slima-mcp 0.3.0 → 0.3.2

package/README.md

@@ -137,19 +137,41 @@ Get your token from [Slima Settings](https://app.slima.ai/settings/api-tokens) o
 gemini mcp add slima --command "npx -y slima-mcp@0"
 ```
 
-> **Why `slima-mcp@0` instead of `slima-mcp` / `slima-mcp@latest`?** Using `@0` pins to the current major version — npx still fetches new `0.x.y` releases automatically (so you get features + bug fixes), but when we ship `1.0.0` with breaking changes you won't silently pick it up without updating your config. We'll announce the `@1` switch in the release notes.
+> **Why `slima-mcp@0` instead of `slima-mcp` / `slima-mcp@latest`?** Using `@0` pins to the current major version — npx fetches new `0.x.y` releases automatically (so you get features + bug fixes), but when we ship `1.0.0` with breaking changes you won't silently pick it up without updating your config. We'll announce the `@1` switch in the release notes.
+>
+> ⚠️ **This only holds if you do not also have a global `slima-mcp` install.** `npx pkg@<range>`
+> will happily satisfy the range from a package already on your `PATH` and never contact the
+> registry at all. Measured on 2026-09-09 with a global `0.2.0` present and `0.3.0` on npm:
+>
+> | command | resolved |
+> |---|---|
+> | `npx -y slima-mcp@0` | **0.2.0** — used the global install |
+> | `npx -y slima-mcp` | **0.2.0** — same |
+> | `npx -y slima-mcp@latest` | 0.3.0 — a dist-tag forces a registry lookup |
+> | `npx -y slima-mcp@0.3.0` | 0.3.0 — the global can't satisfy an exact newer version |
+>
+> So a stale global install makes the npx form silently stop upgrading, while the server keeps
+> telling you to upgrade. Remove it — see below.
 
 #### Migrating from a global install
 
 If you already installed globally with `npm install -g slima-mcp`:
 
 ```bash
-# Remove the old global install (optional but cleaner)
+# Remove the old global install — REQUIRED, not just tidiness.
+# Leaving it in place makes `npx -y slima-mcp@0` resolve to the old global copy
+# forever (see the warning above), so you'd stay outdated while being told to upgrade.
 npm uninstall -g slima-mcp
 
-# Change your config `command` from "slima-mcp" to the npx form above, and restart the client.
+# Then change your config `command` from "slima-mcp" to the npx form above, and restart the client.
+# Verify: `npx -y slima-mcp@0 --version` must print the version shown by `npm view slima-mcp version`.
 ```
 
+⚠️ Check **every** place you may have installed it. A global install can exist per Node version
+manager environment and per OS — on WSL setups it is common to have one under `nvm` *and* one
+under Windows' `AppData/Roaming/npm`, at two different versions, with only one of them on the
+`PATH` your MCP client actually uses.
+
 Or, if you want to stay on a global install, remember to periodically run:
 
 ```bash
@@ -303,8 +325,8 @@ npm run dev:worker
 # Deploy to Cloudflare
 npm run deploy:worker
 
-# Deploy to preview environment
-npm run deploy:worker:preview
+# Deploy to the test environment (test-mcp.slima.ai)
+npm run deploy:worker:test
 ```
 
 ### Project Structure
@@ -352,13 +374,33 @@ git checkout main && git merge dev && git push
 
 ### Cloudflare Worker (Manual)
 
-Worker deployment is separate from npm. Deploy after code changes:
+**Worker deployment is separate from npm, and nothing triggers it automatically.**
+Publishing to npm does NOT update `mcp.slima.ai`. Remote clients (claude.ai /
+ChatGPT connectors) talk to the Worker, so they keep running the old tool set
+until someone runs this by hand:
 
