@aibranch/llm-meta-widget 0.12.0 → 0.12.1

package/README.md

@@ -61,7 +61,7 @@ Option 3 if it does not.
 
 ```ruby
 # Gemfile
-gem "llm_meta_widget", "~> 0.12.0"
+gem "llm_meta_widget", "~> 0.12.1"
 ```
 
 ```bash

package/app/assets/javascripts/llm_meta_widget/llm-meta-widget.js

@@ -589,17 +589,29 @@ function parseSseFrame(raw) {
 var STATIC_PRIMITIVES_META = "io.modelcontextprotocol/static-primitives";
 var PAGE_CARD_MEDIA_TYPE = "application/mcp-static-primitives+json";
 var RESOURCE_SHARE_OF_WINDOW = 0.0625;
+var RESOURCE_BYTES_PER_TOKEN = 4;
 function resourceBudgetBytes(window2, { floor = 8e3, cap = 64e3 } = {}) {
   if (!window2 || !Number.isFinite(window2)) return floor;
-  const share = Math.round(window2 * RESOURCE_SHARE_OF_WINDOW * CHARS_PER_TOKEN);
+  const share = Math.round(window2 * RESOURCE_SHARE_OF_WINDOW * RESOURCE_BYTES_PER_TOKEN);
   return Math.min(cap, Math.max(floor, share));
 }
-var CHARS_PER_TOKEN = 4;
+var PROSE_CHARS_PER_TOKEN = 3.5;
+var DENSE_CHARS_PER_TOKEN = 1.6;
+var CJK_CHARS_PER_TOKEN = 1;
 var MESSAGE_OVERHEAD_TOKENS = 4;
+var CJK_PATTERN = /[\u3000-\u30ff\u3400-\u4dbf\u4e00-\u9fff\uac00-\ud7af\uf900-\ufaff\uff00-\uffef]/g;
+var PROSE_PATTERN = /[A-Za-z \n\t]/g;
+function estimateTextTokens(text) {
+  const str = typeof text === "string" ? text : String(text ?? "");
+  const cjk = (str.match(CJK_PATTERN) || []).length;
+  const prose = (str.match(PROSE_PATTERN) || []).length;
+  const dense = str.length - cjk - prose;
+  return Math.ceil(cjk / CJK_CHARS_PER_TOKEN + prose / PROSE_CHARS_PER_TOKEN + dense / DENSE_CHARS_PER_TOKEN);
+}
 function estimateTokens(messages) {
   return (messages || []).reduce((sum, m) => {
     const content = typeof m?.content === "string" ? m.content : JSON.stringify(m?.content ?? "");
-    return sum + Math.ceil(content.length / CHARS_PER_TOKEN) + MESSAGE_OVERHEAD_TOKENS;
+    return sum + estimateTextTokens(content) + MESSAGE_OVERHEAD_TOKENS;
   }, 0);
 }
 function estimateToolsTokens(tools) {
@@ -608,7 +620,7 @@ function estimateToolsTokens(tools) {
     description: t?.description,
     schema: t?.input_schema || t?.inputSchema
   })).join("");
-  return Math.ceil(text.length / CHARS_PER_TOKEN);
+  return estimateTextTokens(text);
 }
 function evictOldToolResults({ messages, window: window2, reserve = 0, dropped = [] }) {
   if (!window2 || !Number.isFinite(window2)) return { messages, dropped };
@@ -3940,19 +3952,12 @@ function boot(cfg) {
   var toggleBtn = document.getElementById("llm-meta-widget-toggle");
   var historyEl = root.querySelector(".lmw-messages");
   var SCROLL_PIN_SLACK = 40;
-  var followingOutput = true;
   function atBottom() {
     return historyEl.scrollHeight - historyEl.scrollTop - historyEl.clientHeight <= SCROLL_PIN_SLACK;
   }
   function pinToBottom() {
     historyEl.scrollTop = historyEl.scrollHeight;
   }
-  function pinIfFollowing() {
-    if (followingOutput) pinToBottom();
-  }
-  historyEl.addEventListener("scroll", function() {
-    followingOutput = atBottom();
-  });
   var formEl = root.querySelector(".lmw-form");
   var inputEl = root.querySelector(".lmw-input");
   var clearBtn = root.querySelector(".lmw-clear");
@@ -4505,6 +4510,7 @@ function boot(cfg) {
   }
   var pendingTurnLabel = null;
   function appendTurn(role, text, turnLabel) {
