bunnyquery 1.3.4 → 1.4.0

package/README.md

@@ -24,6 +24,9 @@ you can build your own chat UI on top of it. See
   first load and on scroll-up.
 - **Attachments** — drag-and-drop files and folders, per-file upload status
   (uploading / failed / indexed), and overflow collapsing for large batches.
+- **Attachment parser plugins** — register a client-side parser so the widget
+  extracts text in the browser from formats the model can't otherwise read, and
+  indexes it directly. See [Attachment parser plugins](#attachment-parser-plugins).
 - **Settings panel** — in-place inside the chat: light/dark theme, account details,
   newsletter subscription, clear history, and remove account.
 - **Theming** — light and dark modes via CSS custom properties; the choice is
@@ -110,17 +113,19 @@ Mounts the widget. Returns the `BunnyQuery` object.
 | `dev`                    | `boolean` | `false`  | Use the development MCP host and `skapi.app` db-CDN host instead of production.               |
 | `mcpBaseUrl`             | `string`  | `null`   | Override the MCP OAuth server base URL entirely (advanced).                                   |
 | `hostDomain`             | `string`  | `null`   | db-CDN host for temporary file URLs. Defaults to `skapi.app` (dev) / `skapi.com` (prod).     |
+| `attachmentParsers`      | `array`   | `null`   | Client-side attachment parsers. See [Attachment parser plugins](#attachment-parser-plugins). |
 
 ### Methods
 
 The `BunnyQuery` global also exposes:
 
-| Method               | Description                                                        |
-| -------------------- | ----------------------------------------------------------------- |
-| `setTheme(theme)`    | Apply `"light"` or `"dark"` and persist it.                       |
-| `toggleTheme()`      | Switch between light and dark.                                    |
-| `logout()`           | Sign the current user out and return to the login view.           |
-| `version`            | The widget version string.                                        |
+| Method                             | Description                                                                         |
+| ---------------------------------- | ----------------------------------------------------------------------------------- |
+| `setTheme(theme)`                  | Apply `"light"` or `"dark"` and persist it.                                          |
+| `toggleTheme()`                    | Switch between light and dark.                                                       |
+| `logout()`                         | Sign the current user out and return to the login view.                             |
+| `registerAttachmentParser(parser)` | Register a client-side attachment parser. May be called before or after `init()`. See [Attachment parser plugins](#attachment-parser-plugins). |
+| `version`                          | The widget's package version string. Also logged to the console on `init()`.        |
 
 ```js
 BunnyQuery.setTheme("dark");
@@ -129,7 +134,71 @@ BunnyQuery.logout();
 ```
 
 > `init()` is idempotent — calling it twice logs a warning and returns the existing
-> instance rather than re-mounting.
+> instance rather than re-mounting. On a successful mount it logs its version, e.g.
+> `[bunnyquery] v1.3.5`.
+
+## Attachment parser plugins
+
+By default the chat agent reads most uploads via the model's `web_fetch` tool
+(text, CSV, PDF, …), and Office/OpenDocument/EPUB files are extracted on the
+server. For any format that can be read by **neither** (e.g. a proprietary
+binary format), register a **parser plugin**: it runs in the browser, turns the
+uploaded file into text (or an HTML string), and the widget sends that content
+**inline** for indexing — no `web_fetch`, no server extraction for that file.
+
+BunnyQuery ships only the **mechanism**. You bring the parsing library (so the
+widget stays lean and you choose which formats and which library).
+
+A parser is a plain object:
+
+```ts
+interface AttachmentParser {
+  name?: string;                                   // label, used in logs
+  match: (file: { name: string; mime?: string }) => boolean;   // handle this file?
+  parse: (file: File) => string | null | undefined | Promise<string | null | undefined>; // text or HTML; falsy = skip
+}
+```
+
+The first parser whose `match` returns `true` wins. A parser that throws or
+returns nothing is ignored — the file falls back to its normal path. Output is
+capped (~200k chars) before it is inlined.
+
+### Example
+
+Load whatever parsing library reads your format, then register a parser that
+turns a `File` into text:
+
+```html
+<!-- bring your own parsing library, e.g. from a CDN -->
+<script src="https://cdn.example.com/my-format-parser.js"></script>
+<script>
+  BunnyQuery.registerAttachmentParser({
+    name: "my-format",
+    match: (file) => /\.myext$/i.test(file.name),
+    parse: async (file) => {
+      const bytes = new Uint8Array(await file.arrayBuffer());
+      return window.myFormatParser.toText(bytes); // return plain text OR an HTML string
+    },
+  });
+
+  BunnyQuery.init(skapi, "chatbox", { theme: "light" });
+</script>
+```
+
+Equivalent one-shot form via init options:
+
+```js
+BunnyQuery.init(skapi, "chatbox", {
+  attachmentParsers: [ myParser ],
+});
+```
+
+Bundler consumers can import the same registry from the engine:
+
+```js
+import { registerAttachmentParser } from "bunnyquery/engine";
+registerAttachmentParser(myParser);
+```
 