 ```bash
-npm run deploy:worker           # Production (mcp.slima.ai)
-npm run deploy:worker:preview   # Staging
+npm run deploy:worker:test   # Test  (test-mcp.slima.ai -> test-api.slima.ai)
+npm run deploy:worker        # Prod  (mcp.slima.ai      -> api.slima.ai)
 ```
 
+Deploy test first and check `curl https://test-mcp.slima.ai/ | jq .version`
+before doing prod; the same one-liner against `mcp.slima.ai` is how you tell
+whether the Worker is behind npm at all.
+
+> 2026-09-09: the Worker sat on 0.2.0 for four and a half months — it was last
+> deployed the same day npm 0.2.0 shipped, so every change after that reached
+> npm users and no connector users. There is no alarm for this; the version
+> endpoint is the only signal.
+
+> There used to be a `deploy:worker:preview` script pointing at an `[env.preview]`
+> block. It was removed on 2026-09-09: its KV id was the literal placeholder
+> string, `staging-api.slima.ai` does not resolve, and — worst — it defined no
+> `routes`. `routes` is an *inheritable* key in wrangler, so that command would
+> have inherited the top-level `mcp.slima.ai` custom domain and pointed
+> **production's hostname** at the preview Worker. The real staging environment
+> is `[env.test]`.
+
 ### MCP Registry (Manual)
 
 To publish/update the server listing on the [MCP Registry](https://registry.modelcontextprotocol.io/):

package/dist/index.js

@@ -170,7 +170,7 @@ var SlimaApiClient = class {
         headers: {
           Authorization: `Bearer ${token}`,
           "Content-Type": "application/json",
-          "User-Agent": `slima-mcp-server/${"0.3.0"}`
+          "User-Agent": `slima-mcp-server/${"0.3.2"}`
         },
         body: body ? JSON.stringify(body) : void 0,
         signal: controller.signal
@@ -723,7 +723,7 @@ You can now add files using create_file with book_token: ${book.token}`
           };
         }
         const formatted = books.map((book) => {
-          const words = book.totalWordCount?.toLocaleString() || "0";
+          const words = book.manuscriptWordCount?.toLocaleString() || "0";
           return `- **${book.title}** (${book.token}) \u2014 ${studioLabel(book)}
   Author: ${book.authorName || "N/A"} | Words: ${words}`;
         }).join("\n\n");
@@ -767,7 +767,7 @@ _\u{1F4DD} Script Studio books have write restrictions via MCP (see \`get_book\`
 - **Author**: ${book.authorName || "N/A"}
 - **Description**: ${book.description || "N/A"}
 - **Language**: ${book.language || "N/A"}
-- **Total Words**: ${book.totalWordCount?.toLocaleString() || "0"}
+- **Total Words**: ${book.wordCount?.toLocaleString() || "0"}
 - **Manuscript Words**: ${book.manuscriptWordCount?.toLocaleString() || "0"}
 - **Reference Words**: ${book.referenceWordCount?.toLocaleString() || "0"}
 - **Created**: ${book.createdAt}
@@ -851,7 +851,7 @@ figures are account-level and are not exposed here.`,
         const book = await client.getBook(book_token);
         const text2 = `# Writing Stats: ${book.title}
 
-- **Total Words**: ${book.totalWordCount?.toLocaleString() || "0"}
+- **Total Words**: ${book.wordCount?.toLocaleString() || "0"}
 - **Manuscript Words**: ${book.manuscriptWordCount?.toLocaleString() || "0"} (the book itself \u2014 what counts toward the author's word count)
 - **Reference Words**: ${book.referenceWordCount?.toLocaleString() || "0"} (notes, worldbuilding \u2014 never counted)
 - **Language**: ${book.language || "N/A"}
@@ -1525,6 +1525,7 @@ var AI_WRITE_POLICY_NOTE = `
 **Not every file type takes a generic write.**
 - Field-level tools only: ${Object.entries(AI_STRUCTURED_TOOLS).map(([ext, tool]) => `\`${ext}\` \u2192 \`${tool}\``).join(", ")}
 - Not writable at all: ${AI_READONLY_EXTENSIONS.map((e) => `\`${e}\``).join(", ")}
+- \`.map\` is the character relationship graph (\u95DC\u4FC2\u5716) \u2014 not a geographic map; \`.geomap\` is the world map (\u5730\u5716).
 
 A refusal names the file type and what to do instead \u2014 it is information, not
 an obstacle to route around. Call \`get_capabilities\` for the authoritative
