thincoder 0.12.46 → 0.12.47

package/CHANGELOG.md

@@ -2,6 +2,12 @@
 
 本文件记录 ThinCoder CLI 的发布历史。格式基于 [Keep a Changelog](https://keepachangelog.com/zh-CN/1.0.0/)，版本遵循[语义化版本](https://semver.org/lang/zh-CN/)。
 
+## [0.12.47] — 2026-08-28
+
+### Added
+
+- **GLM-5.3-Flash 模型支持**：智谱 2026-08-26 发布的原生多模态 Flash 档位模型——1M 上下文 + 128K 输出 + 文本/图片输入，`/model glm:glm-5.3-flash` 即可选用（不改默认预设）
+
 ## [0.12.46] — 2026-08-27
 
 ### Fixed

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "thincoder",
-  "version": "0.12.46",
+  "version": "0.12.47",
   "description": "Thin coding agent - zero dependencies, no build step, Node.js native. Sharp code, zero bloat.",
   "keywords": [
     "ai",
@@ -32,7 +32,7 @@
   },
   "scripts": {
     "test": "node --test \"test/*.mjs\"",
-    "prepublishOnly": "node --test \"test/*.mjs\"",
+    "prepublishOnly": "npm run lint && node --test \"test/*.mjs\"",
     "lint": "eslint src"
   },
   "author": "liwei <liwei@51marine.com> (上海新舶)",

package/src/config.mjs

@@ -108,6 +108,7 @@ const MODEL_SPECS = [
   // GLM-5.3: thinking always-on (no "disabled"); effort converges to low/high/max — NOT the
   //          7-level glm-5.2 enum (verified vs docs.bigmodel.cn GLM-5.3 page, 2026-08)
   ["glm-5.3",           { context: 1_000_000, maxOutput: 128_000, thinking: true,  cacheMode: "auto", thinkApi: "type", reasoningEcho: "optional", reasoningEffortEnum: ["low", "high", "max"], tempRange: [0, 1], noUsageStream: true }],
+  ["glm-5.3-flash",     { context: 1_000_000, maxOutput: 128_000, thinking: true, multimodal: true, cacheMode: "auto", thinkApi: "type", reasoningEcho: "optional", reasoningEffortEnum: ["low", "high", "max"], tempRange: [0, 1], noUsageStream: true }],
   ["glm-5.2",           { context: 1_000_000, maxOutput: 128_000, thinking: true,  cacheMode: "auto", thinkApi: "type", reasoningEcho: "optional", reasoningEffortEnum: ["max", "xhigh", "high", "medium", "low", "minimal", "none"], tempRange: [0, 1], noUsageStream: true }],
   ["glm-5",             { context: 1_000_000, maxOutput: 128_000, thinking: true,  cacheMode: "auto", thinkApi: "type", reasoningEcho: "optional", reasoningEffortEnum: ["max", "xhigh", "high", "medium", "low", "minimal", "none"], tempRange: [0, 1], noUsageStream: true }],
   ["glm-4",             { context: 128_000,   maxOutput: 32_000,  thinking: true,  cacheMode: "auto", thinkApi: "type", reasoningEcho: "optional", tempRange: [0, 1], noUsageStream: true }],

package/src/tools/read_image.md

@@ -1,8 +1,8 @@
-Read an image file and return it as multimodal content visible to the model. Use this to view screenshots, UI mockups, diagrams, or any visual content. The model only sees images through this tool — it cannot "see" files directly. Supports png, jpg, gif, webp. The image is base64-encoded and included in the response. Large images (>20MB) are rejected.
+Read an image file and return it as multimodal content visible to the model. Use this to view screenshots, UI mockups, diagrams, or any visual content. The model only sees images through this tool — it cannot "see" files directly. Supports png, jpg, gif, webp. The image is base64-encoded and included in the response. Large images (>15MB) are rejected.
 
 Parameters:
 - path (required): Path to image file (relative to cwd or absolute). Supports png, jpg, gif, webp; svg is returned as text source.
 
 Notes:
 - Raster formats only (png/jpg/gif/webp): no mainstream vision API (Kimi, Anthropic, OpenAI, Gemini) accepts svg or bmp, and an unsupported image part in history makes every subsequent request fail with 400. svg files are returned as text source instead (readable by any model); bmp is rejected — convert to PNG first.
-- This tool only works with models that support vision/image input (Kimi K3, Qwen3.7, MiniMax M3). Pure text models (DeepSeek V4, GLM-5) will receive an error — except svg, which needs no vision support since it is read as text.
+- This tool only works with models that support vision/image input (Kimi K3, Qwen3.8, MiniMax M3, GLM-5.3-Flash). Pure text models (DeepSeek V4, GLM-5) will receive an error — except svg, which needs no vision support since it is read as text.