+    var following = atBottom();
     var welcome = historyEl.querySelector(".lmw-welcome");
     if (welcome) welcome.remove();
     var div = document.createElement("div");
@@ -4531,7 +4537,7 @@ function boot(cfg) {
     div.appendChild(document.createTextNode(" "));
     div.appendChild(body);
     historyEl.appendChild(div);
-    pinIfFollowing();
+    if (role === "user" || following) pinToBottom();
     body.roleLabel = label;
     return body;
   }
@@ -4581,6 +4587,7 @@ function boot(cfg) {
     return liveChips;
   }
   function announceToolCall(toolCall) {
+    var following = atBottom();
     var row = chipRow();
     if (!row) return;
     var chip = document.createElement("span");
@@ -4589,7 +4596,7 @@ function boot(cfg) {
     chip.dataset.tool = toolCall.name;
     row.appendChild(chip);
     pendingChips.push(chip);
-    pinIfFollowing();
+    if (following) pinToBottom();
   }
   function resolveToolCall(outcome) {
     var idx = pendingChips.findIndex(function(c) {
@@ -4605,6 +4612,7 @@ function boot(cfg) {
   var currentThinkingBody = null;
   var activeAssistantBody = null;
   function ensureThinkingBlock() {
+    var following = atBottom();
     if (currentThinkingBody) return currentThinkingBody;
     var details = document.createElement("details");
     details.className = "message-thinking";
@@ -4629,7 +4637,7 @@ function boot(cfg) {
     } else {
       historyEl.appendChild(details);
     }
-    pinIfFollowing();
+    if (following) pinToBottom();
     currentThinkingBlock = details;
     currentThinkingBody = body;
     return body;
@@ -4746,7 +4754,6 @@ function boot(cfg) {
     var userText = inputEl.value.trim();
     if (!userText) return;
     inputEl.value = "";
-    followingOutput = true;
     appendTurn("user", userText, pendingTurnLabel);
     pendingTurnLabel = null;
     if (currentAbort) {
@@ -4809,19 +4816,21 @@ function boot(cfg) {
           collapseThinkingBlock();
         },
         onThinkingDelta: function(delta) {
+          var following = atBottom();
           var body = ensureThinkingBlock();
           body.appendChild(document.createTextNode(delta));
           body.scrollTop = body.scrollHeight;
-          pinIfFollowing();
+          if (following) pinToBottom();
         },
         onTextDelta: function(delta) {
+          var following = atBottom();
           markDone(assistantBody.roleLabel);
           collapseThinkingBlock();
           assistantMarkdown += delta;
           renderMarkdownInto(assistantBody, assistantMarkdown);
           liveTurn.content = assistantMarkdown;
           persistSoon();
-          pinIfFollowing();
+          if (following) pinToBottom();
         }
       });
       liveTurn.content = result.content;

package/app/assets/javascripts/llm_meta_widget/orchestrator.js

@@ -937,23 +937,53 @@ export const PAGE_CARD_MEDIA_TYPE = "application/mcp-static-primitives+json"
 // is already generous and a 1M-token model does not need 250 KB of it.
 export const RESOURCE_SHARE_OF_WINDOW = 0.0625
 
+// Bytes per token for SIZING that budget — not the estimator above, which
+// measures real text. Kept at four so the budget stays exactly what it was
+// (8 KB on a 32k model): how many tokens those bytes become depends on the
+// resource, and re-sizing budgets is not this constant's job.