 ## Theming
 

package/bunnyquery.js

@@ -1,10 +1,52 @@
 (function () {
   'use strict';
 
+  // src/engine/attachment_parsers.ts
+  var MAX_PARSED_CONTENT_CHARS = 2e5;
+  var _parsers = [];
+  function registerAttachmentParser(parser) {
+    if (parser && typeof parser.match === "function" && typeof parser.parse === "function" && _parsers.indexOf(parser) === -1) {
+      _parsers.push(parser);
+    }
+  }
+  function findAttachmentParser(name, mime) {
+    for (let i = 0; i < _parsers.length; i++) {
+      try {
+        if (_parsers[i].match({ name, mime })) return _parsers[i];
+      } catch {
+      }
+    }
+    return void 0;
+  }
+  async function parseAttachmentContent(file, name, mime) {
+    const parser = findAttachmentParser(name, mime);
+    if (!parser) return null;
+    let raw;
+    try {
+      raw = await parser.parse(file);
+    } catch (err) {
+      console.error(
+        `[chat-engine] attachment parser ${parser.name || "(unnamed)"} failed for ${name}:`,
+        err
+      );
+      return null;
+    }
+    let text = (raw == null ? "" : String(raw)).trim();
+    if (!text) return null;
+    if (text.length > MAX_PARSED_CONTENT_CHARS) {
+      text = text.slice(0, MAX_PARSED_CONTENT_CHARS) + `
+...[truncated for length; original ${text.length} characters]`;
+    }
+    return text;
+  }
+
   // src/engine/config.ts
   var _config = null;
   function configureChatEngine(config) {
     _config = config;
+    if (config.attachmentParsers) {
+      for (const parser of config.attachmentParsers) registerAttachmentParser(parser);
+    }
   }
   function chatEngineConfig() {
     if (!_config) {
@@ -31,13 +73,41 @@
     "pptx",
     "pptm",
     "hwp",
-    "hwpx"
+    "hwpx",
+    "ods",
+    "odt",
+    "odp",
+    "epub"
+  ]);
+  var WEB_FETCHABLE_TEXT_EXTENSIONS = /* @__PURE__ */ new Set([
+    "csv",
+    "tsv",
+    "tab",
+    "txt",
+    "text",
+    "md",
+    "markdown",
+    "json",
+    "ndjson",
+    "jsonl",
+    "xml",
+    "yaml",
+    "yml",
+    "log",
+    // RTF is a TEXT format (not a binary zip), so web_fetch can read it and the
+    // model decodes its control words. Pin it here so a `.rtf` reported as
+    // `application/msword` isn't misrouted to server-side extraction (which has no
+    // .rtf extractor → "unsupported format" note).
+    "rtf",
+    "htm",
+    "html"
   ]);
   function isOfficeFile(name, mime) {
     const ext = (name || "").split(".").pop()?.toLowerCase() || "";
     if (OFFICE_FILE_EXTENSIONS.has(ext)) return true;
+    if (WEB_FETCHABLE_TEXT_EXTENSIONS.has(ext)) return false;
     const m = (mime || "").toLowerCase();
-    return m.includes("officedocument") || m.includes("hwp") || m === "application/msword" || m === "application/vnd.ms-excel" || m === "application/vnd.ms-powerpoint";
+    return m.includes("officedocument") || m.includes("opendocument") || m.includes("hwp") || m.includes("epub") || m === "application/msword" || m === "application/vnd.ms-excel" || m === "application/vnd.ms-powerpoint";
   }
   var _extractPlaceholderSeq = 0;
   function makeExtractPlaceholder(seed) {
@@ -158,6 +228,14 @@ File metadata:
 ` + (attachment.mime ? `- mime type: ${attachment.mime}
 ` : "") + (typeof attachment.size === "number" ? `- size (bytes): ${attachment.size}
 ` : "");
+    if (options?.inlineContent) {
+      return head + `
+The file's content was parsed by the client and is provided inline below. Read it directly \u2014 do NOT fetch any URL for this file. Use the storage path above (not this content) for the "src::" unique_id.
+
+----- BEGIN FILE CONTENT -----
+${options.inlineContent}
+----- END FILE CONTENT -----`;
+    }
     if (options?.inlineContentPlaceholder) {
       return head + `
 The file's text content was extracted on the server and is provided inline below. Read it directly \u2014 do NOT fetch any URL for this file. Use the storage path above (not this content) for the "src::" unique_id.
@@ -653,14 +731,14 @@ ${options.inlineContentPlaceholder}
     });
   }
   async function notifyAgentSaveAttachment(info) {
-    const { platform, service, owner, attachment } = info;
-    const office = isOfficeFile(attachment.name, attachment.mime);
+    const { platform, service, owner, attachment, parsedContent } = info;