@@ -1798,7 +1799,7 @@ Use this instead of \`read_file\` for \`.map\` files: their raw JSON is node ids
 The summary lists every character, every relationship ("A \u2014childhood friends\u2192 B") and any faction groups,
 so it is useful even in clients that do not display images.
 
-\`.map\` files are read-only to AI \u2014 describe changes you recommend in words; the author edits them in the map editor.`,
+To change one, use \`update_relationship_map\` (one field at a time). A \`.map\` is the relationship graph (\u95DC\u4FC2\u5716), not a geographic map \u2014 that is \`.geomap\`.`,
     {
       book_token: z4.string().describe("Book token (e.g., bk_abc123)"),
       path: z4.string().describe('Path to a .map file (e.g., "world/relations.map")')
@@ -1961,6 +1962,7 @@ var TYPES = [
     tool: "update_relationship_map",
     extension: ".map",
     noun: "relationship map",
+    what: "**This is the character relationship graph (\u95DC\u4FC2\u5716) \u2014 not a geographic map.** A world map\n(\u5730\u5716) is `.geomap`, changed with `update_world_map`.",
     ops: "add_node, update_node, move_node, remove_node, add_edge, update_edge, remove_edge, add_group, update_group, remove_group, set_meta",
     example: '{"op": "add_node", "label": "Lin Shuang", "op_ref": "N1", "position": {"near_id": "<id of Shen Yan>", "direction": "right"}}, {"op": "add_edge", "source_id": "<id of Shen Yan>", "target_id": "@N1", "label": "mentor"}',
     extra: '**Position is content here, not layout.** `update_node` will not move anything \u2014 that is\n`move_node`, so that "I moved her next to him" is its own reviewable change. Prefer\n`{near_id, direction}` over computing numbers. Existing nodes never move; the final\ncoordinates come back in the notes. Group boxes are computed from `member_ids` \u2014 never\nsend x/y/width/height. Removing a node removes its edges, and you are told so.'
@@ -1969,6 +1971,7 @@ var TYPES = [
     tool: "update_world_map",
     extension: ".geomap",
     noun: "world map",
+    what: "**This is the geographic world map (\u5730\u5716).** A character relationship graph (\u95DC\u4FC2\u5716) is\n`.map`, changed with `update_relationship_map`.",
     ops: "add_place, update_place, add_label, update_label, remove_element, add_river, add_border, paint_region, set_meta",
     example: '{"op": "add_place", "x": 210, "y": 96, "name": "Starhaven", "tier": "port"}, {"op": "add_label", "x": 240, "y": 60, "text": "The Cold Sea", "size": "large"}',
     extra: "**Coordinates are grid cells, not pixels**: x 0-519, y 0-363. `read_file` gives you the\nmap with its three terrain grids replaced by a note \u2014 they are machine-encoded and you\ndo not need them; `paint_region` works in cells. `remove_element` takes any element id\n(`pl_` place, `lb_` label, `rv_` river, `bd_` border). Terrain has no undo: paint over it\ninstead. Move a place with `update_place`, never by removing and re-adding it. An unknown\nplace `tier` is refused with the full list of real ones \u2014 read the error, do not guess."
@@ -1994,7 +1997,9 @@ you never have to work out how far it got.
 lands in the author's version history immediately. Say what you changed, not
 "please confirm it".`;
 function describe(type) {
-  return `Change a Slima ${type.noun} (\`${type.extension}\`) one field at a time.
+  return `Change a Slima ${type.noun} (\`${type.extension}\`) one field at a time.${type.what ? `
+
+${type.what}` : ""}
 
 This is the ONLY way to write this file type \u2014 \`write_file\` and \`edit_file\`
 are refused for it, because a whole-file write would drop the parts of the
@@ -2568,7 +2573,7 @@ function createSlimaServer(config) {
   const server = new McpServer(
     {
       name: "slima",
-      version: "0.3.0"
+      version: "0.3.2"
     },
     {
       instructions: SERVER_INSTRUCTIONS
@@ -3029,7 +3034,7 @@ async function runStatus() {
 }
 
 // src/cli/index.ts
-var VERSION = "0.3.0";
+var VERSION = "0.3.2";
 function showHelp() {
   console.log(`
 Slima MCP v${VERSION}