+export const RESOURCE_BYTES_PER_TOKEN = 4
+
 export function resourceBudgetBytes(window, { floor = 8000, cap = 64_000 } = {}) {
   if (!window || !Number.isFinite(window)) return floor
-  const share = Math.round(window * RESOURCE_SHARE_OF_WINDOW * CHARS_PER_TOKEN)
+  const share = Math.round(window * RESOURCE_SHARE_OF_WINDOW * RESOURCE_BYTES_PER_TOKEN)
   return Math.min(cap, Math.max(floor, share))
 }
 
-// A rough token count, the same shape the hub's own estimator uses: characters
-// over four, plus a fixed cost per message. Deliberately approximate — it is
-// used to decide "drop the oldest tool result", never to fill the window
-// exactly, and it errs high so the decision is made early rather than late.
-export const CHARS_PER_TOKEN = 4
+// A rough token count, the same three classes the hub's estimator uses.
+//
+// One ratio cannot describe both prose and a tool result. Letters and spaces
+// tokenize at roughly 3.5 characters each; digits, punctuation and symbols go
+// much denser, and a JSON tool result is mostly those.
+//
+// Measured against a real refusal (2026-10-17): a 289,101-character request
+// the provider counted as 135,291 tokens was 33% letters, 16% digits and 45%
+// punctuation. At a flat four characters per token that is 72,275 — 53% of the
+// truth — so nothing was evicted and the provider refused the turn instead.
+// These classes put it at 106%: high, which is the safe direction here, since
+// underestimating means the turn dies while overestimating only gives up an
+// old tool result slightly early.
+export const PROSE_CHARS_PER_TOKEN = 3.5
+export const DENSE_CHARS_PER_TOKEN = 1.6
+export const CJK_CHARS_PER_TOKEN = 1
 export const MESSAGE_OVERHEAD_TOKENS = 4
 
+const CJK_PATTERN = /[\u3000-\u30ff\u3400-\u4dbf\u4e00-\u9fff\uac00-\ud7af\uf900-\ufaff\uff00-\uffef]/g
+const PROSE_PATTERN = /[A-Za-z \n\t]/g
+
+export function estimateTextTokens(text) {
+  const str = typeof text === "string" ? text : String(text ?? "")
+  const cjk = (str.match(CJK_PATTERN) || []).length
+  const prose = (str.match(PROSE_PATTERN) || []).length
+  const dense = str.length - cjk - prose
+  return Math.ceil(cjk / CJK_CHARS_PER_TOKEN +
+                   prose / PROSE_CHARS_PER_TOKEN +
+                   dense / DENSE_CHARS_PER_TOKEN)
+}
+
 export function estimateTokens(messages) {
   return (messages || []).reduce((sum, m) => {
     const content = typeof m?.content === "string" ? m.content : JSON.stringify(m?.content ?? "")
-    return sum + Math.ceil(content.length / CHARS_PER_TOKEN) + MESSAGE_OVERHEAD_TOKENS
+    return sum + estimateTextTokens(content) + MESSAGE_OVERHEAD_TOKENS
   }, 0)
 }
 
@@ -969,7 +999,8 @@ export function estimateToolsTokens(tools) {
   const text = (tools || []).map((t) => JSON.stringify({
     name: t?.name, description: t?.description, schema: t?.input_schema || t?.inputSchema
   })).join("")
-  return Math.ceil(text.length / CHARS_PER_TOKEN)
+  // Counted with the same classes: a schema is JSON, which is the dense case.
+  return estimateTextTokens(text)
 }
 
 // Makes room for the next round by dropping the OLDEST tool results, which is

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@aibranch/llm-meta-widget",
-  "version": "0.12.0",
+  "version": "0.12.1",
   "//version": "Must stay in step with lib/llm_meta_widget/version.rb. Two independently versioned copies of the same client is the drift docs/custom-element-distribution.md warns about: bump both, release both.",
   "description": "Embeddable browser chat widget: a custom element that discovers tools at page, origin and hub scope and dispatches each tool call to the right one. Two lines of HTML on any host, Rails or not.",
   "keywords": [