+    const office = !parsedContent && isOfficeFile(attachment.name, attachment.mime);
     const placeholder = office ? makeExtractPlaceholder(attachment.storagePath) : void 0;
     const extractContent = office && placeholder ? [{ path: attachment.storagePath, placeholder, name: attachment.name, mime: attachment.mime }] : void 0;
     const skapiExtract = extractContent && extractContent.length ? { _skapi_extract: extractContent } : {};
     const userMessage = buildIndexingUserMessage(
       attachment,
-      placeholder ? { inlineContentPlaceholder: placeholder } : void 0
+      parsedContent ? { inlineContent: parsedContent } : placeholder ? { inlineContentPlaceholder: placeholder } : void 0
     );
     const systemPrompt = buildIndexingSystemPrompt({
       service,
@@ -1221,6 +1299,7 @@ ${options.inlineContentPlaceholder}
           this.enqueueTypewrite(aiIdx, answer, lid);
         }
       }
+      this._removeStrayPendingAssistants();
       this.promoteNextQueuedToRunning();
       this.updateHistoryCache();
       this.host.notify();
@@ -1263,6 +1342,7 @@ ${options.inlineContentPlaceholder}
           if (thPos2 !== -1) this.state.messages.splice(thPos2, 1);
         }
         if (serverId) this.cancelledServerIds.delete(serverId);
+        this._removeStrayPendingAssistants();
         this.promoteNextQueuedToRunning();
         this.updateHistoryCache();
         this.host.notify();
@@ -1276,6 +1356,7 @@ ${options.inlineContentPlaceholder}
         return;
       }
       this.insertAtTarget({ role: "assistant", content: getErrorMessage(err), isError: true }, targetIdx);
+      this._removeStrayPendingAssistants();
       this.promoteNextQueuedToRunning();
       this.updateHistoryCache();
       this.host.notify();
@@ -1437,16 +1518,48 @@ ${options.inlineContentPlaceholder}
       if (pendingIdx === -1) return Promise.resolve();
       if (latest.isError || !latest.content) {
         this.state.messages[pendingIdx] = { role: "assistant", content: latest.content || "", isError: !!latest.isError };
+        this._removeStrayPendingAssistants();
         this.host.notify();
         this.promoteNextQueuedToRunning();
         return Promise.resolve();
       }
       var lid = this._newLocalId();
       this.state.messages[pendingIdx] = { role: "assistant", content: "", isPending: false, _localId: lid };
+      this._removeStrayPendingAssistants();
       this.host.notify();
       this.promoteNextQueuedToRunning();
       return this.enqueueTypewrite(pendingIdx, latest.content, lid);
     }
+    // Remove any leftover non-background pending ("Thinking…") assistant bubbles.
+    // There is normally at most ONE such bubble at a time (promoteNext* refuses to
+    // add a second), so any extra is a duplicate — it appears when a concurrent
+    // history refetch re-maps the still-"running" turn into a pending placeholder
+    // (with a real _serverItemId) while the local pending bubble (no _serverItemId)
+    // is rescued and re-appended (see loadHistory rescue below). Each resolve path
+    // only replaces the FIRST pending bubble, so without this a stray "Thinking…"
+    // survives next to the reply/error. MUST run AFTER the resolved bubble has been
+    // made non-pending and BEFORE promoteNext*() (so a freshly-promoted Thinking,
+    // which is added only once no pending assistant remains, is preserved).
+    _removeStrayPendingAssistants() {
+      for (var k = this.state.messages.length - 1; k >= 0; k--) {
+        var m = this.state.messages[k];
+        if (m.isPending && m.role === "assistant" && !m.isBackgroundTask) this.state.messages.splice(k, 1);
+      }
+    }
+    // Drop the pending flags on the resolved turn's USER bubble (preserving its
+    // content + background-task marker). Needed because a bg "Indexing:" turn's user
+    // bubble carries isPendingInProcess; leaving it set keeps the bubble visually
+    // stuck and keeps its bgTaskQueue entry alive forever.
+    _clearPendingUserBubble(itemId) {
+      var uIdx = this.state.messages.findIndex(function(m) {
+        return m.role === "user" && m._serverItemId === itemId && (m.isPendingInProcess || m.isPendingQueued || m.isSendingToServer);
