MCP-capable client (Claude Code, Claude Desktop, Cursor, Copilot Studio). An account pays to author charts; the code it writes is yours and runs with no licence.",
   "keywords": [
     "mcp",
     "modelcontextprotocol",
@@ -43,8 +43,8 @@
   },
   "// dependencies": "NONE, deliberately. dist/ bundles every module the server uses, so a runtime dependency installs nothing it needs - it only makes npx fetch that package (and its tree) before the first start. Everything the bundle carries is a devDependency; scripts/verify-package.mjs fails the release if a dependency appears or a shipped file imports anything but Node's built-ins.",
   "devDependencies": {
-    "@bicharts/chart-host": "^0.6.52",
-    "@bicharts/shape-core": "^0.6.52",
+    "@bicharts/chart-host": "^0.6.56",
+    "@bicharts/shape-core": "^0.6.56",
     "@modelcontextprotocol/sdk": "^1.0.0",
     "@types/node": "^20.0.0",
     "@types/papaparse": "^5.3.14",

package/skills/bic-charts/SKILL.md

@@ -21,6 +21,16 @@ Skip this if you already have a table. If you are holding a semantic model, a wa
 a database, **you** pick the fields — the tools take a table, not a model, and they cannot see
 what you can. Three decisions, and the third is the one that goes wrong.
 
+**Asked which charts suit the model itself** ("good chart types for this dataset", "what could we
+chart here")? Over a semantic model in a Fabric App, `suggest_charts` answers in one call: it reads
+the model's tables, measures and relationships, finds its natural views (measures by place, flows
+between places, measures over time, measures by category), queries each at its grain, keeps the
+measures that vary there and asks the eligibility engine what fits each. Answer from its reply -
+the counts in it are the model's own - and build the one the person picks from the rows it saved
+(`.bic/data/<view>.csv`, the DAX beside it). Pass `views` (`columns` as `Table[Column]`, `measures`
+by name, or your own `dax`) to ask about other groupings. Elsewhere, pull each candidate grouping
+and ask `list_eligible_charts` about each.
+
 **Fields and filters** follow from the question. *"All loans over the last 6 months, highlighting
 those which defaulted, paying attention to credit score"* wants `LoanId`, `Defaulted`,
 `CreditScore`, filtered to six months.
@@ -464,9 +474,12 @@ build.
 `src/lib/bic-chart-options.ts` (`useBicChartOptions()`: the app's Fabric theme - palette, foreground,
 background - as chart options, so charts follow light and dark) and `src/components/bic-chart-panel.tsx`
 (`<BicChartPanel result={useSemanticModelQuery(...)}>`: a box that measures itself and shows the query's
-loading, error and empty states), and ignores `.bic/`. It also puts every `@microsoft/rayfin-*` package on one version
-(the template installs one too old to deploy, and `rayfin init` later upgrades only some of them - its reply lists every
-`package.json` range it changed; an app already on one deployable version is left alone), and adds
+loading, error and empty states), and ignores `.bic/`. It also puts every `@microsoft/rayfin-*` package on one version -
+npm's latest, the release `rayfin init` installs, so run it before `rayfin init` and init has nothing left to split
+(`rayfin init` installs the latest of only some packages, which leaves two copies of `rayfin-auth` on any other version).
+Its reply lists every `package.json` range it changed and names the Rayfin version installed; an app already on npm's
+latest is left alone. It fixes the template's own `scripts/validate-visual.spec.mjs`, which fails under ESM on a fresh
+scaffold (its reply says so), and adds
 `.agents/skills/regiabi-charts/SKILL.md` beside the template's skills, for agents that read that folder. It never
 overwrites a file, and its reply ends with a worked example.
 
@@ -487,7 +500,7 @@ simply offered other charts. Save the result to a file and pass `csv_path`, or p
 `RevenuePerCapita`, and apply the SAME rename to the live rows at run time - the chart reads columns by
 name. Pass the model's metadata as you rename: `isMeasure`, `format` and `description` (from
 `INFO.VIEW.MEASURES()` / `INFO.VIEW.COLUMNS()`) go on each column in `data`, which is the context a
-Power BI visual gets for free.
+Power BI visual gets for free. In `INFO.VIEW.COLUMNS()` a column's name is `[Name]`, not `[Column]`.
 