+      });
+      if (uIdx === -1) return;
+      var u = this.state.messages[uIdx];
+      var cleaned = { role: "user", content: u.content, _serverItemId: itemId };
+      if (u.isBackgroundTask) cleaned.isBackgroundTask = true;
+      this.state.messages[uIdx] = cleaned;
+    }
     // If an immediate-send request for the current cache key is still in flight
     // (e.g. the view unmounted then remounted mid-request), show the sending
     // state, await it, then render the reply from the cache. Skipped when the
@@ -1485,6 +1598,7 @@ ${options.inlineContentPlaceholder}
         return m.isPending && m._serverItemId === itemId;
       });
       if (idx !== -1) {
+        this._clearPendingUserBubble(itemId);
         if (isErr) {
           this.state.messages[idx] = { role: "assistant", content: answer, isError: true, _serverItemId: itemId };
           this.host.notify();
@@ -1634,12 +1748,16 @@ ${options.inlineContentPlaceholder}
           self.state.messages.forEach(function(m) {
             if (m.isCancelled && m._serverItemId) locallyCancelled[m._serverItemId] = 1;
           });
+          var mappedHasPendingAssistant = mapped.some(function(m) {
+            return m.isPending && m.role === "assistant" && !m.isBackgroundTask;
+          });
           var rescued = [];
           for (var ri = 0; ri < self.state.messages.length; ri++) {
             var mm = self.state.messages[ri];
             if (mm.isBackgroundTask) continue;
             if (mm._serverItemId && serverIds[mm._serverItemId]) continue;
             if (!mm._serverItemId) {
+              if (mappedHasPendingAssistant) continue;
               if (mm.isSendingToServer || mm.isPendingQueued || mm.isPendingInProcess || mm.isPending) rescued.push(mm);
               else if (self.state.sending && mm.role === "user") {
                 var next = self.state.messages[ri + 1];
@@ -1797,44 +1915,49 @@ ${options.inlineContentPlaceholder}
               att.storagePath = member.storagePath;
             }
             var mime = member.file.type || self.host.getMimeType(member.file.name);
-            return notifyAgentSaveAttachment({
-              platform: id.platform,
-              model: id.model,
-              service: id.serviceId,
-              owner: id.owner,
-              userId: id.userId || id.serviceId,
-              serviceName: id.serviceName,
-              serviceDescription: id.serviceDescription,
-              attachment: {
-                name: member.file.name,
-                storagePath: member.storagePath,
-                mime: mime || void 0,
-                size: member.file.size,
-                url
-              }
-            }).then(function(ack) {
-              if (ack && typeof ack.id === "string") {
-                self.bgTaskQueue.push({
-                  serviceId: id.serviceId,
-                  platform: id.platform,
-                  id: ack.id,
-                  filename: member.file.name,
+            return Promise.resolve(
+              parseAttachmentContent(member.file, member.file.name, mime || void 0)
+            ).then(function(parsedContent) {
+              return notifyAgentSaveAttachment({
+                platform: id.platform,
+                model: id.model,
+                service: id.serviceId,
+                owner: id.owner,
+                userId: id.userId || id.serviceId,
+                serviceName: id.serviceName,
+                serviceDescription: id.serviceDescription,
+                attachment: {
+                  name: member.file.name,
                   storagePath: member.storagePath,
-                  isReindex: hadExists,
                   mime: mime || void 0,
                   size: member.file.size,
-                  status: ack.status === "running" ? "running" : "pending",
-                  poll: ack.poll
-                });
-                self.drainBgTaskQueue();
-              }
-            }, function(e) {
-              console.error("[chat-engine] indexing request failed", e);
-              anyIndexFailed = true;
-              if (!att.errorCode && !att.errorDetail) {
-                att.errorCode = e && (e.code || e.body && e.body.code) || "";