 **Steps 1-3 are one call: `query_semantic_model`.** Give it the chart's DAX (`dax`, or a `.dax` file) and a
 `name`; it runs the query through the project's own `fabric-app-data` CLI, renames the headers (dropping the
@@ -588,11 +601,14 @@ it. Anything saved against a mark - a note, a flag - is keyed the same way, neve
 
 **Notes (or flags) on marks, end to end.** People leave a note on a country, a route, a product, and see
 it on that mark: the notes live in Rayfin's data service, and the badge is the chart's `annotations`.
-Every Rayfin fact here was checked on Rayfin 1.36.1, a preview - where your installed version differs,
-its own docs (`node_modules/@microsoft/rayfin-guide/assets/docs/data/`) win.
+This recipe was checked against Rayfin's own docs for Rayfin 1.36.1 (a preview), the version
+`setup_fabric_app` installs as this is written, and on that version it IS the version-matched source:
+follow it as written, and read Rayfin's docs (`node_modules/@microsoft/rayfin-guide/assets/docs/data/`)
+only for what it doesn't cover. `setup_fabric_app`'s reply names the version it installed; where that
+differs from 1.36.1, Rayfin's docs win.
 
-*a. Turn the data service on.* The data app template ships it off. Run `setup_fabric_app` first -
-`setup_fabric_app` puts every `@microsoft/rayfin-*` package on one version - then:
+*a. Turn the data service on.* The data app template ships it off. Run `setup_fabric_app` first (it puts every `@microsoft/rayfin-*` package on one version:
+npm's latest, the release `rayfin init` installs), then:
 
 ```bash
 npx rayfin init --services auth,data --auth-methods fabric --dialect mssql --overwrite --project-name <id from rayfin/rayfin.yml> .
@@ -740,6 +756,8 @@ export function NotesDialog({ title, notes, onAdd, onClose }: {
 Style it with the app's own tokens. The table and the permissions are created on the next
 `npx rayfin up`, and every later `rayfin up` applies entity changes.
 
+Don't stand up a backend to test notes; the deploy creates the tables. Finish with `npx tsc -b` and the tests, and say the notes go live on deploy.
+
 **7. A reader's choice inside a chart is view state.** A what-if chart's rate and horizon are its
 own controls, reported through `viewState` on `<BicChart>` (`uiState` / `setUiState` in the
 integration contract). To save a named scenario, store that - don't rebuild the slider beside it.
@@ -749,8 +767,13 @@ service - the notes recipe above), `VisualContainer` headers, deployment. The ch
 render inside them.
 
 **9. Check every chart, then deploy.** Check every chart locally with this server's `check_chart` tool,
-at the size the layout gives it - you don't need to deploy to check a chart. Then `npx tsc -b` and the
-tests. Deploying (`npx rayfin up`), on Rayfin 1.36.1:
+at the size the panel will give it - by default it reads the chart's `minChartWidth` and `minChartHeight`
+off its `BicChartPanel`, so pass no size unless you mean another one. A `WARNING` line in its reply is a
+label cut off at that size: deal with it before you call the chart done. The reply says whether more room fixes it.
+Never edit the generated chart code by hand: if something's wrong with a generated chart, regenerate it
+(`generate_chart` with a prompt describing the fix) or report it.
+You don't need to deploy to check a chart. Then `npx tsc -b` and the tests. Deploying (`npx rayfin up`), on Rayfin 1.36.1:
+- Signed in? `npx rayfin login status` (a subcommand, not a `--status` flag); `npx rayfin login` if not.
 - Name the workspace: `npx rayfin up -w "<workspace>"`. Left out, it deploys to My Workspace.
 - The Fabric item is named by `id:` in `rayfin/rayfin.yml`, not `name:`. Two projects with the same
   `id:` in one workspace deploy into one item: give each its own `id:`, or deploy with
@@ -758,6 +781,8 @@ tests. Deploying (`npx rayfin up`), on Rayfin 1.36.1:
 - Deleted the app outside Rayfin? `rayfin/.deployments.json` still names the deleted item, so the next
   `rayfin up` fails with 404 Not Found. Move that file aside and deploy again.
 
+What it costs: only the calls that author a chart (generate_chart, and the eligibility lists beyond a free hourly allowance) draw on the account. The chart code they write is the user's to keep and ship: it needs no licence, account, credits or connection to us to run, view or deploy, for any number of viewers.
+
 ## 4. Things that will otherwise cost you time
 
 - **Place names, not coordinates.** If your data has city/state/ZIP but no lat/lon, pass a