-                att.errorDetail = e && (e.message || e.body && e.body.message) || (typeof e === "string" ? e : "");
-              }
+                  url
+                },
+                parsedContent: parsedContent || void 0
+              }).then(function(ack) {
+                if (ack && typeof ack.id === "string") {
+                  self.bgTaskQueue.push({
+                    serviceId: id.serviceId,
+                    platform: id.platform,
+                    id: ack.id,
+                    filename: member.file.name,
+                    storagePath: member.storagePath,
+                    isReindex: hadExists,
+                    mime: mime || void 0,
+                    size: member.file.size,
+                    status: ack.status === "running" ? "running" : "pending",
+                    poll: ack.poll
+                  });
+                  self.drainBgTaskQueue();
+                }
+              }, function(e) {
+                console.error("[chat-engine] indexing request failed", e);
+                anyIndexFailed = true;
+                if (!att.errorCode && !att.errorDetail) {
+                  att.errorCode = e && (e.code || e.body && e.body.code) || "";
+                  att.errorDetail = e && (e.message || e.body && e.body.message) || (typeof e === "string" ? e : "");
+                }
+              });
             });
           });
         });
@@ -1918,6 +2041,7 @@ ${options.inlineContentPlaceholder}
   (function() {
     var MCP_PROD = "https://mcp.broadwayinc.computer";
     var MCP_DEV = "https://mcp-dev.broadwayinc.computer";
+    var BQ_VERSION = "1.4.0" ;
     var ATTACHMENT_URL_EXPIRES_SECONDS = 600;
     var GOOGLE_AUTH_URL = "https://accounts.google.com/o/oauth2/v2/auth";
     var GOOGLE_TOKEN_URL = "https://oauth2.googleapis.com/token";
@@ -2139,7 +2263,7 @@ ${options.inlineContentPlaceholder}
         if (typeof S.skapi.getConnectionInfo === "function") return S.skapi.getConnectionInfo();
         return S.skapi.connection || null;
       }).then(function(conn) {
-        console.log("[bunnyquery] loadServiceInfo", conn);
+        if (S.opts && S.opts.dev) console.log("[bunnyquery] loadServiceInfo", conn);
         if (conn) {
           S.serviceId = conn.service || S.serviceId;
           S.owner = conn.owner || S.owner;
@@ -4961,8 +5085,10 @@ ${options.inlineContentPlaceholder}
         googleClientSecretName: "ggl",
         signupConfirmationUrl: null,
         // defaults to current host page
-        hostDomain: null
+        hostDomain: null,
         // db-CDN host; null → skapi.app (dev) / skapi.com (prod)
+        attachmentParsers: null
+        // client-side attachment parsers, e.g. [createHwpParser()]
       }, opts || {});
       S.mountEl = mountEl;
       clear(mountEl);
@@ -4970,6 +5096,7 @@ ${options.inlineContentPlaceholder}
       mountEl.appendChild(S.root);
       applyTheme(loadTheme());
       S.booted = true;
+      console.log("[bunnyquery] v" + BQ_VERSION);
       configureChatEngine({
         clientSecretRequest: function(o) {
           return S.skapi.clientSecretRequest(o);
@@ -4978,7 +5105,9 @@ ${options.inlineContentPlaceholder}
           return S.skapi.clientSecretRequestHistory(p, f);
         },
         mcpBaseUrl: mcpBaseUrl(),
-        poll: 0
+        poll: 0,
+        // Client-side attachment parsers (e.g. an .hwp parser) passed via init opts.
+        attachmentParsers: S.opts.attachmentParsers || void 0
       });
       if (!S._resizeBound && typeof window !== "undefined" && window.addEventListener) {
         S._resizeBound = true;
@@ -4991,12 +5120,16 @@ ${options.inlineContentPlaceholder}
     }
     var PUBLIC = {
       init,
+      // Register a client-side attachment parser (e.g. createHwpParser()) so the
+      // widget parses matching uploads in-browser and sends the text for indexing.
+      // Can be called before or after init(); also settable via init opts.attachmentParsers.
+      registerAttachmentParser,
       setTheme: function(t) {
         applyTheme(t);
       },
       toggleTheme,
       logout,
-      version: "0.1.0",
+      version: BQ_VERSION,
       _state: S
       // exposed for later-phase modules / debugging
     };